From 5a0b8cb46624cc17fda676d6ae44fb72504f0ad9 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 13 Mar 2018 14:23:28 -0700 Subject: iio: cros_ec: Move cros_ec_sensors_core.h in /include Similar to other common iio frameworks, move cros_ec_sensors_core.h from drivers/iio/common/cros_ec_sensors/ to include/linux/iio/common. Signed-off-by: Gwendal Grignou Signed-off-by: Jonathan Cameron --- include/linux/iio/common/cros_ec_sensors_core.h | 180 ++++++++++++++++++++++++ 1 file changed, 180 insertions(+) create mode 100644 include/linux/iio/common/cros_ec_sensors_core.h (limited to 'include/linux') diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h new file mode 100644 index 000000000000..ce16445411ac --- /dev/null +++ b/include/linux/iio/common/cros_ec_sensors_core.h @@ -0,0 +1,180 @@ +/* + * ChromeOS EC sensor hub + * + * Copyright (C) 2016 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __CROS_EC_SENSORS_CORE_H +#define __CROS_EC_SENSORS_CORE_H + +#include +#include +#include + +enum { + CROS_EC_SENSOR_X, + CROS_EC_SENSOR_Y, + CROS_EC_SENSOR_Z, + CROS_EC_SENSOR_MAX_AXIS, +}; + +/* EC returns sensor values using signed 16 bit registers */ +#define CROS_EC_SENSOR_BITS 16 + +/* + * 4 16 bit channels are allowed. + * Good enough for current sensors, they use up to 3 16 bit vectors. + */ +#define CROS_EC_SAMPLE_SIZE (sizeof(s64) * 2) + +/* Minimum sampling period to use when device is suspending */ +#define CROS_EC_MIN_SUSPEND_SAMPLING_FREQUENCY 1000 /* 1 second */ + +/** + * struct cros_ec_sensors_core_state - state data for EC sensors IIO driver + * @ec: cros EC device structure + * @cmd_lock: lock used to prevent simultaneous access to the + * commands. + * @msg: cros EC command structure + * @param: motion sensor parameters structure + * @resp: motion sensor response structure + * @type: type of motion sensor + * @loc: location where the motion sensor is placed + * @calib: calibration parameters. Note that trigger + * captured data will always provide the calibrated + * data + * @samples: static array to hold data from a single capture. + * For each channel we need 2 bytes, except for + * the timestamp. The timestamp is always last and + * is always 8-byte aligned. + * @read_ec_sensors_data: function used for accessing sensors values + * @cuur_sampl_freq: current sampling period + */ +struct cros_ec_sensors_core_state { + struct cros_ec_device *ec; + struct mutex cmd_lock; + + struct cros_ec_command *msg; + struct ec_params_motion_sense param; + struct ec_response_motion_sense *resp; + + enum motionsensor_type type; + enum motionsensor_location loc; + + s16 calib[CROS_EC_SENSOR_MAX_AXIS]; + + u8 samples[CROS_EC_SAMPLE_SIZE]; + + int (*read_ec_sensors_data)(struct iio_dev *indio_dev, + unsigned long scan_mask, s16 *data); + + int curr_sampl_freq; +}; + +/** + * cros_ec_sensors_read_lpc() - retrieve data from EC shared memory + * @indio_dev: pointer to IIO device + * @scan_mask: bitmap of the sensor indices to scan + * @data: location to store data + * + * This is the safe function for reading the EC data. It guarantees that the + * data sampled was not modified by the EC while being read. + * + * Return: 0 on success, -errno on failure. + */ +int cros_ec_sensors_read_lpc(struct iio_dev *indio_dev, unsigned long scan_mask, + s16 *data); + +/** + * cros_ec_sensors_read_cmd() - retrieve data using the EC command protocol + * @indio_dev: pointer to IIO device + * @scan_mask: bitmap of the sensor indices to scan + * @data: location to store data + * + * Return: 0 on success, -errno on failure. + */ +int cros_ec_sensors_read_cmd(struct iio_dev *indio_dev, unsigned long scan_mask, + s16 *data); + +struct platform_device; +/** + * cros_ec_sensors_core_init() - basic initialization of the core structure + * @pdev: platform device created for the sensors + * @indio_dev: iio device structure of the device + * @physical_device: true if the device refers to a physical device + * + * Return: 0 on success, -errno on failure. + */ +int cros_ec_sensors_core_init(struct platform_device *pdev, + struct iio_dev *indio_dev, bool physical_device); + +/** + * cros_ec_sensors_capture() - the trigger handler function + * @irq: the interrupt number. + * @p: a pointer to the poll function. + * + * On a trigger event occurring, if the pollfunc is attached then this + * handler is called as a threaded interrupt (and hence may sleep). It + * is responsible for grabbing data from the device and pushing it into + * the associated buffer. + * + * Return: IRQ_HANDLED + */ +irqreturn_t cros_ec_sensors_capture(int irq, void *p); + +/** + * cros_ec_motion_send_host_cmd() - send motion sense host command + * @st: pointer to state information for device + * @opt_length: optional length to reduce the response size, useful on the data + * path. Otherwise, the maximal allowed response size is used + * + * When called, the sub-command is assumed to be set in param->cmd. + * + * Return: 0 on success, -errno on failure. + */ +int cros_ec_motion_send_host_cmd(struct cros_ec_sensors_core_state *st, + u16 opt_length); + +/** + * cros_ec_sensors_core_read() - function to request a value from the sensor + * @st: pointer to state information for device + * @chan: channel specification structure table + * @val: will contain one element making up the returned value + * @val2: will contain another element making up the returned value + * @mask: specifies which values to be requested + * + * Return: the type of value returned by the device + */ +int cros_ec_sensors_core_read(struct cros_ec_sensors_core_state *st, + struct iio_chan_spec const *chan, + int *val, int *val2, long mask); + +/** + * cros_ec_sensors_core_write() - function to write a value to the sensor + * @st: pointer to state information for device + * @chan: channel specification structure table + * @val: first part of value to write + * @val2: second part of value to write + * @mask: specifies which values to write + * + * Return: the type of value returned by the device + */ +int cros_ec_sensors_core_write(struct cros_ec_sensors_core_state *st, + struct iio_chan_spec const *chan, + int val, int val2, long mask); + +extern const struct dev_pm_ops cros_ec_sensors_pm_ops; + +/* List of extended channel specification for all sensors */ +extern const struct iio_chan_spec_ext_info cros_ec_sensors_ext_info[]; + +#endif /* __CROS_EC_SENSORS_CORE_H */ -- cgit v1.2.3 From 192af06a287bbfcae0de8fa456dca15767ecd056 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Mon, 12 Mar 2018 17:48:15 +0200 Subject: iio: adc: ad7780: remove IIO_CHAN_INFO_SAMP_FREQ support The `ad7780` driver does not implement setting/getting the sampling frequency. For the ad7780/ad7781 devices, the control is done via an external pin, and the ad7170/ad7171 devices have a fixed sampling rate (so, no control). For these devices, and similar other that may be added later on, a AD_SD_CHANNEL_NO_SAMPLE_FREQ() macro has been added, which doesn't set the IIO_CHAN_INFO_SAMP_FREQ flag. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/ad_sigma_delta.h | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 1fc7abd28b0b..730ead1a46df 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -127,7 +127,7 @@ void ad_sd_cleanup_buffer_and_trigger(struct iio_dev *indio_dev); int ad_sd_validate_trigger(struct iio_dev *indio_dev, struct iio_trigger *trig); #define __AD_SD_CHANNEL(_si, _channel1, _channel2, _address, _bits, \ - _storagebits, _shift, _extend_name, _type) \ + _storagebits, _shift, _extend_name, _type, _mask_all) \ { \ .type = (_type), \ .differential = (_channel2 == -1 ? 0 : 1), \ @@ -139,7 +139,7 @@ int ad_sd_validate_trigger(struct iio_dev *indio_dev, struct iio_trigger *trig); .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ BIT(IIO_CHAN_INFO_OFFSET), \ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ - .info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SAMP_FREQ), \ + .info_mask_shared_by_all = _mask_all, \ .scan_index = (_si), \ .scan_type = { \ .sign = 'u', \ @@ -153,25 +153,35 @@ int ad_sd_validate_trigger(struct iio_dev *indio_dev, struct iio_trigger *trig); #define AD_SD_DIFF_CHANNEL(_si, _channel1, _channel2, _address, _bits, \ _storagebits, _shift) \ __AD_SD_CHANNEL(_si, _channel1, _channel2, _address, _bits, \ - _storagebits, _shift, NULL, IIO_VOLTAGE) + _storagebits, _shift, NULL, IIO_VOLTAGE, \ + BIT(IIO_CHAN_INFO_SAMP_FREQ)) #define AD_SD_SHORTED_CHANNEL(_si, _channel, _address, _bits, \ _storagebits, _shift) \ __AD_SD_CHANNEL(_si, _channel, _channel, _address, _bits, \ - _storagebits, _shift, "shorted", IIO_VOLTAGE) + _storagebits, _shift, "shorted", IIO_VOLTAGE, \ + BIT(IIO_CHAN_INFO_SAMP_FREQ)) #define AD_SD_CHANNEL(_si, _channel, _address, _bits, \ _storagebits, _shift) \ __AD_SD_CHANNEL(_si, _channel, -1, _address, _bits, \ - _storagebits, _shift, NULL, IIO_VOLTAGE) + _storagebits, _shift, NULL, IIO_VOLTAGE, \ + BIT(IIO_CHAN_INFO_SAMP_FREQ)) + +#define AD_SD_CHANNEL_NO_SAMP_FREQ(_si, _channel, _address, _bits, \ + _storagebits, _shift) \ + __AD_SD_CHANNEL(_si, _channel, -1, _address, _bits, \ + _storagebits, _shift, NULL, IIO_VOLTAGE, 0) #define AD_SD_TEMP_CHANNEL(_si, _address, _bits, _storagebits, _shift) \ __AD_SD_CHANNEL(_si, 0, -1, _address, _bits, \ - _storagebits, _shift, NULL, IIO_TEMP) + _storagebits, _shift, NULL, IIO_TEMP, \ + BIT(IIO_CHAN_INFO_SAMP_FREQ)) #define AD_SD_SUPPLY_CHANNEL(_si, _channel, _address, _bits, _storagebits, \ _shift) \ __AD_SD_CHANNEL(_si, _channel, -1, _address, _bits, \ - _storagebits, _shift, "supply", IIO_VOLTAGE) + _storagebits, _shift, "supply", IIO_VOLTAGE, \ + BIT(IIO_CHAN_INFO_SAMP_FREQ)) #endif -- cgit v1.2.3 From 351f683b9823a3d1bffb6e2e3f381601aa0b2671 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Sat, 17 Feb 2018 20:33:13 +0100 Subject: auxdisplay: Replace licenses with SPDX identifiers Cc: Philippe Ombredanne Acked-by: Willy Tarreau Acked-by: Linus Walleij Acked-by: Robin van der Gracht Acked-by: Geert Uytterhoeven Signed-off-by: Miguel Ojeda --- include/linux/cfag12864b.h | 16 +--------------- include/linux/ks0108.h | 16 +--------------- 2 files changed, 2 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cfag12864b.h b/include/linux/cfag12864b.h index b454dfce60d9..4060004968c8 100644 --- a/include/linux/cfag12864b.h +++ b/include/linux/cfag12864b.h @@ -1,25 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Filename: cfag12864b.h * Version: 0.1.0 * Description: cfag12864b LCD driver header - * License: GPLv2 * * Author: Copyright (C) Miguel Ojeda Sandonis * Date: 2006-10-12 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ #ifndef _CFAG12864B_H_ diff --git a/include/linux/ks0108.h b/include/linux/ks0108.h index cb311798e0bc..0738389b42b6 100644 --- a/include/linux/ks0108.h +++ b/include/linux/ks0108.h @@ -1,25 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Filename: ks0108.h * Version: 0.1.0 * Description: ks0108 LCD Controller driver header - * License: GPLv2 * * Author: Copyright (C) Miguel Ojeda Sandonis * Date: 2006-10-31 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ #ifndef _KS0108_H_ -- cgit v1.2.3 From 483cbae76824e12d4894f20fab2608789532db3f Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Wed, 28 Mar 2018 02:22:07 +0000 Subject: ASoC: wm8350: remove snd_soc_codec codec is replace to component. It seems no-one is using it, Let's remove it. Signed-off-by: Kuninori Morimoto Acked-by: Charles Keepax Signed-off-by: Mark Brown --- include/linux/mfd/wm8350/audio.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8350/audio.h b/include/linux/mfd/wm8350/audio.h index bd581c6fa085..0bc41c4c0429 100644 --- a/include/linux/mfd/wm8350/audio.h +++ b/include/linux/mfd/wm8350/audio.h @@ -617,11 +617,8 @@ struct wm8350_audio_platform_data { u32 codec_current_charge:2; /* codec current @ vmid charge */ }; -struct snd_soc_codec; - struct wm8350_codec { struct platform_device *pdev; - struct snd_soc_codec *codec; struct wm8350_audio_platform_data *platform_data; }; -- cgit v1.2.3 From ed645cccc0ebc0329916b6df039dd792d9105c9d Mon Sep 17 00:00:00 2001 From: Andrey Gusakov Date: Tue, 27 Mar 2018 17:19:49 +0300 Subject: hwmon: MC13783: Add uid and die temperature sensor inputs The uid and die temperature can be read out on the ADIN7 using input mux. Map uid and die temperature sensor to channels 16 and 17. Signed-off-by: Andrey Gusakov Acked-by: Guenter Roeck Signed-off-by: Lee Jones --- include/linux/mfd/mc13xxx.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h index 638222e43e48..54a3cd808f9e 100644 --- a/include/linux/mfd/mc13xxx.h +++ b/include/linux/mfd/mc13xxx.h @@ -243,6 +243,8 @@ struct mc13xxx_platform_data { #define MC13XXX_ADC0_LICELLCON (1 << 0) #define MC13XXX_ADC0_CHRGICON (1 << 1) #define MC13XXX_ADC0_BATICON (1 << 2) +#define MC13XXX_ADC0_ADIN7SEL_DIE (1 << 4) +#define MC13XXX_ADC0_ADIN7SEL_UID (2 << 4) #define MC13XXX_ADC0_ADREFEN (1 << 10) #define MC13XXX_ADC0_TSMOD0 (1 << 12) #define MC13XXX_ADC0_TSMOD1 (1 << 13) -- cgit v1.2.3 From ec1ba3e519c0f46523cf40b83dc71562171b7c08 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 22 Mar 2018 11:17:40 +0100 Subject: regulator: ab8500: Drop AB8540/9540 support The AB8540 was an evolved version of the AB8500, but it was never mass produced or put into products, only reference designs exist. The upstream support was never completed and it is unlikely that this will happen so drop the support for now to simplify maintenance of the AB8500. Cc: Loic Pallardy Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 157 +-------------------------------------- 1 file changed, 1 insertion(+), 156 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index d8ecefaf63ca..6d46f962685d 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -49,47 +49,7 @@ enum ab8505_regulator_id { AB8505_NUM_REGULATORS, }; -/* AB9540 regulators */ -enum ab9540_regulator_id { - AB9540_LDO_AUX1, - AB9540_LDO_AUX2, - AB9540_LDO_AUX3, - AB9540_LDO_AUX4, - AB9540_LDO_INTCORE, - AB9540_LDO_TVOUT, - AB9540_LDO_USB, - AB9540_LDO_AUDIO, - AB9540_LDO_ANAMIC1, - AB9540_LDO_ANAMIC2, - AB9540_LDO_DMIC, - AB9540_LDO_ANA, - AB9540_SYSCLKREQ_2, - AB9540_SYSCLKREQ_4, - AB9540_NUM_REGULATORS, -}; - -/* AB8540 regulators */ -enum ab8540_regulator_id { - AB8540_LDO_AUX1, - AB8540_LDO_AUX2, - AB8540_LDO_AUX3, - AB8540_LDO_AUX4, - AB8540_LDO_AUX5, - AB8540_LDO_AUX6, - AB8540_LDO_INTCORE, - AB8540_LDO_TVOUT, - AB8540_LDO_AUDIO, - AB8540_LDO_ANAMIC1, - AB8540_LDO_ANAMIC2, - AB8540_LDO_DMIC, - AB8540_LDO_ANA, - AB8540_LDO_SDIO, - AB8540_SYSCLKREQ_2, - AB8540_SYSCLKREQ_4, - AB8540_NUM_REGULATORS, -}; - -/* AB8500, AB8505, and AB9540 register initialization */ +/* AB8500 and AB8505 register initialization */ struct ab8500_regulator_reg_init { int id; u8 mask; @@ -185,121 +145,6 @@ enum ab8505_regulator_reg { AB8505_NUM_REGULATOR_REGISTERS, }; -/* AB9540 registers */ -enum ab9540_regulator_reg { - AB9540_REGUREQUESTCTRL1, - AB9540_REGUREQUESTCTRL2, - AB9540_REGUREQUESTCTRL3, - AB9540_REGUREQUESTCTRL4, - AB9540_REGUSYSCLKREQ1HPVALID1, - AB9540_REGUSYSCLKREQ1HPVALID2, - AB9540_REGUHWHPREQ1VALID1, - AB9540_REGUHWHPREQ1VALID2, - AB9540_REGUHWHPREQ2VALID1, - AB9540_REGUHWHPREQ2VALID2, - AB9540_REGUSWHPREQVALID1, - AB9540_REGUSWHPREQVALID2, - AB9540_REGUSYSCLKREQVALID1, - AB9540_REGUSYSCLKREQVALID2, - AB9540_REGUVAUX4REQVALID, - AB9540_REGUMISC1, - AB9540_VAUDIOSUPPLY, - AB9540_REGUCTRL1VAMIC, - AB9540_VSMPS1REGU, - AB9540_VSMPS2REGU, - AB9540_VSMPS3REGU, /* NOTE! PRCMU register */ - AB9540_VPLLVANAREGU, - AB9540_EXTSUPPLYREGU, - AB9540_VAUX12REGU, - AB9540_VRF1VAUX3REGU, - AB9540_VSMPS1SEL1, - AB9540_VSMPS1SEL2, - AB9540_VSMPS1SEL3, - AB9540_VSMPS2SEL1, - AB9540_VSMPS2SEL2, - AB9540_VSMPS2SEL3, - AB9540_VSMPS3SEL1, /* NOTE! PRCMU register */ - AB9540_VSMPS3SEL2, /* NOTE! PRCMU register */ - AB9540_VAUX1SEL, - AB9540_VAUX2SEL, - AB9540_VRF1VAUX3SEL, - AB9540_REGUCTRL2SPARE, - AB9540_VAUX4REQCTRL, - AB9540_VAUX4REGU, - AB9540_VAUX4SEL, - AB9540_REGUCTRLDISCH, - AB9540_REGUCTRLDISCH2, - AB9540_REGUCTRLDISCH3, - AB9540_NUM_REGULATOR_REGISTERS, -}; - -/* AB8540 registers */ -enum ab8540_regulator_reg { - AB8540_REGUREQUESTCTRL1, - AB8540_REGUREQUESTCTRL2, - AB8540_REGUREQUESTCTRL3, - AB8540_REGUREQUESTCTRL4, - AB8540_REGUSYSCLKREQ1HPVALID1, - AB8540_REGUSYSCLKREQ1HPVALID2, - AB8540_REGUHWHPREQ1VALID1, - AB8540_REGUHWHPREQ1VALID2, - AB8540_REGUHWHPREQ2VALID1, - AB8540_REGUHWHPREQ2VALID2, - AB8540_REGUSWHPREQVALID1, - AB8540_REGUSWHPREQVALID2, - AB8540_REGUSYSCLKREQVALID1, - AB8540_REGUSYSCLKREQVALID2, - AB8540_REGUVAUX4REQVALID, - AB8540_REGUVAUX5REQVALID, - AB8540_REGUVAUX6REQVALID, - AB8540_REGUVCLKBREQVALID, - AB8540_REGUVRF1REQVALID, - AB8540_REGUMISC1, - AB8540_VAUDIOSUPPLY, - AB8540_REGUCTRL1VAMIC, - AB8540_VHSIC, - AB8540_VSDIO, - AB8540_VSMPS1REGU, - AB8540_VSMPS2REGU, - AB8540_VSMPS3REGU, - AB8540_VPLLVANAREGU, - AB8540_EXTSUPPLYREGU, - AB8540_VAUX12REGU, - AB8540_VRF1VAUX3REGU, - AB8540_VSMPS1SEL1, - AB8540_VSMPS1SEL2, - AB8540_VSMPS1SEL3, - AB8540_VSMPS2SEL1, - AB8540_VSMPS2SEL2, - AB8540_VSMPS2SEL3, - AB8540_VSMPS3SEL1, - AB8540_VSMPS3SEL2, - AB8540_VAUX1SEL, - AB8540_VAUX2SEL, - AB8540_VRF1VAUX3SEL, - AB8540_REGUCTRL2SPARE, - AB8540_VAUX4REQCTRL, - AB8540_VAUX4REGU, - AB8540_VAUX4SEL, - AB8540_VAUX5REQCTRL, - AB8540_VAUX5REGU, - AB8540_VAUX5SEL, - AB8540_VAUX6REQCTRL, - AB8540_VAUX6REGU, - AB8540_VAUX6SEL, - AB8540_VCLKBREQCTRL, - AB8540_VCLKBREGU, - AB8540_VCLKBSEL, - AB8540_VRF1REQCTRL, - AB8540_REGUCTRLDISCH, - AB8540_REGUCTRLDISCH2, - AB8540_REGUCTRLDISCH3, - AB8540_REGUCTRLDISCH4, - AB8540_VSIMSYSCLKCTRL, - AB8540_VANAVPLLSEL, - AB8540_NUM_REGULATOR_REGISTERS, -}; - /* AB8500 external regulators */ struct ab8500_ext_regulator_cfg { bool hwreq; /* requires hw mode or high power mode */ -- cgit v1.2.3 From 44773ba170a6f969620221a6d87d03feae5e464f Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 16 Apr 2018 10:22:01 -0700 Subject: ARM: OMAP2+: Drop unused pm-noop Looks like these functions don't do anything in the mainline kernel so we can just drop it. Note that we must now also remove ir-rx51 pdata as it relies on the dummy platform data that does not do anything. And ir-rx51 is calling a pdata callback that doesn't do anything without checking if it exists first. For configuring device specific minimal latencies, the interface to use is pm_qos_add_request(). For an example, see what was done in commit 9834ffd1ecc3 ("ASoC: omap-mcbsp: Add PM QoS support for McBSP to prevent glitches"). I've added some comments to ir-rx51 so people using it can add pm_qos support and test it. Cc: Ivaylo Dimitrov Cc: Kevin Hilman Cc: Laurent Pinchart Cc: Tomi Valkeinen Acked-by: Mauro Carvalho Chehab Signed-off-by: Tony Lindgren --- include/linux/platform_data/media/ir-rx51.h | 9 --------- 1 file changed, 9 deletions(-) delete mode 100644 include/linux/platform_data/media/ir-rx51.h (limited to 'include/linux') diff --git a/include/linux/platform_data/media/ir-rx51.h b/include/linux/platform_data/media/ir-rx51.h deleted file mode 100644 index 9d127aa648e7..000000000000 --- a/include/linux/platform_data/media/ir-rx51.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _IR_RX51_H -#define _IR_RX51_H - -struct ir_rx51_platform_data { - int(*set_max_mpu_wakeup_lat)(struct device *dev, long t); -}; - -#endif -- cgit v1.2.3 From 69c45d57bab00d5777e7686b3965b68b8ab043c7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 16 Apr 2018 14:20:26 -0400 Subject: remove rpc_rmdir() no users since 2014... Signed-off-by: Al Viro --- include/linux/sunrpc/rpc_pipe_fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index a5704daf5df9..e90b9bd99ded 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -122,8 +122,6 @@ extern struct dentry *rpc_create_cache_dir(struct dentry *, struct cache_detail *); extern void rpc_remove_cache_dir(struct dentry *); -extern int rpc_rmdir(struct dentry *dentry); - struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags); void rpc_destroy_pipe_data(struct rpc_pipe *pipe); extern struct dentry *rpc_mkpipe_dentry(struct dentry *, const char *, void *, -- cgit v1.2.3 From ad56b738c5dd223a2f66685830f82194025a6138 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 21 Mar 2018 21:22:47 +0200 Subject: docs/vm: rename documentation files to .rst Signed-off-by: Mike Rapoport Signed-off-by: Jonathan Corbet --- include/linux/hmm.h | 2 +- include/linux/memremap.h | 4 ++-- include/linux/mmu_notifier.h | 2 +- include/linux/sched/mm.h | 4 ++-- include/linux/swap.h | 2 +- 5 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 325017ad9311..77be87c095f2 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -16,7 +16,7 @@ /* * Heterogeneous Memory Management (HMM) * - * See Documentation/vm/hmm.txt for reasons and overview of what HMM is and it + * See Documentation/vm/hmm.rst for reasons and overview of what HMM is and it * is for. Here we focus on the HMM API description, with some explanation of * the underlying implementation. * diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 7b4899c06f49..74ea5e2310a8 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -45,7 +45,7 @@ struct vmem_altmap { * must be treated as an opaque object, rather than a "normal" struct page. * * A more complete discussion of unaddressable memory may be found in - * include/linux/hmm.h and Documentation/vm/hmm.txt. + * include/linux/hmm.h and Documentation/vm/hmm.rst. * * MEMORY_DEVICE_PUBLIC: * Device memory that is cache coherent from device and CPU point of view. This @@ -67,7 +67,7 @@ enum memory_type { * page_free() * * Additional notes about MEMORY_DEVICE_PRIVATE may be found in - * include/linux/hmm.h and Documentation/vm/hmm.txt. There is also a brief + * include/linux/hmm.h and Documentation/vm/hmm.rst. There is also a brief * explanation in include/linux/memory_hotplug.h. * * The page_fault() callback must migrate page back, from device memory to diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 2d07a1ed5a31..392e6af82701 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -174,7 +174,7 @@ struct mmu_notifier_ops { * invalidate_range_start()/end() notifiers, as * invalidate_range() alread catches the points in time when an * external TLB range needs to be flushed. For more in depth - * discussion on this see Documentation/vm/mmu_notifier.txt + * discussion on this see Documentation/vm/mmu_notifier.rst * * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 1149533aa2fa..df2c7d11f496 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -28,7 +28,7 @@ extern struct mm_struct *mm_alloc(void); * * Use mmdrop() to release the reference acquired by mmgrab(). * - * See also for an in-depth explanation + * See also for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmgrab(struct mm_struct *mm) @@ -51,7 +51,7 @@ extern void mmdrop(struct mm_struct *mm); * * Use mmput() to release the reference acquired by mmget(). * - * See also for an in-depth explanation + * See also for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmget(struct mm_struct *mm) diff --git a/include/linux/swap.h b/include/linux/swap.h index 7b6a59f722a3..4003973deff4 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -53,7 +53,7 @@ static inline int current_is_kswapd(void) /* * Unaddressable device memory support. See include/linux/hmm.h and - * Documentation/vm/hmm.txt. Short description is we need struct pages for + * Documentation/vm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can * migrate part of a process memory to device memory. * -- cgit v1.2.3 From d1361840f8c519eaee9a78ffe09e4f0a1b586846 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 16 Apr 2018 10:33:35 -0700 Subject: tcp: fix SO_RCVLOWAT and RCVBUF autotuning Applications might use SO_RCVLOWAT on TCP socket hoping to receive one [E]POLLIN event only when a given amount of bytes are ready in socket receive queue. Problem is that receive autotuning is not aware of this constraint, meaning sk_rcvbuf might be too small to allow all bytes to be stored. Add a new (struct proto_ops)->set_rcvlowat method so that a protocol can override the default setsockopt(SO_RCVLOWAT) behavior. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/net.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 2248a052061d..6554d3ba4396 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -197,6 +197,7 @@ struct proto_ops { int offset, size_t size, int flags); int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, size_t size); + int (*set_rcvlowat)(struct sock *sk, int val); }; #define DECLARE_SOCKADDR(type, dst, src) \ -- cgit v1.2.3 From e59644b720aed4b9ec9d3818b483f97376fb31ed Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Sun, 1 Apr 2018 08:42:08 +0000 Subject: security: remove security_settime security_settime was a wrapper around security_settime64. There are no more users of it. Therefore it can be removed. It was removed in: commit 4eb1bca17933 ("time: Use do_settimeofday64() internally") Signed-off-by: Sargun Dhillon Signed-off-by: James Morris --- include/linux/security.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 3f5fd988ee87..5111fe8159ce 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -222,12 +222,6 @@ int security_quotactl(int cmds, int type, int id, struct super_block *sb); int security_quota_on(struct dentry *dentry); int security_syslog(int type); int security_settime64(const struct timespec64 *ts, const struct timezone *tz); -static inline int security_settime(const struct timespec *ts, const struct timezone *tz) -{ - struct timespec64 ts64 = timespec_to_timespec64(*ts); - - return security_settime64(&ts64, tz); -} int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); int security_bprm_set_creds(struct linux_binprm *bprm); int security_bprm_check(struct linux_binprm *bprm); @@ -509,14 +503,6 @@ static inline int security_settime64(const struct timespec64 *ts, return cap_settime(ts, tz); } -static inline int security_settime(const struct timespec *ts, - const struct timezone *tz) -{ - struct timespec64 ts64 = timespec_to_timespec64(*ts); - - return cap_settime(&ts64, tz); -} - static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { return __vm_enough_memory(mm, pages, cap_vm_enough_memory(mm, pages)); -- cgit v1.2.3 From 8b4aa4d8dc283a408eb14ca5e27e0a9a689c2e5a Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 5 Apr 2018 12:03:05 -0400 Subject: media: mmp-camera.h: add missing platform data Those definitions used to be part of the original patch: https://patchwork.kernel.org/patch/2815221/ But, somehow, nobody ever noticed until today. Years later, Arnd discovered that mmp-camera driver doesn't build and make it depend on BROKEN. Add the missing bits here, in order to remove BROKEN dependency. Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/media/mmp-camera.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/media/mmp-camera.h b/include/linux/platform_data/media/mmp-camera.h index 83804028115c..d2d3a443eedf 100644 --- a/include/linux/platform_data/media/mmp-camera.h +++ b/include/linux/platform_data/media/mmp-camera.h @@ -3,8 +3,27 @@ * Information for the Marvell Armada MMP camera */ +#include + +enum dphy3_algo { + DPHY3_ALGO_DEFAULT = 0, + DPHY3_ALGO_PXA910, + DPHY3_ALGO_PXA2128 +}; + struct mmp_camera_platform_data { struct platform_device *i2c_device; int sensor_power_gpio; int sensor_reset_gpio; + enum v4l2_mbus_type bus_type; + int mclk_min; /* The minimal value of MCLK */ + int mclk_src; /* which clock source the MCLK derives from */ + int mclk_div; /* Clock Divider Value for MCLK */ + /* + * MIPI support + */ + int dphy[3]; /* DPHY: CSI2_DPHY3, CSI2_DPHY5, CSI2_DPHY6 */ + enum dphy3_algo dphy3_algo; /* algos for calculate CSI2_DPHY3 */ + int lane; /* ccic used lane number; 0 means DVP mode */ + int lane_clk; }; -- cgit v1.2.3 From 190d7f02ce8ef6774a69d3ec18c288c8a9601a4e Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 8 Dec 2017 15:28:18 +0100 Subject: HID: input: do not increment usages when a duplicate is found This is something that bothered us from a long time. When hid-input doesn't know how to map a usage, it uses *_MISC. But there is something else which increments the usage if the evdev code is already used. This leads to few issues: - some devices may have their ABS_X mapped to ABS_Y if they export a bad set of usages (see the DragonRise joysticks IIRC -> fixed in a specific HID driver) - *_MISC + N might (will) conflict with other defined axes (my Logitech H800 exports some multitouch axes because of that) - this prevents to freely add some new evdev usages, because "hey, my headset will now report ABS_COFFEE, and it's not coffee capable". So let's try to kill this nonsense, and hope we won't break too many devices. I my headset case, the ABS_MISC axes are created because of some proprietary usages, so we might not break that many devices. For backward compatibility, a quirk HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE is created and can be applied to any device that needs this behavior. Signed-off-by: Benjamin Tissoires Acked-by: Peter Hutterer Acked-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 8da3e1f48195..0267aa5c1ea3 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -345,6 +345,7 @@ struct hid_item { #define HID_QUIRK_SKIP_OUTPUT_REPORT_ID BIT(17) #define HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP BIT(18) #define HID_QUIRK_HAVE_SPECIAL_DRIVER BIT(19) +#define HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE BIT(20) #define HID_QUIRK_FULLSPEED_INTERVAL BIT(28) #define HID_QUIRK_NO_INIT_REPORTS BIT(29) #define HID_QUIRK_NO_IGNORE BIT(30) @@ -502,6 +503,7 @@ struct hid_output_fifo { #define HID_STAT_ADDED BIT(0) #define HID_STAT_PARSED BIT(1) +#define HID_STAT_DUP_DETECTED BIT(2) struct hid_input { struct list_head list; -- cgit v1.2.3 From 106ca27f2922e8de820d1bd3d79b1cbdf2d78eea Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 17 Apr 2018 16:45:37 +0200 Subject: xdp: move struct xdp_buff from filter.h to xdp.h This is done to prepare for the next patch, and it is also nice to move this XDP related struct out of filter.h. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/filter.h | 24 +----------------------- 1 file changed, 1 insertion(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index fc4e8f91b03d..4da8b2308174 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -30,6 +30,7 @@ struct sock; struct seccomp_data; struct bpf_prog_aux; struct xdp_rxq_info; +struct xdp_buff; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function @@ -500,14 +501,6 @@ struct bpf_skb_data_end { void *data_end; }; -struct xdp_buff { - void *data; - void *data_end; - void *data_meta; - void *data_hard_start; - struct xdp_rxq_info *rxq; -}; - struct sk_msg_buff { void *data; void *data_end; @@ -772,21 +765,6 @@ int xdp_do_redirect(struct net_device *dev, struct bpf_prog *prog); void xdp_do_flush_map(void); -/* Drivers not supporting XDP metadata can use this helper, which - * rejects any room expansion for metadata as a result. - */ -static __always_inline void -xdp_set_data_meta_invalid(struct xdp_buff *xdp) -{ - xdp->data_meta = xdp->data + 1; -} - -static __always_inline bool -xdp_data_meta_unsupported(const struct xdp_buff *xdp) -{ - return unlikely(xdp->data_meta > xdp->data); -} - void bpf_warn_invalid_xdp_action(u32 act); struct sock *do_sk_redirect_map(struct sk_buff *skb); -- cgit v1.2.3 From 1ffcbc8537d0bc32aaca7000cb9c904ec4b6300f Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 17 Apr 2018 16:45:47 +0200 Subject: tun: convert to use generic xdp_frame and xdp_return_frame API The tuntap driver invented it's own driver specific way of queuing XDP packets, by storing the xdp_buff information in the top of the XDP frame data. Convert it over to use the more generic xdp_frame structure. The main problem with the in-driver method is that the xdp_rxq_info pointer cannot be trused/used when dequeueing the frame. V3: Remove check based on feedback from Jason Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/if_tun.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index fd00170b494f..3d2996dc7d85 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -22,7 +22,7 @@ #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); -bool tun_is_xdp_buff(void *ptr); +bool tun_is_xdp_frame(void *ptr); void *tun_xdp_to_ptr(void *ptr); void *tun_ptr_to_xdp(void *ptr); void tun_ptr_free(void *ptr); @@ -39,7 +39,7 @@ static inline struct ptr_ring *tun_get_tx_ring(struct file *f) { return ERR_PTR(-EINVAL); } -static inline bool tun_is_xdp_buff(void *ptr) +static inline bool tun_is_xdp_frame(void *ptr) { return false; } -- cgit v1.2.3 From 44fa2dbd475996ddc8f3a0e6113dee983e0ee3aa Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 17 Apr 2018 16:46:37 +0200 Subject: xdp: transition into using xdp_frame for ndo_xdp_xmit Changing API ndo_xdp_xmit to take a struct xdp_frame instead of struct xdp_buff. This brings xdp_return_frame and ndp_xdp_xmit in sync. This builds towards changing the API further to become a bulk API, because xdp_buff is not a queue-able object while xdp_frame is. V4: Adjust for commit 59655a5b6c83 ("tuntap: XDP_TX can use native XDP") V7: Adjust for commit d9314c474d4f ("i40e: add support for XDP_REDIRECT") Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cf44503ea81a..14e0777ffcfb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1165,7 +1165,7 @@ struct dev_ifalias { * This function is used to set or query state related to XDP on the * netdevice and manage BPF offload. See definition of * enum bpf_netdev_command for details. - * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp); + * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_frame *xdp); * This function is used to submit a XDP packet for transmit on a * netdevice. * void (*ndo_xdp_flush)(struct net_device *dev); @@ -1356,7 +1356,7 @@ struct net_device_ops { int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); int (*ndo_xdp_xmit)(struct net_device *dev, - struct xdp_buff *xdp); + struct xdp_frame *xdp); void (*ndo_xdp_flush)(struct net_device *dev); }; -- cgit v1.2.3 From 1e6c06a7e88c251d8a30271ad5206fbd967a4576 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Sun, 8 Apr 2018 11:06:57 +0800 Subject: hwspinlock: Introduce one new mode for hwspinlock In some scenarios, user need do some time-consuming or sleepable operations under the hardware spinlock protection for synchronization between the multiple subsystems. For example, there is one PMIC efuse on Spreadtrum platform, which need to be accessed under one hardware lock. But during the hardware lock protection, the efuse operation is time-consuming to almost 5 ms, so we can not disable the interrupts or preemption so long in this case. Thus we can introduce one new mode to indicate that we just acquire the hardware lock and do not disable interrupts or preemption, meanwhile we should force user to protect the hardware lock with mutex or spinlock to avoid dead-lock. Signed-off-by: Baolin Wang Signed-off-by: Bjorn Andersson --- include/linux/hwspinlock.h | 58 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h index 859d673d98c8..fe450ee58d55 100644 --- a/include/linux/hwspinlock.h +++ b/include/linux/hwspinlock.h @@ -24,6 +24,7 @@ /* hwspinlock mode argument */ #define HWLOCK_IRQSTATE 0x01 /* Disable interrupts, save state */ #define HWLOCK_IRQ 0x02 /* Disable interrupts, don't save state */ +#define HWLOCK_RAW 0x03 struct device; struct device_node; @@ -175,6 +176,25 @@ static inline int hwspin_trylock_irq(struct hwspinlock *hwlock) return __hwspin_trylock(hwlock, HWLOCK_IRQ, NULL); } +/** + * hwspin_trylock_raw() - attempt to lock a specific hwspinlock + * @hwlock: an hwspinlock which we want to trylock + * + * This function attempts to lock an hwspinlock, and will immediately fail + * if the hwspinlock is already taken. + * + * Caution: User must protect the routine of getting hardware lock with mutex + * or spinlock to avoid dead-lock, that will let user can do some time-consuming + * or sleepable operations under the hardware lock. + * + * Returns 0 if we successfully locked the hwspinlock, -EBUSY if + * the hwspinlock was already taken, and -EINVAL if @hwlock is invalid. + */ +static inline int hwspin_trylock_raw(struct hwspinlock *hwlock) +{ + return __hwspin_trylock(hwlock, HWLOCK_RAW, NULL); +} + /** * hwspin_trylock() - attempt to lock a specific hwspinlock * @hwlock: an hwspinlock which we want to trylock @@ -242,6 +262,29 @@ int hwspin_lock_timeout_irq(struct hwspinlock *hwlock, unsigned int to) return __hwspin_lock_timeout(hwlock, to, HWLOCK_IRQ, NULL); } +/** + * hwspin_lock_timeout_raw() - lock an hwspinlock with timeout limit + * @hwlock: the hwspinlock to be locked + * @to: timeout value in msecs + * + * This function locks the underlying @hwlock. If the @hwlock + * is already taken, the function will busy loop waiting for it to + * be released, but give up when @timeout msecs have elapsed. + * + * Caution: User must protect the routine of getting hardware lock with mutex + * or spinlock to avoid dead-lock, that will let user can do some time-consuming + * or sleepable operations under the hardware lock. + * + * Returns 0 when the @hwlock was successfully taken, and an appropriate + * error code otherwise (most notably an -ETIMEDOUT if the @hwlock is still + * busy after @timeout msecs). The function will never sleep. + */ +static inline +int hwspin_lock_timeout_raw(struct hwspinlock *hwlock, unsigned int to) +{ + return __hwspin_lock_timeout(hwlock, to, HWLOCK_RAW, NULL); +} + /** * hwspin_lock_timeout() - lock an hwspinlock with timeout limit * @hwlock: the hwspinlock to be locked @@ -301,6 +344,21 @@ static inline void hwspin_unlock_irq(struct hwspinlock *hwlock) __hwspin_unlock(hwlock, HWLOCK_IRQ, NULL); } +/** + * hwspin_unlock_raw() - unlock hwspinlock + * @hwlock: a previously-acquired hwspinlock which we want to unlock + * + * This function will unlock a specific hwspinlock. + * + * @hwlock must be already locked (e.g. by hwspin_trylock()) before calling + * this function: it is a bug to call unlock on a @hwlock that is already + * unlocked. + */ +static inline void hwspin_unlock_raw(struct hwspinlock *hwlock) +{ + __hwspin_unlock(hwlock, HWLOCK_RAW, NULL); +} + /** * hwspin_unlock() - unlock hwspinlock * @hwlock: a previously-acquired hwspinlock which we want to unlock -- cgit v1.2.3 From fe1bd78bf18a7cb3eb76fceea9193534fb6619e3 Mon Sep 17 00:00:00 2001 From: Trent Piepho Date: Mon, 2 Apr 2018 13:06:05 -0700 Subject: ARM: imx: Update spi_imx platform data to reflect current state The docs for the spi_imx platform data still refer to a -32 offset used to specify a native chip select. This was removed in commit 602c8f4485cd ("spi: imx: fix use of native chip-selects with devicetree") and no longer works as documented. Update documentation. The macro MXC_SPI_CS() is no longer is needed. If a board uses all native chip selects, then it's not necessary to specify a chip select array at all, as all native is the default (this is how device-tree configured SPI masters work too). Most of the spi-imx platform data users have their chip select arrays removed by this patch. This patch also fixes a bug in mx31moboard introduced in the '602 commit. When that board was updated in commit 901f26bce64a ("ARM: imx: set correct chip_select in platform setup") to reflect the SPI change, only SPI bus 2 was updated and SPI bus 1 was left with non-sequential chip selects. The mc13783 spi device on bus 1 had its chip select updated as if it were on bus 2. CC: Sascha Hauer CC: Fabio Estevam Acked-by: Greg Ungerer Reviewed-by: Oleksij Rempel Signed-off-by: Trent Piepho Signed-off-by: Shawn Guo --- include/linux/platform_data/spi-imx.h | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/spi-imx.h b/include/linux/platform_data/spi-imx.h index 6f012fefa1a2..328f670d10bd 100644 --- a/include/linux/platform_data/spi-imx.h +++ b/include/linux/platform_data/spi-imx.h @@ -5,24 +5,29 @@ /* * struct spi_imx_master - device.platform_data for SPI controller devices. - * @chipselect: Array of chipselects for this master. Numbers >= 0 mean gpio - * pins, numbers < 0 mean internal CSPI chipselects according - * to MXC_SPI_CS(). Normally you want to use gpio based chip - * selects as the CSPI module tries to be intelligent about - * when to assert the chipselect: The CSPI module deasserts the - * chipselect once it runs out of input data. The other problem - * is that it is not possible to mix between high active and low - * active chipselects on one single bus using the internal - * chipselects. Unfortunately Freescale decided to put some + * @chipselect: Array of chipselects for this master or NULL. Numbers >= 0 + * mean GPIO pins, -ENOENT means internal CSPI chipselect + * matching the position in the array. E.g., if chipselect[1] = + * -ENOENT then a SPI slave using chip select 1 will use the + * native SS1 line of the CSPI. Omitting the array will use + * all native chip selects. + + * Normally you want to use gpio based chip selects as the CSPI + * module tries to be intelligent about when to assert the + * chipselect: The CSPI module deasserts the chipselect once it + * runs out of input data. The other problem is that it is not + * possible to mix between high active and low active chipselects + * on one single bus using the internal chipselects. + * Unfortunately, on some SoCs, Freescale decided to put some * chipselects on dedicated pins which are not usable as gpios, * so we have to support the internal chipselects. - * @num_chipselect: ARRAY_SIZE(chipselect) + * + * @num_chipselect: If @chipselect is specified, ARRAY_SIZE(chipselect), + * otherwise the number of native chip selects. */ struct spi_imx_master { int *chipselect; int num_chipselect; }; -#define MXC_SPI_CS(no) ((no) - 32) - #endif /* __MACH_SPI_H_*/ -- cgit v1.2.3 From 91e2dd0a47bae19600f13dcc9e0761082c50afa6 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 28 Mar 2018 13:19:25 -0500 Subject: ipmi: Add a panic handler for IPMI users Users of the IPMI code had their own panic handlers, but the order was not necessarily right, the base IPMI code would need to handle the panic first, and the user had no way to know if the IPMI interface could run at panic time. Add a panic handler to the user interface, it is called if non-NULL and the interface the user is on is capable of panic handling. It also cleans up the panic log handling a bit to reuse the existing interface loop in the main panic handler. Signed-off-by: Corey Minyard --- include/linux/ipmi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 8b0626cec980..39a29fb3131b 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -77,6 +77,12 @@ struct ipmi_user_hndl { /* Called when the interface detects a watchdog pre-timeout. If this is NULL, it will be ignored for the user. */ void (*ipmi_watchdog_pretimeout)(void *handler_data); + + /* + * If not NULL, called at panic time after the interface has + * been set up to handle run to completion. + */ + void (*ipmi_panic_handler)(void *handler_data); }; /* Create a new user of the IPMI layer on the given interface number. */ -- cgit v1.2.3 From 6dc1181f9fbcf7ba0e62adfaea41666f00ee9d18 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 4 Apr 2018 08:54:05 -0500 Subject: ipmi: Clean up comments in include files. Make the comments correct and consistent. Signed-off-by: Corey Minyard --- include/linux/ipmi.h | 105 ++++++++++++++++++++++++++----------------- include/linux/ipmi_smi.h | 115 ++++++++++++++++++++++++++++------------------- 2 files changed, 134 insertions(+), 86 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 39a29fb3131b..3474f04cf9aa 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -23,8 +23,10 @@ struct module; struct device; -/* Opaque type for a IPMI message user. One of these is needed to - send and receive messages. */ +/* + * Opaque type for a IPMI message user. One of these is needed to + * send and receive messages. + */ typedef struct ipmi_user *ipmi_user_t; /* @@ -37,8 +39,10 @@ typedef struct ipmi_user *ipmi_user_t; struct ipmi_recv_msg { struct list_head link; - /* The type of message as defined in the "Receive Types" - defines above. */ + /* + * The type of message as defined in the "Receive Types" + * defines above. + */ int recv_type; ipmi_user_t user; @@ -46,19 +50,25 @@ struct ipmi_recv_msg { long msgid; struct kernel_ipmi_msg msg; - /* The user_msg_data is the data supplied when a message was - sent, if this is a response to a sent message. If this is - not a response to a sent message, then user_msg_data will - be NULL. If the user above is NULL, then this will be the - intf. */ + /* + * The user_msg_data is the data supplied when a message was + * sent, if this is a response to a sent message. If this is + * not a response to a sent message, then user_msg_data will + * be NULL. If the user above is NULL, then this will be the + * intf. + */ void *user_msg_data; - /* Call this when done with the message. It will presumably free - the message and do any other necessary cleanup. */ + /* + * Call this when done with the message. It will presumably free + * the message and do any other necessary cleanup. + */ void (*done)(struct ipmi_recv_msg *msg); - /* Place-holder for the data, don't make any assumptions about - the size or existence of this, since it may change. */ + /* + * Place-holder for the data, don't make any assumptions about + * the size or existence of this, since it may change. + */ unsigned char msg_data[IPMI_MAX_MSG_LENGTH]; }; @@ -66,16 +76,20 @@ struct ipmi_recv_msg { void ipmi_free_recv_msg(struct ipmi_recv_msg *msg); struct ipmi_user_hndl { - /* Routine type to call when a message needs to be routed to - the upper layer. This will be called with some locks held, - the only IPMI routines that can be called are ipmi_request - and the alloc/free operations. The handler_data is the - variable supplied when the receive handler was registered. */ + /* + * Routine type to call when a message needs to be routed to + * the upper layer. This will be called with some locks held, + * the only IPMI routines that can be called are ipmi_request + * and the alloc/free operations. The handler_data is the + * variable supplied when the receive handler was registered. + */ void (*ipmi_recv_hndl)(struct ipmi_recv_msg *msg, void *user_msg_data); - /* Called when the interface detects a watchdog pre-timeout. If - this is NULL, it will be ignored for the user. */ + /* + * Called when the interface detects a watchdog pre-timeout. If + * this is NULL, it will be ignored for the user. + */ void (*ipmi_watchdog_pretimeout)(void *handler_data); /* @@ -91,12 +105,14 @@ int ipmi_create_user(unsigned int if_num, void *handler_data, ipmi_user_t *user); -/* Destroy the given user of the IPMI layer. Note that after this - function returns, the system is guaranteed to not call any - callbacks for the user. Thus as long as you destroy all the users - before you unload a module, you will be safe. And if you destroy - the users before you destroy the callback structures, it should be - safe, too. */ +/* + * Destroy the given user of the IPMI layer. Note that after this + * function returns, the system is guaranteed to not call any + * callbacks for the user. Thus as long as you destroy all the users + * before you unload a module, you will be safe. And if you destroy + * the users before you destroy the callback structures, it should be + * safe, too. + */ int ipmi_destroy_user(ipmi_user_t user); /* Get the IPMI version of the BMC we are talking to. */ @@ -104,12 +120,15 @@ int ipmi_get_version(ipmi_user_t user, unsigned char *major, unsigned char *minor); -/* Set and get the slave address and LUN that we will use for our - source messages. Note that this affects the interface, not just - this user, so it will affect all users of this interface. This is - so some initialization code can come in and do the OEM-specific - things it takes to determine your address (if not the BMC) and set - it for everyone else. Note that each channel can have its own address. */ +/* + * Set and get the slave address and LUN that we will use for our + * source messages. Note that this affects the interface, not just + * this user, so it will affect all users of this interface. This is + * so some initialization code can come in and do the OEM-specific + * things it takes to determine your address (if not the BMC) and set + * it for everyone else. Note that each channel can have its own + * address. + */ int ipmi_set_my_address(ipmi_user_t user, unsigned int channel, unsigned char address); @@ -235,14 +254,18 @@ int ipmi_set_gets_events(ipmi_user_t user, bool val); struct ipmi_smi_watcher { struct list_head link; - /* You must set the owner to the current module, if you are in - a module (generally just set it to "THIS_MODULE"). */ + /* + * You must set the owner to the current module, if you are in + * a module (generally just set it to "THIS_MODULE"). + */ struct module *owner; - /* These two are called with read locks held for the interface - the watcher list. So you can add and remove users from the - IPMI interface, send messages, etc., but you cannot add - or remove SMI watchers or SMI interfaces. */ + /* + * These two are called with read locks held for the interface + * the watcher list. So you can add and remove users from the + * IPMI interface, send messages, etc., but you cannot add + * or remove SMI watchers or SMI interfaces. + */ void (*new_smi)(int if_num, struct device *dev); void (*smi_gone)(int if_num); }; @@ -250,8 +273,10 @@ struct ipmi_smi_watcher { int ipmi_smi_watcher_register(struct ipmi_smi_watcher *watcher); int ipmi_smi_watcher_unregister(struct ipmi_smi_watcher *watcher); -/* The following are various helper functions for dealing with IPMI - addresses. */ +/* + * The following are various helper functions for dealing with IPMI + * addresses. + */ /* Return the maximum length of an IPMI address given it's type. */ unsigned int ipmi_addr_length(int addr_type); diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index af457b5a689e..9e5c3079d232 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -22,8 +22,10 @@ struct device; -/* This files describes the interface for IPMI system management interface - drivers to bind into the IPMI message handler. */ +/* + * This files describes the interface for IPMI system management interface + * drivers to bind into the IPMI message handler. + */ /* Structure for the low-level drivers. */ typedef struct ipmi_smi *ipmi_smi_t; @@ -61,10 +63,12 @@ struct ipmi_smi_msg { struct ipmi_smi_handlers { struct module *owner; - /* The low-level interface cannot start sending messages to - the upper layer until this function is called. This may - not be NULL, the lower layer must take the interface from - this call. */ + /* + * The low-level interface cannot start sending messages to + * the upper layer until this function is called. This may + * not be NULL, the lower layer must take the interface from + * this call. + */ int (*start_processing)(void *send_info, ipmi_smi_t new_intf); @@ -75,25 +79,31 @@ struct ipmi_smi_handlers { */ int (*get_smi_info)(void *send_info, struct ipmi_smi_info *data); - /* Called to enqueue an SMI message to be sent. This - operation is not allowed to fail. If an error occurs, it - should report back the error in a received message. It may - do this in the current call context, since no write locks - are held when this is run. Message are delivered one at - a time by the message handler, a new message will not be - delivered until the previous message is returned. */ + /* + * Called to enqueue an SMI message to be sent. This + * operation is not allowed to fail. If an error occurs, it + * should report back the error in a received message. It may + * do this in the current call context, since no write locks + * are held when this is run. Message are delivered one at + * a time by the message handler, a new message will not be + * delivered until the previous message is returned. + */ void (*sender)(void *send_info, struct ipmi_smi_msg *msg); - /* Called by the upper layer to request that we try to get - events from the BMC we are attached to. */ + /* + * Called by the upper layer to request that we try to get + * events from the BMC we are attached to. + */ void (*request_events)(void *send_info); - /* Called by the upper layer when some user requires that the - interface watch for events, received messages, watchdog - pretimeouts, or not. Used by the SMI to know if it should - watch for these. This may be NULL if the SMI does not - implement it. */ + /* + * Called by the upper layer when some user requires that the + * interface watch for events, received messages, watchdog + * pretimeouts, or not. Used by the SMI to know if it should + * watch for these. This may be NULL if the SMI does not + * implement it. + */ void (*set_need_watch)(void *send_info, bool enable); /* @@ -101,28 +111,36 @@ struct ipmi_smi_handlers { */ void (*flush_messages)(void *send_info); - /* Called when the interface should go into "run to - completion" mode. If this call sets the value to true, the - interface should make sure that all messages are flushed - out and that none are pending, and any new requests are run - to completion immediately. */ + /* + * Called when the interface should go into "run to + * completion" mode. If this call sets the value to true, the + * interface should make sure that all messages are flushed + * out and that none are pending, and any new requests are run + * to completion immediately. + */ void (*set_run_to_completion)(void *send_info, bool run_to_completion); - /* Called to poll for work to do. This is so upper layers can - poll for operations during things like crash dumps. */ + /* + * Called to poll for work to do. This is so upper layers can + * poll for operations during things like crash dumps. + */ void (*poll)(void *send_info); - /* Enable/disable firmware maintenance mode. Note that this - is *not* the modes defined, this is simply an on/off - setting. The message handler does the mode handling. Note - that this is called from interrupt context, so it cannot - block. */ + /* + * Enable/disable firmware maintenance mode. Note that this + * is *not* the modes defined, this is simply an on/off + * setting. The message handler does the mode handling. Note + * that this is called from interrupt context, so it cannot + * block. + */ void (*set_maintenance_mode)(void *send_info, bool enable); - /* Tell the handler that we are using it/not using it. The - message handler get the modules that this handler belongs - to; this function lets the SMI claim any modules that it - uses. These may be NULL if this is not required. */ + /* + * Tell the handler that we are using it/not using it. The + * message handler get the modules that this handler belongs + * to; this function lets the SMI claim any modules that it + * uses. These may be NULL if this is not required. + */ int (*inc_usecount)(void *send_info); void (*dec_usecount)(void *send_info); }; @@ -143,7 +161,8 @@ struct ipmi_device_id { #define ipmi_version_major(v) ((v)->ipmi_version & 0xf) #define ipmi_version_minor(v) ((v)->ipmi_version >> 4) -/* Take a pointer to an IPMI response and extract device id information from +/* + * Take a pointer to an IPMI response and extract device id information from * it. @netfn is in the IPMI_NETFN_ format, so may need to be shifted from * a SI response. */ @@ -187,12 +206,14 @@ static inline int ipmi_demangle_device_id(uint8_t netfn, uint8_t cmd, return 0; } -/* Add a low-level interface to the IPMI driver. Note that if the - interface doesn't know its slave address, it should pass in zero. - The low-level interface should not deliver any messages to the - upper layer until the start_processing() function in the handlers - is called, and the lower layer must get the interface from that - call. */ +/* + * Add a low-level interface to the IPMI driver. Note that if the + * interface doesn't know its slave address, it should pass in zero. + * The low-level interface should not deliver any messages to the + * upper layer until the start_processing() function in the handlers + * is called, and the lower layer must get the interface from that + * call. + */ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, void *send_info, struct device *dev, @@ -223,9 +244,11 @@ static inline void ipmi_free_smi_msg(struct ipmi_smi_msg *msg) } #ifdef CONFIG_IPMI_PROC_INTERFACE -/* Allow the lower layer to add things to the proc filesystem - directory for this interface. Note that the entry will - automatically be dstroyed when the interface is destroyed. */ +/* + * Allow the lower layer to add things to the proc filesystem + * directory for this interface. Note that the entry will + * automatically be dstroyed when the interface is destroyed. + */ int ipmi_smi_add_proc_entry(ipmi_smi_t smi, char *name, const struct file_operations *proc_ops, void *data); -- cgit v1.2.3 From b7780dab90e8da302bc7d0d1b39b538b822017e8 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Thu, 5 Apr 2018 16:44:12 -0500 Subject: ipmi: Add shutdown functions for users and interfaces Since things that IPMI uses can be hot-swapped, the users and interfaces really need to be able to handle this. Add the functions so the users and interfaces can implement them, the actual function will be added after everything is ready. Signed-off-by: Corey Minyard --- include/linux/ipmi.h | 8 ++++++++ include/linux/ipmi_smi.h | 6 ++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 3474f04cf9aa..d89bea1e457a 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -97,6 +97,14 @@ struct ipmi_user_hndl { * been set up to handle run to completion. */ void (*ipmi_panic_handler)(void *handler_data); + + /* + * Called when the interface has been removed. After this returns + * the user handle will be invalid. The interface may or may + * not be usable when this is called, but it will return errors + * if it is not usable. + */ + void (*shutdown)(void *handler_data); }; /* Create a new user of the IPMI layer on the given interface number. */ diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 9e5c3079d232..bdcda4741c89 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -72,6 +72,12 @@ struct ipmi_smi_handlers { int (*start_processing)(void *send_info, ipmi_smi_t new_intf); + /* + * When called, the low-level interface should disable all + * processing, it should be complete shut down when it returns. + */ + void (*shutdown)(void *send_info); + /* * Get the detailed private info of the low level interface and store * it into the structure of ipmi_smi_data. For example: the -- cgit v1.2.3 From 8eb005bf6e58ca08802ac8170e5d3c8486cb2d79 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Thu, 5 Apr 2018 22:10:08 -0500 Subject: ipmi: Remove usecount function from interfaces All the users are now gone. Signed-off-by: Corey Minyard --- include/linux/ipmi_smi.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index bdcda4741c89..16662b0423bf 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -140,15 +140,6 @@ struct ipmi_smi_handlers { * block. */ void (*set_maintenance_mode)(void *send_info, bool enable); - - /* - * Tell the handler that we are using it/not using it. The - * message handler get the modules that this handler belongs - * to; this function lets the SMI claim any modules that it - * uses. These may be NULL if this is not required. - */ - int (*inc_usecount)(void *send_info); - void (*dec_usecount)(void *send_info); }; struct ipmi_device_id { -- cgit v1.2.3 From 6a0d23ed338ed7015128378e0ceec03eaa3d91e2 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 11 Apr 2018 12:41:33 -0500 Subject: ipmi: ipmi_unregister_smi() cannot fail, have it return void Signed-off-by: Corey Minyard --- include/linux/ipmi_smi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 16662b0423bf..26ba57c307f0 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -220,7 +220,7 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, * Remove a low-level interface from the IPMI driver. This will * return an error if the interface is still in use by a user. */ -int ipmi_unregister_smi(ipmi_smi_t intf); +void ipmi_unregister_smi(ipmi_smi_t intf); /* * The lower layer reports received messages through this interface. -- cgit v1.2.3 From 5ce1a7dc806efb2181e93d4a088b281c4cff4eaa Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 11 Apr 2018 13:11:54 -0500 Subject: ipmi: Get rid of ipmi_user_t and ipmi_smi_t in include files Convert over to struct ipmi_user * and struct ipmi_smi *. Signed-off-by: Corey Minyard --- include/linux/ipmi.h | 34 +++++++++++++++++----------------- include/linux/ipmi_smi.h | 12 ++++++------ 2 files changed, 23 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index d89bea1e457a..41f5c086f670 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -45,7 +45,7 @@ struct ipmi_recv_msg { */ int recv_type; - ipmi_user_t user; + struct ipmi_user *user; struct ipmi_addr addr; long msgid; struct kernel_ipmi_msg msg; @@ -111,7 +111,7 @@ struct ipmi_user_hndl { int ipmi_create_user(unsigned int if_num, const struct ipmi_user_hndl *handler, void *handler_data, - ipmi_user_t *user); + struct ipmi_user **user); /* * Destroy the given user of the IPMI layer. Note that after this @@ -121,10 +121,10 @@ int ipmi_create_user(unsigned int if_num, * the users before you destroy the callback structures, it should be * safe, too. */ -int ipmi_destroy_user(ipmi_user_t user); +int ipmi_destroy_user(struct ipmi_user *user); /* Get the IPMI version of the BMC we are talking to. */ -int ipmi_get_version(ipmi_user_t user, +int ipmi_get_version(struct ipmi_user *user, unsigned char *major, unsigned char *minor); @@ -137,16 +137,16 @@ int ipmi_get_version(ipmi_user_t user, * it for everyone else. Note that each channel can have its own * address. */ -int ipmi_set_my_address(ipmi_user_t user, +int ipmi_set_my_address(struct ipmi_user *user, unsigned int channel, unsigned char address); -int ipmi_get_my_address(ipmi_user_t user, +int ipmi_get_my_address(struct ipmi_user *user, unsigned int channel, unsigned char *address); -int ipmi_set_my_LUN(ipmi_user_t user, +int ipmi_set_my_LUN(struct ipmi_user *user, unsigned int channel, unsigned char LUN); -int ipmi_get_my_LUN(ipmi_user_t user, +int ipmi_get_my_LUN(struct ipmi_user *user, unsigned int channel, unsigned char *LUN); @@ -163,7 +163,7 @@ int ipmi_get_my_LUN(ipmi_user_t user, * it makes no sense to do it here. However, this can be used if you * have unusual requirements. */ -int ipmi_request_settime(ipmi_user_t user, +int ipmi_request_settime(struct ipmi_user *user, struct ipmi_addr *addr, long msgid, struct kernel_ipmi_msg *msg, @@ -181,7 +181,7 @@ int ipmi_request_settime(ipmi_user_t user, * change as the system changes, so don't use it unless you REALLY * have to. */ -int ipmi_request_supply_msgs(ipmi_user_t user, +int ipmi_request_supply_msgs(struct ipmi_user *user, struct ipmi_addr *addr, long msgid, struct kernel_ipmi_msg *msg, @@ -197,7 +197,7 @@ int ipmi_request_supply_msgs(ipmi_user_t user, * way. This is useful if you need to spin waiting for something to * happen in the IPMI driver. */ -void ipmi_poll_interface(ipmi_user_t user); +void ipmi_poll_interface(struct ipmi_user *user); /* * When commands come in to the SMS, the user can register to receive @@ -208,11 +208,11 @@ void ipmi_poll_interface(ipmi_user_t user); * error. Channels are specified as a bitfield, use IPMI_CHAN_ALL to * mean all channels. */ -int ipmi_register_for_cmd(ipmi_user_t user, +int ipmi_register_for_cmd(struct ipmi_user *user, unsigned char netfn, unsigned char cmd, unsigned int chans); -int ipmi_unregister_for_cmd(ipmi_user_t user, +int ipmi_unregister_for_cmd(struct ipmi_user *user, unsigned char netfn, unsigned char cmd, unsigned int chans); @@ -243,8 +243,8 @@ int ipmi_unregister_for_cmd(ipmi_user_t user, * * See the IPMI_MAINTENANCE_MODE_xxx defines for what the mode means. */ -int ipmi_get_maintenance_mode(ipmi_user_t user); -int ipmi_set_maintenance_mode(ipmi_user_t user, int mode); +int ipmi_get_maintenance_mode(struct ipmi_user *user); +int ipmi_set_maintenance_mode(struct ipmi_user *user, int mode); /* * When the user is created, it will not receive IPMI events by @@ -252,7 +252,7 @@ int ipmi_set_maintenance_mode(ipmi_user_t user, int mode); * The first user that sets this to TRUE will receive all events that * have been queued while no one was waiting for events. */ -int ipmi_set_gets_events(ipmi_user_t user, bool val); +int ipmi_set_gets_events(struct ipmi_user *user, bool val); /* * Called when a new SMI is registered. This will also be called on @@ -330,7 +330,7 @@ struct ipmi_smi_info { union ipmi_smi_info_union addr_info; }; -/* This is to get the private info of ipmi_smi_t */ +/* This is to get the private info of struct ipmi_smi */ extern int ipmi_get_smi_info(int if_num, struct ipmi_smi_info *data); #endif /* __LINUX_IPMI_H */ diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 26ba57c307f0..0d438662a821 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -69,8 +69,8 @@ struct ipmi_smi_handlers { * not be NULL, the lower layer must take the interface from * this call. */ - int (*start_processing)(void *send_info, - ipmi_smi_t new_intf); + int (*start_processing)(void *send_info, + struct ipmi_smi *new_intf); /* * When called, the low-level interface should disable all @@ -220,7 +220,7 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, * Remove a low-level interface from the IPMI driver. This will * return an error if the interface is still in use by a user. */ -void ipmi_unregister_smi(ipmi_smi_t intf); +void ipmi_unregister_smi(struct ipmi_smi *intf); /* * The lower layer reports received messages through this interface. @@ -228,11 +228,11 @@ void ipmi_unregister_smi(ipmi_smi_t intf); * the lower layer gets an error sending a message, it should format * an error response in the message response. */ -void ipmi_smi_msg_received(ipmi_smi_t intf, +void ipmi_smi_msg_received(struct ipmi_smi *intf, struct ipmi_smi_msg *msg); /* The lower layer received a watchdog pre-timeout on interface. */ -void ipmi_smi_watchdog_pretimeout(ipmi_smi_t intf); +void ipmi_smi_watchdog_pretimeout(struct ipmi_smi *intf); struct ipmi_smi_msg *ipmi_alloc_smi_msg(void); static inline void ipmi_free_smi_msg(struct ipmi_smi_msg *msg) @@ -246,7 +246,7 @@ static inline void ipmi_free_smi_msg(struct ipmi_smi_msg *msg) * directory for this interface. Note that the entry will * automatically be dstroyed when the interface is destroyed. */ -int ipmi_smi_add_proc_entry(ipmi_smi_t smi, char *name, +int ipmi_smi_add_proc_entry(struct ipmi_smi *smi, char *name, const struct file_operations *proc_ops, void *data); #endif -- cgit v1.2.3 From b6240a4df0186c03e5ffff6f61570ed31a1a5172 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Mon, 26 Mar 2018 17:27:41 +0800 Subject: scsi: libsas: add transport class for ATA devices Now ata devices attached with sas controller do not have transport class, so that we can not see any information of these ata devices in /sys/class/ata_port(or ata_link or ata_device). Add transport class for the ata devices attached with sas controller. The /sys/class directory will show the infomation of the ata devices as follows: localhost:/sys/class # ls ata* ata_device: dev1.0 dev2.0 ata_link: link1 link2 ata_port: ata1 ata2 No functional change of the device scanning and io path. The ata transport class was deleted when destroying the sas devices. Signed-off-by: Jason Yan CC: Dan Williams CC: Tejun Heo Acked-by: Tejun Heo Signed-off-by: Martin K. Petersen --- include/linux/libata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 1795fecdea17..0619ebf4d475 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1130,6 +1130,8 @@ extern void ata_sas_async_probe(struct ata_port *ap); extern int ata_sas_sync_probe(struct ata_port *ap); extern int ata_sas_port_init(struct ata_port *); extern int ata_sas_port_start(struct ata_port *ap); +extern int ata_sas_tport_add(struct device *parent, struct ata_port *ap); +extern void ata_sas_tport_delete(struct ata_port *ap); extern void ata_sas_port_stop(struct ata_port *ap); extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *); extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap); -- cgit v1.2.3 From 63273cb40101b6f303a5493f1bdf629d4ab3746b Mon Sep 17 00:00:00 2001 From: Long Li Date: Tue, 27 Mar 2018 17:48:38 -0700 Subject: scsi: vmbus: Add function to report available ring buffer to write in total ring size percentage Netvsc has a function to calculate how much ring buffer in percentage is available to write. This function is also useful for storvsc and other vmbus devices. Define a similar function in vmbus to be used by other vmbus devices. Signed-off-by: Long Li Acked-by: David S. Miller Signed-off-by: Martin K. Petersen --- include/linux/hyperv.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 192ed8fbc403..9ac954ee577e 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -35,6 +35,7 @@ #include #include #include +#include #define MAX_PAGE_BUFFER_COUNT 32 #define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ @@ -120,6 +121,7 @@ struct hv_ring_buffer { struct hv_ring_buffer_info { struct hv_ring_buffer *ring_buffer; u32 ring_size; /* Include the shared header */ + struct reciprocal_value ring_size_div10_reciprocal; spinlock_t ring_lock; u32 ring_datasize; /* < ring_size */ @@ -154,6 +156,16 @@ static inline u32 hv_get_bytes_to_write(const struct hv_ring_buffer_info *rbi) return write; } +static inline u32 hv_get_avail_to_write_percent( + const struct hv_ring_buffer_info *rbi) +{ + u32 avail_write = hv_get_bytes_to_write(rbi); + + return reciprocal_divide( + (avail_write << 3) + (avail_write << 1), + rbi->ring_size_div10_reciprocal); +} + /* * VMBUS version is 32 bit entity broken up into * two 16 bit quantities: major_number. minor_number. -- cgit v1.2.3 From a2dd6877b43ef14129f258910d60b2e81b32100b Mon Sep 17 00:00:00 2001 From: Murali Karicheri Date: Tue, 17 Apr 2018 17:30:31 -0400 Subject: soc: ti: K2G: provide APIs to support driver probe deferral This patch provide APIs to allow client drivers to support probe deferral. On K2G SoC, devices can be probed only after the ti_sci_pm_domains driver is probed and ready. As drivers may get probed at different order, any driver that depends on knav dma and qmss drivers, for example netcp network driver, needs to defer probe until knav devices are probed and ready to service. To do this, add an API to query the device ready status from the knav dma and qmss devices. Signed-off-by: Murali Karicheri Signed-off-by: David S. Miller --- include/linux/soc/ti/knav_dma.h | 12 ++++++++++++ include/linux/soc/ti/knav_qmss.h | 1 + 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h index 66693bc4c6ad..7127ec301537 100644 --- a/include/linux/soc/ti/knav_dma.h +++ b/include/linux/soc/ti/knav_dma.h @@ -167,6 +167,8 @@ struct knav_dma_desc { void *knav_dma_open_channel(struct device *dev, const char *name, struct knav_dma_cfg *config); void knav_dma_close_channel(void *channel); +int knav_dma_get_flow(void *channel); +bool knav_dma_device_ready(void); #else static inline void *knav_dma_open_channel(struct device *dev, const char *name, struct knav_dma_cfg *config) @@ -176,6 +178,16 @@ static inline void *knav_dma_open_channel(struct device *dev, const char *name, static inline void knav_dma_close_channel(void *channel) {} +static inline int knav_dma_get_flow(void *channel) +{ + return -EINVAL; +} + +static inline bool knav_dma_device_ready(void) +{ + return false; +} + #endif #endif /* __SOC_TI_KEYSTONE_NAVIGATOR_DMA_H__ */ diff --git a/include/linux/soc/ti/knav_qmss.h b/include/linux/soc/ti/knav_qmss.h index 9f0ebb3bad27..9745df6ed9d3 100644 --- a/include/linux/soc/ti/knav_qmss.h +++ b/include/linux/soc/ti/knav_qmss.h @@ -86,5 +86,6 @@ int knav_pool_desc_map(void *ph, void *desc, unsigned size, void *knav_pool_desc_unmap(void *ph, dma_addr_t dma, unsigned dma_sz); dma_addr_t knav_pool_desc_virt_to_dma(void *ph, void *virt); void *knav_pool_desc_dma_to_virt(void *ph, dma_addr_t dma); +bool knav_qmss_device_ready(void); #endif /* __SOC_TI_KNAV_QMSS_H__ */ -- cgit v1.2.3 From 5055c67760df8e13c68f73b8534d5792d1d36543 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Tue, 13 Mar 2018 21:03:24 -0700 Subject: compat: Make compat helpers independent of CONFIG_COMPAT Many of the compat time syscalls are also repurposed as 32 bit native syscalls to provide backward compatibility while adding new y2038 safe sycalls. Enabling the helpers makes this possible. Signed-off-by: Arnd Bergmann Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 081281ad5772..3f35f4cfb98d 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -8,8 +8,6 @@ #include -#ifdef CONFIG_COMPAT - #include #include /* for HZ */ #include @@ -20,9 +18,11 @@ #include #include +#ifdef CONFIG_COMPAT #include #include #include +#endif #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER /* @@ -83,6 +83,8 @@ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* COMPAT_SYSCALL_DEFINEx */ +#ifdef CONFIG_COMPAT + #ifndef compat_user_stack_pointer #define compat_user_stack_pointer() current_user_stack_pointer() #endif @@ -1016,7 +1018,9 @@ static inline struct compat_timeval ns_to_compat_timeval(s64 nsec) #else /* !CONFIG_COMPAT */ #define is_compat_task() (0) +#ifndef in_compat_syscall static inline bool in_compat_syscall(void) { return false; } +#endif #endif /* CONFIG_COMPAT */ -- cgit v1.2.3 From 2b5a9a37e97467fea67070a94529d6d07e549270 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 26 Mar 2018 16:59:15 +0200 Subject: time: Add an asm-generic/compat.h file We have a couple of files that try to include asm/compat.h on architectures where this is available. Those should generally use the higher-level linux/compat.h file, but that in turn fails to include asm/compat.h when CONFIG_COMPAT is disabled, unless we can provide that header on all architectures. This adds the asm/compat.h for all remaining architectures to simplify the dependencies. Architectures that are getting removed in linux-4.17 are not changed here, to avoid needless conflicts with the removal patches. Those architectures are broken by this patch, but we have already shown that they have no users. Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 3f35f4cfb98d..48d29b1339be 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -18,8 +18,9 @@ #include #include -#ifdef CONFIG_COMPAT #include + +#ifdef CONFIG_COMPAT #include #include #endif -- cgit v1.2.3 From 0d55303c51a4f35f674617e415632d492b596c26 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Tue, 13 Mar 2018 21:03:25 -0700 Subject: compat: Move compat_timespec/ timeval to compat_time.h All the current architecture specific defines for these are the same. Refactor these common defines to a common header file. The new common linux/compat_time.h is also useful as it will eventually be used to hold all the defines that are needed for compat time types that support non y2038 safe types. New architectures need not have to define these new types as they will only use new y2038 safe syscalls. This file can be deleted after y2038 when we stop supporting non y2038 safe syscalls. The patch also requires an operation similar to: git grep "asm/compat\.h" | cut -d ":" -f 1 | xargs -n 1 sed -i -e "s%asm/compat.h%linux/compat.h%g" Cc: acme@kernel.org Cc: benh@kernel.crashing.org Cc: borntraeger@de.ibm.com Cc: catalin.marinas@arm.com Cc: cmetcalf@mellanox.com Cc: cohuck@redhat.com Cc: davem@davemloft.net Cc: deller@gmx.de Cc: devel@driverdev.osuosl.org Cc: gerald.schaefer@de.ibm.com Cc: gregkh@linuxfoundation.org Cc: heiko.carstens@de.ibm.com Cc: hoeppner@linux.vnet.ibm.com Cc: hpa@zytor.com Cc: jejb@parisc-linux.org Cc: jwi@linux.vnet.ibm.com Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-s390@vger.kernel.org Cc: mark.rutland@arm.com Cc: mingo@redhat.com Cc: mpe@ellerman.id.au Cc: oberpar@linux.vnet.ibm.com Cc: oprofile-list@lists.sf.net Cc: paulus@samba.org Cc: peterz@infradead.org Cc: ralf@linux-mips.org Cc: rostedt@goodmis.org Cc: rric@kernel.org Cc: schwidefsky@de.ibm.com Cc: sebott@linux.vnet.ibm.com Cc: sparclinux@vger.kernel.org Cc: sth@linux.vnet.ibm.com Cc: ubraun@linux.vnet.ibm.com Cc: will.deacon@arm.com Cc: x86@kernel.org Signed-off-by: Arnd Bergmann Signed-off-by: Deepa Dinamani Acked-by: Steven Rostedt (VMware) Acked-by: Catalin Marinas Acked-by: James Hogan Acked-by: Helge Deller Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 1 + include/linux/compat_time.h | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) create mode 100644 include/linux/compat_time.h (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 48d29b1339be..cd50b00ef59a 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -7,6 +7,7 @@ */ #include +#include #include #include /* for HZ */ diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h new file mode 100644 index 000000000000..56a54a1e4355 --- /dev/null +++ b/include/linux/compat_time.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_COMPAT_TIME_H +#define _LINUX_COMPAT_TIME_H + +#include + +typedef s32 compat_time_t; + +struct compat_timespec { + compat_time_t tv_sec; + s32 tv_nsec; +}; + +struct compat_timeval { + compat_time_t tv_sec; + s32 tv_usec; +}; + +#endif /* _LINUX_COMPAT_TIME_H */ -- cgit v1.2.3 From 1c68adf61e5845f3525522fa9c797ed370689c85 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Tue, 13 Mar 2018 21:03:26 -0700 Subject: compat: Enable compat_get/put_timespec64 always These functions are used in the repurposed compat syscalls to provide backward compatibility for using 32 bit time_t on 32 bit systems. Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 2 -- include/linux/compat_time.h | 4 ++++ 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index cd50b00ef59a..cfc1b6383ae0 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -294,8 +294,6 @@ extern int compat_get_timespec(struct timespec *, const void __user *); extern int compat_put_timespec(const struct timespec *, void __user *); extern int compat_get_timeval(struct timeval *, const void __user *); extern int compat_put_timeval(const struct timeval *, void __user *); -extern int compat_get_timespec64(struct timespec64 *, const void __user *); -extern int compat_put_timespec64(const struct timespec64 *, void __user *); extern int get_compat_itimerspec64(struct itimerspec64 *its, const struct compat_itimerspec __user *uits); extern int put_compat_itimerspec64(const struct itimerspec64 *its, diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h index 56a54a1e4355..31f2774f1994 100644 --- a/include/linux/compat_time.h +++ b/include/linux/compat_time.h @@ -3,6 +3,7 @@ #define _LINUX_COMPAT_TIME_H #include +#include typedef s32 compat_time_t; @@ -16,4 +17,7 @@ struct compat_timeval { s32 tv_usec; }; +extern int compat_get_timespec64(struct timespec64 *, const void __user *); +extern int compat_put_timespec64(const struct timespec64 *, void __user *); + #endif /* _LINUX_COMPAT_TIME_H */ -- cgit v1.2.3 From acf8870a62afd4f1b3c0b695aaa619df355c0851 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Tue, 13 Mar 2018 21:03:30 -0700 Subject: time: Add new y2038 safe __kernel_timespec The new struct __kernel_timespec is similar to current internal kernel struct timespec64 on 64 bit architecture. The compat structure however is similar to below on little endian systems (padding and tv_nsec are switched for big endian systems): typedef s32 compat_long_t; typedef s64 compat_kernel_time64_t; struct compat_kernel_timespec { compat_kernel_time64_t tv_sec; compat_long_t tv_nsec; compat_long_t padding; }; This allows for both the native and compat representations to be the same and syscalls using this type as part of their ABI can have a single entry point to both. Note that the compat define is not included anywhere in the kernel explicitly to avoid confusion. These types will be used by the new syscalls that will be introduced in the consequent patches. Most of the new syscalls are just an update to the existing native ones with this new type. Hence, put this new type under an ifdef so that the architectures can define CONFIG_64BIT_TIME when they are ready to handle this switch. Cc: linux-arch@vger.kernel.org Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/time64.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/time64.h b/include/linux/time64.h index 93d39499838e..0d96887ba4e0 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -2,12 +2,20 @@ #ifndef _LINUX_TIME64_H #define _LINUX_TIME64_H -#include #include typedef __s64 time64_t; typedef __u64 timeu64_t; +/* CONFIG_64BIT_TIME enables new 64 bit time_t syscalls in the compat path + * and 32-bit emulation. + */ +#ifndef CONFIG_64BIT_TIME +#define __kernel_timespec timespec +#endif + +#include + #if __BITS_PER_LONG == 64 /* this trick allows us to optimize out timespec64_to_timespec */ # define timespec64 timespec -- cgit v1.2.3 From ea2ce8f3514e2074a1910d8d721842d7341d5c81 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Tue, 13 Mar 2018 21:03:31 -0700 Subject: time: Fix get_timespec64() for y2038 safe compat interfaces get/put_timespec64() interfaces will eventually be used for conversions between the new y2038 safe struct __kernel_timespec and struct timespec64. The new y2038 safe syscalls have a common entry for native and compat interfaces. On compat interfaces, the high order bits of nanoseconds should be zeroed out. This is because the application code or the libc do not guarantee zeroing of these. If used without zeroing, kernel might be at risk of using timespec values incorrectly. Note that clearing of bits is dependent on CONFIG_64BIT_TIME for now. This is until COMPAT_USE_64BIT_TIME has been handled correctly. x86 will be the first architecture that will use the CONFIG_64BIT_TIME. Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/time.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 4b62a2c0a661..aed74463592d 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -10,9 +10,9 @@ extern struct timezone sys_tz; int get_timespec64(struct timespec64 *ts, - const struct timespec __user *uts); + const struct __kernel_timespec __user *uts); int put_timespec64(const struct timespec64 *ts, - struct timespec __user *uts); + struct __kernel_timespec __user *uts); int get_itimerspec64(struct itimerspec64 *it, const struct itimerspec __user *uit); int put_itimerspec64(const struct itimerspec64 *it, -- cgit v1.2.3 From 6d5b84132459c644cf4ee8de090382bad44b8ebd Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Tue, 13 Mar 2018 21:03:32 -0700 Subject: time: Change types to new y2038 safe __kernel_* types Change over clock_settime, clock_gettime and clock_getres syscalls to use __kernel_timespec times. This will enable changing over of these syscalls to use new y2038 safe syscalls when the architectures define the CONFIG_64BIT_TIME. Cc: linux-api@vger.kernel.org Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 70fcda1a9049..40bb40d1741b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -567,11 +567,11 @@ asmlinkage long sys_timer_settime(timer_t timer_id, int flags, struct itimerspec __user *old_setting); asmlinkage long sys_timer_delete(timer_t timer_id); asmlinkage long sys_clock_settime(clockid_t which_clock, - const struct timespec __user *tp); + const struct __kernel_timespec __user *tp); asmlinkage long sys_clock_gettime(clockid_t which_clock, - struct timespec __user *tp); + struct __kernel_timespec __user *tp); asmlinkage long sys_clock_getres(clockid_t which_clock, - struct timespec __user *tp); + struct __kernel_timespec __user *tp); asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags, const struct timespec __user *rqtp, struct timespec __user *rmtp); -- cgit v1.2.3 From 01909974b41036a6a8d3907c66cc7b41c9a73da9 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Tue, 13 Mar 2018 21:03:33 -0700 Subject: time: Change nanosleep to safe __kernel_* types Change over clock_nanosleep syscalls to use y2038 safe __kernel_timespec times. This will enable changing over of these syscalls to use new y2038 safe syscalls when the architectures define the CONFIG_64BIT_TIME. Note that nanosleep syscall is deprecated and does not have a plan for making it y2038 safe. But, the syscall should work as before on 64 bit machines and on 32 bit machines, the syscall works correctly until y2038 as before using the existing compat syscall version. There is no new syscall for supporting 64 bit time_t on 32 bit architectures. Cc: linux-api@vger.kernel.org Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/restart_block.h | 7 ++----- include/linux/syscalls.h | 7 ++++--- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h index bcfdb918cd81..5d83d0c1d06c 100644 --- a/include/linux/restart_block.h +++ b/include/linux/restart_block.h @@ -7,6 +7,7 @@ #include #include +#include struct timespec; struct compat_timespec; @@ -15,9 +16,7 @@ struct pollfd; enum timespec_type { TT_NONE = 0, TT_NATIVE = 1, -#ifdef CONFIG_COMPAT TT_COMPAT = 2, -#endif }; /* @@ -40,10 +39,8 @@ struct restart_block { clockid_t clockid; enum timespec_type type; union { - struct timespec __user *rmtp; -#ifdef CONFIG_COMPAT + struct __kernel_timespec __user *rmtp; struct compat_timespec __user *compat_rmtp; -#endif }; u64 expires; } nanosleep; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 40bb40d1741b..c9a2a2601852 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -536,7 +536,8 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); /* kernel/hrtimer.c */ -asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp); +asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp, + struct __kernel_timespec __user *rmtp); /* kernel/itimer.c */ asmlinkage long sys_getitimer(int which, struct itimerval __user *value); @@ -573,8 +574,8 @@ asmlinkage long sys_clock_gettime(clockid_t which_clock, asmlinkage long sys_clock_getres(clockid_t which_clock, struct __kernel_timespec __user *tp); asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags, - const struct timespec __user *rqtp, - struct timespec __user *rmtp); + const struct __kernel_timespec __user *rqtp, + struct __kernel_timespec __user *rmtp); /* kernel/printk.c */ asmlinkage long sys_syslog(int type, char __user *buf, int len); -- cgit v1.2.3 From e21db6f69a95b846ff04e31fe0a86004cbd000d7 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Tue, 17 Apr 2018 23:18:48 -0700 Subject: tcp: track total bytes delivered with ECN CE marks Introduce a new delivered_ce stat in tcp socket to estimate number of packets being marked with CE bits. The estimation is done via ACKs with ECE bit. Depending on the actual receiver behavior, the estimation could have biases. Since the TCP sender can't really see the CE bit in the data path, so the sender is technically counting packets marked delivered with the "ECE / ECN-Echo" flag set. With RFC3168 ECN, because the ECE bit is sticky, this count can drastically overestimate the nummber of CE-marked data packets With DCTCP-style ECN this should be reasonably precise unless there is loss in the ACK path, in which case it's not precise. With AccECN proposal this can be made still more precise, even in the case some degree of ACK loss. However this is sender's best estimate of CE information. Signed-off-by: Yuchung Cheng Reviewed-by: Neal Cardwell Reviewed-by: Soheil Hassas Yeganeh Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 8f4c54986f97..20585d5c4e1c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -281,6 +281,7 @@ struct tcp_sock { * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ u32 delivered; /* Total data packets delivered incl. rexmits */ + u32 delivered_ce; /* Like the above but only ECE marked packets */ u32 lost; /* Total data packets lost incl. rexmits */ u32 app_limited; /* limited until "delivered" reaches this val */ u64 first_tx_mstamp; /* start of window send phase */ -- cgit v1.2.3 From 88078d98d1bb085d72af8437707279e203524fa5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Apr 2018 11:43:15 -0700 Subject: net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends After working on IP defragmentation lately, I found that some large packets defeat CHECKSUM_COMPLETE optimization because of NIC adding zero paddings on the last (small) fragment. While removing the padding with pskb_trim_rcsum(), we set skb->ip_summed to CHECKSUM_NONE, forcing a full csum validation, even if all prior fragments had CHECKSUM_COMPLETE set. We can instead compute the checksum of the part we are trimming, usually smaller than the part we keep. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9065477ed255..d274059529eb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3131,6 +3131,7 @@ static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) return skb->data; } +int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim @@ -3144,9 +3145,7 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (likely(len >= skb->len)) return 0; - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = CHECKSUM_NONE; - return __pskb_trim(skb, len); + return pskb_trim_rcsum_slow(skb, len); } static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len) -- cgit v1.2.3 From eb3f595dab40b61011c5f123507a7db2df6f0e65 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 18 Apr 2018 15:55:58 -0700 Subject: bpf: btf: Validate type reference After collecting all btf_type in the first pass in an earlier patch, the second pass (in this patch) can validate the reference types (e.g. the referring type does exist and it does not refer to itself). While checking the reference type, it also gathers other information (e.g. the size of an array). This info will be useful in checking the struct's members in a later patch. They will also be useful in doing pretty print later. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/btf.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 include/linux/btf.h (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h new file mode 100644 index 000000000000..f14b60368753 --- /dev/null +++ b/include/linux/btf.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#ifndef _LINUX_BTF_H +#define _LINUX_BTF_H 1 + +#include + +struct btf; +struct btf_type; + +/* Figure out the size of a type_id. If type_id is a modifier + * (e.g. const), it will be resolved to find out the type with size. + * + * For example: + * In describing "const void *", type_id is "const" and "const" + * refers to "void *". The return type will be "void *". + * + * If type_id is a simple "int", then return type will be "int". + * + * @btf: struct btf object + * @type_id: Find out the size of type_id. The type_id of the return + * type is set to *type_id. + * @ret_size: It can be NULL. If not NULL, the size of the return + * type is set to *ret_size. + * Return: The btf_type (resolved to another type with size info if needed). + * NULL is returned if type_id itself does not have size info + * (e.g. void) or it cannot be resolved to another type that + * has size info. + * *type_id and *ret_size will not be changed in the + * NULL return case. + */ +const struct btf_type *btf_type_id_size(const struct btf *btf, + u32 *type_id, + u32 *ret_size); + +#endif -- cgit v1.2.3 From b00b8daec828dd59af7d1f7a42acd6e5867f80c6 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 18 Apr 2018 15:56:00 -0700 Subject: bpf: btf: Add pretty print capability for data with BTF type info This patch adds pretty print capability for data with BTF type info. The current usage is to allow pretty print for a BPF map. The next few patches will allow a read() on a pinned map with BTF type info for its key and value. This patch uses the seq_printf() infra. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/btf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index f14b60368753..d8bdab0280ba 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -33,5 +33,7 @@ struct btf_type; const struct btf_type *btf_type_id_size(const struct btf *btf, u32 *type_id, u32 *ret_size); +void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, + struct seq_file *m); #endif -- cgit v1.2.3 From f56a653c1fd13a197076dec4461c656fd2adec73 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 18 Apr 2018 15:56:01 -0700 Subject: bpf: btf: Add BPF_BTF_LOAD command This patch adds a BPF_BTF_LOAD command which 1) loads and verifies the BTF (implemented in earlier patches) 2) returns a BTF fd to userspace. In the next patch, the BTF fd can be specified during BPF_MAP_CREATE. It currently limits to CAP_SYS_ADMIN. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/btf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index d8bdab0280ba..a7c7072535ea 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -8,7 +8,11 @@ struct btf; struct btf_type; +union bpf_attr; +void btf_put(struct btf *btf); +int btf_new_fd(const union bpf_attr *attr); +struct btf *btf_get_by_fd(int fd); /* Figure out the size of a type_id. If type_id is a modifier * (e.g. const), it will be resolved to find out the type with size. * -- cgit v1.2.3 From 60197cfb6e11ffc03aa0ed23765b2f7e70b2e2d4 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 18 Apr 2018 15:56:02 -0700 Subject: bpf: btf: Add BPF_OBJ_GET_INFO_BY_FD support to BTF fd This patch adds BPF_OBJ_GET_INFO_BY_FD support to BTF fd. The original BTF data, which was used to create the BTF fd during the earlier BPF_BTF_LOAD call, will be returned. The userspace is expected to allocate buffer to info.info and the buffer size is set to info.info_len before calling BPF_OBJ_GET_INFO_BY_FD. The original BTF data is copied to the userspace buffer (info.info). Only upto the user's specified info.info_len will be copied. The original BTF data size is set to info.info_len. The userspace needs to check if it is bigger than its allocated buffer size. If it is, the userspace should realloc with the kernel-returned info.info_len and call the BPF_OBJ_GET_INFO_BY_FD again. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/btf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index a7c7072535ea..a966dc6d61ee 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -10,9 +10,14 @@ struct btf; struct btf_type; union bpf_attr; +extern const struct file_operations btf_fops; + void btf_put(struct btf *btf); int btf_new_fd(const union bpf_attr *attr); struct btf *btf_get_by_fd(int fd); +int btf_get_info_by_fd(const struct btf *btf, + const union bpf_attr *attr, + union bpf_attr __user *uattr); /* Figure out the size of a type_id. If type_id is a modifier * (e.g. const), it will be resolved to find out the type with size. * -- cgit v1.2.3 From a26ca7c982cb576749cbdd01e8ecde4bf010d60a Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 18 Apr 2018 15:56:03 -0700 Subject: bpf: btf: Add pretty print support to the basic arraymap This patch adds pretty print support to the basic arraymap. Support for other bpf maps can be added later. This patch adds new attrs to the BPF_MAP_CREATE command to allow specifying the btf_fd, btf_key_id and btf_value_id. The BPF_MAP_CREATE can then associate the btf to the map if the creating map supports BTF. A BTF supported map needs to implement two new map ops, map_seq_show_elem() and map_check_btf(). This patch has implemented these new map ops for the basic arraymap. It also adds file_operations, bpffs_map_fops, to the pinned map such that the pinned map can be opened and read. After that, the user has an intuitive way to do "cat bpffs/pathto/a-pinned-map" instead of getting an error. bpffs_map_fops should not be extended further to support other operations. Other operations (e.g. write/key-lookup...) should be realized by the userspace tools (e.g. bpftool) through the BPF_OBJ_GET_INFO_BY_FD, map's lookup/update interface...etc. Follow up patches will allow the userspace to obtain the BTF from a map-fd. Here is a sample output when reading a pinned arraymap with the following map's value: struct map_value { int count_a; int count_b; }; cat /sys/fs/bpf/pinned_array_map: 0: {1,2} 1: {3,4} 2: {5,6} ... Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 95a7abd0ee92..ee5275e7d4df 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -22,6 +22,8 @@ struct perf_event; struct bpf_prog; struct bpf_map; struct sock; +struct seq_file; +struct btf; /* map is generic key/value storage optionally accesible by eBPF programs */ struct bpf_map_ops { @@ -43,10 +45,14 @@ struct bpf_map_ops { void (*map_fd_put_ptr)(void *ptr); u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); + void (*map_seq_show_elem)(struct bpf_map *map, void *key, + struct seq_file *m); + int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf, + u32 key_type_id, u32 value_type_id); }; struct bpf_map { - /* 1st cacheline with read-mostly members of which some + /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). */ const struct bpf_map_ops *ops ____cacheline_aligned; @@ -62,10 +68,13 @@ struct bpf_map { u32 pages; u32 id; int numa_node; + u32 btf_key_id; + u32 btf_value_id; + struct btf *btf; bool unpriv_array; - /* 7 bytes hole */ + /* 55 bytes hole */ - /* 2nd cacheline with misc members to avoid false sharing + /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ struct user_struct *user ____cacheline_aligned; @@ -100,6 +109,11 @@ static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) return container_of(map, struct bpf_offloaded_map, map); } +static inline bool bpf_map_support_seq_show(const struct bpf_map *map) +{ + return map->ops->map_seq_show_elem && map->ops->map_check_btf; +} + extern const struct bpf_map_ops bpf_map_offload_ops; /* function argument constraints */ -- cgit v1.2.3 From 9e4d60938a2b2aae3c2c213c923d9eb8d0a87ba2 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 19 Apr 2018 01:02:50 +0200 Subject: net: phy: mdio-gpio: Remove reset function The platform data can contain a function to call to reset the bit banging interface. It is not used, so remove it. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/platform_data/mdio-gpio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h index 11f00cdabe3d..6e8f01a570f2 100644 --- a/include/linux/platform_data/mdio-gpio.h +++ b/include/linux/platform_data/mdio-gpio.h @@ -26,8 +26,6 @@ struct mdio_gpio_platform_data { u32 phy_mask; u32 phy_ignore_ta_mask; int irqs[PHY_MAX_ADDR]; - /* reset callback */ - int (*reset)(struct mii_bus *bus); }; #endif /* __LINUX_MDIO_GPIO_H */ -- cgit v1.2.3 From a3283e2576736463e07ddc684efb2e587a3bbda2 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 19 Apr 2018 01:02:51 +0200 Subject: net: phy: mdio-bitbang: Remove reset support The mdio-gpio driver was the only user of the interface reset option. Since it no longer uses it, remove it from the bit banging code. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mdio-bitbang.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdio-bitbang.h b/include/linux/mdio-bitbang.h index a8ac9cfa014c..5d71e8a8500f 100644 --- a/include/linux/mdio-bitbang.h +++ b/include/linux/mdio-bitbang.h @@ -33,8 +33,6 @@ struct mdiobb_ops { struct mdiobb_ctrl { const struct mdiobb_ops *ops; - /* reset callback */ - int (*reset)(struct mii_bus *bus); }; /* The returned bus is not yet registered with the phy layer. */ -- cgit v1.2.3 From c1b3eb04682f80af74572aa25601dbb555c6bc6e Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 19 Apr 2018 01:02:52 +0200 Subject: net: phy: mdio-gpio: remove support for ignoring turn around This is not needed any more by devices using platform data, so remove it. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/platform_data/mdio-gpio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h index 6e8f01a570f2..b8f914a30126 100644 --- a/include/linux/platform_data/mdio-gpio.h +++ b/include/linux/platform_data/mdio-gpio.h @@ -24,7 +24,6 @@ struct mdio_gpio_platform_data { bool mdo_active_low; u32 phy_mask; - u32 phy_ignore_ta_mask; int irqs[PHY_MAX_ADDR]; }; -- cgit v1.2.3 From 185a16b60a239f9db3fe8b8ce931a2fd61330853 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 19 Apr 2018 01:02:53 +0200 Subject: net: phy: mdio-gpio: remove support for phy mask This is not needed any more by devices using platform data, so remove it. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/platform_data/mdio-gpio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h index b8f914a30126..7d55dfef56dc 100644 --- a/include/linux/platform_data/mdio-gpio.h +++ b/include/linux/platform_data/mdio-gpio.h @@ -23,7 +23,6 @@ struct mdio_gpio_platform_data { bool mdio_active_low; bool mdo_active_low; - u32 phy_mask; int irqs[PHY_MAX_ADDR]; }; -- cgit v1.2.3 From 68abb4f25d7eaf4d5f40108aa748621ddab68209 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 19 Apr 2018 01:02:54 +0200 Subject: net: phy: mdio-gpio: Remove support for IRQs in platform data No current devices use IRQs in platform data, so remove support for it. The MDIO core will also initialise the new bus such that all addresses are polled, so remove the unneeded re-initialisation. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/platform_data/mdio-gpio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h index 7d55dfef56dc..af3be0c4ff9b 100644 --- a/include/linux/platform_data/mdio-gpio.h +++ b/include/linux/platform_data/mdio-gpio.h @@ -22,8 +22,6 @@ struct mdio_gpio_platform_data { bool mdc_active_low; bool mdio_active_low; bool mdo_active_low; - - int irqs[PHY_MAX_ADDR]; }; #endif /* __LINUX_MDIO_GPIO_H */ -- cgit v1.2.3 From c82fc4814a93f36c9b536b5af8dd617e4ee1380f Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 19 Apr 2018 01:02:55 +0200 Subject: net: phy: mdio-gpio: Swap to using gpio descriptors This simplifies the code, removing the need to handle active low flags, etc. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/platform_data/mdio-gpio.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h index af3be0c4ff9b..bd91fa98a3aa 100644 --- a/include/linux/platform_data/mdio-gpio.h +++ b/include/linux/platform_data/mdio-gpio.h @@ -15,13 +15,9 @@ struct mdio_gpio_platform_data { /* GPIO numbers for bus pins */ - unsigned int mdc; - unsigned int mdio; - unsigned int mdo; - - bool mdc_active_low; - bool mdio_active_low; - bool mdo_active_low; + struct gpio_desc *mdc; + struct gpio_desc *mdio; + struct gpio_desc *mdo; }; #endif /* __LINUX_MDIO_GPIO_H */ -- cgit v1.2.3 From fb78a95e22123da57cb79b98bdc62eb33965ca8a Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 19 Apr 2018 01:02:58 +0200 Subject: net: phy: mdio-gpio: Add #defines for the GPIO index's The GPIOs are described in device tree using a list, without names. Add defines to indicate what each index in the list means. These defines should also be used by platform devices passing GPIOs via a GPIO lookup table. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mdio-gpio.h | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 include/linux/mdio-gpio.h (limited to 'include/linux') diff --git a/include/linux/mdio-gpio.h b/include/linux/mdio-gpio.h new file mode 100644 index 000000000000..cea443a672cb --- /dev/null +++ b/include/linux/mdio-gpio.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_MDIO_GPIO_H +#define __LINUX_MDIO_GPIO_H + +#define MDIO_GPIO_MDC 0 +#define MDIO_GPIO_MDIO 1 +#define MDIO_GPIO_MDO 2 + +#endif -- cgit v1.2.3 From 0207dd1173fe31c153ffd439c4bb33d1341829b1 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 19 Apr 2018 01:02:59 +0200 Subject: net: phy: mdio-gpio: Remove redundant platform data header The platform data header file is now unused. Remove it, but add an extra include which it brought in. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/platform_data/mdio-gpio.h | 23 ----------------------- 1 file changed, 23 deletions(-) delete mode 100644 include/linux/platform_data/mdio-gpio.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h deleted file mode 100644 index bd91fa98a3aa..000000000000 --- a/include/linux/platform_data/mdio-gpio.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * MDIO-GPIO bus platform data structures - * - * Copyright (C) 2008, Paulius Zaleckas - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ - -#ifndef __LINUX_MDIO_GPIO_H -#define __LINUX_MDIO_GPIO_H - -#include - -struct mdio_gpio_platform_data { - /* GPIO numbers for bus pins */ - struct gpio_desc *mdc; - struct gpio_desc *mdio; - struct gpio_desc *mdo; -}; - -#endif /* __LINUX_MDIO_GPIO_H */ -- cgit v1.2.3 From a597043304a13defc646bb1f16514e4903b36c3c Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 10 Apr 2018 15:06:05 +0200 Subject: clk: Remove clk_init_cb typedef Since commit c08ee14cc6634457 ("clk: ti: change clock init to use generic of_clk_init"), there is only a single (private) user left of the (public) clk_init_cb typedef. Hence expand its single user in the core clock code, and remove the typedef. Signed-off-by: Geert Uytterhoeven Signed-off-by: Michael Turquette Link: lkml.kernel.org/r/1523365565-17124-1-git-send-email-geert+renesas@glider.be --- include/linux/clk-provider.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 210a890008f9..410a8627b8c0 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -802,8 +802,6 @@ unsigned long clk_hw_round_rate(struct clk_hw *hw, unsigned long rate); struct of_device_id; -typedef void (*of_clk_init_cb_t)(struct device_node *); - struct clk_onecell_data { struct clk **clks; unsigned int clk_num; -- cgit v1.2.3 From 669ca0303ac93adba0e046d414165250861efdb7 Mon Sep 17 00:00:00 2001 From: ryang Date: Thu, 19 Apr 2018 12:18:50 -0400 Subject: regulator: tps6586x: Add support for TPS658624 This version is exists in the Samsung Galaxy Tab 10.1 which is based on the Nvidia Tegra 2 board. The TPS658624 has the same SM2 voltage table as TPS658623. Signed-off-by: ryang Acked-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/tps6586x.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps6586x.h b/include/linux/mfd/tps6586x.h index 2fe68e481230..b19c2801a30e 100644 --- a/include/linux/mfd/tps6586x.h +++ b/include/linux/mfd/tps6586x.h @@ -18,6 +18,7 @@ #define TPS658621A 0x15 #define TPS658621CD 0x2c #define TPS658623 0x1b +#define TPS658624 0x0a #define TPS658640 0x01 #define TPS658640v2 0x02 #define TPS658643 0x03 -- cgit v1.2.3 From 02f3703934a42417021405ef336fe45add13c3d1 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Wed, 18 Apr 2018 08:54:18 -0700 Subject: regulator: Don't return or expect -errno from of_map_mode() In of_get_regulation_constraints() we were taking the result of of_map_mode() (an unsigned int) and assigning it to an int. We were then checking whether this value was -EINVAL. Some implementers of of_map_mode() were returning -EINVAL (even though the return type of their function needed to be unsigned int) because they needed to signal an error back to of_get_regulation_constraints(). In general in the regulator framework the mode is always referred to as an unsigned int. While we could fix this to be a signed int (the highest value we store in there right now is 0x8), it's actually pretty clean to just define the regulator mode 0x0 (the lack of any bits set) as an invalid mode. Let's do that. Fixes: 5e5e3a42c653 ("regulator: of: Add support for parsing initial and suspend modes") Suggested-by: Javier Martinez Canillas Signed-off-by: Douglas Anderson Reviewed-by: Javier Martinez Canillas Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index df176d7c2b87..25602afd4844 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -80,6 +80,7 @@ struct regmap; * These modes can be OR'ed together to make up a mask of valid register modes. */ +#define REGULATOR_MODE_INVALID 0x0 #define REGULATOR_MODE_FAST 0x1 #define REGULATOR_MODE_NORMAL 0x2 #define REGULATOR_MODE_IDLE 0x4 -- cgit v1.2.3 From 21fc538d817ce671f1a28a03996c715247c2ac89 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 13 Apr 2018 13:58:00 +0200 Subject: y2038: ipc: Use __kernel_timespec This is a preparatation for changing over __kernel_timespec to 64-bit times, which involves assigning new system call numbers for mq_timedsend(), mq_timedreceive() and semtimedop() for compatibility with future y2038 proof user space. The existing ABIs will remain available through compat code. Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index c9a2a2601852..b92cb79d38c3 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -680,8 +680,8 @@ asmlinkage long sys_sysinfo(struct sysinfo __user *info); /* ipc/mqueue.c */ asmlinkage long sys_mq_open(const char __user *name, int oflag, umode_t mode, struct mq_attr __user *attr); asmlinkage long sys_mq_unlink(const char __user *name); -asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct timespec __user *abs_timeout); -asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct timespec __user *abs_timeout); +asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct __kernel_timespec __user *abs_timeout); +asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct __kernel_timespec __user *abs_timeout); asmlinkage long sys_mq_notify(mqd_t mqdes, const struct sigevent __user *notification); asmlinkage long sys_mq_getsetattr(mqd_t mqdes, const struct mq_attr __user *mqstat, struct mq_attr __user *omqstat); @@ -698,7 +698,7 @@ asmlinkage long sys_semget(key_t key, int nsems, int semflg); asmlinkage long sys_semctl(int semid, int semnum, int cmd, unsigned long arg); asmlinkage long sys_semtimedop(int semid, struct sembuf __user *sops, unsigned nsops, - const struct timespec __user *timeout); + const struct __kernel_timespec __user *timeout); asmlinkage long sys_semop(int semid, struct sembuf __user *sops, unsigned nsops); -- cgit v1.2.3 From c7f1770f369ae0ec632b3ddc2bd6677b0e485128 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 5 Apr 2018 10:54:14 -0400 Subject: media: omap: omap-iommu.h: allow building drivers with COMPILE_TEST Drivers that depend on omap-iommu.h (currently, just omap3isp) need a stub implementation in order to be built with COMPILE_TEST. Acked-by: Sakari Ailus Acked-by: Hans Verkuil Acked-by: Arnd Bergmann Acked-by: Tony Lindgren Signed-off-by: Mauro Carvalho Chehab --- include/linux/omap-iommu.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/omap-iommu.h b/include/linux/omap-iommu.h index c1aede46718b..ce1b7c6283ee 100644 --- a/include/linux/omap-iommu.h +++ b/include/linux/omap-iommu.h @@ -13,7 +13,12 @@ #ifndef _OMAP_IOMMU_H_ #define _OMAP_IOMMU_H_ +#ifdef CONFIG_OMAP_IOMMU extern void omap_iommu_save_ctx(struct device *dev); extern void omap_iommu_restore_ctx(struct device *dev); +#else +static inline void omap_iommu_save_ctx(struct device *dev) {} +static inline void omap_iommu_restore_ctx(struct device *dev) {} +#endif #endif -- cgit v1.2.3 From 809c45a091d93e05c6e9b5d53bb3f1185273286b Mon Sep 17 00:00:00 2001 From: Shahed Shaikh Date: Thu, 19 Apr 2018 05:50:12 -0700 Subject: qed* : Add new TLV to request PF to update MAC in bulletin board There may be a need for VF driver to request PF to explicitly update its bulletin with a MAC address. e.g. When user assigns a MAC address to VF while VF is still down, and PF's bulletin board contains different MAC address, in this case, when VF's interface is brought up, it gets loaded with MAC address from bulletin board which is not desirable. To handle this corner case, we need a new TLV to request PF to update its bulletin board with suggested MAC. This request will be honored only for trusted VFs. Signed-off-by: Shahed Shaikh Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 147d08ccf813..7f9756fe9180 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -352,6 +352,7 @@ struct qed_eth_ops { int (*configure_arfs_searcher)(struct qed_dev *cdev, enum qed_filter_config_mode mode); int (*get_coalesce)(struct qed_dev *cdev, u16 *coal, void *handle); + int (*req_bulletin_update_mac)(struct qed_dev *cdev, u8 *mac); }; const struct qed_eth_ops *qed_get_eth_ops(void); -- cgit v1.2.3 From 1827b0678863bc97a1653fdf5308762b2aefcd56 Mon Sep 17 00:00:00 2001 From: Phil Elwell Date: Thu, 19 Apr 2018 17:59:39 +0100 Subject: lan78xx: Read LED states from Device Tree Add support for DT property "microchip,led-modes", a vector of zero to four cells (u32s) in the range 0-15, each of which sets the mode for one of the LEDs. Some possible values are: 0=link/activity 1=link1000/activity 2=link100/activity 3=link10/activity 4=link100/1000/activity 5=link10/1000/activity 6=link10/100/activity 14=off 15=on These values are given symbolic constants in a dt-bindings header. Also use the presence of the DT property to indicate that the LEDs should be enabled - necessary in the event that no valid OTP or EEPROM is available. Signed-off-by: Phil Elwell Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/microchipphy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/microchipphy.h b/include/linux/microchipphy.h index eb492d47f717..8e4015e7f8d3 100644 --- a/include/linux/microchipphy.h +++ b/include/linux/microchipphy.h @@ -70,4 +70,7 @@ #define LAN88XX_MMD3_CHIP_ID (32877) #define LAN88XX_MMD3_CHIP_REV (32878) +/* Registers specific to the LAN7800/LAN7850 embedded phy */ +#define LAN78XX_PHY_LED_MODE_SELECT (0x1D) + #endif /* _MICROCHIPPHY_H */ -- cgit v1.2.3 From 8af70cd2ca508061088d5059ba8a8218aca7ddf1 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 20 Apr 2018 10:14:27 -0700 Subject: memory: aemif: add support for board files Currently aemif is supported in two places separately. By the platform driver in drivers/memory and by a hand crafted driver in mach-davinci. We want to drop the latter but also keep the legacy mode. Add support for board files to the aemif driver. The new structure in platform data currently only contains the chip select number, since currently existing users don't require anything else, but it can be extended in the future. While extending the platform data struct, add kernel docs describing its members. Signed-off-by: Bartosz Golaszewski Signed-off-by: Santosh Shilimkar --- include/linux/platform_data/ti-aemif.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/ti-aemif.h b/include/linux/platform_data/ti-aemif.h index ac72e115093c..e6407bafcbf8 100644 --- a/include/linux/platform_data/ti-aemif.h +++ b/include/linux/platform_data/ti-aemif.h @@ -16,8 +16,33 @@ #include +/** + * struct aemif_abus_data - Async bus configuration parameters. + * + * @cs - Chip-select number. + */ +struct aemif_abus_data { + u32 cs; +}; + +/** + * struct aemif_platform_data - Data to set up the TI aemif driver. + * + * @dev_lookup: of_dev_auxdata passed to of_platform_populate() for aemif + * subdevices. + * @cs_offset: Lowest allowed chip-select number. + * @abus_data: Array of async bus configuration entries. + * @num_abus_data: Number of abus entries. + * @sub_devices: Array of platform subdevices. + * @num_sub_devices: Number of subdevices. + */ struct aemif_platform_data { struct of_dev_auxdata *dev_lookup; + u32 cs_offset; + struct aemif_abus_data *abus_data; + size_t num_abus_data; + struct platform_device *sub_devices; + size_t num_sub_devices; }; #endif /* __TI_DAVINCI_AEMIF_DATA_H__ */ -- cgit v1.2.3 From dbef91ec5482239055dd2db8ec656fc13d382add Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Wed, 18 Apr 2018 01:35:06 +0200 Subject: scsi: ilog2: create truly constant version for sparse Sparse emits errors about ilog2() in array indices because of the use of __ilog2_32() and __ilog2_64(), rightly so (https://www.spinics.net/lists/linux-sparse/msg03471.html). Create a const_ilog2() variant that works with sparse for this scenario. (Note: checkpatch.pl complains about missing parentheses, but that appears to be a false positive. I can get rid of the warning simply by inserting whitespace, making checkpatch "see" the whole macro). Signed-off-by: Martin Wilck Signed-off-by: Martin K. Petersen --- include/linux/log2.h | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/log2.h b/include/linux/log2.h index 41a1ae010993..2af7f77866d0 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -72,16 +72,13 @@ unsigned long __rounddown_pow_of_two(unsigned long n) } /** - * ilog2 - log base 2 of 32-bit or a 64-bit unsigned value + * const_ilog2 - log base 2 of 32-bit or a 64-bit constant unsigned value * @n: parameter * - * constant-capable log of base 2 calculation - * - this can be used to initialise global variables from constant data, hence - * the massive ternary operator construction - * - * selects the appropriately-sized optimised version depending on sizeof(n) + * Use this where sparse expects a true constant expression, e.g. for array + * indices. */ -#define ilog2(n) \ +#define const_ilog2(n) \ ( \ __builtin_constant_p(n) ? ( \ (n) < 2 ? 0 : \ @@ -147,10 +144,26 @@ unsigned long __rounddown_pow_of_two(unsigned long n) (n) & (1ULL << 4) ? 4 : \ (n) & (1ULL << 3) ? 3 : \ (n) & (1ULL << 2) ? 2 : \ - 1 ) : \ - (sizeof(n) <= 4) ? \ - __ilog2_u32(n) : \ - __ilog2_u64(n) \ + 1) : \ + -1) + +/** + * ilog2 - log base 2 of 32-bit or a 64-bit unsigned value + * @n: parameter + * + * constant-capable log of base 2 calculation + * - this can be used to initialise global variables from constant data, hence + * the massive ternary operator construction + * + * selects the appropriately-sized optimised version depending on sizeof(n) + */ +#define ilog2(n) \ +( \ + __builtin_constant_p(n) ? \ + const_ilog2(n) : \ + (sizeof(n) <= 4) ? \ + __ilog2_u32(n) : \ + __ilog2_u64(n) \ ) /** -- cgit v1.2.3 From f134fbbb4ff813dd227c9ce40b5c0b2078a77b07 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Sat, 21 Apr 2018 08:54:40 +1000 Subject: mtd: spi-nor: clear Winbond Extended Address Reg on switch to 3-byte addressing. Winbond spi-nor flash 32MB and larger have an 'Extended Address Register' as one option for addressing beyond 16MB (Macronix has the same concept, Spansion has EXTADD bits in the Bank Address Register). According to section 8.2.7 Write Extended Address Register (C5h) of the Winbond W25Q256FV data sheet (256M-BIT SPI flash) The Extended Address Register is only effective when the device is in the 3-Byte Address Mode. When the device operates in the 4-Byte Address Mode (ADS=1), any command with address input of A31-A24 will replace the Extended Address Register values. It is recommended to check and update the Extended Address Register if necessary when the device is switched from 4-Byte to 3-Byte Address Mode. So the documentation suggests clearing the EAR after switching to 3-byte mode. Experimentation shows that the EAR is *always* one after the switch to 3-byte mode, so clearing the EAR is mandatory at shutdown for a subsequent 3-byte-addressed reboot to work. Note that some SOCs (e.g. MT7621) do not assert a reset line at normal reboot, so we cannot rely on hardware reset. The MT7621 does assert a reset line at watchdog-reset. Acked-by: Marek Vasut Signed-off-by: NeilBrown Signed-off-by: Boris Brezillon --- include/linux/mtd/spi-nor.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index de36969eb359..e60da0d34cc1 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -62,6 +62,8 @@ #define SPINOR_OP_RDCR 0x35 /* Read configuration register */ #define SPINOR_OP_RDFSR 0x70 /* Read flag status register */ #define SPINOR_OP_CLFSR 0x50 /* Clear flag status register */ +#define SPINOR_OP_RDEAR 0xc8 /* Read Extended Address Register */ +#define SPINOR_OP_WREAR 0xc5 /* Write Extended Address Register */ /* 4-byte address opcodes - used on Spansion and some Macronix flashes. */ #define SPINOR_OP_READ_4B 0x13 /* Read data bytes (low frequency) */ -- cgit v1.2.3 From a47060cf40c6c8e6e125692f5d73ceea173b12b7 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 6 Apr 2018 15:31:49 +0200 Subject: usb: audio-v2: Correct the comment for struct uac_clock_selector_descriptor The comment in UAC2 clock selector descriptor definition mentions the bAssocTerminal after baCSourceID[], but it doesn't exist in the actual definition. Let's correct it. Fixes: 5dd360ebd832 ("include/linux/usb/audio-v2.h: add more UAC2 details") Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/audio-v2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index aaafecf073ff..49699255cfd3 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -94,7 +94,7 @@ struct uac_clock_selector_descriptor { __u8 bClockID; __u8 bNrInPins; __u8 baCSourceID[]; - /* bmControls, bAssocTerminal and iClockSource omitted */ + /* bmControls and iClockSource omitted */ } __attribute__((packed)); /* 4.7.2.3 Clock Multiplier Descriptor */ -- cgit v1.2.3 From 60b9f942bc059913bcdac90d5b225f557438b5c5 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 18 Apr 2018 11:26:19 +0200 Subject: USB: phy: drop unused legacy controller-phy bind helper Drop the unused legacy usb_bind_phy() helper whose last user was removed in 2016 when OMAP moved to device-tree boot (9080b8dc761a ("ARM: OMAP2+: Remove legacy usb-host.c platform init code")). Note that this means that for the last couple of years the phy_bind_list has been empty (when using mainline kernels) and that consequently all phy lookups using the usb_get_phy_dev() interface have failed with -ENODEV. This helper along with its current users will be removed by follow-on patches. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/phy.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index b7a2625947f5..ac5a079161e1 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -242,8 +242,6 @@ extern struct usb_phy *devm_usb_get_phy_by_node(struct device *dev, struct device_node *node, struct notifier_block *nb); extern void usb_put_phy(struct usb_phy *); extern void devm_usb_put_phy(struct device *dev, struct usb_phy *x); -extern int usb_bind_phy(const char *dev_name, u8 index, - const char *phy_dev_name); extern void usb_phy_set_event(struct usb_phy *x, unsigned long event); extern void usb_phy_set_charger_current(struct usb_phy *usb_phy, unsigned int mA); @@ -293,12 +291,6 @@ static inline void devm_usb_put_phy(struct device *dev, struct usb_phy *x) { } -static inline int usb_bind_phy(const char *dev_name, u8 index, - const char *phy_dev_name) -{ - return -EOPNOTSUPP; -} - static inline void usb_phy_set_event(struct usb_phy *x, unsigned long event) { } -- cgit v1.2.3 From bc40f53417410be18298c5b5dbf5bcae9588d84f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 18 Apr 2018 11:26:20 +0200 Subject: USB: core: hcd: drop support for legacy phys Drop support for looking up and initialising legacy phys in USB core, something which hasn't been used by a mainline kernel since commit 9080b8dc761a ("ARM: OMAP2+: Remove legacy usb-host.c platform init code"). Specifically, since that commit usb_get_phy_dev() have always returned -ENODEV and consequently this code has not been used. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index aef50cb2ed1b..e33009c77840 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -150,7 +150,6 @@ struct usb_hcd { unsigned rh_pollable:1; /* may we poll the root hub? */ unsigned msix_enabled:1; /* driver has MSI-X enabled? */ unsigned msi_enabled:1; /* driver has MSI enabled? */ - unsigned remove_phy:1; /* auto-remove USB phy */ /* * do not manage the PHY state in the HCD core, instead let the driver * handle this (for example if the PHY can only be turned on after a -- cgit v1.2.3 From c3c0ac70c77d34c03e9600170932b2c28478795f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 18 Apr 2018 11:26:24 +0200 Subject: USB: phy: drop legacy board-file support The legacy interface for associating controllers with phys from board files and platform code has been unused since commit 9080b8dc761a ("ARM: OMAP2+: Remove legacy usb-host.c platform init code"). Since then, all calls to usb_get_phy_dev() and its devres version have been returning -ENODEV. Now that the final calls to these functions have been removed, we can drop this legacy lookup interface altogether. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/phy.h | 28 ---------------------------- 1 file changed, 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index ac5a079161e1..e4de6bc1f69b 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -157,22 +157,6 @@ struct usb_phy { enum usb_charger_type (*charger_detect)(struct usb_phy *x); }; -/** - * struct usb_phy_bind - represent the binding for the phy - * @dev_name: the device name of the device that will bind to the phy - * @phy_dev_name: the device name of the phy - * @index: used if a single controller uses multiple phys - * @phy: reference to the phy - * @list: to maintain a linked list of the binding information - */ -struct usb_phy_bind { - const char *dev_name; - const char *phy_dev_name; - u8 index; - struct usb_phy *phy; - struct list_head list; -}; - /* for board-specific init logic */ extern int usb_add_phy(struct usb_phy *, enum usb_phy_type type); extern int usb_add_phy_dev(struct usb_phy *); @@ -234,8 +218,6 @@ usb_phy_vbus_off(struct usb_phy *x) extern struct usb_phy *usb_get_phy(enum usb_phy_type type); extern struct usb_phy *devm_usb_get_phy(struct device *dev, enum usb_phy_type type); -extern struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index); -extern struct usb_phy *devm_usb_get_phy_dev(struct device *dev, u8 index); extern struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev, const char *phandle, u8 index); extern struct usb_phy *devm_usb_get_phy_by_node(struct device *dev, @@ -261,16 +243,6 @@ static inline struct usb_phy *devm_usb_get_phy(struct device *dev, return ERR_PTR(-ENXIO); } -static inline struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index) -{ - return ERR_PTR(-ENXIO); -} - -static inline struct usb_phy *devm_usb_get_phy_dev(struct device *dev, u8 index) -{ - return ERR_PTR(-ENXIO); -} - static inline struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev, const char *phandle, u8 index) { -- cgit v1.2.3 From e8374db15436648411d933b01d929acae0538775 Mon Sep 17 00:00:00 2001 From: Li Jun Date: Mon, 16 Apr 2018 14:54:37 +0800 Subject: usb: typec: tcpm: remove max_snk_mv/ma/mw Since there is no user of max_snk_*, so we can remove them from tcpm. Reviewed-by: Hans de Goede Signed-off-by: Li Jun Reviewed-by: Guenter Roeck Acked-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tcpm.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index f0d839daeaea..f5bda9a0f644 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -62,9 +62,6 @@ enum tcpm_transmit_type { * @snk_pdo: PDO parameters sent to partner as response to * PD_CTRL_GET_SINK_CAP message * @nr_snk_pdo: Number of entries in @snk_pdo - * @max_snk_mv: Maximum acceptable sink voltage in mV - * @max_snk_ma: Maximum sink current in mA - * @max_snk_mw: Maximum required sink power in mW * @operating_snk_mw: * Required operating sink power in mW * @type: Port type (TYPEC_PORT_DFP, TYPEC_PORT_UFP, or @@ -85,9 +82,6 @@ struct tcpc_config { const u32 *snk_vdo; unsigned int nr_snk_vdo; - unsigned int max_snk_mv; - unsigned int max_snk_ma; - unsigned int max_snk_mw; unsigned int operating_snk_mw; enum typec_port_type type; @@ -174,9 +168,6 @@ int tcpm_update_source_capabilities(struct tcpm_port *port, const u32 *pdo, unsigned int nr_pdo); int tcpm_update_sink_capabilities(struct tcpm_port *port, const u32 *pdo, unsigned int nr_pdo, - unsigned int max_snk_mv, - unsigned int max_snk_ma, - unsigned int max_snk_mw, unsigned int operating_snk_mw); void tcpm_vbus_change(struct tcpm_port *port); -- cgit v1.2.3 From ffe95371d2a84f3ad8085656d4fcb2fc926ff7a1 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Thu, 19 Apr 2018 19:05:50 +0300 Subject: usb: define HCD_USB32 speed option for hosts that support USB 3.2 dual-lane Hosts that support USB 3.2 Enhaned SuperSpeed can set their hcd speed to HCD_USB32 to let usb core and host drivers know that the controller supports new USB 3.2 dual-lane features. make sure usb core handle HCD_USB32 hosts correctly, for now similar to HCD_USB32. Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index e33009c77840..34a6ded6f319 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -260,6 +260,7 @@ struct hc_driver { #define HCD_USB25 0x0030 /* Wireless USB 1.0 (USB 2.5)*/ #define HCD_USB3 0x0040 /* USB 3.0 */ #define HCD_USB31 0x0050 /* USB 3.1 */ +#define HCD_USB32 0x0060 /* USB 3.2 */ #define HCD_MASK 0x0070 #define HCD_BH 0x0100 /* URB complete in BH context */ -- cgit v1.2.3 From 013eedb8c56e55549c45df19ca56a029cc804028 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Thu, 19 Apr 2018 19:05:51 +0300 Subject: USB: Add support to store lane count used by USB 3.2 USB 3.2 specification adds Dual-lane support, doubling the maximum SuperSpeedPlus data rate from 10Gbps to 20Gbps. Dual-lane takes into use a second set of rx and tx wires/pins in the Type-C cable and connector. Add "rx_lanes" and "tx_lanes" variables to struct usb_device to store the numer of lanes in use. Number of lanes can be read using the extended port status hub request that was introduced in USB 3.1. Extended port status rx and tx lane count are zero based, maximum lanes supported by non inter-chip (SSIC) USB 3.2 is 2 (dual lane) with rx and tx lane count symmetric. SSIC devices support asymmetric lanes up to 4 lanes per direction. If extended port status is not available then default to one lane. Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 0173597e59aa..beffceec4915 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -551,6 +551,8 @@ struct usb3_lpm_parameters { * @route: tree topology hex string for use with xHCI * @state: device state: configured, not attached, etc. * @speed: device speed: high/full/low (or error) + * @rx_lanes: number of rx lanes in use, USB 3.2 adds dual-lane support + * @tx_lanes: number of tx lanes in use, USB 3.2 adds dual-lane support * @tt: Transaction Translator info; used with low/full speed dev, highspeed hub * @ttport: device port on that tt hub * @toggle: one bit for each endpoint, with ([0] = IN, [1] = OUT) endpoints @@ -624,6 +626,8 @@ struct usb_device { u32 route; enum usb_device_state state; enum usb_device_speed speed; + unsigned int rx_lanes; + unsigned int tx_lanes; struct usb_tt *tt; int ttport; -- cgit v1.2.3 From 143470368efd3f0fb4cbe81aa89f49de8048d8a9 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 Apr 2018 01:02:58 +0300 Subject: usb: tegra: Move utmi-pads reset from ehci-tegra to tegra-phy UTMI pads are shared by USB controllers and reset of UTMI pads is shared with the reset of USB1 controller. Currently reset of UTMI pads is done by the EHCI driver and ChipIdea UDC works because EHCI driver always happen to be probed first. Move reset controls from ehci-tegra to tegra-phy in order to resolve the problem. Signed-off-by: Dmitry Osipenko Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tegra_usb_phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d641ea1660b7..0c5c3ea8b2d7 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -17,6 +17,7 @@ #define __TEGRA_USB_PHY_H #include +#include #include /* @@ -76,6 +77,7 @@ struct tegra_usb_phy { bool is_legacy_phy; bool is_ulpi_phy; int reset_gpio; + struct reset_control *pad_rst; }; void tegra_usb_phy_preresume(struct usb_phy *phy); -- cgit v1.2.3 From c5f78b1fe4e5baf4c4ca30377c2d7e06e2e391ec Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Tue, 27 Mar 2018 11:48:24 +0800 Subject: serial: Introduce UPSTAT_SYNC_FIFO for synchronised FIFOs This change adds a flag to indicate that a UART is has an external means of synchronising its FIFO, without needing CTSRTS or XON/XOFF. This allows us to use the throttle/unthrottle callbacks, without having to claim other methods of flow control. Signed-off-by: Jeremy Kerr Tested-by: Eddie James Tested-by: Joel Stanley Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 1d356105f25a..d224961e1346 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -233,6 +233,7 @@ struct uart_port { #define UPSTAT_AUTORTS ((__force upstat_t) (1 << 2)) #define UPSTAT_AUTOCTS ((__force upstat_t) (1 << 3)) #define UPSTAT_AUTOXOFF ((__force upstat_t) (1 << 4)) +#define UPSTAT_SYNC_FIFO ((__force upstat_t) (1 << 5)) int hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ -- cgit v1.2.3 From ebbaf9ab9ebd69f42b286c7a67cc84571c3d947a Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Tue, 27 Mar 2018 11:48:25 +0800 Subject: serial/8250: export serial8250_read_char Currently, we export serial8250_rx_chars, which does a whole bunch of reads from the 8250 data register, without any form of flow control between reads. An upcoming change to the aspeed vuart driver implements more fine-grained flow control in the interrupt handler, requiring character-at-a-time control over the rx path. This change exports serial8250_read_char to allow this. Signed-off-by: Jeremy Kerr Tested-by: Eddie James Tested-by: Joel Stanley Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index a27ef5f56431..76b9db71e489 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -163,6 +163,7 @@ extern void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); extern int fsl8250_handle_irq(struct uart_port *port); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); unsigned char serial8250_rx_chars(struct uart_8250_port *up, unsigned char lsr); +void serial8250_read_char(struct uart_8250_port *up, unsigned char lsr); void serial8250_tx_chars(struct uart_8250_port *up); unsigned int serial8250_modem_status(struct uart_8250_port *up); void serial8250_init_port(struct uart_8250_port *up); -- cgit v1.2.3 From c1c734cb1f54b062f7e67ffc9656d82f5b412b9c Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 23 Mar 2018 10:58:31 -0700 Subject: serial: core: Make sure compiler barfs for 16-byte earlycon names As part of bringup I ended up wanting to call an earlycon driver by a name that was exactly 16-bytes big, specifically "qcom_geni_serial". Unfortunately, when I tried this I found that things compiled just fine. They just didn't work. Specifically the compiler felt perfectly justified in initting the ".name" field of "struct earlycon_id" with the full 16-bytes and just skipping the '\0'. Needless to say, that behavior didn't seem ideal, but I guess someone must have allowed it for a reason. One way to fix this is to shorten the name field to 15 bytes and then add an extra byte after that nobody touches. This should always be initted to 0 and we're golden. There are, of course, other ways to fix this too. We could audit all the users of the "name" field and make them stop at both null termination or at 16 bytes. We could also just make the name field much bigger so that we're not likely to run into this. ...but both seem like we'll just hit the bug again. Signed-off-by: Douglas Anderson Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index d224961e1346..d2a2e4bc2435 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -349,7 +349,8 @@ struct earlycon_device { }; struct earlycon_id { - char name[16]; + char name[15]; + char name_term; /* In case compiler didn't '\0' term name */ char compatible[128]; int (*setup)(struct earlycon_device *, const char *options); } __aligned(32); -- cgit v1.2.3 From 05e6557b8ed833546ee2b66ce6b58fecf09f439e Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 29 Mar 2018 15:26:48 +1100 Subject: staging: lustre: add container_of_safe() Luster has a container_of0() function which is similar to container_of() but passes an IS_ERR_OR_NULL() pointer through unchanged. This could be generally useful: bcache at last has a similar function. Naming is hard, but the precedent set by hlist_entry_safe() suggests a _safe suffix might be most consistent. So add container_of_safe() to kernel.h, and replace all occurrences of container_of0() with one of - list_first_entry, list_next_entry, when that is a better fit, - container_of(), when the pointer is used as a validpointer in surrounding code, - container_of_safe() when there is no obviously better alternative. Signed-off-by: NeilBrown Reviewed-by: James Simmons Signed-off-by: Greg Kroah-Hartman --- include/linux/kernel.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 6a1eb0b0aad9..58d6645b1425 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -964,6 +964,22 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } "pointer type mismatch in container_of()"); \ ((type *)(__mptr - offsetof(type, member))); }) +/** + * container_of_safe - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + * If IS_ERR_OR_NULL(ptr), ptr is returned unchanged. + */ +#define container_of_safe(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + IS_ERR_OR_NULL(ptr) ? ERR_CAST(ptr) : \ + ((type *)(__mptr - offsetof(type, member))); }) + /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD -- cgit v1.2.3 From af8bb9f89838249872240f258e67774ccbcc5970 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 17 Apr 2018 10:58:09 -0500 Subject: PCI/ACPI: Request LTR control from platform before using it Per the PCI Firmware spec r3.2, sec 4.5, an ACPI-based OS should use _OSC to request control of Latency Tolerance Reporting (LTR) before using it. Request control of LTR, and if the platform does not grant control, don't use it. N.B. If the hardware supports LTR and the ASPM L1.2 substate but the BIOS doesn't support LTR in _OSC, we previously would enable ASPM L1.2. This patch will prevent us from enabling ASPM L1.2 in that case. It does not prevent us from enabling PCI-PM L1.2, since that doesn't depend on LTR. See PCIe r40, sec 5.5.1, for the L1 PM substate entry conditions. Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- include/linux/acpi.h | 3 ++- include/linux/pci.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 15bfb15c2fa5..49f63c67a9d1 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -506,7 +506,8 @@ extern bool osc_pc_lpi_support_confirmed; #define OSC_PCI_EXPRESS_PME_CONTROL 0x00000004 #define OSC_PCI_EXPRESS_AER_CONTROL 0x00000008 #define OSC_PCI_EXPRESS_CAPABILITY_CONTROL 0x00000010 -#define OSC_PCI_CONTROL_MASKS 0x0000001f +#define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 +#define OSC_PCI_CONTROL_MASKS 0x0000003f #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 diff --git a/include/linux/pci.h b/include/linux/pci.h index 73178a2fcee0..d0149c01996d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -473,6 +473,7 @@ struct pci_host_bridge { unsigned int native_aer:1; /* OS may use PCIe AER */ unsigned int native_hotplug:1; /* OS may use PCIe hotplug */ unsigned int native_pme:1; /* OS may use PCIe PME */ + unsigned int native_ltr:1; /* OS may use PCIe LTR */ /* Resource alignment requirements */ resource_size_t (*align_resource)(struct pci_dev *dev, const struct resource *res, -- cgit v1.2.3 From c6849a3ac17e336811f1d5bba991d2a9bdc47af1 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 22 Apr 2018 21:50:04 +0800 Subject: net: init sk_cookie for inet socket With sk_cookie we can identify a socket, that is very helpful for traceing and statistic, i.e. tcp tracepiont and ebpf. So we'd better init it by default for inet socket. When using it, we just need call atomic64_read(&sk->sk_cookie). Signed-off-by: Yafang Shao Signed-off-by: David S. Miller --- include/linux/sock_diag.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 15fe980a27ea..5c916e6dff36 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -25,6 +25,15 @@ void sock_diag_unregister(const struct sock_diag_handler *h); void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); +static inline +void sock_init_cookie(struct sock *sk) +{ + u64 res; + + res = atomic64_inc_return(&sock_net(sk)->cookie_gen); + atomic64_set(&sk->sk_cookie, res); +} + u64 sock_gen_cookie(struct sock *sk); int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie); -- cgit v1.2.3 From 1ac4329a1cff2e0bb12b71c13ad53a0e05bc87a6 Mon Sep 17 00:00:00 2001 From: Denis Bolotin Date: Mon, 23 Apr 2018 14:56:05 +0300 Subject: qed: Add configuration information to register dump and debug data Configuration information is added to the debug data collection, in addition to register dump. Added qed_dbg_nvm_image() that receives an image type, allocates a buffer and reads the image. The images are saved in the buffers and the dump size is updated. Signed-off-by: Denis Bolotin Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index b5b2bc9eacca..e53f9c7c2809 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -159,6 +159,9 @@ struct qed_dcbx_get { enum qed_nvm_images { QED_NVM_IMAGE_ISCSI_CFG, QED_NVM_IMAGE_FCOE_CFG, + QED_NVM_IMAGE_NVM_CFG1, + QED_NVM_IMAGE_DEFAULT_CFG, + QED_NVM_IMAGE_NVM_META, }; struct qed_link_eee_params { -- cgit v1.2.3 From 2ff0dab80a8999e99a93fd70f8d701ec3deab207 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 18 Apr 2018 15:18:02 +0200 Subject: mfd: bd9571mwv: Add DDR Backup Power register bit definitions Add definitions for the KEEPON_* bits in the "BKUP Mode Cnt" register, which control the DDR rails to be kept powered when backup mode is enabled. Signed-off-by: Geert Uytterhoeven Acked-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/bd9571mwv.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/bd9571mwv.h b/include/linux/mfd/bd9571mwv.h index f0708ba4cbba..eb05569f752b 100644 --- a/include/linux/mfd/bd9571mwv.h +++ b/include/linux/mfd/bd9571mwv.h @@ -33,6 +33,11 @@ #define BD9571MWV_I2C_MD2_E1_BIT_2 0x12 #define BD9571MWV_BKUP_MODE_CNT 0x20 +#define BD9571MWV_BKUP_MODE_CNT_KEEPON_MASK GENMASK(3, 0) +#define BD9571MWV_BKUP_MODE_CNT_KEEPON_DDR0 BIT(0) +#define BD9571MWV_BKUP_MODE_CNT_KEEPON_DDR1 BIT(1) +#define BD9571MWV_BKUP_MODE_CNT_KEEPON_DDR0C BIT(2) +#define BD9571MWV_BKUP_MODE_CNT_KEEPON_DDR1C BIT(3) #define BD9571MWV_BKUP_MODE_STATUS 0x21 #define BD9571MWV_BKUP_RECOVERY_CNT 0x22 #define BD9571MWV_BKUP_CTRL_TIM_CNT 0x23 -- cgit v1.2.3 From cd9a5a15808403a7895c51b1378168d6c75cf8a6 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 9 Apr 2018 00:00:57 +0900 Subject: netfilter: ebtables: remove EBT_MATCH and EBT_NOMATCH EBT_MATCH and EBT_NOMATCH are used to change return value. match functions(ebt_xxx.c) return false when received frame is not matched and returns true when received frame is matched. but, EBT_MATCH_ITERATE understands oppositely. so, to change return value, EBT_MATCH and EBT_NOMATCH are used. but, we can use operation '!' simply. Signed-off-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge/ebtables.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 0773b5a032f1..c6935be7c6ca 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -17,10 +17,6 @@ #include #include -/* return values for match() functions */ -#define EBT_MATCH 0 -#define EBT_NOMATCH 1 - struct ebt_match { struct list_head list; const char name[EBT_FUNCTION_MAXNAMELEN]; -- cgit v1.2.3 From f0316f93897c4c4e67278b175bfbfd3a95ba650a Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 5 Dec 2015 18:41:28 +0000 Subject: drm/i2c: tda9950: add CEC driver Add a CEC driver for the TDA9950, which is a stand-alone I2C CEC device, but is also integrated into HDMI transceivers such as the TDA9989 and TDA19989. The TDA9950 contains a command processor which handles retransmissions and the low level bus protocol. The driver just has to read and write the messages, and handle error conditions. Reviewed-by: Hans Verkuil Signed-off-by: Russell King --- include/linux/platform_data/tda9950.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/linux/platform_data/tda9950.h (limited to 'include/linux') diff --git a/include/linux/platform_data/tda9950.h b/include/linux/platform_data/tda9950.h new file mode 100644 index 000000000000..c65efd461102 --- /dev/null +++ b/include/linux/platform_data/tda9950.h @@ -0,0 +1,16 @@ +#ifndef LINUX_PLATFORM_DATA_TDA9950_H +#define LINUX_PLATFORM_DATA_TDA9950_H + +struct device; + +struct tda9950_glue { + struct device *parent; + unsigned long irq_flags; + void *data; + int (*init)(void *); + void (*exit)(void *); + int (*open)(void *); + void (*release)(void *); +}; + +#endif -- cgit v1.2.3 From 026a807c2de37aa826748c2ffa1969fc778406b2 Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Tue, 24 Apr 2018 13:36:01 +0300 Subject: net/dim: Rename *_get_profile() functions to *_get_rx_moderation() Preparation for introducing adaptive TX to net DIM. Signed-off-by: Tal Gilboa Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/net_dim.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index 29ed8fd6379a..7ca3c4deb3a6 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -129,17 +129,17 @@ profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { NET_DIM_CQE_PROFILES, }; -static inline struct net_dim_cq_moder net_dim_get_profile(u8 cq_period_mode, - int ix) +static inline struct net_dim_cq_moder +net_dim_get_rx_moderation(u8 cq_period_mode, int ix) { - struct net_dim_cq_moder cq_moder; + struct net_dim_cq_moder cq_moder = profile[cq_period_mode][ix]; - cq_moder = profile[cq_period_mode][ix]; cq_moder.cq_period_mode = cq_period_mode; return cq_moder; } -static inline struct net_dim_cq_moder net_dim_get_def_profile(u8 rx_cq_period_mode) +static inline struct net_dim_cq_moder +net_dim_get_def_rx_moderation(u8 rx_cq_period_mode) { int default_profile_ix; @@ -148,7 +148,7 @@ static inline struct net_dim_cq_moder net_dim_get_def_profile(u8 rx_cq_period_mo else /* NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE */ default_profile_ix = NET_DIM_DEF_PROFILE_EQE; - return net_dim_get_profile(rx_cq_period_mode, default_profile_ix); + return net_dim_get_rx_moderation(rx_cq_period_mode, default_profile_ix); } static inline bool net_dim_on_top(struct net_dim *dim) -- cgit v1.2.3 From 623ad755226c2b4fb312772bae9cdeccd8219ee3 Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Tue, 24 Apr 2018 13:36:02 +0300 Subject: net/dim: Support adaptive TX moderation Interrupt moderation for TX traffic requires different profiles than RX interrupt moderation. The main goal here is to reduce interrupt rate and allow better payload aggregation by keeping SKBs in the TX queue a bit longer. Ping-pong behavior would get a profile with a short timer, so latency wouldn't increase for these scenarios. There might be a slight degradation in bandwidth for single stream with large message sizes, since net.ipv4.tcp_limit_output_bytes is limiting the allowed TX traffic, but with many streams performance is always improved. Signed-off-by: Tal Gilboa Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/net_dim.h | 63 +++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 50 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index 7ca3c4deb3a6..db99240d00bd 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -103,11 +103,12 @@ enum { #define NET_DIM_PARAMS_NUM_PROFILES 5 /* Adaptive moderation profiles */ #define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 #define NET_DIM_DEF_PROFILE_CQE 1 #define NET_DIM_DEF_PROFILE_EQE 1 /* All profiles sizes must be NET_PARAMS_DIM_NUM_PROFILES */ -#define NET_DIM_EQE_PROFILES { \ +#define NET_DIM_RX_EQE_PROFILES { \ {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ @@ -115,7 +116,7 @@ enum { {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ } -#define NET_DIM_CQE_PROFILES { \ +#define NET_DIM_RX_CQE_PROFILES { \ {2, 256}, \ {8, 128}, \ {16, 64}, \ @@ -123,32 +124,68 @@ enum { {64, 64} \ } +#define NET_DIM_TX_EQE_PROFILES { \ + {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ +} + +#define NET_DIM_TX_CQE_PROFILES { \ + {5, 128}, \ + {8, 64}, \ + {16, 32}, \ + {32, 32}, \ + {64, 32} \ +} + static const struct net_dim_cq_moder -profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { - NET_DIM_EQE_PROFILES, - NET_DIM_CQE_PROFILES, +rx_profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_RX_EQE_PROFILES, + NET_DIM_RX_CQE_PROFILES, +}; + +static const struct net_dim_cq_moder +tx_profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_TX_EQE_PROFILES, + NET_DIM_TX_CQE_PROFILES, }; static inline struct net_dim_cq_moder net_dim_get_rx_moderation(u8 cq_period_mode, int ix) { - struct net_dim_cq_moder cq_moder = profile[cq_period_mode][ix]; + struct net_dim_cq_moder cq_moder = rx_profile[cq_period_mode][ix]; cq_moder.cq_period_mode = cq_period_mode; return cq_moder; } static inline struct net_dim_cq_moder -net_dim_get_def_rx_moderation(u8 rx_cq_period_mode) +net_dim_get_def_rx_moderation(u8 cq_period_mode) +{ + u8 profile_ix = cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE ? + NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE; + + return net_dim_get_rx_moderation(cq_period_mode, profile_ix); +} + +static inline struct net_dim_cq_moder +net_dim_get_tx_moderation(u8 cq_period_mode, int ix) { - int default_profile_ix; + struct net_dim_cq_moder cq_moder = tx_profile[cq_period_mode][ix]; - if (rx_cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE) - default_profile_ix = NET_DIM_DEF_PROFILE_CQE; - else /* NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE */ - default_profile_ix = NET_DIM_DEF_PROFILE_EQE; + cq_moder.cq_period_mode = cq_period_mode; + return cq_moder; +} + +static inline struct net_dim_cq_moder +net_dim_get_def_tx_moderation(u8 cq_period_mode) +{ + u8 profile_ix = cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE ? + NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE; - return net_dim_get_rx_moderation(rx_cq_period_mode, default_profile_ix); + return net_dim_get_tx_moderation(cq_period_mode, profile_ix); } static inline bool net_dim_on_top(struct net_dim *dim) -- cgit v1.2.3 From a06ac0d67d9fda7c255476c6391032319030045d Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Tue, 24 Apr 2018 23:07:45 +0800 Subject: Revert "net: init sk_cookie for inet socket" This reverts commit ("net: init sk_cookie for inet socket") Per discussion with Eric, when update sock_net(sk)->cookie_gen, the whole cache cache line will be invalidated, as this cache line is shared with all cpus, that may cause great performace hit. Bellow is the data form Eric. "Performance is reduced from ~5 Mpps to ~3.8 Mpps with 16 RX queues on my host" when running synflood test. Have to revert it to prevent from cache line false sharing. Signed-off-by: Yafang Shao Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/sock_diag.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 5c916e6dff36..15fe980a27ea 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -25,15 +25,6 @@ void sock_diag_unregister(const struct sock_diag_handler *h); void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); -static inline -void sock_init_cookie(struct sock *sk) -{ - u64 res; - - res = atomic64_inc_return(&sock_net(sk)->cookie_gen); - atomic64_set(&sk->sk_cookie, res); -} - u64 sock_gen_cookie(struct sock *sk); int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie); -- cgit v1.2.3 From f15cd6d99198e9c15229aefec639a34a6e8174c6 Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Mon, 23 Apr 2018 14:42:44 +0800 Subject: regmap: include from include/linux/regmap.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Similar to the readx_poll_timeout() macro calling ktime_* and using ktime_t type, which is declared in . So, make include/linux/regmap.h explicitly include , like include/linux/iopoll.h does. Otherwise, users of the macro will see below errors. error: implicit declaration of function ‘ktime_add_us’ [-Werror=implicit-function-declaration] error: implicit declaration of function ‘ktime_get’ [-Werror=implicit-function-declaration] error: implicit declaration of function ‘ktime_compare’ [-Werror=implicit-function-declaration] include/linux/regmap.h:128:2: error: unknown type name ‘ktime_t’ ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \ Signed-off-by: Sean Wang Signed-off-by: Mark Brown --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 5f7ad0552c03..b6865f070464 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -15,6 +15,7 @@ #include #include +#include #include #include #include -- cgit v1.2.3 From 0c6f69a5e3641bccfe21fd0eeafad45a8c6db987 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 24 Apr 2018 08:29:13 +1000 Subject: rhashtable: remove outdated comments about grow_decision etc grow_decision and shink_decision no longer exist, so remove the remaining references to them. Acked-by: Herbert Xu Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 33 ++++++++++++++------------------- 1 file changed, 14 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 1f8ad121eb43..87d443a5b11d 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -836,9 +836,8 @@ out: * * It is safe to call this function from atomic context. * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. */ static inline int rhashtable_insert_fast( struct rhashtable *ht, struct rhash_head *obj, @@ -866,9 +865,8 @@ static inline int rhashtable_insert_fast( * * It is safe to call this function from atomic context. * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. */ static inline int rhltable_insert_key( struct rhltable *hlt, const void *key, struct rhlist_head *list, @@ -890,9 +888,8 @@ static inline int rhltable_insert_key( * * It is safe to call this function from atomic context. * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. */ static inline int rhltable_insert( struct rhltable *hlt, struct rhlist_head *list, @@ -922,9 +919,8 @@ static inline int rhltable_insert( * * It is safe to call this function from atomic context. * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. */ static inline int rhashtable_lookup_insert_fast( struct rhashtable *ht, struct rhash_head *obj, @@ -981,9 +977,8 @@ static inline void *rhashtable_lookup_get_insert_fast( * * Lookups may occur in parallel with hashtable mutations and resizing. * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. * * Returns zero on success. */ @@ -1134,8 +1129,8 @@ static inline int __rhashtable_remove_fast( * walk the bucket chain upon removal. The removal operation is thus * considerable slow if the hash table is not correctly sized. * - * Will automatically shrink the table via rhashtable_expand() if the - * shrink_decision function specified at rhashtable_init() returns true. + * Will automatically shrink the table if permitted when residency drops + * below 30%. * * Returns zero on success, -ENOENT if the entry could not be found. */ @@ -1156,8 +1151,8 @@ static inline int rhashtable_remove_fast( * walk the bucket chain upon removal. The removal operation is thus * considerable slow if the hash table is not correctly sized. * - * Will automatically shrink the table via rhashtable_expand() if the - * shrink_decision function specified at rhashtable_init() returns true. + * Will automatically shrink the table if permitted when residency drops + * below 30% * * Returns zero on success, -ENOENT if the entry could not be found. */ -- cgit v1.2.3 From 82266e98dd4d8e7d5b8e4a0fedeb91f2eb29d306 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 24 Apr 2018 08:29:13 +1000 Subject: rhashtable: Revise incorrect comment on r{hl, hash}table_walk_enter() Neither rhashtable_walk_enter() or rhltable_walk_enter() sleep, though they do take a spinlock without irq protection. So revise the comments to accurately state the contexts in which these functions can be called. Acked-by: Herbert Xu Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 87d443a5b11d..4e1f535c2034 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -1268,8 +1268,9 @@ static inline int rhashtable_walk_init(struct rhashtable *ht, * For a completely stable walk you should construct your own data * structure outside the hash table. * - * This function may sleep so you must not call it from interrupt - * context or with spin locks held. + * This function may be called from any process context, including + * non-preemptable context, but cannot be called from softirq or + * hardirq context. * * You must call rhashtable_walk_exit after this function returns. */ -- cgit v1.2.3 From 8effc395c2097e258fcedfc02ed4a66d45fb4238 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Sat, 21 Apr 2018 15:23:09 -0500 Subject: PCI/IOV: Add pci_sriov_configure_simple() SR-IOV (Single Root I/O Virtualization) is an optional PCIe capability (see PCIe r4.0, sec 9). A PCIe Function with the SR-IOV capability is referred to as a PF (Physical Function). If SR-IOV is enabled on the PF, several VFs (Virtual Functions) may be created. The VFs can be individually assigned to virtual machines, which allows them to share a single hardware device while being isolated from each other. Some SR-IOV devices have resources such as queues and interrupts that must be set up in the PF before enabling the VFs, so they require a PF driver to do that. Other SR-IOV devices don't require any PF setup before enabling VFs. Add a pci_sriov_configure_simple() interface so PF drivers for such devices can use it without repeating the VF-enabling code. Tested-by: Mark Rustad Signed-off-by: Alexander Duyck [bhelgaas: changelog, comment] Signed-off-by: Bjorn Helgaas Reviewed-by: Greg Rose Reviewed-by: Christoph Hellwig :wq --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 73178a2fcee0..911f9098a466 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1954,6 +1954,7 @@ int pci_num_vf(struct pci_dev *dev); int pci_vfs_assigned(struct pci_dev *dev); int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs); int pci_sriov_get_totalvfs(struct pci_dev *dev); +int pci_sriov_configure_simple(struct pci_dev *dev, int nr_virtfn); resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno); void pci_vf_drivers_autoprobe(struct pci_dev *dev, bool probe); @@ -1986,6 +1987,7 @@ static inline int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs) { return 0; } static inline int pci_sriov_get_totalvfs(struct pci_dev *dev) { return 0; } +#define pci_sriov_configure_simple NULL static inline resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno) { return 0; } static inline void pci_vf_drivers_autoprobe(struct pci_dev *dev, bool probe) { } -- cgit v1.2.3 From a8ccf8a666639ca9184e8b23d515d9fbe722a27d Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 24 Apr 2018 16:47:16 -0500 Subject: PCI/IOV: Add pci-pf-stub driver for PFs that only enable VFs Some SR-IOV PF devices provide no functionality other than acting as a means of enabling VFs. For these devices, we want to enable the VFs and assign them to guest virtual machines, but there's no need to have a driver for the PF itself. Add a new pci-pf-stub driver to claim those PF devices and provide the generic VF enable functionality. An administrator can use the sysfs "sriov_numvfs" file to enable VFs, then assign them to guests. For now I only have one example ID provided by Amazon in terms of devices that require this functionality. The general idea is that in the future we will see other devices added as vendors come up with devices where the PF is more or less just a lightweight shim used to allocate VFs. Signed-off-by: Alexander Duyck [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas Reviewed-by: Greg Rose Reviewed-by: Christoph Hellwig --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index cc608fc55334..411c12287dda 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2552,6 +2552,8 @@ #define PCI_VENDOR_ID_CIRCUITCO 0x1cc8 #define PCI_SUBSYSTEM_ID_CIRCUITCO_MINNOWBOARD 0x0001 +#define PCI_VENDOR_ID_AMAZON 0x1d0f + #define PCI_VENDOR_ID_TEKRAM 0x1de1 #define PCI_DEVICE_ID_TEKRAM_DC290 0xdc29 -- cgit v1.2.3 From 83a530e1610ab996e59c0941db6cc72f763dddbd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 22 Apr 2018 18:23:46 +0200 Subject: rslib: Add GFP aware init function The rslib usage in dm/verity_fec is broken because init_rs() can nest in GFP_NOIO mempool allocations as init_rs() is invoked from the mempool alloc callback. Provide a variant which takes gfp_t flags as argument. Signed-off-by: Thomas Gleixner Cc: Mike Snitzer Cc: Alasdair Kergon Cc: Neil Brown Signed-off-by: Kees Cook --- include/linux/rslib.h | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rslib.h b/include/linux/rslib.h index 746580c1939c..2aae7ef987eb 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -20,6 +20,8 @@ #define _RSLIB_H_ #include +#include /* for gfp_t */ +#include /* for GFP_KERNEL */ /** * struct rs_control - rs control structure @@ -77,10 +79,30 @@ int decode_rs16(struct rs_control *rs, uint16_t *data, uint16_t *par, int len, #endif /* Create or get a matching rs control structure */ -struct rs_control *init_rs(int symsize, int gfpoly, int fcr, int prim, - int nroots); +struct rs_control *init_rs_gfp(int symsize, int gfpoly, int fcr, int prim, + int nroots, gfp_t gfp); + +/** + * init_rs - Create a RS control struct and initialize it + * @symsize: the symbol size (number of bits) + * @gfpoly: the extended Galois field generator polynomial coefficients, + * with the 0th coefficient in the low order bit. The polynomial + * must be primitive; + * @fcr: the first consecutive root of the rs code generator polynomial + * in index form + * @prim: primitive element to generate polynomial roots + * @nroots: RS code generator polynomial degree (number of roots) + * + * Allocations use GFP_KERNEL. + */ +static inline struct rs_control *init_rs(int symsize, int gfpoly, int fcr, + int prim, int nroots) +{ + return init_rs_gfp(symsize, gfpoly, fcr, prim, nroots, GFP_KERNEL); +} + struct rs_control *init_rs_non_canonical(int symsize, int (*func)(int), - int fcr, int prim, int nroots); + int fcr, int prim, int nroots); /* Release a rs control structure */ void free_rs(struct rs_control *rs); -- cgit v1.2.3 From cc4b86e496beb6f3f499e1be260f51b4026aba84 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 22 Apr 2018 18:23:48 +0200 Subject: rslib: Cleanup whitespace damage Instead of mixing the whitespace cleanup into functional changes, mop it up first. Signed-off-by: Thomas Gleixner Cc: Boris Brezillon Cc: Tony Luck Cc: Kees Cook Cc: Segher Boessenkool Cc: Kernel Hardening Cc: Richard Weinberger Cc: Mike Snitzer Cc: Anton Vorontsov Cc: Colin Cross Cc: Andrew Morton Cc: David Woodhouse Cc: Alasdair Kergon Signed-off-by: Kees Cook --- include/linux/rslib.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rslib.h b/include/linux/rslib.h index 2aae7ef987eb..d7bc66931032 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -41,15 +41,15 @@ * @list: List entry for the rs control list */ struct rs_control { - int mm; - int nn; + int mm; + int nn; uint16_t *alpha_to; uint16_t *index_of; uint16_t *genpoly; - int nroots; - int fcr; - int prim; - int iprim; + int nroots; + int fcr; + int prim; + int iprim; int gfpoly; int (*gffunc)(int); int users; -- cgit v1.2.3 From 3413e1891d443b9e936b4b6fb0ba4cdc38ff71b6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 22 Apr 2018 18:23:49 +0200 Subject: rslib: Cleanup top level comments File references and stale CVS ids are really not useful. Signed-off-by: Thomas Gleixner Cc: Boris Brezillon Cc: Tony Luck Cc: Kees Cook Cc: Segher Boessenkool Cc: Kernel Hardening Cc: Richard Weinberger Cc: Mike Snitzer Cc: Anton Vorontsov Cc: Colin Cross Cc: Andrew Morton Cc: David Woodhouse Cc: Alasdair Kergon Signed-off-by: Kees Cook --- include/linux/rslib.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rslib.h b/include/linux/rslib.h index d7bc66931032..a596abaf2e56 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -1,16 +1,11 @@ /* - * include/linux/rslib.h - * - * Overview: - * Generic Reed Solomon encoder / decoder library + * Generic Reed Solomon encoder / decoder library * * Copyright (C) 2004 Thomas Gleixner (tglx@linutronix.de) * * RS code lifted from reed solomon library written by Phil Karn * Copyright 2002 Phil Karn, KA9Q * - * $Id: rslib.h,v 1.4 2005/11/07 11:14:52 gleixner Exp $ - * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. -- cgit v1.2.3 From dc8f923eaee24061c557cb3221abeea3b95072c4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 22 Apr 2018 18:23:50 +0200 Subject: rslib: Add SPDX identifiers The Reed-Solomon library is based on code from Phil Karn who granted permission to import it into the kernel under the GPL V2. See commit 15b5423757a7 ("Shared Reed-Solomon ECC library") in the history git tree at: git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git ... The encoder/decoder code is lifted from the GPL'd userspace RS-library written by Phil Karn. I modified/wrapped it to provide the different functions which we need in the MTD/NAND code. ... Signed-Off-By: Thomas Gleixner Signed-Off-By: David Woodhouse "No objections at all. Just keep the authorship notices." -- Phil Karn Add the proper SPDX identifiers according to Documentation/process/license-rules.rst. Signed-off-by: Thomas Gleixner Reviewed-by: Kate Stewart Reviewed-by: Greg Kroah-Hartman Cc: Boris Brezillon Cc: Tony Luck Cc: Kees Cook Cc: Segher Boessenkool Cc: Kernel Hardening Cc: Richard Weinberger Cc: Mike Snitzer Cc: Anton Vorontsov Cc: Colin Cross Cc: Andrew Morton Cc: David Woodhouse Cc: Alasdair Kergon Signed-off-by: Kees Cook --- include/linux/rslib.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rslib.h b/include/linux/rslib.h index a596abaf2e56..7ace7eec3028 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generic Reed Solomon encoder / decoder library * -- cgit v1.2.3 From 689c6efdfb58d7b21c375f515349e4091e08100b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 22 Apr 2018 18:23:51 +0200 Subject: rslib: Remove GPL boilerplate Now that SPDX identifiers are in place, remove the GPL boiler plate text. Leave the notices which document that Phil Karn granted permission in place (encode/decode source code). The modified files are code written for the kernel by me. Signed-off-by: Thomas Gleixner Reviewed-by: Kate Stewart Reviewed-by: Greg Kroah-Hartman Cc: Boris Brezillon Cc: Tony Luck Cc: Kees Cook Cc: Segher Boessenkool Cc: Kernel Hardening Cc: Richard Weinberger Cc: Mike Snitzer Cc: Anton Vorontsov Cc: Colin Cross Cc: Andrew Morton Cc: David Woodhouse Cc: Alasdair Kergon Signed-off-by: Kees Cook --- include/linux/rslib.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rslib.h b/include/linux/rslib.h index 7ace7eec3028..27652c18bf8c 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -6,12 +6,7 @@ * * RS code lifted from reed solomon library written by Phil Karn * Copyright 2002 Phil Karn, KA9Q - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ - #ifndef _RSLIB_H_ #define _RSLIB_H_ -- cgit v1.2.3 From 2163398192f6a53e84765cfe3e5a2088437c3d2d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 22 Apr 2018 18:23:53 +0200 Subject: rslib: Split rs control struct The decoder library uses variable length arrays on stack. To get rid of them it would be simple to allocate fixed length arrays on stack, but those might become rather large. The other solution is to allocate the buffers in the rs control structure, but this cannot be done as long as the structure can be shared by several users. Sharing is desired because the RS polynom tables are large and initialization is time consuming. To solve this split the codec information out of the control structure and have a pointer to a shared codec in it. Instantiate the control structure for each user, create a new codec if no shareable is avaiable yet. Adjust all affected usage sites to the new scheme. This allows to add per instance decoder buffers to the control structure later on. Signed-off-by: Thomas Gleixner Acked-by: Boris Brezillon Cc: Tony Luck Cc: Kees Cook Cc: Segher Boessenkool Cc: Kernel Hardening Cc: Richard Weinberger Cc: Mike Snitzer Cc: Anton Vorontsov Cc: Colin Cross Cc: Andrew Morton Cc: David Woodhouse Cc: Alasdair Kergon Signed-off-by: Kees Cook --- include/linux/rslib.h | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rslib.h b/include/linux/rslib.h index 27652c18bf8c..6703311beea3 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -15,7 +15,7 @@ #include /* for GFP_KERNEL */ /** - * struct rs_control - rs control structure + * struct rs_codec - rs codec data * * @mm: Bits per symbol * @nn: Symbols per block (= (1<= 3 * rs->nn */ -static inline int rs_modnn(struct rs_control *rs, int x) +static inline int rs_modnn(struct rs_codec *rs, int x) { while (x >= rs->nn) { x -= rs->nn; -- cgit v1.2.3 From 45888b40d2a6221d46bb69959e2600ddba71cc1f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 22 Apr 2018 18:23:55 +0200 Subject: rslib: Allocate decoder buffers to avoid VLAs To get rid of the variable length arrays on stack in the RS decoder it's necessary to allocate the decoder buffers per control structure instance. All usage sites have been checked for potential parallel decoder usage and fixed where necessary. Kees confirmed that the pstore decoding is strictly single threaded so there should be no surprises. Allocate them in the rs control structure sized depending on the number of roots for the chosen codec and adapt the decoder code to make use of them. Document the fact that decode operations based on a particular rs control instance cannot run in parallel and the caller has to ensure that as it's not possible to provide a proper locking construct which fits all use cases. Signed-off-by: Thomas Gleixner Acked-by: Kees Cook Cc: Boris Brezillon Cc: Tony Luck Cc: Segher Boessenkool Cc: Kernel Hardening Cc: Richard Weinberger Cc: Mike Snitzer Cc: Anton Vorontsov Cc: Colin Cross Cc: Andrew Morton Cc: David Woodhouse Cc: Alasdair Kergon Signed-off-by: Kees Cook --- include/linux/rslib.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rslib.h b/include/linux/rslib.h index 6703311beea3..5974cedd008c 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -50,9 +50,11 @@ struct rs_codec { /** * struct rs_control - rs control structure per instance * @codec: The codec used for this instance + * @buffers: Internal scratch buffers used in calls to decode_rs() */ struct rs_control { struct rs_codec *codec; + uint16_t buffers[0]; }; /* General purpose RS codec, 8-bit data width, symbol width 1-15 bit */ -- cgit v1.2.3 From eddac5af06546d2e7a0730e3dc02dde3dc91098a Mon Sep 17 00:00:00 2001 From: Karthikeyan Ramasubramanian Date: Fri, 30 Mar 2018 11:08:17 -0600 Subject: soc: qcom: Add GENI based QUP Wrapper driver This driver manages the Generic Interface (GENI) firmware based Qualcomm Universal Peripheral (QUP) Wrapper. GENI based QUP is the next generation programmable module composed of multiple Serial Engines (SE) and supports a wide range of serial interfaces like UART, SPI, I2C, I3C, etc. This driver also enables managing the serial interface independent aspects of Serial Engines. Signed-off-by: Karthikeyan Ramasubramanian Signed-off-by: Sagar Dharia Signed-off-by: Girish Mahadevan Reviewed-by: Evan Green Signed-off-by: Andy Gross --- include/linux/qcom-geni-se.h | 425 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 425 insertions(+) create mode 100644 include/linux/qcom-geni-se.h (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h new file mode 100644 index 000000000000..5d6144977828 --- /dev/null +++ b/include/linux/qcom-geni-se.h @@ -0,0 +1,425 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. + */ + +#ifndef _LINUX_QCOM_GENI_SE +#define _LINUX_QCOM_GENI_SE + +/* Transfer mode supported by GENI Serial Engines */ +enum geni_se_xfer_mode { + GENI_SE_INVALID, + GENI_SE_FIFO, + GENI_SE_DMA, +}; + +/* Protocols supported by GENI Serial Engines */ +enum geni_se_protocol_type { + GENI_SE_NONE, + GENI_SE_SPI, + GENI_SE_UART, + GENI_SE_I2C, + GENI_SE_I3C, +}; + +struct geni_wrapper; +struct clk; + +/** + * struct geni_se - GENI Serial Engine + * @base: Base Address of the Serial Engine's register block + * @dev: Pointer to the Serial Engine device + * @wrapper: Pointer to the parent QUP Wrapper core + * @clk: Handle to the core serial engine clock + * @num_clk_levels: Number of valid clock levels in clk_perf_tbl + * @clk_perf_tbl: Table of clock frequency input to serial engine clock + */ +struct geni_se { + void __iomem *base; + struct device *dev; + struct geni_wrapper *wrapper; + struct clk *clk; + unsigned int num_clk_levels; + unsigned long *clk_perf_tbl; +}; + +/* Common SE registers */ +#define GENI_FORCE_DEFAULT_REG 0x20 +#define SE_GENI_STATUS 0x40 +#define GENI_SER_M_CLK_CFG 0x48 +#define GENI_SER_S_CLK_CFG 0x4c +#define GENI_FW_REVISION_RO 0x68 +#define SE_GENI_CLK_SEL 0x7c +#define SE_GENI_DMA_MODE_EN 0x258 +#define SE_GENI_M_CMD0 0x600 +#define SE_GENI_M_CMD_CTRL_REG 0x604 +#define SE_GENI_M_IRQ_STATUS 0x610 +#define SE_GENI_M_IRQ_EN 0x614 +#define SE_GENI_M_IRQ_CLEAR 0x618 +#define SE_GENI_S_CMD0 0x630 +#define SE_GENI_S_CMD_CTRL_REG 0x634 +#define SE_GENI_S_IRQ_STATUS 0x640 +#define SE_GENI_S_IRQ_EN 0x644 +#define SE_GENI_S_IRQ_CLEAR 0x648 +#define SE_GENI_TX_FIFOn 0x700 +#define SE_GENI_RX_FIFOn 0x780 +#define SE_GENI_TX_FIFO_STATUS 0x800 +#define SE_GENI_RX_FIFO_STATUS 0x804 +#define SE_GENI_TX_WATERMARK_REG 0x80c +#define SE_GENI_RX_WATERMARK_REG 0x810 +#define SE_GENI_RX_RFR_WATERMARK_REG 0x814 +#define SE_GENI_IOS 0x908 +#define SE_DMA_TX_IRQ_STAT 0xc40 +#define SE_DMA_TX_IRQ_CLR 0xc44 +#define SE_DMA_TX_FSM_RST 0xc58 +#define SE_DMA_RX_IRQ_STAT 0xd40 +#define SE_DMA_RX_IRQ_CLR 0xd44 +#define SE_DMA_RX_FSM_RST 0xd58 +#define SE_HW_PARAM_0 0xe24 +#define SE_HW_PARAM_1 0xe28 + +/* GENI_FORCE_DEFAULT_REG fields */ +#define FORCE_DEFAULT BIT(0) + +/* GENI_STATUS fields */ +#define M_GENI_CMD_ACTIVE BIT(0) +#define S_GENI_CMD_ACTIVE BIT(12) + +/* GENI_SER_M_CLK_CFG/GENI_SER_S_CLK_CFG */ +#define SER_CLK_EN BIT(0) +#define CLK_DIV_MSK GENMASK(15, 4) +#define CLK_DIV_SHFT 4 + +/* GENI_FW_REVISION_RO fields */ +#define FW_REV_PROTOCOL_MSK GENMASK(15, 8) +#define FW_REV_PROTOCOL_SHFT 8 + +/* GENI_CLK_SEL fields */ +#define CLK_SEL_MSK GENMASK(2, 0) + +/* SE_GENI_DMA_MODE_EN */ +#define GENI_DMA_MODE_EN BIT(0) + +/* GENI_M_CMD0 fields */ +#define M_OPCODE_MSK GENMASK(31, 27) +#define M_OPCODE_SHFT 27 +#define M_PARAMS_MSK GENMASK(26, 0) + +/* GENI_M_CMD_CTRL_REG */ +#define M_GENI_CMD_CANCEL BIT(2) +#define M_GENI_CMD_ABORT BIT(1) +#define M_GENI_DISABLE BIT(0) + +/* GENI_S_CMD0 fields */ +#define S_OPCODE_MSK GENMASK(31, 27) +#define S_OPCODE_SHFT 27 +#define S_PARAMS_MSK GENMASK(26, 0) + +/* GENI_S_CMD_CTRL_REG */ +#define S_GENI_CMD_CANCEL BIT(2) +#define S_GENI_CMD_ABORT BIT(1) +#define S_GENI_DISABLE BIT(0) + +/* GENI_M_IRQ_EN fields */ +#define M_CMD_DONE_EN BIT(0) +#define M_CMD_OVERRUN_EN BIT(1) +#define M_ILLEGAL_CMD_EN BIT(2) +#define M_CMD_FAILURE_EN BIT(3) +#define M_CMD_CANCEL_EN BIT(4) +#define M_CMD_ABORT_EN BIT(5) +#define M_TIMESTAMP_EN BIT(6) +#define M_RX_IRQ_EN BIT(7) +#define M_GP_SYNC_IRQ_0_EN BIT(8) +#define M_GP_IRQ_0_EN BIT(9) +#define M_GP_IRQ_1_EN BIT(10) +#define M_GP_IRQ_2_EN BIT(11) +#define M_GP_IRQ_3_EN BIT(12) +#define M_GP_IRQ_4_EN BIT(13) +#define M_GP_IRQ_5_EN BIT(14) +#define M_IO_DATA_DEASSERT_EN BIT(22) +#define M_IO_DATA_ASSERT_EN BIT(23) +#define M_RX_FIFO_RD_ERR_EN BIT(24) +#define M_RX_FIFO_WR_ERR_EN BIT(25) +#define M_RX_FIFO_WATERMARK_EN BIT(26) +#define M_RX_FIFO_LAST_EN BIT(27) +#define M_TX_FIFO_RD_ERR_EN BIT(28) +#define M_TX_FIFO_WR_ERR_EN BIT(29) +#define M_TX_FIFO_WATERMARK_EN BIT(30) +#define M_SEC_IRQ_EN BIT(31) +#define M_COMMON_GENI_M_IRQ_EN (GENMASK(6, 1) | \ + M_IO_DATA_DEASSERT_EN | \ + M_IO_DATA_ASSERT_EN | M_RX_FIFO_RD_ERR_EN | \ + M_RX_FIFO_WR_ERR_EN | M_TX_FIFO_RD_ERR_EN | \ + M_TX_FIFO_WR_ERR_EN) + +/* GENI_S_IRQ_EN fields */ +#define S_CMD_DONE_EN BIT(0) +#define S_CMD_OVERRUN_EN BIT(1) +#define S_ILLEGAL_CMD_EN BIT(2) +#define S_CMD_FAILURE_EN BIT(3) +#define S_CMD_CANCEL_EN BIT(4) +#define S_CMD_ABORT_EN BIT(5) +#define S_GP_SYNC_IRQ_0_EN BIT(8) +#define S_GP_IRQ_0_EN BIT(9) +#define S_GP_IRQ_1_EN BIT(10) +#define S_GP_IRQ_2_EN BIT(11) +#define S_GP_IRQ_3_EN BIT(12) +#define S_GP_IRQ_4_EN BIT(13) +#define S_GP_IRQ_5_EN BIT(14) +#define S_IO_DATA_DEASSERT_EN BIT(22) +#define S_IO_DATA_ASSERT_EN BIT(23) +#define S_RX_FIFO_RD_ERR_EN BIT(24) +#define S_RX_FIFO_WR_ERR_EN BIT(25) +#define S_RX_FIFO_WATERMARK_EN BIT(26) +#define S_RX_FIFO_LAST_EN BIT(27) +#define S_COMMON_GENI_S_IRQ_EN (GENMASK(5, 1) | GENMASK(13, 9) | \ + S_RX_FIFO_RD_ERR_EN | S_RX_FIFO_WR_ERR_EN) + +/* GENI_/TX/RX/RX_RFR/_WATERMARK_REG fields */ +#define WATERMARK_MSK GENMASK(5, 0) + +/* GENI_TX_FIFO_STATUS fields */ +#define TX_FIFO_WC GENMASK(27, 0) + +/* GENI_RX_FIFO_STATUS fields */ +#define RX_LAST BIT(31) +#define RX_LAST_BYTE_VALID_MSK GENMASK(30, 28) +#define RX_LAST_BYTE_VALID_SHFT 28 +#define RX_FIFO_WC_MSK GENMASK(24, 0) + +/* SE_GENI_IOS fields */ +#define IO2_DATA_IN BIT(1) +#define RX_DATA_IN BIT(0) + +/* SE_DMA_TX_IRQ_STAT Register fields */ +#define TX_DMA_DONE BIT(0) +#define TX_EOT BIT(1) +#define TX_SBE BIT(2) +#define TX_RESET_DONE BIT(3) + +/* SE_DMA_RX_IRQ_STAT Register fields */ +#define RX_DMA_DONE BIT(0) +#define RX_EOT BIT(1) +#define RX_SBE BIT(2) +#define RX_RESET_DONE BIT(3) +#define RX_FLUSH_DONE BIT(4) +#define RX_GENI_GP_IRQ GENMASK(10, 5) +#define RX_GENI_CANCEL_IRQ BIT(11) +#define RX_GENI_GP_IRQ_EXT GENMASK(13, 12) + +/* SE_HW_PARAM_0 fields */ +#define TX_FIFO_WIDTH_MSK GENMASK(29, 24) +#define TX_FIFO_WIDTH_SHFT 24 +#define TX_FIFO_DEPTH_MSK GENMASK(21, 16) +#define TX_FIFO_DEPTH_SHFT 16 + +/* SE_HW_PARAM_1 fields */ +#define RX_FIFO_WIDTH_MSK GENMASK(29, 24) +#define RX_FIFO_WIDTH_SHFT 24 +#define RX_FIFO_DEPTH_MSK GENMASK(21, 16) +#define RX_FIFO_DEPTH_SHFT 16 + +#define HW_VER_MAJOR_MASK GENMASK(31, 28) +#define HW_VER_MAJOR_SHFT 28 +#define HW_VER_MINOR_MASK GENMASK(27, 16) +#define HW_VER_MINOR_SHFT 16 +#define HW_VER_STEP_MASK GENMASK(15, 0) + +#if IS_ENABLED(CONFIG_QCOM_GENI_SE) + +u32 geni_se_get_qup_hw_version(struct geni_se *se); + +#define geni_se_get_wrapper_version(se, major, minor, step) do { \ + u32 ver; \ +\ + ver = geni_se_get_qup_hw_version(se); \ + major = (ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT; \ + minor = (ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT; \ + step = version & HW_VER_STEP_MASK; \ +} while (0) + +/** + * geni_se_read_proto() - Read the protocol configured for a serial engine + * @se: Pointer to the concerned serial engine. + * + * Return: Protocol value as configured in the serial engine. + */ +static inline u32 geni_se_read_proto(struct geni_se *se) +{ + u32 val; + + val = readl_relaxed(se->base + GENI_FW_REVISION_RO); + + return (val & FW_REV_PROTOCOL_MSK) >> FW_REV_PROTOCOL_SHFT; +} + +/** + * geni_se_setup_m_cmd() - Setup the primary sequencer + * @se: Pointer to the concerned serial engine. + * @cmd: Command/Operation to setup in the primary sequencer. + * @params: Parameter for the sequencer command. + * + * This function is used to configure the primary sequencer with the + * command and its associated parameters. + */ +static inline void geni_se_setup_m_cmd(struct geni_se *se, u32 cmd, u32 params) +{ + u32 m_cmd; + + m_cmd = (cmd << M_OPCODE_SHFT) | (params & M_PARAMS_MSK); + writel_relaxed(m_cmd, se->base + SE_GENI_M_CMD0); +} + +/** + * geni_se_setup_s_cmd() - Setup the secondary sequencer + * @se: Pointer to the concerned serial engine. + * @cmd: Command/Operation to setup in the secondary sequencer. + * @params: Parameter for the sequencer command. + * + * This function is used to configure the secondary sequencer with the + * command and its associated parameters. + */ +static inline void geni_se_setup_s_cmd(struct geni_se *se, u32 cmd, u32 params) +{ + u32 s_cmd; + + s_cmd = readl_relaxed(se->base + SE_GENI_S_CMD0); + s_cmd &= ~(S_OPCODE_MSK | S_PARAMS_MSK); + s_cmd |= (cmd << S_OPCODE_SHFT); + s_cmd |= (params & S_PARAMS_MSK); + writel_relaxed(s_cmd, se->base + SE_GENI_S_CMD0); +} + +/** + * geni_se_cancel_m_cmd() - Cancel the command configured in the primary + * sequencer + * @se: Pointer to the concerned serial engine. + * + * This function is used to cancel the currently configured command in the + * primary sequencer. + */ +static inline void geni_se_cancel_m_cmd(struct geni_se *se) +{ + writel_relaxed(M_GENI_CMD_CANCEL, se->base + SE_GENI_M_CMD_CTRL_REG); +} + +/** + * geni_se_cancel_s_cmd() - Cancel the command configured in the secondary + * sequencer + * @se: Pointer to the concerned serial engine. + * + * This function is used to cancel the currently configured command in the + * secondary sequencer. + */ +static inline void geni_se_cancel_s_cmd(struct geni_se *se) +{ + writel_relaxed(S_GENI_CMD_CANCEL, se->base + SE_GENI_S_CMD_CTRL_REG); +} + +/** + * geni_se_abort_m_cmd() - Abort the command configured in the primary sequencer + * @se: Pointer to the concerned serial engine. + * + * This function is used to force abort the currently configured command in the + * primary sequencer. + */ +static inline void geni_se_abort_m_cmd(struct geni_se *se) +{ + writel_relaxed(M_GENI_CMD_ABORT, se->base + SE_GENI_M_CMD_CTRL_REG); +} + +/** + * geni_se_abort_s_cmd() - Abort the command configured in the secondary + * sequencer + * @se: Pointer to the concerned serial engine. + * + * This function is used to force abort the currently configured command in the + * secondary sequencer. + */ +static inline void geni_se_abort_s_cmd(struct geni_se *se) +{ + writel_relaxed(S_GENI_CMD_ABORT, se->base + SE_GENI_S_CMD_CTRL_REG); +} + +/** + * geni_se_get_tx_fifo_depth() - Get the TX fifo depth of the serial engine + * @se: Pointer to the concerned serial engine. + * + * This function is used to get the depth i.e. number of elements in the + * TX fifo of the serial engine. + * + * Return: TX fifo depth in units of FIFO words. + */ +static inline u32 geni_se_get_tx_fifo_depth(struct geni_se *se) +{ + u32 val; + + val = readl_relaxed(se->base + SE_HW_PARAM_0); + + return (val & TX_FIFO_DEPTH_MSK) >> TX_FIFO_DEPTH_SHFT; +} + +/** + * geni_se_get_tx_fifo_width() - Get the TX fifo width of the serial engine + * @se: Pointer to the concerned serial engine. + * + * This function is used to get the width i.e. word size per element in the + * TX fifo of the serial engine. + * + * Return: TX fifo width in bits + */ +static inline u32 geni_se_get_tx_fifo_width(struct geni_se *se) +{ + u32 val; + + val = readl_relaxed(se->base + SE_HW_PARAM_0); + + return (val & TX_FIFO_WIDTH_MSK) >> TX_FIFO_WIDTH_SHFT; +} + +/** + * geni_se_get_rx_fifo_depth() - Get the RX fifo depth of the serial engine + * @se: Pointer to the concerned serial engine. + * + * This function is used to get the depth i.e. number of elements in the + * RX fifo of the serial engine. + * + * Return: RX fifo depth in units of FIFO words + */ +static inline u32 geni_se_get_rx_fifo_depth(struct geni_se *se) +{ + u32 val; + + val = readl_relaxed(se->base + SE_HW_PARAM_1); + + return (val & RX_FIFO_DEPTH_MSK) >> RX_FIFO_DEPTH_SHFT; +} + +void geni_se_init(struct geni_se *se, u32 rx_wm, u32 rx_rfr); + +void geni_se_select_mode(struct geni_se *se, enum geni_se_xfer_mode mode); + +void geni_se_config_packing(struct geni_se *se, int bpw, int pack_words, + bool msb_to_lsb, bool tx_cfg, bool rx_cfg); + +int geni_se_resources_off(struct geni_se *se); + +int geni_se_resources_on(struct geni_se *se); + +int geni_se_clk_tbl_get(struct geni_se *se, unsigned long **tbl); + +int geni_se_clk_freq_match(struct geni_se *se, unsigned long req_freq, + unsigned int *index, unsigned long *res_freq, + bool exact); + +int geni_se_tx_dma_prep(struct geni_se *se, void *buf, size_t len, + dma_addr_t *iova); + +int geni_se_rx_dma_prep(struct geni_se *se, void *buf, size_t len, + dma_addr_t *iova); + +void geni_se_tx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len); + +void geni_se_rx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len); +#endif +#endif -- cgit v1.2.3 From 2eadc33f40d4c59dd0649f8b6958872d85ad05d7 Mon Sep 17 00:00:00 2001 From: Adam Thomson Date: Mon, 23 Apr 2018 15:10:56 +0100 Subject: typec: tcpm: Add core support for sink side PPS This commit adds code to handle requesting of PPS APDOs. Switching between standard PDOs and APDOs, and re-requesting an APDO to modify operating voltage/current will be triggered by an external call into TCPM. Signed-off-by: Adam Thomson Acked-by: Heikki Krogerus Reviewed-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd.h | 4 ++-- include/linux/usb/tcpm.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index ff359bdfdc7b..09b570feb297 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -103,8 +103,8 @@ enum pd_ext_msg_type { (((cnt) & PD_HEADER_CNT_MASK) << PD_HEADER_CNT_SHIFT) | \ ((ext_hdr) ? PD_HEADER_EXT_HDR : 0)) -#define PD_HEADER_LE(type, pwr, data, id, cnt) \ - cpu_to_le16(PD_HEADER((type), (pwr), (data), PD_REV20, (id), (cnt), (0))) +#define PD_HEADER_LE(type, pwr, data, rev, id, cnt) \ + cpu_to_le16(PD_HEADER((type), (pwr), (data), (rev), (id), (cnt), (0))) static inline unsigned int pd_header_cnt(u16 header) { diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index f5bda9a0f644..b231b9314240 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -36,6 +36,7 @@ enum typec_cc_polarity { /* Time to wait for TCPC to complete transmit */ #define PD_T_TCPC_TX_TIMEOUT 100 /* in ms */ #define PD_ROLE_SWAP_TIMEOUT (MSEC_PER_SEC * 10) +#define PD_PPS_CTRL_TIMEOUT (MSEC_PER_SEC * 10) enum tcpm_transmit_status { TCPC_TX_SUCCESS = 0, -- cgit v1.2.3 From cf45004195efea6b479a1d710d6fc21c2b19353e Mon Sep 17 00:00:00 2001 From: Adam Thomson Date: Mon, 23 Apr 2018 15:10:59 +0100 Subject: power: supply: Add 'usb_type' property and supporting code This commit adds the 'usb_type' property to represent USB supplies which can report a number of different types based on a connection event. Examples of this already exist in drivers whereby the existing 'type' property is updated, based on an event, to represent what was connected (e.g. USB, USB_DCP, USB_ACA, ...). Current implementations however don't show all supported connectable types, so this knowledge has to be exlicitly known for each driver that supports this. The 'usb_type' property is intended to fill this void and show users all possible USB types supported by a driver. The property, when read, shows all available types for the driver, and the one currently chosen is highlighted/bracketed. It is expected that the 'type' property would then just show the top-level type 'USB', and this would be static. Currently the 'usb_type' enum contains all of the USB variant types that exist for the 'type' enum at this time, and in addition has SDP and PPS types. The mirroring is intentional so as to not impact existing usage of the 'type' property. Signed-off-by: Adam Thomson Reviewed-by: Heikki Krogerus Reviewed-by: Sebastian Reichel Signed-off-by: Greg Kroah-Hartman --- include/linux/power_supply.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index f0139b460a72..0c9a572a1eb8 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -145,6 +145,7 @@ enum power_supply_property { POWER_SUPPLY_PROP_TIME_TO_FULL_NOW, POWER_SUPPLY_PROP_TIME_TO_FULL_AVG, POWER_SUPPLY_PROP_TYPE, /* use power_supply.type instead */ + POWER_SUPPLY_PROP_USB_TYPE, POWER_SUPPLY_PROP_SCOPE, POWER_SUPPLY_PROP_PRECHARGE_CURRENT, POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT, @@ -170,6 +171,19 @@ enum power_supply_type { POWER_SUPPLY_TYPE_APPLE_BRICK_ID, /* Apple Charging Method */ }; +enum power_supply_usb_type { + POWER_SUPPLY_USB_TYPE_UNKNOWN = 0, + POWER_SUPPLY_USB_TYPE_SDP, /* Standard Downstream Port */ + POWER_SUPPLY_USB_TYPE_DCP, /* Dedicated Charging Port */ + POWER_SUPPLY_USB_TYPE_CDP, /* Charging Downstream Port */ + POWER_SUPPLY_USB_TYPE_ACA, /* Accessory Charger Adapters */ + POWER_SUPPLY_USB_TYPE_C, /* Type C Port */ + POWER_SUPPLY_USB_TYPE_PD, /* Power Delivery Port */ + POWER_SUPPLY_USB_TYPE_PD_DRP, /* PD Dual Role Port */ + POWER_SUPPLY_USB_TYPE_PD_PPS, /* PD Programmable Power Supply */ + POWER_SUPPLY_USB_TYPE_APPLE_BRICK_ID, /* Apple Charging Method */ +}; + enum power_supply_notifier_events { PSY_EVENT_PROP_CHANGED, }; @@ -196,6 +210,8 @@ struct power_supply_config { struct power_supply_desc { const char *name; enum power_supply_type type; + enum power_supply_usb_type *usb_types; + size_t num_usb_types; enum power_supply_property *properties; size_t num_properties; -- cgit v1.2.3 From 7d775f63470c3b6ddf34c770c973293ab925a7bb Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 3 Apr 2018 17:16:03 -0400 Subject: macvlan: Rename fwd_priv to accel_priv and add accessor function This change renames the fwd_priv member to accel_priv as this more accurately reflects the actual purpose of this value. In addition I am adding an accessor which will allow us to further abstract this in the future if needed. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/if_macvlan.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 4cb7aeeafce0..c5106ce8273a 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -21,7 +21,7 @@ struct macvlan_dev { struct hlist_node hlist; struct macvlan_port *port; struct net_device *lowerdev; - void *fwd_priv; + void *accel_priv; struct vlan_pcpu_stats __percpu *pcpu_stats; DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ); @@ -86,4 +86,10 @@ macvlan_dev_real_dev(const struct net_device *dev) } #endif +static inline void *macvlan_accel_priv(struct net_device *dev) +{ + struct macvlan_dev *macvlan = netdev_priv(dev); + + return macvlan->accel_priv; +} #endif /* _LINUX_IF_MACVLAN_H */ -- cgit v1.2.3 From a222311283641c9a476426ccacb2a3c82bfe5aaa Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 3 Apr 2018 17:16:19 -0400 Subject: macvlan: macvlan_count_rx shouldn't be static inline AND extern It doesn't make sense to define macvlan_count_rx as a static inline and then add a forward declaration after that as an extern. I am dropping the extern declaration since it seems like it is something that likely got missed when the function was made an inline. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/if_macvlan.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index c5106ce8273a..80089d6c5a0a 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -61,10 +61,6 @@ extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); -extern void macvlan_count_rx(const struct macvlan_dev *vlan, - unsigned int len, bool success, - bool multicast); - extern void macvlan_dellink(struct net_device *dev, struct list_head *head); extern int macvlan_link_register(struct rtnl_link_ops *ops); -- cgit v1.2.3 From 6cb1937d4eff6936089139169377fda208a2701a Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 3 Apr 2018 17:16:25 -0400 Subject: macvlan: Add function to test for destination filtering support This patch adds a function indicating if a given macvlan can fully supports destination filtering, especially as it relates to unicast traffic. For those macvlan interfaces that do not support destination filtering such passthru or source mode filtering we should not be enabling offload support. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/if_macvlan.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 80089d6c5a0a..0221390668a0 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -88,4 +88,13 @@ static inline void *macvlan_accel_priv(struct net_device *dev) return macvlan->accel_priv; } + +static inline bool macvlan_supports_dest_filter(struct net_device *dev) +{ + struct macvlan_dev *macvlan = netdev_priv(dev); + + return macvlan->mode == MACVLAN_MODE_PRIVATE || + macvlan->mode == MACVLAN_MODE_VEPA || + macvlan->mode == MACVLAN_MODE_BRIDGE; +} #endif /* _LINUX_IF_MACVLAN_H */ -- cgit v1.2.3 From 53cd4d8e4dfb231fa5ba125b6c0666b82a0504fa Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 3 Apr 2018 17:16:30 -0400 Subject: macvlan: Provide function for interfaces to release HW offload This patch provides a basic function to allow a lower device to disable macvlan offload if it was previously enabled on a given macvlan. The idea here is to allow for recovery from failure should the lowerdev run out of resources. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/if_macvlan.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 0221390668a0..2e55e4cdbd8a 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -97,4 +97,12 @@ static inline bool macvlan_supports_dest_filter(struct net_device *dev) macvlan->mode == MACVLAN_MODE_VEPA || macvlan->mode == MACVLAN_MODE_BRIDGE; } + +static inline int macvlan_release_l2fw_offload(struct net_device *dev) +{ + struct macvlan_dev *macvlan = netdev_priv(dev); + + macvlan->accel_priv = NULL; + return dev_uc_add(macvlan->lowerdev, dev->dev_addr); +} #endif /* _LINUX_IF_MACVLAN_H */ -- cgit v1.2.3 From 3eb0f5193b497083391aa05d35210d5645211eef Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 17 Apr 2018 15:26:37 -0500 Subject: signal: Ensure every siginfo we send has all bits initialized Call clear_siginfo to ensure every stack allocated siginfo is properly initialized before being passed to the signal sending functions. Note: It is not safe to depend on C initializers to initialize struct siginfo on the stack because C is allowed to skip holes when initializing a structure. The initialization of struct siginfo in tracehook_report_syscall_exit was moved from the helper user_single_step_siginfo into tracehook_report_syscall_exit itself, to make it clear that the local variable siginfo gets fully initialized. In a few cases the scope of struct siginfo has been reduced to make it clear that siginfo siginfo is not used on other paths in the function in which it is declared. Instances of using memset to initialize siginfo have been replaced with calls clear_siginfo for clarity. Signed-off-by: "Eric W. Biederman" --- include/linux/ptrace.h | 1 - include/linux/tracehook.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 919b2a0b0307..037bf0ef1ae9 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -345,7 +345,6 @@ extern void user_single_step_siginfo(struct task_struct *tsk, static inline void user_single_step_siginfo(struct task_struct *tsk, struct pt_regs *regs, siginfo_t *info) { - memset(info, 0, sizeof(*info)); info->si_signo = SIGTRAP; } #endif diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 26c152122a42..4a8841963c2e 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -124,6 +124,7 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) { if (step) { siginfo_t info; + clear_siginfo(&info); user_single_step_siginfo(current, regs, &info); force_sig_info(SIGTRAP, &info, current); return; -- cgit v1.2.3 From 5ef6a16033b47afbc578c7ef8754da5ae7b198d7 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Sat, 21 Apr 2018 18:12:49 -0500 Subject: power: supply: bq27xxx: Add support for BQ27426 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This device is software similar to the BQ27426 except it has different data memory offsets. Add support here. Signed-off-by: Andrew F. Davis Acked-by: Pali Rohár Signed-off-by: Sebastian Reichel --- include/linux/power/bq27xxx_battery.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 01fbf1b16258..d6355f49fbae 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -24,8 +24,9 @@ enum bq27xxx_chip { BQ27546, BQ27742, BQ27545, /* bq27545 */ - BQ27421, /* bq27421, bq27425, bq27441, bq27621 */ + BQ27421, /* bq27421, bq27441, bq27621 */ BQ27425, + BQ27426, BQ27441, BQ27621, }; -- cgit v1.2.3 From 4c4268dc97c424cf6786c4ccc9acf345ba911987 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 22 Mar 2018 11:24:35 +0100 Subject: power: supply: ab8500: Drop AB8540/9540 support The AB8540 was an evolved version of the AB8500, but it was never mass produced or put into products, only reference designs exist. The upstream support was never completed and it is unlikely that this will happen so drop the support for now to simplify maintenance of the AB8500. Cc: Loic Pallardy Signed-off-by: Linus Walleij Acked-by: Lee Jones Signed-off-by: Sebastian Reichel --- include/linux/mfd/abx500.h | 1 - include/linux/mfd/abx500/ab8500-bm.h | 2 -- include/linux/mfd/abx500/ux500_chargalg.h | 4 ---- 3 files changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h index 44412c9d26e1..aa09414756db 100644 --- a/include/linux/mfd/abx500.h +++ b/include/linux/mfd/abx500.h @@ -271,7 +271,6 @@ struct abx500_bm_data { bool autopower_cfg; bool ac_enabled; bool usb_enabled; - bool usb_power_path; bool no_maintenance; bool capacity_scaling; bool chg_unknown_bat; diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h index e63681eb6c62..c06daf3d490a 100644 --- a/include/linux/mfd/abx500/ab8500-bm.h +++ b/include/linux/mfd/abx500/ab8500-bm.h @@ -248,8 +248,6 @@ enum bup_vch_sel { #define BAT_CTRL_20U_ENA 0x02 #define BAT_CTRL_18U_ENA 0x01 #define BAT_CTRL_16U_ENA 0x02 -#define BAT_CTRL_60U_ENA 0x01 -#define BAT_CTRL_120U_ENA 0x02 #define BAT_CTRL_CMP_ENA 0x04 #define FORCE_BAT_CTRL_CMP_HIGH 0x08 #define BAT_CTRL_PULL_UP_ENA 0x10 diff --git a/include/linux/mfd/abx500/ux500_chargalg.h b/include/linux/mfd/abx500/ux500_chargalg.h index 67703f23e7ba..669894f434f5 100644 --- a/include/linux/mfd/abx500/ux500_chargalg.h +++ b/include/linux/mfd/abx500/ux500_chargalg.h @@ -25,8 +25,6 @@ struct ux500_charger_ops { int (*check_enable) (struct ux500_charger *, int, int); int (*kick_wd) (struct ux500_charger *); int (*update_curr) (struct ux500_charger *, int); - int (*pp_enable) (struct ux500_charger *, bool); - int (*pre_chg_enable) (struct ux500_charger *, bool); }; /** @@ -37,7 +35,6 @@ struct ux500_charger_ops { * @max_out_curr maximum output charger current in mA * @enabled indicates if this charger is used or not * @external external charger unit (pm2xxx) - * @power_path USB power path support */ struct ux500_charger { struct power_supply *psy; @@ -47,7 +44,6 @@ struct ux500_charger { int wdt_refresh; bool enabled; bool external; - bool power_path; }; extern struct blocking_notifier_head charger_notifier_list; -- cgit v1.2.3 From 227abcc6da7b803e380f034d6772ea0861612340 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 26 Apr 2018 08:58:27 +0300 Subject: staging: kernel.h: Prevent macro expantion bug in container_of_safe() There aren't many users of this so it doesn't cause a problem, but we obviously want to use "__mptr" here instead of "ptr" to prevent the parameter from being executed twice. Signed-off-by: Dan Carpenter Acked-by: NeilBrown Signed-off-by: Greg Kroah-Hartman --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 58d6645b1425..3dfa3f260fc4 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -977,7 +977,7 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ !__same_type(*(ptr), void), \ "pointer type mismatch in container_of()"); \ - IS_ERR_OR_NULL(ptr) ? ERR_CAST(ptr) : \ + IS_ERR_OR_NULL(__mptr) ? ERR_CAST(__mptr) : \ ((type *)(__mptr - offsetof(type, member))); }) /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ -- cgit v1.2.3 From e1b63c0148a7f8edf1691770ec0527fe86fb6ab8 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 24 Apr 2018 10:04:32 +0200 Subject: HID: store the full list of reports in the hidinput We were only storing the report in case of QUIRK_MULTI_INPUT. It is interesting for the upcoming HID_QUIRK_INPUT_PER_APP to also store the full list of reports that are attached to it. We need the full list because a device (Advanced Silicon has some) might want to use a different report ID for the Input reports and the Output reports. Storing the full list allows the drivers to have all the data. Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 0267aa5c1ea3..396068ccc197 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -464,6 +464,7 @@ struct hid_field { struct hid_report { struct list_head list; + struct list_head hidinput_list; unsigned id; /* id of this report */ unsigned type; /* report type */ struct hid_field *field[HID_MAX_FIELDS]; /* fields of the report */ @@ -510,6 +511,7 @@ struct hid_input { struct hid_report *report; struct input_dev *input; bool registered; + struct list_head reports; /* the list of reports */ }; enum hid_type { -- cgit v1.2.3 From f07b3c1da92db108662f99417a212fc1eddc44d1 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 24 Apr 2018 10:04:33 +0200 Subject: HID: generic: create one input report per application type It is not a good idea to try to fit all types of applications in the same input report. There are a lot of devices that are needing the quirk HID_MULTI_INPUT but this quirk doesn't match the actual HID description as it is based on the report ID. Given that most devices with MULTI_INPUT I can think of split nicely the devices inputs into application, it is a good thing to split the devices by default based on this assumption. Also make hid-multitouch following this rule, to not have to deal with too many input created. While we are at it, fix some checkpatch complaints about converting 'unsigned' to 'unsigned int'. Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 396068ccc197..bcc91bfdd2cb 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -341,6 +341,7 @@ struct hid_item { /* BIT(8) reserved for backward compatibility, was HID_QUIRK_NO_EMPTY_INPUT */ /* BIT(9) reserved for backward compatibility, was NO_INIT_INPUT_REPORTS */ #define HID_QUIRK_ALWAYS_POLL BIT(10) +#define HID_QUIRK_INPUT_PER_APP BIT(11) #define HID_QUIRK_SKIP_OUTPUT_REPORTS BIT(16) #define HID_QUIRK_SKIP_OUTPUT_REPORT_ID BIT(17) #define HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP BIT(18) @@ -465,8 +466,9 @@ struct hid_field { struct hid_report { struct list_head list; struct list_head hidinput_list; - unsigned id; /* id of this report */ - unsigned type; /* report type */ + unsigned int id; /* id of this report */ + unsigned int type; /* report type */ + unsigned int application; /* application usage for this report */ struct hid_field *field[HID_MAX_FIELDS]; /* fields of the report */ unsigned maxfield; /* maximum valid field index */ unsigned size; /* size of the report (bits) */ @@ -861,7 +863,9 @@ void hid_output_report(struct hid_report *report, __u8 *data); void __hid_request(struct hid_device *hid, struct hid_report *rep, int reqtype); u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags); struct hid_device *hid_allocate_device(void); -struct hid_report *hid_register_report(struct hid_device *device, unsigned type, unsigned id); +struct hid_report *hid_register_report(struct hid_device *device, + unsigned int type, unsigned int id, + unsigned int application); int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size); struct hid_report *hid_validate_values(struct hid_device *hid, unsigned int type, unsigned int id, -- cgit v1.2.3 From c554bb045511bd6b498b6a61cffa48e473853703 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 24 Apr 2018 10:04:34 +0200 Subject: HID: input: append a suffix matching the application Given that we create one input node per application, we should name the input node accordingly to not lose userspace. Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index bcc91bfdd2cb..f03d7a410c5d 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -512,6 +512,7 @@ struct hid_input { struct list_head list; struct hid_report *report; struct input_dev *input; + const char *name; bool registered; struct list_head reports; /* the list of reports */ }; -- cgit v1.2.3 From 02946f4b43b11026b1a76857a33b09078b900939 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 24 Apr 2018 10:04:37 +0200 Subject: HID: multitouch: implement precision touchpad latency and switches The Win 8.1 precision touchpad spec introduce new modes for touchpads that can come in handy[1]. Implement the settings of these modes, so we are not taken off-guard if a firmware decides to enforce them. [1] https://docs.microsoft.com/en-us/windows-hardware/design/component-guidelines/windows-precision-touchpad-required-hid-top-level-collections Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index f03d7a410c5d..a1be991e1eae 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -292,9 +292,12 @@ struct hid_item { #define HID_DG_CONTACTCOUNT 0x000d0054 #define HID_DG_CONTACTMAX 0x000d0055 #define HID_DG_SCANTIME 0x000d0056 +#define HID_DG_SURFACESWITCH 0x000d0057 +#define HID_DG_BUTTONSWITCH 0x000d0058 #define HID_DG_BUTTONTYPE 0x000d0059 #define HID_DG_BARRELSWITCH2 0x000d005a #define HID_DG_TOOLSERIALNUMBER 0x000d005b +#define HID_DG_LATENCYMODE 0x000d0060 #define HID_VD_ASUS_CUSTOM_MEDIA_KEYS 0xff310076 /* -- cgit v1.2.3 From ee80d1ebe5ba7f4bd74959c873119175a4fc08d3 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 26 Apr 2018 13:42:16 -0400 Subject: udp: add udp gso Implement generic segmentation offload support for udp datagrams. A follow-up patch adds support to the protocol stack to generate such packets. UDP GSO is not UFO. UFO fragments a single large datagram. GSO splits a large payload into a number of discrete UDP datagrams. The implementation adds a GSO type SKB_UDP_GSO_L4 to differentiate it from UFO (SKB_UDP_GSO). IPPROTO_UDPLITE is excluded, as that protocol has no gso handler registered. [ Export __udp_gso_segment for ipv6. -DaveM ] Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d274059529eb..a4a5c0c5cba8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -573,6 +573,8 @@ enum { SKB_GSO_ESP = 1 << 15, SKB_GSO_UDP = 1 << 16, + + SKB_GSO_UDP_L4 = 1 << 17, }; #if BITS_PER_LONG > 32 -- cgit v1.2.3 From bec1f6f697362c5bc635dacd7ac8499d0a10a4e7 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 26 Apr 2018 13:42:17 -0400 Subject: udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/udp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index eaea63bc79bb..ca840345571b 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -55,6 +55,7 @@ struct udp_sock { * when the socket is uncorked. */ __u16 len; /* total length of pending frames */ + __u16 gso_size; /* * Fields specific to UDP-Lite. */ @@ -87,6 +88,8 @@ struct udp_sock { int forward_deficit; }; +#define UDP_MAX_SEGMENTS (1 << 6UL) + static inline struct udp_sock *udp_sk(const struct sock *sk) { return (struct udp_sock *)sk; -- cgit v1.2.3 From 83aa025f535f76733e334e3d2a4d8577c8441a7e Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 26 Apr 2018 13:42:21 -0400 Subject: udp: add gso support to virtual devices Virtual devices such as tunnels and bonding can handle large packets. Only segment packets when reaching a physical or loopback device. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 5 ++++- include/linux/netdevice.h | 1 + 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 35b79f47a13d..fe2f3b30960e 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -55,8 +55,9 @@ enum { NETIF_F_GSO_SCTP_BIT, /* ... SCTP fragmentation */ NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */ NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */ + NETIF_F_GSO_UDP_L4_BIT, /* ... UDP payload GSO (not UFO) */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ - NETIF_F_GSO_UDP_BIT, + NETIF_F_GSO_UDP_L4_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ @@ -147,6 +148,7 @@ enum { #define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM) #define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT) #define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD) +#define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) @@ -216,6 +218,7 @@ enum { NETIF_F_GSO_GRE_CSUM | \ NETIF_F_GSO_IPXIP4 | \ NETIF_F_GSO_IPXIP6 | \ + NETIF_F_GSO_UDP_L4 | \ NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 14e0777ffcfb..366c32891158 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4186,6 +4186,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } -- cgit v1.2.3 From b5c5f3959bb3c018a68f5659bcd6adf05e141a03 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 26 Apr 2018 22:07:47 +0200 Subject: genirq/irq_sim: Use the SPDX license identifier in the header Use C-style comment for the identifier as per Documentation/process/license-rules.rst and remove the license boilerplate. Signed-off-by: Bartosz Golaszewski Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20180426200747.8344-2-brgl@bgdev.pl --- include/linux/irq_sim.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq_sim.h b/include/linux/irq_sim.h index 0380d899b955..630a57e55db6 100644 --- a/include/linux/irq_sim.h +++ b/include/linux/irq_sim.h @@ -1,14 +1,11 @@ -#ifndef _LINUX_IRQ_SIM_H -#define _LINUX_IRQ_SIM_H +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * Copyright (C) 2017 Bartosz Golaszewski - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. + * Copyright (C) 2017-2018 Bartosz Golaszewski */ +#ifndef _LINUX_IRQ_SIM_H +#define _LINUX_IRQ_SIM_H + #include #include -- cgit v1.2.3 From b12e35832805bf120819b83d8fdb6e4d227a5ddb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 26 Apr 2018 14:29:04 -0700 Subject: cgroup: Limit event generation frequency ".events" files generate file modified event to notify userland of possible new events. Some of the events can be quite bursty (e.g. memory high event) and generating notification each time is costly and pointless. This patch implements a event rate limit mechanism. If a new notification is requested before 10ms has passed since the previous notification, the new notification is delayed till then. As this only delays from the second notification on in a given close cluster of notifications, userland reactions to notifications shouldn't be delayed at all in most cases while avoiding notification storms. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index dc5b70449dc6..133531fcfb33 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -105,6 +105,8 @@ enum { struct cgroup_file { /* do not access any fields from outside cgroup core */ struct kernfs_node *kn; + unsigned long notified_at; + struct timer_list notify_timer; }; /* -- cgit v1.2.3 From c58632b3631cb222da41d9dc0dd39e106c1eafd0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 26 Apr 2018 14:29:04 -0700 Subject: cgroup: Rename stat to rstat stat is too generic a name and ends up causing subtle confusions. It'll be made generic so that controllers can plug into it, which will make the problem worse. Let's rename it to something more specific - cgroup_rstat for cgroup recursive stat. This patch does the following renames. No other changes. * cpu_stat -> rstat_cpu * stat -> rstat * ?cstat -> ?rstatc Note that the renames are selective. The unrenamed are the ones which implement basic resource statistics on top of rstat. This will be further cleaned up in the following patches. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 133531fcfb33..04cb42419310 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -259,11 +259,11 @@ struct css_set { }; /* - * cgroup basic resource usage statistics. Accounting is done per-cpu in - * cgroup_cpu_stat which is then lazily propagated up the hierarchy on - * reads. + * rstat - cgroup scalable recursive statistics. Accounting is done + * per-cpu in cgroup_rstat_cpu which is then lazily propagated up the + * hierarchy on reads. * - * When a stat gets updated, the cgroup_cpu_stat and its ancestors are + * When a stat gets updated, the cgroup_rstat_cpu and its ancestors are * linked into the updated tree. On the following read, propagation only * considers and consumes the updated tree. This makes reading O(the * number of descendants which have been active since last read) instead of @@ -274,7 +274,7 @@ struct css_set { * become very expensive. By propagating selectively, increasing reading * frequency decreases the cost of each read. */ -struct cgroup_cpu_stat { +struct cgroup_rstat_cpu { /* * ->sync protects all the current counters. These are the only * fields which get updated in the hot path. @@ -297,7 +297,7 @@ struct cgroup_cpu_stat { * to the cgroup makes it unnecessary for each per-cpu struct to * point back to the associated cgroup. * - * Protected by per-cpu cgroup_cpu_stat_lock. + * Protected by per-cpu cgroup_rstat_cpu_lock. */ struct cgroup *updated_children; /* terminated by self cgroup */ struct cgroup *updated_next; /* NULL iff not on the list */ @@ -408,8 +408,10 @@ struct cgroup { */ struct cgroup *dom_cgrp; + /* per-cpu recursive resource statistics */ + struct cgroup_rstat_cpu __percpu *rstat_cpu; + /* cgroup basic resource statistics */ - struct cgroup_cpu_stat __percpu *cpu_stat; struct cgroup_stat pending_stat; /* pending from children */ struct cgroup_stat stat; -- cgit v1.2.3 From d4ff749b5e0f1e2d4d69a3e4ea81cdeaeb4904d2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 26 Apr 2018 14:29:04 -0700 Subject: cgroup: Distinguish base resource stat implementation from rstat Base resource stat accounts universial (not specific to any controller) resource consumptions on top of rstat. Currently, its implementation is intermixed with rstat implementation making the code confusing to follow. This patch clarifies the distintion by doing the followings. * Encapsulate base resource stat counters, currently only cputime, in struct cgroup_base_stat. * Move prev_cputime into struct cgroup and initialize it with cgroup. * Rename the related functions so that they start with cgroup_base_stat. * Prefix the related variables and field names with b. This patch doesn't make any functional changes. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 04cb42419310..60d62fe97dc3 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -258,6 +258,10 @@ struct css_set { struct rcu_head rcu_head; }; +struct cgroup_base_stat { + struct task_cputime cputime; +}; + /* * rstat - cgroup scalable recursive statistics. Accounting is done * per-cpu in cgroup_rstat_cpu which is then lazily propagated up the @@ -273,20 +277,24 @@ struct css_set { * aren't active and stat may be read frequently. The combination can * become very expensive. By propagating selectively, increasing reading * frequency decreases the cost of each read. + * + * This struct hosts both the fields which implement the above - + * updated_children and updated_next - and the fields which track basic + * resource statistics on top of it - bsync, bstat and last_bstat. */ struct cgroup_rstat_cpu { /* - * ->sync protects all the current counters. These are the only - * fields which get updated in the hot path. + * ->bsync protects ->bstat. These are the only fields which get + * updated in the hot path. */ - struct u64_stats_sync sync; - struct task_cputime cputime; + struct u64_stats_sync bsync; + struct cgroup_base_stat bstat; /* * Snapshots at the last reading. These are used to calculate the * deltas to propagate to the global counters. */ - struct task_cputime last_cputime; + struct cgroup_base_stat last_bstat; /* * Child cgroups with stat updates on this cpu since the last read @@ -303,12 +311,6 @@ struct cgroup_rstat_cpu { struct cgroup *updated_next; /* NULL iff not on the list */ }; -struct cgroup_stat { - /* per-cpu statistics are collected into the folowing global counters */ - struct task_cputime cputime; - struct prev_cputime prev_cputime; -}; - struct cgroup { /* self css with NULL ->ss, points back to this cgroup */ struct cgroup_subsys_state self; @@ -412,8 +414,9 @@ struct cgroup { struct cgroup_rstat_cpu __percpu *rstat_cpu; /* cgroup basic resource statistics */ - struct cgroup_stat pending_stat; /* pending from children */ - struct cgroup_stat stat; + struct cgroup_base_stat pending_bstat; /* pending from children */ + struct cgroup_base_stat bstat; + struct prev_cputime prev_cputime; /* for printing out cputime */ /* * list of pidlists, up to two for each namespace (one for procs, one -- cgit v1.2.3 From 6162cef0f741c70eb0c7ac7e6142f85808d8abc4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 26 Apr 2018 14:29:05 -0700 Subject: cgroup: Factor out and expose cgroup_rstat_*() interface functions cgroup_rstat is being generalized so that controllers can use it too. This patch factors out and exposes the following interface functions. * cgroup_rstat_updated(): Renamed from cgroup_rstat_cpu_updated() for consistency. * cgroup_rstat_flush_hold/release(): Factored out from base stat implementation. * cgroup_rstat_flush(): Verbatim expose. While at it, drop assert on cgroup_rstat_mutex in cgroup_base_stat_flush() as it crosses layers and make a minor comment update. v2: Added EXPORT_SYMBOL_GPL(cgroup_rstat_updated) to fix a build bug. Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 473e0c0abb86..5c6018fef5aa 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -690,11 +690,18 @@ static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, char *buf, size_t buflen) {} #endif /* !CONFIG_CGROUPS */ +#ifdef CONFIG_CGROUPS /* - * Basic resource stats. + * cgroup scalable recursive statistics. */ -#ifdef CONFIG_CGROUPS +void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); +void cgroup_rstat_flush(struct cgroup *cgrp); +void cgroup_rstat_flush_hold(struct cgroup *cgrp); +void cgroup_rstat_flush_release(void); +/* + * Basic resource stats. + */ #ifdef CONFIG_CGROUP_CPUACCT void cpuacct_charge(struct task_struct *tsk, u64 cputime); void cpuacct_account_field(struct task_struct *tsk, int index, u64 val); -- cgit v1.2.3 From 0fa294fb1985c06c4e3325e30e759d4ca580f59a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 26 Apr 2018 14:29:05 -0700 Subject: cgroup: Replace cgroup_rstat_mutex with a spinlock Currently, rstat flush path is protected with a mutex which is fine as all the existing users are from interface file show path. However, rstat is being generalized for use by controllers and flushing from atomic contexts will be necessary. This patch replaces cgroup_rstat_mutex with a spinlock and adds a irq-safe flush function - cgroup_rstat_flush_irqsafe(). Explicit yield handling is added to the flush path so that other flush functions can yield to other threads and flushers. Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5c6018fef5aa..c9fdf6f57913 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -696,6 +696,7 @@ static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); +void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); void cgroup_rstat_flush_release(void); -- cgit v1.2.3 From 8f53470bab04229e93ff9e4c20338cc08b42b344 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 26 Apr 2018 14:29:05 -0700 Subject: cgroup: Add cgroup_subsys->css_rstat_flush() This patch adds cgroup_subsys->css_rstat_flush(). If a subsystem has this callback, its csses are linked on cgrp->css_rstat_list and rstat will call the function whenever the associated cgroup is flushed. Flush is also performed when such csses are released so that residual counts aren't lost. Combined with the rstat API previous patches factored out, this allows controllers to plug into rstat to manage their statistics in a scalable way. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 60d62fe97dc3..c0e68f903011 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -130,6 +130,9 @@ struct cgroup_subsys_state { struct list_head sibling; struct list_head children; + /* flush target list anchored at cgrp->rstat_css_list */ + struct list_head rstat_css_node; + /* * PI: Subsys-unique ID. 0 is unused and root is always 1. The * matching css can be looked up using css_from_id(). @@ -412,6 +415,7 @@ struct cgroup { /* per-cpu recursive resource statistics */ struct cgroup_rstat_cpu __percpu *rstat_cpu; + struct list_head rstat_css_list; /* cgroup basic resource statistics */ struct cgroup_base_stat pending_bstat; /* pending from children */ @@ -577,6 +581,7 @@ struct cgroup_subsys { void (*css_released)(struct cgroup_subsys_state *css); void (*css_free)(struct cgroup_subsys_state *css); void (*css_reset)(struct cgroup_subsys_state *css); + void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu); int (*css_extra_stat_show)(struct seq_file *seq, struct cgroup_subsys_state *css); -- cgit v1.2.3 From 31931c93dfe05a76385a443ed28244a50e915a46 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 24 Apr 2018 20:59:47 -0500 Subject: signal: Extend siginfo_layout with SIL_FAULT_{MCEERR|BNDERR|PKUERR} Update the siginfo_layout function and enum siginfo_layout to represent all of the possible field layouts of struct siginfo. This allows the uses of siginfo_layout in um and arm64 where they are testing for SIL_FAULT to be more accurate as this rules out the other cases. Further this allows the switch statements on siginfo_layout to be simpler if perhaps a little more wordy. Making it easier to understand what is actually going on. As SIL_FAULT_BNDERR and SIL_FAULT_PKUERR are never expected to appear in signalfd just treat them as SIL_FAULT. To include them would take 20 extra bytes an pretty much fill up what is left of signalfd_siginfo. Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index a9bc7e1b077e..3c5200137b24 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -28,6 +28,9 @@ enum siginfo_layout { SIL_TIMER, SIL_POLL, SIL_FAULT, + SIL_FAULT_MCEERR, + SIL_FAULT_BNDERR, + SIL_FAULT_PKUERR, SIL_CHLD, SIL_RT, SIL_SYS, -- cgit v1.2.3 From ab42ddb9eb71b580349b03e4fc5bfcf230422eb8 Mon Sep 17 00:00:00 2001 From: Eric Long Date: Thu, 19 Apr 2018 10:00:48 +0800 Subject: dmaengine: sprd: Move DMA request mode and interrupt type into head file This patch will move the Spreadtrum DMA request mode and interrupt type into one head file for user to configure. Signed-off-by: Eric Long Signed-off-by: Baolin Wang Signed-off-by: Vinod Koul --- include/linux/dma/sprd-dma.h | 57 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) create mode 100644 include/linux/dma/sprd-dma.h (limited to 'include/linux') diff --git a/include/linux/dma/sprd-dma.h b/include/linux/dma/sprd-dma.h new file mode 100644 index 000000000000..c545162e725b --- /dev/null +++ b/include/linux/dma/sprd-dma.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _SPRD_DMA_H_ +#define _SPRD_DMA_H_ + +/* + * enum sprd_dma_req_mode: define the DMA request mode + * @SPRD_DMA_FRAG_REQ: fragment request mode + * @SPRD_DMA_BLK_REQ: block request mode + * @SPRD_DMA_TRANS_REQ: transaction request mode + * @SPRD_DMA_LIST_REQ: link-list request mode + * + * We have 4 types request mode: fragment mode, block mode, transaction mode + * and linklist mode. One transaction can contain several blocks, one block can + * contain several fragments. Link-list mode means we can save several DMA + * configuration into one reserved memory, then DMA can fetch each DMA + * configuration automatically to start transfer. + */ +enum sprd_dma_req_mode { + SPRD_DMA_FRAG_REQ, + SPRD_DMA_BLK_REQ, + SPRD_DMA_TRANS_REQ, + SPRD_DMA_LIST_REQ, +}; + +/* + * enum sprd_dma_int_type: define the DMA interrupt type + * @SPRD_DMA_NO_INT: do not need generate DMA interrupts. + * @SPRD_DMA_FRAG_INT: fragment done interrupt when one fragment request + * is done. + * @SPRD_DMA_BLK_INT: block done interrupt when one block request is done. + * @SPRD_DMA_BLK_FRAG_INT: block and fragment interrupt when one fragment + * or one block request is done. + * @SPRD_DMA_TRANS_INT: tansaction done interrupt when one transaction + * request is done. + * @SPRD_DMA_TRANS_FRAG_INT: transaction and fragment interrupt when one + * transaction request or fragment request is done. + * @SPRD_DMA_TRANS_BLK_INT: transaction and block interrupt when one + * transaction request or block request is done. + * @SPRD_DMA_LIST_INT: link-list done interrupt when one link-list request + * is done. + * @SPRD_DMA_CFGERR_INT: configure error interrupt when configuration is + * incorrect. + */ +enum sprd_dma_int_type { + SPRD_DMA_NO_INT, + SPRD_DMA_FRAG_INT, + SPRD_DMA_BLK_INT, + SPRD_DMA_BLK_FRAG_INT, + SPRD_DMA_TRANS_INT, + SPRD_DMA_TRANS_FRAG_INT, + SPRD_DMA_TRANS_BLK_INT, + SPRD_DMA_LIST_INT, + SPRD_DMA_CFGERR_INT, +}; + +#endif -- cgit v1.2.3 From fcfdfe30e324725007e9dc5814b62a4c430ea909 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 26 Apr 2018 11:34:15 +0100 Subject: locking/barriers: Introduce smp_cond_load_relaxed() and atomic_cond_read_relaxed() Whilst we currently provide smp_cond_load_acquire() and atomic_cond_read_acquire(), there are cases where the ACQUIRE semantics are not required because of a subsequent fence or release operation once the conditional loop has exited. This patch adds relaxed versions of the conditional spinning primitives to avoid unnecessary barrier overhead on architectures such as arm64. Signed-off-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Acked-by: Waiman Long Cc: Linus Torvalds Cc: Thomas Gleixner Cc: boqun.feng@gmail.com Cc: linux-arm-kernel@lists.infradead.org Cc: paulmck@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1524738868-31318-2-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 8b276fd9a127..01ce3997cb42 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -654,6 +654,7 @@ static inline int atomic_dec_if_positive(atomic_t *v) } #endif +#define atomic_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) #define atomic_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) #ifdef CONFIG_GENERIC_ATOMIC64 @@ -1075,6 +1076,7 @@ static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v } #endif +#define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) #define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) #include -- cgit v1.2.3 From 02acc80d19edb0d5684c997b2004ad19f9f5236e Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 23 Apr 2018 18:10:23 +0200 Subject: delayacct: Use raw_spinlocks try_to_wake_up() might invoke delayacct_blkio_end() while holding the pi_lock (which is a raw_spinlock_t). delayacct_blkio_end() acquires task_delay_info.lock which is a spinlock_t. This causes a might sleep splat on -RT where non raw spinlocks are converted to 'sleeping' spinlocks. task_delay_info.lock is only held for a short amount of time so it's not a problem latency wise to make convert it to a raw spinlock. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: Balbir Singh Link: https://lkml.kernel.org/r/20180423161024.6710-1-bigeasy@linutronix.de --- include/linux/delayacct.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 5e335b6203f4..e6c0448ebcc7 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -29,7 +29,7 @@ #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { - spinlock_t lock; + raw_spinlock_t lock; unsigned int flags; /* Private per-task flags */ /* For each stat XXX, add following, aligned appropriately -- cgit v1.2.3 From c59530d0d5dccc96795af12c139f618182cf98db Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 25 Apr 2018 12:12:47 -0700 Subject: net: Move PHY statistics code into PHY library helpers In order to make it possible for network device drivers that do not necessarily have a phy_device attached, but still report PHY statistics, have a preliminary refactoring consisting in creating helper functions that encapsulate the PHY device driver knowledge within PHYLIB. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index f0b5870a6d40..6ca81395c545 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1066,6 +1066,26 @@ int phy_ethtool_nway_reset(struct net_device *ndev); #if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); void mdio_bus_exit(void); +int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); +int phy_ethtool_get_sset_count(struct phy_device *phydev); +int phy_ethtool_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data); +#else +int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data) +{ + return -EOPNOTSUPP; +} + +int phy_ethtool_get_sset_count(struct phy_device *phydev) +{ + return -EOPNOTSUPP; +} + +int phy_ethtool_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data) +{ + return -EOPNOTSUPP; +} #endif extern struct bus_type mdio_bus_type; -- cgit v1.2.3 From 9994338227179eaf8db6f4493504e108b1fae5fc Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 25 Apr 2018 12:12:48 -0700 Subject: net: Allow network devices to have PHY statistics Add a new callback: get_ethtool_phy_stats() which allows network device drivers not making use of the PHY library to return PHY statistics. Update ethtool_get_phy_stats(), __ethtool_get_sset_count() and __ethtool_get_strings() accordingly to interogate the network device about ETH_SS_PHY_STATS. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/ethtool.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index b32cd2062f18..f8a2245b70ac 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -312,6 +312,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * by kernel. Returns a negative error code or zero. * @get_fecparam: Get the network device Forward Error Correction parameters. * @set_fecparam: Set the network device Forward Error Correction parameters. + * @get_ethtool_phy_stats: Return extended statistics about the PHY device. + * This is only useful if the device maintains PHY statistics and + * cannot use the standard PHY library helpers. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -407,5 +410,7 @@ struct ethtool_ops { struct ethtool_fecparam *); int (*set_fecparam)(struct net_device *, struct ethtool_fecparam *); + void (*get_ethtool_phy_stats)(struct net_device *, + struct ethtool_stats *, u64 *); }; #endif /* _LINUX_ETHTOOL_H */ -- cgit v1.2.3 From 9e8d438e8ba43a38def2890a65a26917f2233a83 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 27 Apr 2018 12:41:49 -0700 Subject: net: phy: Fix modular PHYLIB build After commit c59530d0d5dc ("net: Move PHY statistics code into PHY library helpers") we made net/core/ethtool.c reference symbols which are part of the library which can be modular. David introduced a temporary fix with 1ecd6e8ad996 ("phy: Temporary build fix after phylib changes.") which would prevent such modularity. This is not desireable of course, so instead, just inline the functions into include/linux/phy.h to keep both options available. Fixes: c59530d0d5dc ("net: Move PHY statistics code into PHY library helpers") Fixes: 1ecd6e8ad996 ("phy: Temporary build fix after phylib changes.") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 50 ++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 38 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 6ca81395c545..073235e70442 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1066,27 +1066,53 @@ int phy_ethtool_nway_reset(struct net_device *ndev); #if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); void mdio_bus_exit(void); -int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); -int phy_ethtool_get_sset_count(struct phy_device *phydev); -int phy_ethtool_get_stats(struct phy_device *phydev, - struct ethtool_stats *stats, u64 *data); -#else -int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data) +#endif + +/* Inline function for use within net/core/ethtool.c (built-in) */ +static inline int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data) { - return -EOPNOTSUPP; + if (!phydev->drv) + return -EIO; + + mutex_lock(&phydev->lock); + phydev->drv->get_strings(phydev, data); + mutex_unlock(&phydev->lock); + + return 0; } -int phy_ethtool_get_sset_count(struct phy_device *phydev) +static inline int phy_ethtool_get_sset_count(struct phy_device *phydev) { + int ret; + + if (!phydev->drv) + return -EIO; + + if (phydev->drv->get_sset_count && + phydev->drv->get_strings && + phydev->drv->get_stats) { + mutex_lock(&phydev->lock); + ret = phydev->drv->get_sset_count(phydev); + mutex_unlock(&phydev->lock); + + return ret; + } + return -EOPNOTSUPP; } -int phy_ethtool_get_stats(struct phy_device *phydev, - struct ethtool_stats *stats, u64 *data) +static inline int phy_ethtool_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data) { - return -EOPNOTSUPP; + if (!phydev->drv) + return -EIO; + + mutex_lock(&phydev->lock); + phydev->drv->get_stats(phydev, stats, data); + mutex_unlock(&phydev->lock); + + return 0; } -#endif extern struct bus_type mdio_bus_type; -- cgit v1.2.3 From 256c4fc76a80a69a5108069d8a09b3836bbf6542 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Sun, 22 Apr 2018 18:02:30 +0200 Subject: mtd: rawnand: add a way to pass an ID table with nand_scan() As part of the work of migrating all the drivers to nand_scan(), and because nand_scan() does not provide a way to pass an ID table, rename the function nand_scan_with_ids() and add a third parameter to give a flash ID table (like what was done with nand_scan_ident()). Create a nand_scan() helper that is just a wrapper of nand_scan_with_ids(), passing NULL as the ID table. This way a controller drivers can continue using nand_scan() transparently. Signed-off-by: Miquel Raynal Signed-off-by: Boris Brezillon --- include/linux/mtd/rawnand.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 5dad59b31244..ba8d908f5cc7 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -28,7 +28,14 @@ struct nand_flash_dev; struct device_node; /* Scan and identify a NAND device */ -int nand_scan(struct mtd_info *mtd, int max_chips); +int nand_scan_with_ids(struct mtd_info *mtd, int max_chips, + struct nand_flash_dev *ids); + +static inline int nand_scan(struct mtd_info *mtd, int max_chips) +{ + return nand_scan_with_ids(mtd, max_chips, NULL); +} + /* * Separate phases of nand_scan(), allowing board driver to intervene * and override command or ECC setup according to flash type. -- cgit v1.2.3 From c195651e565ae7f41a68acb7d4aa7390ad215de1 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 28 Apr 2018 22:28:08 -0700 Subject: bpf: add bpf_get_stack helper Currently, stackmap and bpf_get_stackid helper are provided for bpf program to get the stack trace. This approach has a limitation though. If two stack traces have the same hash, only one will get stored in the stackmap table, so some stack traces are missing from user perspective. This patch implements a new helper, bpf_get_stack, will send stack traces directly to bpf program. The bpf program is able to see all stack traces, and then can do in-kernel processing or send stack traces to user space through shared map or bpf_perf_event_output. Acked-by: Alexei Starovoitov Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/linux/filter.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 38ebbc61ed99..c553f6f9c6b0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -692,6 +692,7 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; +extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; /* Shared helpers among cBPF and eBPF. */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 4da8b2308174..64899c04c1a6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -468,7 +468,8 @@ struct bpf_prog { dst_needed:1, /* Do we need dst entry? */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ - kprobe_override:1; /* Do we override a kprobe? */ + kprobe_override:1, /* Do we override a kprobe? */ + has_callchain_buf:1; /* callchain buffer allocated? */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ -- cgit v1.2.3 From 9cbe1f5a32dcd6d0508326f7d9098e5bc380a4fe Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 28 Apr 2018 22:28:11 -0700 Subject: bpf/verifier: improve register value range tracking with ARSH When helpers like bpf_get_stack returns an int value and later on used for arithmetic computation, the LSH and ARSH operations are often required to get proper sign extension into 64-bit. For example, without this patch: 54: R0=inv(id=0,umax_value=800) 54: (bf) r8 = r0 55: R0=inv(id=0,umax_value=800) R8_w=inv(id=0,umax_value=800) 55: (67) r8 <<= 32 56: R8_w=inv(id=0,umax_value=3435973836800,var_off=(0x0; 0x3ff00000000)) 56: (c7) r8 s>>= 32 57: R8=inv(id=0) With this patch: 54: R0=inv(id=0,umax_value=800) 54: (bf) r8 = r0 55: R0=inv(id=0,umax_value=800) R8_w=inv(id=0,umax_value=800) 55: (67) r8 <<= 32 56: R8_w=inv(id=0,umax_value=3435973836800,var_off=(0x0; 0x3ff00000000)) 56: (c7) r8 s>>= 32 57: R8=inv(id=0, umax_value=800,var_off=(0x0; 0x3ff)) With better range of "R8", later on when "R8" is added to other register, e.g., a map pointer or scalar-value register, the better register range can be derived and verifier failure may be avoided. In our later example, ...... usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); if (usize < 0) return 0; ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); ...... Without improving ARSH value range tracking, the register representing "max_len - usize" will have smin_value equal to S64_MIN and will be rejected by verifier. Acked-by: Alexei Starovoitov Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- include/linux/tnum.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tnum.h b/include/linux/tnum.h index 0d2d3da46139..c7dc2b5902c0 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -23,8 +23,10 @@ struct tnum tnum_range(u64 min, u64 max); /* Arithmetic and logical ops */ /* Shift a tnum left (by a fixed shift) */ struct tnum tnum_lshift(struct tnum a, u8 shift); -/* Shift a tnum right (by a fixed shift) */ +/* Shift (rsh) a tnum right (by a fixed shift) */ struct tnum tnum_rshift(struct tnum a, u8 shift); +/* Shift (arsh) a tnum right (by a fixed min_shift) */ +struct tnum tnum_arshift(struct tnum a, u8 min_shift); /* Add two tnums, return @a + @b */ struct tnum tnum_add(struct tnum a, struct tnum b); /* Subtract two tnums, return @a - @b */ -- cgit v1.2.3 From 1b837d489e06a5289753ddbee99cfbc26d251d6d Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 27 Apr 2018 14:06:53 -0400 Subject: net: Revoke export for __skb_tx_hash, update it to just be static skb_tx_hash I am dropping the export of __skb_tx_hash as after my patches nobody is using it outside of the net/core/dev.c file. In addition I am renaming and repurposing it to just be a static declaration of skb_tx_hash since that was the only user for it at this point. By doing this the compiler can inline it into __netdev_pick_tx as that will improve performance. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 366c32891158..82f5a9aba578 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3213,19 +3213,6 @@ static inline int netif_set_xps_queue(struct net_device *dev, } #endif -u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, - unsigned int num_tx_queues); - -/* - * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used - * as a distribution range limit for the returned value. - */ -static inline u16 skb_tx_hash(const struct net_device *dev, - struct sk_buff *skb) -{ - return __skb_tx_hash(dev, skb, dev->real_num_tx_queues); -} - /** * netif_is_multiqueue - test if device has multiple transmit queues * @dev: network device -- cgit v1.2.3 From 3ac305c386f698abccd0523c64a8aef248c89bc6 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 27 Apr 2018 13:11:14 -0700 Subject: net: core: Assert the size of netdev_featres_t We have about 53 netdev_features_t bits defined and counting, add a build time check to catch when an u64 type will not be enough and we will have to convert that to a bitmap. This is done in register_netdevice() for convenience. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 82f5a9aba578..9e09dd897b74 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4108,6 +4108,12 @@ const char *netdev_drivername(const struct net_device *dev); void linkwatch_run_queue(void); +static inline void netdev_features_size_check(void) +{ + BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE < + NETDEV_FEATURE_COUNT); +} + static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { -- cgit v1.2.3 From 4d220ed0f8140c478ab7b0a14d96821da639b646 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sat, 28 Apr 2018 19:56:37 -0700 Subject: bpf: remove tracepoints from bpf core tracepoints to bpf core were added as a way to provide introspection to bpf programs and maps, but after some time it became clear that this approach is inadequate, so prog_id, map_id and corresponding get_next_id, get_fd_by_id, get_info_by_fd, prog_query APIs were introduced and fully adopted by bpftool and other applications. The tracepoints in bpf core started to rot and causing syzbot warnings: WARNING: CPU: 0 PID: 3008 at kernel/trace/trace_event_perf.c:274 Kernel panic - not syncing: panic_on_warn set ... perf_trace_bpf_map_keyval+0x260/0xbd0 include/trace/events/bpf.h:228 trace_bpf_map_update_elem include/trace/events/bpf.h:274 [inline] map_update_elem kernel/bpf/syscall.c:597 [inline] SYSC_bpf kernel/bpf/syscall.c:1478 [inline] Hence this patch deletes tracepoints in bpf core. Reported-by: Eric Biggers Reported-by: syzbot Signed-off-by: Alexei Starovoitov Acked-by: David S. Miller Signed-off-by: Daniel Borkmann --- include/linux/bpf_trace.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_trace.h b/include/linux/bpf_trace.h index e6fe98ae3794..ddf896abcfb6 100644 --- a/include/linux/bpf_trace.h +++ b/include/linux/bpf_trace.h @@ -2,7 +2,6 @@ #ifndef __LINUX_BPF_TRACE_H__ #define __LINUX_BPF_TRACE_H__ -#include #include #endif /* __LINUX_BPF_TRACE_H__ */ -- cgit v1.2.3 From 6552d3141064f09736580dc2dc527019762cbf71 Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Thu, 8 Mar 2018 11:20:45 -0800 Subject: backlight: Add RAVE SP backlight driver This driver provides access to RAVE SP backlight control functionality. Signed-off-by: Andrey Smirnov Acked-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/mfd/rave-sp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rave-sp.h b/include/linux/mfd/rave-sp.h index 796fb9794c9e..fe0ce7bc59cf 100644 --- a/include/linux/mfd/rave-sp.h +++ b/include/linux/mfd/rave-sp.h @@ -21,6 +21,7 @@ enum rave_sp_command { RAVE_SP_CMD_STATUS = 0xA0, RAVE_SP_CMD_SW_WDT = 0xA1, RAVE_SP_CMD_PET_WDT = 0xA2, + RAVE_SP_CMD_SET_BACKLIGHT = 0xA6, RAVE_SP_CMD_RESET = 0xA7, RAVE_SP_CMD_RESET_REASON = 0xA8, -- cgit v1.2.3 From 3157694d8c7fed9046dece8b63434cafef21cbf6 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 28 Mar 2018 19:03:25 +0200 Subject: pwm-backlight: Add support for PWM delays proprieties. Some panels (i.e. N116BGE-L41), in their power sequence specifications, request a delay between set the PWM signal and enable the backlight and between clear the PWM signal and disable the backlight. Add support for the new post-pwm-on-delay-ms and pwm-off-delay-ms proprieties to meet the timings. Signed-off-by: Enric Balletbo i Serra Acked-by: Pavel Machek Acked-by: Daniel Thompson Acked-by: Jingoo Han Acked-by: Thierry Reding Signed-off-by: Lee Jones --- include/linux/pwm_backlight.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm_backlight.h b/include/linux/pwm_backlight.h index e8afbd71a140..8ea265a022fd 100644 --- a/include/linux/pwm_backlight.h +++ b/include/linux/pwm_backlight.h @@ -14,6 +14,8 @@ struct platform_pwm_backlight_data { unsigned int lth_brightness; unsigned int pwm_period_ns; unsigned int *levels; + unsigned int post_pwm_on_delay; + unsigned int pwm_off_delay; /* TODO remove once all users are switched to gpiod_* API */ int enable_gpio; int (*init)(struct device *dev); -- cgit v1.2.3 From 3a0c991fe3b48be02373102b1d06cb99934f0bee Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 25 Apr 2018 19:42:48 +0200 Subject: backlight: Nuke unused backlight.props.state states The backlight power state handling is supremely confusing. We have: - props.power, using FB_BLANK_* defines - props.fb_blank, using the same, but deprecated int favour of props.state - props.state, using the BL_CORE_* defines - and finally a bunch of backlight drivers treat brightness == 0 as off. But of course not all of them. This is way too much confusion to fix in a simple patch, but at least prevent more hilarity from spreading by removing the unused BL_CORE_* defines. I have no idea why exactly anyone would need that. Wrt the ideal state, we really just want a boolean state. The 4 power saving states that the fbdev subsystem uses are overkill in todays hw (this was only relevant for VGA and similar analog circuits like TV-out), the new drm atomic modeset api simplified even the uapi to a simple bool. And there was never a valid technical reason to have the intermediate fbdev power states for backlights (those really only can be either off or on). Cleanup motivated by Meghana's questions about all this. Signed-off-by: Daniel Vetter Acked-by: Daniel Thompson Acked-by: Jingoo Han Reviewed-by: Jani Nikula Signed-off-by: Lee Jones --- include/linux/backlight.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 2baab6f3861d..1db67662bfcb 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -84,9 +84,6 @@ struct backlight_properties { #define BL_CORE_SUSPENDED (1 << 0) /* backlight is suspended */ #define BL_CORE_FBBLANK (1 << 1) /* backlight is under an fb blank event */ -#define BL_CORE_DRIVER4 (1 << 28) /* reserved for driver specific use */ -#define BL_CORE_DRIVER3 (1 << 29) /* reserved for driver specific use */ -#define BL_CORE_DRIVER2 (1 << 30) /* reserved for driver specific use */ #define BL_CORE_DRIVER1 (1 << 31) /* reserved for driver specific use */ }; -- cgit v1.2.3 From 3cf91adaa594e8933af1727942ac560e5c7bc70e Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 25 Apr 2018 19:42:52 +0200 Subject: backlight: Nuke BL_CORE_DRIVER1 Now that the 3 drivers using this are cleaned up we can also remove this final bit of confusion of leaking driver internals into the backlight power interface. The backlight power interface itself is still a massive mess. Signed-off-by: Daniel Vetter Acked-by: Daniel Thompson Reviewed-by: Jani Nikula Signed-off-by: Lee Jones --- include/linux/backlight.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 1db67662bfcb..7fbf0539e14a 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -84,7 +84,6 @@ struct backlight_properties { #define BL_CORE_SUSPENDED (1 << 0) /* backlight is suspended */ #define BL_CORE_FBBLANK (1 << 1) /* backlight is under an fb blank event */ -#define BL_CORE_DRIVER1 (1 << 31) /* reserved for driver specific use */ }; -- cgit v1.2.3 From 4d4fd36126d66d6091ca5aaabab262b5da3849c5 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Sun, 29 Apr 2018 10:56:08 +0300 Subject: net: bridge: Publish bridge accessor functions Add a couple new functions to allow querying FDB and vlan settings of a bridge. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 02639ebea2f0..585d27182425 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -93,11 +93,39 @@ static inline bool br_multicast_router(const struct net_device *dev) #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) bool br_vlan_enabled(const struct net_device *dev); +int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid); +int br_vlan_get_info(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo); #else static inline bool br_vlan_enabled(const struct net_device *dev) { return false; } + +static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) +{ + return -1; +} + +static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo) +{ + return -1; +} +#endif + +#if IS_ENABLED(CONFIG_BRIDGE) +struct net_device *br_fdb_find_port(const struct net_device *br_dev, + const unsigned char *addr, + __u16 vid); +#else +static inline struct net_device * +br_fdb_find_port(const struct net_device *br_dev, + const unsigned char *addr, + __u16 vid) +{ + return NULL; +} #endif #endif -- cgit v1.2.3 From 7a107c0f55a3b4c6f84a4323df5610360bde1684 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Thu, 5 Apr 2018 14:58:06 +0300 Subject: fasync: Fix deadlock between task-context and interrupt-context kill_fasync() I observed the following deadlock between them: [task 1] [task 2] [task 3] kill_fasync() mm_update_next_owner() copy_process() spin_lock_irqsave(&fa->fa_lock) read_lock(&tasklist_lock) write_lock_irq(&tasklist_lock) send_sigio() ... read_lock(&fown->lock) kill_fasync() ... read_lock(&tasklist_lock) spin_lock_irqsave(&fa->fa_lock) ... Task 1 can't acquire read locked tasklist_lock, since there is already task 3 expressed its wish to take the lock exclusive. Task 2 holds the read locked lock, but it can't take the spin lock. Also, there is possible another deadlock (which I haven't observed): [task 1] [task 2] f_getown() kill_fasync() read_lock(&f_own->lock) spin_lock_irqsave(&fa->fa_lock,) send_sigio() write_lock_irq(&f_own->lock) kill_fasync() read_lock(&fown->lock) spin_lock_irqsave(&fa->fa_lock,) Actually, we do not need exclusive fa->fa_lock in kill_fasync_rcu(), as it guarantees fa->fa_file->f_owner integrity only. It may seem, that it used to give a task a small possibility to receive two sequential signals, if there are two parallel kill_fasync() callers, and task handles the first signal fastly, but the behaviour won't become different, since there is exclusive sighand lock in do_send_sig_info(). The patch converts fa_lock into rwlock_t, and this fixes two above deadlocks, as rwlock is allowed to be taken from interrupt handler by qrwlock design. Signed-off-by: Kirill Tkhai Signed-off-by: Jeff Layton --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 760d8da1b6c7..d6c24b68a092 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1250,7 +1250,7 @@ static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) } struct fasync_struct { - spinlock_t fa_lock; + rwlock_t fa_lock; int magic; int fa_fd; struct fasync_struct *fa_next; /* singly linked list */ -- cgit v1.2.3 From 08303c189581c985e60f588ad92a041e46b6e307 Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Mon, 30 Apr 2018 10:16:11 +0300 Subject: net: Rename and export copy_skb_header copy_skb_header is renamed to skb_copy_header and exported. Exposing this function give more flexibility in copying SKBs. skb_copy and skb_copy_expand do not give enough control over which parts are copied. Signed-off-by: Ilya Lesokhin Signed-off-by: Boris Pismenny Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a4a5c0c5cba8..908d66e55b14 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1034,6 +1034,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); +void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority); struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone); -- cgit v1.2.3 From a5c37c63f71b044fbe1a3f893d6f6daa36fee5f5 Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Mon, 30 Apr 2018 10:16:13 +0300 Subject: net: Add TLS offload netdev ops Add new netdev ops to add and delete tls context Signed-off-by: Ilya Lesokhin Signed-off-by: Boris Pismenny Signed-off-by: Aviad Yehezkel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9e09dd897b74..a569bf5524fa 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -865,6 +865,26 @@ struct xfrmdev_ops { }; #endif +#if IS_ENABLED(CONFIG_TLS_DEVICE) +enum tls_offload_ctx_dir { + TLS_OFFLOAD_CTX_DIR_RX, + TLS_OFFLOAD_CTX_DIR_TX, +}; + +struct tls_crypto_info; +struct tls_context; + +struct tlsdev_ops { + int (*tls_dev_add)(struct net_device *netdev, struct sock *sk, + enum tls_offload_ctx_dir direction, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn); + void (*tls_dev_del)(struct net_device *netdev, + struct tls_context *ctx, + enum tls_offload_ctx_dir direction); +}; +#endif + struct dev_ifalias { struct rcu_head rcuhead; char ifalias[]; @@ -1750,6 +1770,10 @@ struct net_device { const struct xfrmdev_ops *xfrmdev_ops; #endif +#if IS_ENABLED(CONFIG_TLS_DEVICE) + const struct tlsdev_ops *tlsdev_ops; +#endif + const struct header_ops *header_ops; unsigned int flags; -- cgit v1.2.3 From 2342a8512a1e98c286b6b36094058e4ee2261c74 Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Mon, 30 Apr 2018 10:16:14 +0300 Subject: net: Add TLS TX offload features This patch adds a netdev feature to configure TLS TX offloads. Signed-off-by: Ilya Lesokhin Signed-off-by: Boris Pismenny Signed-off-by: Aviad Yehezkel Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index fe2f3b30960e..c87c3a3453c1 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -78,6 +78,7 @@ enum { NETIF_F_HW_ESP_BIT, /* Hardware ESP transformation offload */ NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */ + NETIF_F_HW_TLS_TX_BIT, /* Hardware TLS TX offload */ NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */ NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */ @@ -149,6 +150,7 @@ enum { #define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT) #define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD) #define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4) +#define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) -- cgit v1.2.3 From 1ae1732284895498b7119e42323cf12821423e6d Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Mon, 30 Apr 2018 10:16:18 +0300 Subject: net/mlx5: Accel, Add TLS tx offload interface Add routines for manipulating TLS TX offload contexts. In Innova TLS, TLS contexts are added or deleted via a command message over the SBU connection. The HW then sends a response message over the same connection. Add implementation for Innova TLS (FPGA-based) hardware. These routines will be used by the TLS offload support in a later patch mlx5/accel is a middle acceleration layer to allow mlx5e and other ULPs to work directly with mlx5_core rather than Innova FPGA or other mlx5 acceleration providers. In the future, when IPSec/TLS or any other acceleration gets integrated into ConnectX chip, mlx5/accel layer will provide the integrated acceleration, rather than the Innova one. Signed-off-by: Ilya Lesokhin Signed-off-by: Boris Pismenny Acked-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 16 -------- include/linux/mlx5/mlx5_ifc_fpga.h | 77 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1aad455538f4..b8918a1da11f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -356,22 +356,6 @@ struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 reserved_at_6[0x1a]; }; -struct mlx5_ifc_ipv4_layout_bits { - u8 reserved_at_0[0x60]; - - u8 ipv4[0x20]; -}; - -struct mlx5_ifc_ipv6_layout_bits { - u8 ipv6[16][0x8]; -}; - -union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { - struct mlx5_ifc_ipv6_layout_bits ipv6_layout; - struct mlx5_ifc_ipv4_layout_bits ipv4_layout; - u8 reserved_at_0[0x80]; -}; - struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 smac_47_16[0x20]; diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index ec052491ba3d..193091537cb6 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -32,12 +32,29 @@ #ifndef MLX5_IFC_FPGA_H #define MLX5_IFC_FPGA_H +struct mlx5_ifc_ipv4_layout_bits { + u8 reserved_at_0[0x60]; + + u8 ipv4[0x20]; +}; + +struct mlx5_ifc_ipv6_layout_bits { + u8 ipv6[16][0x8]; +}; + +union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { + struct mlx5_ifc_ipv6_layout_bits ipv6_layout; + struct mlx5_ifc_ipv4_layout_bits ipv4_layout; + u8 reserved_at_0[0x80]; +}; + enum { MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX = 0x2c9, }; enum { MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC = 0x2, + MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS = 0x3, }; struct mlx5_ifc_fpga_shell_caps_bits { @@ -370,6 +387,27 @@ struct mlx5_ifc_fpga_destroy_qp_out_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_tls_extended_cap_bits { + u8 aes_gcm_128[0x1]; + u8 aes_gcm_256[0x1]; + u8 reserved_at_2[0x1e]; + u8 reserved_at_20[0x20]; + u8 context_capacity_total[0x20]; + u8 context_capacity_rx[0x20]; + u8 context_capacity_tx[0x20]; + u8 reserved_at_a0[0x10]; + u8 tls_counter_size[0x10]; + u8 tls_counters_addr_low[0x20]; + u8 tls_counters_addr_high[0x20]; + u8 rx[0x1]; + u8 tx[0x1]; + u8 tls_v12[0x1]; + u8 tls_v13[0x1]; + u8 lro[0x1]; + u8 ipv6[0x1]; + u8 reserved_at_106[0x1a]; +}; + struct mlx5_ifc_ipsec_extended_cap_bits { u8 encapsulation[0x20]; @@ -519,4 +557,43 @@ struct mlx5_ifc_fpga_ipsec_sa { __be16 reserved2; } __packed; +enum fpga_tls_cmds { + CMD_SETUP_STREAM = 0x1001, + CMD_TEARDOWN_STREAM = 0x1002, +}; + +#define MLX5_TLS_1_2 (0) + +#define MLX5_TLS_ALG_AES_GCM_128 (0) +#define MLX5_TLS_ALG_AES_GCM_256 (1) + +struct mlx5_ifc_tls_cmd_bits { + u8 command_type[0x20]; + u8 ipv6[0x1]; + u8 direction_sx[0x1]; + u8 tls_version[0x2]; + u8 reserved[0x1c]; + u8 swid[0x20]; + u8 src_port[0x10]; + u8 dst_port[0x10]; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6; + u8 tls_rcd_sn[0x40]; + u8 tcp_sn[0x20]; + u8 tls_implicit_iv[0x20]; + u8 tls_xor_iv[0x40]; + u8 encryption_key[0x100]; + u8 alg[4]; + u8 reserved2[0x1c]; + u8 reserved3[0x4a0]; +}; + +struct mlx5_ifc_tls_resp_bits { + u8 syndrome[0x20]; + u8 stream_id[0x20]; + u8 reserverd[0x40]; +}; + +#define MLX5_TLS_COMMAND_SIZE (0x100) + #endif /* MLX5_IFC_FPGA_H */ -- cgit v1.2.3 From e7420c2d4495cbb9c14dd8bf8b3b4e5bdded6e20 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 16 Apr 2018 10:26:46 -0700 Subject: bus: ti-sysc: Tag some modules resource providers for noirq suspend Modules that provide resources for other modules need to be suspended and resumed in the noirq calls. Tag the resource providing modules. Signed-off-by: Tony Lindgren --- include/linux/platform_data/ti-sysc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 80ce28d40832..990aad477458 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -45,6 +45,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_QUIRK_RESOURCE_PROVIDER BIT(9) #define SYSC_QUIRK_LEGACY_IDLE BIT(8) #define SYSC_QUIRK_RESET_STATUS BIT(7) #define SYSC_QUIRK_NO_IDLE_ON_INIT BIT(6) -- cgit v1.2.3 From e283de3a4fa885aed11525129fd4570f92c1d1a9 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 30 Apr 2018 14:20:05 -0700 Subject: net: core: Inline netdev_features_size_check() We do not require this inline function to be used in multiple different locations, just inline it where it gets used in register_netdevice(). Suggested-by: David Miller Suggested-by: Stephen Hemminger Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a569bf5524fa..46dcb5f7522f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4132,12 +4132,6 @@ const char *netdev_drivername(const struct net_device *dev); void linkwatch_run_queue(void); -static inline void netdev_features_size_check(void) -{ - BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE < - NETDEV_FEATURE_COUNT); -} - static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { -- cgit v1.2.3 From b75eba76d3d72e2374fac999926dafef2997edd2 Mon Sep 17 00:00:00 2001 From: Soheil Hassas Yeganeh Date: Tue, 1 May 2018 15:39:15 -0400 Subject: tcp: send in-queue bytes in cmsg upon read Applications with many concurrent connections, high variance in receive queue length and tight memory bounds cannot allocate worst-case buffer size to drain sockets. Knowing the size of receive queue length, applications can optimize how they allocate buffers to read from the socket. The number of bytes pending on the socket is directly available through ioctl(FIONREAD/SIOCINQ) and can be approximated using getsockopt(MEMINFO) (rmem_alloc includes skb overheads in addition to application data). But, both of these options add an extra syscall per recvmsg. Moreover, ioctl(FIONREAD/SIOCINQ) takes the socket lock. Add the TCP_INQ socket option to TCP. When this socket option is set, recvmsg() relays the number of bytes available on the socket for reading to the application via the TCP_CM_INQ control message. Calculate the number of bytes after releasing the socket lock to include the processed backlog, if any. To avoid an extra branch in the hot path of recvmsg() for this new control message, move all cmsg processing inside an existing branch for processing receive timestamps. Since the socket lock is not held when calculating the size of receive queue, TCP_INQ is a hint. For example, it can overestimate the queue size by one byte, if FIN is received. With this method, applications can start reading from the socket using a small buffer, and then use larger buffers based on the remaining data when needed. V3 change-log: As suggested by David Miller, added loads with barrier to check whether we have multiple threads calling recvmsg in parallel. When that happens we lock the socket to calculate inq. V4 change-log: Removed inline from a static function. Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Yuchung Cheng Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Reviewed-by: Neal Cardwell Suggested-by: David Miller Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 20585d5c4e1c..807776928cb8 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -228,7 +228,7 @@ struct tcp_sock { unused:2; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ - unused1 : 1, + recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ repair : 1, frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; -- cgit v1.2.3 From 2c269b090651234203c2f74af059a19f98ed101d Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Apr 2018 08:17:08 +0200 Subject: dma-fence: Some kerneldoc polish for dma-fence.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Switch to inline member docs for dma_fence_ops. - Mild polish all around. - hyperlink all the things! v2: - Remove the various [in] annotations, they seem really uncommon in kerneldoc and look funny. v3: Linebreak the "Returns" part of the @fill_driver_data kerneldoc (Eric). Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Reviewed-by: Eric Anholt Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20180427061724.28497-2-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 236 ++++++++++++++++++++++++++++++---------------- 1 file changed, 155 insertions(+), 81 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 4c008170fe65..eb9b05aa5aea 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -94,11 +94,11 @@ typedef void (*dma_fence_func_t)(struct dma_fence *fence, struct dma_fence_cb *cb); /** - * struct dma_fence_cb - callback for dma_fence_add_callback - * @node: used by dma_fence_add_callback to append this struct to fence::cb_list + * struct dma_fence_cb - callback for dma_fence_add_callback() + * @node: used by dma_fence_add_callback() to append this struct to fence::cb_list * @func: dma_fence_func_t to call * - * This struct will be initialized by dma_fence_add_callback, additional + * This struct will be initialized by dma_fence_add_callback(), additional * data can be passed along by embedding dma_fence_cb in another struct. */ struct dma_fence_cb { @@ -108,75 +108,143 @@ struct dma_fence_cb { /** * struct dma_fence_ops - operations implemented for fence - * @get_driver_name: returns the driver name. - * @get_timeline_name: return the name of the context this fence belongs to. - * @enable_signaling: enable software signaling of fence. - * @signaled: [optional] peek whether the fence is signaled, can be null. - * @wait: custom wait implementation, or dma_fence_default_wait. - * @release: [optional] called on destruction of fence, can be null - * @fill_driver_data: [optional] callback to fill in free-form debug info - * Returns amount of bytes filled, or -errno. - * @fence_value_str: [optional] fills in the value of the fence as a string - * @timeline_value_str: [optional] fills in the current value of the timeline - * as a string * - * Notes on enable_signaling: - * For fence implementations that have the capability for hw->hw - * signaling, they can implement this op to enable the necessary - * irqs, or insert commands into cmdstream, etc. This is called - * in the first wait() or add_callback() path to let the fence - * implementation know that there is another driver waiting on - * the signal (ie. hw->sw case). - * - * This function can be called from atomic context, but not - * from irq context, so normal spinlocks can be used. - * - * A return value of false indicates the fence already passed, - * or some failure occurred that made it impossible to enable - * signaling. True indicates successful enabling. - * - * fence->error may be set in enable_signaling, but only when false is - * returned. - * - * Calling dma_fence_signal before enable_signaling is called allows - * for a tiny race window in which enable_signaling is called during, - * before, or after dma_fence_signal. To fight this, it is recommended - * that before enable_signaling returns true an extra reference is - * taken on the fence, to be released when the fence is signaled. - * This will mean dma_fence_signal will still be called twice, but - * the second time will be a noop since it was already signaled. - * - * Notes on signaled: - * May set fence->error if returning true. - * - * Notes on wait: - * Must not be NULL, set to dma_fence_default_wait for default implementation. - * the dma_fence_default_wait implementation should work for any fence, as long - * as enable_signaling works correctly. - * - * Must return -ERESTARTSYS if the wait is intr = true and the wait was - * interrupted, and remaining jiffies if fence has signaled, or 0 if wait - * timed out. Can also return other error values on custom implementations, - * which should be treated as if the fence is signaled. For example a hardware - * lockup could be reported like that. - * - * Notes on release: - * Can be NULL, this function allows additional commands to run on - * destruction of the fence. Can be called from irq context. - * If pointer is set to NULL, kfree will get called instead. */ - struct dma_fence_ops { + /** + * @get_driver_name: + * + * Returns the driver name. This is a callback to allow drivers to + * compute the name at runtime, without having it to store permanently + * for each fence, or build a cache of some sort. + * + * This callback is mandatory. + */ const char * (*get_driver_name)(struct dma_fence *fence); + + /** + * @get_timeline_name: + * + * Return the name of the context this fence belongs to. This is a + * callback to allow drivers to compute the name at runtime, without + * having it to store permanently for each fence, or build a cache of + * some sort. + * + * This callback is mandatory. + */ const char * (*get_timeline_name)(struct dma_fence *fence); + + /** + * @enable_signaling: + * + * Enable software signaling of fence. + * + * For fence implementations that have the capability for hw->hw + * signaling, they can implement this op to enable the necessary + * interrupts, or insert commands into cmdstream, etc, to avoid these + * costly operations for the common case where only hw->hw + * synchronization is required. This is called in the first + * dma_fence_wait() or dma_fence_add_callback() path to let the fence + * implementation know that there is another driver waiting on the + * signal (ie. hw->sw case). + * + * This function can be called from atomic context, but not + * from irq context, so normal spinlocks can be used. + * + * A return value of false indicates the fence already passed, + * or some failure occurred that made it impossible to enable + * signaling. True indicates successful enabling. + * + * &dma_fence.error may be set in enable_signaling, but only when false + * is returned. + * + * Since many implementations can call dma_fence_signal() even when before + * @enable_signaling has been called there's a race window, where the + * dma_fence_signal() might result in the final fence reference being + * released and its memory freed. To avoid this, implementations of this + * callback should grab their own reference using dma_fence_get(), to be + * released when the fence is signalled (through e.g. the interrupt + * handler). + * + * This callback is mandatory. + */ bool (*enable_signaling)(struct dma_fence *fence); + + /** + * @signaled: + * + * Peek whether the fence is signaled, as a fastpath optimization for + * e.g. dma_fence_wait() or dma_fence_add_callback(). Note that this + * callback does not need to make any guarantees beyond that a fence + * once indicates as signalled must always return true from this + * callback. This callback may return false even if the fence has + * completed already, in this case information hasn't propogated throug + * the system yet. See also dma_fence_is_signaled(). + * + * May set &dma_fence.error if returning true. + * + * This callback is optional. + */ bool (*signaled)(struct dma_fence *fence); + + /** + * @wait: + * + * Custom wait implementation, or dma_fence_default_wait. + * + * Must not be NULL, set to dma_fence_default_wait for default implementation. + * the dma_fence_default_wait implementation should work for any fence, as long + * as enable_signaling works correctly. + * + * Must return -ERESTARTSYS if the wait is intr = true and the wait was + * interrupted, and remaining jiffies if fence has signaled, or 0 if wait + * timed out. Can also return other error values on custom implementations, + * which should be treated as if the fence is signaled. For example a hardware + * lockup could be reported like that. + * + * This callback is mandatory. + */ signed long (*wait)(struct dma_fence *fence, bool intr, signed long timeout); + + /** + * @release: + * + * Called on destruction of fence to release additional resources. + * Can be called from irq context. This callback is optional. If it is + * NULL, then dma_fence_free() is instead called as the default + * implementation. + */ void (*release)(struct dma_fence *fence); + /** + * @fill_driver_data: + * + * Callback to fill in free-form debug info. + * + * Returns amount of bytes filled, or negative error on failure. + * + * This callback is optional. + */ int (*fill_driver_data)(struct dma_fence *fence, void *data, int size); + + /** + * @fence_value_str: + * + * Callback to fill in free-form debug info specific to this fence, like + * the sequence number. + * + * This callback is optional. + */ void (*fence_value_str)(struct dma_fence *fence, char *str, int size); + + /** + * @timeline_value_str: + * + * Fills in the current value of the timeline as a string, like the + * sequence number. This should match what @fill_driver_data prints for + * the most recently signalled fence (assuming no delayed signalling). + */ void (*timeline_value_str)(struct dma_fence *fence, char *str, int size); }; @@ -189,7 +257,7 @@ void dma_fence_free(struct dma_fence *fence); /** * dma_fence_put - decreases refcount of the fence - * @fence: [in] fence to reduce refcount of + * @fence: fence to reduce refcount of */ static inline void dma_fence_put(struct dma_fence *fence) { @@ -199,7 +267,7 @@ static inline void dma_fence_put(struct dma_fence *fence) /** * dma_fence_get - increases refcount of the fence - * @fence: [in] fence to increase refcount of + * @fence: fence to increase refcount of * * Returns the same fence, with refcount increased by 1. */ @@ -213,7 +281,7 @@ static inline struct dma_fence *dma_fence_get(struct dma_fence *fence) /** * dma_fence_get_rcu - get a fence from a reservation_object_list with * rcu read lock - * @fence: [in] fence to increase refcount of + * @fence: fence to increase refcount of * * Function returns NULL if no refcount could be obtained, or the fence. */ @@ -227,7 +295,7 @@ static inline struct dma_fence *dma_fence_get_rcu(struct dma_fence *fence) /** * dma_fence_get_rcu_safe - acquire a reference to an RCU tracked fence - * @fencep: [in] pointer to fence to increase refcount of + * @fencep: pointer to fence to increase refcount of * * Function returns NULL if no refcount could be obtained, or the fence. * This function handles acquiring a reference to a fence that may be @@ -289,14 +357,16 @@ void dma_fence_enable_sw_signaling(struct dma_fence *fence); /** * dma_fence_is_signaled_locked - Return an indication if the fence * is signaled yet. - * @fence: [in] the fence to check + * @fence: the fence to check * * Returns true if the fence was already signaled, false if not. Since this * function doesn't enable signaling, it is not guaranteed to ever return - * true if dma_fence_add_callback, dma_fence_wait or - * dma_fence_enable_sw_signaling haven't been called before. + * true if dma_fence_add_callback(), dma_fence_wait() or + * dma_fence_enable_sw_signaling() haven't been called before. * - * This function requires fence->lock to be held. + * This function requires &dma_fence.lock to be held. + * + * See also dma_fence_is_signaled(). */ static inline bool dma_fence_is_signaled_locked(struct dma_fence *fence) @@ -314,17 +384,19 @@ dma_fence_is_signaled_locked(struct dma_fence *fence) /** * dma_fence_is_signaled - Return an indication if the fence is signaled yet. - * @fence: [in] the fence to check + * @fence: the fence to check * * Returns true if the fence was already signaled, false if not. Since this * function doesn't enable signaling, it is not guaranteed to ever return - * true if dma_fence_add_callback, dma_fence_wait or - * dma_fence_enable_sw_signaling haven't been called before. + * true if dma_fence_add_callback(), dma_fence_wait() or + * dma_fence_enable_sw_signaling() haven't been called before. * * It's recommended for seqno fences to call dma_fence_signal when the * operation is complete, it makes it possible to prevent issues from * wraparound between time of issue and time of use by checking the return * value of this function before calling hardware-specific wait instructions. + * + * See also dma_fence_is_signaled_locked(). */ static inline bool dma_fence_is_signaled(struct dma_fence *fence) @@ -342,8 +414,8 @@ dma_fence_is_signaled(struct dma_fence *fence) /** * __dma_fence_is_later - return if f1 is chronologically later than f2 - * @f1: [in] the first fence's seqno - * @f2: [in] the second fence's seqno from the same context + * @f1: the first fence's seqno + * @f2: the second fence's seqno from the same context * * Returns true if f1 is chronologically later than f2. Both fences must be * from the same context, since a seqno is not common across contexts. @@ -355,8 +427,8 @@ static inline bool __dma_fence_is_later(u32 f1, u32 f2) /** * dma_fence_is_later - return if f1 is chronologically later than f2 - * @f1: [in] the first fence from the same context - * @f2: [in] the second fence from the same context + * @f1: the first fence from the same context + * @f2: the second fence from the same context * * Returns true if f1 is chronologically later than f2. Both fences must be * from the same context, since a seqno is not re-used across contexts. @@ -372,8 +444,8 @@ static inline bool dma_fence_is_later(struct dma_fence *f1, /** * dma_fence_later - return the chronologically later fence - * @f1: [in] the first fence from the same context - * @f2: [in] the second fence from the same context + * @f1: the first fence from the same context + * @f2: the second fence from the same context * * Returns NULL if both fences are signaled, otherwise the fence that would be * signaled last. Both fences must be from the same context, since a seqno is @@ -398,7 +470,7 @@ static inline struct dma_fence *dma_fence_later(struct dma_fence *f1, /** * dma_fence_get_status_locked - returns the status upon completion - * @fence: [in] the dma_fence to query + * @fence: the dma_fence to query * * Drivers can supply an optional error status condition before they signal * the fence (to indicate whether the fence was completed due to an error @@ -422,8 +494,8 @@ int dma_fence_get_status(struct dma_fence *fence); /** * dma_fence_set_error - flag an error condition on the fence - * @fence: [in] the dma_fence - * @error: [in] the error to store + * @fence: the dma_fence + * @error: the error to store * * Drivers can supply an optional error status condition before they signal * the fence, to indicate that the fence was completed due to an error @@ -449,8 +521,8 @@ signed long dma_fence_wait_any_timeout(struct dma_fence **fences, /** * dma_fence_wait - sleep until the fence gets signaled - * @fence: [in] the fence to wait on - * @intr: [in] if true, do an interruptible wait + * @fence: the fence to wait on + * @intr: if true, do an interruptible wait * * This function will return -ERESTARTSYS if interrupted by a signal, * or 0 if the fence was signaled. Other error values may be @@ -459,6 +531,8 @@ signed long dma_fence_wait_any_timeout(struct dma_fence **fences, * Performs a synchronous wait on this fence. It is assumed the caller * directly or indirectly holds a reference to the fence, otherwise the * fence might be freed before return, resulting in undefined behavior. + * + * See also dma_fence_wait_timeout() and dma_fence_wait_any_timeout(). */ static inline signed long dma_fence_wait(struct dma_fence *fence, bool intr) { -- cgit v1.2.3 From bde1a3d84634f98151e3f748ab90865e9f544b10 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 30 Apr 2018 10:24:42 +0200 Subject: mtd: rawnand: davinci: store the core chipselect number in platform data We have the 'ti,davinci-chipselect' property in the device tree, but when using platform data the driver silently uses the id field of struct platform_device as the chipselect. This is confusing and we almost broke the nand support again recently after converting the platform to common clock framework (which changed the device id in the clock lookup - the problem is gone now that we no longer acquire the clock in the nand driver. This patch adds a new field - core_chipsel - to the platform_data. Subsequent patches will convert the platforms to using this new field. Acked-by: Boris Brezillon Signed-off-by: Bartosz Golaszewski Signed-off-by: Sekhar Nori --- include/linux/platform_data/mtd-davinci.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h index f1a2cf655bdb..1bbfa27cccb4 100644 --- a/include/linux/platform_data/mtd-davinci.h +++ b/include/linux/platform_data/mtd-davinci.h @@ -56,6 +56,16 @@ struct davinci_nand_pdata { /* platform_data */ uint32_t mask_ale; uint32_t mask_cle; + /* + * 0-indexed chip-select number of the asynchronous + * interface to which the NAND device has been connected. + * + * So, if you have NAND connected to CS3 of DA850, you + * will pass '1' here. Since the asynchronous interface + * on DA850 starts from CS2. + */ + uint32_t core_chipsel; + /* for packages using two chipselects */ uint32_t mask_chipsel; -- cgit v1.2.3 From ebc5a1bf4f2afc2f2b348320dcfb45a8c0ac3de5 Mon Sep 17 00:00:00 2001 From: "harish_kandiga@mentor.com" Date: Tue, 10 Apr 2018 12:30:31 +0530 Subject: mmc: core: Add a new quirk for limiting clock rate This patch adds a quirk to limit clock rate which can be used to reduce the SDIO clock rate for some chips with broken UHS. Signed-off-by: Harish Jenny K N Reviewed-by: Shawn Lin Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 279b39008a33..5ebc47855721 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -252,6 +252,7 @@ struct mmc_card { #define MMC_TYPE_SD_COMBO 3 /* SD combo (IO+mem) card */ unsigned int state; /* (our) card state */ unsigned int quirks; /* card quirks */ + unsigned int quirk_max_rate; /* max rate set by quirks */ #define MMC_QUIRK_LENIENT_FN0 (1<<0) /* allow SDIO FN0 writes outside of the VS CCCR range */ #define MMC_QUIRK_BLKSZ_FOR_BYTE_MODE (1<<1) /* use func->cur_blksize */ /* for byte mode */ -- cgit v1.2.3 From 8ccd66f258cd79420102f3735b3bc8d974a22088 Mon Sep 17 00:00:00 2001 From: Diwakar Sharma Date: Tue, 10 Apr 2018 12:30:32 +0530 Subject: mmc: core: sdio: Set SDIO clock of SDR104 to 150MHz for Marvell 8887 chip This patch uses limit clock rate quirk to reduce clock rate for "SDR104" mode on IMX side for Marvell 8887 WiFi + Bluetooth chip side, as Marvell does not recommend to use SDIO at the speed of higher than 150MHz. Signed-off-by: Diwakar Sharma Signed-off-by: Harish Jenny K N Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index cdd66a5fbd5e..2836a96e014a 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -55,6 +55,7 @@ #define SDIO_DEVICE_ID_MARVELL_8688WLAN 0x9104 #define SDIO_DEVICE_ID_MARVELL_8688BT 0x9105 #define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 +#define SDIO_DEVICE_ID_MARVELL_8887WLAN 0x9134 #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 -- cgit v1.2.3 From 247cfe53557524a94dd1001d19e5aa50bd5aca81 Mon Sep 17 00:00:00 2001 From: Kyle Roeschley Date: Fri, 13 Apr 2018 16:54:57 -0500 Subject: mmc: core: Add capability to avoid 3.3V signaling Some SD host controllers cannot handle extended use of 3.3V signaling. To accommodate these controllers, add a capability that requires us to negotiate the voltage down from 3.3V during card initialization. Signed-off-by: Kyle Roeschley Signed-off-by: Jennifer Dahm Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 85146235231e..7c6eaf63f5ce 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -354,6 +354,7 @@ struct mmc_host { #define MMC_CAP2_NO_MMC (1 << 22) /* Do not send (e)MMC commands during initialization */ #define MMC_CAP2_CQE (1 << 23) /* Has eMMC command queue engine */ #define MMC_CAP2_CQE_DCMD (1 << 24) /* CQE can issue a direct command */ +#define MMC_CAP2_AVOID_3_3V (1 << 25) /* Host must negotiate down from 3.3V */ int fixed_drv_type; /* fixed driver type for non-removable media */ -- cgit v1.2.3 From eb06d6bbc45a7561de78a00fb17bfbb75893ee26 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 18 Apr 2018 16:50:01 +0200 Subject: clk: Extract OF clock helpers in The use of of_clk_get_parent_{count,name}() and of_clk_init() is not limited to clock providers. Hence move these helpers into their own header file, so callers that are not clock providers no longer have to include . Suggested-by: Stephen Boyd Signed-off-by: Geert Uytterhoeven Reviewed-by: Heiko Stuebner Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 14 +------------- include/linux/of_clk.h | 30 ++++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+), 13 deletions(-) create mode 100644 include/linux/of_clk.h (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 210a890008f9..61cb4729f22a 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -13,6 +13,7 @@ #include #include +#include #ifdef CONFIG_COMMON_CLK @@ -890,13 +891,10 @@ struct clk_hw *of_clk_hw_simple_get(struct of_phandle_args *clkspec, struct clk *of_clk_src_onecell_get(struct of_phandle_args *clkspec, void *data); struct clk_hw *of_clk_hw_onecell_get(struct of_phandle_args *clkspec, void *data); -unsigned int of_clk_get_parent_count(struct device_node *np); int of_clk_parent_fill(struct device_node *np, const char **parents, unsigned int size); -const char *of_clk_get_parent_name(struct device_node *np, int index); int of_clk_detect_critical(struct device_node *np, int index, unsigned long *flags); -void of_clk_init(const struct of_device_id *matches); #else /* !CONFIG_OF */ @@ -943,26 +941,16 @@ of_clk_hw_onecell_get(struct of_phandle_args *clkspec, void *data) { return ERR_PTR(-ENOENT); } -static inline unsigned int of_clk_get_parent_count(struct device_node *np) -{ - return 0; -} static inline int of_clk_parent_fill(struct device_node *np, const char **parents, unsigned int size) { return 0; } -static inline const char *of_clk_get_parent_name(struct device_node *np, - int index) -{ - return NULL; -} static inline int of_clk_detect_critical(struct device_node *np, int index, unsigned long *flags) { return 0; } -static inline void of_clk_init(const struct of_device_id *matches) {} #endif /* CONFIG_OF */ /* diff --git a/include/linux/of_clk.h b/include/linux/of_clk.h new file mode 100644 index 000000000000..b27da9f164cb --- /dev/null +++ b/include/linux/of_clk.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * OF clock helpers + */ + +#ifndef __LINUX_OF_CLK_H +#define __LINUX_OF_CLK_H + +#if defined(CONFIG_COMMON_CLK) && defined(CONFIG_OF) + +unsigned int of_clk_get_parent_count(struct device_node *np); +const char *of_clk_get_parent_name(struct device_node *np, int index); +void of_clk_init(const struct of_device_id *matches); + +#else /* !CONFIG_COMMON_CLK || !CONFIG_OF */ + +static inline unsigned int of_clk_get_parent_count(struct device_node *np) +{ + return 0; +} +static inline const char *of_clk_get_parent_name(struct device_node *np, + int index) +{ + return NULL; +} +static inline void of_clk_init(const struct of_device_id *matches) {} + +#endif /* !CONFIG_COMMON_CLK || !CONFIG_OF */ + +#endif /* __LINUX_OF_CLK_H */ -- cgit v1.2.3 From 7a074e96dee62586c935c80cecd931431bfdd0be Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 2 May 2018 19:51:00 +0200 Subject: aio: implement io_pgetevents This is the io_getevents equivalent of ppoll/pselect and allows to properly mix signals and aio completions (especially with IOCB_CMD_POLL) and atomically executes the following sequence: sigset_t origmask; pthread_sigmask(SIG_SETMASK, &sigmask, &origmask); ret = io_getevents(ctx, min_nr, nr, events, timeout); pthread_sigmask(SIG_SETMASK, &origmask, NULL); Note that unlike many other signal related calls we do not pass a sigmask size, as that would get us to 7 arguments, which aren't easily supported by the syscall infrastructure. It seems a lot less painful to just add a new syscall variant in the unlikely case we're going to increase the sigset size. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Darrick J. Wong --- include/linux/compat.h | 7 +++++++ include/linux/syscalls.h | 6 ++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 081281ad5772..ad192057b887 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -330,6 +330,7 @@ extern int put_compat_rusage(const struct rusage *, struct compat_rusage __user *); struct compat_siginfo; +struct __compat_aio_sigset; struct compat_dirent { u32 d_ino; @@ -553,6 +554,12 @@ asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id, compat_long_t nr, struct io_event __user *events, struct compat_timespec __user *timeout); +asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id, + compat_long_t min_nr, + compat_long_t nr, + struct io_event __user *events, + struct compat_timespec __user *timeout, + const struct __compat_aio_sigset __user *usig); /* fs/cookies.c */ asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 70fcda1a9049..811172fcb916 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -290,6 +290,12 @@ asmlinkage long sys_io_getevents(aio_context_t ctx_id, long nr, struct io_event __user *events, struct timespec __user *timeout); +asmlinkage long sys_io_pgetevents(aio_context_t ctx_id, + long min_nr, + long nr, + struct io_event __user *events, + struct timespec __user *timeout, + const struct __aio_sigset *sig); /* fs/xattr.c */ asmlinkage long sys_setxattr(const char __user *path, const char __user *name, -- cgit v1.2.3 From 0cb8dae4a0df2a977847c2dc6766a7783ce50f9d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 18 Apr 2018 11:09:47 -0700 Subject: fscrypt: allow synchronous bio decryption Currently, fscrypt provides fscrypt_decrypt_bio_pages() which decrypts a bio's pages asynchronously, then unlocks them afterwards. But, this assumes that decryption is the last "postprocessing step" for the bio, so it's incompatible with additional postprocessing steps such as authenticity verification after decryption. Therefore, rename the existing fscrypt_decrypt_bio_pages() to fscrypt_enqueue_decrypt_bio(). Then, add fscrypt_decrypt_bio() which decrypts the pages in the bio synchronously without unlocking the pages, nor setting them Uptodate; and add fscrypt_enqueue_decrypt_work(), which enqueues work on the fscrypt_read_workqueue. The new functions will be used by filesystems that support both fscrypt and fs-verity. Signed-off-by: Eric Biggers Signed-off-by: Jaegeuk Kim --- include/linux/fscrypt_notsupp.h | 13 ++++++++++--- include/linux/fscrypt_supp.h | 5 ++++- 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h index 44b50c04bae9..9770be37c9d4 100644 --- a/include/linux/fscrypt_notsupp.h +++ b/include/linux/fscrypt_notsupp.h @@ -25,6 +25,10 @@ static inline bool fscrypt_dummy_context_enabled(struct inode *inode) } /* crypto.c */ +static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) +{ +} + static inline struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, gfp_t gfp_flags) { @@ -160,10 +164,13 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname, } /* bio.c */ -static inline void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, - struct bio *bio) +static inline void fscrypt_decrypt_bio(struct bio *bio) +{ +} + +static inline void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, + struct bio *bio) { - return; } static inline void fscrypt_pullback_bio_page(struct page **page, bool restore) diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h index 477a7a6504d2..2c9a86ac5e83 100644 --- a/include/linux/fscrypt_supp.h +++ b/include/linux/fscrypt_supp.h @@ -59,6 +59,7 @@ static inline bool fscrypt_dummy_context_enabled(struct inode *inode) } /* crypto.c */ +extern void fscrypt_enqueue_decrypt_work(struct work_struct *); extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); extern void fscrypt_release_ctx(struct fscrypt_ctx *); extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, @@ -188,7 +189,9 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname, } /* bio.c */ -extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); +extern void fscrypt_decrypt_bio(struct bio *); +extern void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, + struct bio *bio); extern void fscrypt_pullback_bio_page(struct page **, bool); extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, unsigned int); -- cgit v1.2.3 From c16bc9a7678a27ece028dcbfea8df2049a65dbec Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Fri, 27 Apr 2018 17:17:14 +0530 Subject: mmc: sdhci: Disable 1.8v modes (HS200/HS400/UHS) if controller can't support 1.8v The SDHCI controller in a SoC might support HS200/HS400 (indicated using mmc-hs200-1_8v/mmc-hs400-1_8v dt property), but if the board is modeled such that the IO lines are not connected to 1.8v then HS200/HS400 cannot be supported. Disable HS200/HS400 if the board does not have 1.8v connected to the IO lines. Also Disable DDR/UHS in 1.8v if the IO lines are not connected to 1.8v. Signed-off-by: Kishon Vijay Abraham I Acked-by: Tony Lindgren Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 85146235231e..4e80c199c9c2 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -320,6 +320,9 @@ struct mmc_host { #define MMC_CAP_UHS_SDR50 (1 << 18) /* Host supports UHS SDR50 mode */ #define MMC_CAP_UHS_SDR104 (1 << 19) /* Host supports UHS SDR104 mode */ #define MMC_CAP_UHS_DDR50 (1 << 20) /* Host supports UHS DDR50 mode */ +#define MMC_CAP_UHS (MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 | \ + MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 | \ + MMC_CAP_UHS_DDR50) /* (1 << 21) is free for reuse */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ @@ -345,6 +348,7 @@ struct mmc_host { #define MMC_CAP2_HS400_1_2V (1 << 16) /* Can support HS400 1.2V */ #define MMC_CAP2_HS400 (MMC_CAP2_HS400_1_8V | \ MMC_CAP2_HS400_1_2V) +#define MMC_CAP2_HSX00_1_8V (MMC_CAP2_HS200_1_8V_SDR | MMC_CAP2_HS400_1_8V) #define MMC_CAP2_HSX00_1_2V (MMC_CAP2_HS200_1_2V_SDR | MMC_CAP2_HS400_1_2V) #define MMC_CAP2_SDIO_IRQ_NOTHREAD (1 << 17) #define MMC_CAP2_NO_WRITE_PROTECT (1 << 18) /* No physical write protect pin, assume that card is always read-write */ -- cgit v1.2.3 From aee1a37d0f1a904a1443c327211f4bcd645681f1 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 2 May 2018 10:23:59 +0200 Subject: dma-fence: remove fill_driver_data callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Noticed while I was typing docs. Entirely unused. v2: Remove reference in @timeline_value_str too. While at it clarify why timeline_value_str has a fence parameter - we don't have an explicit timeline structure unfortunately. Cc: Eric Anholt Reviewed-by: Christian König (v1) Reviewed-by: Eric Anholt Cc: Christian König (v1) Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180502082359.30345-1-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index eb9b05aa5aea..111aefe1c956 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -217,17 +217,6 @@ struct dma_fence_ops { */ void (*release)(struct dma_fence *fence); - /** - * @fill_driver_data: - * - * Callback to fill in free-form debug info. - * - * Returns amount of bytes filled, or negative error on failure. - * - * This callback is optional. - */ - int (*fill_driver_data)(struct dma_fence *fence, void *data, int size); - /** * @fence_value_str: * @@ -242,8 +231,9 @@ struct dma_fence_ops { * @timeline_value_str: * * Fills in the current value of the timeline as a string, like the - * sequence number. This should match what @fill_driver_data prints for - * the most recently signalled fence (assuming no delayed signalling). + * sequence number. Note that the specific fence passed to this function + * should not matter, drivers should only use it to look up the + * corresponding timeline structures. */ void (*timeline_value_str)(struct dma_fence *fence, char *str, int size); -- cgit v1.2.3 From 95ed01ea97b3d76380a817bc41ceeefffa6a99f1 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Apr 2018 08:17:10 +0200 Subject: dma-fence: Make ->enable_signaling optional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Many drivers have a trivial implementation for ->enable_signaling. Let's make it optional by assuming that signalling is already available when the callback isn't present. Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: Gustavo Padovan Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20180427061724.28497-4-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 111aefe1c956..c053d19e1e24 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -166,7 +166,8 @@ struct dma_fence_ops { * released when the fence is signalled (through e.g. the interrupt * handler). * - * This callback is mandatory. + * This callback is optional. If this callback is not present, then the + * driver must always have signaling enabled. */ bool (*enable_signaling)(struct dma_fence *fence); -- cgit v1.2.3 From 49a53d493e603c594e39dfbc7171917effcaf01e Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Apr 2018 08:17:12 +0200 Subject: dma-fence: Make ->wait callback optional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Almost everyone uses dma_fence_default_wait. Reviewed-by: Christian König Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: Gustavo Padovan Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20180427061724.28497-6-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index c053d19e1e24..02dba8cd033d 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -191,11 +191,14 @@ struct dma_fence_ops { /** * @wait: * - * Custom wait implementation, or dma_fence_default_wait. + * Custom wait implementation, defaults to dma_fence_default_wait() if + * not set. * - * Must not be NULL, set to dma_fence_default_wait for default implementation. - * the dma_fence_default_wait implementation should work for any fence, as long - * as enable_signaling works correctly. + * The dma_fence_default_wait implementation should work for any fence, as long + * as @enable_signaling works correctly. This hook allows drivers to + * have an optimized version for the case where a process context is + * already available, e.g. if @enable_signaling for the general case + * needs to set up a worker thread. * * Must return -ERESTARTSYS if the wait is intr = true and the wait was * interrupted, and remaining jiffies if fence has signaled, or 0 if wait @@ -203,7 +206,7 @@ struct dma_fence_ops { * which should be treated as if the fence is signaled. For example a hardware * lockup could be reported like that. * - * This callback is mandatory. + * This callback is optional. */ signed long (*wait)(struct dma_fence *fence, bool intr, signed long timeout); -- cgit v1.2.3 From 51f170a544bdb06d93316d8ff0814a52daa24a6c Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 3 May 2018 12:31:38 +0200 Subject: Revert 190c462d5be19ba622a82f5fd0625087c870a1e6..bf3012ada1b2222e770de5c35c1bb16f73b3a01d" I shouldn't have pushed this, CI was right - I failed to remove the BUG_ON(!ops->wait); Reported-by: Chris Wilson Acked-by: Chris Wilson Signed-off-by: Daniel Vetter --- include/linux/dma-fence.h | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 02dba8cd033d..eb9b05aa5aea 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -166,8 +166,7 @@ struct dma_fence_ops { * released when the fence is signalled (through e.g. the interrupt * handler). * - * This callback is optional. If this callback is not present, then the - * driver must always have signaling enabled. + * This callback is mandatory. */ bool (*enable_signaling)(struct dma_fence *fence); @@ -191,14 +190,11 @@ struct dma_fence_ops { /** * @wait: * - * Custom wait implementation, defaults to dma_fence_default_wait() if - * not set. + * Custom wait implementation, or dma_fence_default_wait. * - * The dma_fence_default_wait implementation should work for any fence, as long - * as @enable_signaling works correctly. This hook allows drivers to - * have an optimized version for the case where a process context is - * already available, e.g. if @enable_signaling for the general case - * needs to set up a worker thread. + * Must not be NULL, set to dma_fence_default_wait for default implementation. + * the dma_fence_default_wait implementation should work for any fence, as long + * as enable_signaling works correctly. * * Must return -ERESTARTSYS if the wait is intr = true and the wait was * interrupted, and remaining jiffies if fence has signaled, or 0 if wait @@ -206,7 +202,7 @@ struct dma_fence_ops { * which should be treated as if the fence is signaled. For example a hardware * lockup could be reported like that. * - * This callback is optional. + * This callback is mandatory. */ signed long (*wait)(struct dma_fence *fence, bool intr, signed long timeout); @@ -221,6 +217,17 @@ struct dma_fence_ops { */ void (*release)(struct dma_fence *fence); + /** + * @fill_driver_data: + * + * Callback to fill in free-form debug info. + * + * Returns amount of bytes filled, or negative error on failure. + * + * This callback is optional. + */ + int (*fill_driver_data)(struct dma_fence *fence, void *data, int size); + /** * @fence_value_str: * @@ -235,9 +242,8 @@ struct dma_fence_ops { * @timeline_value_str: * * Fills in the current value of the timeline as a string, like the - * sequence number. Note that the specific fence passed to this function - * should not matter, drivers should only use it to look up the - * corresponding timeline structures. + * sequence number. This should match what @fill_driver_data prints for + * the most recently signalled fence (assuming no delayed signalling). */ void (*timeline_value_str)(struct dma_fence *fence, char *str, int size); -- cgit v1.2.3 From 07397df29e57cde5799af16e8f148ae10ed75285 Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Sat, 28 Apr 2018 08:21:58 +0530 Subject: dma-mapping: move dma configuration to bus infrastructure ACPI/OF support for configuration of DMA is a bus specific aspect, and thus should be configured by the bus. Introduces a 'dma_configure' bus method so that busses can control their DMA capabilities. Also update the PCI, Platform, ACPI and host1x buses to use the new method. Suggested-by: Christoph Hellwig Signed-off-by: Nipun Gupta Acked-by: Bjorn Helgaas # PCI parts Acked-by: Thierry Reding Reviewed-by: Greg Kroah-Hartman [hch: simplified host1x_dma_configure based on a comment from Thierry, rewrote changelog] Signed-off-by: Christoph Hellwig --- include/linux/device.h | 4 ++++ include/linux/platform_device.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 477956990f5e..63aa672bd394 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -88,6 +88,8 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @resume: Called to bring a device on this bus out of sleep mode. * @num_vf: Called to find out how many virtual functions a device on this * bus supports. + * @dma_configure: Called to setup DMA configuration on a device on + this bus. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU @@ -130,6 +132,8 @@ struct bus_type { int (*num_vf)(struct device *dev); + int (*dma_configure)(struct device *dev); + const struct dev_pm_ops *pm; const struct iommu_ops *iommu_ops; diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 49f634d96118..3097c943fab9 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -356,6 +356,8 @@ extern int platform_pm_restore(struct device *dev); #define platform_pm_restore NULL #endif +extern int platform_dma_configure(struct device *dev); + #ifdef CONFIG_PM_SLEEP #define USE_PLATFORM_PM_SLEEP_OPS \ .suspend = platform_pm_suspend, \ -- cgit v1.2.3 From 3d6ce86ee79465e1b1b6e287f8ea26b553fc768e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 May 2018 16:25:08 +0200 Subject: drivers: remove force dma flag from buses With each bus implementing its own DMA configuration callback, there is no need for bus to explicitly set the force_dma flag. Modify the of_dma_configure function to accept an input parameter which specifies if implicit DMA configuration is required when it is not described by the firmware. Signed-off-by: Nipun Gupta Acked-by: Bjorn Helgaas # PCI parts Reviewed-by: Rob Herring [hch: tweaked the changelog a bit] Signed-off-by: Christoph Hellwig --- include/linux/device.h | 4 ---- include/linux/of_device.h | 8 ++++++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 63aa672bd394..563077d1cdc1 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -98,8 +98,6 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @p: The private data of the driver core, only the driver core can * touch this. * @lock_key: Lock class key for use by the lock validator - * @force_dma: Assume devices on this bus should be set up by dma_configure() - * even if DMA capability is not explicitly described by firmware. * * A bus is a channel between the processor and one or more devices. For the * purposes of the device model, all devices are connected via a bus, even if @@ -140,8 +138,6 @@ struct bus_type { struct subsys_private *p; struct lock_class_key lock_key; - - bool force_dma; }; extern int __must_check bus_register(struct bus_type *bus); diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 8da5a1b31ece..165fd302b442 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -55,7 +55,9 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) return of_node_get(cpu_dev->of_node); } -int of_dma_configure(struct device *dev, struct device_node *np); +int of_dma_configure(struct device *dev, + struct device_node *np, + bool force_dma); void of_dma_deconfigure(struct device *dev); #else /* CONFIG_OF */ @@ -105,7 +107,9 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) return NULL; } -static inline int of_dma_configure(struct device *dev, struct device_node *np) +static inline int of_dma_configure(struct device *dev, + struct device_node *np, + bool force_dma) { return 0; } -- cgit v1.2.3 From 68e8b849b221b37a78a110a0307717d45e3593a0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Wed, 2 May 2018 13:01:22 +0200 Subject: net: initial AF_XDP skeleton MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Buildable skeleton of AF_XDP without any functionality. Just what it takes to register a new address family. Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov --- include/linux/socket.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index ea50f4a65816..7ed4713d5337 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -207,8 +207,9 @@ struct ucred { * PF_SMC protocol family that * reuses AF_INET address family */ +#define AF_XDP 44 /* XDP sockets */ -#define AF_MAX 44 /* For now.. */ +#define AF_MAX 45 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -257,6 +258,7 @@ struct ucred { #define PF_KCM AF_KCM #define PF_QIPCRTR AF_QIPCRTR #define PF_SMC AF_SMC +#define PF_XDP AF_XDP #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -338,6 +340,7 @@ struct ucred { #define SOL_NFC 280 #define SOL_KCM 281 #define SOL_TLS 282 +#define SOL_XDP 283 /* IPX options */ #define IPX_TYPE 1 -- cgit v1.2.3 From fbfc504a24f53f7ebe128ab55cb5dba634f4ece8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Wed, 2 May 2018 13:01:28 +0200 Subject: bpf: introduce new bpf AF_XDP map type BPF_MAP_TYPE_XSKMAP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The xskmap is yet another BPF map, very much inspired by dev/cpu/sockmap, and is a holder of AF_XDP sockets. A user application adds AF_XDP sockets into the map, and by using the bpf_redirect_map helper, an XDP program can redirect XDP frames to an AF_XDP socket. Note that a socket that is bound to certain ifindex/queue index will *only* accept XDP frames from that netdev/queue index. If an XDP program tries to redirect from a netdev/queue index other than what the socket is bound to, the frame will not be received on the socket. A socket can reside in multiple maps. v3: Fixed race and simplified code. v2: Removed one indirection in map lookup. Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 25 +++++++++++++++++++++++++ include/linux/bpf_types.h | 3 +++ 2 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c553f6f9c6b0..68ecdb4eea09 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -676,6 +676,31 @@ static inline int sock_map_prog(struct bpf_map *map, } #endif +#if defined(CONFIG_XDP_SOCKETS) +struct xdp_sock; +struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key); +int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs); +void __xsk_map_flush(struct bpf_map *map); +#else +struct xdp_sock; +static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, + u32 key) +{ + return NULL; +} + +static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs) +{ + return -EOPNOTSUPP; +} + +static inline void __xsk_map_flush(struct bpf_map *map) +{ +} +#endif + /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 2b28fcf6f6ae..d7df1b323082 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -49,4 +49,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) +#if defined(CONFIG_XDP_SOCKETS) +BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) +#endif #endif -- cgit v1.2.3 From 02671e23e7b383763fe1ae4f20b56d8029f9dfc6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Wed, 2 May 2018 13:01:30 +0200 Subject: xsk: wire up XDP_SKB side of AF_XDP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This commit wires up the xskmap to XDP_SKB layer. Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 64899c04c1a6..b7f81e3a70cb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -760,7 +760,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, * This does not appear to be a real limitation for existing software. */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *prog); + struct xdp_buff *xdp, struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); -- cgit v1.2.3 From 865b03f21162e4edfda51fc08693c864b1d4fdaf Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 2 May 2018 13:01:33 +0200 Subject: dev: packet: make packet_direct_xmit a common function The new dev_direct_xmit will be used by AF_XDP in later commits. Signed-off-by: Magnus Karlsson Signed-off-by: Alexei Starovoitov --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 366c32891158..a30435118530 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2486,6 +2486,7 @@ void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); +int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); -- cgit v1.2.3 From 93731ef086cee90af594e62874bb98ae6d6eee91 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 4 May 2018 01:08:13 +0200 Subject: bpf: migrate ebpf ld_abs/ld_ind tests to test_verifier Remove all eBPF tests involving LD_ABS/LD_IND from test_bpf.ko. Reason is that the eBPF tests from test_bpf module do not go via BPF verifier and therefore any instruction rewrites from verifier cannot take place. Therefore, move them into test_verifier which runs out of user space, so that verfier can rewrite LD_ABS/LD_IND internally in upcoming patches. It will have the same effect since runtime tests are also performed from there. This also allows to finally unexport bpf_skb_vlan_{push,pop}_proto and keep it internal to core kernel. Additionally, also add further cBPF LD_ABS/LD_IND test coverage into test_bpf.ko suite. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 68ecdb4eea09..d0e3d7ef36a8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -714,8 +714,6 @@ extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; -extern const struct bpf_func_proto bpf_skb_vlan_push_proto; -extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; -- cgit v1.2.3 From e0cea7ce988cf48cc4052235d2ad2550b3bc4fa0 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 4 May 2018 01:08:14 +0200 Subject: bpf: implement ld_abs/ld_ind in native bpf The main part of this work is to finally allow removal of LD_ABS and LD_IND from the BPF core by reimplementing them through native eBPF instead. Both LD_ABS/LD_IND were carried over from cBPF and keeping them around in native eBPF caused way more trouble than actually worth it. To just list some of the security issues in the past: * fdfaf64e7539 ("x86: bpf_jit: support negative offsets") * 35607b02dbef ("sparc: bpf_jit: fix loads from negative offsets") * e0ee9c12157d ("x86: bpf_jit: fix two bugs in eBPF JIT compiler") * 07aee9439454 ("bpf, sparc: fix usage of wrong reg for load_skb_regs after call") * 6d59b7dbf72e ("bpf, s390x: do not reload skb pointers in non-skb context") * 87338c8e2cbb ("bpf, ppc64: do not reload skb pointers in non-skb context") For programs in native eBPF, LD_ABS/LD_IND are pretty much legacy these days due to their limitations and more efficient/flexible alternatives that have been developed over time such as direct packet access. LD_ABS/LD_IND only cover 1/2/4 byte loads into a register, the load happens in host endianness and its exception handling can yield unexpected behavior. The latter is explained in depth in f6b1b3bf0d5f ("bpf: fix subprog verifier bypass by div/mod by 0 exception") with similar cases of exceptions we had. In native eBPF more recent program types will disable LD_ABS/LD_IND altogether through may_access_skb() in verifier, and given the limitations in terms of exception handling, it's also disabled in programs that use BPF to BPF calls. In terms of cBPF, the LD_ABS/LD_IND is used in networking programs to access packet data. It is not used in seccomp-BPF but programs that use it for socket filtering or reuseport for demuxing with cBPF. This is mostly relevant for applications that have not yet migrated to native eBPF. The main complexity and source of bugs in LD_ABS/LD_IND is coming from their implementation in the various JITs. Most of them keep the model around from cBPF times by implementing a fastpath written in asm. They use typically two from the BPF program hidden CPU registers for caching the skb's headlen (skb->len - skb->data_len) and skb->data. Throughout the JIT phase this requires to keep track whether LD_ABS/LD_IND are used and if so, the two registers need to be recached each time a BPF helper would change the underlying packet data in native eBPF case. At least in eBPF case, available CPU registers are rare and the additional exit path out of the asm written JIT helper makes it also inflexible since not all parts of the JITer are in control from plain C. A LD_ABS/LD_IND implementation in eBPF therefore allows to significantly reduce the complexity in JITs with comparable performance results for them, e.g.: test_bpf tcpdump port 22 tcpdump complex x64 - before 15 21 10 14 19 18 - after 7 10 10 7 10 15 arm64 - before 40 91 92 40 91 151 - after 51 64 73 51 62 113 For cBPF we now track any usage of LD_ABS/LD_IND in bpf_convert_filter() and cache the skb's headlen and data in the cBPF prologue. The BPF_REG_TMP gets remapped from R8 to R2 since it's mainly just used as a local temporary variable. This allows to shrink the image on x86_64 also for seccomp programs slightly since mapping to %rsi is not an ereg. In callee-saved R8 and R9 we now track skb data and headlen, respectively. For normal prologue emission in the JITs this does not add any extra instructions since R8, R9 are pushed to stack in any case from eBPF side. cBPF uses the convert_bpf_ld_abs() emitter which probes the fast path inline already and falls back to bpf_skb_load_helper_{8,16,32}() helper relying on the cached skb data and headlen as well. R8 and R9 never need to be reloaded due to bpf_helper_changes_pkt_data() since all skb access in cBPF is read-only. Then, for the case of native eBPF, we use the bpf_gen_ld_abs() emitter, which calls the bpf_skb_load_helper_{8,16,32}_no_cache() helper unconditionally, does neither cache skb data and headlen nor has an inlined fast path. The reason for the latter is that native eBPF does not have any extra registers available anyway, but even if there were, it avoids any reload of skb data and headlen in the first place. Additionally, for the negative offsets, we provide an alternative bpf_skb_load_bytes_relative() helper in eBPF which operates similarly as bpf_skb_load_bytes() and allows for more flexibility. Tested myself on x64, arm64, s390x, from Sandipan on ppc64. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ include/linux/filter.h | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d0e3d7ef36a8..0e00a13ff01b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -235,6 +235,8 @@ struct bpf_verifier_ops { struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); + int (*gen_ld_abs)(const struct bpf_insn *orig, + struct bpf_insn *insn_buf); u32 (*convert_ctx_access)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, diff --git a/include/linux/filter.h b/include/linux/filter.h index b7f81e3a70cb..da7e16523128 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -47,7 +47,9 @@ struct xdp_buff; /* Additional register mappings for converted user programs. */ #define BPF_REG_A BPF_REG_0 #define BPF_REG_X BPF_REG_7 -#define BPF_REG_TMP BPF_REG_8 +#define BPF_REG_TMP BPF_REG_2 /* scratch reg */ +#define BPF_REG_D BPF_REG_8 /* data, callee-saved */ +#define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */ /* Kernel hidden auxiliary/helper register for hardening step. * Only used by eBPF JITs. It's nothing more than a temporary -- cgit v1.2.3 From 9ea19e7e7613c0dac114bcbb5adc7f1b08eec615 Mon Sep 17 00:00:00 2001 From: Ruslan Bilovol Date: Fri, 4 May 2018 04:24:03 +0300 Subject: include: usb: audio-v3: add BADD-specific values Add BADD-specific predefined values to audio-v3 so usb-audio in ALSA and UAC3 gadget can use them Signed-off-by: Ruslan Bilovol Signed-off-by: Takashi Iwai --- include/linux/usb/audio-v3.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h index a8959aaba0ae..38add1dedf2e 100644 --- a/include/linux/usb/audio-v3.h +++ b/include/linux/usb/audio-v3.h @@ -392,4 +392,30 @@ struct uac3_interrupt_data_msg { #define UAC3_AC_ACTIVE_INTERFACE_CONTROL 0x01 #define UAC3_AC_POWER_DOMAIN_CONTROL 0x02 +/* BADD predefined Unit/Terminal values */ +#define UAC3_BADD_IT_ID1 1 /* Input Terminal ID1: bTerminalID = 1 */ +#define UAC3_BADD_FU_ID2 2 /* Feature Unit ID2: bUnitID = 2 */ +#define UAC3_BADD_OT_ID3 3 /* Output Terminal ID3: bTerminalID = 3 */ +#define UAC3_BADD_IT_ID4 4 /* Input Terminal ID4: bTerminalID = 4 */ +#define UAC3_BADD_FU_ID5 5 /* Feature Unit ID5: bUnitID = 5 */ +#define UAC3_BADD_OT_ID6 6 /* Output Terminal ID6: bTerminalID = 6 */ +#define UAC3_BADD_FU_ID7 7 /* Feature Unit ID7: bUnitID = 7 */ +#define UAC3_BADD_MU_ID8 8 /* Mixer Unit ID8: bUnitID = 8 */ +#define UAC3_BADD_CS_ID9 9 /* Clock Source Entity ID9: bClockID = 9 */ +#define UAC3_BADD_PD_ID10 10 /* Power Domain ID10: bPowerDomainID = 10 */ +#define UAC3_BADD_PD_ID11 11 /* Power Domain ID11: bPowerDomainID = 11 */ + +/* BADD wMaxPacketSize of AS endpoints */ +#define UAC3_BADD_EP_MAXPSIZE_SYNC_MONO_16 0x0060 +#define UAC3_BADD_EP_MAXPSIZE_ASYNC_MONO_16 0x0062 +#define UAC3_BADD_EP_MAXPSIZE_SYNC_MONO_24 0x0090 +#define UAC3_BADD_EP_MAXPSIZE_ASYNC_MONO_24 0x0093 +#define UAC3_BADD_EP_MAXPSIZE_SYNC_STEREO_16 0x00C0 +#define UAC3_BADD_EP_MAXPSIZE_ASYNC_STEREO_16 0x00C4 +#define UAC3_BADD_EP_MAXPSIZE_SYNC_STEREO_24 0x0120 +#define UAC3_BADD_EP_MAXPSIZE_ASYNC_STEREO_24 0x0126 + +/* BADD sample rate is always fixed to 48kHz */ +#define UAC3_BADD_SAMPLING_RATE 48000 + #endif /* __LINUX_USB_AUDIO_V3_H */ -- cgit v1.2.3 From f910cefa32b6cdabc96b126bcfc46d8940b1dc45 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Wed, 2 May 2018 16:17:17 -0400 Subject: bpf: unify main prog and subprog Currently, verifier treat main prog and subprog differently. All subprogs detected are kept in env->subprog_starts while main prog is not kept there. Instead, main prog is implicitly defined as the prog start at 0. There is actually no difference between main prog and subprog, it is better to unify them, and register all progs detected into env->subprog_starts. This could also help simplifying some code logic. Signed-off-by: Jiong Wang Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7e61c395fddf..f655b926e432 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -191,7 +191,7 @@ struct bpf_verifier_env { bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ struct bpf_verifier_log log; - u32 subprog_starts[BPF_MAX_SUBPROGS]; + u32 subprog_starts[BPF_MAX_SUBPROGS + 1]; /* computes the stack depth of each bpf function */ u16 subprog_stack_depth[BPF_MAX_SUBPROGS + 1]; u32 subprog_cnt; -- cgit v1.2.3 From 9c8105bd4402236b1bb0f8f10709c5cec1440a0c Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Wed, 2 May 2018 16:17:18 -0400 Subject: bpf: centre subprog information fields It is better to centre all subprog information fields into one structure. This structure could later serve as function node in call graph. Signed-off-by: Jiong Wang Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index f655b926e432..8f70dc181e23 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -173,6 +173,11 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) #define BPF_MAX_SUBPROGS 256 +struct bpf_subprog_info { + u32 start; /* insn idx of function entry point */ + u16 stack_depth; /* max. stack depth used by this function */ +}; + /* single container for all structs * one verifier_env per bpf_check() call */ @@ -191,9 +196,7 @@ struct bpf_verifier_env { bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ struct bpf_verifier_log log; - u32 subprog_starts[BPF_MAX_SUBPROGS + 1]; - /* computes the stack depth of each bpf function */ - u16 subprog_stack_depth[BPF_MAX_SUBPROGS + 1]; + struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; u32 subprog_cnt; }; -- cgit v1.2.3 From 101c92dc80c8947b92addb34c11ea7a47a1d2561 Mon Sep 17 00:00:00 2001 From: Honghui Zhang Date: Fri, 4 May 2018 13:47:32 +0800 Subject: PCI: mediatek: Set up vendor ID and class type for MT7622 MT7622's hardware default value of vendor ID and class type is not correct, fix that by setup the correct values before linkup with Endpoint. Signed-off-by: Honghui Zhang Signed-off-by: Lorenzo Pieralisi Acked-by: Ryder Lee --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index cc608fc55334..42117a508119 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2119,6 +2119,8 @@ #define PCI_VENDOR_ID_MYRICOM 0x14c1 +#define PCI_VENDOR_ID_MEDIATEK 0x14c3 + #define PCI_VENDOR_ID_TITAN 0x14D2 #define PCI_DEVICE_ID_TITAN_010L 0x8001 #define PCI_DEVICE_ID_TITAN_100L 0x8010 -- cgit v1.2.3 From aae7cfcbb733cf16f3bc9cbb650673b94d5df75f Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Fri, 4 May 2018 16:28:19 +0200 Subject: security: add hook for socketpair() Right now the LSM labels for socketpairs are always uninitialized, since there is no security hook for the socketpair() syscall. This patch adds the required hooks so LSMs can properly label socketpairs. This allows SO_PEERSEC to return useful information on those sockets. Note that the behavior of socketpair() can be emulated by creating a listener socket, connecting to it, and then discarding the initial listener socket. With this workaround, SO_PEERSEC would return the caller's security context. However, with socketpair(), the uninitialized context is returned unconditionally. This is unexpected and makes socketpair() less useful in situations where the security context is crucial to the application. With the new socketpair-hook this disparity can be solved by making socketpair() return the expected security context. Acked-by: Serge Hallyn Signed-off-by: Tom Gundersen Signed-off-by: David Herrmann Signed-off-by: James Morris --- include/linux/lsm_hooks.h | 7 +++++++ include/linux/security.h | 7 +++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 9d0b286f3dba..8f1131c8dd54 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -757,6 +757,11 @@ * @type contains the requested communications type. * @protocol contains the requested protocol. * @kern set to 1 if a kernel socket. + * @socket_socketpair: + * Check permissions before creating a fresh pair of sockets. + * @socka contains the first socket structure. + * @sockb contains the second socket structure. + * Return 0 if permission is granted and the connection was established. * @socket_bind: * Check permission before socket protocol layer bind operation is * performed and the socket @sock is bound to the address specified in the @@ -1656,6 +1661,7 @@ union security_list_options { int (*socket_create)(int family, int type, int protocol, int kern); int (*socket_post_create)(struct socket *sock, int family, int type, int protocol, int kern); + int (*socket_socketpair)(struct socket *socka, struct socket *sockb); int (*socket_bind)(struct socket *sock, struct sockaddr *address, int addrlen); int (*socket_connect)(struct socket *sock, struct sockaddr *address, @@ -1922,6 +1928,7 @@ struct security_hook_heads { struct hlist_head unix_may_send; struct hlist_head socket_create; struct hlist_head socket_post_create; + struct hlist_head socket_socketpair; struct hlist_head socket_bind; struct hlist_head socket_connect; struct hlist_head socket_listen; diff --git a/include/linux/security.h b/include/linux/security.h index ecb06e1357dd..63030c85ee19 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1177,6 +1177,7 @@ int security_unix_may_send(struct socket *sock, struct socket *other); int security_socket_create(int family, int type, int protocol, int kern); int security_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern); +int security_socket_socketpair(struct socket *socka, struct socket *sockb); int security_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen); int security_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen); int security_socket_listen(struct socket *sock, int backlog); @@ -1248,6 +1249,12 @@ static inline int security_socket_post_create(struct socket *sock, return 0; } +static inline int security_socket_socketpair(struct socket *socka, + struct socket *sockb) +{ + return 0; +} + static inline int security_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) -- cgit v1.2.3 From 0cd3cbed3caf6eae3bc0fa4afa4f26a9babfe55a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 3 May 2018 18:37:08 -0700 Subject: bpf: offload: allow offloaded programs to use perf event arrays BPF_MAP_TYPE_PERF_EVENT_ARRAY is special as far as offload goes. The map only holds glue to perf ring, not actual data. Allow non-offloaded perf event arrays to be used in offloaded programs. Offload driver can extract the events from HW and put them in the map for user space to retrieve. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Reviewed-by: Jiong Wang Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0e00a13ff01b..321969da67b7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -110,6 +110,11 @@ static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) return container_of(map, struct bpf_offloaded_map, map); } +static inline bool bpf_map_offload_neutral(const struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; +} + static inline bool bpf_map_support_seq_show(const struct bpf_map *map) { return map->ops->map_seq_show_elem && map->ops->map_check_btf; -- cgit v1.2.3 From 1e0a601437a6111ecf384df010812c53cada6497 Mon Sep 17 00:00:00 2001 From: Lokesh Vutla Date: Fri, 4 May 2018 23:10:23 -0700 Subject: firmware: ti_sci: Switch to SPDX Licensing Switch to SPDX licensing and drop the GPL text which comes redundant. Acked-by: Nishanth Menon Signed-off-by: Lokesh Vutla Signed-off-by: Santosh Shilimkar --- include/linux/soc/ti/ti_sci_protocol.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 0ccbc138c26a..18435e5c6364 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -1,17 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Texas Instruments System Control Interface Protocol * * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/ * Nishanth Menon - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __TISCI_PROTOCOL_H -- cgit v1.2.3 From 6159e12e11770fb25e748af90f6c5206c1df09ee Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 20 Apr 2018 11:55:13 -0400 Subject: media: meye: allow building it with COMPILE_TEST on non-x86 This driver depends on sony-laptop driver, but this is available only for x86. So, add a stub function, in order to allow building it on non-x86 too. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Mauro Carvalho Chehab --- include/linux/sony-laptop.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sony-laptop.h b/include/linux/sony-laptop.h index 1a4b77317fa1..374d0fdb0743 100644 --- a/include/linux/sony-laptop.h +++ b/include/linux/sony-laptop.h @@ -28,7 +28,11 @@ #define SONY_PIC_COMMAND_GETCAMERAROMVERSION 18 /* obsolete */ #define SONY_PIC_COMMAND_GETCAMERAREVISION 19 /* obsolete */ +#if IS_ENABLED(CONFIG_SONY_LAPTOP) int sony_pic_camera_command(int command, u8 value); +#else +static inline int sony_pic_camera_command(int command, u8 value) { return 0; }; +#endif #endif /* __KERNEL__ */ -- cgit v1.2.3 From bfb15f2a95cbbc548b59abf8007d0fdb35fdfee5 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Thu, 3 May 2018 14:05:40 +0200 Subject: netfilter: extract Passive OS fingerprint infrastructure from xt_osf Add nf_osf_ttl() and nf_osf_match() into nf_osf.c to prepare for nf_tables support. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_osf.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 include/linux/netfilter/nf_osf.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h new file mode 100644 index 000000000000..a2b39602e87d --- /dev/null +++ b/include/linux/netfilter/nf_osf.h @@ -0,0 +1,27 @@ +#include + +/* Initial window size option state machine: multiple of mss, mtu or + * plain numeric value. Can also be made as plain numeric value which + * is not a multiple of specified value. + */ +enum nf_osf_window_size_options { + OSF_WSS_PLAIN = 0, + OSF_WSS_MSS, + OSF_WSS_MTU, + OSF_WSS_MODULO, + OSF_WSS_MAX, +}; + +enum osf_fmatch_states { + /* Packet does not match the fingerprint */ + FMATCH_WRONG = 0, + /* Packet matches the fingerprint */ + FMATCH_OK, + /* Options do not match the fingerprint, but header does */ + FMATCH_OPT_WRONG, +}; + +bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, + int hooknum, struct net_device *in, struct net_device *out, + const struct nf_osf_info *info, struct net *net, + const struct list_head *nf_osf_fingers); -- cgit v1.2.3 From 1d3b9917df9725382f4e0005ecaddee114ebc847 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Apr 2018 19:11:46 +0200 Subject: ide: kill ide_toggle_bounce ide_toggle_bounce did select various strange block bounce limits, including not bouncing at all as soon as an iommu is present in the system. Given that the dma_map routines now handle any required bounce buffering except for ISA DMA, and the ide code already must handle either ISA DMA or highmem at least for iommu equipped systems we can get rid of the block layer bounce limit setting entirely. Signed-off-by: Christoph Hellwig Reviewed-by: Jens Axboe --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index ca9d34feb572..11f0dd03a4b4 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1508,8 +1508,6 @@ static inline void ide_set_hwifdata (ide_hwif_t * hwif, void *data) hwif->hwif_data = data; } -extern void ide_toggle_bounce(ide_drive_t *drive, int on); - u64 ide_get_lba_addr(struct ide_cmd *, int); u8 ide_dump_status(ide_drive_t *, const char *, u8); -- cgit v1.2.3 From 325ef1857fff8b2049322921e19421b6c5ad74e5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 12 Apr 2018 09:33:30 +0200 Subject: PCI: remove PCI_DMA_BUS_IS_PHYS This was used by the ide, scsi and networking code in the past to determine if they should bounce payloads. Now that the dma mapping always have to support dma to all physical memory (thanks to swiotlb for non-iommu systems) there is no need to this crude hack any more. Signed-off-by: Christoph Hellwig Acked-by: Palmer Dabbelt (for riscv) Reviewed-by: Jens Axboe --- include/linux/dma-mapping.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index f8ab1c0f589e..a6d4ac8b81e4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -133,7 +133,6 @@ struct dma_map_ops { #ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK u64 (*get_required_mask)(struct device *dev); #endif - int is_phys; }; extern const struct dma_map_ops dma_direct_ops; -- cgit v1.2.3 From a2268cfbf599e7f55d4ee68193f08b4f44535fac Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 May 2018 15:34:32 -0400 Subject: xprtrdma: Add proper SPDX tags for NetApp-contributed source Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/rpc_rdma.h | 1 + include/linux/sunrpc/xprtrdma.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index 8f144db73e38..92d182fd8e3b 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* * Copyright (c) 2015-2017 Oracle. All rights reserved. * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h index 5859563e3c1f..86fc38ff0355 100644 --- a/include/linux/sunrpc/xprtrdma.h +++ b/include/linux/sunrpc/xprtrdma.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. * -- cgit v1.2.3 From 37ac86c3a76c113619b7d9afe0251bbfc04cb80a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 May 2018 15:34:53 -0400 Subject: SUNRPC: Initialize rpc_rqst outside of xprt->reserve_lock alloc_slot is a transport-specific op, but initializing an rpc_rqst is common to all transports. In addition, the only part of initial- izing an rpc_rqst that needs serialization is getting a fresh XID. Move rpc_rqst initialization to common code in preparation for adding a transport-specific alloc_slot to xprtrdma. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 5fea0fb420df..9784e2875e7e 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -324,6 +324,7 @@ struct xprt_class { struct rpc_xprt *xprt_create_transport(struct xprt_create *args); void xprt_connect(struct rpc_task *task); void xprt_reserve(struct rpc_task *task); +void xprt_request_init(struct rpc_task *task); void xprt_retry_reserve(struct rpc_task *task); int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task); int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); -- cgit v1.2.3 From a9cde23ab7cdf5e4e93432dffd0e734267f2b745 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 May 2018 15:34:59 -0400 Subject: SUNRPC: Add a ->free_slot transport callout Refactor: xprtrdma needs to have better control over when RPCs are awoken from the backlog queue, so replace xprt_free_slot with a transport op callout. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xprt.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 9784e2875e7e..706eef12bbc0 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -127,6 +127,8 @@ struct rpc_xprt_ops { int (*reserve_xprt)(struct rpc_xprt *xprt, struct rpc_task *task); void (*release_xprt)(struct rpc_xprt *xprt, struct rpc_task *task); void (*alloc_slot)(struct rpc_xprt *xprt, struct rpc_task *task); + void (*free_slot)(struct rpc_xprt *xprt, + struct rpc_rqst *req); void (*rpcbind)(struct rpc_task *task); void (*set_port)(struct rpc_xprt *xprt, unsigned short port); void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); @@ -329,6 +331,8 @@ void xprt_retry_reserve(struct rpc_task *task); int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task); int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); +void xprt_free_slot(struct rpc_xprt *xprt, + struct rpc_rqst *req); void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); -- cgit v1.2.3 From edb41e61a54ee75fae31302775e0301fdcb0caaa Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 May 2018 15:35:09 -0400 Subject: xprtrdma: Make rpc_rqst part of rpcrdma_req This simplifies allocation of the generic RPC slot and xprtrdma specific per-RPC resources. It also makes xprtrdma more like the socket-based transports: ->buf_alloc and ->buf_free are now responsible only for send and receive buffers. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 706eef12bbc0..336fd1a19cca 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -84,7 +84,6 @@ struct rpc_rqst { void (*rq_release_snd_buf)(struct rpc_rqst *); /* release rq_enc_pages */ struct list_head rq_list; - void *rq_xprtdata; /* Per-xprt private data */ void *rq_buffer; /* Call XDR encode buffer */ size_t rq_callsize; void *rq_rbuffer; /* Reply XDR decode buffer */ -- cgit v1.2.3 From 04e7b3d7eabefa0807b398233f019f274945ee79 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 7 May 2018 06:35:51 -0300 Subject: iio: iio.h: use nested struct support on kernel-doc markup Solve those Sphinx warnings: ./include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.sign' not described in 'iio_chan_spec' ./include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.realbits' not described in 'iio_chan_spec' ./include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.storagebits' not described in 'iio_chan_spec' ./include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.shift' not described in 'iio_chan_spec' ./include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.repeat' not described in 'iio_chan_spec' ./include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.endianness' not described in 'iio_chan_spec' ./include/linux/iio/iio.h:191: WARNING: Unexpected indentation. ./include/linux/iio/iio.h:192: WARNING: Block quote ends without a blank line; unexpected unindent. ./include/linux/iio/iio.h:198: WARNING: Definition list ends without a blank line; unexpected unindent. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 11579fd4126e..a74cb177dc6f 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -183,18 +183,18 @@ struct iio_event_spec { * @address: Driver specific identifier. * @scan_index: Monotonic index to give ordering in scans when read * from a buffer. - * @scan_type: sign: 's' or 'u' to specify signed or unsigned - * realbits: Number of valid bits of data - * storagebits: Realbits + padding - * shift: Shift right by this before masking out - * realbits. - * repeat: Number of times real/storage bits - * repeats. When the repeat element is - * more than 1, then the type element in - * sysfs will show a repeat value. - * Otherwise, the number of repetitions is - * omitted. - * endianness: little or big endian + * @scan_type: struct describing the scan type + * @scan_type.sign: 's' or 'u' to specify signed or unsigned + * @scan_type.realbits: Number of valid bits of data + * @scan_type.storagebits: Realbits + padding + * @scan_type.shift: Shift right by this before masking out + * realbits. + * @scan_type.repeat: Number of times real/storage bits repeats. + * When the repeat element is more than 1, then + * the type element in sysfs will show a repeat + * value. Otherwise, the number of repetitions + * is omitted. + * @scan_type.endianness: little or big endian * @info_mask_separate: What information is to be exported that is specific to * this channel. * @info_mask_separate_available: What availability information is to be -- cgit v1.2.3 From 333c8c1216c1e7ead6af7b3d667b43eb425b5034 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 7 May 2018 15:52:55 -0500 Subject: PCI: Add Qualcomm vendor ID Add the Qualcomm vendor ID to pci_ids.h and use it in quirks. Signed-off-by: Bjorn Helgaas --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index cc608fc55334..883cb7bf78aa 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2387,6 +2387,8 @@ #define PCI_VENDOR_ID_LENOVO 0x17aa +#define PCI_VENDOR_ID_QCOM 0x17cb + #define PCI_VENDOR_ID_CDNS 0x17cd #define PCI_VENDOR_ID_ARECA 0x17d3 -- cgit v1.2.3 From d22b362184553899f7d6b6760899a77d3b2d7c1b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 3 May 2018 18:39:38 -0500 Subject: PCI: pciehp: Add quirk for Command Completed errata MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Several PCIe hotplug controllers have errata that mean they do not set the Command Completed bit unless writes to the Slot Command register change "Control" bits. Command Completed is never set for writes that only change software notification "Enable" bits. This results in timeouts like this: pciehp 0000:00:1c.0:pcie004: Timeout on hotplug command 0x1038 (issued 65284 msec ago) When this erratum is present, avoid these timeouts by marking commands "completed" immediately unless they change the "Control" bits. Here's the text of the Intel erratum CF118. We assume this applies to all Intel parts: CF118 PCIe Slot Status Register Command Completed bit not always updated on any configuration write to the Slot Control Register Problem: For PCIe root ports (devices 0 - 10) supporting hot-plug, the Slot Status Register (offset AAh) Command Completed (bit[4]) status is updated under the following condition: IOH will set Command Completed bit after delivering the new commands written in the Slot Controller register (offset A8h) to VPP. The IOH detects new commands written in Slot Control register by checking the change of value for Power Controller Control (bit[10]), Power Indicator Control (bits[9:8]), Attention Indicator Control (bits[7:6]), or Electromechanical Interlock Control (bit[11]) fields. Any other configuration writes to the Slot Control register without changing the values of these fields will not cause Command Completed bit to be set. The PCIe Base Specification Revision 2.0 or later describes the “Slot Control Register” in section 7.8.10, as follows (Reference section 7.8.10, Slot Control Register, Offset 18h). In hot-plug capable Downstream Ports, a write to the Slot Control register must cause a hot-plug command to be generated (see Section 6.7.3.2 for details on hot-plug commands). A write to the Slot Control register in a Downstream Port that is not hotplug capable must not cause a hot-plug command to be executed. The PCIe Spec intended that every write to the Slot Control Register is a command and expected a command complete status to abstract the VPP implementation specific nuances from the OS software. IOH PCIe Slot Control Register implementation is not fully conforming to the PCIe Specification in this respect. Implication: Software checking on the Command Completed status after writing to the Slot Control register may time out. Workaround: Software can read the Slot Control register and compare the existing and new values to determine if it should check the Command Completed status after writing to the Slot Control register. Per Sinan, the Qualcomm QDF2400 controller also does not set the Command Completed bit unless writes to the Slot Command register change "Control" bits. Link: http://www.intel.com/content/www/us/en/processors/xeon/xeon-e7-v2-spec-update.html Link: https://lkml.kernel.org/r/8770820b-85a0-172b-7230-3a44524e6c9f@molgen.mpg.de Reported-by: Paul Menzel # Lenovo X60 Tested-by: Paul Menzel # Lenovo X60 Signed-off-by: Sinan Kaya # Qcom quirk Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 73178a2fcee0..14ab65b83067 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -406,6 +406,9 @@ struct pci_dev { struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */ struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file for WC mapping of resources */ +#ifdef CONFIG_HOTPLUG_PCI_PCIE + unsigned int broken_cmd_compl:1; /* No compl for some cmds */ +#endif #ifdef CONFIG_PCIE_PTM unsigned int ptm_root:1; unsigned int ptm_enabled:1; -- cgit v1.2.3 From 17e8f0d4cee2bf50c2764bb4318284ce16152c5f Mon Sep 17 00:00:00 2001 From: Gilles Buloz Date: Thu, 3 May 2018 15:21:44 -0500 Subject: PCI: Check whether bridges allow access to extended config space Even if a device supports extended config space, i.e., it is a PCI-X Mode 2 or a PCI Express device, the extended space may not be accessible if there's a conventional PCI bus in the path to it. We currently figure that out in pci_cfg_space_size() by reading the first dword of extended config space. On most platforms that returns ~0 data if the space is inaccessible, but it may set error bits in PCI status registers, and on some platforms it causes exceptions that we currently don't recover from. For example, a PCIe-to-conventional PCI bridge treats config transactions with a non-zero Extended Register Address as an Unsupported Request on PCIe and a received Master-Abort on the destination bus (see PCI Express to PCI/PCI-X Bridge spec, r1.0, sec 4.1.3). A sample case is a LS1043A CPU (NXP QorIQ Layerscape) platform with the following bus topology: LS1043 PCIe Root Port -> PEX8112 PCIe-to-PCI bridge (doesn't support ext cfg on PCI side) -> PMC slot connector (for legacy PMC modules) With a PMC module topology as follows: PMC connector -> PCI-to-PCIe bridge -> PCIe switch (4 ports) -> 4 PCIe devices (one on each port) The PCIe devices on the PMC module support extended config space, but we can't reach it because the PEX8112 can't generate accesses to the extended space on its secondary bus. Attempts to access it cause Unsupported Request errors, which result in synchronous aborts on this platform. To avoid these errors, check whether bridges are capable of generating extended config space addresses on their secondary interfaces. If they can't, we restrict devices below the bridge to only the 256-byte PCI-compatible config space. Signed-off-by: Gilles Buloz [bhelgaas: changelog, rework patch so bus_flags testing is all in pci_bridge_child_ext_cfg_accessible()] Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 73178a2fcee0..5eb97e198325 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -217,6 +217,7 @@ enum pci_bus_flags { PCI_BUS_FLAGS_NO_MSI = (__force pci_bus_flags_t) 1, PCI_BUS_FLAGS_NO_MMRBC = (__force pci_bus_flags_t) 2, PCI_BUS_FLAGS_NO_AERSID = (__force pci_bus_flags_t) 4, + PCI_BUS_FLAGS_NO_EXTCFG = (__force pci_bus_flags_t) 8, }; /* Values from Link Status register, PCIe r3.1, sec 7.8.8 */ -- cgit v1.2.3 From c36a68fab1c3ddf71918cd1e5937a647cd80ba2b Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Fri, 4 May 2018 17:17:46 +0200 Subject: net: u64_stats_sync: Remove functions without user Commit 67db3e4bfbc9 ("tcp: no longer hold ehash lock while calling tcp_get_info()") removes the only users of u64_stats_update_end/begin_raw() without removing the function in header file. Remove no longer used functions. Cc: Eric Dumazet Signed-off-by: Anna-Maria Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/u64_stats_sync.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 07ee0f84a46c..a27604f99ed0 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -112,20 +112,6 @@ u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, #endif } -static inline void u64_stats_update_begin_raw(struct u64_stats_sync *syncp) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - raw_write_seqcount_begin(&syncp->seq); -#endif -} - -static inline void u64_stats_update_end_raw(struct u64_stats_sync *syncp) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - raw_write_seqcount_end(&syncp->seq); -#endif -} - static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) -- cgit v1.2.3 From 0bc5fe857274133ca028ebb15ff2e8549a369916 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Sat, 5 May 2018 18:42:59 -0700 Subject: qed*: Refactor mf_mode to consist of bits. `mf_mode' field indicates the multi-partitioning mode the device is configured to. This method doesn't scale very well, adding a new MF mode requires going over all the existing conditions, and deciding whether those are needed for the new mode or not. The patch defines a set of bit-fields for modes which are derived according to the mode info shared by the MFW and all the configuration would be made according to those. To add a new mode, there would be a single place where we'll need to go and choose which bits apply and which don't. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index e53f9c7c2809..5dac56147a07 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -359,7 +359,7 @@ struct qed_dev_info { #define QED_MFW_VERSION_3_OFFSET 24 u32 flash_size; - u8 mf_mode; + bool b_inter_pf_switch; bool tx_switching; bool rdma_supported; u16 mtu; -- cgit v1.2.3 From 27bf96e32c92599dc7523b36d6c761fc8312c8c0 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Sat, 5 May 2018 18:43:00 -0700 Subject: qed: Remove unused data member 'is_mf_default'. The data member 'is_mf_default' is not used by the qed/qede drivers, removing the same. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 5dac56147a07..907976fd56f7 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -339,7 +339,6 @@ struct qed_dev_info { u8 num_hwfns; u8 hw_mac[ETH_ALEN]; - bool is_mf_default; /* FW version */ u16 fw_major; -- cgit v1.2.3 From cac6f691546b9efd50c31c0db97fe50d0357104a Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Sat, 5 May 2018 18:43:02 -0700 Subject: qed: Add support for Unified Fabric Port. This patch adds driver changes for supporting the Unified Fabric Port (UFP). This is a new paritioning mode wherein MFW provides the set of parameters to be used by the device such as traffic class, outer-vlan tag value, priority type etc. Drivers receives this info via notifications from mfw and configures the hardware accordingly. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_ll2_if.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 266c1fb45387..5eb022953aca 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -202,6 +202,7 @@ struct qed_ll2_tx_pkt_info { bool enable_ip_cksum; bool enable_l4_cksum; bool calc_ip_len; + bool remove_stag; }; #define QED_LL2_UNUSED_HANDLE (0xff) @@ -220,6 +221,11 @@ struct qed_ll2_params { u8 ll2_mac_address[ETH_ALEN]; }; +enum qed_ll2_xmit_flags { + /* FIP discovery packet */ + QED_LL2_XMIT_FLAGS_FIP_DISCOVERY +}; + struct qed_ll2_ops { /** * @brief start - initializes ll2 @@ -245,10 +251,12 @@ struct qed_ll2_ops { * * @param cdev * @param skb + * @param xmit_flags - Transmit options defined by the enum qed_ll2_xmit_flags. * * @return 0 on success, otherwise error value. */ - int (*start_xmit)(struct qed_dev *cdev, struct sk_buff *skb); + int (*start_xmit)(struct qed_dev *cdev, struct sk_buff *skb, + unsigned long xmit_flags); /** * @brief register_cb_ops - protocol driver register the callback for Rx/Tx -- cgit v1.2.3 From 72a338bcc6ae51e01c95d687e5d775e3fe52eff1 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 4 May 2018 11:32:59 +0200 Subject: net: core: rework basic flow dissection helper When the core networking needs to detect the transport offset in a given packet and parse it explicitly, a full-blown flow_keys struct is used for storage. This patch introduces a smaller keys store, rework the basic flow dissect helper to use it, and apply this new helper where possible - namely in skb_probe_transport_header(). The used flow dissector data structures are renamed to match more closely the new role. The above gives ~50% performance improvement in micro benchmarking around skb_probe_transport_header() and ~30% around eth_get_headlen(), mostly due to the smaller memset. Small, but measurable improvement is measured also in macro benchmarking. v1 -> v2: use the new helper in eth_get_headlen() and skb_get_poff(), as per DaveM suggestion Suggested-by: David Miller Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/skbuff.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 908d66e55b14..693564a9a979 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1171,7 +1171,7 @@ void __skb_get_hash(struct sk_buff *skb); u32 __skb_get_hash_symmetric(const struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, - const struct flow_keys *keys, int hlen); + const struct flow_keys_basic *keys, int hlen); __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, void *data, int hlen_proto); @@ -1208,13 +1208,14 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, NULL, 0, 0, 0, flags); } -static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow, - void *data, __be16 proto, - int nhoff, int hlen, - unsigned int flags) +static inline bool +skb_flow_dissect_flow_keys_basic(const struct sk_buff *skb, + struct flow_keys_basic *flow, void *data, + __be16 proto, int nhoff, int hlen, + unsigned int flags) { memset(flow, 0, sizeof(*flow)); - return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow, + return __skb_flow_dissect(skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } @@ -2350,11 +2351,12 @@ static inline void skb_pop_mac_header(struct sk_buff *skb) static inline void skb_probe_transport_header(struct sk_buff *skb, const int offset_hint) { - struct flow_keys keys; + struct flow_keys_basic keys; if (skb_transport_header_was_set(skb)) return; - else if (skb_flow_dissect_flow_keys(skb, &keys, 0)) + + if (skb_flow_dissect_flow_keys_basic(skb, &keys, 0, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); else skb_set_transport_header(skb, offset_hint); -- cgit v1.2.3 From ea6eca778500b0aaf6e5f10dac4d2cd745c2a50b Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Fri, 4 May 2018 01:08:14 +0000 Subject: seccomp: Audit attempts to modify the actions_logged sysctl The decision to log a seccomp action will always be subject to the value of the kernel.seccomp.actions_logged sysctl, even for processes that are being inspected via the audit subsystem, in an upcoming patch. Therefore, we need to emit an audit record on attempts at writing to the actions_logged sysctl when auditing is enabled. This patch updates the write handler for the actions_logged sysctl to emit an audit record on attempts to write to the sysctl. Successful writes to the sysctl will result in a record that includes a normalized list of logged actions in the "actions" field and a "res" field equal to 1. Unsuccessful writes to the sysctl will result in a record that doesn't include the "actions" field and has a "res" field equal to 0. Not all unsuccessful writes to the sysctl are audited. For example, an audit record will not be emitted if an unprivileged process attempts to open the sysctl file for reading since that access control check is not part of the sysctl's write handler. Below are some example audit records when writing various strings to the actions_logged sysctl. Writing "not-a-real-action", when the kernel.seccomp.actions_logged sysctl previously was "kill_process kill_thread trap errno trace log", emits this audit record: type=CONFIG_CHANGE msg=audit(1525392371.454:120): op=seccomp-logging actions=? old-actions=kill_process,kill_thread,trap,errno,trace,log res=0 If you then write "kill_process kill_thread errno trace log", this audit record is emitted: type=CONFIG_CHANGE msg=audit(1525392401.645:126): op=seccomp-logging actions=kill_process,kill_thread,errno,trace,log old-actions=kill_process,kill_thread,trap,errno,trace,log res=1 If you then write "log log errno trace kill_process kill_thread", which is unordered and contains the log action twice, it results in the same actions value as the previous record: type=CONFIG_CHANGE msg=audit(1525392436.354:132): op=seccomp-logging actions=kill_process,kill_thread,errno,trace,log old-actions=kill_process,kill_thread,errno,trace,log res=1 If you then write an empty string to the sysctl, this audit record is emitted: type=CONFIG_CHANGE msg=audit(1525392494.413:138): op=seccomp-logging actions=(none) old-actions=kill_process,kill_thread,errno,trace,log res=1 No audit records are generated when reading the actions_logged sysctl. Suggested-by: Steve Grubb Signed-off-by: Tyler Hicks Acked-by: Kees Cook Signed-off-by: Paul Moore --- include/linux/audit.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 75d5b031e802..d4e35e7a80c0 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -233,6 +233,8 @@ extern void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type); extern void __audit_seccomp(unsigned long syscall, long signr, int code); +extern void audit_seccomp_actions_logged(const char *names, + const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); static inline bool audit_dummy_context(void) @@ -502,6 +504,9 @@ static inline void __audit_seccomp(unsigned long syscall, long signr, int code) { } static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } +static inline void audit_seccomp_actions_logged(const char *names, + const char *old_names, int res) +{ } static inline int auditsc_get_stamp(struct audit_context *ctx, struct timespec64 *t, unsigned int *serial) { -- cgit v1.2.3 From 326bee0286d7f6b0d780f5b75a35ea9fe489a802 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Fri, 4 May 2018 01:08:15 +0000 Subject: seccomp: Don't special case audited processes when logging Seccomp logging for "handled" actions such as RET_TRAP, RET_TRACE, or RET_ERRNO can be very noisy for processes that are being audited. This patch modifies the seccomp logging behavior to treat processes that are being inspected via the audit subsystem the same as processes that aren't under inspection. Handled actions will no longer be logged just because the process is being inspected. Since v4.14, applications have the ability to request logging of handled actions by using the SECCOMP_FILTER_FLAG_LOG flag when loading seccomp filters. With this patch, the logic for deciding if an action will be logged is: if action == RET_ALLOW: do not log else if action not in actions_logged: do not log else if action == RET_KILL: log else if action == RET_LOG: log else if filter-requests-logging: log else: do not log Reported-by: Steve Grubb Signed-off-by: Tyler Hicks Acked-by: Kees Cook Signed-off-by: Paul Moore --- include/linux/audit.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index d4e35e7a80c0..b639cf1f55ff 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -232,7 +232,7 @@ extern void __audit_file(const struct file *); extern void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type); -extern void __audit_seccomp(unsigned long syscall, long signr, int code); +extern void audit_seccomp(unsigned long syscall, long signr, int code); extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); @@ -304,12 +304,6 @@ static inline void audit_inode_child(struct inode *parent, } void audit_core_dumps(long signr); -static inline void audit_seccomp(unsigned long syscall, long signr, int code) -{ - if (audit_enabled && unlikely(!audit_dummy_context())) - __audit_seccomp(syscall, signr, code); -} - static inline void audit_ptrace(struct task_struct *t) { if (unlikely(!audit_dummy_context())) @@ -500,8 +494,6 @@ static inline void audit_inode_child(struct inode *parent, { } static inline void audit_core_dumps(long signr) { } -static inline void __audit_seccomp(unsigned long syscall, long signr, int code) -{ } static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } static inline void audit_seccomp_actions_logged(const char *names, -- cgit v1.2.3 From 1433269c4d2461be1f36db5dbb453976b38996ff Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 5 Apr 2018 13:42:00 +0200 Subject: mmc: core: Export a function mmc_sw_reset() to allow soft reset of cards It's rather common that a firmware is loaded into an SDIO func device memory, by the corresponding SDIO func driver during ->probe() time. However, to actually start running the new firmware, sometimes a soft reset (no power cycle) and a re-initialization of the card is needed. This is for example the case with the Espressif ESP8089 WiFi chips, when connected to an SDIO interface. To cope with this scenario, let's add a new exported function, mmc_sw_reset(), which may be called when a soft reset and re-initialization of the card are needed. The mmc_sw_reset() is implemented on top of a new bus ops callback, similar to how the mmc_hw_reset() has been implemented. Signed-off-by: Ulf Hansson Tested-by: Quentin Schulz Reviewed-by: Shawn Lin --- include/linux/mmc/core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 927519385482..134a6483347a 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -177,6 +177,7 @@ int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); int mmc_hw_reset(struct mmc_host *host); +int mmc_sw_reset(struct mmc_host *host); void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card); #endif /* LINUX_MMC_CORE_H */ -- cgit v1.2.3 From 15b28bbcd567a9199481ecfef39702b258f9baff Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Apr 2018 17:22:28 +0200 Subject: dma-debug: move initialization to common code Most mainstream architectures are using 65536 entries, so lets stick to that. If someone is really desperate to override it that can still be done through , but I'd rather see a really good rationale for that. dma_debug_init is now called as a core_initcall, which for many architectures means much earlier, and provides dma-debug functionality earlier in the boot process. This should be safe as it only relies on the memory allocator already being available. Signed-off-by: Christoph Hellwig Acked-by: Marek Szyprowski Reviewed-by: Robin Murphy --- include/linux/dma-debug.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index c7d844f09c3a..a785f2507159 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -30,8 +30,6 @@ struct bus_type; extern void dma_debug_add_bus(struct bus_type *bus); -extern void dma_debug_init(u32 num_entries); - extern int dma_debug_resize_entries(u32 num_entries); extern void debug_dma_map_page(struct device *dev, struct page *page, @@ -100,10 +98,6 @@ static inline void dma_debug_add_bus(struct bus_type *bus) { } -static inline void dma_debug_init(u32 num_entries) -{ -} - static inline int dma_debug_resize_entries(u32 num_entries) { return 0; -- cgit v1.2.3 From 5212213aa5a2359dd0474c9dab22b6220b591fe1 Mon Sep 17 00:00:00 2001 From: Ram Pai Date: Tue, 27 Mar 2018 02:09:26 -0700 Subject: mm, powerpc, x86: define VM_PKEY_BITx bits if CONFIG_ARCH_HAS_PKEYS is enabled VM_PKEY_BITx are defined only if CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS is enabled. Powerpc also needs these bits. Hence lets define the VM_PKEY_BITx bits for any architecture that enables CONFIG_ARCH_HAS_PKEYS. Reviewed-by: Dave Hansen Signed-off-by: Ram Pai Reviewed-by: Ingo Molnar Reviewed-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- include/linux/mm.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1ac1f06a4be6..c6a6f2492c1b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -228,15 +228,16 @@ extern unsigned int kobjsize(const void *objp); #define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ -#if defined(CONFIG_X86) -# define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ -#if defined (CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) +#ifdef CONFIG_ARCH_HAS_PKEYS # define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 # define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */ # define VM_PKEY_BIT1 VM_HIGH_ARCH_1 # define VM_PKEY_BIT2 VM_HIGH_ARCH_2 # define VM_PKEY_BIT3 VM_HIGH_ARCH_3 -#endif +#endif /* CONFIG_ARCH_HAS_PKEYS */ + +#if defined(CONFIG_X86) +# define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ #elif defined(CONFIG_PPC) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) -- cgit v1.2.3 From 2c9e0a6fa2bb75697981825153128f43b32f6d08 Mon Sep 17 00:00:00 2001 From: Ram Pai Date: Tue, 27 Mar 2018 02:09:27 -0700 Subject: mm, powerpc, x86: introduce an additional vma bit for powerpc pkey Currently only 4bits are allocated in the vma flags to hold 16 keys. This is sufficient for x86. PowerPC supports 32 keys, which needs 5bits. This patch allocates an additional bit. Reviewed-by: Ingo Molnar Acked-by: Balbir Singh Signed-off-by: Ram Pai [mpe: Fold in #if VM_PKEY_BIT4 as noticed by Dave Hansen] Signed-off-by: Michael Ellerman --- include/linux/mm.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c6a6f2492c1b..fc25929031c0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -231,9 +231,14 @@ extern unsigned int kobjsize(const void *objp); #ifdef CONFIG_ARCH_HAS_PKEYS # define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 # define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */ -# define VM_PKEY_BIT1 VM_HIGH_ARCH_1 +# define VM_PKEY_BIT1 VM_HIGH_ARCH_1 /* on x86 and 5-bit value on ppc64 */ # define VM_PKEY_BIT2 VM_HIGH_ARCH_2 # define VM_PKEY_BIT3 VM_HIGH_ARCH_3 +#ifdef CONFIG_PPC +# define VM_PKEY_BIT4 VM_HIGH_ARCH_4 +#else +# define VM_PKEY_BIT4 0 +#endif #endif /* CONFIG_ARCH_HAS_PKEYS */ #if defined(CONFIG_X86) -- cgit v1.2.3 From cd419a513146367af08b895a8f7d360e4e77b638 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 10 Apr 2018 13:12:20 +1000 Subject: mm/pkeys: Remove include of asm/mmu_context.h from pkeys.h While trying to unify the pkey handling in show_smap() between x86 and powerpc we stumbled across various build failures due to the order of includes between the two arches. Part of the problem is that linux/pkeys.h includes asm/mmu_context.h, and the relationship between asm/mmu_context.h and asm/pkeys.h is not consistent between the two arches. It would be cleaner if linux/pkeys.h only included asm/pkeys.h, creating a single integration point for the arch pkey definitions. So this patch removes the include of asm/mmu_context.h from linux/pkeys.h. We can't prove that this is safe in the general case, but it passes all the build tests I've thrown at it. Also asm/mmu_context.h is included widely while linux/pkeys.h is not, so most likely any code that is including linux/pkeys.h is already getting asm/mmu_context.h from elsewhere. Signed-off-by: Michael Ellerman --- include/linux/pkeys.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index 0794ca78c379..ed06e1a67bfa 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -3,7 +3,6 @@ #define _LINUX_PKEYS_H #include -#include #ifdef CONFIG_ARCH_HAS_PKEYS #include -- cgit v1.2.3 From dbec10e58deadba596d59a0ab4a394fef271992f Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 11 Apr 2018 23:41:42 +1000 Subject: mm/pkeys, powerpc, x86: Provide an empty vma_pkey() in linux/pkeys.h Consolidate the pkey handling by providing a common empty definition of vma_pkey() in pkeys.h when CONFIG_ARCH_HAS_PKEYS=n. This also removes another entanglement of pkeys.h and asm/mmu_context.h. Signed-off-by: Michael Ellerman Reviewed-by: Ram Pai Reviewed-by: Dave Hansen --- include/linux/pkeys.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index ed06e1a67bfa..aad54663763b 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -13,6 +13,11 @@ #define PKEY_DEDICATED_EXECUTE_ONLY 0 #define ARCH_VM_PKEY_FLAGS 0 +static inline int vma_pkey(struct vm_area_struct *vma) +{ + return 0; +} + static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { return (pkey == 0); -- cgit v1.2.3 From 555934a71bb479ce109722807b374f2d98aefe89 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 12 Apr 2018 23:54:00 +1000 Subject: x86/pkeys: Move vma_pkey() into asm/pkeys.h Move the last remaining pkey helper, vma_pkey() into asm/pkeys.h Signed-off-by: Michael Ellerman Reviewed-by: Dave Hansen --- include/linux/pkeys.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index aad54663763b..946cb773b79f 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -2,7 +2,7 @@ #ifndef _LINUX_PKEYS_H #define _LINUX_PKEYS_H -#include +#include #ifdef CONFIG_ARCH_HAS_PKEYS #include -- cgit v1.2.3 From 4414ef9536c398ebc4e1443d59fbae8fea53732b Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 13 Apr 2018 23:54:52 +1000 Subject: mm/pkeys: Add an empty arch_pkeys_enabled() Add an empty arch_pkeys_enabled() in linux/pkeys.h for the CONFIG_ARCH_HAS_PKEYS=n case. Split out of a patch by Ram Pai . Signed-off-by: Michael Ellerman Reviewed-by: Dave Hansen --- include/linux/pkeys.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index 946cb773b79f..2955ba976048 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -39,6 +39,11 @@ static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, return 0; } +static inline bool arch_pkeys_enabled(void) +{ + return false; +} + static inline void copy_init_pkru_to_fpregs(void) { } -- cgit v1.2.3 From fa9b274f8aeffb97787b055b8cfbf9062e158551 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 26 Apr 2017 10:45:46 +0530 Subject: PM / OPP: Implement dev_pm_opp_of_add_table_indexed() The "operating-points-v2" property can contain a list of phandles now, specifically for the power domain providers that provide multiple domains. Add support to parse that. Signed-off-by: Viresh Kumar Reviewed-by: Ulf Hansson --- include/linux/pm_opp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 6c2d2e88f066..f042fdeaaa3c 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -303,6 +303,7 @@ static inline void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) int dev_pm_opp_of_add_table(struct device *dev); +int dev_pm_opp_of_add_table_indexed(struct device *dev, int index); void dev_pm_opp_of_remove_table(struct device *dev); int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask); void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask); @@ -314,6 +315,11 @@ static inline int dev_pm_opp_of_add_table(struct device *dev) return -ENOTSUPP; } +static inline int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) +{ + return -ENOTSUPP; +} + static inline void dev_pm_opp_of_remove_table(struct device *dev) { } -- cgit v1.2.3 From a88bd2a51e901ed8081841d647157de8153df813 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 29 Nov 2017 15:18:36 +0530 Subject: PM / OPP: Implement of_dev_pm_opp_find_required_opp() A device's DT node or its OPP nodes can contain a phandle to other device's OPP node, in the "required-opps" property. This patch implements a routine to find that required OPP from the node that contains the "required-opps" property. Signed-off-by: Viresh Kumar Reviewed-by: Ulf Hansson --- include/linux/pm_opp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index f042fdeaaa3c..70686f434c13 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -309,6 +309,7 @@ int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask); void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask); int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); +struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev, struct device_node *np); #else static inline int dev_pm_opp_of_add_table(struct device *dev) { @@ -342,6 +343,11 @@ static inline struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device { return NULL; } + +static inline struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev, struct device_node *np) +{ + return NULL; +} #endif #endif /* __LINUX_OPP_H__ */ -- cgit v1.2.3 From e2f4b5f8dc59c28605a320ea923905e519fd2ca7 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 12 Jan 2018 10:03:45 +0530 Subject: PM / OPP: Implement dev_pm_opp_get_of_node() This adds a new helper to let the power domain drivers to access opp->np, so that they can read platform specific properties from the node. Signed-off-by: Jordan Crouse Signed-off-by: Rajendra Nayak Signed-off-by: Viresh Kumar Reviewed-by: Ulf Hansson --- include/linux/pm_opp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 70686f434c13..8fd34c4398b2 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -310,6 +310,7 @@ void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask); int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev, struct device_node *np); +struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp); #else static inline int dev_pm_opp_of_add_table(struct device *dev) { @@ -348,6 +349,10 @@ static inline struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device * { return NULL; } +static inline struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp) +{ + return NULL; +} #endif #endif /* __LINUX_OPP_H__ */ -- cgit v1.2.3 From 401ea1572de944df548a13eded82339491a739ff Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 17 Mar 2017 11:26:19 +0530 Subject: PM / Domain: Add struct device to genpd The power-domain core would be using the OPP core going forward and the OPP core has the basic requirement of a device structure for its working. Add a struct device to the genpd structure. This doesn't register the device with device core as the "dev" pointer is mostly used by the OPP core as a cookie for now and registering the device is not mandatory. Signed-off-by: Viresh Kumar Acked-by: Ulf Hansson --- include/linux/pm_domain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 04dbef9847d3..aaacaa35005d 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -49,6 +49,7 @@ struct genpd_power_state { struct genpd_lock_ops; struct generic_pm_domain { + struct device dev; struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ struct list_head master_links; /* Links with PM domain as a master */ -- cgit v1.2.3 From 6e41766a6a504b605a105cc5ab8d276ea20052ba Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 29 Nov 2017 15:21:51 +0530 Subject: PM / Domain: Implement of_genpd_opp_to_performance_state() This implements of_genpd_opp_to_performance_state() which can be used from the device drivers or the OPP core to find the performance state encoded in the "required-opps" property of a node. Normally this would be called only once for each OPP of the device for which the OPP table of the device is getting generated. Different platforms may encode the performance state differently using the OPP table (they may simply return value of opp-hz or opp-microvolt, or apply some algorithm on top of those values) and so a new callback ->opp_to_performance_state() is implemented to allow platform specific drivers to convert the power domain OPP to a performance state value. Signed-off-by: Viresh Kumar Acked-by: Ulf Hansson --- include/linux/pm_domain.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index aaacaa35005d..a2fa297e96f7 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -47,6 +47,7 @@ struct genpd_power_state { }; struct genpd_lock_ops; +struct dev_pm_opp; struct generic_pm_domain { struct device dev; @@ -68,6 +69,8 @@ struct generic_pm_domain { unsigned int performance_state; /* Aggregated max performance state */ int (*power_off)(struct generic_pm_domain *domain); int (*power_on)(struct generic_pm_domain *domain); + unsigned int (*opp_to_performance_state)(struct generic_pm_domain *genpd, + struct dev_pm_opp *opp); int (*set_performance_state)(struct generic_pm_domain *genpd, unsigned int state); struct gpd_dev_ops dev_ops; @@ -244,6 +247,8 @@ extern int of_genpd_add_subdomain(struct of_phandle_args *parent, extern struct generic_pm_domain *of_genpd_remove_last(struct device_node *np); extern int of_genpd_parse_idle_states(struct device_node *dn, struct genpd_power_state **states, int *n); +extern unsigned int of_genpd_opp_to_performance_state(struct device *dev, + struct device_node *opp_node); int genpd_dev_pm_attach(struct device *dev); #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */ @@ -279,6 +284,13 @@ static inline int of_genpd_parse_idle_states(struct device_node *dn, return -ENODEV; } +static inline unsigned int +of_genpd_opp_to_performance_state(struct device *dev, + struct device_node *opp_node) +{ + return -ENODEV; +} + static inline int genpd_dev_pm_attach(struct device *dev) { return -ENODEV; -- cgit v1.2.3 From 28fa4aca262ce0865d27788ebc480e643117d7ab Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 22 Dec 2017 12:08:00 +0530 Subject: PM / OPP: Remove dev_pm_opp_{un}register_get_pstate_helper() These helpers aren't used anymore, remove them. Signed-off-by: Viresh Kumar Reviewed-by: Ulf Hansson --- include/linux/pm_opp.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 8fd34c4398b2..099b31960dec 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -125,8 +125,6 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name); void dev_pm_opp_put_clkname(struct opp_table *opp_table); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); -struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev, int (*get_pstate)(struct device *dev, unsigned long rate)); -void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); @@ -247,14 +245,6 @@ static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device static inline void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) {} -static inline struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev, - int (*get_pstate)(struct device *dev, unsigned long rate)) -{ - return ERR_PTR(-ENOTSUPP); -} - -static inline void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table) {} - static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) { return ERR_PTR(-ENOTSUPP); -- cgit v1.2.3 From 0d3fdb157fd0b96b06be7f1d8cea21dd2bc030da Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Apr 2018 15:34:58 +0200 Subject: iommu-common: move to arch/sparc This code is only used by sparc, and all new iommu drivers should use the drivers/iommu/ framework. Also remove the unused exports. Signed-off-by: Christoph Hellwig Acked-by: David S. Miller Reviewed-by: Anshuman Khandual --- include/linux/iommu-common.h | 53 -------------------------------------------- 1 file changed, 53 deletions(-) delete mode 100644 include/linux/iommu-common.h (limited to 'include/linux') diff --git a/include/linux/iommu-common.h b/include/linux/iommu-common.h deleted file mode 100644 index 802c90c79d1f..000000000000 --- a/include/linux/iommu-common.h +++ /dev/null @@ -1,53 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_IOMMU_COMMON_H -#define _LINUX_IOMMU_COMMON_H - -#include -#include -#include - -#define IOMMU_POOL_HASHBITS 4 -#define IOMMU_NR_POOLS (1 << IOMMU_POOL_HASHBITS) -#define IOMMU_ERROR_CODE (~(unsigned long) 0) - -struct iommu_pool { - unsigned long start; - unsigned long end; - unsigned long hint; - spinlock_t lock; -}; - -struct iommu_map_table { - unsigned long table_map_base; - unsigned long table_shift; - unsigned long nr_pools; - void (*lazy_flush)(struct iommu_map_table *); - unsigned long poolsize; - struct iommu_pool pools[IOMMU_NR_POOLS]; - u32 flags; -#define IOMMU_HAS_LARGE_POOL 0x00000001 -#define IOMMU_NO_SPAN_BOUND 0x00000002 -#define IOMMU_NEED_FLUSH 0x00000004 - struct iommu_pool large_pool; - unsigned long *map; -}; - -extern void iommu_tbl_pool_init(struct iommu_map_table *iommu, - unsigned long num_entries, - u32 table_shift, - void (*lazy_flush)(struct iommu_map_table *), - bool large_pool, u32 npools, - bool skip_span_boundary_check); - -extern unsigned long iommu_tbl_range_alloc(struct device *dev, - struct iommu_map_table *iommu, - unsigned long npages, - unsigned long *handle, - unsigned long mask, - unsigned int align_order); - -extern void iommu_tbl_range_free(struct iommu_map_table *iommu, - u64 dma_addr, unsigned long npages, - unsigned long entry); - -#endif -- cgit v1.2.3 From 79c1879ee5473e3404469b07f9bccfe6d0814b93 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Apr 2018 15:41:07 +0200 Subject: iommu-helper: mark iommu_is_span_boundary as inline This avoids selecting IOMMU_HELPER just for this function. And we only use it once or twice in normal builds so this often even is a size reduction. Signed-off-by: Christoph Hellwig --- include/linux/iommu-helper.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h index cb9a9248c8c0..70d01edcbf8b 100644 --- a/include/linux/iommu-helper.h +++ b/include/linux/iommu-helper.h @@ -2,6 +2,7 @@ #ifndef _LINUX_IOMMU_HELPER_H #define _LINUX_IOMMU_HELPER_H +#include #include static inline unsigned long iommu_device_max_index(unsigned long size, @@ -14,9 +15,15 @@ static inline unsigned long iommu_device_max_index(unsigned long size, return size; } -extern int iommu_is_span_boundary(unsigned int index, unsigned int nr, - unsigned long shift, - unsigned long boundary_size); +static inline int iommu_is_span_boundary(unsigned int index, unsigned int nr, + unsigned long shift, unsigned long boundary_size) +{ + BUG_ON(!is_power_of_2(boundary_size)); + + shift = (shift + index) & (boundary_size - 1); + return shift + nr > boundary_size; +} + extern unsigned long iommu_area_alloc(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long shift, -- cgit v1.2.3 From f616ab59c294b6ea6efa94f6139ea3eda2f52be0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 9 May 2018 06:53:49 +0200 Subject: dma-mapping: move the NEED_DMA_MAP_STATE config symbol to lib/Kconfig This way we have one central definition of it, and user can select it as needed. Note that we now also always select it when CONFIG_DMA_API_DEBUG is select, which fixes some incorrect checks in a few network drivers. Signed-off-by: Christoph Hellwig Reviewed-by: Anshuman Khandual --- include/linux/dma-mapping.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index a6d4ac8b81e4..25a9a2b04f78 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -838,7 +838,7 @@ static inline int dma_mmap_wc(struct device *dev, #define dma_mmap_writecombine dma_mmap_wc #endif -#if defined(CONFIG_NEED_DMA_MAP_STATE) || defined(CONFIG_DMA_API_DEBUG) +#ifdef CONFIG_NEED_DMA_MAP_STATE #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME #define DEFINE_DMA_UNMAP_LEN(LEN_NAME) __u32 LEN_NAME #define dma_unmap_addr(PTR, ADDR_NAME) ((PTR)->ADDR_NAME) -- cgit v1.2.3 From 8e6390795eacf87f717bc755f352f0aa85da5700 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Apr 2018 16:40:54 +0200 Subject: PCI: remove CONFIG_PCI_BUS_ADDR_T_64BIT This symbol is now always identical to CONFIG_ARCH_DMA_ADDR_T_64BIT, so remove it. Signed-off-by: Christoph Hellwig Acked-by: Bjorn Helgaas --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 73178a2fcee0..55371cb827ad 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -670,7 +670,7 @@ int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 val); -#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT typedef u64 pci_bus_addr_t; #else typedef u32 pci_bus_addr_t; -- cgit v1.2.3 From 9c4a121e82634aa000a702c98cd6f05b27d6e186 Mon Sep 17 00:00:00 2001 From: Sean Lanigan Date: Fri, 4 May 2018 16:48:23 +1000 Subject: brcmfmac: Add support for bcm43364 wireless chipset Add support for the BCM43364 chipset via an SDIO interface, as used in e.g. the Murata 1FX module. The BCM43364 uses the same firmware as the BCM43430 (which is already included), the only difference is the omission of Bluetooth. However, the SDIO_ID for the BCM43364 is 02D0:A9A4, giving it a MODALIAS of sdio:c00v02D0dA9A4, which doesn't get recognised and hence doesn't load the brcmfmac module. Adding the 'A9A4' ID in the appropriate place triggers the brcmfmac driver to load, and then correctly use the firmware file 'brcmfmac43430-sdio.bin'. Signed-off-by: Sean Lanigan Acked-by: Ulf Hansson Signed-off-by: Kalle Valo --- include/linux/mmc/sdio_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index cdd66a5fbd5e..0a7abe8a407f 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -35,6 +35,7 @@ #define SDIO_DEVICE_ID_BROADCOM_4335_4339 0x4335 #define SDIO_DEVICE_ID_BROADCOM_4339 0x4339 #define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 +#define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4 #define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 #define SDIO_DEVICE_ID_BROADCOM_4345 0x4345 #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf -- cgit v1.2.3 From a676688032e819c4bb1999a422553a1a1f52ce45 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 7 May 2018 06:35:52 -0300 Subject: mtd: rawnand.h: use nested union kernel-doc markups Gets rid of those warnings and better document the parameters. ./include/linux/mtd/rawnand.h:752: warning: Function parameter or member 'timings.sdr' not described in 'nand_data_interface' ./include/linux/mtd/rawnand.h:817: warning: Function parameter or member 'buf' not described in 'nand_op_data_instr' ./include/linux/mtd/rawnand.h:817: warning: Function parameter or member 'buf.in' not described in 'nand_op_data_instr' ./include/linux/mtd/rawnand.h:817: warning: Function parameter or member 'buf.out' not described in 'nand_op_data_instr' ./include/linux/mtd/rawnand.h:863: warning: Function parameter or member 'ctx' not described in 'nand_op_instr' ./include/linux/mtd/rawnand.h:863: warning: Function parameter or member 'ctx.cmd' not described in 'nand_op_instr' ./include/linux/mtd/rawnand.h:863: warning: Function parameter or member 'ctx.addr' not described in 'nand_op_instr' ./include/linux/mtd/rawnand.h:863: warning: Function parameter or member 'ctx.data' not described in 'nand_op_instr' ./include/linux/mtd/rawnand.h:863: warning: Function parameter or member 'ctx.waitrdy' not described in 'nand_op_instr' ./include/linux/mtd/rawnand.h:1010: warning: Function parameter or member 'ctx' not described in 'nand_op_parser_pattern_elem' ./include/linux/mtd/rawnand.h:1010: warning: Function parameter or member 'ctx.addr' not described in 'nand_op_parser_pattern_elem' ./include/linux/mtd/rawnand.h:1010: warning: Function parameter or member 'ctx.data' not described in 'nand_op_parser_pattern_elem' ./include/linux/mtd/rawnand.h:1313: warning: Function parameter or member 'manufacturer.desc' not described in 'nand_chip' ./include/linux/mtd/rawnand.h:1313: warning: Function parameter or member 'manufacturer.priv' not described in 'nand_chip' ./include/linux/mtd/rawnand.h:848: WARNING: Unexpected indentation. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Boris Brezillon --- include/linux/mtd/rawnand.h | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index ba8d908f5cc7..a206172ec23b 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -747,8 +747,9 @@ enum nand_data_interface_type { /** * struct nand_data_interface - NAND interface timing - * @type: type of the timing - * @timings: The timing, type according to @type + * @type: type of the timing + * @timings: The timing, type according to @type + * @timings.sdr: Use it when @type is %NAND_SDR_IFACE. */ struct nand_data_interface { enum nand_data_interface_type type; @@ -805,8 +806,9 @@ struct nand_op_addr_instr { /** * struct nand_op_data_instr - Definition of a data instruction * @len: number of data bytes to move - * @in: buffer to fill when reading from the NAND chip - * @out: buffer to read from when writing to the NAND chip + * @buf: buffer to fill + * @buf.in: buffer to fill when reading from the NAND chip + * @buf.out: buffer to read from when writing to the NAND chip * @force_8bit: force 8-bit access * * Please note that "in" and "out" are inverted from the ONFI specification @@ -849,9 +851,13 @@ enum nand_op_instr_type { /** * struct nand_op_instr - Instruction object * @type: the instruction type - * @cmd/@addr/@data/@waitrdy: extra data associated to the instruction. - * You'll have to use the appropriate element - * depending on @type + * @ctx: extra data associated to the instruction. You'll have to use the + * appropriate element depending on @type + * @ctx.cmd: use it if @type is %NAND_OP_CMD_INSTR + * @ctx.addr: use it if @type is %NAND_OP_ADDR_INSTR + * @ctx.data: use it if @type is %NAND_OP_DATA_IN_INSTR + * or %NAND_OP_DATA_OUT_INSTR + * @ctx.waitrdy: use it if @type is %NAND_OP_WAITRDY_INSTR * @delay_ns: delay the controller should apply after the instruction has been * issued on the bus. Most modern controllers have internal timings * control logic, and in this case, the controller driver can ignore @@ -1004,7 +1010,9 @@ struct nand_op_parser_data_constraints { * struct nand_op_parser_pattern_elem - One element of a pattern * @type: the instructuction type * @optional: whether this element of the pattern is optional or mandatory - * @addr/@data: address or data constraint (number of cycles or data length) + * @ctx: address or data constraint + * @ctx.addr: address constraint (number of cycles) + * @ctx.data: data constraint (data length) */ struct nand_op_parser_pattern_elem { enum nand_op_instr_type type; @@ -1231,6 +1239,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * devices. * @priv: [OPTIONAL] pointer to private chip data * @manufacturer: [INTERN] Contains manufacturer information + * @manufacturer.desc: [INTERN] Contains manufacturer's description + * @manufacturer.priv: [INTERN] Contains manufacturer private information */ struct nand_chip { -- cgit v1.2.3 From 5238dcf4136fd7287be8e7d38752645bfa5782ec Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Wed, 9 May 2018 02:08:49 -0700 Subject: block: replace bio->bi_issue_stat with bio-specific type struct blk_issue_stat is going away, and bio->bi_issue_stat doesn't even use the blk-stats interface, so we can provide a separate implementation specific for bios. The helpers work the same way as the blk-stats helpers. Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 48 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 17b18b91ebac..b6f1d53cf113 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -8,6 +8,7 @@ #include #include +#include struct bio_set; struct bio; @@ -94,6 +95,52 @@ struct blk_issue_stat { u64 stat; }; +/* + * From most significant bit: + * 1 bit: reserved for other usage, see below + * 12 bits: original size of bio + * 51 bits: issue time of bio + */ +#define BIO_ISSUE_RES_BITS 1 +#define BIO_ISSUE_SIZE_BITS 12 +#define BIO_ISSUE_RES_SHIFT (64 - BIO_ISSUE_RES_BITS) +#define BIO_ISSUE_SIZE_SHIFT (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS) +#define BIO_ISSUE_TIME_MASK ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1) +#define BIO_ISSUE_SIZE_MASK \ + (((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT) +#define BIO_ISSUE_RES_MASK (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1)) + +/* Reserved bit for blk-throtl */ +#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63) + +struct bio_issue { + u64 value; +}; + +static inline u64 __bio_issue_time(u64 time) +{ + return time & BIO_ISSUE_TIME_MASK; +} + +static inline u64 bio_issue_time(struct bio_issue *issue) +{ + return __bio_issue_time(issue->value); +} + +static inline sector_t bio_issue_size(struct bio_issue *issue) +{ + return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT); +} + +static inline void bio_issue_init(struct bio_issue *issue, + sector_t size) +{ + size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1; + issue->value = ((issue->value & BIO_ISSUE_RES_MASK) | + (ktime_get_ns() & BIO_ISSUE_TIME_MASK) | + ((u64)size << BIO_ISSUE_SIZE_SHIFT)); +} + /* * main unit of I/O for the block layer and lower layers (ie drivers and * stacking drivers) @@ -138,7 +185,7 @@ struct bio { struct cgroup_subsys_state *bi_css; #ifdef CONFIG_BLK_DEV_THROTTLING_LOW void *bi_cg_private; - struct blk_issue_stat bi_issue_stat; + struct bio_issue bi_issue; #endif #endif union { -- cgit v1.2.3 From 544ccc8dc904db55d4576c27a1eb66a888ffacea Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Wed, 9 May 2018 02:08:50 -0700 Subject: block: get rid of struct blk_issue_stat struct blk_issue_stat squashes three things into one u64: - The time the driver started working on a request - The original size of the request (for the io.low controller) - Flags for writeback throttling It turns out that on x86_64, we have a 4 byte hole in struct request which we can fill with the non-timestamp fields from blk_issue_stat, simplifying things quite a bit. Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 4 ---- include/linux/blkdev.h | 26 ++++++++++++++++++-------- 2 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index b6f1d53cf113..4cb970cdcd11 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -91,10 +91,6 @@ static inline bool blk_path_error(blk_status_t error) return true; } -struct blk_issue_stat { - u64 stat; -}; - /* * From most significant bit: * 1 bit: reserved for other usage, see below diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c4eee043191..f2c2fc011e6b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -206,8 +206,18 @@ struct request { struct gendisk *rq_disk; struct hd_struct *part; unsigned long start_time; - struct blk_issue_stat issue_stat; - /* Number of scatter-gather DMA addr+len pairs after + /* Time that I/O was submitted to the device. */ + u64 io_start_time_ns; + +#ifdef CONFIG_BLK_WBT + unsigned short wbt_flags; +#endif +#ifdef CONFIG_BLK_DEV_THROTTLING_LOW + unsigned short throtl_size; +#endif + + /* + * Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ unsigned short nr_phys_segments; @@ -267,8 +277,8 @@ struct request { #ifdef CONFIG_BLK_CGROUP struct request_list *rl; /* rl this rq is alloced from */ - unsigned long long start_time_ns; - unsigned long long io_start_time_ns; /* when passed to hardware */ + unsigned long long cgroup_start_time_ns; + unsigned long long cgroup_io_start_time_ns; /* when passed to hardware */ #endif }; @@ -1797,25 +1807,25 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo static inline void set_start_time_ns(struct request *req) { preempt_disable(); - req->start_time_ns = sched_clock(); + req->cgroup_start_time_ns = sched_clock(); preempt_enable(); } static inline void set_io_start_time_ns(struct request *req) { preempt_disable(); - req->io_start_time_ns = sched_clock(); + req->cgroup_io_start_time_ns = sched_clock(); preempt_enable(); } static inline uint64_t rq_start_time_ns(struct request *req) { - return req->start_time_ns; + return req->cgroup_start_time_ns; } static inline uint64_t rq_io_start_time_ns(struct request *req) { - return req->io_start_time_ns; + return req->cgroup_io_start_time_ns; } #else static inline void set_start_time_ns(struct request *req) {} -- cgit v1.2.3 From 84c7afcebed913c93d50f116b046b7f0d8ec0cdc Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Wed, 9 May 2018 02:08:51 -0700 Subject: block: use ktime_get_ns() instead of sched_clock() for cfq and bfq cfq and bfq have some internal fields that use sched_clock() which can trivially use ktime_get_ns() instead. Their timestamp fields in struct request can also use ktime_get_ns(), which resolves the 8 year old comment added by commit 28f4197e5d47 ("block: disable preemption before using sched_clock()"). Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 21 ++++++--------------- 1 file changed, 6 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f2c2fc011e6b..9ef412666df1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1799,42 +1799,33 @@ int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #ifdef CONFIG_BLK_CGROUP -/* - * This should not be using sched_clock(). A real patch is in progress - * to fix this up, until that is in place we need to disable preemption - * around sched_clock() in this function and set_io_start_time_ns(). - */ static inline void set_start_time_ns(struct request *req) { - preempt_disable(); - req->cgroup_start_time_ns = sched_clock(); - preempt_enable(); + req->cgroup_start_time_ns = ktime_get_ns(); } static inline void set_io_start_time_ns(struct request *req) { - preempt_disable(); - req->cgroup_io_start_time_ns = sched_clock(); - preempt_enable(); + req->cgroup_io_start_time_ns = ktime_get_ns(); } -static inline uint64_t rq_start_time_ns(struct request *req) +static inline u64 rq_start_time_ns(struct request *req) { return req->cgroup_start_time_ns; } -static inline uint64_t rq_io_start_time_ns(struct request *req) +static inline u64 rq_io_start_time_ns(struct request *req) { return req->cgroup_io_start_time_ns; } #else static inline void set_start_time_ns(struct request *req) {} static inline void set_io_start_time_ns(struct request *req) {} -static inline uint64_t rq_start_time_ns(struct request *req) +static inline u64 rq_start_time_ns(struct request *req) { return 0; } -static inline uint64_t rq_io_start_time_ns(struct request *req) +static inline u64 rq_io_start_time_ns(struct request *req) { return 0; } -- cgit v1.2.3 From 522a777566f5669606a1227bf13f3fb40963780b Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Wed, 9 May 2018 02:08:53 -0700 Subject: block: consolidate struct request timestamp fields Currently, struct request has four timestamp fields: - A start time, set at get_request time, in jiffies, used for iostats - An I/O start time, set at start_request time, in ktime nanoseconds, used for blk-stats (i.e., wbt, kyber, hybrid polling) - Another start time and another I/O start time, used for cfq and bfq These can all be consolidated into one start time and one I/O start time, both in ktime nanoseconds, shaving off up to 16 bytes from struct request depending on the kernel config. Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 38 ++------------------------------------ 1 file changed, 2 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9ef412666df1..e42d510daf3c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -205,7 +205,8 @@ struct request { struct gendisk *rq_disk; struct hd_struct *part; - unsigned long start_time; + /* Time that I/O was submitted to the kernel. */ + u64 start_time_ns; /* Time that I/O was submitted to the device. */ u64 io_start_time_ns; @@ -277,8 +278,6 @@ struct request { #ifdef CONFIG_BLK_CGROUP struct request_list *rl; /* rl this rq is alloced from */ - unsigned long long cgroup_start_time_ns; - unsigned long long cgroup_io_start_time_ns; /* when passed to hardware */ #endif }; @@ -1798,39 +1797,6 @@ int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); -#ifdef CONFIG_BLK_CGROUP -static inline void set_start_time_ns(struct request *req) -{ - req->cgroup_start_time_ns = ktime_get_ns(); -} - -static inline void set_io_start_time_ns(struct request *req) -{ - req->cgroup_io_start_time_ns = ktime_get_ns(); -} - -static inline u64 rq_start_time_ns(struct request *req) -{ - return req->cgroup_start_time_ns; -} - -static inline u64 rq_io_start_time_ns(struct request *req) -{ - return req->cgroup_io_start_time_ns; -} -#else -static inline void set_start_time_ns(struct request *req) {} -static inline void set_io_start_time_ns(struct request *req) {} -static inline u64 rq_start_time_ns(struct request *req) -{ - return 0; -} -static inline u64 rq_io_start_time_ns(struct request *req) -{ - return 0; -} -#endif - #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ -- cgit v1.2.3 From 78958fca7ead2f81b60a6827881c4866d1ed0c52 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 4 May 2018 14:49:51 -0700 Subject: bpf: btf: Introduce BTF ID This patch gives an ID to each loaded BTF. The ID is allocated by the idr like the existing prog-id and map-id. The bpf_put(map->btf) is moved to __bpf_map_put() so that the userspace can stop seeing the BTF ID ASAP when the last BTF refcnt is gone. It also makes BTF accessible from userspace through the 1. new BPF_BTF_GET_FD_BY_ID command. It is limited to CAP_SYS_ADMIN which is inline with the BPF_BTF_LOAD cmd and the existing BPF_[MAP|PROG]_GET_FD_BY_ID cmd. 2. new btf_id (and btf_key_id + btf_value_id) in "struct bpf_map_info" Once the BTF ID handler is accessible from userspace, freeing a BTF object has to go through a rcu period. The BPF_BTF_GET_FD_BY_ID cmd can then be done under a rcu_read_lock() instead of taking spin_lock. [Note: A similar rcu usage can be done to the existing bpf_prog_get_fd_by_id() in a follow up patch] When processing the BPF_BTF_GET_FD_BY_ID cmd, refcount_inc_not_zero() is needed because the BTF object could be already in the rcu dead row . btf_get() is removed since its usage is currently limited to btf.c alone. refcount_inc() is used directly instead. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/btf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index a966dc6d61ee..e076c4697049 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -44,5 +44,7 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, u32 *ret_size); void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m); +int btf_get_fd_by_id(u32 id); +u32 btf_id(const struct btf *btf); #endif -- cgit v1.2.3 From 0d8300325660f81787892a1c58dc1f9428a67143 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 8 May 2018 19:37:06 -0700 Subject: bpf: xdp: allow offloads to store into rx_queue_index It's fairly easy for offloaded XDP programs to select the RX queue packets go to. We need a way of expressing this in the software. Allow write to the rx_queue_index field of struct xdp_md for device-bound programs. Skip convert_ctx_access callback entirely for offloads. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 321969da67b7..a38e474bf7ee 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -627,7 +627,7 @@ bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); -static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) +static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) { return aux->offload_requested; } -- cgit v1.2.3 From 1baf47c2e5c946fd17ef07597b9d25722d13ff14 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 9 May 2018 17:52:06 +0100 Subject: firmware: arm_scmi: fix kernel-docs documentation There are few missing descriptions for function parameters and structure members along with certain instances where excessive function parameters or structure members are described. This patch fixes all of those warnings. Reported-by: Jonathan Cameron Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index b458c87b866c..a171c1e293e8 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -189,6 +189,14 @@ struct scmi_sensor_ops { * @perf_ops: pointer to set of performance protocol operations * @clk_ops: pointer to set of clock protocol operations * @sensor_ops: pointer to set of sensor protocol operations + * @perf_priv: pointer to private data structure specific to performance + * protocol(for internal use only) + * @clk_priv: pointer to private data structure specific to clock + * protocol(for internal use only) + * @power_priv: pointer to private data structure specific to power + * protocol(for internal use only) + * @sensor_priv: pointer to private data structure specific to sensors + * protocol(for internal use only) */ struct scmi_handle { struct device *dev; -- cgit v1.2.3 From 163475ebf9f3d1b516c1f8ee4f59eb8ff8e97ee8 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 18 Apr 2018 13:01:21 -0500 Subject: ipmi: Remove the proc interface It has been deprecated long enough, get rid of it. Signed-off-by: Corey Minyard --- include/linux/ipmi_smi.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 0d438662a821..7d5fd38d5282 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -240,15 +240,4 @@ static inline void ipmi_free_smi_msg(struct ipmi_smi_msg *msg) msg->done(msg); } -#ifdef CONFIG_IPMI_PROC_INTERFACE -/* - * Allow the lower layer to add things to the proc filesystem - * directory for this interface. Note that the entry will - * automatically be dstroyed when the interface is destroyed. - */ -int ipmi_smi_add_proc_entry(struct ipmi_smi *smi, char *name, - const struct file_operations *proc_ops, - void *data); -#endif - #endif /* __LINUX_IPMI_SMI_H */ -- cgit v1.2.3 From 826950868cd81268913a91b69f00fb6c3f0b6f5b Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Fri, 27 Apr 2018 14:16:38 +0200 Subject: remoteproc/ste: remove abandoned include file STE modem driver has been removed in 2016. This include has no users since then. Signed-off-by: Andrzej Hajda Cc: Jean Delvare Cc: Linus Walleij Cc: Ohad Ben-Cohen Cc: Bjorn Andersson Cc: Suman Anna Acked-by: Jean Delvare Acked-by: Linus Walleij Signed-off-by: Bjorn Andersson --- include/linux/ste_modem_shm.h | 56 ------------------------------------------- 1 file changed, 56 deletions(-) delete mode 100644 include/linux/ste_modem_shm.h (limited to 'include/linux') diff --git a/include/linux/ste_modem_shm.h b/include/linux/ste_modem_shm.h deleted file mode 100644 index 8444a4eff1bb..000000000000 --- a/include/linux/ste_modem_shm.h +++ /dev/null @@ -1,56 +0,0 @@ -/* - * Copyright (C) ST-Ericsson AB 2012 - * Author: Sjur Brendeland / sjur.brandeland@stericsson.com - * - * License terms: GNU General Public License (GPL) version 2 - */ - -#ifndef __INC_MODEM_DEV_H -#define __INC_MODEM_DEV_H -#include -#include - -struct ste_modem_device; - -/** - * struct ste_modem_dev_cb - Callbacks for modem initiated events. - * @kick: Called when the modem kicks the host. - * - * This structure contains callbacks for actions triggered by the modem. - */ -struct ste_modem_dev_cb { - void (*kick)(struct ste_modem_device *mdev, int notify_id); -}; - -/** - * struct ste_modem_dev_ops - Functions to control modem and modem interface. - * - * @power: Main power switch, used for cold-start or complete power off. - * @kick: Kick the modem. - * @kick_subscribe: Subscribe for notifications from the modem. - * @setup: Provide callback functions to modem device. - * - * This structure contains functions used by the ste remoteproc driver - * to manage the modem. - */ -struct ste_modem_dev_ops { - int (*power)(struct ste_modem_device *mdev, bool on); - int (*kick)(struct ste_modem_device *mdev, int notify_id); - int (*kick_subscribe)(struct ste_modem_device *mdev, int notify_id); - int (*setup)(struct ste_modem_device *mdev, - struct ste_modem_dev_cb *cfg); -}; - -/** - * struct ste_modem_device - represent the STE modem device - * @pdev: Reference to platform device - * @ops: Operations used to manage the modem. - * @drv_data: Driver private data. - */ -struct ste_modem_device { - struct platform_device pdev; - struct ste_modem_dev_ops ops; - void *drv_data; -}; - -#endif /*INC_MODEM_DEV_H*/ -- cgit v1.2.3 From 7859e08c1bdef00841d29e8ff320264fd6f9257b Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 9 May 2018 17:52:06 +0100 Subject: firmware: arm_scmi: rename get_transition_latency and add_opps_to_device Most of the scmi code follows the suggestion from Greg KH on a totally different thread[0] to have the subsystem name first, followed by the noun and finally the verb with couple of these exceptions. This patch fixes them so that all the functions names are aligned to that practice. [0] https://www.spinics.net/lists/arm-kernel/msg583673.html Acked-by: Rafael J. Wysocki Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index a171c1e293e8..f4c9fc0fc755 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -85,8 +85,8 @@ struct scmi_clk_ops { * @level_set: sets the performance level of a domain * @level_get: gets the performance level of a domain * @device_domain_id: gets the scmi domain id for a given device - * @get_transition_latency: gets the DVFS transition latency for a given device - * @add_opps_to_device: adds all the OPPs for a given device + * @transition_latency_get: gets the DVFS transition latency for a given device + * @device_opps_add: adds all the OPPs for a given device * @freq_set: sets the frequency for a given device using sustained frequency * to sustained performance level mapping * @freq_get: gets the frequency for a given device using sustained frequency @@ -102,10 +102,10 @@ struct scmi_perf_ops { int (*level_get)(const struct scmi_handle *handle, u32 domain, u32 *level, bool poll); int (*device_domain_id)(struct device *dev); - int (*get_transition_latency)(const struct scmi_handle *handle, + int (*transition_latency_get)(const struct scmi_handle *handle, struct device *dev); - int (*add_opps_to_device)(const struct scmi_handle *handle, - struct device *dev); + int (*device_opps_add)(const struct scmi_handle *handle, + struct device *dev); int (*freq_set)(const struct scmi_handle *handle, u32 domain, unsigned long rate, bool poll); int (*freq_get)(const struct scmi_handle *handle, u32 domain, -- cgit v1.2.3 From a327553965dede92587e6ccbe7df98dba36edcea Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Wed, 9 May 2018 17:16:31 -0700 Subject: sbitmap: fix missed wakeups caused by sbitmap_queue_get_shallow() The sbitmap queue wake batch is calculated such that once allocations start blocking, all of the bits which are already allocated must be enough to fulfill the batch counters of all of the waitqueues. However, the shallow allocation depth can break this invariant, since we block before our full depth is being utilized. Add sbitmap_queue_min_shallow_depth(), which saves the minimum shallow depth the sbq will use, and update sbq_calc_wake_batch() to take it into account. Acked-by: Paolo Valente Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 841585f6e5f2..0c4a9c242dd7 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -127,6 +127,12 @@ struct sbitmap_queue { * @round_robin: Allocate bits in strict round-robin order. */ bool round_robin; + + /** + * @min_shallow_depth: The minimum shallow depth which may be passed to + * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow(). + */ + unsigned int min_shallow_depth; }; /** @@ -390,6 +396,9 @@ int __sbitmap_queue_get(struct sbitmap_queue *sbq); * @shallow_depth: The maximum number of bits to allocate from a single word. * See sbitmap_get_shallow(). * + * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after + * initializing @sbq. + * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, @@ -424,6 +433,9 @@ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq, * @shallow_depth: The maximum number of bits to allocate from a single word. * See sbitmap_get_shallow(). * + * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after + * initializing @sbq. + * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, @@ -438,6 +450,23 @@ static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, return nr; } +/** + * sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the + * minimum shallow depth that will be used. + * @sbq: Bitmap queue in question. + * @min_shallow_depth: The minimum shallow depth that will be passed to + * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow(). + * + * sbitmap_queue_clear() batches wakeups as an optimization. The batch size + * depends on the depth of the bitmap. Since the shallow allocation functions + * effectively operate with a different depth, the shallow depth must be taken + * into account when calculating the batch size. This function must be called + * with the minimum shallow depth that will be used. Failure to do so can result + * in missed wakeups. + */ +void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq, + unsigned int min_shallow_depth); + /** * sbitmap_queue_clear() - Free an allocated bit and wake up waiters on a * &struct sbitmap_queue. -- cgit v1.2.3 From e5c9a705452acf59efe00cb84f086624fda010ab Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Wed, 9 May 2018 18:29:02 +0300 Subject: net/mlx4_core: Report driver version to FW If supported, write a driver version string to FW as part of the INIT_HCA command. Example of driver version: "Linux,mlx4_core,4.0-0" Signed-off-by: Eran Ben Elisha Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 81d0799b6091..122e7e9d3091 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -225,6 +225,7 @@ enum { MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP = 1ULL << 36, MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT = 1ULL << 37, MLX4_DEV_CAP_FLAG2_USER_MAC_EN = 1ULL << 38, + MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW = 1ULL << 39, }; enum { -- cgit v1.2.3 From cef74409ea79b0a37af6889e7abf7a2a9c47979b Mon Sep 17 00:00:00 2001 From: Gil Kupfer Date: Thu, 10 May 2018 17:56:02 -0500 Subject: PCI: Add "pci=noats" boot parameter Adds a "pci=noats" boot parameter. When supplied, all ATS related functions fail immediately and the IOMMU is configured to not use device-IOTLB. Any function that checks for ATS capabilities directly against the devices should also check this flag. Currently, such functions exist only in IOMMU drivers, and they are covered by this patch. The motivation behind this patch is the existence of malicious devices. Lots of research has been done about how to use the IOMMU as protection from such devices. When ATS is supported, any I/O device can access any physical address by faking device-IOTLB entries. Adding the ability to ignore these entries lets sysadmins enhance system security. Signed-off-by: Gil Kupfer Signed-off-by: Bjorn Helgaas Acked-by: Joerg Roedel --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 911f9098a466..aa9c27e129d4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1479,6 +1479,8 @@ static inline void pcie_set_ecrc_checking(struct pci_dev *dev) { } static inline void pcie_ecrc_get_policy(char *str) { } #endif +bool pci_ats_disabled(void); + #ifdef CONFIG_PCI_ATS /* Address Translation Service */ void pci_ats_init(struct pci_dev *dev); -- cgit v1.2.3 From c36ff266dc82f4ae797a6f3513c6ffa344f7f1c7 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 26 Apr 2018 18:18:14 +0200 Subject: spi: Extend the core to ease integration of SPI memory controllers Some controllers are exposing high-level interfaces to access various kind of SPI memories. Unfortunately they do not fit in the current spi_controller model and usually have drivers placed in drivers/mtd/spi-nor which are only supporting SPI NORs and not SPI memories in general. This is an attempt at defining a SPI memory interface which works for all kinds of SPI memories (NORs, NANDs, SRAMs). Signed-off-by: Boris Brezillon Reviewed-by: Frieder Schrempf Tested-by: Frieder Schrempf Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 249 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/spi/spi.h | 7 ++ 2 files changed, 256 insertions(+) create mode 100644 include/linux/spi/spi-mem.h (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h new file mode 100644 index 000000000000..bb4bd15ae1f6 --- /dev/null +++ b/include/linux/spi/spi-mem.h @@ -0,0 +1,249 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2018 Exceet Electronics GmbH + * Copyright (C) 2018 Bootlin + * + * Author: Boris Brezillon + */ + +#ifndef __LINUX_SPI_MEM_H +#define __LINUX_SPI_MEM_H + +#include + +#define SPI_MEM_OP_CMD(__opcode, __buswidth) \ + { \ + .buswidth = __buswidth, \ + .opcode = __opcode, \ + } + +#define SPI_MEM_OP_ADDR(__nbytes, __val, __buswidth) \ + { \ + .nbytes = __nbytes, \ + .val = __val, \ + .buswidth = __buswidth, \ + } + +#define SPI_MEM_OP_NO_ADDR { } + +#define SPI_MEM_OP_DUMMY(__nbytes, __buswidth) \ + { \ + .nbytes = __nbytes, \ + .buswidth = __buswidth, \ + } + +#define SPI_MEM_OP_NO_DUMMY { } + +#define SPI_MEM_OP_DATA_IN(__nbytes, __buf, __buswidth) \ + { \ + .dir = SPI_MEM_DATA_IN, \ + .nbytes = __nbytes, \ + .buf.in = __buf, \ + .buswidth = __buswidth, \ + } + +#define SPI_MEM_OP_DATA_OUT(__nbytes, __buf, __buswidth) \ + { \ + .dir = SPI_MEM_DATA_OUT, \ + .nbytes = __nbytes, \ + .buf.out = __buf, \ + .buswidth = __buswidth, \ + } + +#define SPI_MEM_OP_NO_DATA { } + +/** + * enum spi_mem_data_dir - describes the direction of a SPI memory data + * transfer from the controller perspective + * @SPI_MEM_DATA_IN: data coming from the SPI memory + * @SPI_MEM_DATA_OUT: data sent the SPI memory + */ +enum spi_mem_data_dir { + SPI_MEM_DATA_IN, + SPI_MEM_DATA_OUT, +}; + +/** + * struct spi_mem_op - describes a SPI memory operation + * @cmd.buswidth: number of IO lines used to transmit the command + * @cmd.opcode: operation opcode + * @addr.nbytes: number of address bytes to send. Can be zero if the operation + * does not need to send an address + * @addr.buswidth: number of IO lines used to transmit the address cycles + * @addr.val: address value. This value is always sent MSB first on the bus. + * Note that only @addr.nbytes are taken into account in this + * address value, so users should make sure the value fits in the + * assigned number of bytes. + * @dummy.nbytes: number of dummy bytes to send after an opcode or address. Can + * be zero if the operation does not require dummy bytes + * @dummy.buswidth: number of IO lanes used to transmit the dummy bytes + * @data.buswidth: number of IO lanes used to send/receive the data + * @data.dir: direction of the transfer + * @data.buf.in: input buffer + * @data.buf.out: output buffer + */ +struct spi_mem_op { + struct { + u8 buswidth; + u8 opcode; + } cmd; + + struct { + u8 nbytes; + u8 buswidth; + u64 val; + } addr; + + struct { + u8 nbytes; + u8 buswidth; + } dummy; + + struct { + u8 buswidth; + enum spi_mem_data_dir dir; + unsigned int nbytes; + /* buf.{in,out} must be DMA-able. */ + union { + void *in; + const void *out; + } buf; + } data; +}; + +#define SPI_MEM_OP(__cmd, __addr, __dummy, __data) \ + { \ + .cmd = __cmd, \ + .addr = __addr, \ + .dummy = __dummy, \ + .data = __data, \ + } + +/** + * struct spi_mem - describes a SPI memory device + * @spi: the underlying SPI device + * @drvpriv: spi_mem_drviver private data + * + * Extra information that describe the SPI memory device and may be needed by + * the controller to properly handle this device should be placed here. + * + * One example would be the device size since some controller expose their SPI + * mem devices through a io-mapped region. + */ +struct spi_mem { + struct spi_device *spi; + void *drvpriv; +}; + +/** + * struct spi_mem_set_drvdata() - attach driver private data to a SPI mem + * device + * @mem: memory device + * @data: data to attach to the memory device + */ +static inline void spi_mem_set_drvdata(struct spi_mem *mem, void *data) +{ + mem->drvpriv = data; +} + +/** + * struct spi_mem_get_drvdata() - get driver private data attached to a SPI mem + * device + * @mem: memory device + * + * Return: the data attached to the mem device. + */ +static inline void *spi_mem_get_drvdata(struct spi_mem *mem) +{ + return mem->drvpriv; +} + +/** + * struct spi_controller_mem_ops - SPI memory operations + * @adjust_op_size: shrink the data xfer of an operation to match controller's + * limitations (can be alignment of max RX/TX size + * limitations) + * @supports_op: check if an operation is supported by the controller + * @exec_op: execute a SPI memory operation + * + * This interface should be implemented by SPI controllers providing an + * high-level interface to execute SPI memory operation, which is usually the + * case for QSPI controllers. + */ +struct spi_controller_mem_ops { + int (*adjust_op_size)(struct spi_mem *mem, struct spi_mem_op *op); + bool (*supports_op)(struct spi_mem *mem, + const struct spi_mem_op *op); + int (*exec_op)(struct spi_mem *mem, + const struct spi_mem_op *op); +}; + +/** + * struct spi_mem_driver - SPI memory driver + * @spidrv: inherit from a SPI driver + * @probe: probe a SPI memory. Usually where detection/initialization takes + * place + * @remove: remove a SPI memory + * @shutdown: take appropriate action when the system is shutdown + * + * This is just a thin wrapper around a spi_driver. The core takes care of + * allocating the spi_mem object and forwarding the probe/remove/shutdown + * request to the spi_mem_driver. The reason we use this wrapper is because + * we might have to stuff more information into the spi_mem struct to let + * SPI controllers know more about the SPI memory they interact with, and + * having this intermediate layer allows us to do that without adding more + * useless fields to the spi_device object. + */ +struct spi_mem_driver { + struct spi_driver spidrv; + int (*probe)(struct spi_mem *mem); + int (*remove)(struct spi_mem *mem); + void (*shutdown)(struct spi_mem *mem); +}; + +#if IS_ENABLED(CONFIG_SPI_MEM) +int spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr, + const struct spi_mem_op *op, + struct sg_table *sg); + +void spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr, + const struct spi_mem_op *op, + struct sg_table *sg); +#else +static inline int +spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr, + const struct spi_mem_op *op, + struct sg_table *sg) +{ + return -ENOTSUPP; +} + +static inline void +spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr, + const struct spi_mem_op *op, + struct sg_table *sg) +{ +} +#endif /* CONFIG_SPI_MEM */ + +int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op); + +bool spi_mem_supports_op(struct spi_mem *mem, + const struct spi_mem_op *op); + +int spi_mem_exec_op(struct spi_mem *mem, + const struct spi_mem_op *op); + +int spi_mem_driver_register_with_owner(struct spi_mem_driver *drv, + struct module *owner); + +void spi_mem_driver_unregister(struct spi_mem_driver *drv); + +#define spi_mem_driver_register(__drv) \ + spi_mem_driver_register_with_owner(__drv, THIS_MODULE) + +#define module_spi_mem_driver(__drv) \ + module_driver(__drv, spi_mem_driver_register, \ + spi_mem_driver_unregister) + +#endif /* __LINUX_SPI_MEM_H */ diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index bc6bb325d1bf..a7e0bbed738c 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -27,6 +27,7 @@ struct property_entry; struct spi_controller; struct spi_transfer; struct spi_flash_read_message; +struct spi_controller_mem_ops; /* * INTERFACES between SPI master-side drivers and SPI slave protocol handlers, @@ -376,6 +377,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * transfer_one callback. * @handle_err: the subsystem calls the driver to handle an error that occurs * in the generic implementation of transfer_one_message(). + * @mem_ops: optimized/dedicated operations for interactions with SPI memory. + * This field is optional and should only be implemented if the + * controller has native support for memory like operations. * @unprepare_message: undo any work done by prepare_message(). * @slave_abort: abort the ongoing transfer request on an SPI slave controller * @spi_flash_read: to support spi-controller hardwares that provide @@ -564,6 +568,9 @@ struct spi_controller { void (*handle_err)(struct spi_controller *ctlr, struct spi_message *message); + /* Optimized handlers for SPI memory-like operations. */ + const struct spi_controller_mem_ops *mem_ops; + /* gpio chip select */ int *cs_gpios; -- cgit v1.2.3 From c1f5ba70decfc2f35edcc10505e3e78fb528d212 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 26 Apr 2018 18:18:20 +0200 Subject: spi: Get rid of the spi_flash_read() API This API has been replaced by the spi_mem_xx() one, its only user (spi-nor) has been converted to spi_mem_xx() and all SPI controller drivers that were implementing the ->spi_flash_xxx() hooks are also implementing the spi_mem ones. So we can safely get rid of this API. Signed-off-by: Boris Brezillon Reviewed-by: Frieder Schrempf Tested-by: Frieder Schrempf Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 53 ------------------------------------------------- 1 file changed, 53 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a7e0bbed738c..a64235e05321 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -26,7 +26,6 @@ struct dma_chan; struct property_entry; struct spi_controller; struct spi_transfer; -struct spi_flash_read_message; struct spi_controller_mem_ops; /* @@ -382,11 +381,6 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * controller has native support for memory like operations. * @unprepare_message: undo any work done by prepare_message(). * @slave_abort: abort the ongoing transfer request on an SPI slave controller - * @spi_flash_read: to support spi-controller hardwares that provide - * accelerated interface to read from flash devices. - * @spi_flash_can_dma: analogous to can_dma() interface, but for - * controllers implementing spi_flash_read. - * @flash_read_supported: spi device supports flash read * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS * number. Any individual value may be -ENOENT for CS lines that * are not GPIOs (driven by the SPI controller itself). @@ -552,11 +546,6 @@ struct spi_controller { int (*unprepare_message)(struct spi_controller *ctlr, struct spi_message *message); int (*slave_abort)(struct spi_controller *ctlr); - int (*spi_flash_read)(struct spi_device *spi, - struct spi_flash_read_message *msg); - bool (*spi_flash_can_dma)(struct spi_device *spi, - struct spi_flash_read_message *msg); - bool (*flash_read_supported)(struct spi_device *spi); /* * These hooks are for drivers that use a generic implementation @@ -1190,48 +1179,6 @@ static inline ssize_t spi_w8r16be(struct spi_device *spi, u8 cmd) return be16_to_cpu(result); } -/** - * struct spi_flash_read_message - flash specific information for - * spi-masters that provide accelerated flash read interfaces - * @buf: buffer to read data - * @from: offset within the flash from where data is to be read - * @len: length of data to be read - * @retlen: actual length of data read - * @read_opcode: read_opcode to be used to communicate with flash - * @addr_width: number of address bytes - * @dummy_bytes: number of dummy bytes - * @opcode_nbits: number of lines to send opcode - * @addr_nbits: number of lines to send address - * @data_nbits: number of lines for data - * @rx_sg: Scatterlist for receive data read from flash - * @cur_msg_mapped: message has been mapped for DMA - */ -struct spi_flash_read_message { - void *buf; - loff_t from; - size_t len; - size_t retlen; - u8 read_opcode; - u8 addr_width; - u8 dummy_bytes; - u8 opcode_nbits; - u8 addr_nbits; - u8 data_nbits; - struct sg_table rx_sg; - bool cur_msg_mapped; -}; - -/* SPI core interface for flash read support */ -static inline bool spi_flash_read_supported(struct spi_device *spi) -{ - return spi->controller->spi_flash_read && - (!spi->controller->flash_read_supported || - spi->controller->flash_read_supported(spi)); -} - -int spi_flash_read(struct spi_device *spi, - struct spi_flash_read_message *msg); - /*---------------------------------------------------------------------------*/ /* -- cgit v1.2.3 From 6adba21eb434d8160da05507c564c2339f4afdda Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Wed, 9 May 2018 13:56:13 +0100 Subject: soc: qcom: Add APR bus driver This patch adds support to APR bus (Asynchronous Packet Router) driver. APR driver is made as a bus driver so that the apr devices can added removed more dynamically depending on the state of the services on the dsp. APR is used for communication between application processor and QDSP to use services on QDSP like Audio and others. Signed-off-by: Srinivas Kandagatla Reviewed-and-tested-by: Rohit kumar Acked-by: Andy Gross Reviewed-by: Bjorn Andersson Signed-off-by: Mark Brown --- include/linux/mod_devicetable.h | 11 ++++ include/linux/soc/qcom/apr.h | 128 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 139 insertions(+) create mode 100644 include/linux/soc/qcom/apr.h (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 7d361be2e24f..2014bd19f28e 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -471,6 +471,17 @@ struct slim_device_id { kernel_ulong_t driver_data; }; +#define APR_NAME_SIZE 32 +#define APR_MODULE_PREFIX "apr:" + +struct apr_device_id { + char name[APR_NAME_SIZE]; + __u32 domain_id; + __u32 svc_id; + __u32 svc_version; + kernel_ulong_t driver_data; /* Data private to the driver */ +}; + #define SPMI_NAME_SIZE 32 #define SPMI_MODULE_PREFIX "spmi:" diff --git a/include/linux/soc/qcom/apr.h b/include/linux/soc/qcom/apr.h new file mode 100644 index 000000000000..c5d52e2cb275 --- /dev/null +++ b/include/linux/soc/qcom/apr.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __QCOM_APR_H_ +#define __QCOM_APR_H_ + +#include +#include +#include +#include + +extern struct bus_type aprbus; + +#define APR_HDR_LEN(hdr_len) ((hdr_len)/4) + +/* + * HEADER field + * version:0:3 + * header_size : 4:7 + * message_type : 8:9 + * reserved: 10:15 + */ +#define APR_HDR_FIELD(msg_type, hdr_len, ver)\ + (((msg_type & 0x3) << 8) | ((hdr_len & 0xF) << 4) | (ver & 0xF)) + +#define APR_HDR_SIZE sizeof(struct apr_hdr) +#define APR_SEQ_CMD_HDR_FIELD APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD, \ + APR_HDR_LEN(APR_HDR_SIZE), \ + APR_PKT_VER) +/* Version */ +#define APR_PKT_VER 0x0 + +/* Command and Response Types */ +#define APR_MSG_TYPE_EVENT 0x0 +#define APR_MSG_TYPE_CMD_RSP 0x1 +#define APR_MSG_TYPE_SEQ_CMD 0x2 +#define APR_MSG_TYPE_NSEQ_CMD 0x3 +#define APR_MSG_TYPE_MAX 0x04 + +/* APR Basic Response Message */ +#define APR_BASIC_RSP_RESULT 0x000110E8 +#define APR_RSP_ACCEPTED 0x000100BE + +struct aprv2_ibasic_rsp_result_t { + uint32_t opcode; + uint32_t status; +}; + +/* hdr field Ver [0:3], Size [4:7], Message type [8:10] */ +#define APR_HDR_FIELD_VER(h) (h & 0x000F) +#define APR_HDR_FIELD_SIZE(h) ((h & 0x00F0) >> 4) +#define APR_HDR_FIELD_SIZE_BYTES(h) (((h & 0x00F0) >> 4) * 4) +#define APR_HDR_FIELD_MT(h) ((h & 0x0300) >> 8) + +struct apr_hdr { + uint16_t hdr_field; + uint16_t pkt_size; + uint8_t src_svc; + uint8_t src_domain; + uint16_t src_port; + uint8_t dest_svc; + uint8_t dest_domain; + uint16_t dest_port; + uint32_t token; + uint32_t opcode; +} __packed; + +struct apr_pkt { + struct apr_hdr hdr; + uint8_t payload[]; +}; + +struct apr_resp_pkt { + struct apr_hdr hdr; + void *payload; + int payload_size; +}; + +/* Bits 0 to 15 -- Minor version, Bits 16 to 31 -- Major version */ +#define APR_SVC_MAJOR_VERSION(v) ((v >> 16) & 0xFF) +#define APR_SVC_MINOR_VERSION(v) (v & 0xFF) + +struct apr_device { + struct device dev; + uint16_t svc_id; + uint16_t domain_id; + uint32_t version; + char name[APR_NAME_SIZE]; + spinlock_t lock; + struct list_head node; +}; + +#define to_apr_device(d) container_of(d, struct apr_device, dev) + +struct apr_driver { + int (*probe)(struct apr_device *sl); + int (*remove)(struct apr_device *sl); + int (*callback)(struct apr_device *a, + struct apr_resp_pkt *d); + struct device_driver driver; + const struct apr_device_id *id_table; +}; + +#define to_apr_driver(d) container_of(d, struct apr_driver, driver) + +/* + * use a macro to avoid include chaining to get THIS_MODULE + */ +#define apr_driver_register(drv) __apr_driver_register(drv, THIS_MODULE) + +int __apr_driver_register(struct apr_driver *drv, struct module *owner); +void apr_driver_unregister(struct apr_driver *drv); + +/** + * module_apr_driver() - Helper macro for registering a aprbus driver + * @__aprbus_driver: aprbus_driver struct + * + * Helper macro for aprbus drivers which do not do anything special in + * module init/exit. This eliminates a lot of boilerplate. Each module + * may only use this macro once, and calling it replaces module_init() + * and module_exit() + */ +#define module_apr_driver(__apr_driver) \ + module_driver(__apr_driver, apr_driver_register, \ + apr_driver_unregister) + +int apr_send_pkt(struct apr_device *adev, struct apr_pkt *pkt); + +#endif /* __QCOM_APR_H_ */ -- cgit v1.2.3 From 89e590535f32d4bc548bcf266f3b046e50942f6d Mon Sep 17 00:00:00 2001 From: Sanyog Kale Date: Thu, 26 Apr 2018 18:38:08 +0530 Subject: soundwire: Add support for SoundWire stream management This patch adds APIs and relevant stream data structures for initialization and release of stream. Signed-off-by: Hardik T Shah Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 109 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index e91fdcf41049..610a98da103e 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -61,6 +61,30 @@ enum sdw_command_response { SDW_CMD_FAIL_OTHER = 4, }; +/** + * enum sdw_stream_type: data stream type + * + * @SDW_STREAM_PCM: PCM data stream + * @SDW_STREAM_PDM: PDM data stream + * + * spec doesn't define this, but is used in implementation + */ +enum sdw_stream_type { + SDW_STREAM_PCM = 0, + SDW_STREAM_PDM = 1, +}; + +/** + * enum sdw_data_direction: Data direction + * + * @SDW_DATA_DIR_RX: Data into Port + * @SDW_DATA_DIR_TX: Data out of Port + */ +enum sdw_data_direction { + SDW_DATA_DIR_RX = 0, + SDW_DATA_DIR_TX = 1, +}; + /* * SDW properties, defined in MIPI DisCo spec v1.0 */ @@ -450,6 +474,9 @@ struct sdw_master_ops { * @msg_lock: message lock * @ops: Master callback ops * @prop: Master properties + * @m_rt_list: List of Master instance of all stream(s) running on Bus. This + * is used to compute and program bus bandwidth, clock, frame shape, + * transport and port parameters * @defer_msg: Defer message * @clk_stop_timeout: Clock stop timeout computed */ @@ -462,6 +489,7 @@ struct sdw_bus { struct mutex msg_lock; const struct sdw_master_ops *ops; struct sdw_master_prop prop; + struct list_head m_rt_list; struct sdw_defer defer_msg; unsigned int clk_stop_timeout; }; @@ -469,6 +497,87 @@ struct sdw_bus { int sdw_add_bus_master(struct sdw_bus *bus); void sdw_delete_bus_master(struct sdw_bus *bus); +/** + * sdw_stream_config: Master or Slave stream configuration + * + * @frame_rate: Audio frame rate of the stream, in Hz + * @ch_count: Channel count of the stream + * @bps: Number of bits per audio sample + * @direction: Data direction + * @type: Stream type PCM or PDM + */ +struct sdw_stream_config { + unsigned int frame_rate; + unsigned int ch_count; + unsigned int bps; + enum sdw_data_direction direction; + enum sdw_stream_type type; +}; + +/** + * sdw_stream_state: Stream states + * + * @SDW_STREAM_ALLOCATED: New stream allocated. + * @SDW_STREAM_CONFIGURED: Stream configured + * @SDW_STREAM_PREPARED: Stream prepared + * @SDW_STREAM_ENABLED: Stream enabled + * @SDW_STREAM_DISABLED: Stream disabled + * @SDW_STREAM_DEPREPARED: Stream de-prepared + * @SDW_STREAM_RELEASED: Stream released + */ +enum sdw_stream_state { + SDW_STREAM_ALLOCATED = 0, + SDW_STREAM_CONFIGURED = 1, + SDW_STREAM_PREPARED = 2, + SDW_STREAM_ENABLED = 3, + SDW_STREAM_DISABLED = 4, + SDW_STREAM_DEPREPARED = 5, + SDW_STREAM_RELEASED = 6, +}; + +/** + * sdw_stream_params: Stream parameters + * + * @rate: Sampling frequency, in Hz + * @ch_count: Number of channels + * @bps: bits per channel sample + */ +struct sdw_stream_params { + unsigned int rate; + unsigned int ch_count; + unsigned int bps; +}; + +/** + * sdw_stream_runtime: Runtime stream parameters + * + * @name: SoundWire stream name + * @params: Stream parameters + * @state: Current state of the stream + * @type: Stream type PCM or PDM + * @m_rt: Master runtime + */ +struct sdw_stream_runtime { + char *name; + struct sdw_stream_params params; + enum sdw_stream_state state; + enum sdw_stream_type type; + struct sdw_master_runtime *m_rt; +}; + +struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name); +void sdw_release_stream(struct sdw_stream_runtime *stream); +int sdw_stream_add_master(struct sdw_bus *bus, + struct sdw_stream_config *stream_config, + struct sdw_stream_runtime *stream); +int sdw_stream_add_slave(struct sdw_slave *slave, + struct sdw_stream_config *stream_config, + struct sdw_stream_runtime *stream); +int sdw_stream_remove_master(struct sdw_bus *bus, + struct sdw_stream_runtime *stream); +int sdw_stream_remove_slave(struct sdw_slave *slave, + struct sdw_stream_runtime *stream); + /* messaging and data APIs */ int sdw_read(struct sdw_slave *slave, u32 addr); -- cgit v1.2.3 From bbe7379d8040a88ea832fdcbe49a9d16e9b5755e Mon Sep 17 00:00:00 2001 From: Sanyog Kale Date: Thu, 26 Apr 2018 18:38:13 +0530 Subject: soundwire: Add support for port management Add Soundwire port data structures and APIS for initialization and release of ports. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 67 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 610a98da103e..5e06a0de508c 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -26,6 +26,8 @@ struct sdw_slave; #define SDW_MAX_DEVICES 11 +#define SDW_VALID_PORT_RANGE(n) (n <= 14 && n >= 1) + /** * enum sdw_slave_status - Slave status * @SDW_SLAVE_UNATTACHED: Slave is not attached with the bus. @@ -430,6 +432,56 @@ int sdw_handle_slave_status(struct sdw_bus *bus, * SDW master structures and APIs */ +/** + * struct sdw_port_params: Data Port parameters + * + * @num: Port number + * @bps: Word length of the Port + * @flow_mode: Port Data flow mode + * @data_mode: Test modes or normal mode + * + * This is used to program the Data Port based on Data Port stream + * parameters. + */ +struct sdw_port_params { + unsigned int num; + unsigned int bps; + unsigned int flow_mode; + unsigned int data_mode; +}; + +/** + * struct sdw_transport_params: Data Port Transport Parameters + * + * @blk_grp_ctrl_valid: Port implements block group control + * @num: Port number + * @blk_grp_ctrl: Block group control value + * @sample_interval: Sample interval + * @offset1: Blockoffset of the payload data + * @offset2: Blockoffset of the payload data + * @hstart: Horizontal start of the payload data + * @hstop: Horizontal stop of the payload data + * @blk_pkg_mode: Block per channel or block per port + * @lane_ctrl: Data lane Port uses for Data transfer. Currently only single + * data lane is supported in bus + * + * This is used to program the Data Port based on Data Port transport + * parameters. All these parameters are banked and can be modified + * during a bank switch without any artifacts in audio stream. + */ +struct sdw_transport_params { + bool blk_grp_ctrl_valid; + unsigned int port_num; + unsigned int blk_grp_ctrl; + unsigned int sample_interval; + unsigned int offset1; + unsigned int offset2; + unsigned int hstart; + unsigned int hstop; + unsigned int blk_pkg_mode; + unsigned int lane_ctrl; +}; + struct sdw_msg; /** @@ -497,6 +549,17 @@ struct sdw_bus { int sdw_add_bus_master(struct sdw_bus *bus); void sdw_delete_bus_master(struct sdw_bus *bus); +/** + * sdw_port_config: Master or Slave Port configuration + * + * @num: Port number + * @ch_mask: channels mask for port + */ +struct sdw_port_config { + unsigned int num; + unsigned int ch_mask; +}; + /** * sdw_stream_config: Master or Slave stream configuration * @@ -569,9 +632,13 @@ struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name); void sdw_release_stream(struct sdw_stream_runtime *stream); int sdw_stream_add_master(struct sdw_bus *bus, struct sdw_stream_config *stream_config, + struct sdw_port_config *port_config, + unsigned int num_ports, struct sdw_stream_runtime *stream); int sdw_stream_add_slave(struct sdw_slave *slave, struct sdw_stream_config *stream_config, + struct sdw_port_config *port_config, + unsigned int num_ports, struct sdw_stream_runtime *stream); int sdw_stream_remove_master(struct sdw_bus *bus, struct sdw_stream_runtime *stream); -- cgit v1.2.3 From f8101c74aa542b6e583513216176679a9e922b2f Mon Sep 17 00:00:00 2001 From: Sanyog Kale Date: Thu, 26 Apr 2018 18:38:17 +0530 Subject: soundwire: Add Master and Slave port programming Master and Slave port registers need to be programmed for each port used in a stream. Add the helpers for port register programming. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 47 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 46 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 5e06a0de508c..03b55804d830 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -367,7 +367,30 @@ struct sdw_slave_intr_status { }; /** - * struct sdw_slave_ops - Slave driver callback ops + * sdw_reg_bank - SoundWire register banks + * @SDW_BANK0: Soundwire register bank 0 + * @SDW_BANK1: Soundwire register bank 1 + */ +enum sdw_reg_bank { + SDW_BANK0, + SDW_BANK1, +}; + +/** + * struct sdw_bus_params: Structure holding bus configuration + * + * @curr_bank: Current bank in use (BANK0/BANK1) + * @next_bank: Next bank to use (BANK0/BANK1). next_bank will always be + * set to !curr_bank + */ +struct sdw_bus_params { + enum sdw_reg_bank curr_bank; + enum sdw_reg_bank next_bank; +}; + +/** + * struct sdw_slave_ops: Slave driver callback ops + * * @read_prop: Read Slave properties * @interrupt_callback: Device interrupt notification (invoked in thread * context) @@ -482,6 +505,24 @@ struct sdw_transport_params { unsigned int lane_ctrl; }; +/** + * struct sdw_master_port_ops: Callback functions from bus to Master + * driver to set Master Data ports. + * + * @dpn_set_port_params: Set the Port parameters for the Master Port. + * Mandatory callback + * @dpn_set_port_transport_params: Set transport parameters for the Master + * Port. Mandatory callback + */ +struct sdw_master_port_ops { + int (*dpn_set_port_params)(struct sdw_bus *bus, + struct sdw_port_params *port_params, + unsigned int bank); + int (*dpn_set_port_transport_params)(struct sdw_bus *bus, + struct sdw_transport_params *transport_params, + enum sdw_reg_bank bank); +}; + struct sdw_msg; /** @@ -525,6 +566,8 @@ struct sdw_master_ops { * @bus_lock: bus lock * @msg_lock: message lock * @ops: Master callback ops + * @port_ops: Master port callback ops + * @params: Current bus parameters * @prop: Master properties * @m_rt_list: List of Master instance of all stream(s) running on Bus. This * is used to compute and program bus bandwidth, clock, frame shape, @@ -540,6 +583,8 @@ struct sdw_bus { struct mutex bus_lock; struct mutex msg_lock; const struct sdw_master_ops *ops; + const struct sdw_master_port_ops *port_ops; + struct sdw_bus_params params; struct sdw_master_prop prop; struct list_head m_rt_list; struct sdw_defer defer_msg; -- cgit v1.2.3 From 79df15b7d37c80aee5dff361841500c79e62b1e0 Mon Sep 17 00:00:00 2001 From: Sanyog Kale Date: Thu, 26 Apr 2018 18:38:23 +0530 Subject: soundwire: Add helpers for ports operations Add helpers to configure, prepare, enable, disable and de-prepare ports. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 54 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 03b55804d830..fab7de3c00f1 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -376,6 +376,37 @@ enum sdw_reg_bank { SDW_BANK1, }; +/** + * struct sdw_prepare_ch: Prepare/De-prepare Data Port channel + * + * @num: Port number + * @ch_mask: Active channel mask + * @prepare: Prepare (true) /de-prepare (false) channel + * @bank: Register bank, which bank Slave/Master driver should program for + * implementation defined registers. This is always updated to next_bank + * value read from bus params. + * + */ +struct sdw_prepare_ch { + unsigned int num; + unsigned int ch_mask; + bool prepare; + unsigned int bank; +}; + +/** + * enum sdw_port_prep_ops: Prepare operations for Data Port + * + * @SDW_OPS_PORT_PRE_PREP: Pre prepare operation for the Port + * @SDW_OPS_PORT_PREP: Prepare operation for the Port + * @SDW_OPS_PORT_POST_PREP: Post prepare operation for the Port + */ +enum sdw_port_prep_ops { + SDW_OPS_PORT_PRE_PREP = 0, + SDW_OPS_PORT_PREP = 1, + SDW_OPS_PORT_POST_PREP = 2, +}; + /** * struct sdw_bus_params: Structure holding bus configuration * @@ -395,6 +426,7 @@ struct sdw_bus_params { * @interrupt_callback: Device interrupt notification (invoked in thread * context) * @update_status: Update Slave status + * @port_prep: Prepare the port with parameters */ struct sdw_slave_ops { int (*read_prop)(struct sdw_slave *sdw); @@ -402,6 +434,9 @@ struct sdw_slave_ops { struct sdw_slave_intr_status *status); int (*update_status)(struct sdw_slave *slave, enum sdw_slave_status status); + int (*port_prep)(struct sdw_slave *slave, + struct sdw_prepare_ch *prepare_ch, + enum sdw_port_prep_ops pre_ops); }; /** @@ -505,6 +540,19 @@ struct sdw_transport_params { unsigned int lane_ctrl; }; +/** + * struct sdw_enable_ch: Enable/disable Data Port channel + * + * @num: Port number + * @ch_mask: Active channel mask + * @enable: Enable (true) /disable (false) channel + */ +struct sdw_enable_ch { + unsigned int port_num; + unsigned int ch_mask; + bool enable; +}; + /** * struct sdw_master_port_ops: Callback functions from bus to Master * driver to set Master Data ports. @@ -513,6 +561,8 @@ struct sdw_transport_params { * Mandatory callback * @dpn_set_port_transport_params: Set transport parameters for the Master * Port. Mandatory callback + * @dpn_port_prep: Port prepare operations for the Master Data Port. + * @dpn_port_enable_ch: Enable the channels of Master Port. */ struct sdw_master_port_ops { int (*dpn_set_port_params)(struct sdw_bus *bus, @@ -521,6 +571,10 @@ struct sdw_master_port_ops { int (*dpn_set_port_transport_params)(struct sdw_bus *bus, struct sdw_transport_params *transport_params, enum sdw_reg_bank bank); + int (*dpn_port_prep)(struct sdw_bus *bus, + struct sdw_prepare_ch *prepare_ch); + int (*dpn_port_enable_ch)(struct sdw_bus *bus, + struct sdw_enable_ch *enable_ch, unsigned int bank); }; struct sdw_msg; -- cgit v1.2.3 From 99b8a5d608a64254f22483f6b67a98f26d3eac8c Mon Sep 17 00:00:00 2001 From: Sanyog Kale Date: Thu, 26 Apr 2018 18:38:28 +0530 Subject: soundwire: Add bank switch routine SoundWire supports two registers banks. So, program the alternate bank with new configuration and then performs bank switch. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 48 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index fab7de3c00f1..61d671271592 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -23,7 +23,17 @@ struct sdw_slave; #define SDW_MASTER_DEV_NUM 14 #define SDW_NUM_DEV_ID_REGISTERS 6 +/* frame shape defines */ +/* + * Note: The maximum row define in SoundWire spec 1.1 is 23. In order to + * fill hole with 0, one more dummy entry is added + */ +#define SDW_FRAME_ROWS 24 +#define SDW_FRAME_COLS 8 +#define SDW_FRAME_ROW_COLS (SDW_FRAME_ROWS * SDW_FRAME_COLS) + +#define SDW_FRAME_CTRL_BITS 48 #define SDW_MAX_DEVICES 11 #define SDW_VALID_PORT_RANGE(n) (n <= 14 && n >= 1) @@ -376,6 +386,21 @@ enum sdw_reg_bank { SDW_BANK1, }; +/** + * struct sdw_bus_conf: Bus configuration + * + * @clk_freq: Clock frequency, in Hz + * @num_rows: Number of rows in frame + * @num_cols: Number of columns in frame + * @bank: Next register bank + */ +struct sdw_bus_conf { + unsigned int clk_freq; + unsigned int num_rows; + unsigned int num_cols; + unsigned int bank; +}; + /** * struct sdw_prepare_ch: Prepare/De-prepare Data Port channel * @@ -413,10 +438,20 @@ enum sdw_port_prep_ops { * @curr_bank: Current bank in use (BANK0/BANK1) * @next_bank: Next bank to use (BANK0/BANK1). next_bank will always be * set to !curr_bank + * @max_dr_freq: Maximum double rate clock frequency supported, in Hz + * @curr_dr_freq: Current double rate clock frequency, in Hz + * @bandwidth: Current bandwidth + * @col: Active columns + * @row: Active rows */ struct sdw_bus_params { enum sdw_reg_bank curr_bank; enum sdw_reg_bank next_bank; + unsigned int max_dr_freq; + unsigned int curr_dr_freq; + unsigned int bandwidth; + unsigned int col; + unsigned int row; }; /** @@ -426,6 +461,7 @@ struct sdw_bus_params { * @interrupt_callback: Device interrupt notification (invoked in thread * context) * @update_status: Update Slave status + * @bus_config: Update the bus config for Slave * @port_prep: Prepare the port with parameters */ struct sdw_slave_ops { @@ -434,6 +470,8 @@ struct sdw_slave_ops { struct sdw_slave_intr_status *status); int (*update_status)(struct sdw_slave *slave, enum sdw_slave_status status); + int (*bus_config)(struct sdw_slave *slave, + struct sdw_bus_params *params); int (*port_prep)(struct sdw_slave *slave, struct sdw_prepare_ch *prepare_ch, enum sdw_port_prep_ops pre_ops); @@ -597,6 +635,9 @@ struct sdw_defer { * @xfer_msg: Transfer message callback * @xfer_msg_defer: Defer version of transfer message callback * @reset_page_addr: Reset the SCP page address registers + * @set_bus_conf: Set the bus configuration + * @pre_bank_switch: Callback for pre bank switch + * @post_bank_switch: Callback for post bank switch */ struct sdw_master_ops { int (*read_prop)(struct sdw_bus *bus); @@ -608,6 +649,11 @@ struct sdw_master_ops { struct sdw_defer *defer); enum sdw_command_response (*reset_page_addr) (struct sdw_bus *bus, unsigned int dev_num); + int (*set_bus_conf)(struct sdw_bus *bus, + struct sdw_bus_params *params); + int (*pre_bank_switch)(struct sdw_bus *bus); + int (*post_bank_switch)(struct sdw_bus *bus); + }; /** @@ -628,6 +674,7 @@ struct sdw_master_ops { * transport and port parameters * @defer_msg: Defer message * @clk_stop_timeout: Clock stop timeout computed + * @bank_switch_timeout: Bank switch timeout computed */ struct sdw_bus { struct device *dev; @@ -643,6 +690,7 @@ struct sdw_bus { struct list_head m_rt_list; struct sdw_defer defer_msg; unsigned int clk_stop_timeout; + u32 bank_switch_timeout; }; int sdw_add_bus_master(struct sdw_bus *bus); -- cgit v1.2.3 From 5c3eb9f7bdf1f141e051605b7b4225b1e83820a2 Mon Sep 17 00:00:00 2001 From: Sanyog Kale Date: Thu, 26 Apr 2018 18:38:33 +0530 Subject: soundwire: Add stream configuration APIs Add APIs for prepare, enable, disable and de-prepare stream. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 61d671271592..399cfb295593 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -791,6 +791,10 @@ int sdw_stream_remove_master(struct sdw_bus *bus, struct sdw_stream_runtime *stream); int sdw_stream_remove_slave(struct sdw_slave *slave, struct sdw_stream_runtime *stream); +int sdw_prepare_stream(struct sdw_stream_runtime *stream); +int sdw_enable_stream(struct sdw_stream_runtime *stream); +int sdw_disable_stream(struct sdw_stream_runtime *stream); +int sdw_deprepare_stream(struct sdw_stream_runtime *stream); /* messaging and data APIs */ -- cgit v1.2.3 From c46302ec554c575e79d791c7c84fd4c795e97680 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 26 Apr 2018 18:39:05 +0530 Subject: soundwire: intel: Add audio DAI ops Add DAI registration and DAI ops for the Intel driver along with callback for topology configuration. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 3 +++ include/linux/soundwire/sdw_intel.h | 14 ++++++++++++++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 399cfb295593..962971e6a9c7 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -38,6 +38,9 @@ struct sdw_slave; #define SDW_VALID_PORT_RANGE(n) (n <= 14 && n >= 1) +#define SDW_DAI_ID_RANGE_START 100 +#define SDW_DAI_ID_RANGE_END 200 + /** * enum sdw_slave_status - Slave status * @SDW_SLAVE_UNATTACHED: Slave is not attached with the bus. diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 4b37528f592d..2b9573b8aedd 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -4,18 +4,32 @@ #ifndef __SDW_INTEL_H #define __SDW_INTEL_H +/** + * struct sdw_intel_ops: Intel audio driver callback ops + * + * @config_stream: configure the stream with the hw_params + */ +struct sdw_intel_ops { + int (*config_stream)(void *arg, void *substream, + void *dai, void *hw_params, int stream_num); +}; + /** * struct sdw_intel_res - Soundwire Intel resource structure * @mmio_base: mmio base of SoundWire registers * @irq: interrupt number * @handle: ACPI parent handle * @parent: parent device + * @ops: callback ops + * @arg: callback arg */ struct sdw_intel_res { void __iomem *mmio_base; int irq; acpi_handle handle; struct device *parent; + const struct sdw_intel_ops *ops; + void *arg; }; void *sdw_intel_init(acpi_handle *parent_handle, struct sdw_intel_res *res); -- cgit v1.2.3 From bcf3ffd405df6998914b248d2f22625544a4dd56 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:26:55 -0400 Subject: svcrdma: Add proper SPDX tags for NetApp-contributed source Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 7337e1221590..88da0c9bd7b1 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved. * -- cgit v1.2.3 From ecf85b2384ea5f7cb0577bf6143bc46d9ecfe4d3 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:27:21 -0400 Subject: svcrdma: Introduce svc_rdma_recv_ctxt svc_rdma_op_ctxt's are pre-allocated and maintained on a per-xprt free list. This eliminates the overhead of calling kmalloc / kfree, both of which grab a globally shared lock that disables interrupts. To reduce contention further, separate the use of these objects in the Receive and Send paths in svcrdma. Subsequent patches will take advantage of this separation by allocating real resources which are then cached in these objects. The allocations are freed when the transport is torn down. I've renamed the structure so that static type checking can be used to ensure that uses of op_ctxt and recv_ctxt are not confused. As an additional clean up, structure fields are renamed to conform with kernel coding conventions. As a final clean up, helpers related to recv_ctxt are moved closer to the functions that use them. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 88da0c9bd7b1..37f759d65348 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -128,6 +128,9 @@ struct svcxprt_rdma { unsigned long sc_flags; struct list_head sc_read_complete_q; struct work_struct sc_work; + + spinlock_t sc_recv_lock; + struct list_head sc_recv_ctxts; }; /* sc_flags */ #define RDMAXPRT_CONN_PENDING 3 @@ -142,6 +145,19 @@ struct svcxprt_rdma { #define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD +struct svc_rdma_recv_ctxt { + struct list_head rc_list; + struct ib_recv_wr rc_recv_wr; + struct ib_cqe rc_cqe; + struct xdr_buf rc_arg; + u32 rc_byte_len; + unsigned int rc_page_count; + unsigned int rc_hdr_count; + struct ib_sge rc_sges[1 + + RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE]; + struct page *rc_pages[RPCSVC_MAXPAGES]; +}; + /* Track DMA maps for this transport and context */ static inline void svc_rdma_count_mappings(struct svcxprt_rdma *rdma, struct svc_rdma_op_ctxt *ctxt) @@ -155,13 +171,19 @@ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, struct xdr_buf *rcvbuf); /* svc_rdma_recvfrom.c */ +extern void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma); +extern bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma); +extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, + struct svc_rdma_recv_ctxt *ctxt, + int free_pages); +extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma); extern int svc_rdma_recvfrom(struct svc_rqst *); /* svc_rdma_rw.c */ extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma); extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, - struct svc_rdma_op_ctxt *head, __be32 *p); + struct svc_rdma_recv_ctxt *head, __be32 *p); extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch, struct xdr_buf *xdr); extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, -- cgit v1.2.3 From 2c577bfea85e421bfa91df16ccf5156361aa8d4b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:27:27 -0400 Subject: svcrdma: Remove sc_rq_depth Clean up: No need to retain rq_depth in struct svcrdma_xprt, it is used only in svc_rdma_accept(). Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 37f759d65348..3cb66319a814 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -101,7 +101,6 @@ struct svcxprt_rdma { atomic_t sc_sq_avail; /* SQEs ready to be consumed */ unsigned int sc_sq_depth; /* Depth of SQ */ - unsigned int sc_rq_depth; /* Depth of RQ */ __be32 sc_fc_credits; /* Forward credits */ u32 sc_max_requests; /* Max requests */ u32 sc_max_bc_requests;/* Backward credits */ -- cgit v1.2.3 From 1e5f4160745690a0476929d128a336cae95c1df9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:27:32 -0400 Subject: svcrdma: Simplify svc_rdma_recv_ctxt_put Currently svc_rdma_recv_ctxt_put's callers have to know whether they want to free the ctxt's pages or not. This means the human developers have to know when and why to set that free_pages argument. Instead, the ctxt should carry that information with it so that svc_rdma_recv_ctxt_put does the right thing no matter who is calling. We want to keep track of the number of pages in the Receive buffer separately from the number of pages pulled over by RDMA Read. This is so that the correct number of pages can be freed properly and that number is well-documented. So now, rc_hdr_count is the number of pages consumed by head[0] (ie., the page index where the Read chunk should start); and rc_page_count is always the number of pages that need to be released when the ctxt is put. The @free_pages argument is no longer needed. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 3cb66319a814..f0bd0b6d8931 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -173,8 +173,7 @@ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, extern void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma); extern bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma); extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, - struct svc_rdma_recv_ctxt *ctxt, - int free_pages); + struct svc_rdma_recv_ctxt *ctxt); extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma); extern int svc_rdma_recvfrom(struct svc_rqst *); -- cgit v1.2.3 From 3316f0631139c87631f2652c118da1a0354bd40d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:27:43 -0400 Subject: svcrdma: Persistently allocate and DMA-map Receive buffers The current Receive path uses an array of pages which are allocated and DMA mapped when each Receive WR is posted, and then handed off to the upper layer in rqstp::rq_arg. The page flip releases unused pages in the rq_pages pagelist. This mechanism introduces a significant amount of overhead. So instead, kmalloc the Receive buffer, and leave it DMA-mapped while the transport remains connected. This confers a number of benefits: * Each Receive WR requires only one receive SGE, no matter how large the inline threshold is. This helps the server-side NFS/RDMA transport operate on less capable RDMA devices. * The Receive buffer is left allocated and mapped all the time. This relieves svc_rdma_post_recv from the overhead of allocating and DMA-mapping a fresh buffer. * svc_rdma_wc_receive no longer has to DMA unmap the Receive buffer. It has to DMA sync only the number of bytes that were received. * svc_rdma_build_arg_xdr no longer has to free a page in rq_pages for each page in the Receive buffer, making it a constant-time function. * The Receive buffer is now plugged directly into the rq_arg's head[0].iov_vec, and can be larger than a page without spilling over into rq_arg's page list. This enables simplification of the RDMA Read path in subsequent patches. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index f0bd0b6d8931..01baabfb863b 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -148,12 +148,12 @@ struct svc_rdma_recv_ctxt { struct list_head rc_list; struct ib_recv_wr rc_recv_wr; struct ib_cqe rc_cqe; + struct ib_sge rc_recv_sge; + void *rc_recv_buf; struct xdr_buf rc_arg; u32 rc_byte_len; unsigned int rc_page_count; unsigned int rc_hdr_count; - struct ib_sge rc_sges[1 + - RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE]; struct page *rc_pages[RPCSVC_MAXPAGES]; }; -- cgit v1.2.3 From eb5d7a622e0bbe3fd316b2325d3840a0e030a3c4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:27:48 -0400 Subject: svcrdma: Allocate recv_ctxt's on CPU handling Receives There is a significant latency penalty when processing an ingress Receive if the Receive buffer resides in memory that is not on the same NUMA node as the the CPU handling completions for a CQ. The system administrator and the device driver determine which CPU handles completions. This CPU does not change during life of the CQ. Further the Upper Layer does not have any visibility of which CPU it is. Allocating Receive buffers in the Receive completion handler guarantees that Receive buffers are allocated on the preferred NUMA node for that CQ. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 01baabfb863b..27cf59c7085f 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -151,6 +151,7 @@ struct svc_rdma_recv_ctxt { struct ib_sge rc_recv_sge; void *rc_recv_buf; struct xdr_buf rc_arg; + bool rc_temp; u32 rc_byte_len; unsigned int rc_page_count; unsigned int rc_hdr_count; -- cgit v1.2.3 From f016f305f98159a9131ce200ed3b4ed92133012c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:27:53 -0400 Subject: svcrdma: Refactor svc_rdma_dma_map_buf Clean up: svc_rdma_dma_map_buf does mostly the same thing as svc_rdma_dma_map_page, so let's fold these together. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 27cf59c7085f..95530bc7bfab 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -158,13 +158,6 @@ struct svc_rdma_recv_ctxt { struct page *rc_pages[RPCSVC_MAXPAGES]; }; -/* Track DMA maps for this transport and context */ -static inline void svc_rdma_count_mappings(struct svcxprt_rdma *rdma, - struct svc_rdma_op_ctxt *ctxt) -{ - ctxt->mapped_sges++; -} - /* svc_rdma_backchannel.c */ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, -- cgit v1.2.3 From 232627905f12a05df75853c62451ce0886803cee Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:27:59 -0400 Subject: svcrdma: Clean up Send SGE accounting Clean up: Since there's already a svc_rdma_op_ctxt being passed around with the running count of mapped SGEs, drop unneeded parameters to svc_rdma_post_send_wr(). Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 95530bc7bfab..8827b4e36c3c 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -188,7 +188,7 @@ extern int svc_rdma_map_reply_hdr(struct svcxprt_rdma *rdma, __be32 *rdma_resp, unsigned int len); extern int svc_rdma_post_send_wr(struct svcxprt_rdma *rdma, struct svc_rdma_op_ctxt *ctxt, - int num_sge, u32 inv_rkey); + u32 inv_rkey); extern int svc_rdma_sendto(struct svc_rqst *); /* svc_rdma_transport.c */ -- cgit v1.2.3 From 4201c7464753827803366b40e82eb050c04ebdef Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:28:04 -0400 Subject: svcrdma: Introduce svc_rdma_send_ctxt svc_rdma_op_ctxt's are pre-allocated and maintained on a per-xprt free list. This eliminates the overhead of calling kmalloc / kfree, both of which grab a globally shared lock that disables interrupts. Introduce a replacement to svc_rdma_op_ctxt's that is built especially for the svcrdma Send path. Subsequent patches will take advantage of this new structure by allocating real resources which are then cached in these objects. The allocations are freed when the transport is torn down. I've renamed the structure so that static type checking can be used to ensure that uses of op_ctxt and send_ctxt are not confused. As an additional clean up, structure fields are renamed to conform with kernel coding conventions. Additional clean ups: - Handle svc_rdma_send_ctxt_get allocation failure at each call site, rather than pre-allocating and hoping we guessed correctly - All send_ctxt_put call-sites request page freeing, so remove the @free_pages argument - All send_ctxt_put call-sites unmap SGEs, so fold that into svc_rdma_send_ctxt_put Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 35 +++++++++++++++++++++++------------ 1 file changed, 23 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 8827b4e36c3c..d3e2bb331264 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -109,8 +109,8 @@ struct svcxprt_rdma { struct ib_pd *sc_pd; - spinlock_t sc_ctxt_lock; - struct list_head sc_ctxts; + spinlock_t sc_send_lock; + struct list_head sc_send_ctxts; int sc_ctxt_used; spinlock_t sc_rw_ctxt_lock; struct list_head sc_rw_ctxts; @@ -158,6 +158,19 @@ struct svc_rdma_recv_ctxt { struct page *rc_pages[RPCSVC_MAXPAGES]; }; +enum { + RPCRDMA_MAX_SGES = 1 + (RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE), +}; + +struct svc_rdma_send_ctxt { + struct list_head sc_list; + struct ib_send_wr sc_send_wr; + struct ib_cqe sc_cqe; + int sc_page_count; + struct page *sc_pages[RPCSVC_MAXPAGES]; + struct ib_sge sc_sges[RPCRDMA_MAX_SGES]; +}; + /* svc_rdma_backchannel.c */ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, @@ -183,24 +196,22 @@ extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, struct xdr_buf *xdr); /* svc_rdma_sendto.c */ +extern void svc_rdma_send_ctxts_destroy(struct svcxprt_rdma *rdma); +extern struct svc_rdma_send_ctxt * + svc_rdma_send_ctxt_get(struct svcxprt_rdma *rdma); +extern void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *ctxt); +extern int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr); extern int svc_rdma_map_reply_hdr(struct svcxprt_rdma *rdma, - struct svc_rdma_op_ctxt *ctxt, + struct svc_rdma_send_ctxt *ctxt, __be32 *rdma_resp, unsigned int len); extern int svc_rdma_post_send_wr(struct svcxprt_rdma *rdma, - struct svc_rdma_op_ctxt *ctxt, + struct svc_rdma_send_ctxt *ctxt, u32 inv_rkey); extern int svc_rdma_sendto(struct svc_rqst *); /* svc_rdma_transport.c */ -extern void svc_rdma_wc_send(struct ib_cq *, struct ib_wc *); -extern void svc_rdma_wc_reg(struct ib_cq *, struct ib_wc *); -extern void svc_rdma_wc_read(struct ib_cq *, struct ib_wc *); -extern void svc_rdma_wc_inv(struct ib_cq *, struct ib_wc *); -extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *); extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); -extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *); -extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int); -extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt); extern void svc_sq_reap(struct svcxprt_rdma *); extern void svc_rq_reap(struct svcxprt_rdma *); extern void svc_rdma_prep_reply_hdr(struct svc_rqst *); -- cgit v1.2.3 From 25fd86eca11c26bad2aede6dd4709ff58f89c7cb Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:28:09 -0400 Subject: svcrdma: Don't overrun the SGE array in svc_rdma_send_ctxt Receive buffers are always the same size, but each Send WR has a variable number of SGEs, based on the contents of the xdr_buf being sent. While assembling a Send WR, keep track of the number of SGEs so that we don't exceed the device's maximum, or walk off the end of the Send SGE array. For now the Send path just fails if it exceeds the maximum. The current logic in svc_rdma_accept bases the maximum number of Send SGEs on the largest NFS request that can be sent or received. In the transport layer, the limit is actually based on the capabilities of the underlying device, not on properties of the Upper Layer Protocol. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index d3e2bb331264..bfb8824e31e1 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -96,7 +96,7 @@ struct svcxprt_rdma { struct rdma_cm_id *sc_cm_id; /* RDMA connection id */ struct list_head sc_accept_q; /* Conn. waiting accept */ int sc_ord; /* RDMA read limit */ - int sc_max_sge; + int sc_max_send_sges; bool sc_snd_w_inv; /* OK to use Send With Invalidate */ atomic_t sc_sq_avail; /* SQEs ready to be consumed */ @@ -158,17 +158,14 @@ struct svc_rdma_recv_ctxt { struct page *rc_pages[RPCSVC_MAXPAGES]; }; -enum { - RPCRDMA_MAX_SGES = 1 + (RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE), -}; - struct svc_rdma_send_ctxt { struct list_head sc_list; struct ib_send_wr sc_send_wr; struct ib_cqe sc_cqe; int sc_page_count; + int sc_cur_sge_no; struct page *sc_pages[RPCSVC_MAXPAGES]; - struct ib_sge sc_sges[RPCRDMA_MAX_SGES]; + struct ib_sge sc_sges[]; }; /* svc_rdma_backchannel.c */ -- cgit v1.2.3 From 986b78894b268f605e9ea055b99959bdce0e5945 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:28:15 -0400 Subject: svcrdma: Remove post_send_wr Clean up: Now that the send_wr is part of the svc_rdma_send_ctxt, svc_rdma_post_send_wr is nearly empty. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index bfb8824e31e1..a8bfc214614b 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -202,9 +202,6 @@ extern int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr); extern int svc_rdma_map_reply_hdr(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt, __be32 *rdma_resp, unsigned int len); -extern int svc_rdma_post_send_wr(struct svcxprt_rdma *rdma, - struct svc_rdma_send_ctxt *ctxt, - u32 inv_rkey); extern int svc_rdma_sendto(struct svc_rqst *); /* svc_rdma_transport.c */ -- cgit v1.2.3 From 99722fe4d5a634707ced8d8f42b883b87a86b3c5 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:28:25 -0400 Subject: svcrdma: Persistently allocate and DMA-map Send buffers While sending each RPC Reply, svc_rdma_sendto allocates and DMA- maps a separate buffer where the RPC/RDMA transport header is constructed. The buffer is unmapped and released in the Send completion handler. This is significant per-RPC overhead, especially for small RPCs. Instead, allocate and DMA-map a buffer, and cache it in each svc_rdma_send_ctxt. This buffer and its mapping can be re-used for each RPC, saving the cost of memory allocation and DMA mapping. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index a8bfc214614b..96b14a72d359 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -162,6 +162,7 @@ struct svc_rdma_send_ctxt { struct list_head sc_list; struct ib_send_wr sc_send_wr; struct ib_cqe sc_cqe; + void *sc_xprt_buf; int sc_page_count; int sc_cur_sge_no; struct page *sc_pages[RPCSVC_MAXPAGES]; @@ -199,9 +200,12 @@ extern struct svc_rdma_send_ctxt * extern void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt); extern int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr); -extern int svc_rdma_map_reply_hdr(struct svcxprt_rdma *rdma, +extern void svc_rdma_sync_reply_hdr(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *ctxt, + unsigned int len); +extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt, - __be32 *rdma_resp, unsigned int len); + struct xdr_buf *xdr, __be32 *wr_lst); extern int svc_rdma_sendto(struct svc_rqst *); /* svc_rdma_transport.c */ -- cgit v1.2.3 From 51cc257a1186f69dbb6faec1bd48cc7e1fc31079 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:28:31 -0400 Subject: svcrdma: Remove unused svc_rdma_op_ctxt Clean up: Eliminate a structure that is no longer used. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 96b14a72d359..fd78f78df5c6 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -71,26 +71,6 @@ extern atomic_t rdma_stat_rq_prod; extern atomic_t rdma_stat_sq_poll; extern atomic_t rdma_stat_sq_prod; -/* - * Contexts are built when an RDMA request is created and are a - * record of the resources that can be recovered when the request - * completes. - */ -struct svc_rdma_op_ctxt { - struct list_head list; - struct xdr_buf arg; - struct ib_cqe cqe; - u32 byte_len; - struct svcxprt_rdma *xprt; - enum dma_data_direction direction; - int count; - unsigned int mapped_sges; - int hdr_count; - struct ib_send_wr send_wr; - struct ib_sge sge[1 + RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE]; - struct page *pages[RPCSVC_MAXPAGES]; -}; - struct svcxprt_rdma { struct svc_xprt sc_xprt; /* SVC transport structure */ struct rdma_cm_id *sc_cm_id; /* RDMA connection id */ @@ -111,7 +91,6 @@ struct svcxprt_rdma { spinlock_t sc_send_lock; struct list_head sc_send_ctxts; - int sc_ctxt_used; spinlock_t sc_rw_ctxt_lock; struct list_head sc_rw_ctxts; -- cgit v1.2.3 From 5ac40790b4708e4cb1a64ba2cb77320939bc5240 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 11 May 2018 12:51:03 -0600 Subject: libata: introduce notion of separate hardware tags Rigth now these are the same, but drivers should be using ->hw_tag for their command setup and issue. Signed-off-by: Jens Axboe Signed-off-by: Tejun Heo --- include/linux/libata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 1795fecdea17..07a8d54ba7af 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -637,7 +637,8 @@ struct ata_queued_cmd { u8 cdb[ATAPI_CDB_LEN]; unsigned long flags; /* ATA_QCFLAG_xxx */ - unsigned int tag; + unsigned int tag; /* libata core tag */ + unsigned int hw_tag; /* driver tag */ unsigned int n_elem; unsigned int orig_n_elem; -- cgit v1.2.3 From e3ed8939644166a7560a33c46f508584a7f1756a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 11 May 2018 12:51:05 -0600 Subject: libata: bump ->qc_active to a 64-bit type This is in preparation for allowing full usage of the tag space, which means that our reserved error handling command will be using an internal tag value of 32. This doesn't fit in a u32, so move to a u64. Signed-off-by: Jens Axboe Signed-off-by: Tejun Heo --- include/linux/libata.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 07a8d54ba7af..2881919b3728 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -852,7 +852,7 @@ struct ata_port { struct ata_queued_cmd qcmd[ATA_MAX_QUEUE]; unsigned long sas_tag_allocated; /* for sas tag allocation only */ - unsigned int qc_active; + u64 qc_active; int nr_active_links; /* #links with active qcs */ unsigned int sas_last_tag; /* track next tag hw expects */ @@ -1185,7 +1185,7 @@ extern void ata_id_c_string(const u16 *id, unsigned char *s, extern unsigned int ata_do_dev_read_id(struct ata_device *dev, struct ata_taskfile *tf, u16 *id); extern void ata_qc_complete(struct ata_queued_cmd *qc); -extern int ata_qc_complete_multiple(struct ata_port *ap, u32 qc_active); +extern int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active); extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd); extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, -- cgit v1.2.3 From 2e2cc676cee8962cdc82a23723df2fb394d35c64 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 11 May 2018 12:51:06 -0600 Subject: libata: use ata_tag_internal() consistently Some check for the value directly, use the provided helper instead. Also make it return a bool, since that's what it does. Signed-off-by: Jens Axboe Signed-off-by: Tejun Heo --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 2881919b3728..60ce1ba26fdd 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1491,7 +1491,7 @@ static inline unsigned int ata_tag_valid(unsigned int tag) return (tag < ATA_MAX_QUEUE) ? 1 : 0; } -static inline unsigned int ata_tag_internal(unsigned int tag) +static inline bool ata_tag_internal(unsigned int tag) { return tag == ATA_TAG_INTERNAL; } -- cgit v1.2.3 From 28361c403683c2b00d4f5e76045f3ccd299bf99d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 11 May 2018 12:51:09 -0600 Subject: libata: add extra internal command Bump the internal tag to 32, instead of stealing the last tag in our regular command space. This works just fine, since we don't actually need a separate hardware tag for this. Internal commands cannot coexist with NCQ commands. As a bonus, we get rid of the special casing of what tag to use for the internal command. This is in preparation for utilizing all 32 commands for normal IO. Signed-off-by: Jens Axboe Signed-off-by: Tejun Heo --- include/linux/libata.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 60ce1ba26fdd..1d026719461b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -125,9 +125,8 @@ enum { LIBATA_MAX_PRD = ATA_MAX_PRD / 2, LIBATA_DUMB_MAX_PRD = ATA_MAX_PRD / 4, /* Worst case */ ATA_DEF_QUEUE = 1, - /* tag ATA_MAX_QUEUE - 1 is reserved for internal commands */ ATA_MAX_QUEUE = 32, - ATA_TAG_INTERNAL = ATA_MAX_QUEUE - 1, + ATA_TAG_INTERNAL = ATA_MAX_QUEUE, ATA_SHORT_PAUSE = 16, ATAPI_MAX_DRAIN = 16 << 10, @@ -850,7 +849,7 @@ struct ata_port { unsigned int udma_mask; unsigned int cbl; /* cable type; ATA_CBL_xxx */ - struct ata_queued_cmd qcmd[ATA_MAX_QUEUE]; + struct ata_queued_cmd qcmd[ATA_MAX_QUEUE + 1]; unsigned long sas_tag_allocated; /* for sas tag allocation only */ u64 qc_active; int nr_active_links; /* #links with active qcs */ @@ -1486,14 +1485,14 @@ extern void ata_port_pbar_desc(struct ata_port *ap, int bar, ssize_t offset, const char *name); #endif -static inline unsigned int ata_tag_valid(unsigned int tag) +static inline bool ata_tag_internal(unsigned int tag) { - return (tag < ATA_MAX_QUEUE) ? 1 : 0; + return tag == ATA_TAG_INTERNAL; } -static inline bool ata_tag_internal(unsigned int tag) +static inline bool ata_tag_valid(unsigned int tag) { - return tag == ATA_TAG_INTERNAL; + return tag < ATA_MAX_QUEUE || ata_tag_internal(tag); } /* @@ -1656,7 +1655,7 @@ static inline void ata_qc_set_polling(struct ata_queued_cmd *qc) static inline struct ata_queued_cmd *__ata_qc_from_tag(struct ata_port *ap, unsigned int tag) { - if (likely(ata_tag_valid(tag))) + if (ata_tag_valid(tag)) return &ap->qcmd[tag]; return NULL; } -- cgit v1.2.3 From c06c4d793584b965bf5fa3fb107f6279643574e2 Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Thu, 10 May 2018 20:12:23 -0400 Subject: staging: iio: tsl2x7x/tsl2772: move out of staging Move the tsl2772 driver out of staging and into mainline. Signed-off-by: Brian Masney Signed-off-by: Jonathan Cameron --- include/linux/platform_data/tsl2772.h | 101 ++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) create mode 100644 include/linux/platform_data/tsl2772.h (limited to 'include/linux') diff --git a/include/linux/platform_data/tsl2772.h b/include/linux/platform_data/tsl2772.h new file mode 100644 index 000000000000..f8ade15a35e2 --- /dev/null +++ b/include/linux/platform_data/tsl2772.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Device driver for monitoring ambient light intensity (lux) + * and proximity (prox) within the TAOS TSL2772 family of devices. + * + * Copyright (c) 2012, TAOS Corporation. + * Copyright (c) 2017-2018 Brian Masney + */ + +#ifndef __TSL2772_H +#define __TSL2772_H + +struct tsl2772_lux { + unsigned int ch0; + unsigned int ch1; +}; + +/* Max number of segments allowable in LUX table */ +#define TSL2772_MAX_LUX_TABLE_SIZE 6 +/* The default LUX tables all have 3 elements. */ +#define TSL2772_DEF_LUX_TABLE_SZ 3 +#define TSL2772_DEFAULT_TABLE_BYTES (sizeof(struct tsl2772_lux) * \ + TSL2772_DEF_LUX_TABLE_SZ) + +/* Proximity diode to use */ +#define TSL2772_DIODE0 0x01 +#define TSL2772_DIODE1 0x02 +#define TSL2772_DIODE_BOTH 0x03 + +/* LED Power */ +#define TSL2772_100_mA 0x00 +#define TSL2772_50_mA 0x01 +#define TSL2772_25_mA 0x02 +#define TSL2772_13_mA 0x03 + +/** + * struct tsl2772_settings - Settings for the tsl2772 driver + * @als_time: Integration time of the ALS channel ADCs in 2.73 ms + * increments. Total integration time is + * (256 - als_time) * 2.73. + * @als_gain: Index into the tsl2772_als_gain array. + * @als_gain_trim: Default gain trim to account for aperture effects. + * @wait_time: Time between proximity and ALS cycles in 2.73 + * periods. + * @prox_time: Integration time of the proximity ADC in 2.73 ms + * increments. Total integration time is + * (256 - prx_time) * 2.73. + * @prox_gain: Index into the tsl2772_prx_gain array. + * @als_prox_config: The value of the ALS / Proximity configuration + * register. + * @als_cal_target: Known external ALS reading for calibration. + * @als_persistence: H/W Filters, Number of 'out of limits' ALS readings. + * @als_interrupt_en: Enable/Disable ALS interrupts + * @als_thresh_low: CH0 'low' count to trigger interrupt. + * @als_thresh_high: CH0 'high' count to trigger interrupt. + * @prox_persistence: H/W Filters, Number of 'out of limits' proximity + * readings. + * @prox_interrupt_en: Enable/Disable proximity interrupts. + * @prox_thres_low: Low threshold proximity detection. + * @prox_thres_high: High threshold proximity detection. + * @prox_pulse_count: Number if proximity emitter pulses. + * @prox_max_samples_cal: The number of samples that are taken when performing + * a proximity calibration. + * @prox_diode Which diode(s) to use for driving the external + * LED(s) for proximity sensing. + * @prox_power The amount of power to use for the external LED(s). + */ +struct tsl2772_settings { + int als_time; + int als_gain; + int als_gain_trim; + int wait_time; + int prox_time; + int prox_gain; + int als_prox_config; + int als_cal_target; + u8 als_persistence; + bool als_interrupt_en; + int als_thresh_low; + int als_thresh_high; + u8 prox_persistence; + bool prox_interrupt_en; + int prox_thres_low; + int prox_thres_high; + int prox_pulse_count; + int prox_max_samples_cal; + int prox_diode; + int prox_power; +}; + +/** + * struct tsl2772_platform_data - Platform callback, glass and defaults + * @platform_lux_table: Device specific glass coefficents + * @platform_default_settings: Device specific power on defaults + */ +struct tsl2772_platform_data { + struct tsl2772_lux platform_lux_table[TSL2772_MAX_LUX_TABLE_SIZE]; + struct tsl2772_settings *platform_default_settings; +}; + +#endif /* __TSL2772_H */ -- cgit v1.2.3 From 98004a78bb6cf18c260cecb49cb01e36cf6a72be Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Tue, 27 Mar 2018 10:02:01 +0000 Subject: platform_data/mlxreg: Document fixes for hotplug device Remove redunadant description of label in struct mlxreg_hotplug_device. Change location of access_mode in struct mlxreg_hotplug_device. Signed-off-by: Vadim Pasternak Signed-off-by: Darren Hart (VMware) --- include/linux/platform_data/mlxreg.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 2744cff1b297..19f5cb618c55 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -58,11 +58,10 @@ struct mlxreg_hotplug_device { * struct mlxreg_core_data - attributes control data: * * @label: attribute label; - * @label: attribute register offset; * @reg: attribute register; * @mask: attribute access mask; - * @mode: access mode; * @bit: attribute effective bit; + * @mode: access mode; * @np - pointer to node platform associated with attribute; * @hpdev - hotplug device data; * @health_cntr: dynamic device health indication counter; -- cgit v1.2.3 From 63fab6977a1f2f70ef0bc97e5de33dd5c51cb5b0 Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Sat, 5 May 2018 22:36:03 +0200 Subject: ACPI: Add missing prototype_for arch_post_acpi_subsys_init() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In commit e7ff3a47630d (x86/amd: Check for the C1E bug post ACPI subsystem init) a new function arch_post_acpi_subsys_init() was introduced. This weak function can potentially be overridden on a per arch basis, introduce the prototype for clarity. Silence the following gcc warning (W=1): init/main.c:484:20: warning: no previous prototype for ‘arch_post_acpi_subsys_init’ [-Wmissing-prototypes] Signed-off-by: Mathieu Malaterre Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 15bfb15c2fa5..cb4d7b6b085c 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -578,6 +578,7 @@ int acpi_match_platform_list(const struct acpi_platform_list *plat); extern void acpi_early_init(void); extern void acpi_subsystem_init(void); +extern void arch_post_acpi_subsys_init(void); extern int acpi_nvs_register(__u64 start, __u64 size); -- cgit v1.2.3 From 0be8153cbc2af9a96e9ab8631fc3ba23bb52dbe3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 8 May 2018 13:14:30 +0100 Subject: genirq/msi: Allow level-triggered MSIs to be exposed by MSI providers So far, MSIs have been used to signal edge-triggered interrupts, as a write is a good model for an edge (you can't "unwrite" something). On the other hand, routing zillions of wires in an SoC because you need level interrupts is a bit extreme. People have come up with a variety of schemes to support this, which involves sending two messages: one to signal the interrupt, and one to clear it. Since the kernel cannot represent this, we've ended up with side-band mechanisms that are pretty awful. Instead, let's acknoledge the requirement, and ensure that, under the right circumstances, the irq_compose_msg and irq_write_msg can take as a parameter an array of two messages instead of a pointer to a single one. We also add some checking that the compose method only clobbers the second message if the MSI domain has been created with the MSI_FLAG_LEVEL_CAPABLE flags. Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Cc: Rob Herring Cc: Jason Cooper Cc: Ard Biesheuvel Cc: Srinivas Kandagatla Cc: Thomas Petazzoni Cc: Miquel Raynal Link: https://lkml.kernel.org/r/20180508121438.11301-2-marc.zyngier@arm.com --- include/linux/msi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 1f1bbb5b4679..5839d8062dfc 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -289,6 +289,8 @@ enum { * MSI_FLAG_ACTIVATE_EARLY has been set. */ MSI_FLAG_MUST_REACTIVATE = (1 << 5), + /* Is level-triggered capable, using two messages */ + MSI_FLAG_LEVEL_CAPABLE = (1 << 6), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, -- cgit v1.2.3 From 6988e0e0d28328467e218f59589b2770675a9ebd Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 8 May 2018 13:14:31 +0100 Subject: genirq/msi: Limit level-triggered MSI to platform devices Nobody would be insane enough to try and use level triggered MSIs on PCI, but let's make sure it doesn't happen. Also, let's mandate that the irqchip backing the platform MSI domain is providing the IRQCHIP_SUPPORTS_LEVEL_MSI flag. Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Cc: Rob Herring Cc: Jason Cooper Cc: Ard Biesheuvel Cc: Srinivas Kandagatla Cc: Thomas Petazzoni Cc: Miquel Raynal Link: https://lkml.kernel.org/r/20180508121438.11301-3-marc.zyngier@arm.com --- include/linux/irq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 65916a305f3d..b2067083aa94 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -512,6 +512,7 @@ enum { IRQCHIP_SKIP_SET_WAKE = (1 << 4), IRQCHIP_ONESHOT_SAFE = (1 << 5), IRQCHIP_EOI_THREADED = (1 << 6), + IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7), }; #include -- cgit v1.2.3 From 8a22a3e1e768c309b718f99bd86f9f25a453e0dc Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 8 May 2018 13:14:33 +0100 Subject: dma-iommu: Fix compilation when !CONFIG_IOMMU_DMA MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Inclusion of include/dma-iommu.h when CONFIG_IOMMU_DMA is not selected results in the following splat: In file included from drivers/irqchip/irq-gic-v3-mbi.c:20:0: ./include/linux/dma-iommu.h:95:69: error: unknown type name ‘dma_addr_t’ static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) ^~~~~~~~~~ ./include/linux/dma-iommu.h:108:74: warning: ‘struct list_head’ declared inside parameter list will not be visible outside of this definition or declaration static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list) ^~~~~~~~~ scripts/Makefile.build:312: recipe for target 'drivers/irqchip/irq-gic-v3-mbi.o' failed Fix it by including linux/types.h. Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Cc: Rob Herring Cc: Jason Cooper Cc: Ard Biesheuvel Cc: Srinivas Kandagatla Cc: Thomas Petazzoni Cc: Miquel Raynal Link: https://lkml.kernel.org/r/20180508121438.11301-5-marc.zyngier@arm.com --- include/linux/dma-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h index 92f20832fd28..e8ca5e654277 100644 --- a/include/linux/dma-iommu.h +++ b/include/linux/dma-iommu.h @@ -17,6 +17,7 @@ #define __DMA_IOMMU_H #ifdef __KERNEL__ +#include #include #ifdef CONFIG_IOMMU_DMA -- cgit v1.2.3 From 6461934371bfc1bfe6b424b197a546b4effd0a32 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 8 May 2018 13:14:34 +0100 Subject: irqdomain: Let irq_find_host default to DOMAIN_BUS_WIRED At the beginning of times, irq_find_host() was simple. Each device node implemented at most one irq domain, and we were happy. Over time, things have become more complex, and we now have nodes implementing a plurality of domains, tagged by "bus_token". Crutially, users of irq_find_host() all expect the most basic domain to be returned, and not any other domain such as a bus-specific MSI domain. So let's change irq_find_host() to first look for a DOMAIN_BUS_WIRED domain, and only if this fails fallback to DOMAIN_BUS_ANY. Note that this is consistent with what irq_create_fwspec_mapping is already doing, see 530cbe100ef7 ("irqdomain: Allow domain lookup with DOMAIN_BUS_WIRED token"). Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Cc: Rob Herring Cc: Jason Cooper Cc: Ard Biesheuvel Cc: Srinivas Kandagatla Cc: Thomas Petazzoni Cc: Miquel Raynal Link: https://lkml.kernel.org/r/20180508121438.11301-6-marc.zyngier@arm.com --- include/linux/irqdomain.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 48c7e86bb556..dccfa65aee96 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -301,7 +301,13 @@ static inline struct irq_domain *irq_find_matching_host(struct device_node *node static inline struct irq_domain *irq_find_host(struct device_node *node) { - return irq_find_matching_host(node, DOMAIN_BUS_ANY); + struct irq_domain *d; + + d = irq_find_matching_host(node, DOMAIN_BUS_WIRED); + if (!d) + d = irq_find_matching_host(node, DOMAIN_BUS_ANY); + + return d; } /** -- cgit v1.2.3 From 505287525c24d5c78b662fd73721ad9900b91fcc Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 8 May 2018 13:14:36 +0100 Subject: irqchip/gic-v3: Add support for Message Based Interrupts as an MSI controller GICv3 offers the possibility to signal SPIs using a pair of doorbells (SETPI, CLRSPI) under the name of Message Based Interrupts (MBI). They can be used as either traditional (edge) MSIs, or the more exotic level-triggered flavour. Let's implement support for platform MSI, which is the original intent for this feature. Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Cc: Rob Herring Cc: Jason Cooper Cc: Ard Biesheuvel Cc: Srinivas Kandagatla Cc: Thomas Petazzoni Cc: Miquel Raynal Link: https://lkml.kernel.org/r/20180508121438.11301-8-marc.zyngier@arm.com --- include/linux/irqchip/arm-gic-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index f5af3b594e6e..cbb872c1b607 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -587,6 +587,7 @@ struct fwnode_handle; int its_cpu_init(void); int its_init(struct fwnode_handle *handle, struct rdists *rdists, struct irq_domain *domain); +int mbi_init(struct fwnode_handle *fwnode, struct irq_domain *parent); static inline bool gic_enable_sre(void) { -- cgit v1.2.3 From 0c8e3fe35db9b66ae0030849545030ec7c0fc45c Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sun, 13 May 2018 22:40:30 -0400 Subject: vfs: add the sb_start_intwrite_trylock() helper Needed by ext4 to test frozen fs before updating s_last_mounted. Signed-off-by: Amir Goldstein Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 760d8da1b6c7..cac41f1bad05 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1597,6 +1597,11 @@ static inline void sb_start_intwrite(struct super_block *sb) __sb_start_write(sb, SB_FREEZE_FS, true); } +static inline int sb_start_intwrite_trylock(struct super_block *sb) +{ + return __sb_start_write(sb, SB_FREEZE_FS, false); +} + extern bool inode_owner_or_capable(const struct inode *inode); -- cgit v1.2.3 From 742632d237ce180439ab4af31e9891df0df81233 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Fri, 4 May 2018 07:59:49 +0200 Subject: efi: Fix IA32/X64 Processor Error Record definition Based on UEFI 2.7 Table 255. Processor Error Record, the "Local APIC_ID" field is 8 bytes but Linux defines this field as 1 byte. Fix this in the struct cper_sec_proc_ia definition. Signed-off-by: Yazen Ghannam Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20180504060003.19618-4-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/cper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cper.h b/include/linux/cper.h index d14ef4e77c8a..4b5f8459b403 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -381,7 +381,7 @@ struct cper_sec_proc_generic { /* IA32/X64 Processor Error Section */ struct cper_sec_proc_ia { __u64 validation_bits; - __u8 lapic_id; + __u64 lapic_id; __u8 cpuid[48]; }; -- cgit v1.2.3 From f9e1bdb9f35f4f5cfa7c9025ac68c02909b6d3b1 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Fri, 4 May 2018 07:59:50 +0200 Subject: efi: Decode IA32/X64 Processor Error Section Recognize the IA32/X64 Processor Error Section. Do the section decoding in a new "cper-x86.c" file and add this to the Makefile depending on a new "UEFI_CPER_X86" config option. Print the Local APIC ID and CPUID info from the Processor Error Record. The "Processor Error Info" and "Processor Context" fields will be decoded in following patches. Based on UEFI 2.7 Table 252. Processor Error Record. Signed-off-by: Yazen Ghannam Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20180504060003.19618-5-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/cper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cper.h b/include/linux/cper.h index 4b5f8459b403..9c703a0abe6e 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -551,5 +551,7 @@ const char *cper_mem_err_unpack(struct trace_seq *, struct cper_mem_err_compact *); void cper_print_proc_arm(const char *pfx, const struct cper_sec_proc_arm *proc); +void cper_print_proc_ia(const char *pfx, + const struct cper_sec_proc_ia *proc); #endif -- cgit v1.2.3 From cb0ba793525788e40e7a9ee82de8f3b017ca4459 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 4 May 2018 07:59:59 +0200 Subject: efi: Align efi_pci_io_protocol typedefs to type naming convention In order to use the helper macros that perform type mangling with the EFI PCI I/O protocol struct typedefs, align their Linux typenames with the convention we use for definitionns that originate in the UEFI spec, and add the trailing _t to each. Tested-by: Hans de Goede Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20180504060003.19618-14-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 3016d8c456bc..56add823f190 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -397,7 +397,7 @@ typedef struct { u32 set_bar_attributes; u64 romsize; u32 romimage; -} efi_pci_io_protocol_32; +} efi_pci_io_protocol_32_t; typedef struct { u64 poll_mem; @@ -417,7 +417,7 @@ typedef struct { u64 set_bar_attributes; u64 romsize; u64 romimage; -} efi_pci_io_protocol_64; +} efi_pci_io_protocol_64_t; typedef struct { void *poll_mem; @@ -437,7 +437,7 @@ typedef struct { void *set_bar_attributes; uint64_t romsize; void *romimage; -} efi_pci_io_protocol; +} efi_pci_io_protocol_t; #define EFI_PCI_IO_ATTRIBUTE_ISA_MOTHERBOARD_IO 0x0001 #define EFI_PCI_IO_ATTRIBUTE_ISA_IO 0x0002 -- cgit v1.2.3 From a59a68fee05d46cccc4279ab6609421f7270398e Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 4 May 2018 12:42:24 +0200 Subject: sched/wait: Include in kbuild bot reported against an intermediate RT patch that the build fails with: > In file included from include/linux/completion.h:12:0, > from include/linux/rcupdate_wait.h:10, > from kernel/rcu/srcutiny.c:27: > kernel/rcu/srcutiny.c: In function 'srcu_drive_gp': > >> include/linux/swait.h:172:7: error: implicit declaration of function '___wait_is_interruptible'; did you mean '__swait_event_interruptible'? > if (___wait_is_interruptible(state) && __int) { \ That error vanishes a few patches later (in the RT queue) because wait.h is then pulled in by other means. It does not seem to surface on !RT. I think that swait should include a header file for a function/macro (___wait_is_interruptible()) it is using. Reported-by: kbuild test robot Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/20180504104224.20218-1-bigeasy@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/swait.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swait.h b/include/linux/swait.h index c98aaf677466..84f9745365ff 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -5,6 +5,7 @@ #include #include #include +#include #include /* -- cgit v1.2.3 From 943d355d7feef380e15a95892be3dff1095ef54b Mon Sep 17 00:00:00 2001 From: Rohit Jain Date: Wed, 9 May 2018 09:39:48 -0700 Subject: sched/core: Distinguish between idle_cpu() calls based on desired effect, introduce available_idle_cpu() In the following commit: 247f2f6f3c70 ("sched/core: Don't schedule threads on pre-empted vCPUs") ... we distinguish between idle_cpu() when the vCPU is not running for scheduling threads. However, the idle_cpu() function is used in other places for actually checking whether the state of the CPU is idle or not. Hence split the use of that function based on the desired return value, by introducing the available_idle_cpu() function. This fixes a (slight) regression in that initial vCPU commit, because some code paths (like the load-balancer) don't care and shouldn't care if the vCPU is preempted or not, they just want to know if there's any tasks on the CPU. Signed-off-by: Rohit Jain Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dhaval.giani@oracle.com Cc: linux-kernel@vger.kernel.org Cc: matt@codeblueprint.co.uk Cc: steven.sistare@oracle.com Cc: subhra.mazumdar@oracle.com Link: http://lkml.kernel.org/r/1525883988-10356-1-git-send-email-rohit.k.jain@oracle.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c2413703f45d..959a8588e365 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1504,6 +1504,7 @@ static inline int task_nice(const struct task_struct *p) extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); +extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern int sched_setattr(struct task_struct *, const struct sched_attr *); -- cgit v1.2.3 From 0f6f47bacba514f4e9f61de0d85940dfb41498cc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 8 May 2018 15:38:19 +0200 Subject: softirq/core: Turn default irq_cpustat_t to standard per-cpu In order to optimize and consolidate softirq mask accesses, let's convert the default irq_cpustat_t implementation to per-CPU standard API. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: Benjamin Herrenschmidt Cc: David S. Miller Cc: Fenghua Yu Cc: Heiko Carstens Cc: Helge Deller Cc: James E.J. Bottomley Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Paul Mackerras Cc: Rich Felker Cc: Sebastian Andrzej Siewior Cc: Tony Luck Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/1525786706-22846-5-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/irq_cpustat.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq_cpustat.h b/include/linux/irq_cpustat.h index 4954948d1973..ddea03c7c39d 100644 --- a/include/linux/irq_cpustat.h +++ b/include/linux/irq_cpustat.h @@ -18,8 +18,8 @@ */ #ifndef __ARCH_IRQ_STAT -extern irq_cpustat_t irq_stat[]; /* defined in asm/hardirq.h */ -#define __IRQ_STAT(cpu, member) (irq_stat[cpu].member) +DECLARE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat); /* defined in asm/hardirq.h */ +#define __IRQ_STAT(cpu, member) (per_cpu(irq_stat.member, cpu)) #endif /* arch independent irq_stat fields */ -- cgit v1.2.3 From 0fd7d86285290ccebc0dc6eb536b6b043dd6a1e4 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 8 May 2018 15:38:20 +0200 Subject: softirq/core: Consolidate default local_softirq_pending() implementations Consolidate and optimize default softirq mask API implementations. Per-CPU operations are expected to be faster and a few architectures already rely on them to implement local_softirq_pending() and related accessors/mutators. Those will be migrated to the new generic code. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: Benjamin Herrenschmidt Cc: David S. Miller Cc: Fenghua Yu Cc: Heiko Carstens Cc: Helge Deller Cc: James E.J. Bottomley Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Paul Mackerras Cc: Rich Felker Cc: Sebastian Andrzej Siewior Cc: Tony Luck Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/1525786706-22846-6-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/interrupt.h | 14 ++++++++++++++ include/linux/irq_cpustat.h | 6 +----- 2 files changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 5426627f9c55..7a11f73c5c3b 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -432,11 +432,25 @@ extern bool force_irqthreads; #define force_irqthreads (0) #endif +#ifndef local_softirq_pending + +#ifndef local_softirq_pending_ref +#define local_softirq_pending_ref irq_stat.__softirq_pending +#endif + +#define local_softirq_pending() (__this_cpu_read(local_softirq_pending_ref)) +#define set_softirq_pending(x) (__this_cpu_write(local_softirq_pending_ref, (x))) +#define or_softirq_pending(x) (__this_cpu_or(local_softirq_pending_ref, (x))) + +#else /* local_softirq_pending */ + #ifndef __ARCH_SET_SOFTIRQ_PENDING #define set_softirq_pending(x) (local_softirq_pending() = (x)) #define or_softirq_pending(x) (local_softirq_pending() |= (x)) #endif +#endif /* local_softirq_pending */ + /* Some architectures might implement lazy enabling/disabling of * interrupts. In some cases, such as stop_machine, we might want * to ensure that after a local_irq_disable(), interrupts have diff --git a/include/linux/irq_cpustat.h b/include/linux/irq_cpustat.h index ddea03c7c39d..6e8895cd4d92 100644 --- a/include/linux/irq_cpustat.h +++ b/include/linux/irq_cpustat.h @@ -22,11 +22,7 @@ DECLARE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat); /* defined in asm/hardirq.h */ #define __IRQ_STAT(cpu, member) (per_cpu(irq_stat.member, cpu)) #endif - /* arch independent irq_stat fields */ -#define local_softirq_pending() \ - __IRQ_STAT(smp_processor_id(), __softirq_pending) - - /* arch dependent irq_stat fields */ +/* arch dependent irq_stat fields */ #define nmi_count(cpu) __IRQ_STAT((cpu), __nmi_count) /* i386 */ #endif /* __irq_cpustat_h */ -- cgit v1.2.3 From 48bda43eabb8d086204f543cf8bbad696b8c6391 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 8 May 2018 15:38:26 +0200 Subject: softirq/s390: Move default mutators of overwritten softirq mask to s390 s390 is now the last architecture that entirely overwrites local_softirq_pending() and uses the according default definitions of set_softirq_pending() and or_softirq_pending(). Just move these to s390 to debloat the generic code complexity. Suggested-by: Peter Zijlstra Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: Benjamin Herrenschmidt Cc: David S. Miller Cc: Fenghua Yu Cc: Heiko Carstens Cc: Helge Deller Cc: James E.J. Bottomley Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Paul Mackerras Cc: Rich Felker Cc: Sebastian Andrzej Siewior Cc: Tony Luck Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/1525786706-22846-12-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/interrupt.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 7a11f73c5c3b..eeceac3376fc 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -442,13 +442,6 @@ extern bool force_irqthreads; #define set_softirq_pending(x) (__this_cpu_write(local_softirq_pending_ref, (x))) #define or_softirq_pending(x) (__this_cpu_or(local_softirq_pending_ref, (x))) -#else /* local_softirq_pending */ - -#ifndef __ARCH_SET_SOFTIRQ_PENDING -#define set_softirq_pending(x) (local_softirq_pending() = (x)) -#define or_softirq_pending(x) (local_softirq_pending() |= (x)) -#endif - #endif /* local_softirq_pending */ /* Some architectures might implement lazy enabling/disabling of -- cgit v1.2.3 From e7deb3c7741eaa558458696e55f57141886fcc5c Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Mon, 14 May 2018 15:47:30 +0200 Subject: drm: shmobile: remove unused MERAM support Since commit a521422ea4ae ("ARM: shmobile: mackerel: Remove Legacy C board code") MERAM functionality is unused. Remove it. Reviewed-by: Simon Horman Cc: Geert Uytterhoeven Acked-by: Laurent Pinchart Acked-by: Daniel Vetter Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/platform_data/shmob_drm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/shmob_drm.h b/include/linux/platform_data/shmob_drm.h index 7c686d335c12..ee495d707f17 100644 --- a/include/linux/platform_data/shmob_drm.h +++ b/include/linux/platform_data/shmob_drm.h @@ -18,9 +18,6 @@ #include -struct sh_mobile_meram_cfg; -struct sh_mobile_meram_info; - enum shmob_drm_clk_source { SHMOB_DRM_CLK_BUS, SHMOB_DRM_CLK_PERIPHERAL, @@ -93,7 +90,6 @@ struct shmob_drm_platform_data { struct shmob_drm_interface_data iface; struct shmob_drm_panel_data panel; struct shmob_drm_backlight_data backlight; - const struct sh_mobile_meram_cfg *meram; }; #endif /* __SHMOB_DRM_H__ */ -- cgit v1.2.3 From 2220c5b0a7fb7d7d00c9a0b1e5222a7ae1f35956 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 24 Apr 2018 21:22:04 -0400 Subject: make xattr_getsecurity() static many years overdue... Signed-off-by: Al Viro --- include/linux/xattr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index d70f77a4b62a..6dad031be3c2 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -46,7 +46,6 @@ struct xattr { size_t value_len; }; -ssize_t xattr_getsecurity(struct inode *, const char *, void *, size_t); ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t); ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); -- cgit v1.2.3 From 0fccb85ad21d65c6ee1ea912acc3f0ae4df31876 Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Thu, 10 May 2018 05:59:39 -0700 Subject: virtchnl: Whitespace and parenthesis cleanup Clean up existing instances of unnecessary parentheses in if statement and change order of conditionals to make it easier to read The opening /* should be followed by a single space and the closing */ should be preceded with a single space. Signed-off-by: Bruce Allan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index b0a7f315bfbe..212b3822d180 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -485,7 +485,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key); struct virtchnl_rss_lut { u16 vsi_id; u16 lut_entries; - u8 lut[1]; /* RSS lookup table*/ + u8 lut[1]; /* RSS lookup table */ }; VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut); @@ -819,7 +819,7 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, return VIRTCHNL_ERR_PARAM; } /* few more checks */ - if ((valid_len != msglen) || (err_msg_format)) + if (err_msg_format || valid_len != msglen) return VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH; return 0; -- cgit v1.2.3 From ae20b254306a6a47054ea0eb8444e0bd8e71fe12 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Sat, 12 May 2018 02:30:33 -0700 Subject: Drivers: hv: vmbus: enable VMBus protocol version 5.0 With VMBus protocol 5.0, we're able to better support new features, e.g. running two or more VMBus drivers simultaneously in a single VM -- note: we can't simply load the current VMBus driver twice, instead, a secondary VMBus driver must be implemented. This patch adds the support for the new VMBus protocol, which is available on new Windows hosts, by: 1) We still use SINT2 for compatibility; 2) We must use Connection ID 4 for the Initiate Contact Message, and for subsequent messages, we must use the Message Connection ID field in the host-returned VersionResponse Message. Notes for developers of the secondary VMBus driver: 1) Must use VMBus protocol 5.0 as well; 2) Must use a different SINT number that is not in use. 3) Must use Connection ID 4 for the Initiate Contact Message, and for subsequent messages, must use the Message Connection ID field in the host-returned VersionResponse Message. 4) It's possible that the primary VMBus driver using protocol version 4.0 can work with a secondary VMBus driver using protocol version 5.0, but it's recommended that both should use 5.0 for new Hyper-V features in the future. Signed-off-by: Dexuan Cui Cc: Stephen Hemminger Cc: K. Y. Srinivasan Cc: Michael Kelley Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 192ed8fbc403..11b5612dc066 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -163,6 +163,7 @@ static inline u32 hv_get_bytes_to_write(const struct hv_ring_buffer_info *rbi) * 2 . 4 (Windows 8) * 3 . 0 (Windows 8 R2) * 4 . 0 (Windows 10) + * 5 . 0 (Newer Windows 10) */ #define VERSION_WS2008 ((0 << 16) | (13)) @@ -170,10 +171,11 @@ static inline u32 hv_get_bytes_to_write(const struct hv_ring_buffer_info *rbi) #define VERSION_WIN8 ((2 << 16) | (4)) #define VERSION_WIN8_1 ((3 << 16) | (0)) #define VERSION_WIN10 ((4 << 16) | (0)) +#define VERSION_WIN10_V5 ((5 << 16) | (0)) #define VERSION_INVAL -1 -#define VERSION_CURRENT VERSION_WIN10 +#define VERSION_CURRENT VERSION_WIN10_V5 /* Make maximum size of pipe payload of 16K */ #define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384) @@ -570,7 +572,14 @@ struct vmbus_channel_initiate_contact { struct vmbus_channel_message_header header; u32 vmbus_version_requested; u32 target_vcpu; /* The VCPU the host should respond to */ - u64 interrupt_page; + union { + u64 interrupt_page; + struct { + u8 msg_sint; + u8 padding1[3]; + u32 padding2; + }; + }; u64 monitor_page1; u64 monitor_page2; } __packed; @@ -585,6 +594,19 @@ struct vmbus_channel_tl_connect_request { struct vmbus_channel_version_response { struct vmbus_channel_message_header header; u8 version_supported; + + u8 connection_state; + u16 padding; + + /* + * On new hosts that support VMBus protocol 5.0, we must use + * VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate Contact Message, + * and for subsequent messages, we must use the Message Connection ID + * field in the host-returned Version Response Message. + * + * On old hosts, we should always use VMBUS_MESSAGE_CONNECTION_ID (1). + */ + u32 msg_conn_id; } __packed; enum vmbus_channel_state { -- cgit v1.2.3 From a93e7b331568227500186a465fee3c2cb5dffd1f Mon Sep 17 00:00:00 2001 From: Hamish Martin Date: Mon, 14 May 2018 13:32:23 +1200 Subject: uio: Prevent device destruction while fds are open Prevent destruction of a uio_device while user space apps hold open file descriptors to that device. Further, access to the 'info' member of the struct uio_device is protected by spinlock. This is to ensure stale pointers to data not under control of the UIO subsystem are not dereferenced. Signed-off-by: Hamish Martin Reviewed-by: Chris Packham Signed-off-by: Greg Kroah-Hartman --- include/linux/uio_driver.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 3c85c81b0027..6c5f2074e14f 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -14,6 +14,7 @@ #ifndef _UIO_DRIVER_H_ #define _UIO_DRIVER_H_ +#include #include #include @@ -68,12 +69,13 @@ struct uio_port { struct uio_device { struct module *owner; - struct device *dev; + struct device dev; int minor; atomic_t event; struct fasync_struct *async_queue; wait_queue_head_t wait; struct uio_info *info; + spinlock_t info_lock; struct kobject *map_dir; struct kobject *portio_dir; }; -- cgit v1.2.3 From ad0dfdfd874c38d42bc4e5ef8969d86f3da0b93a Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Wed, 9 May 2018 12:06:04 -0600 Subject: coresight: Moving framework and drivers to SPDX identifier Moving all kernel side CoreSight framework and drivers to SPDX identifier. Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index d950dad5056a..c265e0468414 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -1,13 +1,6 @@ -/* Copyright (c) 2012, The Linux Foundation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 and - * only version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2012, The Linux Foundation. All rights reserved. */ #ifndef _LINUX_CORESIGHT_H -- cgit v1.2.3 From b3db17e4b864e46ad150ebef69c0e0130a1c5fca Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 11 May 2018 12:06:56 +0100 Subject: drivers: nvmem: Export nvmem_add_cells() Not all platforms use device tree. It is useful to be able to add cells to a NVMEM device from code. Export nvmem_add_cells() so making this possible. This required changing the parameters a bit, so that just the cells and the number of cells are passed, not the whole nvmem config structure. Signed-off-by: Andrew Lunn Reviewed-by: Andrey Smirnov Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index f89598bc4e1c..24def6ad09bb 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -77,6 +77,9 @@ struct nvmem_device *devm_nvmem_register(struct device *dev, int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem); +int nvmem_add_cells(struct nvmem_device *nvmem, + const struct nvmem_cell_info *info, + int ncells); #else static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) @@ -99,6 +102,14 @@ static inline int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) { return nvmem_unregister(nvmem); + +} + +static inline int nvmem_add_cells(struct nvmem_device *nvmem, + const struct nvmem_cell_info *info, + int ncells) +{ + return -ENOSYS; } #endif /* CONFIG_NVMEM */ -- cgit v1.2.3 From bdeeed098811b36d1f988521600a89a400830a4b Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Wed, 9 May 2018 11:04:48 +1000 Subject: nubus: Call bus_register unconditionally Loading a NuBus driver module on a non-NuBus machine triggers the BUG_ON(!drv->bus->p) in driver_register(), because bus_register() was not called, because it is conditional on MACH_IS_MAC. Fix the crash by calling bus_register() unconditionally. Call it from a postcore_initcall(), like other busses do. Hence, the bus type is available for device_register(), which happens in a subsys initcall, and for driver_register(), which happens in a device or module initcall. Cc: Greg Kroah-Hartman Reported-by: Michael Schmitz Tested-by: Stan Johnson Fixes: 7f86c765a6a2 ("nubus: Add support for the driver model") Signed-off-by: Finn Thain Reviewed-by: Geert Uytterhoeven Signed-off-by: Greg Kroah-Hartman --- include/linux/nubus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nubus.h b/include/linux/nubus.h index 6e8200215321..eba50b057f6f 100644 --- a/include/linux/nubus.h +++ b/include/linux/nubus.h @@ -163,7 +163,7 @@ void nubus_seq_write_rsrc_mem(struct seq_file *m, unsigned char *nubus_dirptr(const struct nubus_dirent *nd); /* Declarations relating to driver model objects */ -int nubus_bus_register(void); +int nubus_parent_device_register(void); int nubus_device_register(struct nubus_board *board); int nubus_driver_register(struct nubus_driver *ndrv); void nubus_driver_unregister(struct nubus_driver *ndrv); -- cgit v1.2.3 From 7dcc01343e483efda0882456f8361f061a5f416d Mon Sep 17 00:00:00 2001 From: Andres Rodriguez Date: Thu, 10 May 2018 13:08:45 -0700 Subject: firmware: add firmware_request_nowarn() - load firmware without warnings Currently the firmware loader only exposes one silent path for querying optional firmware, and that is firmware_request_direct(). This function also disables the sysfs fallback mechanism, which might not always be the desired behaviour [0]. This patch introduces a variations of request_firmware() that enable the caller to disable the undesired warning messages but enables the sysfs fallback mechanism. This is equivalent to adding FW_OPT_NO_WARN to the old behaviour. [0]: https://git.kernel.org/linus/c0cc00f250e1 Signed-off-by: Andres Rodriguez Reviewed-by: Kees Cook Acked-by: Luis R. Rodriguez [mcgrof: used the old API calls as the full rename is not done yet, and add the caller for when FW_LOADER is disabled, enhance documentation ] Signed-off-by: Luis R. Rodriguez Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 41050417cafb..2dd566c91d44 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -42,6 +42,8 @@ struct builtin_fw { #if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE)) int request_firmware(const struct firmware **fw, const char *name, struct device *device); +int firmware_request_nowarn(const struct firmware **fw, const char *name, + struct device *device); int request_firmware_nowait( struct module *module, bool uevent, const char *name, struct device *device, gfp_t gfp, void *context, @@ -59,6 +61,14 @@ static inline int request_firmware(const struct firmware **fw, { return -EINVAL; } + +static inline int firmware_request_nowarn(const struct firmware **fw, + const char *name, + struct device *device) +{ + return -EINVAL; +} + static inline int request_firmware_nowait( struct module *module, bool uevent, const char *name, struct device *device, gfp_t gfp, void *context, -- cgit v1.2.3 From ff005a066240efb73ae29a2bb9269ae726bc2eae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 9 May 2018 09:54:05 +0200 Subject: block: sanitize blk_get_request calling conventions Switch everyone to blk_get_request_flags, and then rename blk_get_request_flags to blk_get_request. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e42d510daf3c..f3999719f828 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -976,11 +976,8 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_init_request_from_bio(struct request *req, struct bio *bio); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); -extern struct request *blk_get_request_flags(struct request_queue *, - unsigned int op, - blk_mq_req_flags_t flags); extern struct request *blk_get_request(struct request_queue *, unsigned int op, - gfp_t gfp_mask); + blk_mq_req_flags_t flags); extern void blk_requeue_request(struct request_queue *, struct request *); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, -- cgit v1.2.3 From 9e2aee80c78d5084e0c58745e9762c29da6bd53f Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 11 May 2018 12:15:30 -0500 Subject: PCI: Move private DT related functions into private header The functions in linux/of_pci.h are primarily used by host bridge drivers, so they can be private to drivers/pci/. The remaining functions are still used mostly in host bridge drivers that still live in arch specific code. Hopefully someday, those will get moved into drivers/pci as well. Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Reviewed-by: Linus Walleij Acked-by: Jingoo Han --- include/linux/of_pci.h | 34 ---------------------------------- 1 file changed, 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 091033a6b836..e83d87fc5673 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -13,9 +13,6 @@ struct device_node; struct device_node *of_pci_find_child_device(struct device_node *parent, unsigned int devfn); int of_pci_get_devfn(struct device_node *np); -int of_pci_parse_bus_range(struct device_node *node, struct resource *res); -int of_get_pci_domain_nr(struct device_node *node); -int of_pci_get_max_link_speed(struct device_node *node); void of_pci_check_probe_only(void); int of_pci_map_rid(struct device_node *np, u32 rid, const char *map_name, const char *map_mask_name, @@ -32,18 +29,6 @@ static inline int of_pci_get_devfn(struct device_node *np) return -EINVAL; } -static inline int -of_pci_parse_bus_range(struct device_node *node, struct resource *res) -{ - return -EINVAL; -} - -static inline int -of_get_pci_domain_nr(struct device_node *node) -{ - return -1; -} - static inline int of_pci_map_rid(struct device_node *np, u32 rid, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out) @@ -51,12 +36,6 @@ static inline int of_pci_map_rid(struct device_node *np, u32 rid, return -EINVAL; } -static inline int -of_pci_get_max_link_speed(struct device_node *node) -{ - return -EINVAL; -} - static inline void of_pci_check_probe_only(void) { } #endif @@ -70,17 +49,4 @@ of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) } #endif -#if defined(CONFIG_OF_ADDRESS) -int of_pci_get_host_bridge_resources(struct device_node *dev, - unsigned char busno, unsigned char bus_max, - struct list_head *resources, resource_size_t *io_base); -#else -static inline int of_pci_get_host_bridge_resources(struct device_node *dev, - unsigned char busno, unsigned char bus_max, - struct list_head *resources, resource_size_t *io_base) -{ - return -EINVAL; -} -#endif - #endif -- cgit v1.2.3 From 2724273e8fd00b512596a77ee063f49b25f36507 Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Wed, 2 May 2018 15:17:17 +0530 Subject: vmcore: add API to collect hardware dump in second kernel The sequence of actions done by device drivers to append their device specific hardware/firmware logs to /proc/vmcore are as follows: 1. During probe (before hardware is initialized), device drivers register to the vmcore module (via vmcore_add_device_dump()), with callback function, along with buffer size and log name needed for firmware/hardware log collection. 2. vmcore module allocates the buffer with requested size. It adds an Elf note and invokes the device driver's registered callback function. 3. Device driver collects all hardware/firmware logs into the buffer and returns control back to vmcore module. Ensure that the device dump buffer size is always aligned to page size so that it can be mmaped. Also, rename alloc_elfnotes_buf() to vmcore_alloc_buf() to make it more generic and reserve NT_VMCOREDD note type to indicate vmcore device dump. Suggested-by: Eric Biederman . Signed-off-by: Rahul Lakkireddy Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- include/linux/crash_dump.h | 18 ++++++++++++++++++ include/linux/kcore.h | 6 ++++++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index f7ac2aa93269..3e4ba9d753c8 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -5,6 +5,7 @@ #include #include #include +#include #include /* for pgprot_t */ @@ -93,4 +94,21 @@ static inline bool is_kdump_kernel(void) { return 0; } #endif /* CONFIG_CRASH_DUMP */ extern unsigned long saved_max_pfn; + +/* Device Dump information to be filled by drivers */ +struct vmcoredd_data { + char dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Unique name of the dump */ + unsigned int size; /* Size of the dump */ + /* Driver's registered callback to be invoked to collect dump */ + int (*vmcoredd_callback)(struct vmcoredd_data *data, void *buf); +}; + +#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP +int vmcore_add_device_dump(struct vmcoredd_data *data); +#else +static inline int vmcore_add_device_dump(struct vmcoredd_data *data) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ #endif /* LINUX_CRASHDUMP_H */ diff --git a/include/linux/kcore.h b/include/linux/kcore.h index 80db19d3a505..8de55e4b5ee9 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -28,6 +28,12 @@ struct vmcore { loff_t offset; }; +struct vmcoredd_node { + struct list_head list; /* List of dumps */ + void *buf; /* Buffer containing device's dump */ + unsigned int size; /* Size of the buffer */ +}; + #ifdef CONFIG_PROC_KCORE extern void kclist_add(struct kcore_list *, void *, size_t, int type); #else -- cgit v1.2.3 From c1a67fefd0546a5552289c65fe31b1d60e64b643 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 4 May 2015 16:52:20 -0700 Subject: mempool: Add mempool_init()/mempool_exit() Allows mempools to be embedded in other structs, getting rid of a pointer indirection from allocation fastpaths. mempool_exit() is safe to call on an uninitialized but zeroed mempool. Signed-off-by: Kent Overstreet Signed-off-by: Jens Axboe --- include/linux/mempool.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mempool.h b/include/linux/mempool.h index b51f5c430c26..0c964ac107c2 100644 --- a/include/linux/mempool.h +++ b/include/linux/mempool.h @@ -25,6 +25,18 @@ typedef struct mempool_s { wait_queue_head_t wait; } mempool_t; +static inline bool mempool_initialized(mempool_t *pool) +{ + return pool->elements != NULL; +} + +void mempool_exit(mempool_t *pool); +int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data, + gfp_t gfp_mask, int node_id); +int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data); + extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, @@ -43,6 +55,14 @@ extern void mempool_free(void *element, mempool_t *pool); */ void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data); void mempool_free_slab(void *element, void *pool_data); + +static inline int +mempool_init_slab_pool(mempool_t *pool, int min_nr, struct kmem_cache *kc) +{ + return mempool_init(pool, min_nr, mempool_alloc_slab, + mempool_free_slab, (void *) kc); +} + static inline mempool_t * mempool_create_slab_pool(int min_nr, struct kmem_cache *kc) { @@ -56,6 +76,13 @@ mempool_create_slab_pool(int min_nr, struct kmem_cache *kc) */ void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data); void mempool_kfree(void *element, void *pool_data); + +static inline int mempool_init_kmalloc_pool(mempool_t *pool, int min_nr, size_t size) +{ + return mempool_init(pool, min_nr, mempool_kmalloc, + mempool_kfree, (void *) size); +} + static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size) { return mempool_create(min_nr, mempool_kmalloc, mempool_kfree, @@ -68,6 +95,13 @@ static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size) */ void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data); void mempool_free_pages(void *element, void *pool_data); + +static inline int mempool_init_page_pool(mempool_t *pool, int min_nr, int order) +{ + return mempool_init(pool, min_nr, mempool_alloc_pages, + mempool_free_pages, (void *)(long)order); +} + static inline mempool_t *mempool_create_page_pool(int min_nr, int order) { return mempool_create(min_nr, mempool_alloc_pages, mempool_free_pages, -- cgit v1.2.3 From 8aa6ba2f6e3deaff70e517e3cfbf38d1105f9d4f Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 8 May 2018 21:33:50 -0400 Subject: block: Convert bio_set to mempool_init() Minor performance improvement by getting rid of pointer indirections from allocation/freeing fastpaths. Signed-off-by: Kent Overstreet Signed-off-by: Jens Axboe --- include/linux/bio.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index ce547a25e8ae..720f7261d042 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -412,7 +412,7 @@ enum { BIOSET_NEED_RESCUER = BIT(1), }; extern void bioset_free(struct bio_set *); -extern mempool_t *biovec_create_pool(int pool_entries); +extern int biovec_init_pool(mempool_t *pool, int pool_entries); extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *); extern void bio_put(struct bio *); @@ -722,11 +722,11 @@ struct bio_set { struct kmem_cache *bio_slab; unsigned int front_pad; - mempool_t *bio_pool; - mempool_t *bvec_pool; + mempool_t bio_pool; + mempool_t bvec_pool; #if defined(CONFIG_BLK_DEV_INTEGRITY) - mempool_t *bio_integrity_pool; - mempool_t *bvec_integrity_pool; + mempool_t bio_integrity_pool; + mempool_t bvec_integrity_pool; #endif /* -- cgit v1.2.3 From 917a38c71af82185c39e31589587591fa764fb85 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 8 May 2018 21:33:51 -0400 Subject: block: Add bioset_init()/bioset_exit() Similarly to mempool_init()/mempool_exit(), take a pointer indirection out of allocation/freeing by allowing biosets to be embedded in other structs. Signed-off-by: Kent Overstreet Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 720f7261d042..fa3cf94a5015 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -406,6 +406,8 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors, return bio_split(bio, sectors, gfp, bs); } +extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); +extern void bioset_exit(struct bio_set *); extern struct bio_set *bioset_create(unsigned int, unsigned int, int flags); enum { BIOSET_NEED_BVECS = BIT(0), -- cgit v1.2.3 From f4f8154a08bc5801a3f130db69e370d249e791ab Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 8 May 2018 21:33:52 -0400 Subject: block: Use bioset_init() for fs_bio_set Minor optimization - remove a pointer indirection when using fs_bio_set. Signed-off-by: Kent Overstreet Signed-off-by: Jens Axboe --- include/linux/bio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index fa3cf94a5015..91b02520e2f8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -423,11 +423,11 @@ extern void __bio_clone_fast(struct bio *, struct bio *); extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs); -extern struct bio_set *fs_bio_set; +extern struct bio_set fs_bio_set; static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) { - return bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set); + return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set); } static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs) -- cgit v1.2.3 From 38a72dac48f631c2a90b831a3847cde116f21d3a Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 8 May 2018 21:33:53 -0400 Subject: block: Add bio_copy_data_iter(), zero_fill_bio_iter() Add versions that take bvec_iter args instead of using bio->bi_iter - to be used by bcachefs. Signed-off-by: Kent Overstreet Signed-off-by: Jens Axboe --- include/linux/bio.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 91b02520e2f8..5a6ee955a8ac 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -67,8 +67,12 @@ #define bio_multiple_segments(bio) \ ((bio)->bi_iter.bi_size != bio_iovec(bio).bv_len) -#define bio_sectors(bio) ((bio)->bi_iter.bi_size >> 9) -#define bio_end_sector(bio) ((bio)->bi_iter.bi_sector + bio_sectors((bio))) + +#define bvec_iter_sectors(iter) ((iter).bi_size >> 9) +#define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter))) + +#define bio_sectors(bio) bvec_iter_sectors((bio)->bi_iter) +#define bio_end_sector(bio) bvec_iter_end_sector((bio)->bi_iter) /* * Return the data direction, READ or WRITE. @@ -501,6 +505,8 @@ static inline void bio_flush_dcache_pages(struct bio *bi) } #endif +extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter dst_iter, + struct bio *src, struct bvec_iter src_iter); extern void bio_copy_data(struct bio *dst, struct bio *src); extern void bio_free_pages(struct bio *bio); @@ -509,7 +515,13 @@ extern struct bio *bio_copy_user_iov(struct request_queue *, struct iov_iter *, gfp_t); extern int bio_uncopy_user(struct bio *); -void zero_fill_bio(struct bio *bio); +void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter); + +static inline void zero_fill_bio(struct bio *bio) +{ + zero_fill_bio_iter(bio, bio->bi_iter); +} + extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); -- cgit v1.2.3 From 45db54d58de0b7171fe1f0d1dfc14378e464949e Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 8 May 2018 21:33:54 -0400 Subject: block: Split out bio_list_copy_data() Found a bug (with ASAN) where we were passing a bio to bio_copy_data() with bi_next not NULL, when it should have been - a driver had left bi_next set to something after calling bio_endio(). Since the normal case is only copying single bios, split out bio_list_copy_data() to avoid more bugs like this in the future. Signed-off-by: Kent Overstreet Signed-off-by: Jens Axboe --- include/linux/bio.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 5a6ee955a8ac..98b175cc00d5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -505,9 +505,10 @@ static inline void bio_flush_dcache_pages(struct bio *bi) } #endif -extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter dst_iter, - struct bio *src, struct bvec_iter src_iter); +extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, + struct bio *src, struct bvec_iter *src_iter); extern void bio_copy_data(struct bio *dst, struct bio *src); +extern void bio_list_copy_data(struct bio *dst, struct bio *src); extern void bio_free_pages(struct bio *bio); extern struct bio *bio_copy_user_iov(struct request_queue *, -- cgit v1.2.3 From f0b752168d7091f38e7d61a80de2542e8b71d266 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Sat, 12 May 2018 21:58:19 -0400 Subject: audit: convert sessionid unset to a macro Use a macro, "AUDIT_SID_UNSET", to replace each instance of initialization and comparison to an audit session ID. Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index b639cf1f55ff..2d15bce7aa3c 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -510,7 +510,7 @@ static inline kuid_t audit_get_loginuid(struct task_struct *tsk) } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { - return -1; + return AUDIT_SID_UNSET; } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } -- cgit v1.2.3 From 919b7308fcc452cd4e282bab389c33384a9f3790 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 9 May 2018 12:17:52 +0200 Subject: PM / Domains: Allow a better error handling of dev_pm_domain_attach() The callers of dev_pm_domain_attach() currently checks the returned error code for -EPROBE_DEFER and needs to ignore other error codes. This is an unnecessary limitation, which also leads to a rather strange behaviour in the error path. Address this limitation, by changing the return codes from acpi_dev_pm_attach() and genpd_dev_pm_attach(). More precisely, let them return 0, when no PM domain is needed for the device and then return 1, in case the device was successfully attached to its PM domain. In this way, dev_pm_domain_attach(), gets a better understanding of what happens in the attach attempts and also allowing its caller to better act on real errors codes. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 +- include/linux/pm_domain.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 15bfb15c2fa5..c01675b3d93f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -899,7 +899,7 @@ static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) { - return -ENODEV; + return 0; } #endif diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 04dbef9847d3..ab1854863a8c 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -280,7 +280,7 @@ static inline int of_genpd_parse_idle_states(struct device_node *dn, static inline int genpd_dev_pm_attach(struct device *dev) { - return -ENODEV; + return 0; } static inline @@ -297,7 +297,7 @@ extern void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd); #else static inline int dev_pm_domain_attach(struct device *dev, bool power_on) { - return -ENODEV; + return 0; } static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {} static inline void dev_pm_domain_set(struct device *dev, -- cgit v1.2.3 From cdfb6b341f0f2409aba24b84f3b4b2bba50be5c5 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Sat, 12 May 2018 21:58:20 -0400 Subject: audit: use inline function to get audit context Recognizing that the audit context is an internal audit value, use an access function to retrieve the audit context pointer for the task rather than reaching directly into the task struct to get it. Signed-off-by: Richard Guy Briggs [PM: merge fuzz in auditsc.c and selinuxfs.c, checkpatch.pl fixes] Signed-off-by: Paul Moore --- include/linux/audit.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 2d15bce7aa3c..831a4684df40 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -237,9 +237,14 @@ extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); +static inline struct audit_context *audit_context(void) +{ + return current->audit_context; +} + static inline bool audit_dummy_context(void) { - void *p = current->audit_context; + void *p = audit_context(); return !p || *(int *)p; } static inline void audit_free(struct task_struct *task) @@ -251,12 +256,12 @@ static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { - if (unlikely(current->audit_context)) + if (unlikely(audit_context())) __audit_syscall_entry(major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) { - if (unlikely(current->audit_context)) { + if (unlikely(audit_context())) { int success = is_syscall_success(pt_regs); long return_code = regs_return_value(pt_regs); @@ -464,6 +469,10 @@ static inline bool audit_dummy_context(void) { return true; } +static inline struct audit_context *audit_context(void) +{ + return NULL; +} static inline struct filename *audit_reusename(const __user char *name) { return NULL; -- cgit v1.2.3 From c0b0ae8a871bc2ebbe1ff9c9871efcf88994ffec Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Sat, 12 May 2018 21:58:21 -0400 Subject: audit: use inline function to set audit context Recognizing that the audit context is an internal audit value, use an access function to set the audit context pointer for the task rather than reaching directly into the task struct to set it. Signed-off-by: Richard Guy Briggs [PM: merge fuzz in audit.h] Signed-off-by: Paul Moore --- include/linux/audit.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 831a4684df40..69c78477590b 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -237,6 +237,11 @@ extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); +static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) +{ + task->audit_context = ctx; +} + static inline struct audit_context *audit_context(void) { return current->audit_context; @@ -469,6 +474,8 @@ static inline bool audit_dummy_context(void) { return true; } +static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) +{ } static inline struct audit_context *audit_context(void) { return NULL; -- cgit v1.2.3 From 1d38f5d828b45546e53095a172c77556642a8a04 Mon Sep 17 00:00:00 2001 From: Jorge Sanjuan Date: Fri, 11 May 2018 16:25:36 +0100 Subject: ALSA: usb-audio: UAC3 Add support for connector insertion. This adds support for the UAC3 insertion controls. The status is reported as a boolean value in the same way it used to do for UAC2. Hence, the presence of any connector in the response will make the control saying the jack is connected. The UAC2 support for this control has been moved to a dedicated control for connectors as both UAC2 and UAC3 follow a specific Control Request Parameter Block for this control. This parameter block for UAC3 could not be read in the same simplistic manner as in UAC2. This implementation is not requesting additional information from the HIGH CAPABILITY Connectors descriptor. Tested with an UAC3 device with UAC2 as legacy configuration. The connector status can be read with `amixer` and the interrupt is also caught with `alsactl monitor`. Signed-off-by: Jorge Sanjuan Reviewed-by: Ruslan Bilovol Tested-by: Ruslan Bilovol Signed-off-by: Takashi Iwai --- include/linux/usb/audio-v2.h | 7 +++++++ include/linux/usb/audio-v3.h | 14 ++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index aaafecf073ff..a96ed2ce3254 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -189,6 +189,13 @@ struct uac2_iso_endpoint_descriptor { #define UAC2_CONTROL_DATA_OVERRUN (3 << 2) #define UAC2_CONTROL_DATA_UNDERRUN (3 << 4) +/* 5.2.5.4.2 Connector Control Parameter Block */ +struct uac2_connectors_ctl_blk { + __u8 bNrChannels; + __le32 bmChannelConfig; + __u8 iChannelNames; +} __attribute__((packed)); + /* 6.1 Interrupt Data Message */ #define UAC2_INTERRUPT_DATA_MSG_VENDOR (1 << 0) diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h index 38add1dedf2e..a710e28b5215 100644 --- a/include/linux/usb/audio-v3.h +++ b/include/linux/usb/audio-v3.h @@ -221,6 +221,12 @@ struct uac3_iso_endpoint_descriptor { __le16 wLockDelay; } __attribute__((packed)); +/* 5.2.1.6.1 INSERTION CONTROL PARAMETER BLOCK */ +struct uac3_insertion_ctl_blk { + __u8 bSize; + __u8 bmConInserted; +} __attribute__ ((packed)); + /* 6.1 INTERRUPT DATA MESSAGE */ struct uac3_interrupt_data_msg { __u8 bInfo; @@ -392,6 +398,14 @@ struct uac3_interrupt_data_msg { #define UAC3_AC_ACTIVE_INTERFACE_CONTROL 0x01 #define UAC3_AC_POWER_DOMAIN_CONTROL 0x02 +/* A.23.5 TERMINAL CONTROL SELECTORS */ +#define UAC3_TE_UNDEFINED 0x00 +#define UAC3_TE_INSERTION 0x01 +#define UAC3_TE_OVERLOAD 0x02 +#define UAC3_TE_UNDERFLOW 0x03 +#define UAC3_TE_OVERFLOW 0x04 +#define UAC3_TE_LATENCY 0x05 + /* BADD predefined Unit/Terminal values */ #define UAC3_BADD_IT_ID1 1 /* Input Terminal ID1: bTerminalID = 1 */ #define UAC3_BADD_FU_ID2 2 /* Feature Unit ID2: bUnitID = 2 */ -- cgit v1.2.3 From b7e4aadef28f217de8907eec60a964328797a2be Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Mon, 14 May 2018 16:01:27 -0700 Subject: locking/spinlocks: Document the semantics of spin_is_locked() There appeared to be a certain, recurrent uncertainty concerning the semantics of spin_is_locked(), likely a consequence of the fact that this semantics remains undocumented or that it has been historically linked to the (likewise unclear) semantics of spin_unlock_wait(). A recent auditing [1] of the callers of the primitive confirmed that none of them are relying on particular ordering guarantees; document this semantics by adding a docbook header to spin_is_locked(). Also, describe behaviors specific to certain CONFIG_SMP=n builds. [1] https://marc.info/?l=linux-kernel&m=151981440005264&w=2 https://marc.info/?l=linux-kernel&m=152042843808540&w=2 https://marc.info/?l=linux-kernel&m=152043346110262&w=2 Co-Developed-by: Andrea Parri Co-Developed-by: Alan Stern Co-Developed-by: David Howells Signed-off-by: Andrea Parri Signed-off-by: Alan Stern Signed-off-by: David Howells Signed-off-by: Paul E. McKenney Acked-by: Randy Dunlap Cc: Akira Yokosawa Cc: Andrew Morton Cc: Boqun Feng Cc: Jade Alglave Cc: Linus Torvalds Cc: Luc Maranget Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arch@vger.kernel.org Cc: parri.andrea@gmail.com Link: http://lkml.kernel.org/r/1526338889-7003-1-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/spinlock.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 4894d322d258..1e8a46435838 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -380,6 +380,24 @@ static __always_inline int spin_trylock_irq(spinlock_t *lock) raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) +/** + * spin_is_locked() - Check whether a spinlock is locked. + * @lock: Pointer to the spinlock. + * + * This function is NOT required to provide any memory ordering + * guarantees; it could be used for debugging purposes or, when + * additional synchronization is needed, accompanied with other + * constructs (memory barriers) enforcing the synchronization. + * + * Returns: 1 if @lock is locked, 0 otherwise. + * + * Note that the function only tells you that the spinlock is + * seen to be locked, not that it is locked on your CPU. + * + * Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n, + * the return value is always 0 (see include/linux/spinlock_up.h). + * Therefore you should not rely heavily on the return value. + */ static __always_inline int spin_is_locked(spinlock_t *lock) { return raw_spin_is_locked(&lock->rlock); -- cgit v1.2.3 From 1362ae43c503a4e333ab6948fc4c6e0e794e1558 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Mon, 14 May 2018 16:01:29 -0700 Subject: locking/spinlocks: Clean up comment and #ifndef for {,queued_}spin_is_locked() Removes "#ifndef queued_spin_is_locked" from the generic code: this is unused and it's reasonable to conclude that it will continue to be unused. Also removes the comment about spin_is_locked() from mutex_is_locked(): the comment remains valid but not particularly useful. Suggested-by: Will Deacon Signed-off-by: Andrea Parri Signed-off-by: Paul E. McKenney Acked-by: Will Deacon Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akiyks@gmail.com Cc: boqun.feng@gmail.com Cc: dhowells@redhat.com Cc: j.alglave@ucl.ac.uk Cc: linux-arch@vger.kernel.org Cc: luc.maranget@inria.fr Cc: npiggin@gmail.com Cc: parri.andrea@gmail.com Cc: stern@rowland.harvard.edu Link: http://lkml.kernel.org/r/1526338889-7003-3-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/mutex.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 14bc0d5d0ee5..3093dd162424 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -146,9 +146,6 @@ extern void __mutex_init(struct mutex *lock, const char *name, */ static inline bool mutex_is_locked(struct mutex *lock) { - /* - * XXX think about spin_is_locked - */ return __mutex_owner(lock) != NULL; } -- cgit v1.2.3 From 60622d68227d6d71fdfba5fb39f7f3d44cdd8815 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 3 May 2018 17:06:21 -0700 Subject: x86/asm/memcpy_mcsafe: Return bytes remaining Machine check safe memory copies are currently deployed in the pmem driver whenever reading from persistent memory media, so that -EIO is returned rather than triggering a kernel panic. While this protects most pmem accesses, it is not complete in the filesystem-dax case. When filesystem-dax is enabled reads may bypass the block layer and the driver via dax_iomap_actor() and its usage of copy_to_iter(). In preparation for creating a copy_to_iter() variant that can handle machine checks, teach memcpy_mcsafe() to return the number of bytes remaining rather than -EFAULT when an exception occurs. Co-developed-by: Tony Luck Signed-off-by: Dan Williams Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tony Luck Cc: hch@lst.de Cc: linux-fsdevel@vger.kernel.org Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/152539238119.31796.14318473522414462886.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar --- include/linux/string.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index dd39a690c841..4a5a0eb7df51 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -147,8 +147,8 @@ extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCPY_MCSAFE -static inline __must_check int memcpy_mcsafe(void *dst, const void *src, - size_t cnt) +static inline __must_check unsigned long memcpy_mcsafe(void *dst, + const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; -- cgit v1.2.3 From 8780356ef630aa577fd4daa49e49b79674711fae Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 3 May 2018 17:06:31 -0700 Subject: x86/asm/memcpy_mcsafe: Define copy_to_iter_mcsafe() Use the updated memcpy_mcsafe() implementation to define copy_user_mcsafe() and copy_to_iter_mcsafe(). The most significant difference from typical copy_to_iter() is that the ITER_KVEC and ITER_BVEC iterator types can fail to complete a full transfer. Signed-off-by: Dan Williams Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tony Luck Cc: hch@lst.de Cc: linux-fsdevel@vger.kernel.org Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/152539239150.31796.9189779163576449784.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar --- include/linux/uio.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index e67e12adb136..f5766e853a77 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -154,6 +154,12 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #define _copy_from_iter_flushcache _copy_from_iter_nocache #endif +#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE +size_t _copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i); +#else +#define _copy_to_iter_mcsafe _copy_to_iter +#endif + static __always_inline __must_check size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { @@ -163,6 +169,15 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) return _copy_from_iter_flushcache(addr, bytes, i); } +static __always_inline __must_check +size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, false))) + return 0; + else + return _copy_to_iter_mcsafe(addr, bytes, i); +} + size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); -- cgit v1.2.3 From 655016dc2d30379a417404ae88df9bfb7ede38e6 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 4 May 2018 06:59:42 +1000 Subject: usb/gadget: Constify usb_gadget_get_string "table" argument The table is never modified by the function. This allows us to use it on a statically defined table that is marked const. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 847f423ad9b3..e5cd84a0f84a 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -763,7 +763,7 @@ struct usb_gadget_string_container { }; /* put descriptor for string with that id into buf (buflen >= 256) */ -int usb_gadget_get_string(struct usb_gadget_strings *table, int id, u8 *buf); +int usb_gadget_get_string(const struct usb_gadget_strings *table, int id, u8 *buf); /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From d2b9889f77165891378d79efd40d74e0162f56d8 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 Apr 2018 01:02:58 +0300 Subject: usb: tegra: Move utmi-pads reset from ehci-tegra to tegra-phy UTMI pads are shared by USB controllers and reset of UTMI pads is shared with the reset of USB1 controller. Currently reset of UTMI pads is done by the EHCI driver and ChipIdea UDC works because EHCI driver always happen to be probed first. Move reset controls from ehci-tegra to tegra-phy in order to resolve the problem. Signed-off-by: Dmitry Osipenko Signed-off-by: Felipe Balbi --- include/linux/usb/tegra_usb_phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d641ea1660b7..0c5c3ea8b2d7 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -17,6 +17,7 @@ #define __TEGRA_USB_PHY_H #include +#include #include /* @@ -76,6 +77,7 @@ struct tegra_usb_phy { bool is_legacy_phy; bool is_ulpi_phy; int reset_gpio; + struct reset_control *pad_rst; }; void tegra_usb_phy_preresume(struct usb_phy *phy); -- cgit v1.2.3 From 2f8519f6ed42cd332ec442e3b9edc0575bc4df48 Mon Sep 17 00:00:00 2001 From: Romain Izard Date: Fri, 11 May 2018 12:19:55 +0200 Subject: usb: gadget: udc: atmel: Remove obsolete include The include defines the private platform_data structure used with AVR platforms. It has no user since 7c55984e191f. Remove it. Acked-by: Ludovic Desroches Acked-by: Nicolas Ferre Signed-off-by: Romain Izard Signed-off-by: Felipe Balbi --- include/linux/usb/atmel_usba_udc.h | 24 ------------------------ 1 file changed, 24 deletions(-) delete mode 100644 include/linux/usb/atmel_usba_udc.h (limited to 'include/linux') diff --git a/include/linux/usb/atmel_usba_udc.h b/include/linux/usb/atmel_usba_udc.h deleted file mode 100644 index 9bb00df3b53f..000000000000 --- a/include/linux/usb/atmel_usba_udc.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Platform data definitions for Atmel USBA gadget driver. - */ -#ifndef __LINUX_USB_USBA_H -#define __LINUX_USB_USBA_H - -struct usba_ep_data { - char *name; - int index; - int fifo_size; - int nr_banks; - int can_dma; - int can_isoc; -}; - -struct usba_platform_data { - int vbus_pin; - int vbus_pin_inverted; - int num_ep; - struct usba_ep_data ep[0]; -}; - -#endif /* __LINUX_USB_USBA_H */ -- cgit v1.2.3 From 4fad8868afe7b168c34fab3d959d875f4f8b3624 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 25 Mar 2018 14:49:01 +0200 Subject: i2c: Get rid of i2c_board_info->archdata The only user of i2c_board_info->archdata is the OF parsing code and it just pass a zero-initialized object which has the same effect as leaving ->archdata to NULL since the client object is allocated with kzalloc(). Get rid of this useless field. Signed-off-by: Boris Brezillon Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 44ad14e016b5..aeb655772ef8 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -394,7 +394,6 @@ static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } * @addr: stored in i2c_client.addr * @dev_name: Overrides the default - dev_name if set * @platform_data: stored in i2c_client.dev.platform_data - * @archdata: copied into i2c_client.dev.archdata * @of_node: pointer to OpenFirmware device node * @fwnode: device node supplied by the platform firmware * @properties: additional device properties for the device @@ -419,7 +418,6 @@ struct i2c_board_info { unsigned short addr; const char *dev_name; void *platform_data; - struct dev_archdata *archdata; struct device_node *of_node; struct fwnode_handle *fwnode; const struct property_entry *properties; -- cgit v1.2.3 From c164d6abf3841ffacfdb757c10616f9cb1f67276 Mon Sep 17 00:00:00 2001 From: Rodrigo Rivas Costa Date: Mon, 16 Apr 2018 14:27:02 +0200 Subject: HID: add driver for Valve Steam Controller There are two ways to connect the Steam Controller: directly to the USB or with the USB wireless adapter. Both methods are similar, but the wireless adapter can connect up to 4 devices at the same time. The wired device will appear as 3 interfaces: a virtual mouse, a virtual keyboard and a custom HID device. The wireless device will appear as 5 interfaces: a virtual keyboard and 4 custom HID devices, that will remain silent until a device is actually connected. The custom HID device has a report descriptor with all vendor specific usages, so the hid-generic is not very useful. In a PC/SteamBox Valve Steam Client provices a software translation by using hidraw and a creates a uinput virtual gamepad and XTest keyboard/mouse. This driver intercepts the hidraw usage, so it can get out of the way when the Steam Client is in use. Signed-off-by: Rodrigo Rivas Costa Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 26240a22978a..08d92bb005fd 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -367,6 +367,7 @@ struct hid_item { #define HID_GROUP_RMI 0x0100 #define HID_GROUP_WACOM 0x0101 #define HID_GROUP_LOGITECH_DJ_DEVICE 0x0102 +#define HID_GROUP_STEAM 0x0103 /* * HID protocol status -- cgit v1.2.3 From ab96746aaa344fb720a198245a837e266fad3b62 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Fri, 4 May 2018 13:08:18 +0800 Subject: iommu/vt-d: Clean up pasid quirk for pre-production devices The pasid28 quirk is needed only for some pre-production devices. Remove it to make the code concise. Signed-off-by: Ashok Raj Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index ef169d67df92..1df940196ab2 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -121,7 +121,6 @@ #define ecap_srs(e) ((e >> 31) & 0x1) #define ecap_ers(e) ((e >> 30) & 0x1) #define ecap_prs(e) ((e >> 29) & 0x1) -#define ecap_broken_pasid(e) ((e >> 28) & 0x1) #define ecap_dis(e) ((e >> 27) & 0x1) #define ecap_nest(e) ((e >> 26) & 0x1) #define ecap_mts(e) ((e >> 25) & 0x1) -- cgit v1.2.3 From 1d906b22076e12cf6557cf4658defe82c0b5ff1f Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Tue, 15 May 2018 15:41:42 +0100 Subject: PCI: dwc: Add support for EP mode The PCIe controller dual mode is capable of operating in Root Complex (RC) mode as well as EP mode by configuration option. Add EP support to the DesignWare driver on top of RC mode support. Add new property on pci_epc structure which allow to configure pci_epf_test driver accordingly to the controller specific requirements. Signed-off-by: Gustavo Pimentel Signed-off-by: Lorenzo Pieralisi Acked-by: Kishon Vijay Abraham I --- include/linux/pci-epc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index af657ca58b70..243eaa5a66ff 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -90,8 +90,16 @@ struct pci_epc { struct config_group *group; /* spinlock to protect against concurrent access of EP controller */ spinlock_t lock; + unsigned int features; }; +#define EPC_FEATURE_NO_LINKUP_NOTIFIER BIT(0) +#define EPC_FEATURE_BAR_MASK (BIT(1) | BIT(2) | BIT(3)) +#define EPC_FEATURE_SET_BAR(features, bar) \ + (features |= (EPC_FEATURE_BAR_MASK & (bar << 1))) +#define EPC_FEATURE_GET_BAR(features) \ + ((features & EPC_FEATURE_BAR_MASK) >> 1) + #define to_pci_epc(device) container_of((device), struct pci_epc, dev) #define pci_epc_create(dev, ops) \ -- cgit v1.2.3 From e5cd3abcb31a48d4ea91bd32f0618802ca5f3592 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 14 May 2018 10:00:16 -0700 Subject: bpf: sockmap, refactor sockmap routines to work with hashmap This patch only refactors the existing sockmap code. This will allow much of the psock initialization code path and bpf helper codes to work for both sockmap bpf map types that are backed by an array, the currently supported type, and the new hash backed bpf map type sockhash. Most the fallout comes from three changes, - Pushing bpf programs into an independent structure so we can use it from the htab struct in the next patch. - Generalizing helpers to use void *key instead of the hardcoded u32. - Instead of passing map/key through the metadata we now do the lookup inline. This avoids storing the key in the metadata which will be useful when keys can be longer than 4 bytes. We rename the sk pointers to sk_redir at this point as well to avoid any confusion between the current sk pointer and the redirect pointer sk_redir. Signed-off-by: John Fastabend Acked-by: David S. Miller Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index da7e16523128..9dbcb9d55921 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -515,9 +515,8 @@ struct sk_msg_buff { int sg_end; struct scatterlist sg_data[MAX_SKB_FRAGS]; bool sg_copy[MAX_SKB_FRAGS]; - __u32 key; __u32 flags; - struct bpf_map *map; + struct sock *sk_redir; struct sk_buff *skb; struct list_head list; }; -- cgit v1.2.3 From cee4393989333795ae04dc9f3b83a578afe3fca6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 2 Mar 2018 16:35:27 -0800 Subject: rcu: Rename cond_resched_rcu_qs() to cond_resched_tasks_rcu_qs() Commit e31d28b6ab8f ("trace: Eliminate cond_resched_rcu_qs() in favor of cond_resched()") substituted cond_resched() for the earlier call to cond_resched_rcu_qs(). However, the new-age cond_resched() does not do anything to help RCU-tasks grace periods because (1) RCU-tasks is only enabled when CONFIG_PREEMPT=y and (2) cond_resched() is a complete no-op when preemption is enabled. This situation results in hangs when running the trace benchmarks. A number of potential fixes were discussed on LKML (https://lkml.kernel.org/r/20180224151240.0d63a059@vmware.local.home), including making cond_resched() not be a no-op; making cond_resched() not be a no-op, but only when running tracing benchmarks; reverting the aforementioned commit (which works because cond_resched_rcu_qs() does provide an RCU-tasks quiescent state; and adding a call to the scheduler/RCU rcu_note_voluntary_context_switch() function. All were deemed unsatisfactory, either due to added cond_resched() overhead or due to magic functions inviting cargo culting. This commit renames cond_resched_rcu_qs() to cond_resched_tasks_rcu_qs(), which provides a clear hint as to what this function is doing and why and where it should be used, and then replaces the call to cond_resched() with cond_resched_tasks_rcu_qs() in the trace benchmark's benchmark_event_kthread() function. Reported-by: Steven Rostedt Signed-off-by: Paul E. McKenney Tested-by: Nicholas Piggin --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 36360d07f25b..19d235fefdb9 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -188,13 +188,13 @@ static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU */ /** - * cond_resched_rcu_qs - Report potential quiescent states to RCU + * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPT kernels. */ -#define cond_resched_rcu_qs() \ +#define cond_resched_tasks_rcu_qs() \ do { \ if (!cond_resched()) \ rcu_note_voluntary_context_switch_lite(current); \ -- cgit v1.2.3 From c3442697c2d73d3cdb9d4135cf630ad36ba8552f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 5 Mar 2018 11:29:40 -0800 Subject: softirq: Eliminate unused cond_resched_softirq() macro The cond_resched_softirq() macro is not used anywhere in mainline, so this commit simplifies the kernel by eliminating it. Suggested-by: Eric Dumazet Signed-off-by: Paul E. McKenney Cc: Ingo Molnar Acked-by: Peter Zijlstra (Intel) Reviewed-by: Eric Dumazet Tested-by: Nicholas Piggin --- include/linux/sched.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b3d697f3b573..6fc99045658a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1613,7 +1613,6 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) * explicit rescheduling in places that are safe. The return * value indicates whether a reschedule was done in fact. * cond_resched_lock() will drop the spinlock before scheduling, - * cond_resched_softirq() will enable bhs before scheduling. */ #ifndef CONFIG_PREEMPT extern int _cond_resched(void); @@ -1633,13 +1632,6 @@ extern int __cond_resched_lock(spinlock_t *lock); __cond_resched_lock(lock); \ }) -extern int __cond_resched_softirq(void); - -#define cond_resched_softirq() ({ \ - ___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ - __cond_resched_softirq(); \ -}) - static inline void cond_resched_rcu(void) { #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) -- cgit v1.2.3 From 17672480fb1e953f999623b598a98130f8aacfbc Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sun, 25 Mar 2018 20:50:03 +0300 Subject: rcu: Declare rcu_eqs_special_set() in public header Because rcu_eqs_special_set() is declared only in internal header kernel/rcu/tree.h and stubbed in include/linux/rcutiny.h, it is inaccessible outside of the RCU implementation. This patch therefore moves the rcu_eqs_special_set() declaration to include/linux/rcutree.h, which allows it to be used in non-rcu kernel code. Signed-off-by: Yury Norov Signed-off-by: Paul E. McKenney Tested-by: Nicholas Piggin --- include/linux/rcutree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index fd996cdf1833..448f20f27396 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -74,6 +74,7 @@ static inline void synchronize_rcu_bh_expedited(void) void rcu_barrier(void); void rcu_barrier_bh(void); void rcu_barrier_sched(void); +bool rcu_eqs_special_set(int cpu); unsigned long get_state_synchronize_rcu(void); void cond_synchronize_rcu(unsigned long oldstate); unsigned long get_state_synchronize_sched(void); -- cgit v1.2.3 From f7194ac32ca241d28765a98e42a7fe13debc85a7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 5 Apr 2018 17:19:17 -0700 Subject: srcu: Add cleanup_srcu_struct_quiesced() The current cleanup_srcu_struct() flushes work, which prevents it from being invoked from some workqueue contexts, as well as from atomic (non-blocking) contexts. This patch therefore introduced a cleanup_srcu_struct_quiesced(), which can be invoked only after all activity on the specified srcu_struct has completed. This restriction allows cleanup_srcu_struct_quiesced() to be invoked from workqueue contexts as well as from atomic contexts. Suggested-by: Christoph Hellwig Signed-off-by: Paul E. McKenney Tested-by: Nitzan Carmi Tested-by: Nicholas Piggin --- include/linux/srcu.h | 36 +++++++++++++++++++++++++++++++++++- 1 file changed, 35 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 33c1c698df09..91494d7e8e41 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -69,11 +69,45 @@ struct srcu_struct { }; void call_srcu(struct srcu_struct *sp, struct rcu_head *head, void (*func)(struct rcu_head *head)); -void cleanup_srcu_struct(struct srcu_struct *sp); +void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced); int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp); void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); void synchronize_srcu(struct srcu_struct *sp); +/** + * cleanup_srcu_struct - deconstruct a sleep-RCU structure + * @sp: structure to clean up. + * + * Must invoke this after you are finished using a given srcu_struct that + * was initialized via init_srcu_struct(), else you leak memory. + */ +static inline void cleanup_srcu_struct(struct srcu_struct *sp) +{ + _cleanup_srcu_struct(sp, false); +} + +/** + * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure + * @sp: structure to clean up. + * + * Must invoke this after you are finished using a given srcu_struct that + * was initialized via init_srcu_struct(), else you leak memory. Also, + * all grace-period processing must have completed. + * + * "Completed" means that the last synchronize_srcu() and + * synchronize_srcu_expedited() calls must have returned before the call + * to cleanup_srcu_struct_quiesced(). It also means that the callback + * from the last call_srcu() must have been invoked before the call to + * cleanup_srcu_struct_quiesced(), but you can use srcu_barrier() to help + * with this last. Violating these rules will get you a WARN_ON() splat + * (with high probability, anyway), and will also cause the srcu_struct + * to be leaked. + */ +static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *sp) +{ + _cleanup_srcu_struct(sp, true); +} + #ifdef CONFIG_DEBUG_LOCK_ALLOC /** -- cgit v1.2.3 From ae07b786888f1872ac2b63d74a17e206d441ec9f Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 15 May 2018 11:07:00 +0200 Subject: PCI: Make pci_get_new_domain_nr() static The only user of pci_get_new_domain_nr() is of_pci_bus_find_domain_nr(). Since they are defined in the same file, pci_get_new_domain_nr() can be made static, which also simplifies preprocessor conditionals. No functional change intended. Signed-off-by: Jan Kiszka Signed-off-by: Bjorn Helgaas Acked-by: Lorenzo Pieralisi --- include/linux/pci.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 73178a2fcee0..963232a6cd2e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1510,12 +1510,10 @@ void pci_cfg_access_unlock(struct pci_dev *dev); */ #ifdef CONFIG_PCI_DOMAINS extern int pci_domains_supported; -int pci_get_new_domain_nr(void); #else enum { pci_domains_supported = 0 }; static inline int pci_domain_nr(struct pci_bus *bus) { return 0; } static inline int pci_proc_domain(struct pci_bus *bus) { return 0; } -static inline int pci_get_new_domain_nr(void) { return -ENOSYS; } #endif /* CONFIG_PCI_DOMAINS */ /* @@ -1670,7 +1668,6 @@ static inline struct pci_dev *pci_get_domain_bus_and_slot(int domain, static inline int pci_domain_nr(struct pci_bus *bus) { return 0; } static inline struct pci_dev *pci_dev_get(struct pci_dev *dev) { return NULL; } -static inline int pci_get_new_domain_nr(void) { return -ENOSYS; } #define dev_is_pci(d) (false) #define dev_is_pf(d) (false) -- cgit v1.2.3 From 81110384441a59cff47430f20f049e69b98c17f4 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 14 May 2018 10:00:17 -0700 Subject: bpf: sockmap, add hash map support Sockmap is currently backed by an array and enforces keys to be four bytes. This works well for many use cases and was originally modeled after devmap which also uses four bytes keys. However, this has become limiting in larger use cases where a hash would be more appropriate. For example users may want to use the 5-tuple of the socket as the lookup key. To support this add hash support. Signed-off-by: John Fastabend Acked-by: David S. Miller Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 8 ++++++++ include/linux/bpf_types.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a38e474bf7ee..ed0122b45b63 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -668,6 +668,7 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_INET) struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); +struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key); int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); #else static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) @@ -675,6 +676,12 @@ static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) return NULL; } +static inline struct sock *__sock_hash_lookup_elem(struct bpf_map *map, + void *key) +{ + return NULL; +} + static inline int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) @@ -724,6 +731,7 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; +extern const struct bpf_func_proto bpf_sock_hash_update_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index d7df1b323082..b67f8793de0d 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -47,6 +47,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_INET) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #if defined(CONFIG_XDP_SOCKETS) -- cgit v1.2.3 From c6d24c324e78a71e55af4e00de014cf0e0524dcb Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 4 May 2018 04:13:45 +0300 Subject: lib/string_helpers: Add missed declaration of struct task_struct Starting from the commit 0d0443288f22 the new function has been introduced which takes struct task_struct as a parameter. Though, compiler doesn't know where to get information about it at this stage. Add missed declaration of struct task_struct to satisfy compiler. Fixes: 0d0443288f22 ("string_helpers: add kstrdup_quotable_cmdline") Cc: Kees Cook Cc: James Morris Signed-off-by: Andy Shevchenko Acked-by: Kees Cook --- include/linux/string_helpers.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 4397c52ec4a4..d23c5030901a 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -5,6 +5,7 @@ #include struct file; +struct task_struct; /* Descriptions of the types of units to * print in */ -- cgit v1.2.3 From 67482129cdabf7cede1301d2415ef4f0156d35cd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 10 May 2018 08:38:15 -0700 Subject: iomap: add a swapfile activation function Add a new iomap_swapfile_activate function so that filesystems can activate swap files without having to use the obsolete and slow bmap function. This enables XFS to support fallocate'd swap files and swap files on realtime devices. Signed-off-by: Darrick J. Wong Reviewed-by: Jan Kara --- include/linux/iomap.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 19a07de28212..4bd87294219a 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -106,4 +106,15 @@ typedef int (iomap_dio_end_io_t)(struct kiocb *iocb, ssize_t ret, ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, iomap_dio_end_io_t end_io); +#ifdef CONFIG_SWAP +struct file; +struct swap_info_struct; + +int iomap_swapfile_activate(struct swap_info_struct *sis, + struct file *swap_file, sector_t *pagespan, + const struct iomap_ops *ops); +#else +# define iomap_swapfile_activate(sis, swapfile, pagespan, ops) (-EIO) +#endif /* CONFIG_SWAP */ + #endif /* LINUX_IOMAP_H */ -- cgit v1.2.3 From 76f668be1e8e87d235fbd50037f50fdde948b46d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 16 May 2018 07:19:01 +0200 Subject: proc: introduce a proc_pid_ns helper Factor out retrieving the per-sb pid namespaces from the sb private data into an easier to understand helper. Suggested-by: Eric W. Biederman Signed-off-by: Christoph Hellwig --- include/linux/proc_fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 928ef9e4d912..4edcde510631 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -83,4 +83,10 @@ struct ns_common; int open_related_ns(struct ns_common *ns, struct ns_common *(*get_ns)(struct ns_common *ns)); +/* get the associated pid namespace for a file in procfs */ +static inline struct pid_namespace *proc_pid_ns(struct inode *inode) +{ + return inode->i_sb->s_fs_info; +} + #endif /* _LINUX_PROC_FS_H */ -- cgit v1.2.3 From fddda2b7b521185f3aa018f9559eb33b0aee53a9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 13 Apr 2018 19:44:18 +0200 Subject: proc: introduce proc_create_seq{,_data} Variants of proc_create{,_data} that directly take a struct seq_operations argument and drastically reduces the boilerplate code in the callers. All trivial callers converted over. Signed-off-by: Christoph Hellwig --- include/linux/proc_fs.h | 9 +++++++++ include/linux/tty.h | 3 ++- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 4edcde510631..f368a896a8cb 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -9,6 +9,7 @@ #include struct proc_dir_entry; +struct seq_operations; #ifdef CONFIG_PROC_FS @@ -23,6 +24,12 @@ extern struct proc_dir_entry *proc_mkdir_data(const char *, umode_t, extern struct proc_dir_entry *proc_mkdir_mode(const char *, umode_t, struct proc_dir_entry *); struct proc_dir_entry *proc_create_mount_point(const char *name); + +struct proc_dir_entry *proc_create_seq_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, const struct seq_operations *ops, + void *data); +#define proc_create_seq(name, mode, parent, ops) \ + proc_create_seq_data(name, mode, parent, ops, NULL) extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *, @@ -57,6 +64,8 @@ static inline struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; } static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return NULL; } +#define proc_create_seq_data(name, mode, parent, ops, data) ({NULL;}) +#define proc_create_seq(name, mode, parent, ops) ({NULL;}) #define proc_create(name, mode, parent, proc_fops) ({NULL;}) #define proc_create_data(name, mode, parent, proc_fops, data) ({NULL;}) diff --git a/include/linux/tty.h b/include/linux/tty.h index 1dd587ba6d88..9bd7d37adbfa 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -535,7 +536,7 @@ extern void tty_ldisc_deref(struct tty_ldisc *); extern struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *); extern void tty_ldisc_hangup(struct tty_struct *tty, bool reset); extern int tty_ldisc_reinit(struct tty_struct *tty, int disc); -extern const struct file_operations tty_ldiscs_proc_fops; +extern const struct seq_operations tty_ldiscs_seq_ops; extern void tty_wakeup(struct tty_struct *tty); extern void tty_ldisc_flush(struct tty_struct *tty); -- cgit v1.2.3 From 44414d82cfe0f68cb59d0a42f599ccd893ae0032 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Apr 2018 17:05:17 +0200 Subject: proc: introduce proc_create_seq_private Variant of proc_create_data that directly take a struct seq_operations argument + a private state size and drastically reduces the boilerplate code in the callers. All trivial callers converted over. Signed-off-by: Christoph Hellwig --- include/linux/atalk.h | 7 ++++++- include/linux/proc_fs.h | 9 ++++++--- 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atalk.h b/include/linux/atalk.h index 40373920ea58..23f805562f4e 100644 --- a/include/linux/atalk.h +++ b/include/linux/atalk.h @@ -145,7 +145,12 @@ extern rwlock_t atalk_interfaces_lock; extern struct atalk_route atrtr_default; -extern const struct file_operations atalk_seq_arp_fops; +struct aarp_iter_state { + int bucket; + struct aarp_entry **table; +}; + +extern const struct seq_operations aarp_seq_ops; extern int sysctl_aarp_expiry_time; extern int sysctl_aarp_tick_time; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index f368a896a8cb..314713a48817 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -25,11 +25,13 @@ extern struct proc_dir_entry *proc_mkdir_mode(const char *, umode_t, struct proc_dir_entry *); struct proc_dir_entry *proc_create_mount_point(const char *name); -struct proc_dir_entry *proc_create_seq_data(const char *name, umode_t mode, +struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, - void *data); + unsigned int state_size, void *data); +#define proc_create_seq_data(name, mode, parent, ops, data) \ + proc_create_seq_private(name, mode, parent, ops, 0, data) #define proc_create_seq(name, mode, parent, ops) \ - proc_create_seq_data(name, mode, parent, ops, NULL) + proc_create_seq_private(name, mode, parent, ops, 0, NULL) extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *, @@ -64,6 +66,7 @@ static inline struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; } static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return NULL; } +#define proc_create_seq_private(name, mode, parent, ops, 0, data) ({NULL;}) #define proc_create_seq_data(name, mode, parent, ops, data) ({NULL;}) #define proc_create_seq(name, mode, parent, ops) ({NULL;}) #define proc_create(name, mode, parent, proc_fops) ({NULL;}) -- cgit v1.2.3 From 3f3942aca6da351a12543aa776467791b63b3a78 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 15 May 2018 15:57:23 +0200 Subject: proc: introduce proc_create_single{,_data} Variants of proc_create{,_data} that directly take a seq_file show callback and drastically reduces the boilerplate code in the callers. All trivial callers converted over. Signed-off-by: Christoph Hellwig --- include/linux/proc_fs.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 314713a48817..2529b871f379 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -9,6 +9,7 @@ #include struct proc_dir_entry; +struct seq_file; struct seq_operations; #ifdef CONFIG_PROC_FS @@ -32,6 +33,11 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, proc_create_seq_private(name, mode, parent, ops, 0, data) #define proc_create_seq(name, mode, parent, ops) \ proc_create_seq_private(name, mode, parent, ops, 0, NULL) +struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, + int (*show)(struct seq_file *, void *), void *data); +#define proc_create_single(name, mode, parent, show) \ + proc_create_single_data(name, mode, parent, show, NULL) extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *, @@ -66,9 +72,11 @@ static inline struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; } static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return NULL; } -#define proc_create_seq_private(name, mode, parent, ops, 0, data) ({NULL;}) +#define proc_create_seq_private(name, mode, parent, ops, size, data) ({NULL;}) #define proc_create_seq_data(name, mode, parent, ops, data) ({NULL;}) #define proc_create_seq(name, mode, parent, ops) ({NULL;}) +#define proc_create_single(name, mode, parent, show) ({NULL;}) +#define proc_create_single_data(name, mode, parent, show, data) ({NULL;}) #define proc_create(name, mode, parent, proc_fops) ({NULL;}) #define proc_create_data(name, mode, parent, proc_fops, data) ({NULL;}) -- cgit v1.2.3 From a2dcdee3748b664bf011b4b12de64e945dd4c8c2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Apr 2018 12:32:45 +0200 Subject: net: move seq_file_single_net to This helper deals with single_{open,release}_net internals and thus belongs here. Signed-off-by: Christoph Hellwig --- include/linux/seq_file_net.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seq_file_net.h b/include/linux/seq_file_net.h index 43ccd84127b6..ed20faa99e05 100644 --- a/include/linux/seq_file_net.h +++ b/include/linux/seq_file_net.h @@ -28,4 +28,17 @@ static inline struct net *seq_file_net(struct seq_file *seq) #endif } +/* + * This one is needed for single_open_net since net is stored directly in + * private not as a struct i.e. seq_file_net can't be used. + */ +static inline struct net *seq_file_single_net(struct seq_file *seq) +{ +#ifdef CONFIG_NET_NS + return (struct net *)seq->private; +#else + return &init_net; +#endif +} + #endif -- cgit v1.2.3 From c3506372277779fccbffee2475400fcd689d5738 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Apr 2018 19:42:55 +0200 Subject: proc: introduce proc_create_net{,_data} Variants of proc_create{,_data} that directly take a struct seq_operations and deal with network namespaces in ->open and ->release. All callers of proc_create + seq_open_net converted over, and seq_{open,release}_net are removed entirely. Signed-off-by: Christoph Hellwig --- include/linux/proc_fs.h | 9 +++++++++ include/linux/seq_file_net.h | 3 --- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 2529b871f379..9dcde9644253 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -53,6 +53,12 @@ extern void proc_remove(struct proc_dir_entry *); extern void remove_proc_entry(const char *, struct proc_dir_entry *); extern int remove_proc_subtree(const char *, struct proc_dir_entry *); +struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, const struct seq_operations *ops, + unsigned int state_size, void *data); +#define proc_create_net(name, mode, parent, state_size, ops) \ + proc_create_net_data(name, mode, parent, state_size, ops, NULL) + #else /* CONFIG_PROC_FS */ static inline void proc_root_init(void) @@ -89,6 +95,9 @@ static inline void proc_remove(struct proc_dir_entry *de) {} #define remove_proc_entry(name, parent) do {} while (0) static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { return 0; } +#define proc_create_net_data(name, mode, parent, ops, state_size, data) ({NULL;}) +#define proc_create_net(name, mode, parent, state_size, ops) ({NULL;}) + #endif /* CONFIG_PROC_FS */ struct net; diff --git a/include/linux/seq_file_net.h b/include/linux/seq_file_net.h index ed20faa99e05..5ea18a16291a 100644 --- a/include/linux/seq_file_net.h +++ b/include/linux/seq_file_net.h @@ -13,11 +13,8 @@ struct seq_net_private { #endif }; -int seq_open_net(struct inode *, struct file *, - const struct seq_operations *, int); int single_open_net(struct inode *, struct file *file, int (*show)(struct seq_file *, void *)); -int seq_release_net(struct inode *, struct file *); int single_release_net(struct inode *, struct file *); static inline struct net *seq_file_net(struct seq_file *seq) { -- cgit v1.2.3 From 3617d9496cd92dcca4d0893191d95554590d8d9f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 13 Apr 2018 20:38:35 +0200 Subject: proc: introduce proc_create_net_single Variant of proc_create_data that directly take a seq_file show callback and deals with network namespaces in ->open and ->release. All callers of proc_create + single_open_net converted over, and single_{open,release}_net are removed entirely. Signed-off-by: Christoph Hellwig --- include/linux/proc_fs.h | 4 ++++ include/linux/seq_file_net.h | 7 ++----- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 9dcde9644253..e518352137e7 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -58,6 +58,9 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, unsigned int state_size, void *data); #define proc_create_net(name, mode, parent, state_size, ops) \ proc_create_net_data(name, mode, parent, state_size, ops, NULL) +struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, + struct proc_dir_entry *parent, + int (*show)(struct seq_file *, void *), void *data); #else /* CONFIG_PROC_FS */ @@ -97,6 +100,7 @@ static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *p #define proc_create_net_data(name, mode, parent, ops, state_size, data) ({NULL;}) #define proc_create_net(name, mode, parent, state_size, ops) ({NULL;}) +#define proc_create_net_single(name, mode, parent, show, data) ({NULL;}) #endif /* CONFIG_PROC_FS */ diff --git a/include/linux/seq_file_net.h b/include/linux/seq_file_net.h index 5ea18a16291a..0fdbe1ddd8d1 100644 --- a/include/linux/seq_file_net.h +++ b/include/linux/seq_file_net.h @@ -13,9 +13,6 @@ struct seq_net_private { #endif }; -int single_open_net(struct inode *, struct file *file, - int (*show)(struct seq_file *, void *)); -int single_release_net(struct inode *, struct file *); static inline struct net *seq_file_net(struct seq_file *seq) { #ifdef CONFIG_NET_NS @@ -26,8 +23,8 @@ static inline struct net *seq_file_net(struct seq_file *seq) } /* - * This one is needed for single_open_net since net is stored directly in - * private not as a struct i.e. seq_file_net can't be used. + * This one is needed for proc_create_net_single since net is stored directly + * in private not as a struct i.e. seq_file_net can't be used. */ static inline struct net *seq_file_single_net(struct seq_file *seq) { -- cgit v1.2.3 From 2cd1f0ddbb5667f61e69089964209e8f716e9009 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Apr 2018 18:39:29 +0200 Subject: isdn: replace ->proc_fops with ->proc_show And switch to proc_create_single_data. Signed-off-by: Christoph Hellwig --- include/linux/isdn/capilli.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/isdn/capilli.h b/include/linux/isdn/capilli.h index 11b57c485854..d75e1ad72964 100644 --- a/include/linux/isdn/capilli.h +++ b/include/linux/isdn/capilli.h @@ -50,7 +50,7 @@ struct capi_ctr { u16 (*send_message)(struct capi_ctr *, struct sk_buff *skb); char *(*procinfo)(struct capi_ctr *); - const struct file_operations *proc_fops; + int (*proc_show)(struct seq_file *, void *); /* filled in before calling ready callback */ u8 manu[CAPI_MANUFACTURER_LEN]; /* CAPI_GET_MANUFACTURER */ -- cgit v1.2.3 From ec7d9c9ce897174243af4fcd201dbfc34df0f3a3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 13 Apr 2018 21:25:54 +0200 Subject: ide: replace ->proc_fops with ->proc_show Just set up the show callback in the tty_operations, and use proc_create_single_data to create the file without additional boilerplace code. Signed-off-by: Christoph Hellwig --- include/linux/ide.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index ca9d34feb572..752464f5a772 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -961,7 +961,7 @@ __IDE_PROC_DEVSET(_name, _min, _max, NULL, NULL) typedef struct { const char *name; umode_t mode; - const struct file_operations *proc_fops; + int (*show)(struct seq_file *, void *); } ide_proc_entry_t; void proc_ide_create(void); @@ -973,8 +973,8 @@ void ide_proc_unregister_port(ide_hwif_t *); void ide_proc_register_driver(ide_drive_t *, struct ide_driver *); void ide_proc_unregister_driver(ide_drive_t *, struct ide_driver *); -extern const struct file_operations ide_capacity_proc_fops; -extern const struct file_operations ide_geometry_proc_fops; +int ide_capacity_proc_show(struct seq_file *m, void *v); +int ide_geometry_proc_show(struct seq_file *m, void *v); #else static inline void proc_ide_create(void) { ; } static inline void proc_ide_destroy(void) { ; } -- cgit v1.2.3 From 8a8dcabffb991a08fa1fab4e75b80a9075825606 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 13 Apr 2018 21:04:45 +0200 Subject: tty: replace ->proc_fops with ->proc_show Just set up the show callback in the tty_operations, and use proc_create_single_data to create the file without additional boilerplace code. Signed-off-by: Christoph Hellwig --- include/linux/tty_driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 31c2b5b166de..71dbc891851a 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -293,7 +293,7 @@ struct tty_operations { int (*poll_get_char)(struct tty_driver *driver, int line); void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif - const struct file_operations *proc_fops; + int (*proc_show)(struct seq_file *, void *); } __randomize_layout; struct tty_driver { -- cgit v1.2.3 From 0c6609805b638debcb7d9d44556546b043ded2e9 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Wed, 16 May 2018 09:35:57 +0200 Subject: mfd: stm32-timers: Add support for DMAs STM32 Timers can support up to 7 DMA requests: - 4 channels, update, compare and trigger. Optionally request part, or all DMAs from stm32-timers MFD core. Also add routine to implement burst reads using DMA from timer registers. This is exported. So, it can be used by child drivers, PWM capture for instance (but not limited to). Signed-off-by: Fabrice Gasnier Reviewed-by: Benjamin Gaignard Signed-off-by: Lee Jones --- include/linux/mfd/stm32-timers.h | 46 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index 2aadab6f34a1..9596d5c58859 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -8,6 +8,8 @@ #define _LINUX_STM32_GPTIMER_H_ #include +#include +#include #include #define TIM_CR1 0x00 /* Control Register 1 */ @@ -27,6 +29,8 @@ #define TIM_CCR3 0x3C /* Capt/Comp Register 3 */ #define TIM_CCR4 0x40 /* Capt/Comp Register 4 */ #define TIM_BDTR 0x44 /* Break and Dead-Time Reg */ +#define TIM_DCR 0x48 /* DMA control register */ +#define TIM_DMAR 0x4C /* DMA register for transfer */ #define TIM_CR1_CEN BIT(0) /* Counter Enable */ #define TIM_CR1_DIR BIT(4) /* Counter Direction */ @@ -36,6 +40,13 @@ #define TIM_SMCR_SMS (BIT(0) | BIT(1) | BIT(2)) /* Slave mode selection */ #define TIM_SMCR_TS (BIT(4) | BIT(5) | BIT(6)) /* Trigger selection */ #define TIM_DIER_UIE BIT(0) /* Update interrupt */ +#define TIM_DIER_UDE BIT(8) /* Update DMA request Enable */ +#define TIM_DIER_CC1DE BIT(9) /* CC1 DMA request Enable */ +#define TIM_DIER_CC2DE BIT(10) /* CC2 DMA request Enable */ +#define TIM_DIER_CC3DE BIT(11) /* CC3 DMA request Enable */ +#define TIM_DIER_CC4DE BIT(12) /* CC4 DMA request Enable */ +#define TIM_DIER_COMDE BIT(13) /* COM DMA request Enable */ +#define TIM_DIER_TDE BIT(14) /* Trigger DMA request Enable */ #define TIM_SR_UIF BIT(0) /* Update interrupt flag */ #define TIM_EGR_UG BIT(0) /* Update Generation */ #define TIM_CCMR_PE BIT(3) /* Channel Preload Enable */ @@ -56,6 +67,8 @@ #define TIM_BDTR_BK2F (BIT(20) | BIT(21) | BIT(22) | BIT(23)) #define TIM_BDTR_BK2E BIT(24) /* Break 2 input enable */ #define TIM_BDTR_BK2P BIT(25) /* Break 2 input polarity */ +#define TIM_DCR_DBA GENMASK(4, 0) /* DMA base addr */ +#define TIM_DCR_DBL GENMASK(12, 8) /* DMA burst len */ #define MAX_TIM_PSC 0xFFFF #define TIM_CR2_MMS_SHIFT 4 @@ -65,9 +78,42 @@ #define TIM_BDTR_BKF_SHIFT 16 #define TIM_BDTR_BK2F_SHIFT 20 +enum stm32_timers_dmas { + STM32_TIMERS_DMA_CH1, + STM32_TIMERS_DMA_CH2, + STM32_TIMERS_DMA_CH3, + STM32_TIMERS_DMA_CH4, + STM32_TIMERS_DMA_UP, + STM32_TIMERS_DMA_TRIG, + STM32_TIMERS_DMA_COM, + STM32_TIMERS_MAX_DMAS, +}; + +/** + * struct stm32_timers_dma - STM32 timer DMA handling. + * @completion: end of DMA transfer completion + * @phys_base: control registers physical base address + * @lock: protect DMA access + * @chan: DMA channel in use + * @chans: DMA channels available for this timer instance + */ +struct stm32_timers_dma { + struct completion completion; + phys_addr_t phys_base; + struct mutex lock; + struct dma_chan *chan; + struct dma_chan *chans[STM32_TIMERS_MAX_DMAS]; +}; + struct stm32_timers { struct clk *clk; struct regmap *regmap; u32 max_arr; + struct stm32_timers_dma dma; /* Only to be used by the parent */ }; + +int stm32_timers_dma_burst_read(struct device *dev, u32 *buf, + enum stm32_timers_dmas id, u32 reg, + unsigned int num_reg, unsigned int bursts, + unsigned long tmo_ms); #endif -- cgit v1.2.3 From 53e38fe73f941291fd20794c15c3bb7b104a4a17 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Wed, 16 May 2018 09:35:58 +0200 Subject: pwm: stm32: Add capture support Add support for PMW input mode on pwm-stm32. STM32 timers support period and duty cycle capture as long as they have at least two PWM channels. One capture channel is used for period (rising-edge), one for duty-cycle (falling-edge). When there's only one channel available, only period can be captured. Duty-cycle is simply zero'ed in such a case. Capture requires exclusive access (e.g. no pwm output running at the same time, to protect common prescaler). Timer DMA burst mode (from MFD core) is being used, to take two snapshots of capture registers (upon each period rising edge). Signed-off-by: Fabrice Gasnier Reviewed-by: Benjamin Gaignard Acked-by: Thierry Reding Signed-off-by: Lee Jones --- include/linux/mfd/stm32-timers.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index 9596d5c58859..d46f5500928e 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -51,13 +51,24 @@ #define TIM_EGR_UG BIT(0) /* Update Generation */ #define TIM_CCMR_PE BIT(3) /* Channel Preload Enable */ #define TIM_CCMR_M1 (BIT(6) | BIT(5)) /* Channel PWM Mode 1 */ +#define TIM_CCMR_CC1S (BIT(0) | BIT(1)) /* Capture/compare 1 sel */ +#define TIM_CCMR_IC1PSC GENMASK(3, 2) /* Input capture 1 prescaler */ +#define TIM_CCMR_CC2S (BIT(8) | BIT(9)) /* Capture/compare 2 sel */ +#define TIM_CCMR_IC2PSC GENMASK(11, 10) /* Input capture 2 prescaler */ +#define TIM_CCMR_CC1S_TI1 BIT(0) /* IC1/IC3 selects TI1/TI3 */ +#define TIM_CCMR_CC1S_TI2 BIT(1) /* IC1/IC3 selects TI2/TI4 */ +#define TIM_CCMR_CC2S_TI2 BIT(8) /* IC2/IC4 selects TI2/TI4 */ +#define TIM_CCMR_CC2S_TI1 BIT(9) /* IC2/IC4 selects TI1/TI3 */ #define TIM_CCER_CC1E BIT(0) /* Capt/Comp 1 out Ena */ #define TIM_CCER_CC1P BIT(1) /* Capt/Comp 1 Polarity */ #define TIM_CCER_CC1NE BIT(2) /* Capt/Comp 1N out Ena */ #define TIM_CCER_CC1NP BIT(3) /* Capt/Comp 1N Polarity */ #define TIM_CCER_CC2E BIT(4) /* Capt/Comp 2 out Ena */ +#define TIM_CCER_CC2P BIT(5) /* Capt/Comp 2 Polarity */ #define TIM_CCER_CC3E BIT(8) /* Capt/Comp 3 out Ena */ +#define TIM_CCER_CC3P BIT(9) /* Capt/Comp 3 Polarity */ #define TIM_CCER_CC4E BIT(12) /* Capt/Comp 4 out Ena */ +#define TIM_CCER_CC4P BIT(13) /* Capt/Comp 4 Polarity */ #define TIM_CCER_CCXE (BIT(0) | BIT(4) | BIT(8) | BIT(12)) #define TIM_BDTR_BKE BIT(12) /* Break input enable */ #define TIM_BDTR_BKP BIT(13) /* Break input polarity */ -- cgit v1.2.3 From ab3a897847834bf3e864fb07b733c444895a24ba Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Wed, 16 May 2018 09:36:00 +0200 Subject: pwm: stm32: Use input prescaler to improve period capture Using input prescaler, capture unit will trigger DMA once every configurable /2, /4 or /8 events (rising edge). This helps improve period (only) capture accuracy at high rates. Signed-off-by: Fabrice Gasnier Reviewed-by: Benjamin Gaignard Acked-by: Thierry Reding Signed-off-by: Lee Jones --- include/linux/mfd/stm32-timers.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index d46f5500928e..9da1d7ece079 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -82,6 +82,7 @@ #define TIM_DCR_DBL GENMASK(12, 8) /* DMA burst len */ #define MAX_TIM_PSC 0xFFFF +#define MAX_TIM_ICPSC 0x3 #define TIM_CR2_MMS_SHIFT 4 #define TIM_CR2_MMS2_SHIFT 20 #define TIM_SMCR_TS_SHIFT 4 -- cgit v1.2.3 From 30feec093021ef665233a3c78a99f444673389a2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 9 Jan 2018 19:59:21 +0100 Subject: mfd: syscon: Remove unused Exynos PMU headers Since commit 5812f0106c44 ("phy: exynos4: Remove duplicated defines of PHY register defines") and commit 7a66647b25b6 ("phy: exynos: Use one define for enable bit") all users of syscon Exynos PMU headers (for PHY drivers) are converted to use different headers so these can be removed. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/syscon/exynos4-pmu.h | 21 --------------------- include/linux/mfd/syscon/exynos5-pmu.h | 19 ------------------- 2 files changed, 40 deletions(-) delete mode 100644 include/linux/mfd/syscon/exynos4-pmu.h delete mode 100644 include/linux/mfd/syscon/exynos5-pmu.h (limited to 'include/linux') diff --git a/include/linux/mfd/syscon/exynos4-pmu.h b/include/linux/mfd/syscon/exynos4-pmu.h deleted file mode 100644 index 278b1b1549e9..000000000000 --- a/include/linux/mfd/syscon/exynos4-pmu.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * Copyright (C) 2015 Samsung Electronics Co., Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef _LINUX_MFD_SYSCON_PMU_EXYNOS4_H_ -#define _LINUX_MFD_SYSCON_PMU_EXYNOS4_H_ - -/* Exynos4 PMU register definitions */ - -/* MIPI_PHYn_CONTROL register offset: n = 0..1 */ -#define EXYNOS4_MIPI_PHY_CONTROL(n) (0x710 + (n) * 4) -#define EXYNOS4_MIPI_PHY_ENABLE (1 << 0) -#define EXYNOS4_MIPI_PHY_SRESETN (1 << 1) -#define EXYNOS4_MIPI_PHY_MRESETN (1 << 2) -#define EXYNOS4_MIPI_PHY_RESET_MASK (3 << 1) - -#endif /* _LINUX_MFD_SYSCON_PMU_EXYNOS4_H_ */ diff --git a/include/linux/mfd/syscon/exynos5-pmu.h b/include/linux/mfd/syscon/exynos5-pmu.h deleted file mode 100644 index b4942a32b81d..000000000000 --- a/include/linux/mfd/syscon/exynos5-pmu.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * Exynos5 SoC series Power Management Unit (PMU) register offsets - * and bit definitions. - * - * Copyright (C) 2014 Samsung Electronics Co., Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef _LINUX_MFD_SYSCON_PMU_EXYNOS5_H_ -#define _LINUX_MFD_SYSCON_PMU_EXYNOS5_H_ - -#define EXYNOS5_PHY_ENABLE BIT(0) -#define EXYNOS5_MIPI_PHY_S_RESETN BIT(1) -#define EXYNOS5_MIPI_PHY_M_RESETN BIT(2) - -#endif /* _LINUX_MFD_SYSCON_PMU_EXYNOS5_H_ */ -- cgit v1.2.3 From efc9b2048c7f6bb52f70cc84b8b8b8dcc685a0d6 Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Thu, 15 Feb 2018 22:17:05 -0600 Subject: mfd: tps65218: Reorder tps65218_regulator_id enum Commit 2dc4940360d4 ("regulator: tps65218: Remove all the compatibles") changes the probe function of drivers/regulator/tps65218-regulator.c so that it iterates through all available regulators and assumes that the regulator IDs are sequential and match the order present in the enum tps65218_regulator_id. However, for some reason the much older commit c0ea88b890d6 ("regulator: tps65218: add support for LS3 current regulator") updated all arrays with LS3 at the end but added it second to last for the enum. Because of this long standing mismatch in order between the tps65218_regulator_id enum and the regulator_desc array in the tps65218 regulator driver, the new probe function causes the strobe values to be associated with the wrong regulator ID. This causes LDO1 to fail to suspend in tps65218_pmic_set_suspend_disable due to not having anything probes for its strobe value. Fix the order in the enum so the probe function works as the update intended. Fixes: 2dc4940360d4 ("regulator: tps65218: Remove all the compatibles") Signed-off-by: Dave Gerlach Signed-off-by: Lee Jones --- include/linux/mfd/tps65218.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index f069c518c0ed..c204d9a79436 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -205,10 +205,10 @@ enum tps65218_regulator_id { TPS65218_DCDC_4, TPS65218_DCDC_5, TPS65218_DCDC_6, - /* LS's */ - TPS65218_LS_3, /* LDOs */ TPS65218_LDO_1, + /* LS's */ + TPS65218_LS_3, }; #define TPS65218_MAX_REG_ID TPS65218_LDO_1 -- cgit v1.2.3 From 37c089d1facaf03969f66a5469c169a2c73429f6 Mon Sep 17 00:00:00 2001 From: Rajmohan Mani Date: Tue, 20 Feb 2018 15:54:07 -0800 Subject: mfd: Update to SPDX license identifier Remove the GPL v2 license boilerplate and update with the SPDX license identifier. Signed-off-by: Rajmohan Mani Signed-off-by: Lee Jones --- include/linux/mfd/tps68470.h | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps68470.h b/include/linux/mfd/tps68470.h index 44f9d9f647ed..ffe81127d91c 100644 --- a/include/linux/mfd/tps68470.h +++ b/include/linux/mfd/tps68470.h @@ -1,17 +1,6 @@ -/* - * Copyright (c) 2017 Intel Corporation - * - * Functions to access TPS68470 power management chip. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2017 Intel Corporation */ +/* Functions to access TPS68470 power management chip. */ #ifndef __LINUX_MFD_TPS68470_H #define __LINUX_MFD_TPS68470_H -- cgit v1.2.3 From 99fb0f25c448ab72481bd700b66e0e48c583ef5a Mon Sep 17 00:00:00 2001 From: Wenkai Du Date: Thu, 22 Feb 2018 13:30:52 -0800 Subject: Revert "mfd: cros_ec: Add ACPI GPE handler for LID0 devices" This reverts commit e04653a9dcf4d98defe2149c885382e5cc72082f. It is no longer needed to install Chrome EC GPE handler to have GPE enabled in suspend to idle path. It is found that with this handler installed, EC wake up doesn't work because default EC event handler that can wake up system is not getting called. Signed-off-by: Wenkai Du Acked-by: Benson Leung Signed-off-by: Lee Jones --- include/linux/mfd/cros_ec.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 2d4e23c9ea0a..4ff0cec979b0 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -328,22 +328,4 @@ extern struct attribute_group cros_ec_vbc_attr_group; int cros_ec_debugfs_init(struct cros_ec_dev *ec); void cros_ec_debugfs_remove(struct cros_ec_dev *ec); -/* ACPI GPE handler */ -#ifdef CONFIG_ACPI - -int cros_ec_acpi_install_gpe_handler(struct device *dev); -void cros_ec_acpi_remove_gpe_handler(void); -void cros_ec_acpi_clear_gpe(void); - -#else /* CONFIG_ACPI */ - -static inline int cros_ec_acpi_install_gpe_handler(struct device *dev) -{ - return -ENODEV; -} -static inline void cros_ec_acpi_remove_gpe_handler(void) {} -static inline void cros_ec_acpi_clear_gpe(void) {} - -#endif /* CONFIG_ACPI */ - #endif /* __LINUX_MFD_CROS_EC_H */ -- cgit v1.2.3 From c18604660ad02324dfc21de5dfd0c8d15e9070a5 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 12 Mar 2018 15:52:00 +0000 Subject: mfd: arizona: Update reset pin to use GPIOD Now GPIOD has support for both pdata systems and for non-standard DT bindings the Arizona reset GPIO can be converted to use it. Worth noting gpiod_set_raw_value_cansleep is used to match the behaviour of the old GPIOs. This is because the part is fairly widely used and it is unknown how many DTs are correctly setting active low through device tree, so to avoid breaking any existing users it is best to match the previous behaviour. Signed-off-by: Charles Keepax Reviewed-by: Linus Walleij Signed-off-by: Lee Jones --- include/linux/mfd/arizona/pdata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index f72dc53848d7..0013075d4cda 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -56,6 +56,7 @@ #define ARIZONA_MAX_PDM_SPK 2 struct regulator_init_data; +struct gpio_desc; struct arizona_micbias { int mV; /** Regulated voltage */ @@ -77,7 +78,7 @@ struct arizona_micd_range { }; struct arizona_pdata { - int reset; /** GPIO controlling /RESET, if any */ + struct gpio_desc *reset; /** GPIO controlling /RESET, if any */ /** Regulator configuration for MICVDD */ struct arizona_micsupp_pdata micvdd; -- cgit v1.2.3 From 531a469ead6ad1e79e8c84ffd4787c0747336e5a Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Thu, 29 Mar 2018 12:31:13 +0800 Subject: mfd: axp20x: Constify struct mfd_cell and struct resource The axp20x driver has lots of mfd_cell and resource structs. These can all be const-ified. Signed-off-by: Chen-Yu Tsai Signed-off-by: Lee Jones --- include/linux/mfd/axp20x.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 82bf7747b312..a2489363a998 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -642,7 +642,7 @@ struct axp20x_dev { struct regmap_irq_chip_data *regmap_irqc; long variant; int nr_cells; - struct mfd_cell *cells; + const struct mfd_cell *cells; const struct regmap_config *regmap_cfg; const struct regmap_irq_chip *regmap_irq_chip; }; -- cgit v1.2.3 From eef2b53a3ec6b1919d32bd722d2f5d33769a1f48 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Thu, 29 Mar 2018 12:31:15 +0800 Subject: mfd: axp20x: Correct AXP806 POK interrupt prefix When AXP806 support was added, POK was incorrectly expanded to PWROK. However, the datasheet lists them as POK[LSNP], which is the same as on the AXP288. Furthermore, the registers associated with POK functions are the same as the PEK on the other AXP PMICs. This suggests that "POK" means "Power On Key", much like "PEK" means "Power Enable Key", instead of "Power OK". This patch changes the "PWROK" prefix to "POK" for these interrupts. Signed-off-by: Chen-Yu Tsai Signed-off-by: Lee Jones --- include/linux/mfd/axp20x.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index a2489363a998..517e60eecbcb 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -592,11 +592,11 @@ enum axp806_irqs { AXP806_IRQ_DCDCC_V_LOW, AXP806_IRQ_DCDCD_V_LOW, AXP806_IRQ_DCDCE_V_LOW, - AXP806_IRQ_PWROK_LONG, - AXP806_IRQ_PWROK_SHORT, + AXP806_IRQ_POK_LONG, + AXP806_IRQ_POK_SHORT, AXP806_IRQ_WAKEUP, - AXP806_IRQ_PWROK_FALL, - AXP806_IRQ_PWROK_RISE, + AXP806_IRQ_POK_FALL, + AXP806_IRQ_POK_RISE, }; enum axp809_irqs { -- cgit v1.2.3 From a411e81e61df24023f40255145d8f023402002c9 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 10 Apr 2018 22:30:28 +0200 Subject: gpiolib: add hogs support for machine code Board files constitute a significant part of the users of the legacy GPIO framework. In many cases they only export a line and set its desired value. We could use GPIO hogs for that like we do for DT and ACPI but there's no support for that in machine code. This patch proposes to extend the machine.h API with support for registering hog tables in board files. Signed-off-by: Bartosz Golaszewski Signed-off-by: Linus Walleij --- include/linux/gpio/machine.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index b2f2dc638463..daa44eac9241 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -39,6 +39,23 @@ struct gpiod_lookup_table { struct gpiod_lookup table[]; }; +/** + * struct gpiod_hog - GPIO line hog table + * @chip_label: name of the chip the GPIO belongs to + * @chip_hwnum: hardware number (i.e. relative to the chip) of the GPIO + * @line_name: consumer name for the hogged line + * @lflags: mask of GPIO lookup flags + * @dflags: GPIO flags used to specify the direction and value + */ +struct gpiod_hog { + struct list_head list; + const char *chip_label; + u16 chip_hwnum; + const char *line_name; + enum gpio_lookup_flags lflags; + int dflags; +}; + /* * Simple definition of a single GPIO under a con_id */ @@ -59,10 +76,23 @@ struct gpiod_lookup_table { .flags = _flags, \ } +/* + * Simple definition of a single GPIO hog in an array. + */ +#define GPIO_HOG(_chip_label, _chip_hwnum, _line_name, _lflags, _dflags) \ +{ \ + .chip_label = _chip_label, \ + .chip_hwnum = _chip_hwnum, \ + .line_name = _line_name, \ + .lflags = _lflags, \ + .dflags = _dflags, \ +} + #ifdef CONFIG_GPIOLIB void gpiod_add_lookup_table(struct gpiod_lookup_table *table); void gpiod_add_lookup_tables(struct gpiod_lookup_table **tables, size_t n); void gpiod_remove_lookup_table(struct gpiod_lookup_table *table); +void gpiod_add_hogs(struct gpiod_hog *hogs); #else static inline void gpiod_add_lookup_table(struct gpiod_lookup_table *table) {} @@ -70,6 +100,7 @@ static inline void gpiod_add_lookup_tables(struct gpiod_lookup_table **tables, size_t n) {} static inline void gpiod_remove_lookup_table(struct gpiod_lookup_table *table) {} +static inline void gpiod_add_hogs(struct gpiod_hog *hogs) {} #endif #endif /* __LINUX_GPIO_MACHINE_H */ -- cgit v1.2.3 From e6ca26abd37606ba4864f20c85d3fe4a2173b93f Mon Sep 17 00:00:00 2001 From: Phil Edworthy Date: Thu, 26 Apr 2018 17:19:47 +0100 Subject: gpio: dwapb: Add support for 1 interrupt per port A GPIO The DesignWare GPIO IP can be configured for either 1 interrupt or 1 per GPIO in port A, but the driver currently only supports 1 interrupt. See the DesignWare DW_apb_gpio Databook description of the 'GPIO_INTR_IO' parameter. This change allows the driver to work with up to 32 interrupts, it will get as many interrupts as specified in the DT 'interrupts' property. It doesn't do anything clever with the different interrupts, it just calls the same handler used for single interrupt hardware. ACPI companion code provided by Hoan Tran . This was tested on X-Gene by Hoan. Signed-off-by: Phil Edworthy Reviewed-by: Rob Herring Acked-by: Lee Jones Acked-by: Hoan Tran Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-dwapb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-dwapb.h b/include/linux/platform_data/gpio-dwapb.h index 2dc7f4a8ab09..5a52d69c13f3 100644 --- a/include/linux/platform_data/gpio-dwapb.h +++ b/include/linux/platform_data/gpio-dwapb.h @@ -19,7 +19,8 @@ struct dwapb_port_property { unsigned int idx; unsigned int ngpio; unsigned int gpio_base; - unsigned int irq; + unsigned int irq[32]; + bool has_irq; bool irq_shared; }; -- cgit v1.2.3 From c59b3715ac16544f8f68ab7af03f108e339b36aa Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 16 May 2018 21:08:42 +0200 Subject: rtc: nvmem: don't return an error when not enabled Avoid reporting an error when RTC_NVMEM is not selected. Reported-by: kernel test robot Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 4c007f69082f..6268208760e9 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -285,7 +285,7 @@ void rtc_nvmem_unregister(struct rtc_device *rtc); static inline int rtc_nvmem_register(struct rtc_device *rtc, struct nvmem_config *nvmem_config) { - return -ENODEV; + return 0; } static inline void rtc_nvmem_unregister(struct rtc_device *rtc) {} #endif -- cgit v1.2.3 From be2d04d11fd33bd46622f94619aae1596d9f9303 Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Wed, 16 May 2018 22:27:41 +0200 Subject: bpf: add __printf verification to bpf_verifier_vlog MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit __printf is useful to verify format and arguments. ‘bpf_verifier_vlog’ function is used twice in verifier.c in both cases the caller function already uses the __printf gcc attribute. Remove the following warning, triggered with W=1: kernel/bpf/verifier.c:176:2: warning: function might be possible candidate for ‘gnu_printf’ format attribute [-Wsuggest-attribute=format] Signed-off-by: Mathieu Malaterre Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 8f70dc181e23..c286813deaeb 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -200,8 +200,8 @@ struct bpf_verifier_env { u32 subprog_cnt; }; -void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, - va_list args); +__printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, + const char *fmt, va_list args); __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); -- cgit v1.2.3 From 71c6e8638ce3baf9ec16d64d263aab74beac912d Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Sun, 13 May 2018 14:33:34 +0300 Subject: IB/mlx5: Add support for MPLS flow specification This patch introduces support for the MPLS flow spec and allows the creation of rules that are matching on the MPLS label. Applying the rule matching depends on the flow specs order and the location of the MPLS in the spec list as there are different configurations to be made in the device in the cases of MPLSoGRE and MPLSoUDP vs. non-encapsulated MPLS. Reviewed-by: Mark Bloch Signed-off-by: Ariel Levkovich Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/device.h | 7 +++++++ include/linux/mlx5/mlx5_ifc.h | 45 +++++++++++++++++++++++++++++++++++++------ 2 files changed, 46 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 2bc27f8c5b87..fd1a9341edfa 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -994,6 +994,13 @@ enum mlx5_wol_mode { MLX5_WOL_PHY_ACTIVITY = 1 << 7, }; +enum mlx5_mpls_supported_fields { + MLX5_FIELD_SUPPORT_MPLS_LABEL = 1 << 0, + MLX5_FIELD_SUPPORT_MPLS_EXP = 1 << 1, + MLX5_FIELD_SUPPORT_MPLS_S_BOS = 1 << 2, + MLX5_FIELD_SUPPORT_MPLS_TTL = 1 << 3 +}; + /* MLX5 DEV CAPs */ /* TODO: EAT.ME */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1aad455538f4..3fee2f74d09d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -298,9 +298,15 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 inner_tcp_dport[0x1]; u8 inner_tcp_flags[0x1]; u8 reserved_at_37[0x9]; - u8 reserved_at_40[0x17]; + + u8 reserved_at_40[0x5]; + u8 outer_first_mpls_over_udp[0x4]; + u8 outer_first_mpls_over_gre[0x4]; + u8 inner_first_mpls[0x4]; + u8 outer_first_mpls[0x4]; + u8 reserved_at_55[0x2]; u8 outer_esp_spi[0x1]; - u8 reserved_at_58[0x2]; + u8 reserved_at_58[0x2]; u8 bth_dst_qp[0x1]; u8 reserved_at_5b[0x25]; @@ -450,6 +456,29 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 reserved_at_1a0[0x60]; }; +struct mlx5_ifc_fte_match_mpls_bits { + u8 mpls_label[0x14]; + u8 mpls_exp[0x3]; + u8 mpls_s_bos[0x1]; + u8 mpls_ttl[0x8]; +}; + +struct mlx5_ifc_fte_match_set_misc2_bits { + struct mlx5_ifc_fte_match_mpls_bits outer_first_mpls; + + struct mlx5_ifc_fte_match_mpls_bits inner_first_mpls; + + struct mlx5_ifc_fte_match_mpls_bits outer_first_mpls_over_gre; + + struct mlx5_ifc_fte_match_mpls_bits outer_first_mpls_over_udp; + + u8 reserved_at_80[0x100]; + + u8 metadata_reg_a[0x20]; + + u8 reserved_at_1a0[0x60]; +}; + struct mlx5_ifc_cmd_pas_bits { u8 pa_h[0x20]; @@ -1170,7 +1199,9 @@ struct mlx5_ifc_fte_match_param_bits { struct mlx5_ifc_fte_match_set_lyr_2_4_bits inner_headers; - u8 reserved_at_600[0xa00]; + struct mlx5_ifc_fte_match_set_misc2_bits misc_parameters_2; + + u8 reserved_at_800[0x800]; }; enum { @@ -4579,6 +4610,7 @@ enum { MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_INNER_HEADERS = 0x2, + MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0X3, }; struct mlx5_ifc_query_flow_group_out_bits { @@ -6969,9 +7001,10 @@ struct mlx5_ifc_create_flow_group_out_bits { }; enum { - MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, - MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, - MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_INNER_HEADERS = 0x2, + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_INNER_HEADERS = 0x2, + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0x3, }; struct mlx5_ifc_create_flow_group_in_bits { -- cgit v1.2.3 From e818e255a58d64e86c8c93e3aa52498b1a3d1760 Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Sun, 13 May 2018 14:33:35 +0300 Subject: IB/mlx5: Expose MPLS related tunneling offloads This patch reports the device's capbilities to offload encapsulated MPLS tunnel protocols to user-space: - Capability to offload MPLS over GRE. - Capability to offload MPLS over UDP. Reviewed-by: Mark Bloch Signed-off-by: Ariel Levkovich Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/device.h | 5 +++++ include/linux/mlx5/mlx5_ifc.h | 4 +++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index fd1a9341edfa..5004ddc702e3 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1001,6 +1001,11 @@ enum mlx5_mpls_supported_fields { MLX5_FIELD_SUPPORT_MPLS_TTL = 1 << 3 }; +enum mlx5_flex_parser_protos { + MLX5_FLEX_PROTO_CW_MPLS_GRE = 1 << 4, + MLX5_FLEX_PROTO_CW_MPLS_UDP = 1 << 5, +}; + /* MLX5 DEV CAPs */ /* TODO: EAT.ME */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3fee2f74d09d..68f756ea550d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1138,7 +1138,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_500[0x20]; u8 num_of_uars_per_page[0x20]; - u8 reserved_at_540[0x40]; + + u8 flex_parser_protocols[0x20]; + u8 reserved_at_560[0x20]; u8 reserved_at_580[0x3d]; u8 cqe_128_always[0x1]; -- cgit v1.2.3 From 84b3a7c9c6befe5ab4d49070fe7bcab2da22637e Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 15 May 2018 15:07:17 -0700 Subject: regulator: core: Allow for regulators that can't be read at bootup Regulators attached via RPMh on Qualcomm sdm845 apparently are write-only. Specifically you can send a request for a certain voltage but you can't read back to see what voltage you've requested. What this means is that at bootup we have absolutely no idea what voltage we could be at. As discussed in the patches to try to support the RPMh regulators [1], the fact that regulators are write-only means that its driver's get_voltage_sel() should return an error code if it's called before any calls to set_voltage_sel(). This causes problems in machine_constraints_voltage() when trying to apply the constraints. A proposed fix was to come up with an error code that could be returned by get_voltage_sel() which would cause the regulator framework to simply try setting the voltage with the current constraints. In this patch I propose the error code -ENOTRECOVERABLE. In errno.h this error is described as "State not recoverable". Though the error code was originally intended "for robust mutexes", the description of the error code seems to apply here because we can't read the state of the regulator. Also note that the only existing user of this error code in the regulator framework is tps65090-regulator.c which returns this error code from the enable() call (not get_voltage() or get_voltage_sel()), so there should be no existing regulators that might accidentally get the new behavior. (Side note is that tps65090 seems to interpret this error code to mean an error that you can't recover from rather than some data that can't be recovered). [1] https://patchwork.kernel.org/patch/10340897/ Signed-off-by: Douglas Anderson Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 4fc96cb8e5d7..14e512ad6d4f 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -81,9 +81,12 @@ struct regulator_linear_range { * @set_voltage_sel: Set the voltage for the regulator using the specified * selector. * @map_voltage: Convert a voltage into a selector - * @get_voltage: Return the currently configured voltage for the regulator. + * @get_voltage: Return the currently configured voltage for the regulator; + * return -ENOTRECOVERABLE if regulator can't be read at + * bootup and hasn't been set yet. * @get_voltage_sel: Return the currently configured voltage selector for the - * regulator. + * regulator; return -ENOTRECOVERABLE if regulator can't + * be read at bootup and hasn't been set yet. * @list_voltage: Return one of the supported voltages, in microvolts; zero * if the selector indicates a voltage that is unusable on this system; * or negative errno. Selectors range from zero to one less than -- cgit v1.2.3 From e1739e86f0cb9c48e8745a610e6981a4e24cadad Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 14 May 2018 10:06:24 +0200 Subject: regulator: arizona-ldo1: Look up a descriptor and pass to the core Instead of passing a global GPIO number, pass a descriptor looked up with the standard devm_gpiod_get_optional() call. We have augmented the GPIO core to look up the regulator special GPIO "wlf,ldoena" in commit 6a537d48461d "gpio: of: Support regulator nonstandard GPIO properties". Signed-off-by: Linus Walleij Acked-by: Charles Keepax Signed-off-by: Mark Brown --- include/linux/regulator/arizona-ldo1.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/arizona-ldo1.h b/include/linux/regulator/arizona-ldo1.h index c685f1277c63..fe74ab9990e6 100644 --- a/include/linux/regulator/arizona-ldo1.h +++ b/include/linux/regulator/arizona-ldo1.h @@ -14,9 +14,6 @@ struct regulator_init_data; struct arizona_ldo1_pdata { - /** GPIO controlling LDOENA, if any */ - int ldoena; - /** Regulator configuration for LDO1 */ const struct regulator_init_data *init_data; }; -- cgit v1.2.3 From 66cf9a7e0192734c1c94751e628bd075be62cff4 Mon Sep 17 00:00:00 2001 From: Maciej Purski Date: Mon, 23 Apr 2018 16:33:37 +0200 Subject: regulator: core: Make locks re-entrant Setting voltage, enabling/disabling regulators requires operations on all regulators related with the regulator being changed. Therefore, all of them should be locked for the whole operation. With the current locking implementation, adding additional dependency (regulators coupling) causes deadlocks in some cases. Introduce a possibility to attempt to lock a mutex multiple times by the same task without waiting on a mutex. This should handle all reasonable coupling-supplying combinations, especially when two coupled regulators share common supplies. The only situation that should be forbidden is simultaneous coupling and supplying between a pair of regulators. The idea is based on clk core. Signed-off-by: Maciej Purski Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 14e512ad6d4f..c2a181fa7287 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -434,6 +434,8 @@ struct regulator_dev { struct blocking_notifier_head notifier; struct mutex mutex; /* consumer lock */ + struct task_struct *mutex_owner; + int ref_cnt; struct module *owner; struct device dev; struct regulation_constraints *constraints; -- cgit v1.2.3 From a085a31af566254fb8f7721911c828c8fa797894 Mon Sep 17 00:00:00 2001 From: Maciej Purski Date: Mon, 23 Apr 2018 16:33:39 +0200 Subject: regulator: core: Parse coupled regulators properties On Odroid XU3/4 and other Exynos5422 based boards there is a case, that different devices on the board are supplied by different regulators with non-fixed voltages. If one of these devices temporarily requires higher voltage, there might occur a situation that the spread between devices' voltages is so high, that there is a risk of changing 'high' and 'low' states on the interconnection between devices powered by those regulators. Add new structure "coupling_desc" to regulator_dev, which contains pointers to all coupled regulators including the owner of the structure, number of coupled regulators and counter of currently resolved regulators. Add of_functions to parse all data needed in regulator coupling. Provide method to check DTS data consistency. Check if each coupled regulator's max_spread is equal and if their lists of regulators match. Signed-off-by: Maciej Purski Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 18 ++++++++++++++++++ include/linux/regulator/machine.h | 4 ++++ 2 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index c2a181fa7287..fc2dc8df476f 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -15,6 +15,8 @@ #ifndef __LINUX_REGULATOR_DRIVER_H_ #define __LINUX_REGULATOR_DRIVER_H_ +#define MAX_COUPLED 4 + #include #include #include @@ -409,6 +411,20 @@ struct regulator_config { unsigned int ena_gpio_flags; }; +/* + * struct coupling_desc + * + * Describes coupling of regulators. Each regulator should have + * at least a pointer to itself in coupled_rdevs array. + * When a new coupled regulator is resolved, n_resolved is + * incremented. + */ +struct coupling_desc { + struct regulator_dev *coupled_rdevs[MAX_COUPLED]; + int n_resolved; + int n_coupled; +}; + /* * struct regulator_dev * @@ -432,6 +448,8 @@ struct regulator_dev { /* lists we own */ struct list_head consumer_list; /* consumers we supply */ + struct coupling_desc coupling_desc; + struct blocking_notifier_head notifier; struct mutex mutex; /* consumer lock */ struct task_struct *mutex_owner; diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 93a04893c739..3468703d663a 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -103,6 +103,7 @@ struct regulator_state { * @ilim_uA: Maximum input current. * @system_load: Load that isn't captured by any consumer requests. * + * @max_spread: Max possible spread between coupled regulators * @valid_modes_mask: Mask of modes which may be configured by consumers. * @valid_ops_mask: Operations which may be performed by consumers. * @@ -154,6 +155,9 @@ struct regulation_constraints { int system_load; + /* used for coupled regulators */ + int max_spread; + /* valid regulator operating modes for this machine */ unsigned int valid_modes_mask; -- cgit v1.2.3 From 3c6b38d45fa51c7c51c5e2347fc1a6bef6a46525 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 14 May 2018 10:06:34 +0200 Subject: regulator: wm8994: Pass descriptor instead of GPIO number Instead of passing a global GPIO number for the enable GPIO, pass a descriptor looked up from the device tree node or the board file decriptor table for the regulator. There is a single board file passing the GPIOs for LDO1 and LDO2 through platform data, so augment this to pass descriptors associated with the i2c device as well. The special GPIO enable DT property for the enable GPIO is nonstandard but this was accomodated in commit 6a537d48461deacc57c07ed86d9915e5aa4b3539 "gpio: of: Support regulator nonstandard GPIO properties". Signed-off-by: Linus Walleij Acked-by: Charles Keepax Acked-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/wm8994/pdata.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8994/pdata.h b/include/linux/mfd/wm8994/pdata.h index 90c60524a496..fca67bd194e2 100644 --- a/include/linux/mfd/wm8994/pdata.h +++ b/include/linux/mfd/wm8994/pdata.h @@ -20,9 +20,6 @@ #define WM8994_NUM_AIF 3 struct wm8994_ldo_pdata { - /** GPIOs to enable regulator, 0 or less if not available */ - int enable; - const struct regulator_init_data *init_data; }; -- cgit v1.2.3 From 421bf6a1f061a6edba47e5e7a5458f29eb791de9 Mon Sep 17 00:00:00 2001 From: Akshu Agrawal Date: Wed, 9 May 2018 17:59:00 +0800 Subject: clk: x86: Add ST oscout platform clock Stoney SoC provides oscout clock. This clock can support 25Mhz and 48Mhz of frequency. The clock is available for general system use. Signed-off-by: Akshu Agrawal Reviewed-by: Daniel Kurtz Reviewed-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/platform_data/clk-st.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/linux/platform_data/clk-st.h (limited to 'include/linux') diff --git a/include/linux/platform_data/clk-st.h b/include/linux/platform_data/clk-st.h new file mode 100644 index 000000000000..7cdb6a402b35 --- /dev/null +++ b/include/linux/platform_data/clk-st.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: MIT */ +/* + * clock framework for AMD Stoney based clock + * + * Copyright 2018 Advanced Micro Devices, Inc. + */ + +#ifndef __CLK_ST_H +#define __CLK_ST_H + +#include + +struct st_clk_data { + void __iomem *base; +}; + +#endif /* __CLK_ST_H */ -- cgit v1.2.3 From 63dcc7090137a893322432e156d66be3ce104615 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 15 May 2018 20:32:02 +0300 Subject: device property: Get rid of union aliasing Commit 318a19718261 (device property: refactor built-in properties support) went way too far and brought a union aliasing. Partially revert it here to get rid of union aliasing. Note, all Apple properties are considered as u8 arrays. To get a value of any of them the caller must use device_property_read_u8_array(). What's union aliasing? ~~~~~~~~~~~~~~~~~~~~~~ The C99 standard in section 6.2.5 paragraph 20 defines union type as "an overlapping nonempty set of member objects". It also states in section 6.7.2.1 paragraph 14 that "the value of at most one of the members can be stored in a union object at any time'. Union aliasing is a type punning mechanism using union members to store as one type and read back as another. Why it's not good? ~~~~~~~~~~~~~~~~~~ Section 6.2.6.1 paragraph 6 says that a union object may not be a trap representation, although its member objects may be. Meanwhile annex J.1 says that "the value of a union member other than the last one stored into" is unspecified [removed in C11]. In TC3, a footnote is added which specifies that accessing a member of a union other than the last one stored causes "the object representation" to be re-interpreted in the new type and specifically refers to this as "type punning". This conflicts to some degree with Annex J.1. While it's working in Linux with GCC, the use of union members to do type punning is not clear area in the C standard and might lead to unspecified behaviour. More information is available in this [1] blog post. [1]: https://davmac.wordpress.com/2010/02/26/c99-revisited/ Signed-off-by: Andy Shevchenko Acked-by: Ard Biesheuvel Reviewed-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 52 +++++++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 2eea4b310fc2..ac8a1ebc4c1b 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -178,7 +178,7 @@ static inline int fwnode_property_read_u64(const struct fwnode_handle *fwnode, * @name: Name of the property. * @length: Length of data making up the value. * @is_array: True when the property is an array. - * @is_string: True when property is a string. + * @type: Type of the data in unions. * @pointer: Pointer to the property (an array of items of the given type). * @value: Value of the property (when it is a single item of the given type). */ @@ -186,10 +186,9 @@ struct property_entry { const char *name; size_t length; bool is_array; - bool is_string; + enum dev_prop_type type; union { union { - const void *raw_data; const u8 *u8_data; const u16 *u16_data; const u32 *u32_data; @@ -197,7 +196,6 @@ struct property_entry { const char * const *str; } pointer; union { - unsigned long long raw_data; u8 u8_data; u16 u16_data; u32 u32_data; @@ -213,55 +211,55 @@ struct property_entry { * and structs. */ -#define PROPERTY_ENTRY_INTEGER_ARRAY(_name_, _type_, _val_) \ -(struct property_entry) { \ - .name = _name_, \ - .length = ARRAY_SIZE(_val_) * sizeof(_type_), \ - .is_array = true, \ - .is_string = false, \ - { .pointer = { ._type_##_data = _val_ } }, \ +#define PROPERTY_ENTRY_INTEGER_ARRAY(_name_, _type_, _Type_, _val_) \ +(struct property_entry) { \ + .name = _name_, \ + .length = ARRAY_SIZE(_val_) * sizeof(_type_), \ + .is_array = true, \ + .type = DEV_PROP_##_Type_, \ + { .pointer = { ._type_##_data = _val_ } }, \ } #define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u8, _val_) + PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u8, U8, _val_) #define PROPERTY_ENTRY_U16_ARRAY(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u16, _val_) + PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u16, U16, _val_) #define PROPERTY_ENTRY_U32_ARRAY(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u32, _val_) + PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u32, U32, _val_) #define PROPERTY_ENTRY_U64_ARRAY(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u64, _val_) + PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u64, U64, _val_) #define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_) \ (struct property_entry) { \ .name = _name_, \ .length = ARRAY_SIZE(_val_) * sizeof(const char *), \ .is_array = true, \ - .is_string = true, \ + .type = DEV_PROP_STRING, \ { .pointer = { .str = _val_ } }, \ } -#define PROPERTY_ENTRY_INTEGER(_name_, _type_, _val_) \ -(struct property_entry) { \ - .name = _name_, \ - .length = sizeof(_type_), \ - .is_string = false, \ - { .value = { ._type_##_data = _val_ } }, \ +#define PROPERTY_ENTRY_INTEGER(_name_, _type_, _Type_, _val_) \ +(struct property_entry) { \ + .name = _name_, \ + .length = sizeof(_type_), \ + .type = DEV_PROP_##_Type_, \ + { .value = { ._type_##_data = _val_ } }, \ } #define PROPERTY_ENTRY_U8(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER(_name_, u8, _val_) + PROPERTY_ENTRY_INTEGER(_name_, u8, U8, _val_) #define PROPERTY_ENTRY_U16(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER(_name_, u16, _val_) + PROPERTY_ENTRY_INTEGER(_name_, u16, U16, _val_) #define PROPERTY_ENTRY_U32(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER(_name_, u32, _val_) + PROPERTY_ENTRY_INTEGER(_name_, u32, U32, _val_) #define PROPERTY_ENTRY_U64(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER(_name_, u64, _val_) + PROPERTY_ENTRY_INTEGER(_name_, u64, U64, _val_) #define PROPERTY_ENTRY_STRING(_name_, _val_) \ (struct property_entry) { \ .name = _name_, \ .length = sizeof(_val_), \ - .is_string = true, \ + .type = DEV_PROP_STRING, \ { .value = { .str = _val_ } }, \ } -- cgit v1.2.3 From 01cd267bff52619a53fa05c930ea5ed53493d21a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 May 2018 10:05:38 +0200 Subject: netfilter: fix fallout from xt/nf osf separation Stephen Rothwell says: today's linux-next build (x86_64 allmodconfig) produced this warning: ./usr/include/linux/netfilter/nf_osf.h:25: found __[us]{8,16,32,64} type without #include Fix that up and also move kernel-private struct out of uapi (it was not exposed in any released kernel version). tested via allmodconfig build + make headers_check. Reported-by: Stephen Rothwell Fixes: bfb15f2a95cb ("netfilter: extract Passive OS fingerprint infrastructure from xt_osf") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_osf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h index a2b39602e87d..0e114c492fb8 100644 --- a/include/linux/netfilter/nf_osf.h +++ b/include/linux/netfilter/nf_osf.h @@ -21,6 +21,12 @@ enum osf_fmatch_states { FMATCH_OPT_WRONG, }; +struct nf_osf_finger { + struct rcu_head rcu_head; + struct list_head finger_entry; + struct nf_osf_user_finger finger; +}; + bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, int hooknum, struct net_device *in, struct net_device *out, const struct nf_osf_info *info, struct net *net, -- cgit v1.2.3 From 94e58e0ac31284fa26597c0e00a9b1d87a691d02 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 9 May 2018 16:23:49 +0900 Subject: export.h: remove code for prefixing symbols with underscore CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX was selected by BLACKFIN, METAG. They were removed by commit 4ba66a976072 ("arch: remove blackfin port"), commit bb6fb6dfcc17 ("metag: Remove arch/metag/"), respectively. No more architecture enables CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX. Clean up the export.h headers. I am keeping VMLINUX_SYMBOL() and VMLINUX_SYMBOL_STR() because they are widely used. Signed-off-by: Masahiro Yamada Reviewed-by: Sam Ravnborg --- include/linux/export.h | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index 1a1dfdb2a5c6..b768d6dd3c90 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -10,14 +10,8 @@ * hackers place grumpy comments in header files. */ -/* Some toolchains use a `_' prefix for all user symbols. */ -#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX -#define __VMLINUX_SYMBOL(x) _##x -#define __VMLINUX_SYMBOL_STR(x) "_" #x -#else #define __VMLINUX_SYMBOL(x) x #define __VMLINUX_SYMBOL_STR(x) #x -#endif /* Indirect, so macros are expanded before pasting. */ #define VMLINUX_SYMBOL(x) __VMLINUX_SYMBOL(x) @@ -46,14 +40,14 @@ extern struct module __this_module; #if defined(CONFIG_MODULE_REL_CRCS) #define __CRC_SYMBOL(sym, sec) \ asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \ - " .weak " VMLINUX_SYMBOL_STR(__crc_##sym) " \n" \ - " .long " VMLINUX_SYMBOL_STR(__crc_##sym) " - . \n" \ + " .weak __crc_" #sym " \n" \ + " .long __crc_" #sym " - . \n" \ " .previous \n"); #else #define __CRC_SYMBOL(sym, sec) \ asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \ - " .weak " VMLINUX_SYMBOL_STR(__crc_##sym) " \n" \ - " .long " VMLINUX_SYMBOL_STR(__crc_##sym) " \n" \ + " .weak __crc_" #sym " \n" \ + " .long __crc_" #sym " \n" \ " .previous \n"); #endif #else @@ -66,7 +60,7 @@ extern struct module __this_module; __CRC_SYMBOL(sym, sec) \ static const char __kstrtab_##sym[] \ __attribute__((section("__ksymtab_strings"), aligned(1))) \ - = VMLINUX_SYMBOL_STR(sym); \ + = #sym; \ static const struct kernel_symbol __ksymtab_##sym \ __used \ __attribute__((section("___ksymtab" sec "+" #sym), used)) \ -- cgit v1.2.3 From 1e9d42194e4c8f0ba3f9d4f72b5f54050ddf7a39 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 19 Apr 2018 22:00:07 +0200 Subject: i2c: gpio: move header to platform_data This header only contains platform_data. Move it to the proper directory. Signed-off-by: Wolfram Sang Acked-by: Tony Lindgren Acked-by: Lee Jones Acked-by: Robert Jarzmik Acked-by: Mauro Carvalho Chehab Acked-by: James Hogan Acked-by: Greg Ungerer --- include/linux/i2c-gpio.h | 34 ---------------------------------- include/linux/platform_data/i2c-gpio.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 34 deletions(-) delete mode 100644 include/linux/i2c-gpio.h create mode 100644 include/linux/platform_data/i2c-gpio.h (limited to 'include/linux') diff --git a/include/linux/i2c-gpio.h b/include/linux/i2c-gpio.h deleted file mode 100644 index 352c1426fd4d..000000000000 --- a/include/linux/i2c-gpio.h +++ /dev/null @@ -1,34 +0,0 @@ -/* - * i2c-gpio interface to platform code - * - * Copyright (C) 2007 Atmel Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#ifndef _LINUX_I2C_GPIO_H -#define _LINUX_I2C_GPIO_H - -/** - * struct i2c_gpio_platform_data - Platform-dependent data for i2c-gpio - * @udelay: signal toggle delay. SCL frequency is (500 / udelay) kHz - * @timeout: clock stretching timeout in jiffies. If the slave keeps - * SCL low for longer than this, the transfer will time out. - * @sda_is_open_drain: SDA is configured as open drain, i.e. the pin - * isn't actively driven high when setting the output value high. - * gpio_get_value() must return the actual pin state even if the - * pin is configured as an output. - * @scl_is_open_drain: SCL is set up as open drain. Same requirements - * as for sda_is_open_drain apply. - * @scl_is_output_only: SCL output drivers cannot be turned off. - */ -struct i2c_gpio_platform_data { - int udelay; - int timeout; - unsigned int sda_is_open_drain:1; - unsigned int scl_is_open_drain:1; - unsigned int scl_is_output_only:1; -}; - -#endif /* _LINUX_I2C_GPIO_H */ diff --git a/include/linux/platform_data/i2c-gpio.h b/include/linux/platform_data/i2c-gpio.h new file mode 100644 index 000000000000..352c1426fd4d --- /dev/null +++ b/include/linux/platform_data/i2c-gpio.h @@ -0,0 +1,34 @@ +/* + * i2c-gpio interface to platform code + * + * Copyright (C) 2007 Atmel Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _LINUX_I2C_GPIO_H +#define _LINUX_I2C_GPIO_H + +/** + * struct i2c_gpio_platform_data - Platform-dependent data for i2c-gpio + * @udelay: signal toggle delay. SCL frequency is (500 / udelay) kHz + * @timeout: clock stretching timeout in jiffies. If the slave keeps + * SCL low for longer than this, the transfer will time out. + * @sda_is_open_drain: SDA is configured as open drain, i.e. the pin + * isn't actively driven high when setting the output value high. + * gpio_get_value() must return the actual pin state even if the + * pin is configured as an output. + * @scl_is_open_drain: SCL is set up as open drain. Same requirements + * as for sda_is_open_drain apply. + * @scl_is_output_only: SCL output drivers cannot be turned off. + */ +struct i2c_gpio_platform_data { + int udelay; + int timeout; + unsigned int sda_is_open_drain:1; + unsigned int scl_is_open_drain:1; + unsigned int scl_is_output_only:1; +}; + +#endif /* _LINUX_I2C_GPIO_H */ -- cgit v1.2.3 From 62ea22c4954f5b147488eefa644d668e843be6f7 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 19 Apr 2018 22:00:08 +0200 Subject: i2c: mux: gpio: move header to platform_data This header only contains platform_data. Move it to the proper directory. Signed-off-by: Wolfram Sang Acked-by: Peter Korsgaard --- include/linux/i2c-mux-gpio.h | 43 ------------------------------ include/linux/platform_data/i2c-mux-gpio.h | 43 ++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+), 43 deletions(-) delete mode 100644 include/linux/i2c-mux-gpio.h create mode 100644 include/linux/platform_data/i2c-mux-gpio.h (limited to 'include/linux') diff --git a/include/linux/i2c-mux-gpio.h b/include/linux/i2c-mux-gpio.h deleted file mode 100644 index 4406108201fe..000000000000 --- a/include/linux/i2c-mux-gpio.h +++ /dev/null @@ -1,43 +0,0 @@ -/* - * i2c-mux-gpio interface to platform code - * - * Peter Korsgaard - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef _LINUX_I2C_MUX_GPIO_H -#define _LINUX_I2C_MUX_GPIO_H - -/* MUX has no specific idle mode */ -#define I2C_MUX_GPIO_NO_IDLE ((unsigned)-1) - -/** - * struct i2c_mux_gpio_platform_data - Platform-dependent data for i2c-mux-gpio - * @parent: Parent I2C bus adapter number - * @base_nr: Base I2C bus number to number adapters from or zero for dynamic - * @values: Array of bitmasks of GPIO settings (low/high) for each - * position - * @n_values: Number of multiplexer positions (busses to instantiate) - * @classes: Optional I2C auto-detection classes - * @gpio_chip: Optional GPIO chip name; if set, GPIO pin numbers are given - * relative to the base GPIO number of that chip - * @gpios: Array of GPIO numbers used to control MUX - * @n_gpios: Number of GPIOs used to control MUX - * @idle: Bitmask to write to MUX when idle or GPIO_I2CMUX_NO_IDLE if not used - */ -struct i2c_mux_gpio_platform_data { - int parent; - int base_nr; - const unsigned *values; - int n_values; - const unsigned *classes; - char *gpio_chip; - const unsigned *gpios; - int n_gpios; - unsigned idle; -}; - -#endif /* _LINUX_I2C_MUX_GPIO_H */ diff --git a/include/linux/platform_data/i2c-mux-gpio.h b/include/linux/platform_data/i2c-mux-gpio.h new file mode 100644 index 000000000000..4406108201fe --- /dev/null +++ b/include/linux/platform_data/i2c-mux-gpio.h @@ -0,0 +1,43 @@ +/* + * i2c-mux-gpio interface to platform code + * + * Peter Korsgaard + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_I2C_MUX_GPIO_H +#define _LINUX_I2C_MUX_GPIO_H + +/* MUX has no specific idle mode */ +#define I2C_MUX_GPIO_NO_IDLE ((unsigned)-1) + +/** + * struct i2c_mux_gpio_platform_data - Platform-dependent data for i2c-mux-gpio + * @parent: Parent I2C bus adapter number + * @base_nr: Base I2C bus number to number adapters from or zero for dynamic + * @values: Array of bitmasks of GPIO settings (low/high) for each + * position + * @n_values: Number of multiplexer positions (busses to instantiate) + * @classes: Optional I2C auto-detection classes + * @gpio_chip: Optional GPIO chip name; if set, GPIO pin numbers are given + * relative to the base GPIO number of that chip + * @gpios: Array of GPIO numbers used to control MUX + * @n_gpios: Number of GPIOs used to control MUX + * @idle: Bitmask to write to MUX when idle or GPIO_I2CMUX_NO_IDLE if not used + */ +struct i2c_mux_gpio_platform_data { + int parent; + int base_nr; + const unsigned *values; + int n_values; + const unsigned *classes; + char *gpio_chip; + const unsigned *gpios; + int n_gpios; + unsigned idle; +}; + +#endif /* _LINUX_I2C_MUX_GPIO_H */ -- cgit v1.2.3 From 985ecf00375bde7d80be03a749f5b94d5ba77ac8 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 19 Apr 2018 22:00:09 +0200 Subject: i2c: ocores: move header to platform_data This header only contains platform_data. Move it to the proper directory. Signed-off-by: Wolfram Sang Acked-by: Lee Jones --- include/linux/i2c-ocores.h | 23 ----------------------- include/linux/platform_data/i2c-ocores.h | 23 +++++++++++++++++++++++ 2 files changed, 23 insertions(+), 23 deletions(-) delete mode 100644 include/linux/i2c-ocores.h create mode 100644 include/linux/platform_data/i2c-ocores.h (limited to 'include/linux') diff --git a/include/linux/i2c-ocores.h b/include/linux/i2c-ocores.h deleted file mode 100644 index 01edd96fe1f7..000000000000 --- a/include/linux/i2c-ocores.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * i2c-ocores.h - definitions for the i2c-ocores interface - * - * Peter Korsgaard - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ - -#ifndef _LINUX_I2C_OCORES_H -#define _LINUX_I2C_OCORES_H - -struct ocores_i2c_platform_data { - u32 reg_shift; /* register offset shift value */ - u32 reg_io_width; /* register io read/write width */ - u32 clock_khz; /* input clock in kHz */ - bool big_endian; /* registers are big endian */ - u8 num_devices; /* number of devices in the devices list */ - struct i2c_board_info const *devices; /* devices connected to the bus */ -}; - -#endif /* _LINUX_I2C_OCORES_H */ diff --git a/include/linux/platform_data/i2c-ocores.h b/include/linux/platform_data/i2c-ocores.h new file mode 100644 index 000000000000..01edd96fe1f7 --- /dev/null +++ b/include/linux/platform_data/i2c-ocores.h @@ -0,0 +1,23 @@ +/* + * i2c-ocores.h - definitions for the i2c-ocores interface + * + * Peter Korsgaard + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#ifndef _LINUX_I2C_OCORES_H +#define _LINUX_I2C_OCORES_H + +struct ocores_i2c_platform_data { + u32 reg_shift; /* register offset shift value */ + u32 reg_io_width; /* register io read/write width */ + u32 clock_khz; /* input clock in kHz */ + bool big_endian; /* registers are big endian */ + u8 num_devices; /* number of devices in the devices list */ + struct i2c_board_info const *devices; /* devices connected to the bus */ +}; + +#endif /* _LINUX_I2C_OCORES_H */ -- cgit v1.2.3 From 79fc540fd543f47e77e1c7d407f2c082872a4625 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 19 Apr 2018 22:00:10 +0200 Subject: i2c: omap: move header to platform_data This header only contains platform_data. Move it to the proper directory. Signed-off-by: Wolfram Sang Acked-by: Tony Lindgren --- include/linux/i2c-omap.h | 39 ---------------------------------- include/linux/platform_data/i2c-omap.h | 39 ++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+), 39 deletions(-) delete mode 100644 include/linux/i2c-omap.h create mode 100644 include/linux/platform_data/i2c-omap.h (limited to 'include/linux') diff --git a/include/linux/i2c-omap.h b/include/linux/i2c-omap.h deleted file mode 100644 index 3444265ee8ee..000000000000 --- a/include/linux/i2c-omap.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __I2C_OMAP_H__ -#define __I2C_OMAP_H__ - -#include - -/* - * Version 2 of the I2C peripheral unit has a different register - * layout and extra registers. The ID register in the V2 peripheral - * unit on the OMAP4430 reports the same ID as the V1 peripheral - * unit on the OMAP3530, so we must inform the driver which IP - * version we know it is running on from platform / cpu-specific - * code using these constants in the hwmod class definition. - */ - -#define OMAP_I2C_IP_VERSION_1 1 -#define OMAP_I2C_IP_VERSION_2 2 - -/* struct omap_i2c_bus_platform_data .flags meanings */ - -#define OMAP_I2C_FLAG_NO_FIFO BIT(0) -#define OMAP_I2C_FLAG_SIMPLE_CLOCK BIT(1) -#define OMAP_I2C_FLAG_16BIT_DATA_REG BIT(2) -#define OMAP_I2C_FLAG_ALWAYS_ARMXOR_CLK BIT(5) -#define OMAP_I2C_FLAG_FORCE_19200_INT_CLK BIT(6) -/* how the CPU address bus must be translated for I2C unit access */ -#define OMAP_I2C_FLAG_BUS_SHIFT_NONE 0 -#define OMAP_I2C_FLAG_BUS_SHIFT_1 BIT(7) -#define OMAP_I2C_FLAG_BUS_SHIFT_2 BIT(8) -#define OMAP_I2C_FLAG_BUS_SHIFT__SHIFT 7 - -struct omap_i2c_bus_platform_data { - u32 clkrate; - u32 rev; - u32 flags; - void (*set_mpu_wkup_lat)(struct device *dev, long set); -}; - -#endif diff --git a/include/linux/platform_data/i2c-omap.h b/include/linux/platform_data/i2c-omap.h new file mode 100644 index 000000000000..3444265ee8ee --- /dev/null +++ b/include/linux/platform_data/i2c-omap.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __I2C_OMAP_H__ +#define __I2C_OMAP_H__ + +#include + +/* + * Version 2 of the I2C peripheral unit has a different register + * layout and extra registers. The ID register in the V2 peripheral + * unit on the OMAP4430 reports the same ID as the V1 peripheral + * unit on the OMAP3530, so we must inform the driver which IP + * version we know it is running on from platform / cpu-specific + * code using these constants in the hwmod class definition. + */ + +#define OMAP_I2C_IP_VERSION_1 1 +#define OMAP_I2C_IP_VERSION_2 2 + +/* struct omap_i2c_bus_platform_data .flags meanings */ + +#define OMAP_I2C_FLAG_NO_FIFO BIT(0) +#define OMAP_I2C_FLAG_SIMPLE_CLOCK BIT(1) +#define OMAP_I2C_FLAG_16BIT_DATA_REG BIT(2) +#define OMAP_I2C_FLAG_ALWAYS_ARMXOR_CLK BIT(5) +#define OMAP_I2C_FLAG_FORCE_19200_INT_CLK BIT(6) +/* how the CPU address bus must be translated for I2C unit access */ +#define OMAP_I2C_FLAG_BUS_SHIFT_NONE 0 +#define OMAP_I2C_FLAG_BUS_SHIFT_1 BIT(7) +#define OMAP_I2C_FLAG_BUS_SHIFT_2 BIT(8) +#define OMAP_I2C_FLAG_BUS_SHIFT__SHIFT 7 + +struct omap_i2c_bus_platform_data { + u32 clkrate; + u32 rev; + u32 flags; + void (*set_mpu_wkup_lat)(struct device *dev, long set); +}; + +#endif -- cgit v1.2.3 From e5c7137793a754500e65ffd7477e88ff7a06ac53 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 19 Apr 2018 22:00:11 +0200 Subject: i2c: pca-platform: move header to platform_data This header only contains platform_data. Move it to the proper directory. Signed-off-by: Wolfram Sang --- include/linux/i2c-pca-platform.h | 10 ---------- include/linux/platform_data/i2c-pca-platform.h | 10 ++++++++++ 2 files changed, 10 insertions(+), 10 deletions(-) delete mode 100644 include/linux/i2c-pca-platform.h create mode 100644 include/linux/platform_data/i2c-pca-platform.h (limited to 'include/linux') diff --git a/include/linux/i2c-pca-platform.h b/include/linux/i2c-pca-platform.h deleted file mode 100644 index c37329432a8e..000000000000 --- a/include/linux/i2c-pca-platform.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef I2C_PCA9564_PLATFORM_H -#define I2C_PCA9564_PLATFORM_H - -struct i2c_pca9564_pf_platform_data { - int i2c_clock_speed; /* values are defined in linux/i2c-algo-pca.h */ - int timeout; /* timeout in jiffies */ -}; - -#endif /* I2C_PCA9564_PLATFORM_H */ diff --git a/include/linux/platform_data/i2c-pca-platform.h b/include/linux/platform_data/i2c-pca-platform.h new file mode 100644 index 000000000000..c37329432a8e --- /dev/null +++ b/include/linux/platform_data/i2c-pca-platform.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef I2C_PCA9564_PLATFORM_H +#define I2C_PCA9564_PLATFORM_H + +struct i2c_pca9564_pf_platform_data { + int i2c_clock_speed; /* values are defined in linux/i2c-algo-pca.h */ + int timeout; /* timeout in jiffies */ +}; + +#endif /* I2C_PCA9564_PLATFORM_H */ -- cgit v1.2.3 From 7072b75c15271cef07792f659eaf0cc7160f6442 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 19 Apr 2018 22:00:12 +0200 Subject: i2c: xiic: move header to platform_data This header only contains platform_data. Move it to the proper directory. Signed-off-by: Wolfram Sang Acked-by: Lee Jones --- include/linux/i2c-xiic.h | 43 ---------------------------------- include/linux/platform_data/i2c-xiic.h | 43 ++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+), 43 deletions(-) delete mode 100644 include/linux/i2c-xiic.h create mode 100644 include/linux/platform_data/i2c-xiic.h (limited to 'include/linux') diff --git a/include/linux/i2c-xiic.h b/include/linux/i2c-xiic.h deleted file mode 100644 index 4f9f2256a97e..000000000000 --- a/include/linux/i2c-xiic.h +++ /dev/null @@ -1,43 +0,0 @@ -/* - * i2c-xiic.h - * Copyright (c) 2009 Intel Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -/* Supports: - * Xilinx IIC - */ - -#ifndef _LINUX_I2C_XIIC_H -#define _LINUX_I2C_XIIC_H - -/** - * struct xiic_i2c_platform_data - Platform data of the Xilinx I2C driver - * @num_devices: Number of devices that shall be added when the driver - * is probed. - * @devices: The actuall devices to add. - * - * This purpose of this platform data struct is to be able to provide a number - * of devices that should be added to the I2C bus. The reason is that sometimes - * the I2C board info is not enough, a new PCI board can for instance be - * plugged into a standard PC, and the bus number might be unknown at - * early init time. - */ -struct xiic_i2c_platform_data { - u8 num_devices; - struct i2c_board_info const *devices; -}; - -#endif /* _LINUX_I2C_XIIC_H */ diff --git a/include/linux/platform_data/i2c-xiic.h b/include/linux/platform_data/i2c-xiic.h new file mode 100644 index 000000000000..4f9f2256a97e --- /dev/null +++ b/include/linux/platform_data/i2c-xiic.h @@ -0,0 +1,43 @@ +/* + * i2c-xiic.h + * Copyright (c) 2009 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +/* Supports: + * Xilinx IIC + */ + +#ifndef _LINUX_I2C_XIIC_H +#define _LINUX_I2C_XIIC_H + +/** + * struct xiic_i2c_platform_data - Platform data of the Xilinx I2C driver + * @num_devices: Number of devices that shall be added when the driver + * is probed. + * @devices: The actuall devices to add. + * + * This purpose of this platform data struct is to be able to provide a number + * of devices that should be added to the I2C bus. The reason is that sometimes + * the I2C board info is not enough, a new PCI board can for instance be + * plugged into a standard PC, and the bus number might be unknown at + * early init time. + */ +struct xiic_i2c_platform_data { + u8 num_devices; + struct i2c_board_info const *devices; +}; + +#endif /* _LINUX_I2C_XIIC_H */ -- cgit v1.2.3 From caaccda136ae3fa1c5f6563aae22ca3c199f563a Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 19 Apr 2018 22:00:13 +0200 Subject: i2c: pnx: move header into the driver There are no platform_data users anymore. Move the structs into the driver. Signed-off-by: Wolfram Sang Acked-by: Vladimir Zapolskiy --- include/linux/i2c-pnx.h | 38 -------------------------------------- 1 file changed, 38 deletions(-) delete mode 100644 include/linux/i2c-pnx.h (limited to 'include/linux') diff --git a/include/linux/i2c-pnx.h b/include/linux/i2c-pnx.h deleted file mode 100644 index 5388326fbbff..000000000000 --- a/include/linux/i2c-pnx.h +++ /dev/null @@ -1,38 +0,0 @@ -/* - * Header file for I2C support on PNX010x/4008. - * - * Author: Dennis Kovalev - * - * 2004-2006 (c) MontaVista Software, Inc. This file is licensed under - * the terms of the GNU General Public License version 2. This program - * is licensed "as is" without any warranty of any kind, whether express - * or implied. - */ - -#ifndef __I2C_PNX_H__ -#define __I2C_PNX_H__ - -struct platform_device; -struct clk; - -struct i2c_pnx_mif { - int ret; /* Return value */ - int mode; /* Interface mode */ - struct completion complete; /* I/O completion */ - struct timer_list timer; /* Timeout */ - u8 * buf; /* Data buffer */ - int len; /* Length of data buffer */ - int order; /* RX Bytes to order via TX */ -}; - -struct i2c_pnx_algo_data { - void __iomem *ioaddr; - struct i2c_pnx_mif mif; - int last; - struct clk *clk; - struct i2c_adapter adapter; - int irq; - u32 timeout; -}; - -#endif /* __I2C_PNX_H__ */ -- cgit v1.2.3 From 9b97387c5c4260ffcdf3b913bdef0d98cb2d4a74 Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Fri, 11 May 2018 18:57:58 -0500 Subject: cacheinfo: rename of_node to fw_token Rename and change the type of of_node to indicate it is a generic pointer which is generally only used for comparison purposes. In a later patch we will put an ACPI/PPTT token pointer in fw_token so that the code which builds the shared cpu masks can be reused. Tested-by: Ard Biesheuvel Tested-by: Vijaya Kumar K Tested-by: Xiongfeng Wang Tested-by: Tomasz Nowicki Acked-by: Sudeep Holla Acked-by: Ard Biesheuvel Acked-by: Greg Kroah-Hartman Signed-off-by: Jeremy Linton Signed-off-by: Catalin Marinas --- include/linux/cacheinfo.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 3d9805297cda..0c6f658054d2 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -34,9 +34,8 @@ enum cache_type { * @shared_cpu_map: logical cpumask representing all the cpus sharing * this cache node * @attributes: bitfield representing various cache attributes - * @of_node: if devicetree is used, this represents either the cpu node in - * case there's no explicit cache node or the cache node itself in the - * device tree + * @fw_token: Unique value used to determine if different cacheinfo + * structures represent a single hardware cache instance. * @disable_sysfs: indicates whether this node is visible to the user via * sysfs or not * @priv: pointer to any private data structure specific to particular @@ -65,8 +64,7 @@ struct cacheinfo { #define CACHE_ALLOCATE_POLICY_MASK \ (CACHE_READ_ALLOCATE | CACHE_WRITE_ALLOCATE) #define CACHE_ID BIT(4) - - struct device_node *of_node; + void *fw_token; bool disable_sysfs; void *priv; }; -- cgit v1.2.3 From 2bd00bcd73e5edd5769e2a5f24c59a517582d862 Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Fri, 11 May 2018 18:58:00 -0500 Subject: ACPI/PPTT: Add Processor Properties Topology Table parsing ACPI 6.2 adds a new table, which describes how processing units are related to each other in tree like fashion. Caches are also sprinkled throughout the tree and describe the properties of the caches in relation to other caches and processing units. Add the code to parse the cache hierarchy and report the total number of levels of cache for a given core using acpi_find_last_cache_level() as well as fill out the individual cores cache information with cache_setup_acpi() once the cpu_cacheinfo structure has been populated by the arch specific code. An additional patch later in the set adds the ability to report peers in the topology using find_acpi_cpu_topology() to report a unique ID for each processing unit at a given level in the tree. These unique id's can then be used to match related processing units which exist as threads, within a given package, etc. Tested-by: Ard Biesheuvel Tested-by: Vijaya Kumar K Tested-by: Xiongfeng Wang Tested-by: Tomasz Nowicki Acked-by: Sudeep Holla Acked-by: Ard Biesheuvel Acked-by: Rafael J. Wysocki Signed-off-by: Jeremy Linton Signed-off-by: Catalin Marinas --- include/linux/acpi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 15bfb15c2fa5..032e12a2fdc2 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1297,4 +1297,8 @@ static inline int lpit_read_residency_count_address(u64 *address) } #endif +int find_acpi_cpu_topology(unsigned int cpu, int level); +int find_acpi_cpu_topology_package(unsigned int cpu); +int find_acpi_cpu_cache_topology(unsigned int cpu, int level); + #endif /*_LINUX_ACPI_H*/ -- cgit v1.2.3 From 582b468bdc6d9c287a432a63225cf7922e985e15 Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Fri, 11 May 2018 18:58:02 -0500 Subject: drivers: base cacheinfo: Add support for ACPI based firmware tables Call ACPI cache parsing routines from base cacheinfo code if ACPI is enabled. Also stub out cache_setup_acpi and acpi_find_last_cache_level so that individual architectures can enable ACPI topology parsing. Tested-by: Ard Biesheuvel Tested-by: Vijaya Kumar K Tested-by: Xiongfeng Wang Tested-by: Tomasz Nowicki Acked-by: Sudeep Holla Acked-by: Ard Biesheuvel Acked-by: Greg Kroah-Hartman Signed-off-by: Jeremy Linton Signed-off-by: Catalin Marinas --- include/linux/cacheinfo.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 0c6f658054d2..89397e30e269 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -97,6 +97,23 @@ int func(unsigned int cpu) \ struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu); int init_cache_level(unsigned int cpu); int populate_cache_leaves(unsigned int cpu); +int cache_setup_acpi(unsigned int cpu); +#ifndef CONFIG_ACPI +/* + * acpi_find_last_cache_level is only called on ACPI enabled + * platforms using the PPTT for topology. This means that if + * the platform supports other firmware configuration methods + * we need to stub out the call when ACPI is disabled. + * ACPI enabled platforms not using PPTT won't be making calls + * to this function so we need not worry about them. + */ +static inline int acpi_find_last_cache_level(unsigned int cpu) +{ + return 0; +} +#else +int acpi_find_last_cache_level(unsigned int cpu); +#endif const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf); -- cgit v1.2.3 From 021a17ed796b62383f7623f4fea73787abddad77 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 15 May 2018 16:24:37 +0200 Subject: pfifo_fast: drop unneeded additional lock on dequeue After the previous patch, for NOLOCK qdiscs, q->seqlock is always held when the dequeue() is invoked, we can drop any additional locking to protect such operation. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/skb_array.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index a6b6e8bb3d7b..62d9b0a6329f 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -97,6 +97,11 @@ static inline bool skb_array_empty_any(struct skb_array *a) return ptr_ring_empty_any(&a->ring); } +static inline struct sk_buff *__skb_array_consume(struct skb_array *a) +{ + return __ptr_ring_consume(&a->ring); +} + static inline struct sk_buff *skb_array_consume(struct skb_array *a) { return ptr_ring_consume(&a->ring); -- cgit v1.2.3 From 5490b8725d80cdfd5266a3732e23d61d0e9f7d2f Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Thu, 17 May 2018 10:29:32 +0200 Subject: phy: add 2.5G SGMII mode to the phy_mode enum This patch adds one more generic PHY mode to the phy_mode enum, to allow configuring generic PHYs to the 2.5G SGMII mode by using the set_mode callback. Signed-off-by: Antoine Tenart Acked-by: Kishon Vijay Abraham I Signed-off-by: David S. Miller --- include/linux/phy/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index c9d14eeee7f5..9713aebdd348 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -36,6 +36,7 @@ enum phy_mode { PHY_MODE_USB_DEVICE_SS, PHY_MODE_USB_OTG, PHY_MODE_SGMII, + PHY_MODE_2500SGMII, PHY_MODE_10GKR, PHY_MODE_UFS_HS_A, PHY_MODE_UFS_HS_B, -- cgit v1.2.3 From a6d04569120d53ebac1f0e6ffd5497b22c75f037 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Tue, 5 Dec 2017 10:38:58 +0200 Subject: net/mlx5: Add merged e-switch cap When merged e-switch is supported, the per-port e-switch is logically merged into one e-switch that spans both physical ports and all the VFs. Under merged eswitch, both the matching on source vport and setting destination vport can have a 2nd attribute which is the vhca id of the eswitch owner. For example: esw0: {match: action: fwd to } is a flow set on eswitch0 matching on source vport=1 from his eswitch and the action being fwd to dest vport=7 of eswitch1. Signed-off-by: Roi Dayan Reviewed-by: Shahar Klein Reviewed-by: Or Gerlitz Klein Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1aad455538f4..ef15f751a984 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -557,7 +557,8 @@ struct mlx5_ifc_e_switch_cap_bits { u8 vport_svlan_insert[0x1]; u8 vport_cvlan_insert_if_not_exist[0x1]; u8 vport_cvlan_insert_overwrite[0x1]; - u8 reserved_at_5[0x19]; + u8 reserved_at_5[0x18]; + u8 merged_eswitch[0x1]; u8 nic_vport_node_guid_modify[0x1]; u8 nic_vport_port_guid_modify[0x1]; -- cgit v1.2.3 From b17f7fc10facca9e1b2b9cef39af0a8179796c14 Mon Sep 17 00:00:00 2001 From: Shahar Klein Date: Thu, 22 Mar 2018 12:32:12 +0200 Subject: net/mlx5: Add destination e-switch owner The destination e-switch owner allows a rule in namespace of one e-switch owner to point to a vport that is natively associated with another e-switch owner. Signed-off-by: Shahar Klein Reviewed-by: Or Gerlitz Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 6 +++++- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 47aecc4fa8c2..9f4d32e41c06 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -90,8 +90,12 @@ struct mlx5_flow_destination { union { u32 tir_num; struct mlx5_flow_table *ft; - u32 vport_num; struct mlx5_fc *counter; + struct { + u16 num; + u16 vhca_id; + bool vhca_id_valid; + } vport; }; }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ef15f751a984..3d17709bc30c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1148,8 +1148,9 @@ enum mlx5_flow_destination_type { struct mlx5_ifc_dest_format_struct_bits { u8 destination_type[0x8]; u8 destination_id[0x18]; - - u8 reserved_at_20[0x20]; + u8 destination_eswitch_owner_vhca_id_valid[0x1]; + u8 reserved_at_21[0xf]; + u8 destination_eswitch_owner_vhca_id[0x10]; }; struct mlx5_ifc_flow_counter_list_bits { -- cgit v1.2.3 From 3e99df87722874c669f6c24a79bd1b4ba5fec819 Mon Sep 17 00:00:00 2001 From: Shahar Klein Date: Sun, 18 Mar 2018 09:02:06 +0200 Subject: net/mlx5: Add source e-switch owner The source e-switch owner allows a vport on one e-switch port be associated with a rule defined on the second port e-switch. The role of the source eswitch owner valid bit in the flow group is to allow the firmware fail driver attempts to wild card the source eswitch match field. If this bit is not set, the firmware ignores the source eswitch owner field totally. Signed-off-by: Shahar Klein Reviewed-by: Or Gerlitz Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3d17709bc30c..9c3538f1b8b9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -412,7 +412,7 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 reserved_at_0[0x8]; u8 source_sqn[0x18]; - u8 reserved_at_20[0x10]; + u8 source_eswitch_owner_vhca_id[0x10]; u8 source_port[0x10]; u8 outer_second_prio[0x3]; @@ -6995,7 +6995,9 @@ struct mlx5_ifc_create_flow_group_in_bits { u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_at_c0[0x20]; + u8 source_eswitch_owner_vhca_id_valid[0x1]; + + u8 reserved_at_c1[0x1f]; u8 start_flow_index[0x20]; -- cgit v1.2.3 From 2e28bc84cf6eecd3759d7ae723bb0f5f09becf76 Mon Sep 17 00:00:00 2001 From: Oza Pawandeep Date: Thu, 17 May 2018 16:44:15 -0500 Subject: PCI/AER: Factor out error reporting to drivers/pci/pcie/err.c Move the error reporting callbacks from aerdrv_core.c to err.c, where they can be used by DPC in addition to AER. As part of aerdrv_core.c, these callbacks were built under CONFIG_PCIEAER. Moving them to the new err.c means they will now be built under CONFIG_PCIEPORTBUS, so adjust the definition of pci_uevent_ers() to match. Signed-off-by: Oza Pawandeep [bhelgaas: in reset_link(), initialize "driver" even if CONFIG_PCIEAER is unset, update pci_uevent_ers() #ifdef wrapper] Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 73178a2fcee0..4f721f757363 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2284,7 +2284,7 @@ static inline bool pci_is_thunderbolt_attached(struct pci_dev *pdev) return false; } -#if defined(CONFIG_PCIEAER) || defined(CONFIG_EEH) +#if defined(CONFIG_PCIEPORTBUS) || defined(CONFIG_EEH) void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #endif -- cgit v1.2.3 From 75abe32946604887a3fa600eb0956e9946d4170c Mon Sep 17 00:00:00 2001 From: Li Qiang Date: Thu, 17 May 2018 19:01:03 -0700 Subject: fs.h: fix outdated comment about file flags The __dentry_open function was removed in commit <2a027e7a18738>("fold __dentry_open() into its sole caller"). Signed-off-by: Li Qiang Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 760d8da1b6c7..7f07977bdfd7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -94,7 +94,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond - * to O_WRONLY and O_RDWR via the strange trick in __dentry_open() + * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ -- cgit v1.2.3 From 564def71765caf65040f926c0783b9c27cc6c087 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 18 May 2018 11:46:15 +0100 Subject: proc: Add a way to make network proc files writable Provide two extra functions, proc_create_net_data_write() and proc_create_net_single_write() that act like their non-write versions but also set a write method in the proc_dir_entry struct. An internal simple write function is provided that will copy its buffer and hand it to the pde->write() method if available (or give an error if not). The buffer may be modified by the write method. Signed-off-by: David Howells --- include/linux/proc_fs.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index e518352137e7..626fc65c4336 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -14,6 +14,8 @@ struct seq_operations; #ifdef CONFIG_PROC_FS +typedef int (*proc_write_t)(struct file *, char *, size_t); + extern void proc_root_init(void); extern void proc_flush_task(struct task_struct *); @@ -61,6 +63,16 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), void *data); +struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode, + struct proc_dir_entry *parent, + const struct seq_operations *ops, + proc_write_t write, + unsigned int state_size, void *data); +struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode, + struct proc_dir_entry *parent, + int (*show)(struct seq_file *, void *), + proc_write_t write, + void *data); #else /* CONFIG_PROC_FS */ -- cgit v1.2.3 From d6f7b98bc8147abd290ead82922f8d83c525fb42 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 20 Apr 2018 16:10:49 -0700 Subject: fsnotify: use type id to identify connector object type An fsnotify_mark_connector is referencing a single type of object (either inode or vfsmount). Instead of storing a type mask in connector->flags, store a single type id in connector->type to identify the type of object. When a connector object is detached from the object, its type is set to FSNOTIFY_OBJ_TYPE_DETACHED and this object is not going to be reused. The function fsnotify_clear_marks_by_group() is the only place where type mask was used, so use type flags instead of type id to this function. This change is going to be more convenient when adding a new object type (super block). Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index e64c0294f50b..435c94a31c8c 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -201,6 +201,17 @@ struct fsnotify_group { #define FSNOTIFY_EVENT_PATH 1 #define FSNOTIFY_EVENT_INODE 2 +enum fsnotify_obj_type { + FSNOTIFY_OBJ_TYPE_INODE, + FSNOTIFY_OBJ_TYPE_VFSMOUNT, + FSNOTIFY_OBJ_TYPE_COUNT, + FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT +}; + +#define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE) +#define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) +#define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) + /* * Inode / vfsmount point to this structure which tracks all marks attached to * the inode / vfsmount. The reference to inode / vfsmount is held by this @@ -209,11 +220,7 @@ struct fsnotify_group { */ struct fsnotify_mark_connector { spinlock_t lock; -#define FSNOTIFY_OBJ_TYPE_INODE 0x01 -#define FSNOTIFY_OBJ_TYPE_VFSMOUNT 0x02 -#define FSNOTIFY_OBJ_ALL_TYPES (FSNOTIFY_OBJ_TYPE_INODE | \ - FSNOTIFY_OBJ_TYPE_VFSMOUNT) - unsigned int flags; /* Type of object [lock] */ + unsigned int type; /* Type of object [lock] */ union { /* Object pointer [lock] */ struct inode *inode; struct vfsmount *mnt; @@ -369,12 +376,12 @@ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); -- cgit v1.2.3 From 5b0457ad021f3f7e3d9f4b84e7c3080748f383f8 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 20 Apr 2018 16:10:50 -0700 Subject: fsnotify: remove redundant arguments to handle_event() inode_mark and vfsmount_mark arguments are passed to handle_event() operation as function arguments as well as on iter_info struct. The difference is that iter_info struct may contain marks that should not be handled and are represented as NULL arguments to inode_mark or vfsmount_mark. Instead of passing the inode_mark and vfsmount_mark arguments, add a report_mask member to iter_info struct to indicate which marks should be handled, versus marks that should only be kept alive during user wait. This change is going to be used for passing more mark types with handle_event() (i.e. super block marks). Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 435c94a31c8c..9da5edf4ac0f 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -98,8 +98,6 @@ struct fsnotify_iter_info; struct fsnotify_ops { int (*handle_event)(struct fsnotify_group *group, struct inode *inode, - struct fsnotify_mark *inode_mark, - struct fsnotify_mark *vfsmount_mark, u32 mask, const void *data, int data_type, const unsigned char *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); @@ -212,6 +210,24 @@ enum fsnotify_obj_type { #define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) #define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) +struct fsnotify_iter_info { + struct fsnotify_mark *inode_mark; + struct fsnotify_mark *vfsmount_mark; + unsigned int report_mask; + int srcu_idx; +}; + +#define FSNOTIFY_ITER_FUNCS(name, NAME) \ +static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ + struct fsnotify_iter_info *iter_info) \ +{ \ + return (iter_info->report_mask & FSNOTIFY_OBJ_TYPE_##NAME##_FL) ? \ + iter_info->name##_mark : NULL; \ +} + +FSNOTIFY_ITER_FUNCS(inode, INODE) +FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) + /* * Inode / vfsmount point to this structure which tracks all marks attached to * the inode / vfsmount. The reference to inode / vfsmount is held by this -- cgit v1.2.3 From 47d9c7cc457adc5d6d8ca966482a51459f81e852 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 20 Apr 2018 16:10:52 -0700 Subject: fsnotify: generalize iteration of marks by object type Make some code that handles marks of object types inode and vfsmount generic, so it can handle other object types. Introduce fsnotify_foreach_obj_type macro to iterate marks by object type and fsnotify_iter_{should|set}_report_type macros to set/test report_mask. This is going to be used for adding mark of another object type (super block mark). Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 9da5edf4ac0f..763423bfa3d6 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -211,23 +211,45 @@ enum fsnotify_obj_type { #define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) struct fsnotify_iter_info { - struct fsnotify_mark *inode_mark; - struct fsnotify_mark *vfsmount_mark; + struct fsnotify_mark *marks[FSNOTIFY_OBJ_TYPE_COUNT]; unsigned int report_mask; int srcu_idx; }; +static inline bool fsnotify_iter_should_report_type( + struct fsnotify_iter_info *iter_info, int type) +{ + return (iter_info->report_mask & (1U << type)); +} + +static inline void fsnotify_iter_set_report_type( + struct fsnotify_iter_info *iter_info, int type) +{ + iter_info->report_mask |= (1U << type); +} + +static inline void fsnotify_iter_set_report_type_mark( + struct fsnotify_iter_info *iter_info, int type, + struct fsnotify_mark *mark) +{ + iter_info->marks[type] = mark; + iter_info->report_mask |= (1U << type); +} + #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ return (iter_info->report_mask & FSNOTIFY_OBJ_TYPE_##NAME##_FL) ? \ - iter_info->name##_mark : NULL; \ + iter_info->marks[FSNOTIFY_OBJ_TYPE_##NAME] : NULL; \ } FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) +#define fsnotify_foreach_obj_type(type) \ + for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++) + /* * Inode / vfsmount point to this structure which tracks all marks attached to * the inode / vfsmount. The reference to inode / vfsmount is held by this -- cgit v1.2.3 From b249f5be6165811749b04a927806056c198222b1 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 20 Apr 2018 16:10:55 -0700 Subject: fsnotify: add fsnotify_add_inode_mark() wrappers Before changing the arguments of the functions fsnotify_add_mark() and fsnotify_add_mark_locked(), convert most callers to use a wrapper. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 763423bfa3d6..b38964a7a521 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -401,7 +401,21 @@ extern struct fsnotify_mark *fsnotify_find_mark( extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct inode *inode, struct vfsmount *mnt, int allow_dups); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, - struct inode *inode, struct vfsmount *mnt, int allow_dups); + struct inode *inode, struct vfsmount *mnt, + int allow_dups); +/* attach the mark to the inode */ +static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, + struct inode *inode, + int allow_dups) +{ + return fsnotify_add_mark(mark, inode, NULL, allow_dups); +} +static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, + struct inode *inode, + int allow_dups) +{ + return fsnotify_add_mark_locked(mark, inode, NULL, allow_dups); +} /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); -- cgit v1.2.3 From 5d9f4262b7ea41ca9981cc790e37cca6e37c789e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 17 May 2018 14:47:26 -0700 Subject: tcp: add SACK compression MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When TCP receives an out-of-order packet, it immediately sends a SACK packet, generating network load but also forcing the receiver to send 1-MSS pathological packets, increasing its RTX queue length/depth, and thus processing time. Wifi networks suffer from this aggressive behavior, but generally speaking, all these SACK packets add fuel to the fire when networks are under congestion. This patch adds a high resolution timer and tp->compressed_ack counter. Instead of sending a SACK, we program this timer with a small delay, based on RTT and capped to 1 ms : delay = min ( 5 % of RTT, 1 ms) If subsequent SACKs need to be sent while the timer has not yet expired, we simply increment tp->compressed_ack. When timer expires, a SACK is sent with the latest information. Whenever an ACK is sent (if data is sent, or if in-order data is received) timer is canceled. Note that tcp_sack_new_ofo_skb() is able to force a SACK to be sent if the sack blocks need to be shuffled, even if the timer has not expired. A new SNMP counter is added in the following patch. Two other patches add sysctls to allow changing the 1,000,000 and 44 values that this commit hard-coded. Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Yuchung Cheng Acked-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 807776928cb8..72705eaf4b84 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -218,6 +218,7 @@ struct tcp_sock { reord:1; /* reordering detected */ } rack; u16 advmss; /* Advertised MSS */ + u8 compressed_ack; u32 chrono_start; /* Start time in jiffies of a TCP chrono */ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u8 chrono_type:2, /* current chronograph type */ @@ -297,6 +298,7 @@ struct tcp_sock { u32 sacked_out; /* SACK'd packets */ struct hrtimer pacing_timer; + struct hrtimer compressed_ack_timer; /* from STCP, retrans queue hinting */ struct sk_buff* lost_skb_hint; -- cgit v1.2.3 From ef1433f717a2c63747a519d86965d73ff9bd08b3 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Mon, 2 Apr 2018 18:59:35 +0530 Subject: PCI: endpoint: Create configfs entry for each pci_epf_device_id table entry In order to be able to provide correct driver_data for pci_epf device, a separate configfs entry for each pci_epf_device_id table entry in pci_epf_driver is required. Add support to create configfs entry for each pci_epf_device_id table entry here. Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Tested-by: Gustavo Pimentel --- include/linux/pci-epf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index f7d6f4883f8b..4e7764935fa8 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -72,7 +72,7 @@ struct pci_epf_ops { * @driver: PCI EPF driver * @ops: set of function pointers for performing EPF operations * @owner: the owner of the module that registers the PCI EPF driver - * @group: configfs group corresponding to the PCI EPF driver + * @epf_group: list of configfs group corresponding to the PCI EPF driver * @id_table: identifies EPF devices for probing */ struct pci_epf_driver { @@ -82,7 +82,7 @@ struct pci_epf_driver { struct device_driver driver; struct pci_epf_ops *ops; struct module *owner; - struct config_group *group; + struct list_head epf_group; const struct pci_epf_device_id *id_table; }; -- cgit v1.2.3 From 6b59808bfe482642287ddf3fe9d4cccb10756652 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 18 May 2018 08:47:13 -0700 Subject: workqueue: Show the latest workqueue name in /proc/PID/{comm,stat,status} There can be a lot of workqueue workers and they all show up with the cryptic kworker/* names making it difficult to understand which is doing what and how they came to be. # ps -ef | grep kworker root 4 2 0 Feb25 ? 00:00:00 [kworker/0:0H] root 6 2 0 Feb25 ? 00:00:00 [kworker/u112:0] root 19 2 0 Feb25 ? 00:00:00 [kworker/1:0H] root 25 2 0 Feb25 ? 00:00:00 [kworker/2:0H] root 31 2 0 Feb25 ? 00:00:00 [kworker/3:0H] ... This patch makes workqueue workers report the latest workqueue it was executing for through /proc/PID/{comm,stat,status}. The extra information is appended to the kthread name with intervening '+' if currently executing, otherwise '-'. # cat /proc/25/comm kworker/2:0-events_power_efficient # cat /proc/25/stat 25 (kworker/2:0-events_power_efficient) I 2 0 0 0 -1 69238880 0 0... # grep Name /proc/25/status Name: kworker/2:0-events_power_efficient Unfortunately, ps(1) truncates comm to 15 characters, # ps 25 PID TTY STAT TIME COMMAND 25 ? I 0:00 [kworker/2:0-eve] making it a lot less useful; however, this should be an easy fix from ps(1) side. Signed-off-by: Tejun Heo Suggested-by: Linus Torvalds Cc: Craig Small --- include/linux/workqueue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 39a0e215022a..60d673e15632 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -494,6 +494,7 @@ extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_workqueue_state(void); +extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); /** * queue_work - queue work on a workqueue -- cgit v1.2.3 From 24c94e166dfe89839129b8e0fae208b6af60d6f1 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Sat, 5 May 2018 08:45:47 +0200 Subject: gpu: host1x: Remove wait check support The job submission userspace ABI doesn't support this and there are no plans to implement it, so all of this code is dead and can be removed. Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Thierry Reding --- include/linux/host1x.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index ddf7f9ca86cc..f66bece1e1b7 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -192,13 +192,6 @@ struct host1x_reloc { unsigned long shift; }; -struct host1x_waitchk { - struct host1x_bo *bo; - u32 offset; - u32 syncpt_id; - u32 thresh; -}; - struct host1x_job { /* When refcount goes to zero, job can be freed */ struct kref ref; @@ -215,11 +208,6 @@ struct host1x_job { struct host1x_job_gather *gathers; unsigned int num_gathers; - /* Wait checks to be processed at submit time */ - struct host1x_waitchk *waitchk; - unsigned int num_waitchk; - u32 waitchk_mask; - /* Array of handles to be pinned & unpinned */ struct host1x_reloc *relocarray; unsigned int num_relocs; @@ -261,8 +249,7 @@ struct host1x_job { }; struct host1x_job *host1x_job_alloc(struct host1x_channel *ch, - u32 num_cmdbufs, u32 num_relocs, - u32 num_waitchks); + u32 num_cmdbufs, u32 num_relocs); void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *mem_id, u32 words, u32 offset); struct host1x_job *host1x_job_get(struct host1x_job *job); -- cgit v1.2.3 From bf3d41ccabb53c57e19fcfc8b81d790043ac2bed Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 16 May 2018 14:12:33 +0200 Subject: gpu: host1x: Store pointer to client in jobs Rather than storing some identifier derived from the application context that can't be used concretely anywhere, store a pointer to the client directly so that accesses can be made directly through that client object. Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Thierry Reding --- include/linux/host1x.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index f66bece1e1b7..0632010f47fb 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -202,7 +202,8 @@ struct host1x_job { /* Channel where job is submitted to */ struct host1x_channel *channel; - u32 client; + /* client where the job originated */ + struct host1x_client *client; /* Gathers and their memory */ struct host1x_job_gather *gathers; -- cgit v1.2.3 From 06490bb99e1840ab2b6814af7356e8b4ab0e3ee6 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 16 May 2018 16:58:44 +0200 Subject: gpu: host1x: Rename relocarray -> relocs for consistency All other array variables use a plural, and this is the only one using the *array suffix. This is confusing, so rename it for consistency. Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Thierry Reding --- include/linux/host1x.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 0632010f47fb..dcb6140d39d7 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -210,7 +210,7 @@ struct host1x_job { unsigned int num_gathers; /* Array of handles to be pinned & unpinned */ - struct host1x_reloc *relocarray; + struct host1x_reloc *relocs; unsigned int num_relocs; struct host1x_job_unpin_data *unpins; unsigned int num_unpins; -- cgit v1.2.3 From 326bbd79fd61716841585a52d5b68f48f4e6644e Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 16 May 2018 17:01:43 +0200 Subject: gpu: host1x: Use not explicitly sized types The number of words and the offset in a gather don't need to be explicitly sized, so make them unsigned int instead. Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Thierry Reding --- include/linux/host1x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index dcb6140d39d7..89110d896d72 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -251,8 +251,8 @@ struct host1x_job { struct host1x_job *host1x_job_alloc(struct host1x_channel *ch, u32 num_cmdbufs, u32 num_relocs); -void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *mem_id, - u32 words, u32 offset); +void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *bo, + unsigned int words, unsigned int offset); struct host1x_job *host1x_job_get(struct host1x_job *job); void host1x_job_put(struct host1x_job *job); int host1x_job_pin(struct host1x_job *job, struct device *dev); -- cgit v1.2.3 From 303def35f64e37bcd5401d202889f5fbc0241179 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 17 May 2018 14:16:58 -0700 Subject: bpf: allow sk_msg programs to read sock fields Currently sk_msg programs only have access to the raw data. However, it is often useful when building policies to have the policies specific to the socket endpoint. This allows using the socket tuple as input into filters, etc. This patch adds ctx access to the sock fields. Signed-off-by: John Fastabend Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 9dbcb9d55921..d358d1815c16 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -517,6 +517,7 @@ struct sk_msg_buff { bool sg_copy[MAX_SKB_FRAGS]; __u32 flags; struct sock *sk_redir; + struct sock *sk; struct sk_buff *skb; struct list_head list; }; -- cgit v1.2.3 From 782e6769c0df744e773dc2acff71c974b3bba4e9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Apr 2018 15:24:51 +0200 Subject: dma-mapping: provide a generic dma-noncoherent implementation Add a new dma_map_ops implementation that uses dma-direct for the address mapping of streaming mappings, and which requires arch-specific implemenations of coherent allocate/free. Architectures have to provide flushing helpers to ownership trasnfers to the device and/or CPU, and can provide optional implementations of the coherent mmap functionality, and the cache_flush routines for non-coherent long term allocations. Signed-off-by: Christoph Hellwig Tested-by: Alexey Brodkin Acked-by: Vineet Gupta --- include/linux/dma-direct.h | 7 +++++- include/linux/dma-mapping.h | 1 + include/linux/dma-noncoherent.h | 47 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 54 insertions(+), 1 deletion(-) create mode 100644 include/linux/dma-noncoherent.h (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 53ad6a47f513..8d9f33febde5 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -59,6 +59,11 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); +dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs); +int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, + enum dma_data_direction dir, unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); - +int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 25a9a2b04f78..4be070df5fc5 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -136,6 +136,7 @@ struct dma_map_ops { }; extern const struct dma_map_ops dma_direct_ops; +extern const struct dma_map_ops dma_noncoherent_ops; extern const struct dma_map_ops dma_virt_ops; #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h new file mode 100644 index 000000000000..10b2654d549b --- /dev/null +++ b/include/linux/dma-noncoherent.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_DMA_NONCOHERENT_H +#define _LINUX_DMA_NONCOHERENT_H 1 + +#include + +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs); +void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_addr, unsigned long attrs); + +#ifdef CONFIG_DMA_NONCOHERENT_MMAP +int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +#else +#define arch_dma_mmap NULL +#endif /* CONFIG_DMA_NONCOHERENT_MMAP */ + +#ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC +void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, + enum dma_data_direction direction); +#else +#define arch_dma_cache_sync NULL +#endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */ + +#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE +void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir); +#else +static inline void arch_sync_dma_for_device(struct device *dev, + phys_addr_t paddr, size_t size, enum dma_data_direction dir) +{ +} +#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */ + +#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU +void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir); +#else +static inline void arch_sync_dma_for_cpu(struct device *dev, + phys_addr_t paddr, size_t size, enum dma_data_direction dir) +{ +} +#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */ + +#endif /* _LINUX_DMA_NONCOHERENT_H */ -- cgit v1.2.3 From 4f0fad9a603aee91a374e8411c23953894a77479 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 27 Apr 2018 15:40:12 +0200 Subject: timekeeping: Remove timespec64 hack At this point, we have converted most of the kernel to use timespec64 consistently in place of timespec, so it seems it's time to make timespec64 the native structure and define timespec in terms of that one on 64-bit architectures. Starting with gcc-5, the compiler can completely optimize away the timespec_to_timespec64 and timespec64_to_timespec functions on 64-bit architectures. With older compilers, we introduce a couple of extra copies of local variables, but those are easily avoided by using the timespec64 based interfaces consistently, as we do in most of the important code paths already. The main upside of removing the hack is that printing the tv_sec field of a timespec64 structure can now use the %lld format string on all architectures without a cast to time64_t. Without this patch, the field is a 'long' type and would have to be printed using %ld on 64-bit architectures. Signed-off-by: Arnd Bergmann Signed-off-by: Thomas Gleixner Cc: Stephen Boyd Cc: y2038@lists.linaro.org Cc: John Stultz Link: https://lkml.kernel.org/r/20180427134016.2525989-2-arnd@arndb.de --- include/linux/time32.h | 18 +++-------------- include/linux/time64.h | 7 ------- include/linux/timekeeping32.h | 45 ------------------------------------------- 3 files changed, 3 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time32.h b/include/linux/time32.h index d2bcd4377b56..0b14f936100a 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -18,25 +18,14 @@ /* timespec64 is defined as timespec here */ static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) { - return ts64; + return *(const struct timespec *)&ts64; } static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) { - return ts; + return *(const struct timespec64 *)&ts; } -# define timespec_equal timespec64_equal -# define timespec_compare timespec64_compare -# define set_normalized_timespec set_normalized_timespec64 -# define timespec_add timespec64_add -# define timespec_sub timespec64_sub -# define timespec_valid timespec64_valid -# define timespec_valid_strict timespec64_valid_strict -# define timespec_to_ns timespec64_to_ns -# define ns_to_timespec ns_to_timespec64 -# define timespec_add_ns timespec64_add_ns - #else static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) { @@ -55,6 +44,7 @@ static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) ret.tv_nsec = ts.tv_nsec; return ret; } +#endif static inline int timespec_equal(const struct timespec *a, const struct timespec *b) @@ -159,8 +149,6 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) a->tv_nsec = ns; } -#endif - /** * time_to_tm - converts the calendar time to local broken-down time * diff --git a/include/linux/time64.h b/include/linux/time64.h index 0d96887ba4e0..0a7b2f79cec7 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -16,11 +16,6 @@ typedef __u64 timeu64_t; #include -#if __BITS_PER_LONG == 64 -/* this trick allows us to optimize out timespec64_to_timespec */ -# define timespec64 timespec -#define itimerspec64 itimerspec -#else struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ @@ -31,8 +26,6 @@ struct itimerspec64 { struct timespec64 it_value; }; -#endif - /* Parameters used to convert the timespec values: */ #define MSEC_PER_SEC 1000L #define USEC_PER_MSEC 1000L diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index 3616b4becb59..4ea45d0df1d4 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -16,50 +16,6 @@ static inline struct timespec current_kernel_time(void) return timespec64_to_timespec(now); } -#if BITS_PER_LONG == 64 -/** - * Deprecated. Use do_settimeofday64(). - */ -static inline int do_settimeofday(const struct timespec *ts) -{ - return do_settimeofday64(ts); -} - -static inline int __getnstimeofday(struct timespec *ts) -{ - return __getnstimeofday64(ts); -} - -static inline void getnstimeofday(struct timespec *ts) -{ - getnstimeofday64(ts); -} - -static inline void ktime_get_ts(struct timespec *ts) -{ - ktime_get_ts64(ts); -} - -static inline void ktime_get_real_ts(struct timespec *ts) -{ - getnstimeofday64(ts); -} - -static inline void getrawmonotonic(struct timespec *ts) -{ - getrawmonotonic64(ts); -} - -static inline struct timespec get_monotonic_coarse(void) -{ - return get_monotonic_coarse64(); -} - -static inline void getboottime(struct timespec *ts) -{ - return getboottime64(ts); -} -#else /** * Deprecated. Use do_settimeofday64(). */ @@ -124,7 +80,6 @@ static inline void getboottime(struct timespec *ts) getboottime64(&ts64); *ts = timespec64_to_timespec(ts64); } -#endif /* * Timespec interfaces utilizing the ktime based ones -- cgit v1.2.3 From edca71fecb77e2697337d192cbfe96f513407761 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 27 Apr 2018 15:40:13 +0200 Subject: timekeeping: Clean up ktime_get_real_ts64 In a move to make ktime_get_*() the preferred driver interface into the timekeeping code, sanitizes ktime_get_real_ts64() to be a proper exported symbol rather than an alias for getnstimeofday64(). The internal __getnstimeofday64() is no longer used, so remove that and merge it into ktime_get_real_ts64(). Signed-off-by: Arnd Bergmann Signed-off-by: Thomas Gleixner Cc: Stephen Boyd Cc: y2038@lists.linaro.org Cc: John Stultz Link: https://lkml.kernel.org/r/20180427134016.2525989-3-arnd@arndb.de --- include/linux/timekeeping.h | 8 +++++--- include/linux/timekeeping32.h | 13 ++----------- 2 files changed, 7 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 588a0e4b1ab9..415dae6bf1f5 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -30,15 +30,13 @@ struct timespec64 current_kernel_time64(void); struct timespec64 get_monotonic_coarse64(void); extern void getrawmonotonic64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); +extern void ktime_get_real_ts64(struct timespec64 *tv); extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); -extern int __getnstimeofday64(struct timespec64 *tv); -extern void getnstimeofday64(struct timespec64 *tv); extern void getboottime64(struct timespec64 *ts); -#define ktime_get_real_ts64(ts) getnstimeofday64(ts) /* * ktime_t based interfaces @@ -210,5 +208,9 @@ extern void read_persistent_clock64(struct timespec64 *ts); extern void read_boot_clock64(struct timespec64 *ts); extern int update_persistent_clock64(struct timespec64 now); +/* + * deprecated aliases, don't use in new code + */ +#define getnstimeofday64(ts) ktime_get_real_ts64(ts) #endif diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index 4ea45d0df1d4..5abff52d07fd 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -27,20 +27,11 @@ static inline int do_settimeofday(const struct timespec *ts) return do_settimeofday64(&ts64); } -static inline int __getnstimeofday(struct timespec *ts) -{ - struct timespec64 ts64; - int ret = __getnstimeofday64(&ts64); - - *ts = timespec64_to_timespec(ts64); - return ret; -} - static inline void getnstimeofday(struct timespec *ts) { struct timespec64 ts64; - getnstimeofday64(&ts64); + ktime_get_real_ts64(&ts64); *ts = timespec64_to_timespec(ts64); } @@ -56,7 +47,7 @@ static inline void ktime_get_real_ts(struct timespec *ts) { struct timespec64 ts64; - getnstimeofday64(&ts64); + ktime_get_real_ts64(&ts64); *ts = timespec64_to_timespec(ts64); } -- cgit v1.2.3 From fb7fcc96a86cfaef0f6dcc0665516aa68611e736 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 27 Apr 2018 15:40:14 +0200 Subject: timekeeping: Standardize on ktime_get_*() naming The current_kernel_time64, get_monotonic_coarse64, getrawmonotonic64, get_monotonic_boottime64 and timekeeping_clocktai64 interfaces have rather inconsistent naming, and they differ in the calling conventions by passing the output either by reference or as a return value. Rename them to ktime_get_coarse_real_ts64, ktime_get_coarse_ts64, ktime_get_raw_ts64, ktime_get_boottime_ts64 and ktime_get_clocktai_ts64 respectively, and provide the interfaces with macros or inline functions as needed. Signed-off-by: Arnd Bergmann Signed-off-by: Thomas Gleixner Cc: Stephen Boyd Cc: y2038@lists.linaro.org Cc: John Stultz Link: https://lkml.kernel.org/r/20180427134016.2525989-4-arnd@arndb.de --- include/linux/timekeeping.h | 43 ++++++++++++++++++++++++++++++++----------- include/linux/timekeeping32.h | 14 ++++++++++---- 2 files changed, 42 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 415dae6bf1f5..3ef9791d7d75 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -19,25 +19,25 @@ extern void xtime_update(unsigned long ticks); extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); -/* - * Kernel time accessors - */ -struct timespec64 current_kernel_time64(void); /* * timespec64 based interfaces */ -struct timespec64 get_monotonic_coarse64(void); -extern void getrawmonotonic64(struct timespec64 *ts); +extern void ktime_get_raw_ts64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); +extern void ktime_get_coarse_ts64(struct timespec64 *ts); +extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); + +void getboottime64(struct timespec64 *ts); + +/* + * time64_t base interfaces + */ extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); -extern void getboottime64(struct timespec64 *ts); - - /* * ktime_t based interfaces */ @@ -123,12 +123,12 @@ extern u64 ktime_get_real_fast_ns(void); /* * timespec64 interfaces utilizing the ktime based ones */ -static inline void get_monotonic_boottime64(struct timespec64 *ts) +static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } -static inline void timekeeping_clocktai64(struct timespec64 *ts) +static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } @@ -212,5 +212,26 @@ extern int update_persistent_clock64(struct timespec64 now); * deprecated aliases, don't use in new code */ #define getnstimeofday64(ts) ktime_get_real_ts64(ts) +#define get_monotonic_boottime64(ts) ktime_get_boottime_ts64(ts) +#define getrawmonotonic64(ts) ktime_get_raw_ts64(ts) +#define timekeeping_clocktai64(ts) ktime_get_clocktai_ts64(ts) + +static inline struct timespec64 current_kernel_time64(void) +{ + struct timespec64 ts; + + ktime_get_coarse_real_ts64(&ts); + + return ts; +} + +static inline struct timespec64 get_monotonic_coarse64(void) +{ + struct timespec64 ts; + + ktime_get_coarse_ts64(&ts); + + return ts; +} #endif diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index 5abff52d07fd..8762c2f45f8b 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -11,9 +11,11 @@ unsigned long get_seconds(void); static inline struct timespec current_kernel_time(void) { - struct timespec64 now = current_kernel_time64(); + struct timespec64 ts64; + + ktime_get_coarse_real_ts64(&ts64); - return timespec64_to_timespec(now); + return timespec64_to_timespec(ts64); } /** @@ -55,13 +57,17 @@ static inline void getrawmonotonic(struct timespec *ts) { struct timespec64 ts64; - getrawmonotonic64(&ts64); + ktime_get_raw_ts64(&ts64); *ts = timespec64_to_timespec(ts64); } static inline struct timespec get_monotonic_coarse(void) { - return timespec64_to_timespec(get_monotonic_coarse64()); + struct timespec64 ts64; + + ktime_get_coarse_ts64(&ts64); + + return timespec64_to_timespec(ts64); } static inline void getboottime(struct timespec *ts) -- cgit v1.2.3 From b9ff604cff1135cc576cf952d394ed9401aa234b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 27 Apr 2018 15:40:15 +0200 Subject: timekeeping: Add ktime_get_coarse_with_offset I have run into a couple of drivers using current_kernel_time() suffering from the y2038 problem, and they could be converted to using ktime_t, but don't have interfaces that skip the nanosecond calculation at the moment. This introduces ktime_get_coarse_with_offset() as a simpler variant of ktime_get_with_offset(), and adds wrappers for the three time domains we support with the existing function. Signed-off-by: Arnd Bergmann Signed-off-by: Thomas Gleixner Cc: Stephen Boyd Cc: y2038@lists.linaro.org Cc: John Stultz Link: https://lkml.kernel.org/r/20180427134016.2525989-5-arnd@arndb.de --- include/linux/timekeeping.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 3ef9791d7d75..42f71f4b658a 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -51,6 +51,7 @@ enum tk_offsets { extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); +extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); @@ -63,6 +64,11 @@ static inline ktime_t ktime_get_real(void) return ktime_get_with_offset(TK_OFFS_REAL); } +static inline ktime_t ktime_get_coarse_real(void) +{ + return ktime_get_coarse_with_offset(TK_OFFS_REAL); +} + /** * ktime_get_boottime - Returns monotonic time since boot in ktime_t format * @@ -74,6 +80,11 @@ static inline ktime_t ktime_get_boottime(void) return ktime_get_with_offset(TK_OFFS_BOOT); } +static inline ktime_t ktime_get_coarse_boottime(void) +{ + return ktime_get_coarse_with_offset(TK_OFFS_BOOT); +} + /** * ktime_get_clocktai - Returns the TAI time of day in ktime_t format */ @@ -82,6 +93,11 @@ static inline ktime_t ktime_get_clocktai(void) return ktime_get_with_offset(TK_OFFS_TAI); } +static inline ktime_t ktime_get_coarse_clocktai(void) +{ + return ktime_get_coarse_with_offset(TK_OFFS_TAI); +} + /** * ktime_mono_to_real - Convert monotonic time to clock realtime */ -- cgit v1.2.3 From 06aa376903b6e8c8741395a4702d78d47c7c27c6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 27 Apr 2018 15:40:16 +0200 Subject: timekeeping: Add more coarse clocktai/boottime interfaces The set of APIs we provide has a few holes for coarse times, e.g. we provide ktime_get_coarse_boottime() and ktime_get_boottime_ts64(), but not the combination of the two. This adds four new functions: ktime_get_coarse_boottime_ts64() ktime_get_boottime_seconds() ktime_get_coarse_clocktai_ts64() ktime_get_clocktai_seconds() to fill in some of the missing pieces. I have missed only the ktime_get_boottime_seconds() accessor in a few occasions in the past, but it seems better to just provide all four together, as there is very little cost to having them. Signed-off-by: Arnd Bergmann Signed-off-by: Thomas Gleixner Cc: Stephen Boyd Cc: y2038@lists.linaro.org Cc: John Stultz Link: https://lkml.kernel.org/r/20180427134016.2525989-6-arnd@arndb.de --- include/linux/timekeeping.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 42f71f4b658a..86bc2026efce 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -137,18 +137,40 @@ extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* - * timespec64 interfaces utilizing the ktime based ones + * timespec64/time64_t interfaces utilizing the ktime based ones + * for API completeness, these could be implemented more efficiently + * if needed. */ static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } +static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts) +{ + *ts = ktime_to_timespec64(ktime_get_coarse_boottime()); +} + +static inline time64_t ktime_get_boottime_seconds(void) +{ + return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC); +} + static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } +static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts) +{ + *ts = ktime_to_timespec64(ktime_get_coarse_clocktai()); +} + +static inline time64_t ktime_get_clocktai_seconds(void) +{ + return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC); +} + /* * RTC specific */ -- cgit v1.2.3 From ed582db639cfe65e2d901fca1be8fd813a18fec4 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Tue, 15 May 2018 17:19:17 +0200 Subject: iio: adc: stm32-dfsdm: include stm32-dfsdm-adc.h Fix the following sparse warnings: CHECK drivers/iio/adc/stm32-dfsdm-adc.c symbol 'stm32_dfsdm_get_buff_cb' was not declared. Should it be static? symbol 'stm32_dfsdm_release_buff_cb' was not declared. Should it be static? BTW, move interrupt.h to sort headers alphabetically. Signed-off-by: Fabrice Gasnier Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/stm32-dfsdm-adc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/adc/stm32-dfsdm-adc.h b/include/linux/iio/adc/stm32-dfsdm-adc.h index e7dc7a542a4e..0da298b41737 100644 --- a/include/linux/iio/adc/stm32-dfsdm-adc.h +++ b/include/linux/iio/adc/stm32-dfsdm-adc.h @@ -9,6 +9,8 @@ #ifndef STM32_DFSDM_ADC_H #define STM32_DFSDM_ADC_H +#include + int stm32_dfsdm_get_buff_cb(struct iio_dev *iio_dev, int (*cb)(const void *data, size_t size, void *private), -- cgit v1.2.3 From bbbc3fb663947764d338c305087322a646298894 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 30 Apr 2018 15:51:35 -0700 Subject: fs, fscrypt: only define ->s_cop when FS_ENCRYPTION is enabled Now that filesystems only set and use their fscrypt_operations when they are built with encryption support, we can remove ->s_cop from 'struct super_block' when FS_ENCRYPTION is disabled. This saves a few bytes on some kernels and also makes it consistent with ->i_crypt_info. Signed-off-by: Eric Biggers Signed-off-by: Theodore Ts'o --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 760d8da1b6c7..8e2460694c3a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1364,9 +1364,9 @@ struct super_block { void *s_security; #endif const struct xattr_handler **s_xattr; - +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) const struct fscrypt_operations *s_cop; - +#endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; -- cgit v1.2.3 From 54222025f2fe8055fa88c39b5d9f68cbd76b1be0 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 30 Apr 2018 15:51:36 -0700 Subject: fscrypt: clean up after fscrypt_prepare_lookup() conversions Now that all filesystems have been converted to use fscrypt_prepare_lookup(), we can remove the fscrypt_set_d_op() and fscrypt_set_encrypted_dentry() functions as well as un-export fscrypt_d_ops. Signed-off-by: Eric Biggers Signed-off-by: Theodore Ts'o --- include/linux/fscrypt_notsupp.h | 10 ---------- include/linux/fscrypt_supp.h | 14 -------------- 2 files changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h index 44b50c04bae9..25b6492de6e5 100644 --- a/include/linux/fscrypt_notsupp.h +++ b/include/linux/fscrypt_notsupp.h @@ -64,16 +64,6 @@ static inline void fscrypt_restore_control_page(struct page *page) return; } -static inline void fscrypt_set_d_op(struct dentry *dentry) -{ - return; -} - -static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry) -{ - return; -} - /* policy.c */ static inline int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg) diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h index 477a7a6504d2..c9c2cc26bc62 100644 --- a/include/linux/fscrypt_supp.h +++ b/include/linux/fscrypt_supp.h @@ -74,20 +74,6 @@ static inline struct page *fscrypt_control_page(struct page *page) extern void fscrypt_restore_control_page(struct page *); -extern const struct dentry_operations fscrypt_d_ops; - -static inline void fscrypt_set_d_op(struct dentry *dentry) -{ - d_set_d_op(dentry, &fscrypt_d_ops); -} - -static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry) -{ - spin_lock(&dentry->d_lock); - dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY; - spin_unlock(&dentry->d_lock); -} - /* policy.c */ extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); extern int fscrypt_ioctl_get_policy(struct file *, void __user *); -- cgit v1.2.3 From e12ee6836a3fd3c6ebc9b2dc8a7974af592340d0 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 30 Apr 2018 15:51:44 -0700 Subject: fscrypt: make fscrypt_operations.max_namelen an integer Now ->max_namelen() is only called to limit the filename length when adding NUL padding, and only for real filenames -- not symlink targets. It also didn't give the correct length for symlink targets anyway since it forgot to subtract 'sizeof(struct fscrypt_symlink_data)'. Thus, change ->max_namelen from a function to a simple 'unsigned int' that gives the filesystem's maximum filename length. Signed-off-by: Eric Biggers Signed-off-by: Theodore Ts'o --- include/linux/fscrypt_supp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h index c9c2cc26bc62..5080cb1bec4c 100644 --- a/include/linux/fscrypt_supp.h +++ b/include/linux/fscrypt_supp.h @@ -29,7 +29,7 @@ struct fscrypt_operations { int (*set_context)(struct inode *, const void *, size_t, void *); bool (*dummy_context)(struct inode *); bool (*empty_dir)(struct inode *); - unsigned (*max_namelen)(struct inode *); + unsigned int max_namelen; }; struct fscrypt_ctx { -- cgit v1.2.3 From 877b7cb0b6f283593a663134ee52703f12c895cc Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 19 May 2018 22:31:34 +0200 Subject: net: dsa: mv88e6xxx: Add minimal platform_data support Not all the world uses device tree. Some parts of the world still use platform devices and platform data. Add basic support for probing a Marvell switch via platform data. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/platform_data/mv88e6xxx.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/linux/platform_data/mv88e6xxx.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mv88e6xxx.h b/include/linux/platform_data/mv88e6xxx.h new file mode 100644 index 000000000000..88e91e05f48f --- /dev/null +++ b/include/linux/platform_data/mv88e6xxx.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __DSA_MV88E6XXX_H +#define __DSA_MV88E6XXX_H + +#include + +struct dsa_mv88e6xxx_pdata { + /* Must be first, such that dsa_register_switch() can access this + * without gory pointer manipulations + */ + struct dsa_chip_data cd; + const char *compatible; + unsigned int enabled_ports; + struct net_device *netdev; +}; + +#endif -- cgit v1.2.3 From 00baabe5286c41d21ed4a78f479b021eba1f0d51 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 19 May 2018 22:31:35 +0200 Subject: net: dsa: mv88e6xxx: Add support for EEPROM via platform data Add the size of the EEPROM to the platform data, so it can also be instantiated by a platform device. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/platform_data/mv88e6xxx.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mv88e6xxx.h b/include/linux/platform_data/mv88e6xxx.h index 88e91e05f48f..f63af2955ea0 100644 --- a/include/linux/platform_data/mv88e6xxx.h +++ b/include/linux/platform_data/mv88e6xxx.h @@ -12,6 +12,7 @@ struct dsa_mv88e6xxx_pdata { const char *compatible; unsigned int enabled_ports; struct net_device *netdev; + u32 eeprom_len; }; #endif -- cgit v1.2.3 From bf3c592b9d78ab2768150c680de22ef99e6e3b32 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sun, 20 May 2018 08:56:30 -0700 Subject: net: dsa: b53: Extend platform data to include DSA ports The b53 driver already defines and internally uses platform data to let the glue drivers specify parameters such as the chip id. What we were missing was a way to tell the core DSA layer about the ports and their type. Place a dsa_chip_data structure at the beginning of b53_platform_data for dsa_register_switch() to access it. This does not require modifications to b53_common.c which will pass platform_data trough. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/platform_data/b53.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/b53.h b/include/linux/platform_data/b53.h index 69d279c0da96..8eaef2f2b691 100644 --- a/include/linux/platform_data/b53.h +++ b/include/linux/platform_data/b53.h @@ -20,8 +20,12 @@ #define __B53_H #include +#include struct b53_platform_data { + /* Must be first such that dsa_register_switch() can access it */ + struct dsa_chip_data cd; + u32 chip_id; u16 enabled_ports; -- cgit v1.2.3 From a665140e583caad47bd2d10a433669bb26ce3b64 Mon Sep 17 00:00:00 2001 From: Joel Pepper Date: Thu, 26 Apr 2018 20:26:08 +0200 Subject: usb: gadget: composite Allow for larger configuration descriptors The composite framework allows us to create gadgets composed from many different functions, which need to fit into a single configuration descriptor. Some functions (like uvc) can produce configuration descriptors upwards of 2500 bytes on their own. This patch increases the limit from 1024 bytes to 4096. Signed-off-by: Joel Pepper Signed-off-by: Felipe Balbi --- include/linux/usb/composite.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 4b6b9283fa7b..8675e145ea8b 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -52,7 +52,7 @@ #define USB_GADGET_DELAYED_STATUS 0x7fff /* Impossibly large value */ /* big enough to hold our biggest descriptor */ -#define USB_COMP_EP0_BUFSIZ 1024 +#define USB_COMP_EP0_BUFSIZ 4096 /* OS feature descriptor length <= 4kB */ #define USB_COMP_EP0_OS_DESC_BUFSIZ 4096 -- cgit v1.2.3 From 6d796c68cd15234a33a4bd2ef7231125fea2dc6c Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Tue, 8 May 2018 09:04:20 +0800 Subject: mmc: core: add tunable delay waiting for power to be stable The hard-coded 10ms delay in mmc_power_up came from commit 79bccc5aefb4 ("mmc: increase power up delay"), which said "The TI controller on Toshiba Tecra M5 needs more time to power up or the cards will init incorrectly or not at all." But it's too engineering solution for a special board but force all platforms to wait for that long time, especially painful for mmc_power_up for eMMC when booting. However, it's added since 2009, and we can't tell if other platforms benefit from it. But in practise, the modern hardware are most likely to have a stable power supply with 1ms after setting it for no matter PMIC or discrete power. And more importnatly, most regulators implement the callback of ->set_voltage_time_sel() for regulator core to wait for specific period of time for the power supply to be stable, which means once regulator_set_voltage_* return, the power should reach the the minimum voltage that works for initialization. Of course, if there are some other ways for host to power the card, we should allow them to argue a suitable delay as well. With this patch, we could assign the delay from firmware, or we could assigne it via ->set_ios() callback from host drivers. Signed-off-by: Shawn Lin Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 8f1859044db1..64300a48dcce 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -22,6 +22,7 @@ struct mmc_ios { unsigned int clock; /* clock rate */ unsigned short vdd; + unsigned int power_delay_ms; /* waiting for stable power */ /* vdd stores the bit number of the selected voltage range from below. */ -- cgit v1.2.3 From 0788f1e97324d8378e860dc2560699ddc6f3aef9 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 10 May 2018 11:35:15 +0100 Subject: arm_pmu: simplify arm_pmu::handle_irq The arm_pmu::handle_irq() callback has the same prototype as a generic IRQ handler, taking the IRQ number and a void pointer argument which it must convert to an arm_pmu pointer. This means that all arm_pmu::handle_irq() take an IRQ number they never use, and all must explicitly cast the void pointer to an arm_pmu pointer. Instead, let's change arm_pmu::handle_irq to take an arm_pmu pointer, allowing these casts to be removed. The redundant IRQ number parameter is also removed. Suggested-by: Hoeun Ryu Signed-off-by: Mark Rutland Cc: Will Deacon Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 40036a57d072..ad5444491975 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -78,7 +78,7 @@ struct arm_pmu { struct pmu pmu; cpumask_t supported_cpus; char *name; - irqreturn_t (*handle_irq)(int irq_num, void *dev); + irqreturn_t (*handle_irq)(struct arm_pmu *pmu); void (*enable)(struct perf_event *event); void (*disable)(struct perf_event *event); int (*get_event_idx)(struct pmu_hw_events *hw_events, -- cgit v1.2.3 From 7b0c6b38c4f9f9736ccd41363b3cfd7143e1f823 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 21 May 2018 13:08:44 +0200 Subject: tty: add missing const to termios hw-change helper Add missing const qualifiers to the parameters of the termios hw-change helper, which is used by a few USB serial drivers. This specifically allows the pl2303 driver to use const arguments in one of its helper as well. Cc: Jiri Slaby Acked-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 1dd587ba6d88..955cd0c93d84 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -527,7 +527,7 @@ static inline speed_t tty_get_baud_rate(struct tty_struct *tty) } extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old); -extern int tty_termios_hw_change(struct ktermios *a, struct ktermios *b); +extern int tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b); extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *); -- cgit v1.2.3 From 2bc2e05f925dda7caaec4b715f4a22cb58e23393 Mon Sep 17 00:00:00 2001 From: Bin Liu Date: Mon, 21 May 2018 08:42:16 -0500 Subject: usb: musb: remove unused members in struct musb_hdrc_config The following members in struct musb_hdrc_config are not used, so remove them. soft_con utm_16 big_endian mult_bulk_tx mult_bulk_rx high_iso_tx high_iso_rx dma dma_channels dyn_fifo_size vendor_ctrl vendor_stat vendor_req dma_req_chan musb_hdrc_eps_bits Signed-off-by: Bin Liu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/musb.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h index 9eb908a98033..fc6c77918481 100644 --- a/include/linux/usb/musb.h +++ b/include/linux/usb/musb.h @@ -67,28 +67,13 @@ struct musb_hdrc_config { /* MUSB configuration-specific details */ unsigned multipoint:1; /* multipoint device */ unsigned dyn_fifo:1 __deprecated; /* supports dynamic fifo sizing */ - unsigned soft_con:1 __deprecated; /* soft connect required */ - unsigned utm_16:1 __deprecated; /* utm data witdh is 16 bits */ - unsigned big_endian:1; /* true if CPU uses big-endian */ - unsigned mult_bulk_tx:1; /* Tx ep required for multbulk pkts */ - unsigned mult_bulk_rx:1; /* Rx ep required for multbulk pkts */ - unsigned high_iso_tx:1; /* Tx ep required for HB iso */ - unsigned high_iso_rx:1; /* Rx ep required for HD iso */ - unsigned dma:1 __deprecated; /* supports DMA */ - unsigned vendor_req:1 __deprecated; /* vendor registers required */ /* need to explicitly de-assert the port reset after resume? */ unsigned host_port_deassert_reset_at_resume:1; u8 num_eps; /* number of endpoints _with_ ep0 */ - u8 dma_channels __deprecated; /* number of dma channels */ - u8 dyn_fifo_size; /* dynamic size in bytes */ - u8 vendor_ctrl __deprecated; /* vendor control reg width */ - u8 vendor_stat __deprecated; /* vendor status reg witdh */ - u8 dma_req_chan __deprecated; /* bitmask for required dma channels */ u8 ram_bits; /* ram address size */ - struct musb_hdrc_eps_bits *eps_bits __deprecated; u32 maximum_speed; }; -- cgit v1.2.3 From da0086d018223529c686ef46db039533572418d8 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 25 Mar 2018 14:49:03 +0200 Subject: i2c: Export of_i2c_get_board_info() I3C busses have to know about all I2C devices connected on the I3C bus to properly initialize the I3C master, and I2C frames can't be sent on the bus until this initialization is done. We can't let the I2C core parse the DT and instantiate I2C devices as part of its i2c_add_adapter() procedure because, when done this way, I2C devices are directly registered to the device-model and might be attached to drivers which could in turn start sending frames on the bus, which won't work since, as said above, the bus is not yet initialized. Export of_i2c_register_device() in order to let the I3C core parse the I2C device nodes by itself and initialize the bus. Signed-off-by: Boris Brezillon Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index aeb655772ef8..254cd34eeae2 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -901,6 +901,9 @@ extern const struct of_device_id *i2c_of_match_device(const struct of_device_id *matches, struct i2c_client *client); +int of_i2c_get_board_info(struct device *dev, struct device_node *node, + struct i2c_board_info *info); + #else static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) @@ -925,6 +928,13 @@ static inline const struct of_device_id return NULL; } +static inline int of_i2c_get_board_info(struct device *dev, + struct device_node *node, + struct i2c_board_info *info) +{ + return -ENOTSUPP; +} + #endif /* CONFIG_OF */ #if IS_ENABLED(CONFIG_ACPI) -- cgit v1.2.3 From e7638488434415aa478e78435cac8f0365737638 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 16 May 2018 11:46:08 -0700 Subject: mm: introduce MEMORY_DEVICE_FS_DAX and CONFIG_DEV_PAGEMAP_OPS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation for fixing dax-dma-vs-unmap issues, filesystems need to be able to rely on the fact that they will get wakeups on dev_pagemap page-idle events. Introduce MEMORY_DEVICE_FS_DAX and generic_dax_page_free() as common indicator / infrastructure for dax filesytems to require. With this change there are no users of the MEMORY_DEVICE_HOST designation, so remove it. The HMM sub-system extended dev_pagemap to arrange a callback when a dev_pagemap managed page is freed. Since a dev_pagemap page is free / idle when its reference count is 1 it requires an additional branch to check the page-type at put_page() time. Given put_page() is a hot-path we do not want to incur that check if HMM is not in use, so a static branch is used to avoid that overhead when not necessary. Now, the FS_DAX implementation wants to reuse this mechanism for receiving dev_pagemap ->page_free() callbacks. Rework the HMM-specific static-key into a generic mechanism that either HMM or FS_DAX code paths can enable. For ARCH=um builds, and any other arch that lacks ZONE_DEVICE support, care must be taken to compile out the DEV_PAGEMAP_OPS infrastructure. However, we still need to support FS_DAX in the FS_DAX_LIMITED case implemented by the s390/dcssblk driver. Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Michal Hocko Reported-by: kbuild test robot Reported-by: Thomas Meyer Reported-by: Dave Jiang Cc: "Jérôme Glisse" Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/memremap.h | 36 +++++++----------------- include/linux/mm.h | 71 ++++++++++++++++++++++++++++++++++++------------ 2 files changed, 63 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 7b4899c06f49..5ebfff65da4d 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ -#include #include #include @@ -30,13 +29,6 @@ struct vmem_altmap { * Specialize ZONE_DEVICE memory into multiple types each having differents * usage. * - * MEMORY_DEVICE_HOST: - * Persistent device memory (pmem): struct page might be allocated in different - * memory and architecture might want to perform special actions. It is similar - * to regular memory, in that the CPU can access it transparently. However, - * it is likely to have different bandwidth and latency than regular memory. - * See Documentation/nvdimm/nvdimm.txt for more information. - * * MEMORY_DEVICE_PRIVATE: * Device memory that is not directly addressable by the CPU: CPU can neither * read nor write private memory. In this case, we do still have struct pages @@ -53,11 +45,19 @@ struct vmem_altmap { * driver can hotplug the device memory using ZONE_DEVICE and with that memory * type. Any page of a process can be migrated to such memory. However no one * should be allow to pin such memory so that it can always be evicted. + * + * MEMORY_DEVICE_FS_DAX: + * Host memory that has similar access semantics as System RAM i.e. DMA + * coherent and supports page pinning. In support of coordinating page + * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a + * wakeup event whenever a page is unpinned and becomes idle. This + * wakeup is used to coordinate physical address space management (ex: + * fs truncate/hole punch) vs pinned pages (ex: device dma). */ enum memory_type { - MEMORY_DEVICE_HOST = 0, - MEMORY_DEVICE_PRIVATE, + MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_PUBLIC, + MEMORY_DEVICE_FS_DAX, }; /* @@ -129,8 +129,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); - -static inline bool is_zone_device_page(const struct page *page); #else static inline void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) @@ -161,20 +159,6 @@ static inline void vmem_altmap_free(struct vmem_altmap *altmap, } #endif /* CONFIG_ZONE_DEVICE */ -#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC) -static inline bool is_device_private_page(const struct page *page) -{ - return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PRIVATE; -} - -static inline bool is_device_public_page(const struct page *page) -{ - return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PUBLIC; -} -#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ - static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) diff --git a/include/linux/mm.h b/include/linux/mm.h index 1ac1f06a4be6..6e19265ee8f8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -821,27 +821,65 @@ static inline bool is_zone_device_page(const struct page *page) } #endif -#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC) -void put_zone_device_private_or_public_page(struct page *page); -DECLARE_STATIC_KEY_FALSE(device_private_key); -#define IS_HMM_ENABLED static_branch_unlikely(&device_private_key) -static inline bool is_device_private_page(const struct page *page); -static inline bool is_device_public_page(const struct page *page); -#else /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ -static inline void put_zone_device_private_or_public_page(struct page *page) +#ifdef CONFIG_DEV_PAGEMAP_OPS +void dev_pagemap_get_ops(void); +void dev_pagemap_put_ops(void); +void __put_devmap_managed_page(struct page *page); +DECLARE_STATIC_KEY_FALSE(devmap_managed_key); +static inline bool put_devmap_managed_page(struct page *page) +{ + if (!static_branch_unlikely(&devmap_managed_key)) + return false; + if (!is_zone_device_page(page)) + return false; + switch (page->pgmap->type) { + case MEMORY_DEVICE_PRIVATE: + case MEMORY_DEVICE_PUBLIC: + case MEMORY_DEVICE_FS_DAX: + __put_devmap_managed_page(page); + return true; + default: + break; + } + return false; +} + +static inline bool is_device_private_page(const struct page *page) { + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PRIVATE; } -#define IS_HMM_ENABLED 0 + +static inline bool is_device_public_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PUBLIC; +} + +#else /* CONFIG_DEV_PAGEMAP_OPS */ +static inline void dev_pagemap_get_ops(void) +{ +} + +static inline void dev_pagemap_put_ops(void) +{ +} + +static inline bool put_devmap_managed_page(struct page *page) +{ + return false; +} + static inline bool is_device_private_page(const struct page *page) { return false; } + static inline bool is_device_public_page(const struct page *page) { return false; } -#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ - +#endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline void get_page(struct page *page) { @@ -859,16 +897,13 @@ static inline void put_page(struct page *page) page = compound_head(page); /* - * For private device pages we need to catch refcount transition from - * 2 to 1, when refcount reach one it means the private device page is - * free and we need to inform the device driver through callback. See + * For devmap managed pages we need to catch refcount transition from + * 2 to 1, when refcount reach one it means the page is free and we + * need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ - if (IS_HMM_ENABLED && unlikely(is_device_private_page(page) || - unlikely(is_device_public_page(page)))) { - put_zone_device_private_or_public_page(page); + if (put_devmap_managed_page(page)) return; - } if (put_page_testzero(page)) __put_page(page); -- cgit v1.2.3 From 5fac7408d828719db6d3fdba63e3c3726a6d1ee5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 9 Mar 2018 17:44:31 -0800 Subject: mm, fs, dax: handle layout changes to pinned dax mappings Background: get_user_pages() in the filesystem pins file backed memory pages for access by devices performing dma. However, it only pins the memory pages not the page-to-file offset association. If a file is truncated the pages are mapped out of the file and dma may continue indefinitely into a page that is owned by a device driver. This breaks coherency of the file vs dma, but the assumption is that if userspace wants the file-space truncated it does not matter what data is inbound from the device, it is not relevant anymore. The only expectation is that dma can safely continue while the filesystem reallocates the block(s). Problem: This expectation that dma can safely continue while the filesystem changes the block map is broken by dax. With dax the target dma page *is* the filesystem block. The model of leaving the page pinned for dma, but truncating the file block out of the file, means that the filesytem is free to reallocate a block under active dma to another file and now the expected data-incoherency situation has turned into active data-corruption. Solution: Defer all filesystem operations (fallocate(), truncate()) on a dax mode file while any page/block in the file is under active dma. This solution assumes that dma is transient. Cases where dma operations are known to not be transient, like RDMA, have been explicitly disabled via commits like 5f1d43de5416 "IB/core: disable memory registration of filesystem-dax vmas". The dax_layout_busy_page() routine is called by filesystems with a lock held against mm faults (i_mmap_lock) to find pinned / busy dax pages. The process of looking up a busy page invalidates all mappings to trigger any subsequent get_user_pages() to block on i_mmap_lock. The filesystem continues to call dax_layout_busy_page() until it finally returns no more active pages. This approach assumes that the page pinning is transient, if that assumption is violated the system would have likely hung from the uncompleted I/O. Cc: Jeff Moyer Cc: Dave Chinner Cc: Matthew Wilcox Cc: Alexander Viro Cc: "Darrick J. Wong" Cc: Ross Zwisler Cc: Dave Hansen Cc: Andrew Morton Reported-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Dan Williams --- include/linux/dax.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index f9eb22ad341e..25bab6abb695 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -83,6 +83,8 @@ static inline void fs_put_dax(struct dax_device *dax_dev) struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc); + +struct page *dax_layout_busy_page(struct address_space *mapping); #else static inline int bdev_dax_supported(struct super_block *sb, int blocksize) { @@ -103,6 +105,11 @@ static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) return NULL; } +static inline struct page *dax_layout_busy_page(struct address_space *mapping) +{ + return NULL; +} + static inline int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc) { -- cgit v1.2.3 From f64c6013a2029316ea552f99823d116ee5f5f955 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 22 May 2018 09:50:53 -0700 Subject: rcu/x86: Provide early rcu_cpu_starting() callback The x86/mtrr code does horrific things because hardware. It uses stop_machine_from_inactive_cpu(), which does a wakeup (of the stopper thread on another CPU), which uses RCU, all before the CPU is onlined. RCU complains about this, because wakeups use RCU and RCU does (rightfully) not consider offline CPUs for grace-periods. Fix this by initializing RCU way early in the MTRR case. Tested-by: Mike Galbraith Signed-off-by: Peter Zijlstra Signed-off-by: Paul E. McKenney [ paulmck: Add !SMP support, per 0day Test Robot report. ] --- include/linux/rcupdate.h | 1 - include/linux/rcutiny.h | 1 + include/linux/rcutree.h | 1 + 3 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 19d235fefdb9..e679b175b411 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -108,7 +108,6 @@ void rcu_sched_qs(void); void rcu_bh_qs(void); void rcu_check_callbacks(int user); void rcu_report_dead(unsigned int cpu); -void rcu_cpu_starting(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); #ifdef CONFIG_RCU_STALL_COMMON diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index ce9beec35e34..7b3c82e8a625 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -132,5 +132,6 @@ static inline void rcu_all_qs(void) { barrier(); } #define rcutree_offline_cpu NULL #define rcutree_dead_cpu NULL #define rcutree_dying_cpu NULL +static inline void rcu_cpu_starting(unsigned int cpu) { } #endif /* __LINUX_RCUTINY_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 448f20f27396..914655848ef6 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -101,5 +101,6 @@ int rcutree_online_cpu(unsigned int cpu); int rcutree_offline_cpu(unsigned int cpu); int rcutree_dead_cpu(unsigned int cpu); int rcutree_dying_cpu(unsigned int cpu); +void rcu_cpu_starting(unsigned int cpu); #endif /* __LINUX_RCUTREE_H */ -- cgit v1.2.3 From 2528c389936efbbece25088426fe7c3c91ff355f Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Tue, 22 May 2018 00:28:38 -0700 Subject: qed: Add support for tlv request processing. The patch adds driver support for processing TLV requests/repsonses from the mfw and upper driver layers respectively. The implementation reads the requested TLVs from the shared memory, requests the values from upper layer drivers, populates this info (TLVs) shared memory and notifies MFW about the TLV values. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 907976fd56f7..8e4fad427ac2 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -182,6 +182,43 @@ enum qed_led_mode { QED_LED_MODE_RESTORE }; +struct qed_mfw_tlv_eth { + u16 lso_maxoff_size; + bool lso_maxoff_size_set; + u16 lso_minseg_size; + bool lso_minseg_size_set; + u8 prom_mode; + bool prom_mode_set; + u16 tx_descr_size; + bool tx_descr_size_set; + u16 rx_descr_size; + bool rx_descr_size_set; + u16 netq_count; + bool netq_count_set; + u32 tcp4_offloads; + bool tcp4_offloads_set; + u32 tcp6_offloads; + bool tcp6_offloads_set; + u16 tx_descr_qdepth; + bool tx_descr_qdepth_set; + u16 rx_descr_qdepth; + bool rx_descr_qdepth_set; + u8 iov_offload; +#define QED_MFW_TLV_IOV_OFFLOAD_NONE (0) +#define QED_MFW_TLV_IOV_OFFLOAD_MULTIQUEUE (1) +#define QED_MFW_TLV_IOV_OFFLOAD_VEB (2) +#define QED_MFW_TLV_IOV_OFFLOAD_VEPA (3) + bool iov_offload_set; + u8 txqs_empty; + bool txqs_empty_set; + u8 rxqs_empty; + bool rxqs_empty_set; + u8 num_txqs_full; + bool num_txqs_full_set; + u8 num_rxqs_full; + bool num_rxqs_full_set; +}; + #define DIRECT_REG_WR(reg_addr, val) writel((u32)val, \ (void __iomem *)(reg_addr)) -- cgit v1.2.3 From f240b6882211aae7155a9839dff1426e2853fe30 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Tue, 22 May 2018 00:28:39 -0700 Subject: qed: Add support for processing fcoe tlv request. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 193 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 193 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8e4fad427ac2..74c2b9ad8afa 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -219,6 +219,199 @@ struct qed_mfw_tlv_eth { bool num_rxqs_full_set; }; +#define QED_MFW_TLV_TIME_SIZE 14 +struct qed_mfw_tlv_time { + bool b_set; + u8 month; + u8 day; + u8 hour; + u8 min; + u16 msec; + u16 usec; +}; + +struct qed_mfw_tlv_fcoe { + u8 scsi_timeout; + bool scsi_timeout_set; + u32 rt_tov; + bool rt_tov_set; + u32 ra_tov; + bool ra_tov_set; + u32 ed_tov; + bool ed_tov_set; + u32 cr_tov; + bool cr_tov_set; + u8 boot_type; + bool boot_type_set; + u8 npiv_state; + bool npiv_state_set; + u32 num_npiv_ids; + bool num_npiv_ids_set; + u8 switch_name[8]; + bool switch_name_set; + u16 switch_portnum; + bool switch_portnum_set; + u8 switch_portid[3]; + bool switch_portid_set; + u8 vendor_name[8]; + bool vendor_name_set; + u8 switch_model[8]; + bool switch_model_set; + u8 switch_fw_version[8]; + bool switch_fw_version_set; + u8 qos_pri; + bool qos_pri_set; + u8 port_alias[3]; + bool port_alias_set; + u8 port_state; +#define QED_MFW_TLV_PORT_STATE_OFFLINE (0) +#define QED_MFW_TLV_PORT_STATE_LOOP (1) +#define QED_MFW_TLV_PORT_STATE_P2P (2) +#define QED_MFW_TLV_PORT_STATE_FABRIC (3) + bool port_state_set; + u16 fip_tx_descr_size; + bool fip_tx_descr_size_set; + u16 fip_rx_descr_size; + bool fip_rx_descr_size_set; + u16 link_failures; + bool link_failures_set; + u8 fcoe_boot_progress; + bool fcoe_boot_progress_set; + u64 rx_bcast; + bool rx_bcast_set; + u64 tx_bcast; + bool tx_bcast_set; + u16 fcoe_txq_depth; + bool fcoe_txq_depth_set; + u16 fcoe_rxq_depth; + bool fcoe_rxq_depth_set; + u64 fcoe_rx_frames; + bool fcoe_rx_frames_set; + u64 fcoe_rx_bytes; + bool fcoe_rx_bytes_set; + u64 fcoe_tx_frames; + bool fcoe_tx_frames_set; + u64 fcoe_tx_bytes; + bool fcoe_tx_bytes_set; + u16 crc_count; + bool crc_count_set; + u32 crc_err_src_fcid[5]; + bool crc_err_src_fcid_set[5]; + struct qed_mfw_tlv_time crc_err[5]; + u16 losync_err; + bool losync_err_set; + u16 losig_err; + bool losig_err_set; + u16 primtive_err; + bool primtive_err_set; + u16 disparity_err; + bool disparity_err_set; + u16 code_violation_err; + bool code_violation_err_set; + u32 flogi_param[4]; + bool flogi_param_set[4]; + struct qed_mfw_tlv_time flogi_tstamp; + u32 flogi_acc_param[4]; + bool flogi_acc_param_set[4]; + struct qed_mfw_tlv_time flogi_acc_tstamp; + u32 flogi_rjt; + bool flogi_rjt_set; + struct qed_mfw_tlv_time flogi_rjt_tstamp; + u32 fdiscs; + bool fdiscs_set; + u8 fdisc_acc; + bool fdisc_acc_set; + u8 fdisc_rjt; + bool fdisc_rjt_set; + u8 plogi; + bool plogi_set; + u8 plogi_acc; + bool plogi_acc_set; + u8 plogi_rjt; + bool plogi_rjt_set; + u32 plogi_dst_fcid[5]; + bool plogi_dst_fcid_set[5]; + struct qed_mfw_tlv_time plogi_tstamp[5]; + u32 plogi_acc_src_fcid[5]; + bool plogi_acc_src_fcid_set[5]; + struct qed_mfw_tlv_time plogi_acc_tstamp[5]; + u8 tx_plogos; + bool tx_plogos_set; + u8 plogo_acc; + bool plogo_acc_set; + u8 plogo_rjt; + bool plogo_rjt_set; + u32 plogo_src_fcid[5]; + bool plogo_src_fcid_set[5]; + struct qed_mfw_tlv_time plogo_tstamp[5]; + u8 rx_logos; + bool rx_logos_set; + u8 tx_accs; + bool tx_accs_set; + u8 tx_prlis; + bool tx_prlis_set; + u8 rx_accs; + bool rx_accs_set; + u8 tx_abts; + bool tx_abts_set; + u8 rx_abts_acc; + bool rx_abts_acc_set; + u8 rx_abts_rjt; + bool rx_abts_rjt_set; + u32 abts_dst_fcid[5]; + bool abts_dst_fcid_set[5]; + struct qed_mfw_tlv_time abts_tstamp[5]; + u8 rx_rscn; + bool rx_rscn_set; + u32 rx_rscn_nport[4]; + bool rx_rscn_nport_set[4]; + u8 tx_lun_rst; + bool tx_lun_rst_set; + u8 abort_task_sets; + bool abort_task_sets_set; + u8 tx_tprlos; + bool tx_tprlos_set; + u8 tx_nos; + bool tx_nos_set; + u8 rx_nos; + bool rx_nos_set; + u8 ols; + bool ols_set; + u8 lr; + bool lr_set; + u8 lrr; + bool lrr_set; + u8 tx_lip; + bool tx_lip_set; + u8 rx_lip; + bool rx_lip_set; + u8 eofa; + bool eofa_set; + u8 eofni; + bool eofni_set; + u8 scsi_chks; + bool scsi_chks_set; + u8 scsi_cond_met; + bool scsi_cond_met_set; + u8 scsi_busy; + bool scsi_busy_set; + u8 scsi_inter; + bool scsi_inter_set; + u8 scsi_inter_cond_met; + bool scsi_inter_cond_met_set; + u8 scsi_rsv_conflicts; + bool scsi_rsv_conflicts_set; + u8 scsi_tsk_full; + bool scsi_tsk_full_set; + u8 scsi_aca_active; + bool scsi_aca_active_set; + u8 scsi_tsk_abort; + bool scsi_tsk_abort_set; + u32 scsi_rx_chk[5]; + bool scsi_rx_chk_set[5]; + struct qed_mfw_tlv_time scsi_chk_tstamp[5]; +}; + #define DIRECT_REG_WR(reg_addr, val) writel((u32)val, \ (void __iomem *)(reg_addr)) -- cgit v1.2.3 From 77a509e4f6d14c2e09acbab5a89a769740bda62c Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Tue, 22 May 2018 00:28:40 -0700 Subject: qed: Add support for processing iscsi tlv request. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 74c2b9ad8afa..92b5352287df 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -412,6 +412,42 @@ struct qed_mfw_tlv_fcoe { struct qed_mfw_tlv_time scsi_chk_tstamp[5]; }; +struct qed_mfw_tlv_iscsi { + u8 target_llmnr; + bool target_llmnr_set; + u8 header_digest; + bool header_digest_set; + u8 data_digest; + bool data_digest_set; + u8 auth_method; +#define QED_MFW_TLV_AUTH_METHOD_NONE (1) +#define QED_MFW_TLV_AUTH_METHOD_CHAP (2) +#define QED_MFW_TLV_AUTH_METHOD_MUTUAL_CHAP (3) + bool auth_method_set; + u16 boot_taget_portal; + bool boot_taget_portal_set; + u16 frame_size; + bool frame_size_set; + u16 tx_desc_size; + bool tx_desc_size_set; + u16 rx_desc_size; + bool rx_desc_size_set; + u8 boot_progress; + bool boot_progress_set; + u16 tx_desc_qdepth; + bool tx_desc_qdepth_set; + u16 rx_desc_qdepth; + bool rx_desc_qdepth_set; + u64 rx_frames; + bool rx_frames_set; + u64 rx_bytes; + bool rx_bytes_set; + u64 tx_frames; + bool tx_frames_set; + u64 tx_bytes; + bool tx_bytes_set; +}; + #define DIRECT_REG_WR(reg_addr, val) writel((u32)val, \ (void __iomem *)(reg_addr)) -- cgit v1.2.3 From 59ccf86fe69a6a77afebe706913d6b551d84d5bc Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Tue, 22 May 2018 00:28:41 -0700 Subject: qed: Add driver infrastucture for handling mfw requests. MFW requests the TLVs in interrupt context. Extracting of the required data from upper layers and populating of the TLVs require process context. The patch adds work-queues for processing the tlv requests. It also adds the implementation for requesting the tlv values from appropriate protocol driver. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 92b5352287df..44af652e7407 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -751,6 +751,14 @@ struct qed_int_info { u8 used_cnt; }; +struct qed_generic_tlvs { +#define QED_TLV_IP_CSUM BIT(0) +#define QED_TLV_LSO BIT(1) + u16 feat_flags; +#define QED_TLV_MAC_COUNT 3 + u8 mac[QED_TLV_MAC_COUNT][ETH_ALEN]; +}; + #define QED_NVM_SIGNATURE 0x12435687 enum qed_nvm_flash_cmd { @@ -765,6 +773,8 @@ struct qed_common_cb_ops { void (*link_update)(void *dev, struct qed_link_output *link); void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); + void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); + void (*get_protocol_tlv_data)(void *dev, void *data); }; struct qed_selftest_ops { -- cgit v1.2.3 From 522239b445a2de988edb81672963708a6aaf9046 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 22 May 2018 23:17:03 -0700 Subject: uio, lib: Fix CONFIG_ARCH_HAS_UACCESS_MCSAFE compilation Add a common Kconfig CONFIG_ARCH_HAS_UACCESS_MCSAFE that archs can optionally select, and fixup the declaration of _copy_to_iter_mcsafe(). Fixes: 8780356ef630 ("x86/asm/memcpy_mcsafe: Define copy_to_iter_mcsafe()") Signed-off-by: Dan Williams --- include/linux/uio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index f5766e853a77..409c845d4cd3 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -155,7 +155,7 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #endif #ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE -size_t _copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i); +size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_to_iter_mcsafe _copy_to_iter #endif -- cgit v1.2.3 From b3a9a0c36e1f7b9e2e6cf965c2bb973624f2b3b9 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 2 May 2018 06:46:33 -0700 Subject: dax: Introduce a ->copy_to_iter dax operation Similar to the ->copy_from_iter() operation, a platform may want to deploy an architecture or device specific routine for handling reads from a dax_device like /dev/pmemX. On x86 this routine will point to a machine check safe version of copy_to_iter(). For now, add the plumbing to device-mapper and the dax core. Cc: Ross Zwisler Cc: Mike Snitzer Cc: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/dax.h | 5 +++++ include/linux/device-mapper.h | 5 +++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index f9eb22ad341e..a43b396fb336 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -20,6 +20,9 @@ struct dax_operations { /* copy_from_iter: required operation for fs-dax direct-i/o */ size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, struct iov_iter *); + /* copy_to_iter: required operation for fs-dax direct-i/o */ + size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t, + struct iov_iter *); }; extern struct attribute_group dax_attribute_group; @@ -118,6 +121,8 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); +size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, + size_t bytes, struct iov_iter *i); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 31fef7c34185..6fb0808e87c8 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -133,7 +133,7 @@ typedef int (*dm_busy_fn) (struct dm_target *ti); */ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); -typedef size_t (*dm_dax_copy_from_iter_fn)(struct dm_target *ti, pgoff_t pgoff, +typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); #define PAGE_SECTORS (PAGE_SIZE / 512) @@ -184,7 +184,8 @@ struct target_type { dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; - dm_dax_copy_from_iter_fn dax_copy_from_iter; + dm_dax_copy_iter_fn dax_copy_from_iter; + dm_dax_copy_iter_fn dax_copy_to_iter; /* For internal device-mapper use. */ struct list_head list; -- cgit v1.2.3 From a37061a678cab6d164f2989dd6f3b65f730289c7 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 14 May 2018 23:46:59 +0200 Subject: netfilter: lift one-nat-hook-only restriction This reverts commit f92b40a8b2645 ("netfilter: core: only allow one nat hook per hook point"), this limitation is no longer needed. The nat core now invokes these functions and makes sure that hook evaluation stops after a mapping is created and a null binding is created otherwise. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 85a1a0b32c66..72f5871b9a0a 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -67,7 +67,6 @@ struct nf_hook_ops { struct net_device *dev; void *priv; u_int8_t pf; - bool nat_hook; unsigned int hooknum; /* Hooks are ordered in ascending priority. */ int priority; -- cgit v1.2.3 From 1f4b24397d3e164dde7026b91056e67304724fb6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 23 May 2018 09:17:12 +0200 Subject: netfilter: add struct nf_ct_hook and use it Move the nf_ct_destroy indirection to the struct nf_ct_hook. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 72f5871b9a0a..75ded6f6eebe 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -373,13 +373,18 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; void nf_ct_attach(struct sk_buff *, const struct sk_buff *); -extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif struct nf_conn; enum ip_conntrack_info; + +struct nf_ct_hook { + void (*destroy)(struct nf_conntrack *); +}; +extern struct nf_ct_hook __rcu *nf_ct_hook; + struct nlattr; struct nfnl_ct_hook { -- cgit v1.2.3 From 2c205dd3981f79cef097207ba9c61c2260812f39 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 23 May 2018 09:17:19 +0200 Subject: netfilter: add struct nf_nat_hook and use it Move decode_session() and parse_nat_setup_hook() indirections to struct nf_nat_hook structure. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 75ded6f6eebe..e8d09dc028f6 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -320,18 +320,29 @@ int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry); #include -extern void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); + +struct nf_conn; +enum nf_nat_manip_type; +struct nlattr; + +struct nf_nat_hook { + int (*parse_nat_setup)(struct nf_conn *ct, enum nf_nat_manip_type manip, + const struct nlattr *attr); + void (*decode_session)(struct sk_buff *skb, struct flowi *fl); +}; + +extern struct nf_nat_hook __rcu *nf_nat_hook; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { #ifdef CONFIG_NF_NAT_NEEDED - void (*decodefn)(struct sk_buff *, struct flowi *); + struct nf_nat_hook *nat_hook; rcu_read_lock(); - decodefn = rcu_dereference(nf_nat_decode_session_hook); - if (decodefn) - decodefn(skb, fl); + nat_hook = rcu_dereference(nf_nat_hook); + if (nat_hook->decode_session) + nat_hook->decode_session(skb, fl); rcu_read_unlock(); #endif } -- cgit v1.2.3 From 368982cd7d1bd41cd39049c794990aca3770db44 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 23 May 2018 09:17:24 +0200 Subject: netfilter: nfnetlink_queue: resolve clash for unconfirmed conntracks In nfqueue, two consecutive skbuffs may race to create the conntrack entry. Hence, the one that loses the race gets dropped due to clash in the insertion into the hashes from the nf_conntrack_confirm() path. This patch adds a new nf_conntrack_update() function which searches for possible clashes and resolve them. NAT mangling for the packet losing race is corrected by using the conntrack information that won race. In order to avoid direct module dependencies with conntrack and NAT, the nf_ct_hook and nf_nat_hook structures are used for this purpose. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index e8d09dc028f6..04551af2ff23 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -324,11 +324,15 @@ int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry); struct nf_conn; enum nf_nat_manip_type; struct nlattr; +enum ip_conntrack_dir; struct nf_nat_hook { int (*parse_nat_setup)(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr); void (*decode_session)(struct sk_buff *skb, struct flowi *fl); + unsigned int (*manip_pkt)(struct sk_buff *skb, struct nf_conn *ct, + enum nf_nat_manip_type mtype, + enum ip_conntrack_dir dir); }; extern struct nf_nat_hook __rcu *nf_nat_hook; @@ -392,6 +396,7 @@ struct nf_conn; enum ip_conntrack_info; struct nf_ct_hook { + int (*update)(struct net *net, struct sk_buff *skb); void (*destroy)(struct nf_conntrack *); }; extern struct nf_ct_hook __rcu *nf_ct_hook; -- cgit v1.2.3 From 036399782bf51dafb932b680b260936b2b5f8dd6 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 22 May 2018 15:31:30 +0530 Subject: cpufreq: Rename cpufreq_can_do_remote_dvfs() This routine checks if the CPU running this code belongs to the policy of the target CPU or if not, can it do remote DVFS for it remotely. But the current name of it implies as if it is only about doing remote updates. Rename it to make it more relevant. Suggested-by: Rafael J. Wysocki Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 87f48dd932eb..882a9b9e34bc 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -571,7 +571,7 @@ struct governor_attr { size_t count); }; -static inline bool cpufreq_can_do_remote_dvfs(struct cpufreq_policy *policy) +static inline bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy) { /* * Allow remote callbacks if: -- cgit v1.2.3 From dcab51f19b291d5ee23724c51b0a3a597c16451a Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 22 May 2018 15:03:31 -0700 Subject: bpf: Expose check_uarg_tail_zero() This patch exposes check_uarg_tail_zero() which will be reused by a later BTF patch. Its name is changed to bpf_check_uarg_tail_zero(). Signed-off-by: Martin KaFai Lau Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ed0122b45b63..f6fe3c719ca8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -463,6 +463,8 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_get_file_flag(int flags); +int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size, + size_t actual_size); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. -- cgit v1.2.3 From 9b2cf328b2eccf761537a06bef914d2a0700fba7 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 22 May 2018 14:57:21 -0700 Subject: bpf: btf: Rename btf_key_id and btf_value_id in bpf_map_info In "struct bpf_map_info", the name "btf_id", "btf_key_id" and "btf_value_id" could cause confusion because the "id" of "btf_id" means the BPF obj id given to the BTF object while "btf_key_id" and "btf_value_id" means the BTF type id within that BTF object. To make it clear, btf_key_id and btf_value_id are renamed to btf_key_type_id and btf_value_type_id. Suggested-by: Daniel Borkmann Signed-off-by: Martin KaFai Lau Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f6fe3c719ca8..1795eeee846c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -69,8 +69,8 @@ struct bpf_map { u32 pages; u32 id; int numa_node; - u32 btf_key_id; - u32 btf_value_id; + u32 btf_key_type_id; + u32 btf_value_type_id; struct btf *btf; bool unpriv_array; /* 55 bytes hole */ -- cgit v1.2.3 From 3027743f83f867d85662f5134e835c2e199cb9be Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Mon, 21 May 2018 10:57:07 -0700 Subject: gpio: Remove VLA from gpiolib The new challenge is to remove VLAs from the kernel (see https://lkml.org/lkml/2018/3/7/621) to eventually turn on -Wvla. Using a kmalloc array is the easy way to fix this but kmalloc is still more expensive than stack allocation. Introduce a fast path with a fixed size stack array to cover most chip with gpios below some fixed amount. The slow path dynamically allocates an array to cover those chips with a large number of gpios. Reviewed-by: Geert Uytterhoeven Reviewed-by: Phil Reid Reviewed-and-tested-by: Lukas Wunner Signed-off-by: Lukas Wunner Signed-off-by: Laura Abbott Reviewed-by: Andy Shevchenko Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index dbd065963296..243112c7fa7d 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -116,7 +116,7 @@ int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, int *value_array); void gpiod_set_raw_value(struct gpio_desc *desc, int value); -void gpiod_set_raw_array_value(unsigned int array_size, +int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, int *value_array); @@ -134,7 +134,7 @@ int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, int *value_array); void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value); -void gpiod_set_raw_array_value_cansleep(unsigned int array_size, +int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, int *value_array); @@ -369,12 +369,13 @@ static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_raw_array_value(unsigned int array_size, +static inline int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, int *value_array) { /* GPIO can never have been requested */ WARN_ON(1); + return 0; } static inline int gpiod_get_value_cansleep(const struct gpio_desc *desc) @@ -423,12 +424,13 @@ static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_raw_array_value_cansleep(unsigned int array_size, +static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, int *value_array) { /* GPIO can never have been requested */ WARN_ON(1); + return 0; } static inline int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce) -- cgit v1.2.3 From 449325b52b7a6208f65ed67d3484fd7b7184477b Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 21 May 2018 19:22:29 -0700 Subject: umh: introduce fork_usermode_blob() helper Introduce helper: int fork_usermode_blob(void *data, size_t len, struct umh_info *info); struct umh_info { struct file *pipe_to_umh; struct file *pipe_from_umh; pid_t pid; }; that GPLed kernel modules (signed or unsigned) can use it to execute part of its own data as swappable user mode process. The kernel will do: - allocate a unique file in tmpfs - populate that file with [data, data + len] bytes - user-mode-helper code will do_execve that file and, before the process starts, the kernel will create two unix pipes for bidirectional communication between kernel module and umh - close tmpfs file, effectively deleting it - the fork_usermode_blob will return zero on success and populate 'struct umh_info' with two unix pipes and the pid of the user process As the first step in the development of the bpfilter project the fork_usermode_blob() helper is introduced to allow user mode code to be invoked from a kernel module. The idea is that user mode code plus normal kernel module code are built as part of the kernel build and installed as traditional kernel module into distro specified location, such that from a distribution point of view, there is no difference between regular kernel modules and kernel modules + umh code. Such modules can be signed, modprobed, rmmod, etc. The use of this new helper by a kernel module doesn't make it any special from kernel and user space tooling point of view. Such approach enables kernel to delegate functionality traditionally done by the kernel modules into the user space processes (either root or !root) and reduces security attack surface of the new code. The buggy umh code would crash the user process, but not the kernel. Another advantage is that umh code of the kernel module can be debugged and tested out of user space (e.g. opening the possibility to run clang sanitizers, fuzzers or user space test suites on the umh code). In case of the bpfilter project such architecture allows complex control plane to be done in the user space while bpf based data plane stays in the kernel. Since umh can crash, can be oom-ed by the kernel, killed by the admin, the kernel module that uses them (like bpfilter) needs to manage life time of umh on its own via two unix pipes and the pid of umh. The exit code of such kernel module should kill the umh it started, so that rmmod of the kernel module will cleanup the corresponding umh. Just like if the kernel module does kmalloc() it should kfree() it in the exit code. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/binfmts.h | 1 + include/linux/umh.h | 12 ++++++++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 4955e0863b83..c05f24fac4f6 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -150,5 +150,6 @@ extern int do_execveat(int, struct filename *, const char __user * const __user *, const char __user * const __user *, int); +int do_execve_file(struct file *file, void *__argv, void *__envp); #endif /* _LINUX_BINFMTS_H */ diff --git a/include/linux/umh.h b/include/linux/umh.h index 244aff638220..5c812acbb80a 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -22,8 +22,10 @@ struct subprocess_info { const char *path; char **argv; char **envp; + struct file *file; int wait; int retval; + pid_t pid; int (*init)(struct subprocess_info *info, struct cred *new); void (*cleanup)(struct subprocess_info *info); void *data; @@ -38,6 +40,16 @@ call_usermodehelper_setup(const char *path, char **argv, char **envp, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *), void *data); +struct subprocess_info *call_usermodehelper_setup_file(struct file *file, + int (*init)(struct subprocess_info *info, struct cred *new), + void (*cleanup)(struct subprocess_info *), void *data); +struct umh_info { + struct file *pipe_to_umh; + struct file *pipe_from_umh; + pid_t pid; +}; +int fork_usermode_blob(void *data, size_t len, struct umh_info *info); + extern int call_usermodehelper_exec(struct subprocess_info *info, int wait); -- cgit v1.2.3 From d2ba09c17a0647f899d6c20a11bab9e6d3382f07 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 21 May 2018 19:22:30 -0700 Subject: net: add skeleton of bpfilter kernel module bpfilter.ko consists of bpfilter_kern.c (normal kernel module code) and user mode helper code that is embedded into bpfilter.ko The steps to build bpfilter.ko are the following: - main.c is compiled by HOSTCC into the bpfilter_umh elf executable file - with quite a bit of objcopy and Makefile magic the bpfilter_umh elf file is converted into bpfilter_umh.o object file with _binary_net_bpfilter_bpfilter_umh_start and _end symbols Example: $ nm ./bld_x64/net/bpfilter/bpfilter_umh.o 0000000000004cf8 T _binary_net_bpfilter_bpfilter_umh_end 0000000000004cf8 A _binary_net_bpfilter_bpfilter_umh_size 0000000000000000 T _binary_net_bpfilter_bpfilter_umh_start - bpfilter_umh.o and bpfilter_kern.o are linked together into bpfilter.ko bpfilter_kern.c is a normal kernel module code that calls the fork_usermode_blob() helper to execute part of its own data as a user mode process. Notice that _binary_net_bpfilter_bpfilter_umh_start - end is placed into .init.rodata section, so it's freed as soon as __init function of bpfilter.ko is finished. As part of __init the bpfilter.ko does first request/reply action via two unix pipe provided by fork_usermode_blob() helper to make sure that umh is healthy. If not it will kill it via pid. Later bpfilter_process_sockopt() will be called from bpfilter hooks in get/setsockopt() to pass iptable commands into umh via bpfilter.ko If admin does 'rmmod bpfilter' the __exit code bpfilter.ko will kill umh as well. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpfilter.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/bpfilter.h (limited to 'include/linux') diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h new file mode 100644 index 000000000000..687b1760bb9f --- /dev/null +++ b/include/linux/bpfilter.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BPFILTER_H +#define _LINUX_BPFILTER_H + +#include + +struct sock; +int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char *optval, + unsigned int optlen); +int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char *optval, + int *optlen); +extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname, + char __user *optval, + unsigned int optlen, bool is_set); +#endif -- cgit v1.2.3 From 8eea1ca82be90a7e7a4624ab9cb323574a5f71df Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 22 May 2018 11:34:40 -0400 Subject: gso: limit udp gso to egress-only virtual devices Until the udp receive stack supports large packets (UDP GRO), GSO packets must not loop from the egress to the ingress path. Revert the change that added NETIF_F_GSO_UDP_L4 to various virtual devices through NETIF_F_GSO_ENCAP_ALL as this included devices that may loop packets, such as veth and macvlan. Instead add it to specific devices that forward to another device's egress path, bonding and team. Fixes: 83aa025f535f ("udp: add gso support to virtual devices") CC: Alexander Duyck Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index c87c3a3453c1..623bb8ced060 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -220,7 +220,6 @@ enum { NETIF_F_GSO_GRE_CSUM | \ NETIF_F_GSO_IPXIP4 | \ NETIF_F_GSO_IPXIP6 | \ - NETIF_F_GSO_UDP_L4 | \ NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) -- cgit v1.2.3 From cd3092c7f8db8c320ea7f1aa7c1adeac2450f43a Mon Sep 17 00:00:00 2001 From: Mathieu Xhonneux Date: Sun, 20 May 2018 14:58:15 +0100 Subject: bpf: Split lwt inout verifier structures The new bpf_lwt_push_encap helper should only be accessible within the LWT BPF IN hook, and not the OUT one, as this may lead to a skb under panic. At the moment, both LWT BPF IN and OUT share the same list of helpers, whose calls are authorized by the verifier. This patch separates the verifier ops for the IN and OUT hooks, and allows the IN hook to call the bpf_lwt_push_encap helper. This patch is also the occasion to put all lwt_*_func_proto functions together for clarity. At the moment, socks_op_func_proto is in the middle of lwt_inout_func_proto and lwt_xmit_func_proto. Signed-off-by: Mathieu Xhonneux Acked-by: David Lebrun Signed-off-by: Daniel Borkmann --- include/linux/bpf_types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index b67f8793de0d..aa5c8b878474 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -9,8 +9,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) -- cgit v1.2.3 From 004d4b274e2a1a895a0e5dc66158b90a7d463d44 Mon Sep 17 00:00:00 2001 From: Mathieu Xhonneux Date: Sun, 20 May 2018 14:58:16 +0100 Subject: ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux Acked-by: David Lebrun Signed-off-by: Daniel Borkmann --- include/linux/bpf_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index aa5c8b878474..b161e506dcfc 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -12,6 +12,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local) BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg) -- cgit v1.2.3 From 2468f0d51548b23507ceb3bba5f4e3acaea117ba Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 14 May 2018 10:06:28 +0200 Subject: regulator: lp8788-ldo: Pass descriptor instead of GPIO number Instead of passing a global GPIO number, pass a descriptor looked up with the standard devm_gpiod_get_index_optional() call. This driver has supported passing a LDO enable GPIO for years, yet this facility has never been put to use in the upstream kernel. If someone desires to put in place GPIO control for the LDOs, this can be done by adding a GPIO descriptor table in the MFD nexus in drivers/mfd/lp8788.c for the LDO device when spawning the MFD children, or using a board file. Signed-off-by: Linus Walleij Acked-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/lp8788.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/lp8788.h b/include/linux/mfd/lp8788.h index 786bf6679a28..2010e0de3e34 100644 --- a/include/linux/mfd/lp8788.h +++ b/include/linux/mfd/lp8788.h @@ -181,20 +181,6 @@ struct lp8788_buck2_dvs { enum lp8788_dvs_sel vsel; }; -/* - * struct lp8788_ldo_enable_pin - * - * Basically, all LDOs are enabled through the I2C commands. - * But ALDO 1 ~ 5, 7, DLDO 7, 9, 11 can be enabled by external gpio pins. - * - * @gpio : gpio number which is used for enabling ldos - * @init_state : initial gpio state (ex. GPIOF_OUT_INIT_LOW) - */ -struct lp8788_ldo_enable_pin { - int gpio; - int init_state; -}; - /* * struct lp8788_chg_param * @addr : charging control register address (range : 0x11 ~ 0x1C) @@ -288,7 +274,6 @@ struct lp8788_vib_platform_data { * @aldo_data : regulator initial data for analog ldo * @buck1_dvs : gpio configurations for buck1 dvs * @buck2_dvs : gpio configurations for buck2 dvs - * @ldo_pin : gpio configurations for enabling LDOs * @chg_pdata : platform data for charger driver * @alarm_sel : rtc alarm selection (1 or 2) * @bl_pdata : configurable data for backlight driver @@ -306,7 +291,6 @@ struct lp8788_platform_data { struct regulator_init_data *aldo_data[LP8788_NUM_ALDOS]; struct lp8788_buck1_dvs *buck1_dvs; struct lp8788_buck2_dvs *buck2_dvs; - struct lp8788_ldo_enable_pin *ldo_pin[EN_LDOS_MAX]; /* charger */ struct lp8788_charger_platform_data *chg_pdata; -- cgit v1.2.3 From d7a261c2d1f233260c48651b4e68987ce1206139 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 14 May 2018 10:06:29 +0200 Subject: regulator: max8952: Pass descriptor instead of GPIO number Instead of passing a global GPIO number for the enable GPIO, pass a descriptor looked up with the standard devm_gpiod_get_optional() call. All users of this regulator use device tree so the transition is pretty smooth. Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- include/linux/regulator/max8952.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/max8952.h b/include/linux/regulator/max8952.h index 4dbb63a1d4ab..686c42c041b5 100644 --- a/include/linux/regulator/max8952.h +++ b/include/linux/regulator/max8952.h @@ -120,7 +120,6 @@ enum { struct max8952_platform_data { int gpio_vid0; int gpio_vid1; - int gpio_en; u32 default_mode; u32 dvs_mode[MAX8952_NUM_DVS_MODE]; /* MAX8952_DVS_MODEx_XXXXmV */ -- cgit v1.2.3 From 9ae5cc75ceaacf69cc50b9fd4713276c2aa62eb9 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 14 May 2018 10:06:32 +0200 Subject: regulator: s5m8767: Pass descriptor instead of GPIO number Instead of passing a global GPIO number for the enable GPIO, pass a descriptor looked up from the device tree node for the regulator. This regulator supports passing platform data, but enable/sleep regulators are looked up from the device tree exclusively, so we can need not touch other files. Signed-off-by: Linus Walleij Acked-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/samsung/core.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index 5a23dd4df432..28f4ae76271d 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -39,6 +39,8 @@ #define STEP_12_5_MV 12500 #define STEP_6_25_MV 6250 +struct gpio_desc; + enum sec_device_type { S5M8751X, S5M8763X, @@ -151,7 +153,7 @@ struct sec_regulator_data { int id; struct regulator_init_data *initdata; struct device_node *reg_node; - int ext_control_gpio; + struct gpio_desc *ext_control_gpiod; }; /* -- cgit v1.2.3 From 3012e81446d011c1bd99812e562e2292f21060fb Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 14 May 2018 10:06:33 +0200 Subject: regulator: tps65090: Pass descriptor instead of GPIO number Instead of passing a global GPIO number for the enable GPIO, pass a descriptor looked up from the device tree node for the regulator. This regulator supports passing platform data, but enable/sleep regulators are looked up from the device tree exclusively, so we can need not touch other files. Signed-off-by: Linus Walleij Acked-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/tps65090.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h index 67d144b3b8f9..f05bf4a146e2 100644 --- a/include/linux/mfd/tps65090.h +++ b/include/linux/mfd/tps65090.h @@ -83,6 +83,8 @@ enum { #define TPS65090_MAX_REG TPS65090_REG_AD_OUT2 #define TPS65090_NUM_REGS (TPS65090_MAX_REG + 1) +struct gpio_desc; + struct tps65090 { struct device *dev; struct regmap *rmap; @@ -95,8 +97,8 @@ struct tps65090 { * @reg_init_data: The regulator init data. * @enable_ext_control: Enable extrenal control or not. Only available for * DCDC1, DCDC2 and DCDC3. - * @gpio: Gpio number if external control is enabled and controlled through - * gpio. + * @gpiod: Gpio descriptor if external control is enabled and controlled through + * gpio * @overcurrent_wait_valid: True if the overcurrent_wait should be applied. * @overcurrent_wait: Value to set as the overcurrent wait time. This is the * actual bitfield value, not a time in ms (valid value are 0 - 3). @@ -104,7 +106,7 @@ struct tps65090 { struct tps65090_regulator_plat_data { struct regulator_init_data *reg_init_data; bool enable_ext_control; - int gpio; + struct gpio_desc *gpiod; bool overcurrent_wait_valid; int overcurrent_wait; }; -- cgit v1.2.3 From ece711b5a42ce9b99a2a3706c56bf70a5425a7bf Mon Sep 17 00:00:00 2001 From: Adam Thomson Date: Tue, 22 May 2018 16:16:23 +0100 Subject: power: supply: Add fwnode pointer to power_supply_config struct To allow users of the power supply framework to be hw description agnostic, this commit adds the ability to pass a fwnode pointer, via the power_supply_config structure, to the initialisation code of the core, instead of explicitly specifying of_ndoe. If that fwnode pointer is provided then it will automatically resolve down to of_node on platforms which support it, otherwise it will be NULL. In the future, when ACPI support is added, this can be modified to accommodate ACPI without the need to change calling code which already provides the fwnode handle in this manner. Signed-off-by: Adam Thomson Suggested-by: Heikki Krogerus Reviewed-by: Sebastian Reichel Reviewed-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/power_supply.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 0c9a572a1eb8..b21c4bd96b84 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -199,6 +199,8 @@ struct power_supply; /* Run-time specific power supply configuration */ struct power_supply_config { struct device_node *of_node; + struct fwnode_handle *fwnode; + /* Driver private data */ void *drv_data; -- cgit v1.2.3 From 8b22f3d2f6b8652b71301d68d8ca69f91b5311a7 Mon Sep 17 00:00:00 2001 From: Jon Derrick Date: Fri, 18 May 2018 13:27:58 -0600 Subject: PCI: Add Intel VMD devices to pci ids Add the Intel VMD device ids to the pci id database and update the VMD driver. Signed-off-by: Jon Derrick Signed-off-by: Lorenzo Pieralisi --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index cc608fc55334..0334066f2e48 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2672,6 +2672,7 @@ #define PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI 0x1e31 #define PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MIN 0x1e40 #define PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MAX 0x1e5f +#define PCI_DEVICE_ID_INTEL_VMD_201D 0x201d #define PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MIN 0x2310 #define PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MAX 0x231f #define PCI_DEVICE_ID_INTEL_82801AA_0 0x2410 @@ -2776,6 +2777,7 @@ #define PCI_DEVICE_ID_INTEL_ICH8_4 0x2815 #define PCI_DEVICE_ID_INTEL_ICH8_5 0x283e #define PCI_DEVICE_ID_INTEL_ICH8_6 0x2850 +#define PCI_DEVICE_ID_INTEL_VMD_28C0 0x28c0 #define PCI_DEVICE_ID_INTEL_ICH9_0 0x2910 #define PCI_DEVICE_ID_INTEL_ICH9_1 0x2917 #define PCI_DEVICE_ID_INTEL_ICH9_2 0x2912 -- cgit v1.2.3 From e6fc46498784e799d3eb95d83079180e413c4e7d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 24 May 2018 11:00:39 -0600 Subject: blk-mq: avoid starving tag allocation after allocating process migrates When the allocation process is scheduled back and the mapped hw queue is changed, fake one extra wake up on previous queue for compensating wake up miss, so other allocations on the previous queue won't be starved. This patch fixes one request allocation hang issue, which can be triggered easily in case of very low nr_request. The race is as follows: 1) 2 hw queues, nr_requests are 2, and wake_batch is one 2) there are 3 waiters on hw queue 0 3) two in-flight requests in hw queue 0 are completed, and only two waiters of 3 are waken up because of wake_batch, but both the two waiters can be scheduled to another CPU and cause to switch to hw queue 1 4) then the 3rd waiter will wait for ever, since no in-flight request is in hw queue 0 any more. 5) this patch fixes it by the fake wakeup when waiter is scheduled to another hw queue Cc: Reviewed-by: Omar Sandoval Signed-off-by: Ming Lei Modified commit message to make it clearer, and make it apply on top of the 4.18 branch. Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 0c4a9c242dd7..e6539536dea9 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -512,6 +512,13 @@ static inline struct sbq_wait_state *sbq_wait_ptr(struct sbitmap_queue *sbq, */ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq); +/** + * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue + * on a &struct sbitmap_queue. + * @sbq: Bitmap queue to wake up. + */ +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq); + /** * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct * seq_file. -- cgit v1.2.3 From eebba71e1cb4f3464645c4b106f8ccc31bc5cd11 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Fri, 11 May 2018 12:03:16 -0500 Subject: hwspinlock/core: Switch to SPDX license identifier Use the appropriate SPDX license identifier in the Hwspinlock core driver source files and drop the previous boilerplate license text. Signed-off-by: Suman Anna Signed-off-by: Bjorn Andersson --- include/linux/hwspinlock.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h index fe450ee58d55..57537e67b468 100644 --- a/include/linux/hwspinlock.h +++ b/include/linux/hwspinlock.h @@ -1,18 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Hardware spinlock public header * * Copyright (C) 2010 Texas Instruments Incorporated - http://www.ti.com * * Contact: Ohad Ben-Cohen - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __LINUX_HWSPINLOCK_H -- cgit v1.2.3 From 87e5808d52b65fc5b0bfda209ba8864cc2f933e5 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 23 May 2018 08:05:20 +0200 Subject: net: phy: replace bool members in struct phy_device with bit-fields In struct phy_device we have a number of flags being defined as type bool. Similar to e.g. struct pci_dev we can save some space by using bit-fields. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 073235e70442..6cd09098427c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -406,13 +406,17 @@ struct phy_device { u32 phy_id; struct phy_c45_device_ids c45_ids; - bool is_c45; - bool is_internal; - bool is_pseudo_fixed_link; - bool has_fixups; - bool suspended; - bool sysfs_links; - bool loopback_enabled; + unsigned is_c45:1; + unsigned is_internal:1; + unsigned is_pseudo_fixed_link:1; + unsigned has_fixups:1; + unsigned suspended:1; + unsigned sysfs_links:1; + unsigned loopback_enabled:1; + + unsigned autoneg:1; + /* The most recently read link state */ + unsigned link:1; enum phy_state state; @@ -429,9 +433,6 @@ struct phy_device { int pause; int asym_pause; - /* The most recently read link state */ - int link; - /* Enabled Interrupts */ u32 interrupts; @@ -444,8 +445,6 @@ struct phy_device { /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; - int autoneg; - int link_timeout; #ifdef CONFIG_LED_TRIGGER_PHY -- cgit v1.2.3 From df5f1361cc080877013f7838b61d31ad31307c2b Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Wed, 28 Feb 2018 14:16:47 -0600 Subject: net/mlx5: Add pbmc and pptb in the port_access_reg_cap_mask Add pbmc and pptb in the port_access_reg_cap_mask. These two bits determine if device supports receive buffer configuration. Signed-off-by: Huy Nguyen Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 3 +++ include/linux/mlx5/mlx5_ifc.h | 12 ++++++++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 2bc27f8c5b87..db0332a6d23c 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1152,6 +1152,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_PCAM_FEATURE(mdev, fld) \ MLX5_GET(pcam_reg, (mdev)->caps.pcam, feature_cap_mask.enhanced_features.fld) +#define MLX5_CAP_PCAM_REG(mdev, reg) \ + MLX5_GET(pcam_reg, (mdev)->caps.pcam, port_access_reg_cap_mask.regs_5000_to_507f.reg) + #define MLX5_CAP_MCAM_REG(mdev, reg) \ MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_access_reg_cap_mask.access_regs.reg) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b4ea8a9914c4..f687989d336b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8003,6 +8003,17 @@ struct mlx5_ifc_pcam_enhanced_features_bits { u8 ppcnt_statistical_group[0x1]; }; +struct mlx5_ifc_pcam_regs_5000_to_507f_bits { + u8 port_access_reg_cap_mask_127_to_96[0x20]; + u8 port_access_reg_cap_mask_95_to_64[0x20]; + u8 port_access_reg_cap_mask_63_to_32[0x20]; + + u8 port_access_reg_cap_mask_31_to_13[0x13]; + u8 pbmc[0x1]; + u8 pptb[0x1]; + u8 port_access_reg_cap_mask_10_to_0[0xb]; +}; + struct mlx5_ifc_pcam_reg_bits { u8 reserved_at_0[0x8]; u8 feature_group[0x8]; @@ -8012,6 +8023,7 @@ struct mlx5_ifc_pcam_reg_bits { u8 reserved_at_20[0x20]; union { + struct mlx5_ifc_pcam_regs_5000_to_507f_bits regs_5000_to_507f; u8 reserved_at_0[0x80]; } port_access_reg_cap_mask; -- cgit v1.2.3 From 50b4a3c23646254c7345f3663ff1e0a6cbcd9abb Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Fri, 2 Mar 2018 15:47:01 -0600 Subject: net/mlx5: PPTB and PBMC register firmware command support Add firmware command interface to read and write PPTB and PBMC registers. PPTB register enables mappings priority to a specific receive buffer. PBMC registers enables changing the receive buffer's configuration such as buffer size, xon/xoff thresholds, buffer's lossy property and buffer's shared property. Signed-off-by: Huy Nguyen Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ include/linux/mlx5/mlx5_ifc.h | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d703774982ca..92d292454351 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -124,6 +124,8 @@ enum { MLX5_REG_PAOS = 0x5006, MLX5_REG_PFCC = 0x5007, MLX5_REG_PPCNT = 0x5008, + MLX5_REG_PPTB = 0x500b, + MLX5_REG_PBMC = 0x500c, MLX5_REG_PMAOS = 0x5012, MLX5_REG_PUDE = 0x5009, MLX5_REG_PMPE = 0x5010, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f687989d336b..edbddeaacc88 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8788,6 +8788,41 @@ struct mlx5_ifc_qpts_reg_bits { u8 trust_state[0x3]; }; +struct mlx5_ifc_pptb_reg_bits { + u8 reserved_at_0[0x2]; + u8 mm[0x2]; + u8 reserved_at_4[0x4]; + u8 local_port[0x8]; + u8 reserved_at_10[0x6]; + u8 cm[0x1]; + u8 um[0x1]; + u8 pm[0x8]; + + u8 prio_x_buff[0x20]; + + u8 pm_msb[0x8]; + u8 reserved_at_48[0x10]; + u8 ctrl_buff[0x4]; + u8 untagged_buff[0x4]; +}; + +struct mlx5_ifc_pbmc_reg_bits { + u8 reserved_at_0[0x8]; + u8 local_port[0x8]; + u8 reserved_at_10[0x10]; + + u8 xoff_timer_value[0x10]; + u8 xoff_refresh[0x10]; + + u8 reserved_at_40[0x9]; + u8 fullness_threshold[0x7]; + u8 port_buffer_size[0x10]; + + struct mlx5_ifc_bufferx_reg_bits buffer[10]; + + u8 reserved_at_2e0[0x40]; +}; + struct mlx5_ifc_qtct_reg_bits { u8 reserved_at_0[0x8]; u8 port_number[0x8]; -- cgit v1.2.3 From f8d959a5b188dc81e57a6bac34a1b2986f61e2fd Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 24 May 2018 11:21:08 -0700 Subject: perf/core: add perf_get_event() to return perf_event given a struct file A new extern function, perf_get_event(), is added to return a perf event given a struct file. This function will be used in later patches. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- include/linux/perf_event.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e71e99eb9a4e..eec302b61cfe 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -868,6 +868,7 @@ extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); +extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); @@ -1289,6 +1290,10 @@ static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } +static inline const struct perf_event *perf_get_event(struct file *file) +{ + return ERR_PTR(-EINVAL); +} static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); -- cgit v1.2.3 From 41bdc4b40ed6fb26c6acc655ed9a243a348709c9 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 24 May 2018 11:21:09 -0700 Subject: bpf: introduce bpf subcommand BPF_TASK_FD_QUERY Currently, suppose a userspace application has loaded a bpf program and attached it to a tracepoint/kprobe/uprobe, and a bpf introspection tool, e.g., bpftool, wants to show which bpf program is attached to which tracepoint/kprobe/uprobe. Such attachment information will be really useful to understand the overall bpf deployment in the system. There is a name field (16 bytes) for each program, which could be used to encode the attachment point. There are some drawbacks for this approaches. First, bpftool user (e.g., an admin) may not really understand the association between the name and the attachment point. Second, if one program is attached to multiple places, encoding a proper name which can imply all these attachments becomes difficult. This patch introduces a new bpf subcommand BPF_TASK_FD_QUERY. Given a pid and fd, if the is associated with a tracepoint/kprobe/uprobe perf event, BPF_TASK_FD_QUERY will return . prog_id . tracepoint name, or . k[ret]probe funcname + offset or kernel addr, or . u[ret]probe filename + offset to the userspace. The user can use "bpftool prog" to find more information about bpf program itself with prog_id. Acked-by: Martin KaFai Lau Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- include/linux/trace_events.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2bde3eff564c..d34144a3c5b5 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -473,6 +473,9 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info); int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog); int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog); struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name); +int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, + u32 *fd_type, const char **buf, + u64 *probe_offset, u64 *probe_addr); #else static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { @@ -504,6 +507,13 @@ static inline struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name { return NULL; } +static inline int bpf_get_perf_event_info(const struct perf_event *event, + u32 *prog_id, u32 *fd_type, + const char **buf, u64 *probe_offset, + u64 *probe_addr) +{ + return -EOPNOTSUPP; +} #endif enum { @@ -560,10 +570,17 @@ extern void perf_trace_del(struct perf_event *event, int flags); #ifdef CONFIG_KPROBE_EVENTS extern int perf_kprobe_init(struct perf_event *event, bool is_retprobe); extern void perf_kprobe_destroy(struct perf_event *event); +extern int bpf_get_kprobe_info(const struct perf_event *event, + u32 *fd_type, const char **symbol, + u64 *probe_offset, u64 *probe_addr, + bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS extern int perf_uprobe_init(struct perf_event *event, bool is_retprobe); extern void perf_uprobe_destroy(struct perf_event *event); +extern int bpf_get_uprobe_info(const struct perf_event *event, + u32 *fd_type, const char **filename, + u64 *probe_offset, bool perf_type_tracepoint); #endif extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); -- cgit v1.2.3 From 67f29e07e131ffa13ea158c259a513f474c7df27 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 24 May 2018 16:45:46 +0200 Subject: bpf: devmap introduce dev_map_enqueue Functionality is the same, but the ndo_xdp_xmit call is now simply invoked from inside the devmap.c code. V2: Fix compile issue reported by kbuild test robot V5: Cleanups requested by Daniel - Newlines before func definition - Use BUILD_BUG_ON checks - Remove unnecessary use return value store in dev_map_enqueue Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1795eeee846c..23a809da452d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -487,14 +487,16 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); /* Map specifics */ -struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); +struct xdp_buff; + +struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); void __cpu_map_flush(struct bpf_map *map); -struct xdp_buff; int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -573,6 +575,15 @@ static inline void __dev_map_flush(struct bpf_map *map) { } +struct xdp_buff; +struct bpf_dtab_netdev; + +static inline +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp) +{ + return 0; +} + static inline struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) { @@ -587,7 +598,6 @@ static inline void __cpu_map_flush(struct bpf_map *map) { } -struct xdp_buff; static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx) -- cgit v1.2.3 From 38edddb81172e8b8decb057c0cd23271583a5fa0 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 24 May 2018 16:45:57 +0200 Subject: xdp: add tracepoint for devmap like cpumap have Notice how this allow us get XDP statistic without affecting the XDP performance, as tracepoint is no-longer activated on a per packet basis. V5: Spotted by John Fastabend. Fix 'sent' also counted 'drops' in this patch, a later patch corrected this, but it was a mistake in this intermediate step. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 23a809da452d..bbe297436e5d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -492,7 +492,8 @@ struct xdp_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp); +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, + struct net_device *dev_rx); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); @@ -579,7 +580,8 @@ struct xdp_buff; struct bpf_dtab_netdev; static inline -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp) +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, + struct net_device *dev_rx) { return 0; } -- cgit v1.2.3 From 735fc4054b3a25034445c6713d259da0f96f8131 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 24 May 2018 16:46:12 +0200 Subject: xdp: change ndo_xdp_xmit API to support bulking This patch change the API for ndo_xdp_xmit to support bulking xdp_frames. When kernel is compiled with CONFIG_RETPOLINE, XDP sees a huge slowdown. Most of the slowdown is caused by DMA API indirect function calls, but also the net_device->ndo_xdp_xmit() call. Benchmarked patch with CONFIG_RETPOLINE, using xdp_redirect_map with single flow/core test (CPU E5-1650 v4 @ 3.60GHz), showed performance improved: for driver ixgbe: 6,042,682 pps -> 6,853,768 pps = +811,086 pps for driver i40e : 6,187,169 pps -> 6,724,519 pps = +537,350 pps With frames avail as a bulk inside the driver ndo_xdp_xmit call, further optimizations are possible, like bulk DMA-mapping for TX. Testing without CONFIG_RETPOLINE show the same performance for physical NIC drivers. The virtual NIC driver tun sees a huge performance boost, as it can avoid doing per frame producer locking, but instead amortize the locking cost over the bulk. V2: Fix compile errors reported by kbuild test robot V4: Isolated ndo, driver changes and callers. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov --- include/linux/netdevice.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 03ed492c4e14..debdb6286170 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1185,9 +1185,13 @@ struct dev_ifalias { * This function is used to set or query state related to XDP on the * netdevice and manage BPF offload. See definition of * enum bpf_netdev_command for details. - * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_frame *xdp); - * This function is used to submit a XDP packet for transmit on a - * netdevice. + * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp); + * This function is used to submit @n XDP packets for transmit on a + * netdevice. Returns number of frames successfully transmitted, frames + * that got dropped are freed/returned via xdp_return_frame(). + * Returns negative number, means general error invoking ndo, meaning + * no frames were xmit'ed and core-caller will free all frames. + * TODO: Consider add flag to allow sending flush operation. * void (*ndo_xdp_flush)(struct net_device *dev); * This function is used to inform the driver to flush a particular * xdp tx queue. Must be called on same CPU as xdp_xmit. @@ -1375,8 +1379,8 @@ struct net_device_ops { int needed_headroom); int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); - int (*ndo_xdp_xmit)(struct net_device *dev, - struct xdp_frame *xdp); + int (*ndo_xdp_xmit)(struct net_device *dev, int n, + struct xdp_frame **xdp); void (*ndo_xdp_flush)(struct net_device *dev); }; -- cgit v1.2.3 From f44aa9ef7950a56daa3a5b41f069761f945f1a1f Mon Sep 17 00:00:00 2001 From: John Hurley Date: Wed, 23 May 2018 19:22:52 -0700 Subject: net: include hash policy in LAG changeupper info LAG upper event notifiers contain the tx type used by the LAG device. Extend this to also include the hash policy used for tx types that utilize hashing. Signed-off-by: John Hurley Signed-off-by: David S. Miller --- include/linux/netdevice.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index debdb6286170..8452f72087ef 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2332,8 +2332,19 @@ enum netdev_lag_tx_type { NETDEV_LAG_TX_TYPE_HASH, }; +enum netdev_lag_hash { + NETDEV_LAG_HASH_NONE, + NETDEV_LAG_HASH_L2, + NETDEV_LAG_HASH_L34, + NETDEV_LAG_HASH_L23, + NETDEV_LAG_HASH_E23, + NETDEV_LAG_HASH_E34, + NETDEV_LAG_HASH_UNKNOWN, +}; + struct netdev_lag_upper_info { enum netdev_lag_tx_type tx_type; + enum netdev_lag_hash hash_type; }; struct netdev_lag_lower_state_info { -- cgit v1.2.3 From a1150c202207cc8501bebc45b63c264f91959260 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 3 May 2018 12:47:16 -0700 Subject: perf/core: Fix group scheduling with mixed hw and sw events When hw and sw events are mixed in the same group, they are all attached to the hw perf_event_context. This sometimes requires moving group of perf_event to a different context. We found a bug in how the kernel handles this, for example if we do: perf stat -e '{faults,ref-cycles,faults}' -I 1000 1.005591180 1,297 faults 1.005591180 457,476,576 ref-cycles 1.005591180 faults First, sw event "faults" is attached to the sw context, and becomes the group leader. Then, hw event "ref-cycles" is attached, so both events are moved to the hw context. Last, another sw "faults" tries to attach, but it fails because of mismatch between the new target ctx (from sw pmu) and the group_leader's ctx (hw context, same as ref-cycles). The broken condition is: group_leader is sw event; group_leader is on hw context; add a sw event to the group. Fix this scenario by checking group_leader's context (instead of just event type). If group_leader is on hw context, use the ->pmu of this context to look up context for the new event. Signed-off-by: Song Liu Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: b04243ef7006 ("perf: Complete software pmu grouping") Link: http://lkml.kernel.org/r/20180503194716.162815-1-songliubraving@fb.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e71e99eb9a4e..def866f7269b 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1016,6 +1016,14 @@ static inline int is_software_event(struct perf_event *event) return event->event_caps & PERF_EV_CAP_SOFTWARE; } +/* + * Return 1 for event in sw context, 0 for event in hw context + */ +static inline int in_software_context(struct perf_event *event) +{ + return event->ctx->pmu->task_ctx_nr == perf_sw_context; +} + extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); -- cgit v1.2.3 From 9511bce9fe8e5e6c0f923c09243a713eba560141 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Tue, 17 Apr 2018 23:29:07 -0700 Subject: perf/core: Fix bad use of igrab() As Miklos reported and suggested: "This pattern repeats two times in trace_uprobe.c and in kernel/events/core.c as well: ret = kern_path(filename, LOOKUP_FOLLOW, &path); if (ret) goto fail_address_parse; inode = igrab(d_inode(path.dentry)); path_put(&path); And it's wrong. You can only hold a reference to the inode if you have an active ref to the superblock as well (which is normally through path.mnt) or holding s_umount. This way unmounting the containing filesystem while the tracepoint is active will give you the "VFS: Busy inodes after unmount..." message and a crash when the inode is finally put. Solution: store path instead of inode." This patch fixes the issue in kernel/event/core.c. Reviewed-and-tested-by: Alexander Shishkin Reported-by: Miklos Szeredi Signed-off-by: Song Liu Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: 375637bc5249 ("perf/core: Introduce address range filtering") Link: http://lkml.kernel.org/r/20180418062907.3210386-2-songliubraving@fb.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index def866f7269b..bea0b0cd4bf7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -467,7 +467,7 @@ enum perf_addr_filter_action_t { */ struct perf_addr_filter { struct list_head entry; - struct inode *inode; + struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action; -- cgit v1.2.3 From 884571f0de7b02bb784be3a5c870eabce62cdaeb Mon Sep 17 00:00:00 2001 From: Huaisheng Ye Date: Fri, 25 May 2018 13:00:00 +0800 Subject: dma-mapping: remove unused gfp_t parameter to arch_dma_alloc_attrs Signed-off-by: Huaisheng Ye Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 4be070df5fc5..15e4b4e9cc20 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -502,7 +502,7 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0) #ifndef arch_dma_alloc_attrs -#define arch_dma_alloc_attrs(dev, flag) (true) +#define arch_dma_alloc_attrs(dev) (true) #endif static inline void *dma_alloc_attrs(struct device *dev, size_t size, @@ -521,7 +521,7 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size, /* let the implementation decide on the zone to allocate from: */ flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM); - if (!arch_dma_alloc_attrs(&dev, &flag)) + if (!arch_dma_alloc_attrs(&dev)) return NULL; if (!ops->alloc) return NULL; -- cgit v1.2.3 From 93ee37c2a6a97e5d358af2d8f0510817b6e75679 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Wed, 11 Apr 2018 17:54:20 +0100 Subject: thread_info: Add update_thread_flag() helpers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are a number of bits of code sprinkled around the kernel to set a thread flag if a certain condition is true, and clear it otherwise. To help make those call sites terser and less cumbersome, this patch adds a new family of thread flag manipulators update*_thread_flag([...,] flag, cond) which do the equivalent of: if (cond) set*_thread_flag([...,] flag); else clear*_thread_flag([...,] flag); Signed-off-by: Dave Martin Reviewed-by: Alex Bennée Acked-by: Steven Rostedt (VMware) Acked-by: Marc Zyngier Acked-by: Catalin Marinas Acked-by: Peter Zijlstra (Intel) Cc: Ingo Molnar Cc: Oleg Nesterov Signed-off-by: Marc Zyngier --- include/linux/sched.h | 6 ++++++ include/linux/thread_info.h | 11 +++++++++++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b3d697f3b573..c2c305199721 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1578,6 +1578,12 @@ static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag) clear_ti_thread_flag(task_thread_info(tsk), flag); } +static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag, + bool value) +{ + update_ti_thread_flag(task_thread_info(tsk), flag, value); +} + static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_set_ti_thread_flag(task_thread_info(tsk), flag); diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index cf2862bd134a..8d8821b3689a 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -60,6 +60,15 @@ static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) clear_bit(flag, (unsigned long *)&ti->flags); } +static inline void update_ti_thread_flag(struct thread_info *ti, int flag, + bool value) +{ + if (value) + set_ti_thread_flag(ti, flag); + else + clear_ti_thread_flag(ti, flag); +} + static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); @@ -79,6 +88,8 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) +#define update_thread_flag(flag, value) \ + update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ -- cgit v1.2.3 From bd2a6394fd2d3ea528d4b9c67f829e35f1f5d5dd Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Fri, 23 Feb 2018 17:23:57 +0100 Subject: KVM: arm/arm64: Introduce kvm_arch_vcpu_run_pid_change MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KVM/ARM differs from other architectures in having to maintain an additional virtual address space from that of the host and the guest, because we split the execution of KVM across both EL1 and EL2. This results in a need to explicitly map data structures into EL2 (hyp) which are accessed from the hyp code. As we are about to be more clever with our FPSIMD handling on arm64, which stores data in the task struct and uses thread_info flags, we will have to map parts of the currently executing task struct into the EL2 virtual address space. However, we don't want to do this on every KVM_RUN, because it is a fairly expensive operation to walk the page tables, and the common execution mode is to map a single thread to a VCPU. By introducing a hook that architectures can select with HAVE_KVM_VCPU_RUN_PID_CHANGE, we do not introduce overhead for other architectures, but have a simple way to only map the data we need when required for arm64. This patch introduces the framework only, and wires it up in the arm/arm64 KVM common code. No functional change. Signed-off-by: Christoffer Dall Signed-off-by: Dave Martin Reviewed-by: Marc Zyngier Reviewed-by: Alex Bennée Signed-off-by: Marc Zyngier --- include/linux/kvm_host.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6930c63126c7..4268ace60bf1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1276,4 +1276,13 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end); +#ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE +int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); +#else +static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) +{ + return 0; +} +#endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ + #endif -- cgit v1.2.3 From 7085e2a94f7df5f419e3cfb2fe809ce6564e9629 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Wed, 16 May 2018 18:49:55 -0500 Subject: fpga: manager: change api, don't use drvdata Change fpga_mgr_register to not set or use drvdata. This supports the case where a PCIe device has more than one manager. Add fpga_mgr_create/free functions. Change fpga_mgr_register and fpga_mgr_unregister functions to take the mgr struct as their only parameter. struct fpga_manager *fpga_mgr_create(struct device *dev, const char *name, const struct fpga_manager_ops *mops, void *priv); void fpga_mgr_free(struct fpga_manager *mgr); int fpga_mgr_register(struct fpga_manager *mgr); void fpga_mgr_unregister(struct fpga_manager *mgr); Update the drivers that call fpga_mgr_register with the new API. Signed-off-by: Alan Tull [Moritz: Fixup whitespace issue] Reported-by: Jiuyue Ma Signed-off-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 3c6de23aabdf..1266c1108e70 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -170,9 +170,11 @@ struct fpga_manager *fpga_mgr_get(struct device *dev); void fpga_mgr_put(struct fpga_manager *mgr); -int fpga_mgr_register(struct device *dev, const char *name, - const struct fpga_manager_ops *mops, void *priv); - -void fpga_mgr_unregister(struct device *dev); +struct fpga_manager *fpga_mgr_create(struct device *dev, const char *name, + const struct fpga_manager_ops *mops, + void *priv); +void fpga_mgr_free(struct fpga_manager *mgr); +int fpga_mgr_register(struct fpga_manager *mgr); +void fpga_mgr_unregister(struct fpga_manager *mgr); #endif /*_LINUX_FPGA_MGR_H */ -- cgit v1.2.3 From 371cd1b1fdabb33603340559049e46dfeae45b1e Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Wed, 16 May 2018 18:49:56 -0500 Subject: fpga: bridge: change api, don't use drvdata Change fpga_bridge_register to not set drvdata. This is to support the case where a PCIe device can have more than one bridge. Add API functions to create/free the fpga bridge struct. Change fpga_bridge_register/unregister to take FPGA bridge struct as the only parameter. struct fpga_bridge *fpga_bridge_create(struct device *dev, const char *name, const struct fpga_bridge_ops *br_ops, void *priv); void fpga_bridge_free(struct fpga_bridge *br); int fpga_bridge_register(struct fpga_bridge *br); void fpga_bridge_unregister(struct fpga_bridge *br); Update the drivers that call fpga_bridge_register with the new API. Signed-off-by: Alan Tull Reported-by: Jiuyue Ma Signed-off-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-bridge.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h index 3694821a6d2d..ce550fcf6360 100644 --- a/include/linux/fpga/fpga-bridge.h +++ b/include/linux/fpga/fpga-bridge.h @@ -62,8 +62,11 @@ int of_fpga_bridge_get_to_list(struct device_node *np, struct fpga_image_info *info, struct list_head *bridge_list); -int fpga_bridge_register(struct device *dev, const char *name, - const struct fpga_bridge_ops *br_ops, void *priv); -void fpga_bridge_unregister(struct device *dev); +struct fpga_bridge *fpga_bridge_create(struct device *dev, const char *name, + const struct fpga_bridge_ops *br_ops, + void *priv); +void fpga_bridge_free(struct fpga_bridge *br); +int fpga_bridge_register(struct fpga_bridge *br); +void fpga_bridge_unregister(struct fpga_bridge *br); #endif /* _LINUX_FPGA_BRIDGE_H */ -- cgit v1.2.3 From 9f368977b4589e2fe0b9d3a4cbaf11ff6a58ecf5 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Wed, 16 May 2018 18:49:57 -0500 Subject: fpga: region: change api, add fpga_region_create/free Add fpga_region_create/free API functions. Change fpga_region_register to take FPGA region struct as the only parameter. Change fpga_region_unregister to return void. struct fpga_region *fpga_region_create(struct device *dev, struct fpga_manager *mgr, int (*get_bridges)(struct fpga_region *)); void fpga_region_free(struct fpga_region *region); int fpga_region_register(struct fpga_region *region); void fpga_region_unregister(struct fpga_region *region); Remove groups storage from struct fpga_region, it's not needed. Callers can just "region->dev.groups = groups;" after calling fpga_region_create. Update the drivers that call fpga_region_register with the new API. Signed-off-by: Alan Tull Signed-off-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-region.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index b6520318ab9c..f2e215bd1330 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -14,7 +14,6 @@ * @info: FPGA image info * @priv: private data * @get_bridges: optional function to get bridges to a list - * @groups: optional attribute groups. */ struct fpga_region { struct device dev; @@ -24,7 +23,6 @@ struct fpga_region { struct fpga_image_info *info; void *priv; int (*get_bridges)(struct fpga_region *region); - const struct attribute_group **groups; }; #define to_fpga_region(d) container_of(d, struct fpga_region, dev) @@ -34,7 +32,12 @@ struct fpga_region *fpga_region_class_find( int (*match)(struct device *, const void *)); int fpga_region_program_fpga(struct fpga_region *region); -int fpga_region_register(struct device *dev, struct fpga_region *region); -int fpga_region_unregister(struct fpga_region *region); + +struct fpga_region +*fpga_region_create(struct device *dev, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *)); +void fpga_region_free(struct fpga_region *region); +int fpga_region_register(struct fpga_region *region); +void fpga_region_unregister(struct fpga_region *region); #endif /* _FPGA_REGION_H */ -- cgit v1.2.3 From 473f01f7e4b9fc53d44c446ad22b39070c65393f Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Wed, 16 May 2018 18:49:58 -0500 Subject: fpga: use SPDX Replace GPLv2 boilerplate with SPDX in FPGA code that came from me or from Altera. Signed-off-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/altera-pr-ip-core.h | 13 +------------ include/linux/fpga/fpga-mgr.h | 13 +------------ include/linux/fpga/fpga-region.h | 2 ++ 3 files changed, 4 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fpga/altera-pr-ip-core.h b/include/linux/fpga/altera-pr-ip-core.h index 3810a9033f49..7d4664730d60 100644 --- a/include/linux/fpga/altera-pr-ip-core.h +++ b/include/linux/fpga/altera-pr-ip-core.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Driver for Altera Partial Reconfiguration IP Core * @@ -5,18 +6,6 @@ * * Based on socfpga-a10.c Copyright (C) 2015-2016 Altera Corporation * by Alan Tull - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see . */ #ifndef _ALT_PR_IP_CORE_H diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 1266c1108e70..eec7c2478b0d 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -1,20 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * FPGA Framework * * Copyright (C) 2013-2016 Altera Corporation * Copyright (C) 2017 Intel Corporation - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see . */ #ifndef _LINUX_FPGA_MGR_H #define _LINUX_FPGA_MGR_H diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index f2e215bd1330..d7071cddd727 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + #ifndef _FPGA_REGION_H #define _FPGA_REGION_H -- cgit v1.2.3 From ed24d568bd9190cee046ae64df5890494dea2ca4 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Fri, 25 May 2018 14:50:36 +0100 Subject: regmap: add missing prototype for devm_init_slimbus For some reason the devm variant of slimbus init is not added into the header eventhough this __devm_regmap_init_slimbus() is an exported function. This patch adds this. This also fixes below warning in regmap-slimbus.c regmap-slimbus.c:65:15: warning: symbol '__devm_regmap_init_slimbus' was not declared. Should it be static? regmap-slimbus.c:65:16: warning: no previous prototype for '__devm_regmap_init_slimbus' [-Wmissing-prototypes] Fixes: 7d6f7fb053ad ("regmap: add SLIMbus support") Signed-off-by: Srinivas Kandagatla Signed-off-by: Mark Brown --- include/linux/regmap.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index b6865f070464..4f38068ffb71 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -588,7 +588,10 @@ struct regmap *__devm_regmap_init_sdw(struct sdw_slave *sdw, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); - +struct regmap *__devm_regmap_init_slimbus(struct slim_device *slimbus, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); /* * Wrapper for regmap_init macros to include a unique lockdep key and name * for each call. No-op if CONFIG_LOCKDEP is not set. @@ -907,6 +910,19 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); __regmap_lockdep_wrapper(__devm_regmap_init_sdw, #config, \ sdw, config) +/** + * devm_regmap_init_slimbus() - Initialise managed register map + * + * @slimbus: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_slimbus(slimbus, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_slimbus, #config, \ + slimbus, config) int regmap_mmio_attach_clk(struct regmap *map, struct clk *clk); void regmap_mmio_detach_clk(struct regmap *map); void regmap_exit(struct regmap *map); -- cgit v1.2.3 From 7d850abd5f4edb1b1ca4b4141a4453305736f564 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 24 May 2018 11:56:48 +0300 Subject: net: bridge: add support for port isolation This patch adds support for a new port flag - BR_ISOLATED. If it is set then isolated ports cannot communicate between each other, but they can still communicate with non-isolated ports. The same can be achieved via ACLs but they can't scale with large number of ports and also the complexity of the rules grows. This feature can be used to achieve isolated vlan functionality (similar to pvlan) as well, though currently it will be port-wide (for all vlans on the port). The new test in should_deliver uses data that is already cache hot and the new boolean is used to avoid an additional source port test in should_deliver. Signed-off-by: Nikolay Aleksandrov Reviewed-by: Toshiaki Makita Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 585d27182425..7843b98e1c6e 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -50,6 +50,7 @@ struct br_ip_list { #define BR_VLAN_TUNNEL BIT(13) #define BR_BCAST_FLOOD BIT(14) #define BR_NEIGH_SUPPRESS BIT(15) +#define BR_ISOLATED BIT(16) #define BR_DEFAULT_AGEING_TIME (300 * HZ) -- cgit v1.2.3 From 3893fc62b1769db3ef160f7f1e36d3db754497ee Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Thu, 24 May 2018 09:54:51 -0700 Subject: qed*: Support other classification modes. Currently, driver supports flow classification to PF receive queues based on TCP/UDP 4 tuples [src_ip, dst_ip, src_port, dst_port] only. This patch enables to configure different flow profiles [For example - only UDP dest port or src_ip based] on the adapter so that classification can be done according to just those fields as well. Although, at a time just one type of flow configuration is supported due to limited number of flow profiles available on the device. For example - ethtool -N enp7s0f0 flow-type udp4 dst-port 45762 action 2 ethtool -N enp7s0f0 flow-type tcp4 src-ip 192.16.4.10 action 1 ethtool -N enp7s0f0 flow-type udp6 dst-port 45762 action 3 Signed-off-by: Manish Chopra Signed-off-by: Shahed Shaikh Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 7f9756fe9180..557e86e1c7d9 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -66,6 +66,7 @@ enum qed_filter_config_mode { QED_FILTER_CONFIG_MODE_5_TUPLE, QED_FILTER_CONFIG_MODE_L4_PORT, QED_FILTER_CONFIG_MODE_IP_DEST, + QED_FILTER_CONFIG_MODE_IP_SRC, }; struct qed_ntuple_filter_params { -- cgit v1.2.3 From 608e00d0a2eb53079c55dc9c14d8711bbb3a4390 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Thu, 24 May 2018 09:54:53 -0700 Subject: qed*: Support drop action classification With this patch, User can configure for the supported flows to be dropped. Added a stat "gft_filter_drop" as well to be populated in ethtool for the dropped flows. For example - ethtool -N p5p1 flow-type udp4 dst-port 8000 action -1 ethtool -N p5p1 flow-type tcp4 scr-ip 192.168.8.1 action -1 Signed-off-by: Manish Chopra Signed-off-by: Shahed Shaikh Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 3 +++ include/linux/qed/qed_if.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 557e86e1c7d9..2978fa4add42 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -89,6 +89,9 @@ struct qed_ntuple_filter_params { /* true iff this filter is to be added. Else to be removed */ bool b_is_add; + + /* If flow needs to be dropped */ + bool b_is_drop; }; struct qed_dev_eth_info { diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 44af652e7407..ac991a3b8f03 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1129,6 +1129,7 @@ struct qed_eth_stats_common { u64 rx_bcast_pkts; u64 mftag_filter_discards; u64 mac_filter_discards; + u64 gft_filter_drop; u64 tx_ucast_bytes; u64 tx_mcast_bytes; u64 tx_bcast_bytes; -- cgit v1.2.3 From 6d361c1db7b69fddf5748cf212169ab57bb13a6e Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 25 Apr 2018 10:18:20 -0500 Subject: soc: qcom: smem: introduce qcom_smem_virt_to_phys() Create function qcom_smem_virt_to_phys(), which returns the physical address corresponding to a given SMEM item's virtual address. This feature is required for a driver that will soon be out for review. Signed-off-by: Alex Elder Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/soc/qcom/smem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/smem.h b/include/linux/soc/qcom/smem.h index c1657ed27b30..86e1b358688a 100644 --- a/include/linux/soc/qcom/smem.h +++ b/include/linux/soc/qcom/smem.h @@ -9,4 +9,6 @@ void *qcom_smem_get(unsigned host, unsigned item, size_t *size); int qcom_smem_get_free_space(unsigned host); +phys_addr_t qcom_smem_virt_to_phys(void *p); + #endif -- cgit v1.2.3 From b45630021b52c203c2547a95a5c811b57aed4ead Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Tue, 24 Apr 2018 11:21:46 +0900 Subject: net/mlx5: Add cap bits for flow table destination in FDB table If set, the FDB table supports the forward action with a destination list that includes a flow table. Signed-off-by: Chris Mi Reviewed-by: Paul Blakey Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index edbddeaacc88..05b480fae27d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -524,7 +524,9 @@ struct mlx5_ifc_flow_table_nic_cap_bits { }; struct mlx5_ifc_flow_table_eswitch_cap_bits { - u8 reserved_at_0[0x200]; + u8 reserved_at_0[0x1c]; + u8 fdb_multi_path_to_table[0x1]; + u8 reserved_at_1d[0x1e3]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb; -- cgit v1.2.3 From 3a2f70331226c140e5aa27ee6bbe2a5c618acb4c Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 4 Apr 2018 12:54:23 +0300 Subject: net/mlx5: Use order-0 allocations for all WQ types Complete the transition of all WQ types to use fragmented order-0 coherent memory instead of high-order allocations. CQ-WQ already uses order-0. Here we do the same for cyclic and linked-list WQs. This allows the driver to load cleanly on systems with a highly fragmented coherent memory. Performance tests: ConnectX-5 100Gbps, CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz Packet rate of 64B packets, single transmit ring, size 8K. No degradation is sensed. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 92d292454351..80cbb7fdce4a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -983,16 +983,24 @@ static inline u32 mlx5_base_mkey(const u32 key) return key & 0xffffff00u; } -static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, - void *cqc) +static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, + struct mlx5_frag_buf_ctrl *fbc) { - fbc->log_stride = 6 + MLX5_GET(cqc, cqc, cqe_sz); - fbc->log_sz = MLX5_GET(cqc, cqc, log_cq_size); + fbc->log_stride = log_stride; + fbc->log_sz = log_sz; fbc->sz_m1 = (1 << fbc->log_sz) - 1; fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride; fbc->frag_sz_m1 = (1 << fbc->log_frag_strides) - 1; } +static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, + void *cqc) +{ + mlx5_fill_fbc(6 + MLX5_GET(cqc, cqc, cqe_sz), + MLX5_GET(cqc, cqc, log_cq_size), + fbc); +} + static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, u32 ix) { -- cgit v1.2.3 From e5b1db0186bfb3bede41e412b27c9bcf2b336622 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 30 Mar 2018 14:41:49 -0500 Subject: PCI: Remove unused pcie_get_minimum_link() In some cases pcie_get_minimum_link() returned misleading information because it found the slowest link and the narrowest link without considering the total bandwidth of the link. For example, consider a path with these two links: - 16.0 GT/s x1 link (16.0 * 10^9 * 128 / 130) * 1 / 8 = 1969 MB/s - 2.5 GT/s x16 link ( 2.5 * 10^9 * 8 / 10) * 16 / 8 = 4000 MB/s The available bandwidth of the path is limited by the 16 GT/s link to about 1969 MB/s, but pcie_get_minimum_link() returned 2.5 GT/s x1, which corresponds to only 250 MB/s. Callers should use pcie_print_link_status() instead, or pcie_bandwidth_available() if they need more detailed information. Remove pcie_get_minimum_link() since there are no callers left. Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 5eb97e198325..f7aa6d9f8999 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1080,8 +1080,6 @@ int pcie_get_readrq(struct pci_dev *dev); int pcie_set_readrq(struct pci_dev *dev, int rq); int pcie_get_mps(struct pci_dev *dev); int pcie_set_mps(struct pci_dev *dev, int mps); -int pcie_get_minimum_link(struct pci_dev *dev, enum pci_bus_speed *speed, - enum pcie_link_width *width); u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, enum pci_bus_speed *speed, enum pcie_link_width *width); -- cgit v1.2.3 From 8efd6894ff089adeeac7cb9f32125b85d963d1bc Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sun, 22 Apr 2018 20:18:46 -0700 Subject: fs: add timespec64_truncate() As vfs moves to using struct timespec64 to represent times, update the argument to timespec_truncate() to use struct timespec64. Also change the name of the function. The rest of the implementation logic is the same. Move this to fs/inode.c instead of kernel/time/time.c as all the users of this api are filesystems. Signed-off-by: Deepa Dinamani Cc: --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 760d8da1b6c7..7f6997e0dabf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1476,6 +1476,7 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); } +extern struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran); extern struct timespec current_time(struct inode *inode); /* -- cgit v1.2.3 From 8f546ae1fc5ce8396827d4868c7eee1f1cc6947a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Jan 2018 12:23:05 +0100 Subject: fs: unexport poll_schedule_timeout No users outside of select.c. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Darrick J. Wong --- include/linux/poll.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/poll.h b/include/linux/poll.h index f45ebd017eaa..a3576da63377 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -96,8 +96,6 @@ struct poll_wqueues { extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); -extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state, - ktime_t *expires, unsigned long slack); extern u64 select_estimate_accuracy(struct timespec64 *tv); #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1) -- cgit v1.2.3 From 9965ed174e7d38896e5d2582159d8ef31ecd4cb5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 5 Mar 2018 07:26:05 -0800 Subject: fs: add new vfs_poll and file_can_poll helpers These abstract out calls to the poll method in preparation for changes in how we poll. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Darrick J. Wong --- include/linux/poll.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/poll.h b/include/linux/poll.h index a3576da63377..7e0fdcf905d2 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -74,6 +74,18 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) pt->_key = ~(__poll_t)0; /* all events enabled */ } +static inline bool file_can_poll(struct file *file) +{ + return file->f_op->poll; +} + +static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt) +{ + if (unlikely(!file->f_op->poll)) + return DEFAULT_POLLMASK; + return file->f_op->poll(file, pt); +} + struct poll_table_entry { struct file *filp; __poll_t key; -- cgit v1.2.3 From 3deb642f0de4c14f37437dd247f9c77839f043f8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Jan 2018 15:29:24 +0100 Subject: fs: introduce new ->get_poll_head and ->poll_mask methods ->get_poll_head returns the waitqueue that the poll operation is going to sleep on. Note that this means we can only use a single waitqueue for the poll, unlike some current drivers that use two waitqueues for different events. But now that we have keyed wakeups and heavily use those for poll there aren't that many good reason left to keep the multiple waitqueues, and if there are any ->poll is still around, the driver just won't support aio poll. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Darrick J. Wong --- include/linux/fs.h | 2 ++ include/linux/poll.h | 12 ++++++------ 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 760d8da1b6c7..4b6045ebb2f2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1711,6 +1711,8 @@ struct file_operations { int (*iterate) (struct file *, struct dir_context *); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); + struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t); + __poll_t (*poll_mask) (struct file *, __poll_t); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); diff --git a/include/linux/poll.h b/include/linux/poll.h index 7e0fdcf905d2..fdf86b4cbc71 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -74,18 +74,18 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) pt->_key = ~(__poll_t)0; /* all events enabled */ } -static inline bool file_can_poll(struct file *file) +static inline bool file_has_poll_mask(struct file *file) { - return file->f_op->poll; + return file->f_op->get_poll_head && file->f_op->poll_mask; } -static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt) +static inline bool file_can_poll(struct file *file) { - if (unlikely(!file->f_op->poll)) - return DEFAULT_POLLMASK; - return file->f_op->poll(file, pt); + return file->f_op->poll || file_has_poll_mask(file); } +__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt); + struct poll_table_entry { struct file *filp; __poll_t key; -- cgit v1.2.3 From f3a2752a43de18eb2eafa869d06f6e423ff0ce61 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 30 Mar 2018 11:19:25 +0200 Subject: aio: simplify KIOCB_KEY handling No need to pass the key field to lookup_iocb to compare it with KIOCB_KEY, as we can do that right after retrieving it from userspace. Also move the KIOCB_KEY definition to aio.c as it is an internal value not used by any other place in the kernel. Signed-off-by: Christoph Hellwig --- include/linux/aio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 9d8aabecfe2d..b83e68dd006f 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -8,8 +8,6 @@ struct kioctx; struct kiocb; struct mm_struct; -#define KIOCB_KEY 0 - typedef int (kiocb_cancel_fn)(struct kiocb *); /* prototypes */ -- cgit v1.2.3 From 152524231023c76b3b7b3e71017c7f951812868d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 9 Apr 2018 15:25:28 +0200 Subject: net: add support for ->poll_mask in proto_ops The socket file operations still implement ->poll until all protocols are switched over. Signed-off-by: Christoph Hellwig --- include/linux/net.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 2248a052061d..3fd9d8c16581 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -147,6 +147,7 @@ struct proto_ops { int (*getname) (struct socket *sock, struct sockaddr *addr, int peer); + __poll_t (*poll_mask) (struct socket *sock, __poll_t events); __poll_t (*poll) (struct file *file, struct socket *sock, struct poll_table_struct *wait); int (*ioctl) (struct socket *sock, unsigned int cmd, -- cgit v1.2.3 From db5051ead64a987e863f71a770351a75be542b15 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 9 Apr 2018 15:27:37 +0200 Subject: net: convert datagram_poll users tp ->poll_mask Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman --- include/linux/skbuff.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9065477ed255..89198379b39d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3250,8 +3250,7 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, int *peeked, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); -__poll_t datagram_poll(struct file *file, struct socket *sock, - struct poll_table_struct *wait); +__poll_t datagram_poll_mask(struct socket *sock, __poll_t events); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, struct iov_iter *to, int size); static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, -- cgit v1.2.3 From 7053df4edb3ae3ae15c316fe49122c0b3936e9dd Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 16 May 2018 17:21:28 +0200 Subject: KVM: introduce kvm_make_vcpus_request_mask() API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Hyper-V style PV TLB flush hypercalls inmplementation will use this API. To avoid memory allocation in CONFIG_CPUMASK_OFFSTACK case add cpumask_var_t argument. Signed-off-by: Vitaly Kuznetsov Signed-off-by: Radim Krčmář --- include/linux/kvm_host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6d6e79c59e68..14e710d639c7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -730,6 +730,9 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); + +bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, + unsigned long *vcpu_bitmap, cpumask_var_t tmp); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); long kvm_arch_dev_ioctl(struct file *filp, -- cgit v1.2.3 From c1a957d17086d20d52d7f9c8dffaeac2ee09d6f9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 May 2018 17:54:41 +0200 Subject: PM / suspend: Prevent might sleep splats timekeeping suspend/resume calls read_persistent_clock() which takes rtc_lock. That results in might sleep warnings because at that point we run with interrupts disabled. We cannot convert rtc_lock to a raw spinlock as that would trigger other might sleep warnings. As a workaround we disable the might sleep warnings by setting system_state to SYSTEM_SUSPEND before calling sysdev_suspend() and restoring it to SYSTEM_RUNNING afer sysdev_resume(). There is no lock contention because hibernate / suspend to RAM is single-CPU at this point. In s2idle's case the system_state is set to SYSTEM_SUSPEND before timekeeping_suspend() which is invoked by the last CPU. In the resume case it set back to SYSTEM_RUNNING after timekeeping_resume() which is invoked by the first CPU in the resume case. The other CPUs will block on tick_freeze_lock. Signed-off-by: Thomas Gleixner [bigeasy: cover s2idle in tick_freeze() / tick_unfreeze()] Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Rafael J. Wysocki --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 6a1eb0b0aad9..7aed92624531 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -542,6 +542,7 @@ extern enum system_states { SYSTEM_HALT, SYSTEM_POWER_OFF, SYSTEM_RESTART, + SYSTEM_SUSPEND, } system_state; /* This cannot be an enum because some may be used in assembly source. */ -- cgit v1.2.3 From 1e8378619841ef1d621b130bbd3fc3b7e6739b50 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 18 May 2018 10:48:49 +0200 Subject: PM / runtime: Fixup reference counting of device link suppliers at probe In the driver core, before it invokes really_probe() it runtime resumes the suppliers for the device via calling pm_runtime_get_suppliers(), which also increases the runtime PM usage count for each of the available supplier. This makes sense, as to be able to allow the consumer device to be probed by its driver. However, if the driver decides to add a new supplier link during ->probe(), hence updating the list of suppliers, the following call to pm_runtime_put_suppliers(), invoked after really_probe() in the driver core, we get into trouble. More precisely, pm_runtime_put() gets called also for the new supplier(s), which is wrong as the driver core, didn't trigger pm_runtime_get_sync() to be called for it in the first place. In other words, the new supplier may be runtime suspended even in cases when it shouldn't. Fix this behaviour, by runtime resume suppliers according to the same conditions as managed by the runtime PM core, when runtime resume callbacks are being invoked. Additionally, don't try to runtime suspend any of the suppliers after really_probe(), but instead rely on that to happen via the consumer device, when it becomes runtime suspended. Fixes: 21d5c57b3726 (PM / runtime: Use device links) Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index f0fc4700b6ff..db5dbbf7a48d 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -56,8 +56,7 @@ extern void pm_runtime_update_max_time_suspended(struct device *dev, s64 delta_ns); extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); extern void pm_runtime_clean_up_links(struct device *dev); -extern void pm_runtime_get_suppliers(struct device *dev); -extern void pm_runtime_put_suppliers(struct device *dev); +extern void pm_runtime_resume_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device *dev); @@ -173,8 +172,7 @@ static inline unsigned long pm_runtime_autosuspend_expiration( static inline void pm_runtime_set_memalloc_noio(struct device *dev, bool enable){} static inline void pm_runtime_clean_up_links(struct device *dev) {} -static inline void pm_runtime_get_suppliers(struct device *dev) {} -static inline void pm_runtime_put_suppliers(struct device *dev) {} +static inline void pm_runtime_resume_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device *dev) {} -- cgit v1.2.3 From 02f6bf8717a359cabe042c632f3d03fc772450bf Mon Sep 17 00:00:00 2001 From: Phil Edworthy Date: Fri, 25 May 2018 16:11:34 +0100 Subject: gpio: dwapb: Fix rework support for 1 interrupt per port A GPIO Commit da069d5d2b814d9887989dcdb29fb0202eac8b38 ("gpio: dwapb: Rework support for 1 interrupt per port A GPIO"), was an incremental patch that was supposed to provide the delta between v5 and v6 patch set for adding support for 1 interupt per port A GPIO. v5 was applied, then some other feedback came afterwards. However, in my haste I managed to drop the changes made to dwapb_port_property struct. This patch includes those missing changes. Signed-off-by: Phil Edworthy Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-dwapb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-dwapb.h b/include/linux/platform_data/gpio-dwapb.h index 5a52d69c13f3..419cfacb4b42 100644 --- a/include/linux/platform_data/gpio-dwapb.h +++ b/include/linux/platform_data/gpio-dwapb.h @@ -19,7 +19,7 @@ struct dwapb_port_property { unsigned int idx; unsigned int ngpio; unsigned int gpio_base; - unsigned int irq[32]; + int irq[32]; bool has_irq; bool irq_shared; }; -- cgit v1.2.3 From f068fe3170bcf06f14fd0a9eec0be12be04ff012 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 Apr 2018 09:02:55 +0200 Subject: core, dma-direct: add a flag 32-bit dma limits Various PCI bridges (VIA PCI, Xilinx PCIe) limit DMA to only 32-bits even if the device itself supports more. Add a single bit flag to struct device (to be moved into the dma extension once we get to it) to flag such devices and reject larger DMA to them. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman --- include/linux/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 563077d1cdc1..00b6c3b42437 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -904,6 +904,8 @@ struct dev_links_info { * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. + * @dma_32bit_limit: bridge limited to 32bit DMA even if the device itself + * indicates support for a higher limit in the dma_mask field. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -992,6 +994,7 @@ struct device { bool offline_disabled:1; bool offline:1; bool of_node_reused:1; + bool dma_32bit_limit:1; }; static inline struct device *kobj_to_dev(struct kobject *kobj) -- cgit v1.2.3 From 0ead51c3fbd15a4bc91e984f1b18b5c9422fbb02 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 28 May 2018 12:47:57 +0200 Subject: x86/pci-dma: switch the VIA 32-bit DMA quirk to use the struct device flag Instead of globally disabling > 32bit DMA using the arch_dma_supported hook walk the PCI bus under the actually affected bridge and mark every device with the dma_32bit_limit flag. This also gets rid of the arch_dma_supported hook entirely. Signed-off-by: Christoph Hellwig Reviewed-by: Thomas Gleixner --- include/linux/dma-mapping.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 15e4b4e9cc20..f9cc309507d9 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -572,14 +572,6 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) return 0; } -/* - * This is a hack for the legacy x86 forbid_dac and iommu_sac_force. Please - * don't use this in new code. - */ -#ifndef arch_dma_supported -#define arch_dma_supported(dev, mask) (1) -#endif - static inline void dma_check_mask(struct device *dev, u64 mask) { if (sme_active() && (mask < (((u64)sme_get_me_mask() << 1) - 1))) @@ -592,9 +584,6 @@ static inline int dma_supported(struct device *dev, u64 mask) if (!ops) return 0; - if (!arch_dma_supported(dev, mask)) - return 0; - if (!ops->dma_supported) return 1; return ops->dma_supported(dev, mask); -- cgit v1.2.3 From 13193b0f392f5a65d0d54185cb95ed5e99c0a5bf Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 25 May 2018 08:55:22 -0700 Subject: bpf: Define cgroup_bpf_enabled for CONFIG_CGROUP_BPF=n Static key is used to enable/disable cgroup-bpf related code paths at run time. Though it's not defined when cgroup-bpf is disabled at compile time, i.e. CONFIG_CGROUP_BPF=n, and if some code wants to use it, it has to do this: #ifdef CONFIG_CGROUP_BPF if (cgroup_bpf_enabled) { /* ... some work ... */ } #endif This code can be simplified by setting cgroup_bpf_enabled to 0 for CONFIG_CGROUP_BPF=n case: if (cgroup_bpf_enabled) { /* ... some work ... */ } And it aligns well with existing BPF_CGROUP_RUN_PROG_* macros that defined for both states of CONFIG_CGROUP_BPF. Signed-off-by: Andrey Ignatov Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 30d15e64b993..de8e89a3758b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -185,6 +185,7 @@ struct cgroup_bpf {}; static inline void cgroup_bpf_put(struct cgroup *cgrp) {} static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } +#define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) -- cgit v1.2.3 From 1cedee13d25ab118d325f95588c1a084e9317229 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 25 May 2018 08:55:23 -0700 Subject: bpf: Hooks for sys_sendmsg In addition to already existing BPF hooks for sys_bind and sys_connect, the patch provides new hooks for sys_sendmsg. It leverages existing BPF program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR` that provides access to socket itlself (properties like family, type, protocol) and user-passed `struct sockaddr *` so that BPF program can override destination IP and port for system calls such as sendto(2) or sendmsg(2) and/or assign source IP to the socket. The hooks are implemented as two new attach types: `BPF_CGROUP_UDP4_SENDMSG` and `BPF_CGROUP_UDP6_SENDMSG` for UDPv4 and UDPv6 correspondingly. UDPv4 and UDPv6 separate attach types for same reason as sys_bind and sys_connect hooks, i.e. to prevent reading from / writing to e.g. user_ip6 fields when user passes sockaddr_in since it'd be out-of-bound. The difference with already existing hooks is sys_sendmsg are implemented only for unconnected UDP. For TCP it doesn't make sense to change user-provided `struct sockaddr *` at sendto(2)/sendmsg(2) time since socket either was already connected and has source/destination set or wasn't connected and call to sendto(2)/sendmsg(2) would lead to ENOTCONN anyway. Connected UDP is already handled by sys_connect hooks that can override source/destination at connect time and use fast-path later, i.e. these hooks don't affect UDP fast-path. Rewriting source IP is implemented differently than that in sys_connect hooks. When sys_sendmsg is used with unconnected UDP it doesn't work to just bind socket to desired local IP address since source IP can be set on per-packet basis by using ancillary data (cmsg(3)). So no matter if socket is bound or not, source IP has to be rewritten on every call to sys_sendmsg. To do so two new fields are added to UAPI `struct bpf_sock_addr`; * `msg_src_ip4` to set source IPv4 for UDPv4; * `msg_src_ip6` to set source IPv6 for UDPv6. Signed-off-by: Andrey Ignatov Acked-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 23 +++++++++++++++++------ include/linux/filter.h | 1 + 2 files changed, 18 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index de8e89a3758b..975fb4cf1bb7 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -66,7 +66,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, - enum bpf_attach_type type); + enum bpf_attach_type type, + void *t_ctx); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, @@ -120,16 +121,18 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + NULL); \ __ret; \ }) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type) \ +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + t_ctx); \ release_sock(sk); \ } \ __ret; \ @@ -151,10 +154,16 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_CONNECT) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT, NULL) + +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP4_SENDMSG, t_ctx) + +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ @@ -198,6 +207,8 @@ static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) diff --git a/include/linux/filter.h b/include/linux/filter.h index d358d1815c16..d90abdaea94b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1010,6 +1010,7 @@ struct bpf_sock_addr_kern { * only two (src and dst) are available at convert_ctx_access time */ u64 tmp_reg; + void *t_ctx; /* Attach type specific context. */ }; struct bpf_sock_ops_kern { -- cgit v1.2.3 From 30c8bd5aa8b2c78546c3e52337101b9c85879320 Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Thu, 24 May 2018 09:55:13 -0700 Subject: net: Introduce generic failover module The failover module provides a generic interface for paravirtual drivers to register a netdev and a set of ops with a failover instance. The ops are used as event handlers that get called to handle netdev register/ unregister/link change/name change events on slave pci ethernet devices with the same mac address as the failover netdev. This enables paravirtual drivers to use a VF as an accelerated low latency datapath. It also allows migration of VMs with direct attached VFs by failing over to the paravirtual datapath when the VF is unplugged. Signed-off-by: Sridhar Samudrala Signed-off-by: David S. Miller --- include/linux/netdevice.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8452f72087ef..f45b1a4e37ab 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1425,6 +1425,8 @@ struct net_device_ops { * entity (i.e. the master device for bridged veth) * @IFF_MACSEC: device is a MACsec device * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook + * @IFF_FAILOVER: device is a failover master device + * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1454,6 +1456,8 @@ enum netdev_priv_flags { IFF_PHONY_HEADROOM = 1<<24, IFF_MACSEC = 1<<25, IFF_NO_RX_HANDLER = 1<<26, + IFF_FAILOVER = 1<<27, + IFF_FAILOVER_SLAVE = 1<<28, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1482,6 +1486,8 @@ enum netdev_priv_flags { #define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED #define IFF_MACSEC IFF_MACSEC #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER +#define IFF_FAILOVER IFF_FAILOVER +#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE /** * struct net_device - The DEVICE structure. @@ -4336,6 +4342,16 @@ static inline bool netif_is_rxfh_configured(const struct net_device *dev) return dev->priv_flags & IFF_RXFH_CONFIGURED; } +static inline bool netif_is_failover(const struct net_device *dev) +{ + return dev->priv_flags & IFF_FAILOVER; +} + +static inline bool netif_is_failover_slave(const struct net_device *dev) +{ + return dev->priv_flags & IFF_FAILOVER_SLAVE; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { -- cgit v1.2.3 From 6c50c1ed72aeb5cd1ae8cd267d5a79904c82a04f Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Fri, 25 May 2018 12:40:35 +0800 Subject: ptp_qoriq: move some definitions to header file This patch is to move some definitions in ptp_qoriq.c to the header file. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/linux/fsl/ptp_qoriq.h | 141 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 141 insertions(+) create mode 100644 include/linux/fsl/ptp_qoriq.h (limited to 'include/linux') diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h new file mode 100644 index 000000000000..b462d9ea8007 --- /dev/null +++ b/include/linux/fsl/ptp_qoriq.h @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2010 OMICRON electronics GmbH + * Copyright 2018 NXP + */ +#ifndef __PTP_QORIQ_H__ +#define __PTP_QORIQ_H__ + +#include +#include + +/* + * qoriq ptp registers + * Generated by regen.tcl on Thu May 13 01:38:57 PM CEST 2010 + */ +struct qoriq_ptp_registers { + u32 tmr_ctrl; /* Timer control register */ + u32 tmr_tevent; /* Timestamp event register */ + u32 tmr_temask; /* Timer event mask register */ + u32 tmr_pevent; /* Timestamp event register */ + u32 tmr_pemask; /* Timer event mask register */ + u32 tmr_stat; /* Timestamp status register */ + u32 tmr_cnt_h; /* Timer counter high register */ + u32 tmr_cnt_l; /* Timer counter low register */ + u32 tmr_add; /* Timer drift compensation addend register */ + u32 tmr_acc; /* Timer accumulator register */ + u32 tmr_prsc; /* Timer prescale */ + u8 res1[4]; + u32 tmroff_h; /* Timer offset high */ + u32 tmroff_l; /* Timer offset low */ + u8 res2[8]; + u32 tmr_alarm1_h; /* Timer alarm 1 high register */ + u32 tmr_alarm1_l; /* Timer alarm 1 high register */ + u32 tmr_alarm2_h; /* Timer alarm 2 high register */ + u32 tmr_alarm2_l; /* Timer alarm 2 high register */ + u8 res3[48]; + u32 tmr_fiper1; /* Timer fixed period interval */ + u32 tmr_fiper2; /* Timer fixed period interval */ + u32 tmr_fiper3; /* Timer fixed period interval */ + u8 res4[20]; + u32 tmr_etts1_h; /* Timestamp of general purpose external trigger */ + u32 tmr_etts1_l; /* Timestamp of general purpose external trigger */ + u32 tmr_etts2_h; /* Timestamp of general purpose external trigger */ + u32 tmr_etts2_l; /* Timestamp of general purpose external trigger */ +}; + +/* Bit definitions for the TMR_CTRL register */ +#define ALM1P (1<<31) /* Alarm1 output polarity */ +#define ALM2P (1<<30) /* Alarm2 output polarity */ +#define FIPERST (1<<28) /* FIPER start indication */ +#define PP1L (1<<27) /* Fiper1 pulse loopback mode enabled. */ +#define PP2L (1<<26) /* Fiper2 pulse loopback mode enabled. */ +#define TCLK_PERIOD_SHIFT (16) /* 1588 timer reference clock period. */ +#define TCLK_PERIOD_MASK (0x3ff) +#define RTPE (1<<15) /* Record Tx Timestamp to PAL Enable. */ +#define FRD (1<<14) /* FIPER Realignment Disable */ +#define ESFDP (1<<11) /* External Tx/Rx SFD Polarity. */ +#define ESFDE (1<<10) /* External Tx/Rx SFD Enable. */ +#define ETEP2 (1<<9) /* External trigger 2 edge polarity */ +#define ETEP1 (1<<8) /* External trigger 1 edge polarity */ +#define COPH (1<<7) /* Generated clock output phase. */ +#define CIPH (1<<6) /* External oscillator input clock phase */ +#define TMSR (1<<5) /* Timer soft reset. */ +#define BYP (1<<3) /* Bypass drift compensated clock */ +#define TE (1<<2) /* 1588 timer enable. */ +#define CKSEL_SHIFT (0) /* 1588 Timer reference clock source */ +#define CKSEL_MASK (0x3) + +/* Bit definitions for the TMR_TEVENT register */ +#define ETS2 (1<<25) /* External trigger 2 timestamp sampled */ +#define ETS1 (1<<24) /* External trigger 1 timestamp sampled */ +#define ALM2 (1<<17) /* Current time = alarm time register 2 */ +#define ALM1 (1<<16) /* Current time = alarm time register 1 */ +#define PP1 (1<<7) /* periodic pulse generated on FIPER1 */ +#define PP2 (1<<6) /* periodic pulse generated on FIPER2 */ +#define PP3 (1<<5) /* periodic pulse generated on FIPER3 */ + +/* Bit definitions for the TMR_TEMASK register */ +#define ETS2EN (1<<25) /* External trigger 2 timestamp enable */ +#define ETS1EN (1<<24) /* External trigger 1 timestamp enable */ +#define ALM2EN (1<<17) /* Timer ALM2 event enable */ +#define ALM1EN (1<<16) /* Timer ALM1 event enable */ +#define PP1EN (1<<7) /* Periodic pulse event 1 enable */ +#define PP2EN (1<<6) /* Periodic pulse event 2 enable */ + +/* Bit definitions for the TMR_PEVENT register */ +#define TXP2 (1<<9) /* PTP transmitted timestamp im TXTS2 */ +#define TXP1 (1<<8) /* PTP transmitted timestamp in TXTS1 */ +#define RXP (1<<0) /* PTP frame has been received */ + +/* Bit definitions for the TMR_PEMASK register */ +#define TXP2EN (1<<9) /* Transmit PTP packet event 2 enable */ +#define TXP1EN (1<<8) /* Transmit PTP packet event 1 enable */ +#define RXPEN (1<<0) /* Receive PTP packet event enable */ + +/* Bit definitions for the TMR_STAT register */ +#define STAT_VEC_SHIFT (0) /* Timer general purpose status vector */ +#define STAT_VEC_MASK (0x3f) + +/* Bit definitions for the TMR_PRSC register */ +#define PRSC_OCK_SHIFT (0) /* Output clock division/prescale factor. */ +#define PRSC_OCK_MASK (0xffff) + + +#define DRIVER "ptp_qoriq" +#define DEFAULT_CKSEL 1 +#define N_EXT_TS 2 +#define REG_SIZE sizeof(struct qoriq_ptp_registers) + +struct qoriq_ptp { + struct qoriq_ptp_registers __iomem *regs; + spinlock_t lock; /* protects regs */ + struct ptp_clock *clock; + struct ptp_clock_info caps; + struct resource *rsrc; + int irq; + int phc_index; + u64 alarm_interval; /* for periodic alarm */ + u64 alarm_value; + u32 tclk_period; /* nanoseconds */ + u32 tmr_prsc; + u32 tmr_add; + u32 cksel; + u32 tmr_fiper1; + u32 tmr_fiper2; +}; + +static inline u32 qoriq_read(unsigned __iomem *addr) +{ + u32 val; + + val = ioread32be(addr); + return val; +} + +static inline void qoriq_write(unsigned __iomem *addr, u32 val) +{ + iowrite32be(val, addr); +} + +#endif -- cgit v1.2.3 From ca1b7d3daff43a269fb7a0479055ac5b741638d8 Mon Sep 17 00:00:00 2001 From: Eric Long Date: Wed, 23 May 2018 17:31:11 +0800 Subject: dmaengine: sprd: Add Spreadtrum DMA configuration This patch adds the 'device_config' and 'device_prep_slave_sg' interfaces for users to configure DMA, as well as adding one 'struct sprd_dma_config' structure to save Spreadtrum DMA configuration for each DMA channel. Signed-off-by: Eric Long Signed-off-by: Baolin Wang Signed-off-by: Vinod Koul --- include/linux/dma/sprd-dma.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma/sprd-dma.h b/include/linux/dma/sprd-dma.h index c545162e725b..b0115e340fbc 100644 --- a/include/linux/dma/sprd-dma.h +++ b/include/linux/dma/sprd-dma.h @@ -3,6 +3,10 @@ #ifndef _SPRD_DMA_H_ #define _SPRD_DMA_H_ +#define SPRD_DMA_REQ_SHIFT 16 +#define SPRD_DMA_FLAGS(req_mode, int_type) \ + ((req_mode) << SPRD_DMA_REQ_SHIFT | (int_type)) + /* * enum sprd_dma_req_mode: define the DMA request mode * @SPRD_DMA_FRAG_REQ: fragment request mode -- cgit v1.2.3 From 44d99d737279eb2021b2c66df3cee6f8a21ff4e4 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Wed, 18 Apr 2018 12:24:00 +0200 Subject: mfd: cros_ec: Don't try to grab log when suspended We should stop our worker thread while we're suspended. If we don't then we'll get messages like: cros-ec-spi spi5.0: spi transfer failed: -108 cros-ec-spi spi5.0: cs-deassert spi transfer failed: -108 cros-ec-ctl cros-ec-ctl.0.auto: EC communication failed Signed-off-by: Douglas Anderson Signed-off-by: Enric Balletbo i Serra Reviewed-by: Andy Shevchenko Signed-off-by: Lee Jones --- include/linux/mfd/cros_ec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 4ff0cec979b0..b8e750d91200 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -327,5 +327,7 @@ extern struct attribute_group cros_ec_vbc_attr_group; /* debugfs stuff */ int cros_ec_debugfs_init(struct cros_ec_dev *ec); void cros_ec_debugfs_remove(struct cros_ec_dev *ec); +void cros_ec_debugfs_suspend(struct cros_ec_dev *ec); +void cros_ec_debugfs_resume(struct cros_ec_dev *ec); #endif /* __LINUX_MFD_CROS_EC_H */ -- cgit v1.2.3 From a0d476654a2b222567710ab13f3660a39c5641c8 Mon Sep 17 00:00:00 2001 From: "yinbo.zhu" Date: Thu, 24 May 2018 11:38:25 +0800 Subject: mmc: sd: Define name for default speed dtr Add a new define for the sd default speed 25MHz case Signed-off-by: Yinbo Zhu Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 5ebc47855721..de7377815b6b 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -156,6 +156,7 @@ struct sd_switch_caps { #define UHS_DDR50_MAX_DTR 50000000 #define UHS_SDR25_MAX_DTR UHS_DDR50_MAX_DTR #define UHS_SDR12_MAX_DTR 25000000 +#define DEFAULT_SPEED_MAX_DTR UHS_SDR12_MAX_DTR unsigned int sd3_bus_mode; #define UHS_SDR12_BUS_SPEED 0 #define HIGH_SPEED_BUS_SPEED 1 -- cgit v1.2.3 From c94e45bc38ae484ee989e6e3b2496a52776da9e4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 7 May 2018 16:02:14 -0400 Subject: tracing: Do not reference event data in post call triggers Trace event triggers can be called before or after the event has been committed. If it has been called after the commit, there's a possibility that the event no longer exists. Currently, the two post callers is the trigger to disable tracing (traceoff) and the one that will record a stack dump (stacktrace). Neither of them reference the trace event entry record, as that would lead to a race condition that could pass in corrupted data. To prevent any other users of the post data triggers from using the trace event record, pass in NULL to the post call trigger functions for the event record, as they should never need to use them in the first place. This does not fix any bug, but prevents bugs from happening by new post call trigger users. Reviewed-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2bde3eff564c..d1c442d9bd85 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -435,8 +435,7 @@ event_triggers_call(struct trace_event_file *file, void *rec, struct ring_buffer_event *event); extern void event_triggers_post_call(struct trace_event_file *file, - enum event_trigger_type tt, - void *rec, struct ring_buffer_event *event); + enum event_trigger_type tt); bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); -- cgit v1.2.3 From 46ca359955fee63486dc1cfc528ae5692bb16dcd Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 29 May 2018 10:26:44 +0200 Subject: doc: document scope NOFS, NOIO APIs Although the api is documented in the source code Ted has pointed out that there is no mention in the core-api Documentation and there are people looking there to find answers how to use a specific API. Requested-by: "Theodore Y. Ts'o" Reviewed-by: Dave Chinner Signed-off-by: Michal Hocko Signed-off-by: Jonathan Corbet --- include/linux/sched/mm.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 4e1411bbbcfc..76a8cb4ef178 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -170,6 +170,17 @@ static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif +/** + * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope. + * + * This functions marks the beginning of the GFP_NOIO allocation scope. + * All further allocations will implicitly drop __GFP_IO flag and so + * they are safe for the IO critical section from the allocation recursion + * point of view. Use memalloc_noio_restore to end the scope with flags + * returned by this function. + * + * This function is safe to be used from any context. + */ static inline unsigned int memalloc_noio_save(void) { unsigned int flags = current->flags & PF_MEMALLOC_NOIO; @@ -177,11 +188,30 @@ static inline unsigned int memalloc_noio_save(void) return flags; } +/** + * memalloc_noio_restore - Ends the implicit GFP_NOIO scope. + * @flags: Flags to restore. + * + * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function. + * Always make sure that that the given flags is the return value from the + * pairing memalloc_noio_save call. + */ static inline void memalloc_noio_restore(unsigned int flags) { current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags; } +/** + * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope. + * + * This functions marks the beginning of the GFP_NOFS allocation scope. + * All further allocations will implicitly drop __GFP_FS flag and so + * they are safe for the FS critical section from the allocation recursion + * point of view. Use memalloc_nofs_restore to end the scope with flags + * returned by this function. + * + * This function is safe to be used from any context. + */ static inline unsigned int memalloc_nofs_save(void) { unsigned int flags = current->flags & PF_MEMALLOC_NOFS; @@ -189,6 +219,14 @@ static inline unsigned int memalloc_nofs_save(void) return flags; } +/** + * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope. + * @flags: Flags to restore. + * + * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function. + * Always make sure that that the given flags is the return value from the + * pairing memalloc_nofs_save call. + */ static inline void memalloc_nofs_restore(unsigned int flags) { current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags; -- cgit v1.2.3 From f971b132300fb0df63a8de631947adc74a7b3db1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 25 May 2018 21:53:35 -0700 Subject: net: sched: mq: add simple offload notification mq offload is trivial, we just need to let the device know that the root qdisc is mq. Alternative approach would be to export qdisc_lookup() and make drivers check the root type themselves, but notification via ndo_setup_tc is more in line with other qdiscs. Note that mq doesn't hold any stats on it's own, it just adds up stats of its children. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f45b1a4e37ab..6b863ed3174a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -791,6 +791,7 @@ enum tc_setup_type { TC_SETUP_QDISC_CBS, TC_SETUP_QDISC_RED, TC_SETUP_QDISC_PRIO, + TC_SETUP_QDISC_MQ, }; /* These structures hold the attributes of bpf state that are being passed -- cgit v1.2.3 From af4d768ad28cbf6542ba70dba10b49127b31b762 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 27 May 2018 08:09:57 -0700 Subject: net/ipv4: Add support for specifying metric of connected routes Add support for IFA_RT_PRIORITY to ipv4 addresses. If the metric is changed on an existing address then the new route is inserted before removing the old one. Since the metric is one of the route keys, the prefix route can not be replaced. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index e16fe7d44a71..27650f1bff3d 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -139,6 +139,7 @@ struct in_ifaddr { __be32 ifa_local; __be32 ifa_address; __be32 ifa_mask; + __u32 ifa_rt_priority; __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; -- cgit v1.2.3 From 01fc27d96950149c3e6c0b8dfbe05e26725381cb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 May 2018 15:52:26 +0200 Subject: libata: remove ata_scsi_timed_out As far as I can tell this function can't even be called any more, given that ATA implements its own eh_strategy_handler with ata_scsi_error, which never calls ->eh_timed_out. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/libata.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 1795fecdea17..1c113134c98f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1133,7 +1133,6 @@ extern int ata_sas_port_start(struct ata_port *ap); extern void ata_sas_port_stop(struct ata_port *ap); extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *); extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap); -extern enum blk_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd); extern int sata_scr_valid(struct ata_link *link); extern int sata_scr_read(struct ata_link *link, int reg, u32 *val); extern int sata_scr_write(struct ata_link *link, int reg, u32 val); @@ -1359,7 +1358,6 @@ extern struct device_attribute *ata_common_sdev_attrs[]; .proc_name = drv_name, \ .slave_configure = ata_scsi_slave_config, \ .slave_destroy = ata_scsi_slave_destroy, \ - .eh_timed_out = ata_scsi_timed_out, \ .bios_param = ata_std_bios_param, \ .unlock_native_capacity = ata_scsi_unlock_native_capacity, \ .sdev_attrs = ata_common_sdev_attrs -- cgit v1.2.3 From 6059577cb28d8b15d2b7dad51eb90d885f1ed9ab Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 14 May 2018 10:06:22 +0200 Subject: regulator: fixed: Convert to use GPIO descriptor only As we augmented the regulator core to accept a GPIO descriptor instead of a GPIO number, we can augment the fixed GPIO regulator to look up and pass that descriptor directly from device tree or board GPIO descriptor look up tables. Some boards just auto-enumerate their fixed regulator platform devices and I have assumed they get names like "fixed-regulator.0" but it's pretty hard to guess this. I need some testing from board maintainers to be sure. Other boards are straight forward, using just plain "fixed-regulator" (ID -1) or "fixed-regulator.1" hammering down the device ID. The OMAP didn't have proper label names on its GPIO chips so I have fixed this with a separate patch to the GPIO tree, see commit 088413bc0bd5f5fb66ca22a19d66a49d7154ba4c "gpio: omap: Give unique labels to each GPIO bank/chip" It seems the da9055 and da9211 has never got around to actually passing any enable gpio into its platform data (not the in-tree code anyway) so we can just decide to simply pass a descriptor instead. The fixed GPIO-controlled regulator in mach-pxa/ezx.c was confusingly named "*_dummy_supply_device" while it is a very real device backed by a GPIO line. There is nothing dummy about it at all, so I renamed it with the infix *_regulator_* as part of this patch set. For the patch hunk hitting arch/blackfin I would say I do not expect testing, review or ACKs anymore so if it works, it works. The hunk hitting the x86 BCM43xx driver is especially tricky as the number comes out of SFI which is a mystery to me. I definately need someone to look at this. (Hi Andy.) Cc: Andy Shevchenko # Check the x86 BCM stuff Cc: Alexander Shiyan # i.MX boards user Cc: Haojian Zhuang # MMP2 maintainer Cc: Aaro Koskinen # OMAP1 maintainer Cc: Tony Lindgren # OMAP1,2,3 maintainer Cc: Mike Rapoport # EM-X270 maintainer Cc: Robert Jarzmik # EZX maintainer Cc: Philipp Zabel # Magician maintainer Cc: Daniel Mack # Raumfeld maintainer Cc: Marc Zyngier # Zeus maintainer Cc: Geert Uytterhoeven # SuperH pinctrl/GPIO maintainer Cc: Russell King # SA1100 Signed-off-by: Linus Walleij Acked-by: Andy Shevchenko Acked-by: Tony Lindgren Signed-off-by: Mark Brown --- include/linux/regulator/fixed.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h index 48918be649d4..1a4340ed8e2b 100644 --- a/include/linux/regulator/fixed.h +++ b/include/linux/regulator/fixed.h @@ -24,8 +24,6 @@ struct regulator_init_data; * @supply_name: Name of the regulator supply * @input_supply: Name of the input regulator supply * @microvolts: Output voltage of regulator - * @gpio: GPIO to use for enable control - * set to -EINVAL if not used * @startup_delay: Start-up time in microseconds * @gpio_is_open_drain: Gpio pin is open drain or normal type. * If it is open drain type then HIGH will be set @@ -49,7 +47,6 @@ struct fixed_voltage_config { const char *supply_name; const char *input_supply; int microvolts; - int gpio; unsigned startup_delay; unsigned gpio_is_open_drain:1; unsigned enable_high:1; -- cgit v1.2.3 From 37bed97f00734ce329495823d9682181028b51e4 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 14 May 2018 10:06:23 +0200 Subject: regulator: gpio: Get enable GPIO using GPIO descriptor We augment the GPIO regulator to get the *enable* regulator GPIO line (not the other lines) using a descriptor rather than a global number. We then pass this into the regulator core which has been prepared to hande enable descriptors in a separate patch. Switch over the two boardfiles using this facility and clean up so we only pass descriptors around. Cc: Philipp Zabel # HX4700/Magician maintainer Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- include/linux/regulator/gpio-regulator.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/gpio-regulator.h b/include/linux/regulator/gpio-regulator.h index 19fbd267406d..536cab86f2d5 100644 --- a/include/linux/regulator/gpio-regulator.h +++ b/include/linux/regulator/gpio-regulator.h @@ -44,8 +44,6 @@ struct gpio_regulator_state { /** * struct gpio_regulator_config - config structure * @supply_name: Name of the regulator supply - * @enable_gpio: GPIO to use for enable control - * set to -EINVAL if not used * @enable_high: Polarity of enable GPIO * 1 = Active high, 0 = Active low * @enabled_at_boot: Whether regulator has been enabled at @@ -69,7 +67,6 @@ struct gpio_regulator_state { struct gpio_regulator_config { const char *supply_name; - int enable_gpio; unsigned enable_high:1; unsigned enabled_at_boot:1; unsigned startup_delay; -- cgit v1.2.3 From 12f5b93145450c750f315657ef239a314811aeeb Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 29 May 2018 15:52:28 +0200 Subject: blk-mq: Remove generation seqeunce This patch simplifies the timeout handling by relying on the request reference counting to ensure the iterator is operating on an inflight and truly timed out request. Since the reference counting prevents the tag from being reallocated, the block layer no longer needs to prevent drivers from completing their requests while the timeout handler is operating on it: a driver completing a request is allowed to proceed to the next state without additional syncronization with the block layer. This also removes any need for generation sequence numbers since the request lifetime is prevented from being reallocated as a new sequence while timeout handling is operating on it. To enables this a refcount is added to struct request so that request users can be sure they're operating on the same request without it changing while they're processing it. The request's tag won't be released for reuse until both the timeout handler and the completion are done with it. Signed-off-by: Keith Busch [hch: slight cleanups, added back submission side hctx lock, use cmpxchg for completions] Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 35 ++++++++++++----------------------- 1 file changed, 12 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3999719f828..a1c05e85a443 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -125,15 +125,22 @@ typedef __u32 __bitwise req_flags_t; #define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) /* The per-zone write lock is held for this request */ #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) -/* timeout is expired */ -#define RQF_MQ_TIMEOUT_EXPIRED ((__force req_flags_t)(1 << 20)) /* already slept for hybrid poll */ -#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 21)) +#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) +/* + * Request state for blk-mq. + */ +enum mq_rq_state { + MQ_RQ_IDLE = 0, + MQ_RQ_IN_FLIGHT = 1, + MQ_RQ_COMPLETE = 2, +}; + /* * Try to put the fields that are referenced together in the same cacheline. * @@ -236,26 +243,8 @@ struct request { unsigned int extra_len; /* length of alignment and padding */ - /* - * On blk-mq, the lower bits of ->gstate (generation number and - * state) carry the MQ_RQ_* state value and the upper bits the - * generation number which is monotonically incremented and used to - * distinguish the reuse instances. - * - * ->gstate_seq allows updates to ->gstate and other fields - * (currently ->deadline) during request start to be read - * atomically from the timeout path, so that it can operate on a - * coherent set of information. - */ - seqcount_t gstate_seq; - u64 gstate; - - /* - * ->aborted_gstate is used by the timeout to claim a specific - * recycle instance of this request. See blk_mq_timeout_work(). - */ - struct u64_stats_sync aborted_gstate_sync; - u64 aborted_gstate; + enum mq_rq_state state; + refcount_t ref; /* access through blk_rq_set_deadline, blk_rq_deadline */ unsigned long __deadline; -- cgit v1.2.3 From 6600593cbd9340b3d4fcde8e58d17653732620c4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 May 2018 15:52:29 +0200 Subject: block: rename BLK_EH_NOT_HANDLED to BLK_EH_DONE The BLK_EH_NOT_HANDLED implies nothing happen, but very often that is not what is happening - instead the driver already completed the command. Fix the symbolic name to reflect that a little better. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a1c05e85a443..f82e05df905b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -326,7 +326,7 @@ typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); typedef void (exit_rq_fn)(struct request_queue *, struct request *); enum blk_eh_timer_return { - BLK_EH_NOT_HANDLED, + BLK_EH_DONE, BLK_EH_HANDLED, BLK_EH_RESET_TIMER, }; -- cgit v1.2.3 From f6e7d48a780a95a599d7e325f45e9ac208ac6f13 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 May 2018 15:52:37 +0200 Subject: block: remove BLK_EH_HANDLED Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f82e05df905b..d838a89639f2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -327,7 +327,6 @@ typedef void (exit_rq_fn)(struct request_queue *, struct request *); enum blk_eh_timer_return { BLK_EH_DONE, - BLK_EH_HANDLED, BLK_EH_RESET_TIMER, }; -- cgit v1.2.3 From 88b0cfad288831a86ffd79b6d00b689489598186 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 May 2018 15:52:38 +0200 Subject: block: document the blk_eh_timer_return values Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d838a89639f2..9f06b29adaa4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -326,8 +326,8 @@ typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); typedef void (exit_rq_fn)(struct request_queue *, struct request *); enum blk_eh_timer_return { - BLK_EH_DONE, - BLK_EH_RESET_TIMER, + BLK_EH_DONE, /* drivers has completed the command */ + BLK_EH_RESET_TIMER, /* reset timer and try again */ }; typedef enum blk_eh_timer_return (rq_timed_out_fn)(struct request *); -- cgit v1.2.3 From 0b7576d8eb4c5634276ada359bfdb72e69eebc25 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 29 May 2018 08:47:57 -0600 Subject: block: move ->timeout request member After the recent timeout handling changes, we have two holes in the struct. Move the timeout near the deadline, killing both, and moving related members closer together. On my config on x86-64, this shrinks struct request from 312 to 304 bytes. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9f06b29adaa4..4efd9af62e25 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -237,8 +237,6 @@ struct request { unsigned short write_hint; unsigned short ioprio; - unsigned int timeout; - void *special; /* opaque pointer available for LLD use */ unsigned int extra_len; /* length of alignment and padding */ @@ -246,6 +244,8 @@ struct request { enum mq_rq_state state; refcount_t ref; + unsigned int timeout; + /* access through blk_rq_set_deadline, blk_rq_deadline */ unsigned long __deadline; -- cgit v1.2.3 From 5afb78356cead66db2203061fed6fc8957527ed4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 May 2018 16:42:59 +0200 Subject: block: don't print a message when the device went away The information about a size change in this case just creates confusion. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 760d8da1b6c7..d8d4831af9ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2570,7 +2570,7 @@ extern bool is_bad_inode(struct inode *); #ifdef CONFIG_BLOCK extern void check_disk_size_change(struct gendisk *disk, - struct block_device *bdev); + struct block_device *bdev, bool verbose); extern int revalidate_disk(struct gendisk *); extern int check_disk_change(struct block_device *); extern int __invalidate_device(struct block_device *, bool); -- cgit v1.2.3 From 5de815a7eedfacf593817ef34634eaa9b75a1482 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 May 2018 08:40:23 +0200 Subject: block: remove parent device reference from struct bsg_class_device Bsg holding a reference to the parent device may result in a crash if a bsg file handle is closed after the parent device driver has unloaded. Holding a reference is not really needed: the parent device must exist between bsg_register_queue and bsg_unregister_queue. Before the device goes away the caller does blk_cleanup_queue so that all in-flight requests to the device are gone and all new requests cannot pass beyond the queue. The queue itself is a refcounted object and it will stay alive with a bsg file. Based on analysis, previous patch and changelog from Anatoliy Glagolev. Reported-by: Anatoliy Glagolev Reviewed-by: James E.J. Bottomley Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bsg-lib.h | 3 +-- include/linux/bsg.h | 6 +----- 2 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 28a7ccc55c89..6aeaf6472665 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -72,8 +72,7 @@ struct bsg_job { void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); struct request_queue *bsg_setup_queue(struct device *dev, const char *name, - bsg_job_fn *job_fn, int dd_job_size, - void (*release)(struct device *)); + bsg_job_fn *job_fn, int dd_job_size); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); diff --git a/include/linux/bsg.h b/include/linux/bsg.h index 0c7dd9ceb139..dac37b6e00ec 100644 --- a/include/linux/bsg.h +++ b/include/linux/bsg.h @@ -17,17 +17,13 @@ struct bsg_ops { struct bsg_class_device { struct device *class_dev; - struct device *parent; int minor; struct request_queue *queue; - struct kref ref; const struct bsg_ops *ops; - void (*release)(struct device *); }; int bsg_register_queue(struct request_queue *q, struct device *parent, - const char *name, const struct bsg_ops *ops, - void (*release)(struct device *)); + const char *name, const struct bsg_ops *ops); int bsg_scsi_register_queue(struct request_queue *q, struct device *parent); void bsg_unregister_queue(struct request_queue *q); #else -- cgit v1.2.3 From ab741b2eed3e456cebd2240d4c9c6be003d5ae72 Mon Sep 17 00:00:00 2001 From: Yonatan Cohen Date: Sun, 27 May 2018 13:42:32 +0300 Subject: net/mlx5: Exposing a new mini-CQE format The new mini-CQE format includes byte-count, checksum and stride index. Reviewed-by: Yishai Hadas Reviewed-by: Guy Levi Signed-off-by: Yonatan Cohen Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 9c3538f1b8b9..10c1613d9434 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1112,7 +1112,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 num_of_uars_per_page[0x20]; u8 reserved_at_540[0x40]; - u8 reserved_at_580[0x3d]; + u8 reserved_at_580[0x3c]; + u8 mini_cqe_resp_stride_index[0x1]; u8 cqe_128_always[0x1]; u8 cqe_compression_128[0x1]; u8 cqe_compression[0x1]; -- cgit v1.2.3 From 7e3c03817feccdf2b26722993825dc09377908b4 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Mon, 7 May 2018 11:52:29 -0600 Subject: drivers: thermal: Update license to SPDX format Update licences format for core thermal files. Signed-off-by: Lina Iyer Acked-by: Daniel Lezcano Signed-off-by: Zhang Rui --- include/linux/thermal.h | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 7834be668d80..5f4705f46c2f 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -1,25 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * thermal.h ($Revision: 0 $) * * Copyright (C) 2008 Intel Corp * Copyright (C) 2008 Zhang Rui * Copyright (C) 2008 Sujith Thomas - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ #ifndef __THERMAL_H__ -- cgit v1.2.3 From 9c80172b902db58233346adbb139cfdcb9229f0f Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 25 May 2018 12:19:57 +0200 Subject: kernel/SRCU: provide a static initializer There are macros for static initializer for the three out of four possible notifier types, that are: ATOMIC_NOTIFIER_HEAD() BLOCKING_NOTIFIER_HEAD() RAW_NOTIFIER_HEAD() This patch provides a static initilizer for the forth type to make it complete. Signed-off-by: Sebastian Andrzej Siewior Tested-by: Paul E. McKenney Reviewed-by: Paul E. McKenney Signed-off-by: Rafael J. Wysocki --- include/linux/notifier.h | 34 +++++++++++++++++++++++++++++----- include/linux/srcutiny.h | 6 +++--- include/linux/srcutree.h | 6 +++--- 3 files changed, 35 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 6d731110e0db..f35c7bf76143 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -43,9 +43,7 @@ * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. * As compensation, srcu_notifier_chain_unregister() is rather expensive. * SRCU notifier chains should be used when the chain will be called very - * often but notifier_blocks will seldom be removed. Also, SRCU notifier - * chains are slightly more difficult to use because they require special - * runtime initialization. + * often but notifier_blocks will seldom be removed. */ struct notifier_block; @@ -91,7 +89,7 @@ struct srcu_notifier_head { (name)->head = NULL; \ } while (0) -/* srcu_notifier_heads must be initialized and cleaned up dynamically */ +/* srcu_notifier_heads must be cleaned up dynamically */ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #define srcu_cleanup_notifier_head(name) \ cleanup_srcu_struct(&(name)->srcu); @@ -104,7 +102,13 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); .head = NULL } #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } -/* srcu_notifier_heads cannot be initialized statically */ + +#define SRCU_NOTIFIER_INIT(name, pcpu) \ + { \ + .mutex = __MUTEX_INITIALIZER(name.mutex), \ + .head = NULL, \ + .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ + } #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ @@ -116,6 +120,26 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); struct raw_notifier_head name = \ RAW_NOTIFIER_INIT(name) +#ifdef CONFIG_TREE_SRCU +#define _SRCU_NOTIFIER_HEAD(name, mod) \ + static DEFINE_PER_CPU(struct srcu_data, \ + name##_head_srcu_data); \ + mod struct srcu_notifier_head name = \ + SRCU_NOTIFIER_INIT(name, name##_head_srcu_data) + +#else +#define _SRCU_NOTIFIER_HEAD(name, mod) \ + mod struct srcu_notifier_head name = \ + SRCU_NOTIFIER_INIT(name, name) + +#endif + +#define SRCU_NOTIFIER_HEAD(name) \ + _SRCU_NOTIFIER_HEAD(name, /* not static */) + +#define SRCU_NOTIFIER_HEAD_STATIC(name) \ + _SRCU_NOTIFIER_HEAD(name, static) + #ifdef __KERNEL__ extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 261471f407a5..f41d2fb09f87 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -43,7 +43,7 @@ struct srcu_struct { void srcu_drive_gp(struct work_struct *wp); -#define __SRCU_STRUCT_INIT(name) \ +#define __SRCU_STRUCT_INIT(name, __ignored) \ { \ .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ .srcu_cb_tail = &name.srcu_cb_head, \ @@ -56,9 +56,9 @@ void srcu_drive_gp(struct work_struct *wp); * Tree SRCU, which needs some per-CPU data. */ #define DEFINE_SRCU(name) \ - struct srcu_struct name = __SRCU_STRUCT_INIT(name) + struct srcu_struct name = __SRCU_STRUCT_INIT(name, name) #define DEFINE_STATIC_SRCU(name) \ - static struct srcu_struct name = __SRCU_STRUCT_INIT(name) + static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name) void synchronize_srcu(struct srcu_struct *sp); diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 4eda108abee0..745d4ca4dd50 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -104,9 +104,9 @@ struct srcu_struct { #define SRCU_STATE_SCAN1 1 #define SRCU_STATE_SCAN2 2 -#define __SRCU_STRUCT_INIT(name) \ +#define __SRCU_STRUCT_INIT(name, pcpu_name) \ { \ - .sda = &name##_srcu_data, \ + .sda = &pcpu_name, \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq_needed = 0 - 1, \ __SRCU_DEP_MAP_INIT(name) \ @@ -133,7 +133,7 @@ struct srcu_struct { */ #define __DEFINE_SRCU(name, is_static) \ static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data);\ - is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) + is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_data) #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) -- cgit v1.2.3 From f4364dcfc86df7c1ca47b256eaf6b6d0cdd0d936 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Sun, 27 May 2018 12:24:09 +0100 Subject: media: rc: introduce BPF_PROG_LIRC_MODE2 Add support for BPF_PROG_LIRC_MODE2. This type of BPF program can call rc_keydown() to reported decoded IR scancodes, or rc_repeat() to report that the last key should be repeated. The bpf program can be attached to using the bpf(BPF_PROG_ATTACH) syscall; the target_fd must be the /dev/lircN device. Acked-by: Yonghong Song Signed-off-by: Sean Young Signed-off-by: Daniel Borkmann --- include/linux/bpf_lirc.h | 29 +++++++++++++++++++++++++++++ include/linux/bpf_types.h | 3 +++ 2 files changed, 32 insertions(+) create mode 100644 include/linux/bpf_lirc.h (limited to 'include/linux') diff --git a/include/linux/bpf_lirc.h b/include/linux/bpf_lirc.h new file mode 100644 index 000000000000..5f8a4283092d --- /dev/null +++ b/include/linux/bpf_lirc.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_LIRC_H +#define _BPF_LIRC_H + +#include + +#ifdef CONFIG_BPF_LIRC_MODE2 +int lirc_prog_attach(const union bpf_attr *attr); +int lirc_prog_detach(const union bpf_attr *attr); +int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +#else +static inline int lirc_prog_attach(const union bpf_attr *attr) +{ + return -EINVAL; +} + +static inline int lirc_prog_detach(const union bpf_attr *attr) +{ + return -EINVAL; +} + +static inline int lirc_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} +#endif + +#endif /* _BPF_LIRC_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index b161e506dcfc..c5700c2d5549 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -26,6 +26,9 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint) #ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) #endif +#ifdef CONFIG_BPF_LIRC_MODE2 +BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) -- cgit v1.2.3 From 781b9d6b84324b47e316a233433fa2c179cb1ee5 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 29 May 2018 12:04:13 +0200 Subject: PM / Domains: Drop extern declarations of functions in pm_domain.h Using "extern" to declare a function in a public header file is somewhat pointless, but also doesn't hurt. However, to make all the function declarations in pm_domain.h to be consistent, let's drop the use of "extern". Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 51 +++++++++++++++++++++-------------------------- 1 file changed, 23 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 4e5764083fd8..c847e9a3033d 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -143,21 +143,17 @@ static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev) return to_gpd_data(dev->power.subsys_data->domain_data); } -extern int __pm_genpd_add_device(struct generic_pm_domain *genpd, - struct device *dev, - struct gpd_timing_data *td); - -extern int pm_genpd_remove_device(struct generic_pm_domain *genpd, - struct device *dev); -extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, - struct generic_pm_domain *new_subdomain); -extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, - struct generic_pm_domain *target); -extern int pm_genpd_init(struct generic_pm_domain *genpd, - struct dev_power_governor *gov, bool is_off); -extern int pm_genpd_remove(struct generic_pm_domain *genpd); -extern int dev_pm_genpd_set_performance_state(struct device *dev, - unsigned int state); +int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, + struct gpd_timing_data *td); +int pm_genpd_remove_device(struct generic_pm_domain *genpd, struct device *dev); +int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, + struct generic_pm_domain *new_subdomain); +int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, + struct generic_pm_domain *target); +int pm_genpd_init(struct generic_pm_domain *genpd, + struct dev_power_governor *gov, bool is_off); +int pm_genpd_remove(struct generic_pm_domain *genpd); +int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; @@ -215,8 +211,8 @@ static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, } #ifdef CONFIG_PM_GENERIC_DOMAINS_SLEEP -extern void pm_genpd_syscore_poweroff(struct device *dev); -extern void pm_genpd_syscore_poweron(struct device *dev); +void pm_genpd_syscore_poweroff(struct device *dev); +void pm_genpd_syscore_poweron(struct device *dev); #else static inline void pm_genpd_syscore_poweroff(struct device *dev) {} static inline void pm_genpd_syscore_poweron(struct device *dev) {} @@ -240,14 +236,13 @@ int of_genpd_add_provider_simple(struct device_node *np, int of_genpd_add_provider_onecell(struct device_node *np, struct genpd_onecell_data *data); void of_genpd_del_provider(struct device_node *np); -extern int of_genpd_add_device(struct of_phandle_args *args, - struct device *dev); -extern int of_genpd_add_subdomain(struct of_phandle_args *parent, - struct of_phandle_args *new_subdomain); -extern struct generic_pm_domain *of_genpd_remove_last(struct device_node *np); -extern int of_genpd_parse_idle_states(struct device_node *dn, - struct genpd_power_state **states, int *n); -extern unsigned int of_genpd_opp_to_performance_state(struct device *dev, +int of_genpd_add_device(struct of_phandle_args *args, struct device *dev); +int of_genpd_add_subdomain(struct of_phandle_args *parent, + struct of_phandle_args *new_subdomain); +struct generic_pm_domain *of_genpd_remove_last(struct device_node *np); +int of_genpd_parse_idle_states(struct device_node *dn, + struct genpd_power_state **states, int *n); +unsigned int of_genpd_opp_to_performance_state(struct device *dev, struct device_node *opp_node); int genpd_dev_pm_attach(struct device *dev); @@ -304,9 +299,9 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np) #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */ #ifdef CONFIG_PM -extern int dev_pm_domain_attach(struct device *dev, bool power_on); -extern void dev_pm_domain_detach(struct device *dev, bool power_off); -extern void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd); +int dev_pm_domain_attach(struct device *dev, bool power_on); +void dev_pm_domain_detach(struct device *dev, bool power_off); +void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd); #else static inline int dev_pm_domain_attach(struct device *dev, bool power_on) { -- cgit v1.2.3 From 1a7a67072f35b3e65e76fc694b088ca48b4dae35 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 29 May 2018 12:04:14 +0200 Subject: PM / Domains: Drop __pm_genpd_add_device() There are still a few non-DT existing users of genpd, however neither of them uses __pm_genpd_add_device(), hence let's drop it. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index c847e9a3033d..79888fb4a81f 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -143,8 +143,7 @@ static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev) return to_gpd_data(dev->power.subsys_data->domain_data); } -int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, - struct gpd_timing_data *td); +int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev); int pm_genpd_remove_device(struct generic_pm_domain *genpd, struct device *dev); int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_subdomain); @@ -163,9 +162,8 @@ static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev) { return ERR_PTR(-ENOSYS); } -static inline int __pm_genpd_add_device(struct generic_pm_domain *genpd, - struct device *dev, - struct gpd_timing_data *td) +static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, + struct device *dev) { return -ENOSYS; } @@ -204,12 +202,6 @@ static inline int dev_pm_genpd_set_performance_state(struct device *dev, #define pm_domain_always_on_gov (*(struct dev_power_governor *)(NULL)) #endif -static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, - struct device *dev) -{ - return __pm_genpd_add_device(genpd, dev, NULL); -} - #ifdef CONFIG_PM_GENERIC_DOMAINS_SLEEP void pm_genpd_syscore_poweroff(struct device *dev); void pm_genpd_syscore_poweron(struct device *dev); -- cgit v1.2.3 From 924f448699627722a7dcaefb857d09fd324e75c5 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 29 May 2018 12:04:15 +0200 Subject: PM / Domains: Drop genpd as in-param for pm_genpd_remove_device() There is no need to pass a genpd struct to pm_genpd_remove_device(), as we already have the information about the PM domain (genpd) through the device structure. Additionally, we don't allow to remove a PM domain from a device, other than the one it may have assigned to it, so really it does not make sense to have a separate in-param for it. For these reason, drop it and update the current only call to pm_genpd_remove_device() from amdgpu_acp. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 79888fb4a81f..42e0d649e653 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -144,7 +144,7 @@ static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev) } int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev); -int pm_genpd_remove_device(struct generic_pm_domain *genpd, struct device *dev); +int pm_genpd_remove_device(struct device *dev); int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_subdomain); int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, @@ -167,8 +167,7 @@ static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, { return -ENOSYS; } -static inline int pm_genpd_remove_device(struct generic_pm_domain *genpd, - struct device *dev) +static inline int pm_genpd_remove_device(struct device *dev) { return -ENOSYS; } -- cgit v1.2.3 From ab4d11e2c2329cf7cb7be31ff22489aae4dee5dc Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 30 May 2018 15:15:20 +0100 Subject: regulator: wm8994: Fix shared GPIOs This reverts commit 3c6b38d45fa51c7c51 "regulator: wm8994: Pass descriptor instead of GPIO number" as it has problems with shared GPIOs similar to that on s2mps11. Reported-by: Marek Szyprowski Signed-off-by: Mark Brown --- include/linux/mfd/wm8994/pdata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8994/pdata.h b/include/linux/mfd/wm8994/pdata.h index fca67bd194e2..90c60524a496 100644 --- a/include/linux/mfd/wm8994/pdata.h +++ b/include/linux/mfd/wm8994/pdata.h @@ -20,6 +20,9 @@ #define WM8994_NUM_AIF 3 struct wm8994_ldo_pdata { + /** GPIOs to enable regulator, 0 or less if not available */ + int enable; + const struct regulator_init_data *init_data; }; -- cgit v1.2.3 From edd303ff0e9ebc39118e633916278b5ca8558c30 Mon Sep 17 00:00:00 2001 From: Janakarajan Natarajan Date: Fri, 25 May 2018 15:23:29 -0500 Subject: crypto: ccp - Add DOWNLOAD_FIRMWARE SEV command The DOWNLOAD_FIRMWARE command, added as of SEV API v0.15, allows the OS to install SEV firmware newer than the currently active SEV firmware. For the new SEV firmware to be applied it must: * Pass the validation test performed by the existing firmware. * Be of the same build or a newer build compared to the existing firmware. For more information please refer to "Section 5.11 DOWNLOAD_FIRMWARE" of https://support.amd.com/TechDocs/55766_SEV-KM%20API_Specification.pdf Signed-off-by: Janakarajan Natarajan Signed-off-by: Herbert Xu --- include/linux/psp-sev.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 93addfa34061..1d2496246072 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -54,6 +54,7 @@ enum sev_cmd { SEV_CMD_PDH_CERT_EXPORT = 0x008, SEV_CMD_PDH_GEN = 0x009, SEV_CMD_DF_FLUSH = 0x00A, + SEV_CMD_DOWNLOAD_FIRMWARE = 0x00B, /* Guest commands */ SEV_CMD_DECOMMISSION = 0x020, @@ -129,6 +130,17 @@ struct sev_data_pek_cert_import { u32 oca_cert_len; /* In */ } __packed; +/** + * struct sev_data_download_firmware - DOWNLOAD_FIRMWARE command parameters + * + * @address: physical address of firmware image + * @len: len of the firmware image + */ +struct sev_data_download_firmware { + u64 address; /* In */ + u32 len; /* In */ +} __packed; + /** * struct sev_data_pdh_cert_export - PDH_CERT_EXPORT command parameters * -- cgit v1.2.3 From 0b3a830bb407dce79468a26f382260131b50b3c5 Mon Sep 17 00:00:00 2001 From: Janakarajan Natarajan Date: Fri, 25 May 2018 15:23:30 -0500 Subject: crypto: ccp - Add GET_ID SEV command The GET_ID command, added as of SEV API v0.16, allows the SEV firmware to be queried about a unique CPU ID. This unique ID can then be used to obtain the public certificate containing the Chip Endorsement Key (CEK) public key signed by the AMD SEV Signing Key (ASK). For more information please refer to "Section 5.12 GET_ID" of https://support.amd.com/TechDocs/55766_SEV-KM%20API_Specification.pdf Signed-off-by: Janakarajan Natarajan Signed-off-by: Herbert Xu --- include/linux/psp-sev.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 1d2496246072..827c601841c4 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -55,6 +55,7 @@ enum sev_cmd { SEV_CMD_PDH_GEN = 0x009, SEV_CMD_DF_FLUSH = 0x00A, SEV_CMD_DOWNLOAD_FIRMWARE = 0x00B, + SEV_CMD_GET_ID = 0x00C, /* Guest commands */ SEV_CMD_DECOMMISSION = 0x020, @@ -141,6 +142,16 @@ struct sev_data_download_firmware { u32 len; /* In */ } __packed; +/** + * struct sev_data_get_id - GET_ID command parameters + * + * @address: physical address of region to place unique CPU ID(s) + * @len: len of the region + */ +struct sev_data_get_id { + u64 address; /* In */ + u32 len; /* In/Out */ +} __packed; /** * struct sev_data_pdh_cert_export - PDH_CERT_EXPORT command parameters * -- cgit v1.2.3 From 126b7de6bfd84b2daadca2c3396108cd847adb5d Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 15 May 2018 11:07:02 +0200 Subject: PCI: Rename of_pci_get_host_bridge_resources() device node parameter We will add a "struct device *dev" parameter to this function soon, so rename the existing "struct device_node *dev" parameter to "dev_node". Tested-by: Vladimir Zapolskiy Signed-off-by: Jan Kiszka Signed-off-by: Bjorn Helgaas Reviewed-by: Vladimir Zapolskiy --- include/linux/of_pci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 091033a6b836..74eec1943ad2 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -71,11 +71,11 @@ of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) #endif #if defined(CONFIG_OF_ADDRESS) -int of_pci_get_host_bridge_resources(struct device_node *dev, +int of_pci_get_host_bridge_resources(struct device_node *dev_node, unsigned char busno, unsigned char bus_max, struct list_head *resources, resource_size_t *io_base); #else -static inline int of_pci_get_host_bridge_resources(struct device_node *dev, +static inline int of_pci_get_host_bridge_resources(struct device_node *dev_node, unsigned char busno, unsigned char bus_max, struct list_head *resources, resource_size_t *io_base) { -- cgit v1.2.3 From 055f87a2a33640923d400fd5c3ebfff24198459f Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 15 May 2018 11:07:03 +0200 Subject: PCI: Pass struct device to of_pci_get_host_bridge_resources() Another step towards a managed version of of_pci_get_host_bridge_resources(): Feed in the underlying device, rather than just the OF node. This will allow us to use managed resource allocation internally later on. Tested-by: Vladimir Zapolskiy Signed-off-by: Jan Kiszka Signed-off-by: Bjorn Helgaas Reviewed-by: Vladimir Zapolskiy Acked-by: Jingoo Han CC: Joao Pinto CC: Lorenzo Pieralisi --- include/linux/of_pci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 74eec1943ad2..e6684c68cb94 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -71,11 +71,11 @@ of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) #endif #if defined(CONFIG_OF_ADDRESS) -int of_pci_get_host_bridge_resources(struct device_node *dev_node, +int of_pci_get_host_bridge_resources(struct device *dev, unsigned char busno, unsigned char bus_max, struct list_head *resources, resource_size_t *io_base); #else -static inline int of_pci_get_host_bridge_resources(struct device_node *dev_node, +static inline int of_pci_get_host_bridge_resources(struct device *dev, unsigned char busno, unsigned char bus_max, struct list_head *resources, resource_size_t *io_base) { -- cgit v1.2.3 From 5bd51b35c7cbbc98786282ada940429a33b52e17 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 15 May 2018 11:07:05 +0200 Subject: PCI: Rework of_pci_get_host_bridge_resources() to devm_of_pci_get_host_bridge_resources() of_pci_get_host_bridge_resources() allocates the resource structures it fills dynamically, but none of its callers care to release them so far. Rather than requiring everyone to do this explicitly, convert the existing function to a managed version. Tested-by: Vladimir Zapolskiy Signed-off-by: Jan Kiszka Signed-off-by: Bjorn Helgaas Reviewed-by: Vladimir Zapolskiy Acked-by: Joao Pinto Acked-by: Jingoo Han CC: Lorenzo Pieralisi --- include/linux/of_pci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index e6684c68cb94..fa4463a52900 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -71,11 +71,11 @@ of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) #endif #if defined(CONFIG_OF_ADDRESS) -int of_pci_get_host_bridge_resources(struct device *dev, +int devm_of_pci_get_host_bridge_resources(struct device *dev, unsigned char busno, unsigned char bus_max, struct list_head *resources, resource_size_t *io_base); #else -static inline int of_pci_get_host_bridge_resources(struct device *dev, +static inline int devm_of_pci_get_host_bridge_resources(struct device *dev, unsigned char busno, unsigned char bus_max, struct list_head *resources, resource_size_t *io_base) { -- cgit v1.2.3 From 01fcb7f777a9f5d216a1ff41228f15656e50fb63 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 15 May 2018 11:07:06 +0200 Subject: PCI: Add support for unbinding the generic PCI host controller Add support for unbinding the generic PCI host controller. This is particularly useful when working in virtual environments where the controller may come and go, but possibly not only there. Signed-off-by: Jan Kiszka Signed-off-by: Bjorn Helgaas CC: Will Deacon CC: Lorenzo Pieralisi --- include/linux/pci-ecam.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index baadad1aabbc..29efa09d686b 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -62,5 +62,6 @@ extern struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x */ /* for DT-based PCI controllers that support ECAM */ int pci_host_common_probe(struct platform_device *pdev, struct pci_ecam_ops *ops); +int pci_host_common_remove(struct platform_device *pdev); #endif #endif -- cgit v1.2.3 From 9c5587346490ad4355e8de6ae402b76e55c411d5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 30 May 2018 15:26:07 +0800 Subject: blk-mq: abstract out blk-mq-sched rq list iteration bio merge helper No functional changes in this patch, just a prep patch for utilizing this in an IO scheduler. Signed-off-by: Jens Axboe Reviewed-by: Omar Sandoval --- include/linux/blk-mq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ebc34a5686dc..fb355173f3c7 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -259,7 +259,8 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); - +bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, + struct bio *bio); bool blk_mq_queue_stopped(struct request_queue *q); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); -- cgit v1.2.3 From 79a3d60300fc28def9b58dc30d86274b47052422 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Wed, 30 May 2018 09:04:13 -0700 Subject: platform/chrome: Use to_cros_ec_dev more broadly Move to_cros_ec_dev macro to cros_ec.h and use it when the private ec object is needed from device object. Signed-off-by: Gwendal Grignou Reviewed-by: Enric Balletbo i Serra Signed-off-by: Benson Leung --- include/linux/mfd/cros_ec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 2d4e23c9ea0a..f09e9cf2e4ab 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -197,6 +197,8 @@ struct cros_ec_dev { u32 features[2]; }; +#define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev) + /** * cros_ec_suspend - Handle a suspend operation for the ChromeOS EC device * -- cgit v1.2.3 From 76c9dd9dbd6459f1faf2b10351eb3d3f90255fa1 Mon Sep 17 00:00:00 2001 From: David Lechner Date: Fri, 25 May 2018 13:11:47 -0500 Subject: clk: davinci: pll: allow dev == NULL This modifies the TI Davinci PLL clock driver to allow for the case when dev == NULL. On some (most) SoCs that use this driver, the PLL clock needs to be registered during early boot because it is used for clocksource/clkevent and there will be no platform device available. Signed-off-by: David Lechner Reviewed-by: Sekhar Nori Signed-off-by: Michael Turquette Link: lkml.kernel.org/r/20180525181150.17873-7-david@lechnology.com --- include/linux/clk/davinci.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 include/linux/clk/davinci.h (limited to 'include/linux') diff --git a/include/linux/clk/davinci.h b/include/linux/clk/davinci.h new file mode 100644 index 000000000000..ebdd9df1c0ef --- /dev/null +++ b/include/linux/clk/davinci.h @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Clock drivers for TI DaVinci PLL and PSC controllers + * + * Copyright (C) 2018 David Lechner + */ + +#ifndef __LINUX_CLK_DAVINCI_PLL_H___ +#define __LINUX_CLK_DAVINCI_PLL_H___ + +#include +#include + +/* function for registering clocks in early boot */ + +int da830_pll_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); +int da850_pll0_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); +int dm355_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); +int dm365_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); +int dm365_pll2_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); +int dm644x_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); +int dm646x_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); + +#endif /* __LINUX_CLK_DAVINCI_PLL_H___ */ -- cgit v1.2.3 From 043eaa70ad736380a631e820e32ad9176b020887 Mon Sep 17 00:00:00 2001 From: David Lechner Date: Fri, 25 May 2018 13:11:49 -0500 Subject: clk: davinci: psc: allow for dev == NULL On some davinci SoCs, we need to register the PSC clocks during early boot because they are needed for clocksource/clockevent. These changes allow for dev == NULL because in this case, we won't have a platform device for the clocks. Signed-off-by: David Lechner Reviewed-by: Sekhar Nori Signed-off-by: Michael Turquette Link: lkml.kernel.org/r/20180525181150.17873-9-david@lechnology.com --- include/linux/clk/davinci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/davinci.h b/include/linux/clk/davinci.h index ebdd9df1c0ef..62764c5cc86e 100644 --- a/include/linux/clk/davinci.h +++ b/include/linux/clk/davinci.h @@ -21,4 +21,9 @@ int dm365_pll2_init(struct device *dev, void __iomem *base, struct regmap *cfgch int dm644x_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); int dm646x_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); +int dm355_psc_init(struct device *dev, void __iomem *base); +int dm365_psc_init(struct device *dev, void __iomem *base); +int dm644x_psc_init(struct device *dev, void __iomem *base); +int dm646x_psc_init(struct device *dev, void __iomem *base); + #endif /* __LINUX_CLK_DAVINCI_PLL_H___ */ -- cgit v1.2.3 From 4eff0bebf4ed5ed6d1a4dffe7dfd420b270c229a Mon Sep 17 00:00:00 2001 From: David Lechner Date: Fri, 25 May 2018 13:11:50 -0500 Subject: clk: davinci: Fix link errors when not all SoCs are enabled This fixes linker errors due to undefined symbols when one or more of the TI DaVinci SoCs is not enabled in the kernel config. Signed-off-by: David Lechner Signed-off-by: Michael Turquette Link: lkml.kernel.org/r/20180525181150.17873-10-david@lechnology.com --- include/linux/clk/davinci.h | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk/davinci.h b/include/linux/clk/davinci.h index 62764c5cc86e..8a7b5cd7eac0 100644 --- a/include/linux/clk/davinci.h +++ b/include/linux/clk/davinci.h @@ -13,17 +13,28 @@ /* function for registering clocks in early boot */ +#ifdef CONFIG_ARCH_DAVINCI_DA830 int da830_pll_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); +#endif +#ifdef CONFIG_ARCH_DAVINCI_DA850 int da850_pll0_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); +#endif +#ifdef CONFIG_ARCH_DAVINCI_DM355 int dm355_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); +int dm355_psc_init(struct device *dev, void __iomem *base); +#endif +#ifdef CONFIG_ARCH_DAVINCI_DM365 int dm365_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); int dm365_pll2_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); -int dm644x_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); -int dm646x_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); - -int dm355_psc_init(struct device *dev, void __iomem *base); int dm365_psc_init(struct device *dev, void __iomem *base); +#endif +#ifdef CONFIG_ARCH_DAVINCI_DM644x +int dm644x_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); int dm644x_psc_init(struct device *dev, void __iomem *base); +#endif +#ifdef CONFIG_ARCH_DAVINCI_DM646x +int dm646x_pll1_init(struct device *dev, void __iomem *base, struct regmap *cfgchip); int dm646x_psc_init(struct device *dev, void __iomem *base); +#endif #endif /* __LINUX_CLK_DAVINCI_PLL_H___ */ -- cgit v1.2.3 From 0fc784fb09f6db8d6650aac137daa779da25c73b Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 30 May 2018 13:43:01 +0200 Subject: cpuidle: governors: Consolidate PM QoS handling There is some code duplication related to the PM QoS handling between the existing cpuidle governors, so move that code to a common helper function and call that from the governors. Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 1eefabf1621f..4325d6fdde9b 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -258,6 +258,7 @@ struct cpuidle_governor { #ifdef CONFIG_CPU_IDLE extern int cpuidle_register_governor(struct cpuidle_governor *gov); +extern int cpuidle_governor_latency_req(unsigned int cpu); #else static inline int cpuidle_register_governor(struct cpuidle_governor *gov) {return 0;} -- cgit v1.2.3 From 338aa96d5661048b3c0cafc6d91876025603cacf Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 20 May 2018 18:25:47 -0400 Subject: block: convert bounce, q->bio_split to bioset_init()/mempool_init() Convert the core block functionality to embedded bio sets. Reviewed-by: Christoph Hellwig Signed-off-by: Kent Overstreet Signed-off-by: Jens Axboe --- include/linux/bio.h | 5 +++++ include/linux/blkdev.h | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 98b175cc00d5..5e472fcafa24 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -760,6 +760,11 @@ struct biovec_slab { struct kmem_cache *slab; }; +static inline bool bioset_initialized(struct bio_set *bs) +{ + return bs->bio_slab != NULL; +} + /* * a small number of entries is fine, not going to be performance critical. * basically we just need to survive diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4efd9af62e25..bca3a92eb55f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -652,7 +652,7 @@ struct request_queue { struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; - struct bio_set *bio_split; + struct bio_set bio_split; #ifdef CONFIG_BLK_DEBUG_FS struct dentry *debugfs_dir; -- cgit v1.2.3 From 64c4bc4de79fec06bb46d9827e7c4df67a025590 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 20 May 2018 18:25:49 -0400 Subject: pktcdvd: convert to bioset_init()/mempool_init() Convert pktcdvd to embedded bio sets. Signed-off-by: Kent Overstreet Signed-off-by: Jens Axboe --- include/linux/pktcdvd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 93d142ad1528..174601554b06 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -186,7 +186,7 @@ struct pktcdvd_device sector_t current_sector; /* Keep track of where the elevator is */ atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */ /* needs to be run. */ - mempool_t *rb_pool; /* mempool for pkt_rb_node allocations */ + mempool_t rb_pool; /* mempool for pkt_rb_node allocations */ struct packet_iosched iosched; struct gendisk *disk; -- cgit v1.2.3 From dad08527525f9a8ac9c7f278864c65f94bc5e9b3 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 20 May 2018 18:25:58 -0400 Subject: block: Drop bioset_create() All users have been converted to bioset_init(), kill off the old API. Reviewed-by: Christoph Hellwig Signed-off-by: Kent Overstreet Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 5e472fcafa24..810a8bee8f85 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -410,14 +410,12 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors, return bio_split(bio, sectors, gfp, bs); } -extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); -extern void bioset_exit(struct bio_set *); -extern struct bio_set *bioset_create(unsigned int, unsigned int, int flags); enum { BIOSET_NEED_BVECS = BIT(0), BIOSET_NEED_RESCUER = BIT(1), }; -extern void bioset_free(struct bio_set *); +extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); +extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *); -- cgit v1.2.3 From 8c97a46af04b4f7c0a0dded031fef1806872e648 Mon Sep 17 00:00:00 2001 From: Martin Liu Date: Thu, 31 May 2018 00:31:36 +0800 Subject: driver core: hold dev's parent lock when needed SoC have internal I/O buses that can't be proved for devices. The devices on the buses can be accessed directly without additinal configuration required. This type of bus is represented as "simple-bus". In some platforms, we name "soc" with "simple-bus" attribute and many devices are hooked under it described in DT (device tree). In commit bf74ad5bc417 ("Hold the device's parent's lock during probe and remove") to solve USB subsystem lock sequence since USB device's characteristic. Thus "soc" needs to be locked whenever a device and driver's probing happen under "soc" bus. During this period, an async driver tries to probe a device which is under the "soc" bus would be blocked until previous driver finish the probing and release "soc" lock. And the next probing under the "soc" bus need to wait for async finish. Because of that, driver's async probe for init time improvement will be shadowed. Since many devices don't have USB devices' characteristic, they actually don't need parent's lock. Thus, we introduce a lock flag in bus_type struct and driver core would lock the parent lock base on the flag. For USB, we set this flag in usb_bus_type to keep original lock behavior in driver core. Async probe could have more benefit after this patch. Signed-off-by: Martin Liu Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 477956990f5e..beca424395dd 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -98,6 +98,8 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @lock_key: Lock class key for use by the lock validator * @force_dma: Assume devices on this bus should be set up by dma_configure() * even if DMA capability is not explicitly described by firmware. + * @need_parent_lock: When probing or removing a device on this bus, the + * device core should lock the device's parent. * * A bus is a channel between the processor and one or more devices. For the * purposes of the device model, all devices are connected via a bus, even if @@ -138,6 +140,7 @@ struct bus_type { struct lock_class_key lock_key; bool force_dma; + bool need_parent_lock; }; extern int __must_check bus_register(struct bus_type *bus); -- cgit v1.2.3 From 80ea09a002bf4384fda5f087b1b198b3a274f9da Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 17 May 2018 10:53:05 +0200 Subject: vfs: factor out inode_insert5() Split out common helper for race free insertion of an already allocated inode into the cache. Use this from iget5_locked() and insert_inode_locked4(). Make iget5_locked() use new_inode()/iput() instead of alloc_inode()/destroy_inode() directly. Also export to modules for use by filesystems which want to preallocate an inode before file/directory creation. Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 760d8da1b6c7..4f637a9b213d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2879,6 +2879,10 @@ extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); +extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, + int (*test)(struct inode *, void *), + int (*set)(struct inode *, void *), + void *data); extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); extern struct inode *find_inode_nowait(struct super_block *, -- cgit v1.2.3 From 25244227158e1502062041365a439a54cb8fe673 Mon Sep 17 00:00:00 2001 From: Nicolas Boichat Date: Mon, 28 May 2018 14:32:18 +0800 Subject: usb: hub: Per-port setting to use old enumeration scheme The "old" enumeration scheme is considerably faster (it takes ~244ms instead of ~356ms to get the descriptor). It is currently only possible to use the old scheme globally (/sys/module/usbcore/parameters/old_scheme_first), which is not desirable as the new scheme was introduced to increase compatibility with more devices. However, in our case, we care about time-to-active for a specific USB device (which we make the firmware for), on a specific port (that is pogo-pin based: not a standard USB port). This new sysfs option makes it possible to use the old scheme on a single port only. Signed-off-by: Nicolas Boichat Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index beffceec4915..2ade17992ed6 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -489,6 +489,13 @@ enum usb_port_connect_type { USB_PORT_NOT_USED, }; +/* + * USB port quirks. + */ + +/* For the given port, prefer the old (faster) enumeration scheme. */ +#define USB_PORT_QUIRK_OLD_SCHEME BIT(0) + /* * USB 2.0 Link Power Management (LPM) parameters. */ -- cgit v1.2.3 From aa071a92bbf09d993ff0dbf3b1f2b53ac93ad654 Mon Sep 17 00:00:00 2001 From: Nicolas Boichat Date: Mon, 28 May 2018 14:32:19 +0800 Subject: usb: hub: Per-port setting to reduce TRSTRCY to 10 ms Currently, the USB hub core waits for 50 ms after enumerating the device. This was added to help "some high speed devices" to enumerate (b789696af8 "[PATCH] USB: relax usbcore reset timings"). On some devices, the time-to-active is important, so we provide a per-port option to reduce the time to what the USB specification requires: 10 ms. Signed-off-by: Nicolas Boichat Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 2ade17992ed6..4cdd515a4385 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -496,6 +496,9 @@ enum usb_port_connect_type { /* For the given port, prefer the old (faster) enumeration scheme. */ #define USB_PORT_QUIRK_OLD_SCHEME BIT(0) +/* Decrease TRSTRCY to 10ms during device enumeration. */ +#define USB_PORT_QUIRK_FAST_ENUM BIT(1) + /* * USB 2.0 Link Power Management (LPM) parameters. */ -- cgit v1.2.3 From aa43457799f715d76cb77342baab0615877e2b8a Mon Sep 17 00:00:00 2001 From: Adam Manzanares Date: Tue, 22 May 2018 10:52:17 -0700 Subject: block: add ioprio_check_cap function Aio per command iopriority support introduces a second interface between userland and the kernel capable of passing iopriority. The aio interface also needs the ability to verify that the submitting context has sufficient privileges to submit IOPRIO_RT commands. This patch creates the ioprio_check_cap function to be used by the ioprio_set system call and also by the aio interface. Signed-off-by: Adam Manzanares Reviewed-by: Christoph Hellwig Reviewed-by: Jeff Moyer Signed-off-by: Al Viro --- include/linux/ioprio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index 627efac73e6d..4a28cec49ec3 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -77,4 +77,6 @@ extern int ioprio_best(unsigned short aprio, unsigned short bprio); extern int set_task_ioprio(struct task_struct *task, int ioprio); +extern int ioprio_check_cap(int ioprio); + #endif -- cgit v1.2.3 From fc28724d67c90ff48b976e0687caf79993160bed Mon Sep 17 00:00:00 2001 From: Adam Manzanares Date: Tue, 22 May 2018 10:52:18 -0700 Subject: fs: Convert kiocb rw_hint from enum to u16 In order to avoid kiocb bloat for per command iopriority support, rw_hint is converted from enum to a u16. Added a guard around ki_hint assignment. Signed-off-by: Adam Manzanares Signed-off-by: Al Viro --- include/linux/fs.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4b6045ebb2f2..b432fc3feb93 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -299,7 +299,7 @@ struct kiocb { void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); void *private; int ki_flags; - enum rw_hint ki_hint; + u16 ki_hint; } __randomize_layout; static inline bool is_sync_kiocb(struct kiocb *kiocb) @@ -1929,12 +1929,21 @@ static inline enum rw_hint file_write_hint(struct file *file) static inline int iocb_flags(struct file *file); +static inline u16 ki_hint_validate(enum rw_hint hint) +{ + typeof(((struct kiocb *)0)->ki_hint) max_hint = -1; + + if (hint <= max_hint) + return hint; + return 0; +} + static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = iocb_flags(filp), - .ki_hint = file_write_hint(filp), + .ki_hint = ki_hint_validate(file_write_hint(filp)), }; } -- cgit v1.2.3 From d9a08a9e616beeccdbd0e7262b7225ffdfa49e92 Mon Sep 17 00:00:00 2001 From: Adam Manzanares Date: Tue, 22 May 2018 10:52:19 -0700 Subject: fs: Add aio iopriority support This is the per-I/O equivalent of the ioprio_set system call. When IOCB_FLAG_IOPRIO is set on the iocb aio_flags field, then we set the newly added kiocb ki_ioprio field to the value in the iocb aio_reqprio field. This patch depends on block: add ioprio_check_cap function. Signed-off-by: Adam Manzanares Reviewed-by: Jeff Moyer Reviewed-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b432fc3feb93..eef9334b26d1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -36,6 +36,7 @@ #include #include #include +#include #include #include @@ -300,6 +301,7 @@ struct kiocb { void *private; int ki_flags; u16 ki_hint; + u16 ki_ioprio; /* See linux/ioprio.h */ } __randomize_layout; static inline bool is_sync_kiocb(struct kiocb *kiocb) @@ -1944,6 +1946,7 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) .ki_filp = filp, .ki_flags = iocb_flags(filp), .ki_hint = ki_hint_validate(file_write_hint(filp)), + .ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0), }; } -- cgit v1.2.3 From ba23cba9b3bdc967aabdc6ff1e3e9b11ce05bb4f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 30 May 2018 13:03:45 -0700 Subject: fs: allow per-device dax status checking for filesystems Change bdev_dax_supported so it takes a bdev parameter. This enables multi-device filesystems like xfs to check that a dax device can work for the particular filesystem. Once that's in place, actually fix all the parts of XFS where we need to be able to distinguish between datadev and rtdev. This patch fixes the problem where we screw up the dax support checking in xfs if the datadev and rtdev have different dax capabilities. Signed-off-by: Darrick J. Wong [rez: Re-added __bdev_dax_supported() for !CONFIG_FS_DAX cases] Signed-off-by: Ross Zwisler Reviewed-by: Eric Sandeen --- include/linux/dax.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index f9eb22ad341e..2a4f7295c12b 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -64,10 +64,10 @@ static inline bool dax_write_cache_enabled(struct dax_device *dax_dev) struct writeback_control; int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) -int __bdev_dax_supported(struct super_block *sb, int blocksize); -static inline int bdev_dax_supported(struct super_block *sb, int blocksize) +int __bdev_dax_supported(struct block_device *bdev, int blocksize); +static inline int bdev_dax_supported(struct block_device *bdev, int blocksize) { - return __bdev_dax_supported(sb, blocksize); + return __bdev_dax_supported(bdev, blocksize); } static inline struct dax_device *fs_dax_get_by_host(const char *host) @@ -84,7 +84,8 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc); #else -static inline int bdev_dax_supported(struct super_block *sb, int blocksize) +static inline int bdev_dax_supported(struct block_device *bdev, + int blocksize) { return -EOPNOTSUPP; } -- cgit v1.2.3 From 80660f20252d6f76c9f203874ad7c7a4a8508cf8 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 30 May 2018 13:03:46 -0700 Subject: dax: change bdev_dax_supported() to support boolean returns The function return values are confusing with the way the function is named. We expect a true or false return value but it actually returns 0/-errno. This makes the code very confusing. Changing the return values to return a bool where if DAX is supported then return true and no DAX support returns false. Signed-off-by: Dave Jiang Signed-off-by: Ross Zwisler Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/dax.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 2a4f7295c12b..c99692ddd4b5 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -64,8 +64,8 @@ static inline bool dax_write_cache_enabled(struct dax_device *dax_dev) struct writeback_control; int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) -int __bdev_dax_supported(struct block_device *bdev, int blocksize); -static inline int bdev_dax_supported(struct block_device *bdev, int blocksize) +bool __bdev_dax_supported(struct block_device *bdev, int blocksize); +static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) { return __bdev_dax_supported(bdev, blocksize); } @@ -84,10 +84,10 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc); #else -static inline int bdev_dax_supported(struct block_device *bdev, +static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) { - return -EOPNOTSUPP; + return false; } static inline struct dax_device *fs_dax_get_by_host(const char *host) -- cgit v1.2.3 From eff0e9e1078ea7dc1d794dc50e31baef984c46d7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 29 May 2018 13:11:05 +0100 Subject: arm/arm64: smccc: Add SMCCC-specific return codes We've so far used the PSCI return codes for SMCCC because they were extremely similar. But with the new ARM DEN 0070A specification, "NOT_REQUIRED" (-2) is clashing with PSCI's "PSCI_RET_INVALID_PARAMS". Let's bite the bullet and add SMCCC specific return codes. Users can be repainted as and when required. Acked-by: Will Deacon Reviewed-by: Mark Rutland Signed-off-by: Marc Zyngier Signed-off-by: Catalin Marinas --- include/linux/arm-smccc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index a031897fca76..c89da86de99f 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -291,5 +291,10 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, */ #define arm_smccc_1_1_hvc(...) __arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__) +/* Return codes defined in ARM DEN 0070A */ +#define SMCCC_RET_SUCCESS 0 +#define SMCCC_RET_NOT_SUPPORTED -1 +#define SMCCC_RET_NOT_REQUIRED -2 + #endif /*__ASSEMBLY__*/ #endif /*__LINUX_ARM_SMCCC_H*/ -- cgit v1.2.3 From 8e2906245f1e3b0d027169d9f2e55ce0548cb96e Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 29 May 2018 13:11:06 +0100 Subject: arm64: Call ARCH_WORKAROUND_2 on transitions between EL0 and EL1 In order for the kernel to protect itself, let's call the SSBD mitigation implemented by the higher exception level (either hypervisor or firmware) on each transition between userspace and kernel. We must take the PSCI conduit into account in order to target the right exception level, hence the introduction of a runtime patching callback. Reviewed-by: Mark Rutland Reviewed-by: Julien Grall Acked-by: Will Deacon Signed-off-by: Marc Zyngier Signed-off-by: Catalin Marinas --- include/linux/arm-smccc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index c89da86de99f..ca1d2cc2cdfa 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -80,6 +80,11 @@ ARM_SMCCC_SMC_32, \ 0, 0x8000) +#define ARM_SMCCC_ARCH_WORKAROUND_2 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x7fff) + #ifndef __ASSEMBLY__ #include -- cgit v1.2.3 From 868c2392a700fc1e72fb1bc044b7cceecd4f095c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 22 May 2018 11:09:54 +0200 Subject: nvme.h: untangle AEN notice definitions Stop including the event type in the definitions for the notice type. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Reviewed-by: Johannes Thumshirn --- include/linux/nvme.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4112e2bd747f..c37103a4ad38 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -436,10 +436,14 @@ enum { enum { NVME_AER_ERROR = 0, NVME_AER_SMART = 1, + NVME_AER_NOTICE = 2, NVME_AER_CSS = 6, NVME_AER_VS = 7, - NVME_AER_NOTICE_NS_CHANGED = 0x0002, - NVME_AER_NOTICE_FW_ACT_STARTING = 0x0102, +}; + +enum { + NVME_AER_NOTICE_NS_CHANGED = 0x00, + NVME_AER_NOTICE_FW_ACT_STARTING = 0x01, }; struct nvme_lba_range_type { -- cgit v1.2.3 From b3984e064ec15aa349a635affd70d16eedbb539b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 May 2018 17:18:33 +0200 Subject: nvme.h: add the changed namespace list log Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Reviewed-by: Johannes Thumshirn --- include/linux/nvme.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index c37103a4ad38..7ce0f3cf4409 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -751,6 +751,7 @@ enum { NVME_LOG_ERROR = 0x01, NVME_LOG_SMART = 0x02, NVME_LOG_FW_SLOT = 0x03, + NVME_LOG_CHANGED_NS = 0x04, NVME_LOG_CMD_EFFECTS = 0x05, NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, @@ -759,6 +760,8 @@ enum { NVME_FWACT_ACTV = (2 << 3), }; +#define NVME_MAX_CHANGED_NAMESPACES 1024 + struct nvme_identify { __u8 opcode; __u8 flags; -- cgit v1.2.3 From 32d26a685c1802a0e485bd674e7dd038e88019f7 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Tue, 29 May 2018 02:31:24 -0700 Subject: qed*: Add link change count value to ethtool statistics display. This patch adds driver changes for capturing the link change count in ethtool statistics display. Please consider applying this to "net-next". Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index ac991a3b8f03..b4040023cbfb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1180,6 +1180,7 @@ struct qed_eth_stats_common { u64 tx_mac_mc_packets; u64 tx_mac_bc_packets; u64 tx_mac_ctrl_frames; + u64 link_change_count; }; struct qed_eth_stats_bb { -- cgit v1.2.3 From ead9ad7253f4296ba8cd3eb930f06a74924700a9 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 30 Apr 2018 14:31:30 +1000 Subject: rculist: add list_for_each_entry_from_rcu() list_for_each_entry_from_rcu() is an RCU version of list_for_each_entry_from(). It walks a linked list under rcu protection, from a given start point. It is similar to list_for_each_entry_continue_rcu() but starts *at* the given position rather than *after* it. Naturally, the start point must be known to be in the list. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/rculist.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 127f534fec94..36df6ccbc874 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -403,6 +403,19 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) +/** + * list_for_each_entry_from_rcu - iterate over a list from current point + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_node within the struct. + * + * Iterate over the tail of a list starting from a given position, + * which must have been in the list when the RCU read lock was taken. + */ +#define list_for_each_entry_from_rcu(pos, head, member) \ + for (; &(pos)->member != (head); \ + pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) + /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. -- cgit v1.2.3 From fb91fb0ee7b266ed0344515c048f57ac65cdb4b4 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 4 May 2018 16:22:48 -0400 Subject: NFS: Move call to nfs4_state_protect_write() to nfs4_write_setup() This doesn't really need to be in the generic NFS client code, and I think it makes more sense to keep the v4 code in one place. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 34d28564ecf3..1009269e1a49 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1620,7 +1620,8 @@ struct nfs_rpc_ops { struct nfs_pgio_header *); void (*read_setup)(struct nfs_pgio_header *, struct rpc_message *); int (*read_done)(struct rpc_task *, struct nfs_pgio_header *); - void (*write_setup)(struct nfs_pgio_header *, struct rpc_message *); + void (*write_setup)(struct nfs_pgio_header *, struct rpc_message *, + struct rpc_clnt **); int (*write_done)(struct rpc_task *, struct nfs_pgio_header *); void (*commit_setup) (struct nfs_commit_data *, struct rpc_message *); void (*commit_rpc_prepare)(struct rpc_task *, struct nfs_commit_data *); -- cgit v1.2.3 From e9ae1ee2b2ace7dcc37bc4e486b4410e7702ae57 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 4 May 2018 16:22:49 -0400 Subject: NFS: Move call to nfs4_state_protect() to nfs4_commit_setup() Rather than doing this in the generic NFS client code. Let's put this with the other v4 stuff so it's all in one place. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 1009269e1a49..52b481dfd61e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1623,7 +1623,8 @@ struct nfs_rpc_ops { void (*write_setup)(struct nfs_pgio_header *, struct rpc_message *, struct rpc_clnt **); int (*write_done)(struct rpc_task *, struct nfs_pgio_header *); - void (*commit_setup) (struct nfs_commit_data *, struct rpc_message *); + void (*commit_setup) (struct nfs_commit_data *, struct rpc_message *, + struct rpc_clnt **); void (*commit_rpc_prepare)(struct rpc_task *, struct nfs_commit_data *); int (*commit_done) (struct rpc_task *, struct nfs_commit_data *); int (*lock)(struct file *, int, struct file_lock *); -- cgit v1.2.3 From ed7e9ad0908a8c2a502f49ceed940d0ce122fe8b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 30 May 2018 16:11:52 -0400 Subject: NFSv4: Fix sillyrename to return the delegation when appropriate Ensure that we pass down the inode of the file being deleted so that we can return any delegation being held. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 52b481dfd61e..d3cefe57c2a3 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1591,7 +1591,7 @@ struct nfs_rpc_ops { int (*create) (struct inode *, struct dentry *, struct iattr *, int); int (*remove) (struct inode *, struct dentry *); - void (*unlink_setup) (struct rpc_message *, struct dentry *); + void (*unlink_setup) (struct rpc_message *, struct dentry *, struct inode *); void (*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *); int (*unlink_done) (struct rpc_task *, struct inode *); void (*rename_setup) (struct rpc_message *msg, -- cgit v1.2.3 From 808ba32abe84b74abef5eb7507b8031f65b8221d Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Tue, 4 Oct 2016 15:02:21 -0400 Subject: pnfs: Store return value of decode_layoutget for later processing This will be needed to seperate return value of OPEN and LAYOUTGET when they are combined into a single RPC. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index d3cefe57c2a3..d3aa5eaf99a7 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -259,6 +259,7 @@ struct nfs4_layoutget_args { struct nfs4_layoutget_res { struct nfs4_sequence_res seq_res; + int status; __u32 return_on_close; struct pnfs_layout_range range; __u32 type; -- cgit v1.2.3 From 56f487f8c8fc5d6e582b79a86fc132d050129e15 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Wed, 21 Sep 2016 11:43:41 -0400 Subject: pnfs: Add conditional encode/decode of LAYOUTGET within OPEN compound Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index d3aa5eaf99a7..bc235e50415f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -436,6 +436,7 @@ struct nfs_openargs { enum createmode4 createmode; const struct nfs4_label *label; umode_t umask; + struct nfs4_layoutget_args *lg_args; }; struct nfs_openres { @@ -458,6 +459,7 @@ struct nfs_openres { __u32 access_request; __u32 access_supported; __u32 access_result; + struct nfs4_layoutget_res *lg_res; }; /* -- cgit v1.2.3 From 6e01260ceeca299b82d466660935534c5c909d54 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Tue, 4 Oct 2016 15:26:41 -0400 Subject: pnfs: Stop attempting LAYOUTGET on OPEN on failure Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 4e735be53e70..2c18d618604e 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -235,6 +235,7 @@ struct nfs_server { #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) /* #define NFS_CAP_CHANGE_ATTR (1U << 5) */ +#define NFS_CAP_LGOPEN (1U << 5) #define NFS_CAP_FILEID (1U << 6) #define NFS_CAP_MODE (1U << 7) #define NFS_CAP_NLINK (1U << 8) -- cgit v1.2.3 From c49b5209f99abe082d3d4cd94f0ad924baea34ed Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Wed, 5 Oct 2016 09:37:12 -0400 Subject: pnfs: Add barrier to prevent lgopen using LAYOUTGET during recall Since the LAYOUTGET on OPEN can be sent without prior inode information, existing methods to prevent LAYOUTGET from being sent while processing CB_LAYOUTRECALL don't work. Track if a recall occurred while LAYOUTGET was being sent, and if so ignore the results. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + include/linux/nfs_xdr.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 2c18d618604e..74ae3e1d19a0 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -28,6 +28,7 @@ struct nfs41_impl_id; struct nfs_client { refcount_t cl_count; atomic_t cl_mds_count; + seqcount_t cl_callback_count; int cl_cons_state; /* current construction state (-ve: init error) */ #define NFS_CS_READY 0 /* ready to be used */ #define NFS_CS_INITING 1 /* busy initialising */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index bc235e50415f..09dc14ac5804 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -271,6 +271,7 @@ struct nfs4_layoutget { struct nfs4_layoutget_args args; struct nfs4_layoutget_res res; struct rpc_cred *cred; + unsigned callback_count; gfp_t gfp_flags; }; -- cgit v1.2.3 From 1865ea9adbfaf341c5cd5d8f7d384f19948b2fe9 Mon Sep 17 00:00:00 2001 From: Ilan Tayari Date: Wed, 30 May 2018 10:59:49 -0700 Subject: net/mlx5: Add temperature warning event to log Temperature warning event is sent by FW to indicate high temperature as detected by one of the sensors on the board. Add handling of this event by writing the numbers of the alert sensors to the kernel log. Signed-off-by: Ilan Tayari Signed-off-by: Adi Nissim Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 7 +++++++ include/linux/mlx5/mlx5_ifc.h | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index db0332a6d23c..c1095e08f0c8 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -314,6 +314,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_PORT_CHANGE = 0x09, MLX5_EVENT_TYPE_GPIO_EVENT = 0x15, MLX5_EVENT_TYPE_PORT_MODULE_EVENT = 0x16, + MLX5_EVENT_TYPE_TEMP_WARN_EVENT = 0x17, MLX5_EVENT_TYPE_REMOTE_CONFIG = 0x19, MLX5_EVENT_TYPE_GENERAL_EVENT = 0x22, MLX5_EVENT_TYPE_PPS_EVENT = 0x25, @@ -626,6 +627,11 @@ struct mlx5_eqe_dct { __be32 dctn; }; +struct mlx5_eqe_temp_warning { + __be64 sensor_warning_msb; + __be64 sensor_warning_lsb; +} __packed; + union ev_data { __be32 raw[7]; struct mlx5_eqe_cmd cmd; @@ -642,6 +648,7 @@ union ev_data { struct mlx5_eqe_port_module port_module; struct mlx5_eqe_pps pps; struct mlx5_eqe_dct dct; + struct mlx5_eqe_temp_warning temp_warning; } __packed; struct mlx5_eqe { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 05b480fae27d..ca6c0dfb5ffe 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -912,7 +912,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_msg[0x5]; u8 reserved_at_1c8[0x4]; u8 max_tc[0x4]; - u8 reserved_at_1d0[0x1]; + u8 temp_warn_event[0x1]; u8 dcbx[0x1]; u8 general_notification_event[0x1]; u8 reserved_at_1d3[0x2]; -- cgit v1.2.3 From 1f0cf89b09305743fca5898660a7be83aab38a74 Mon Sep 17 00:00:00 2001 From: Ilan Tayari Date: Wed, 30 May 2018 10:59:50 -0700 Subject: net/mlx5: Add FPGA QP error event The FPGA queue pair (QP) event fires whenever a QP on the FPGA transitions to the error state. At this stage, this event is unrecoverable, it may become recoverable in the future. Signed-off-by: Ilan Tayari Signed-off-by: Adi Nissim Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 1 + include/linux/mlx5/mlx5_ifc.h | 1 + include/linux/mlx5/mlx5_ifc_fpga.h | 16 ++++++++++++++++ 3 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index c1095e08f0c8..0f006cf8343d 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -331,6 +331,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_DCT_DRAINED = 0x1c, MLX5_EVENT_TYPE_FPGA_ERROR = 0x20, + MLX5_EVENT_TYPE_FPGA_QP_ERROR = 0x21, }; enum { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ca6c0dfb5ffe..8e0b8865f91e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -60,6 +60,7 @@ enum { MLX5_EVENT_TYPE_CODING_COMMAND_INTERFACE_COMPLETION = 0xa, MLX5_EVENT_TYPE_CODING_PAGE_REQUEST = 0xb, MLX5_EVENT_TYPE_CODING_FPGA_ERROR = 0x20, + MLX5_EVENT_TYPE_CODING_FPGA_QP_ERROR = 0x21 }; enum { diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index 193091537cb6..64d0f40d4cc3 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -470,6 +470,22 @@ struct mlx5_ifc_ipsec_counters_bits { u8 dropped_cmd[0x40]; }; +enum { + MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RETRY_COUNTER_EXPIRED = 0x1, + MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RNR_EXPIRED = 0x2, +}; + +struct mlx5_ifc_fpga_qp_error_event_bits { + u8 reserved_at_0[0x40]; + + u8 reserved_at_40[0x18]; + u8 syndrome[0x8]; + + u8 reserved_at_60[0x60]; + + u8 reserved_at_c0[0x8]; + u8 fpga_qpn[0x18]; +}; enum mlx5_ifc_fpga_ipsec_response_syndrome { MLX5_FPGA_IPSEC_RESPONSE_SUCCESS = 0, MLX5_FPGA_IPSEC_RESPONSE_ILLEGAL_REQUEST = 1, -- cgit v1.2.3 From f0907827a8a9152aedac2833ed1b674a7b2a44f2 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 8 May 2018 00:36:27 +0200 Subject: compiler.h: enable builtin overflow checkers and add fallback code This adds wrappers for the __builtin overflow checkers present in gcc 5.1+ as well as fallback implementations for earlier compilers. It's not that easy to implement the fully generic __builtin_X_overflow(T1 a, T2 b, T3 *d) in macros, so the fallback code assumes that T1, T2 and T3 are the same. We obviously don't want the wrappers to have different semantics depending on $GCC_VERSION, so we also insist on that even when using the builtins. There are a few problems with the 'a+b < a' idiom for checking for overflow: For signed types, it relies on undefined behaviour and is not actually complete (it doesn't check underflow; e.g. INT_MIN+INT_MIN == 0 isn't caught). Due to type promotion it is wrong for all types (signed and unsigned) narrower than int. Similarly, when a and b does not have the same type, there are subtle cases like u32 a; if (a + sizeof(foo) < a) return -EOVERFLOW; a += sizeof(foo); where the test is always false on 64 bit platforms. Add to that that it is not always possible to determine the types involved at a glance. The new overflow.h is somewhat bulky, but that's mostly a result of trying to be type-generic, complete (e.g. catching not only overflow but also signed underflow) and not relying on undefined behaviour. Linus is of course right [1] that for unsigned subtraction a-b, the right way to check for overflow (underflow) is "b > a" and not "__builtin_sub_overflow(a, b, &d)", but that's just one out of six cases covered here, and included mostly for completeness. So is it worth it? I think it is, if nothing else for the documentation value of seeing if (check_add_overflow(a, b, &d)) return -EGOAWAY; do_stuff_with(d); instead of the open-coded (and possibly wrong and/or incomplete and/or UBsan-tickling) if (a+b < a) return -EGOAWAY; do_stuff_with(a+b); While gcc does recognize the 'a+b < a' idiom for testing unsigned add overflow, it doesn't do nearly as good for unsigned multiplication (there's also no single well-established idiom). So using check_mul_overflow in kcalloc and friends may also make gcc generate slightly better code. [1] https://lkml.org/lkml/2015/11/2/658 Signed-off-by: Rasmus Villemoes Signed-off-by: Kees Cook --- include/linux/compiler-clang.h | 14 +++ include/linux/compiler-gcc.h | 4 + include/linux/compiler-intel.h | 4 + include/linux/overflow.h | 205 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 227 insertions(+) create mode 100644 include/linux/overflow.h (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 7d98e263e048..7087446c24c8 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -32,3 +32,17 @@ #ifdef __noretpoline #undef __noretpoline #endif + +/* + * Not all versions of clang implement the the type-generic versions + * of the builtin overflow checkers. Fortunately, clang implements + * __has_builtin allowing us to avoid awkward version + * checks. Unfortunately, we don't know which version of gcc clang + * pretends to be, so the macro may or may not be defined. + */ +#undef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW +#if __has_builtin(__builtin_mul_overflow) && \ + __has_builtin(__builtin_add_overflow) && \ + __has_builtin(__builtin_sub_overflow) +#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 +#endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index b4bf73f5e38f..f1a7492a5cc8 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -343,3 +343,7 @@ * code */ #define uninitialized_var(x) x = x + +#if GCC_VERSION >= 50100 +#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 +#endif diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index bfa08160db3a..547cdc920a3c 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -44,3 +44,7 @@ #define __builtin_bswap16 _bswap16 #endif +/* + * icc defines __GNUC__, but does not implement the builtin overflow checkers. + */ +#undef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW diff --git a/include/linux/overflow.h b/include/linux/overflow.h new file mode 100644 index 000000000000..c8890ec358a7 --- /dev/null +++ b/include/linux/overflow.h @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +#ifndef __LINUX_OVERFLOW_H +#define __LINUX_OVERFLOW_H + +#include + +/* + * In the fallback code below, we need to compute the minimum and + * maximum values representable in a given type. These macros may also + * be useful elsewhere, so we provide them outside the + * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. + * + * It would seem more obvious to do something like + * + * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) + * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) + * + * Unfortunately, the middle expressions, strictly speaking, have + * undefined behaviour, and at least some versions of gcc warn about + * the type_max expression (but not if -fsanitize=undefined is in + * effect; in that case, the warning is deferred to runtime...). + * + * The slightly excessive casting in type_min is to make sure the + * macros also produce sensible values for the exotic type _Bool. [The + * overflow checkers only almost work for _Bool, but that's + * a-feature-not-a-bug, since people shouldn't be doing arithmetic on + * _Bools. Besides, the gcc builtins don't allow _Bool* as third + * argument.] + * + * Idea stolen from + * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html - + * credit to Christian Biere. + */ +#define is_signed_type(type) (((type)(-1)) < (type)1) +#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type))) +#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) +#define type_min(T) ((T)((T)-type_max(T)-(T)1)) + + +#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW +/* + * For simplicity and code hygiene, the fallback code below insists on + * a, b and *d having the same type (similar to the min() and max() + * macros), whereas gcc's type-generic overflow checkers accept + * different types. Hence we don't just make check_add_overflow an + * alias for __builtin_add_overflow, but add type checks similar to + * below. + */ +#define check_add_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + __builtin_add_overflow(__a, __b, __d); \ +}) + +#define check_sub_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + __builtin_sub_overflow(__a, __b, __d); \ +}) + +#define check_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + __builtin_mul_overflow(__a, __b, __d); \ +}) + +#else + + +/* Checking for unsigned overflow is relatively easy without causing UB. */ +#define __unsigned_add_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a + __b; \ + *__d < __a; \ +}) +#define __unsigned_sub_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a - __b; \ + __a < __b; \ +}) +/* + * If one of a or b is a compile-time constant, this avoids a division. + */ +#define __unsigned_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a * __b; \ + __builtin_constant_p(__b) ? \ + __b > 0 && __a > type_max(typeof(__a)) / __b : \ + __a > 0 && __b > type_max(typeof(__b)) / __a; \ +}) + +/* + * For signed types, detecting overflow is much harder, especially if + * we want to avoid UB. But the interface of these macros is such that + * we must provide a result in *d, and in fact we must produce the + * result promised by gcc's builtins, which is simply the possibly + * wrapped-around value. Fortunately, we can just formally do the + * operations in the widest relevant unsigned type (u64) and then + * truncate the result - gcc is smart enough to generate the same code + * with and without the (u64) casts. + */ + +/* + * Adding two signed integers can overflow only if they have the same + * sign, and overflow has happened iff the result has the opposite + * sign. + */ +#define __signed_add_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a + (u64)__b; \ + (((~(__a ^ __b)) & (*__d ^ __a)) \ + & type_min(typeof(__a))) != 0; \ +}) + +/* + * Subtraction is similar, except that overflow can now happen only + * when the signs are opposite. In this case, overflow has happened if + * the result has the opposite sign of a. + */ +#define __signed_sub_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a - (u64)__b; \ + ((((__a ^ __b)) & (*__d ^ __a)) \ + & type_min(typeof(__a))) != 0; \ +}) + +/* + * Signed multiplication is rather hard. gcc always follows C99, so + * division is truncated towards 0. This means that we can write the + * overflow check like this: + * + * (a > 0 && (b > MAX/a || b < MIN/a)) || + * (a < -1 && (b > MIN/a || b < MAX/a) || + * (a == -1 && b == MIN) + * + * The redundant casts of -1 are to silence an annoying -Wtype-limits + * (included in -Wextra) warning: When the type is u8 or u16, the + * __b_c_e in check_mul_overflow obviously selects + * __unsigned_mul_overflow, but unfortunately gcc still parses this + * code and warns about the limited range of __b. + */ + +#define __signed_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + typeof(a) __tmax = type_max(typeof(a)); \ + typeof(a) __tmin = type_min(typeof(a)); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a * (u64)__b; \ + (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ + (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ + (__b == (typeof(__b))-1 && __a == __tmin); \ +}) + + +#define check_add_overflow(a, b, d) \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_add_overflow(a, b, d), \ + __unsigned_add_overflow(a, b, d)) + +#define check_sub_overflow(a, b, d) \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_sub_overflow(a, b, d), \ + __unsigned_sub_overflow(a, b, d)) + +#define check_mul_overflow(a, b, d) \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_mul_overflow(a, b, d), \ + __unsigned_mul_overflow(a, b, d)) + + +#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ + +#endif /* __LINUX_OVERFLOW_H */ -- cgit v1.2.3 From 09ea0dfbf972c63dfea8cf46f2fb67f39e4d833b Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Tue, 29 May 2018 15:59:18 +0200 Subject: dma-buf: make map_atomic and map function pointers optional So drivers don't need dummy functions just returning NULL. Cc: Daniel Vetter Signed-off-by: Gerd Hoffmann Reviewed-by: Daniel Vetter Reviewed-by: Oleksandr Andrushchenko Link: http://patchwork.freedesktop.org/patch/msgid/20180529135918.19729-1-kraxel@redhat.com --- include/linux/dma-buf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 085db2fee2d7..88917fa796e4 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -39,12 +39,12 @@ struct dma_buf_attachment; /** * struct dma_buf_ops - operations possible on struct dma_buf - * @map_atomic: maps a page from the buffer into kernel address + * @map_atomic: [optional] maps a page from the buffer into kernel address * space, users may not block until the subsequent unmap call. * This callback must not sleep. * @unmap_atomic: [optional] unmaps a atomically mapped page from the buffer. * This Callback must not sleep. - * @map: maps a page from the buffer into kernel address space. + * @map: [optional] maps a page from the buffer into kernel address space. * @unmap: [optional] unmaps a page from the buffer. * @vmap: [optional] creates a virtual mapping for the buffer into kernel * address space. Same restrictions as for vmap and friends apply. -- cgit v1.2.3 From a654de8fdc1815676ab750e70cab231fc814c29f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 30 May 2018 20:18:57 +0200 Subject: netfilter: nf_tables: fix chain dependency validation The following ruleset: add table ip filter add chain ip filter input { type filter hook input priority 4; } add chain ip filter ap add rule ip filter input jump ap add rule ip filter ap masquerade results in a panic, because the masquerade extension should be rejected from the filter chain. The existing validation is missing a chain dependency check when the rule is added to the non-base chain. This patch fixes the problem by walking down the rules from the basechains, searching for either immediate or lookup expressions, then jumping to non-base chains and again walking down the rules to perform the expression validation, so we make sure the full ruleset graph is validated. This is done only once from the commit phase, in case of problem, we abort the transaction and perform fine grain validation for error reporting. This patch requires 003087911af2 ("netfilter: nfnetlink: allow commit to fail") to achieve this behaviour. This patch also adds a cleanup callback to nfnl batch interface to reset the validate state from the exit path. As a result of this patch, nf_tables_check_loops() doesn't use ->validate to check for loops, instead it just checks for immediate expressions. Reported-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 34551f8aaf9d..3ecc3050be0e 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -31,6 +31,7 @@ struct nfnetlink_subsystem { const struct nfnl_callback *cb; /* callback for individual types */ int (*commit)(struct net *net, struct sk_buff *skb); int (*abort)(struct net *net, struct sk_buff *skb); + void (*cleanup)(struct net *net); bool (*valid_genid)(struct net *net, u32 genid); }; -- cgit v1.2.3 From aafd3afe9d2e731f50477cd1b4db7efa86d2637a Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 25 May 2018 17:34:00 +0200 Subject: nvme.h: add AEN configuration symbols Signed-off-by: Hannes Reinecke [hch: split from a larger patch] Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Reviewed-by: Johannes Thumshirn --- include/linux/nvme.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 7ce0f3cf4409..2950ce957656 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -446,6 +446,11 @@ enum { NVME_AER_NOTICE_FW_ACT_STARTING = 0x01, }; +enum { + NVME_AEN_CFG_NS_ATTR = 1 << 8, + NVME_AEN_CFG_FW_ACT = 1 << 9, +}; + struct nvme_lba_range_type { __u8 type; __u8 attributes; -- cgit v1.2.3 From f567c71f4f91d173795a2f46d6fc493387ce084d Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 15 May 2018 17:08:21 +0200 Subject: mtd: nand: Pass mode information to nand_page_io_req The NAND sub-layers are likely to need the MTD_OPS_XXX mode information in order to decide if they should enable/disable ECC or how they should place the OOB bytes in the provided OOB buffer. Add a field to nand_page_io_req to pass this information. Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal Tested-by: Frieder Schrempf Reviewed-by: Frieder Schrempf --- include/linux/mtd/nand.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 792ea5c26329..abe975c87b90 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -86,6 +86,7 @@ struct nand_pos { * @ooboffs: the OOB offset within the page * @ooblen: the number of OOB bytes to read from/write to this page * @oobbuf: buffer to store OOB data in or get OOB data from + * @mode: one of the %MTD_OPS_XXX mode * * This object is used to pass per-page I/O requests to NAND sub-layers. This * way all useful information are already formatted in a useful way and @@ -106,6 +107,7 @@ struct nand_page_io_req { const void *out; void *in; } oobbuf; + int mode; }; /** @@ -599,6 +601,7 @@ static inline void nanddev_io_iter_init(struct nand_device *nand, { struct mtd_info *mtd = nanddev_to_mtd(nand); + iter->req.mode = req->mode; iter->req.dataoffs = nanddev_offs_to_pos(nand, offs, &iter->req.pos); iter->req.ooboffs = req->ooboffs; iter->oobbytes_per_page = mtd_oobavail(mtd, req); -- cgit v1.2.3 From a8a275c9c2fb6bc9b45ad3e4187469726e2af7d1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 31 May 2018 19:11:37 +0200 Subject: block: unexport elevator_init/exit These are only used by the block core. Also move the declarations to block/blk.h. Reported-by: Damien Le Moal Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Tested-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/elevator.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 6d9e230dffd2..a02deea30185 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -218,8 +218,6 @@ extern void elv_unregister(struct elevator_type *); extern ssize_t elv_iosched_show(struct request_queue *, char *); extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); -extern int elevator_init(struct request_queue *, char *); -extern void elevator_exit(struct request_queue *, struct elevator_queue *); extern bool elv_bio_merge_ok(struct request *, struct bio *); extern struct elevator_queue *elevator_alloc(struct request_queue *, struct elevator_type *); -- cgit v1.2.3 From a7c9e9109ca1142f33b882615cc5fa048e07f3ea Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Javier=20Gonz=C3=A1lez?= Date: Fri, 1 Jun 2018 15:04:24 +0200 Subject: lightnvm: pass flag on graceful teardown to targets MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If the namespace is unregistered before the LightNVM target is removed (e.g., on hot unplug) it is too late for the target to store any metadata on the device - any attempt to write to the device will fail. In this case, pass on a "gracefull teardown" flag to the target to let it know when this happens. In the case of pblk, we pad the open line (close all open chunks) to improve data retention. In the event of an ungraceful shutdown, avoid this part and just clean up. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 6e0859b9d4d2..e9e0d1c7eaf5 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -489,7 +489,7 @@ typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, int flags); -typedef void (nvm_tgt_exit_fn)(void *); +typedef void (nvm_tgt_exit_fn)(void *, bool); typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *); typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *); -- cgit v1.2.3 From 27d036e33237e49801780eb703ea38dad5449e12 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 29 May 2018 15:14:07 +0300 Subject: mm: Remove return value of zap_vma_ptes() All callers of zap_vma_ptes() are not interested in the return value of that function, so let's simplify its interface and drop the return value. Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mm.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1ac1f06a4be6..edf44265c752 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -379,7 +379,7 @@ enum page_entry_size { /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer - * to the functions called when a no-page or a wp-page exception occurs. + * to the functions called when a no-page or a wp-page exception occurs. */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); @@ -1267,10 +1267,10 @@ struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); -int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, - unsigned long size); +void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, + unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, - unsigned long size); + unsigned long size); void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); -- cgit v1.2.3 From 1499fa809e9e6713952ef84a7e9d51606881681f Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Thu, 19 Apr 2018 00:49:58 +0530 Subject: kvm: Change return type to vm_fault_t Use new return type vm_fault_t for fault handler. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. commit 1c8f422059ae ("mm: change return type to vm_fault_t") Signed-off-by: Souptick Joarder Reviewed-by: Matthew Wilcox Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b81769a5a2b7..bca28637bcd4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -739,7 +739,7 @@ long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); -int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf); +vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf); int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext); -- cgit v1.2.3 From d1e5b0e98ea27b4f17871dc4e8ea4b0447e35221 Mon Sep 17 00:00:00 2001 From: Marc Orr Date: Tue, 15 May 2018 04:37:37 -0700 Subject: kvm: Make VM ioctl do valloc for some archs The kvm struct has been bloating. For example, it's tens of kilo-bytes for x86, which turns out to be a large amount of memory to allocate contiguously via kzalloc. Thus, this patch does the following: 1. Uses architecture-specific routines to allocate the kvm struct via vzalloc for x86. 2. Switches arm to __KVM_HAVE_ARCH_VM_ALLOC so that it can use vzalloc when has_vhe() is true. Other architectures continue to default to kalloc, as they have a dependency on kalloc or have a small-enough struct kvm. Signed-off-by: Marc Orr Reviewed-by: Marc Zyngier Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bca28637bcd4..4ee7bc548a83 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -811,6 +812,10 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); #ifndef __KVM_HAVE_ARCH_VM_ALLOC +/* + * All architectures that want to use vzalloc currently also + * need their own kvm_arch_alloc_vm implementation. + */ static inline struct kvm *kvm_arch_alloc_vm(void) { return kzalloc(sizeof(struct kvm), GFP_KERNEL); -- cgit v1.2.3 From 0aa69fd32a5f766e997ca8ab4723c5a1146efa8b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 1 Jun 2018 09:03:05 -0700 Subject: block: add a lower-level bio_add_page interface For the upcoming removal of buffer heads in XFS we need to keep track of the number of outstanding writeback requests per page. For this we need to know if bio_add_page merged a region with the previous bvec or not. Instead of adding additional arguments this refactors bio_add_page to be implemented using three lower level helpers which users like XFS can use directly if they care about the merge decisions. Signed-off-by: Christoph Hellwig Reviewed-by: Jens Axboe Reviewed-by: Ming Lei Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/bio.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index ce547a25e8ae..3e73c8bc25ea 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -123,6 +123,11 @@ static inline void *bio_data(struct bio *bio) return NULL; } +static inline bool bio_full(struct bio *bio) +{ + return bio->bi_vcnt >= bio->bi_max_vecs; +} + /* * will die */ @@ -470,6 +475,10 @@ void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); +bool __bio_try_merge_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int off); +void __bio_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); struct rq_map_data; extern struct bio *bio_map_user_iov(struct request_queue *, -- cgit v1.2.3 From 19319b53210c6b89c375cf395c08f156cccd83ea Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 1 Jun 2018 09:03:06 -0700 Subject: iomap: inline data should be an iomap type, not a flag Inline data is fundamentally different from our normal mapped case in that it doesn't even have a block address. So instead of having a flag for it it should be an entirely separate iomap range type. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 4bd87294219a..8f7095fc514e 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -18,6 +18,7 @@ struct vm_fault; #define IOMAP_DELALLOC 0x02 /* delayed allocation blocks */ #define IOMAP_MAPPED 0x03 /* blocks allocated at @addr */ #define IOMAP_UNWRITTEN 0x04 /* blocks allocated at @addr in unwritten state */ +#define IOMAP_INLINE 0x05 /* data inline in the inode */ /* * Flags for all iomap mappings: @@ -34,7 +35,6 @@ struct vm_fault; */ #define IOMAP_F_MERGED 0x10 /* contains multiple blocks/extents */ #define IOMAP_F_SHARED 0x20 /* block shared with another file */ -#define IOMAP_F_DATA_INLINE 0x40 /* data inline in the inode */ /* * Magic value for addr: -- cgit v1.2.3 From 9ecac0ef2233edcb418cc17f9fcbe51ddb0c696c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 1 Jun 2018 09:03:07 -0700 Subject: iomap: fix the comment describing IOMAP_NOWAIT Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8f7095fc514e..13d19b4c29a9 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -59,7 +59,7 @@ struct iomap { #define IOMAP_REPORT (1 << 2) /* report extent status, e.g. FIEMAP */ #define IOMAP_FAULT (1 << 3) /* mapping for page fault */ #define IOMAP_DIRECT (1 << 4) /* direct I/O */ -#define IOMAP_NOWAIT (1 << 5) /* Don't wait for writeback */ +#define IOMAP_NOWAIT (1 << 5) /* do not block */ struct iomap_ops { /* -- cgit v1.2.3 From 7ee66c03e40a570cbf641ff83c063f5209eb22b2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 1 Jun 2018 09:03:07 -0700 Subject: iomap: move IOMAP_F_BOUNDARY to gfs2 Just define a range of fs specific flags and use that in gfs2 instead of exposing this internal flag globally. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 13d19b4c29a9..819e0cd2a950 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -27,8 +27,7 @@ struct vm_fault; * written data and requires fdatasync to commit them to persistent storage. */ #define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */ -#define IOMAP_F_BOUNDARY 0x02 /* mapping ends at metadata boundary */ -#define IOMAP_F_DIRTY 0x04 /* uncommitted metadata */ +#define IOMAP_F_DIRTY 0x02 /* uncommitted metadata */ /* * Flags that only need to be reported for IOMAP_REPORT requests: @@ -36,6 +35,12 @@ struct vm_fault; #define IOMAP_F_MERGED 0x10 /* contains multiple blocks/extents */ #define IOMAP_F_SHARED 0x20 /* block shared with another file */ +/* + * Flags from 0x1000 up are for file system specific usage: + */ +#define IOMAP_F_PRIVATE 0x1000 + + /* * Magic value for addr: */ -- cgit v1.2.3 From 89eb1906a9530ef694b2a5817c9498997722754f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 1 Jun 2018 09:03:08 -0700 Subject: iomap: add an iomap-based bmap implementation This adds a simple iomap-based implementation of the legacy ->bmap interface. Note that we can't easily add checks for rt or reflink files, so these will have to remain in the callers. This interface just needs to die.. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 819e0cd2a950..a044a824da85 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -4,6 +4,7 @@ #include +struct address_space; struct fiemap_extent_info; struct inode; struct iov_iter; @@ -100,6 +101,8 @@ loff_t iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops); loff_t iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops); +sector_t iomap_bmap(struct address_space *mapping, sector_t bno, + const struct iomap_ops *ops); /* * Flags for direct I/O ->end_io: -- cgit v1.2.3 From 8a78cb1f1b98e5ea970674e0f049832d19e76ace Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 1 Jun 2018 09:04:40 -0700 Subject: fs: move page_cache_seek_hole_data to iomap.c This function is only used by the iomap code, depends on being called from it, and will soon stop poking into buffer head internals. Signed-off-by: Christoph Hellwig Reviewed-by: Andreas Gruenbacher Reviewed-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/buffer_head.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 894e5d125de6..96225a77c112 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -205,8 +205,6 @@ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); int bh_submit_read(struct buffer_head *bh); -loff_t page_cache_seek_hole_data(struct inode *inode, loff_t offset, - loff_t length, int whence); extern int buffer_heads_over_limit; -- cgit v1.2.3 From c1c2873df06372a108976599583eba7e47483379 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 29 May 2018 18:08:04 +0200 Subject: clk: remove clk_debugfs_add_file() No one was using this api call, so remove it. If it is ever needed in the future, a "raw" debugfs call can be used. Cc: Michael Turquette Cc: Stephen Boyd Signed-off-by: Greg Kroah-Hartman Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 210a890008f9..00e55d4d07f1 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -996,10 +996,5 @@ static inline void clk_writel(u32 val, u32 __iomem *reg) #endif /* platform dependent I/O accessors */ -#ifdef CONFIG_DEBUG_FS -struct dentry *clk_debugfs_add_file(struct clk_hw *hw, char *name, umode_t mode, - void *data, const struct file_operations *fops); -#endif - #endif /* CONFIG_COMMON_CLK */ #endif /* CLK_PROVIDER_H */ -- cgit v1.2.3 From 5f9bf63ae80c4d0e5e986b6c1280bf8174978545 Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Thu, 31 May 2018 16:43:30 +0300 Subject: net/mlx5: Export flow counter related API Exports counters API to be used in both IB and EN. Reviewed-by: Yishai Hadas Signed-off-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 9f4d32e41c06..3b4c3298061c 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -186,6 +186,9 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); +int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, + u64 *packets, u64 *bytes); + int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); -- cgit v1.2.3 From 3b3233fbf02ee4c5de4d635ca6c4f2566d9716df Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Thu, 31 May 2018 16:43:39 +0300 Subject: IB/mlx5: Add flow counters binding support Associates a counters with a flow when IB_FLOW_SPEC_ACTION_COUNT is part of the flow specifications. The counters user space placements of location and description (index, description) pairs are passed as private data of the counters flow specification. Reviewed-by: Yishai Hadas Signed-off-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 3b4c3298061c..757b4a30281e 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -160,6 +160,7 @@ struct mlx5_flow_act { u32 modify_id; uintptr_t esp_id; struct mlx5_fs_vlan vlan; + struct ib_counters *counters; }; #define MLX5_DECLARE_FLOW_ACT(name) \ -- cgit v1.2.3 From d75d50c016a4eff96e004921402128dc2bc3d65b Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 1 Jun 2018 21:42:07 -0700 Subject: clk: Return void from debug_init op We only have two users of the debug_init hook, and we recently stopped caring about the return value from that op. Finish that off by changing the clk_op to return void instead of int because it doesn't matter if debugfs fails or not. Cc: Eric Anholt Cc: David Lechner Cc: Sekhar Nori Cc: Greg Kroah-Hartman Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 00e55d4d07f1..a4dc15afbdaf 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -218,7 +218,7 @@ struct clk_ops { int (*get_phase)(struct clk_hw *hw); int (*set_phase)(struct clk_hw *hw, int degrees); void (*init)(struct clk_hw *hw); - int (*debug_init)(struct clk_hw *hw, struct dentry *dentry); + void (*debug_init)(struct clk_hw *hw, struct dentry *dentry); }; /** -- cgit v1.2.3 From 9310f0dc1c6430ca9e370a8341bea9f5dc85f40b Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 23 May 2018 17:22:19 -0500 Subject: PCI: pciehp: Rename host->native_hotplug to host->native_pcie_hotplug Rename host->native_hotplug to host->native_pcie_hotplug to make room for a similar flag for SHPC hotplug. Suggested-by: Bjorn Helgaas Signed-off-by: Mika Westerberg [bhelgaas: split to separate patch] Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 14ab65b83067..30ec7e86af55 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -474,7 +474,7 @@ struct pci_host_bridge { unsigned int ignore_reset_delay:1; /* For entire hierarchy */ unsigned int no_ext_tags:1; /* No Extended Tags */ unsigned int native_aer:1; /* OS may use PCIe AER */ - unsigned int native_hotplug:1; /* OS may use PCIe hotplug */ + unsigned int native_pcie_hotplug:1; /* OS may use PCIe hotplug */ unsigned int native_pme:1; /* OS may use PCIe PME */ /* Resource alignment requirements */ resource_size_t (*align_resource)(struct pci_dev *dev, -- cgit v1.2.3 From 5352a44a561d708f1a975a90f5ce16a054fe265c Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 23 May 2018 17:24:08 -0500 Subject: PCI: pciehp: Make pciehp_is_native() stricter Previously pciehp_is_native() returned true for any PCI device in a hierarchy where _OSC says we can use pciehp. This is incorrect because bridges without PCI_EXP_SLTCAP_HPC capability should be managed by acpiphp instead. Improve pciehp_is_native() to return true only when PCI_EXP_SLTCAP_HPC is set and the pciehp driver is present. In any other case return false to let acpiphp handle those. Suggested-by: Bjorn Helgaas Signed-off-by: Mika Westerberg [bhelgaas: remove NULL pointer check] Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- include/linux/pci.h | 2 ++ include/linux/pci_hotplug.h | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 30ec7e86af55..3f009003706a 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1454,8 +1454,10 @@ static inline int pci_irqd_intx_xlate(struct irq_domain *d, #ifdef CONFIG_PCIEPORTBUS extern bool pcie_ports_disabled; +extern bool pcie_ports_native; #else #define pcie_ports_disabled true +#define pcie_ports_native false #endif #ifdef CONFIG_PCIEASPM diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 26213024e81b..3f32575d1ce8 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -162,7 +162,7 @@ struct hotplug_params { #ifdef CONFIG_ACPI #include int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp); -bool pciehp_is_native(struct pci_dev *pdev); +bool pciehp_is_native(struct pci_dev *bridge); int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags); int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle); int acpi_pci_detect_ejectable(acpi_handle handle); @@ -172,6 +172,6 @@ static inline int pci_get_hp_params(struct pci_dev *dev, { return -ENODEV; } -static inline bool pciehp_is_native(struct pci_dev *pdev) { return true; } +static inline bool pciehp_is_native(struct pci_dev *bridge) { return true; } #endif #endif -- cgit v1.2.3 From 1df81a6d6e01ff3f351c614c5bc35b49847e1dc5 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 23 May 2018 17:40:23 -0500 Subject: PCI: shpchp: Request SHPC control via _OSC when adding host bridge The SHPC driver now must be builtin (it cannot be a module). If it is present, request SHPC control immediately when adding the ACPI host bridge. This is similar to how we handle native PCIe hotplug via pciehp. Suggested-by: Bjorn Helgaas Signed-off-by: Mika Westerberg [bhelgaas: split to separate patch] Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 3f009003706a..a4968cdb5f33 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -475,6 +475,7 @@ struct pci_host_bridge { unsigned int no_ext_tags:1; /* No Extended Tags */ unsigned int native_aer:1; /* OS may use PCIe AER */ unsigned int native_pcie_hotplug:1; /* OS may use PCIe hotplug */ + unsigned int native_shpc_hotplug:1; /* OS may use SHPC hotplug */ unsigned int native_pme:1; /* OS may use PCIe PME */ /* Resource alignment requirements */ resource_size_t (*align_resource)(struct pci_dev *dev, -- cgit v1.2.3 From 6f77fa4941aac0fa721eef5fe61820a4c314fffb Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 23 May 2018 17:32:23 -0500 Subject: PCI: shpchp: Remove acpi_get_hp_hw_control_from_firmware() flags acpi_get_hp_hw_control_from_firmware() no longer uses the flags parameter, so remove it. Signed-off-by: Mika Westerberg [bhelgaas: split to separate patch] Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- include/linux/pci_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 3f32575d1ce8..39591213a584 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -163,7 +163,7 @@ struct hotplug_params { #include int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp); bool pciehp_is_native(struct pci_dev *bridge); -int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags); +int acpi_get_hp_hw_control_from_firmware(struct pci_dev *bridge); int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle); int acpi_pci_detect_ejectable(acpi_handle handle); #else -- cgit v1.2.3 From 96a621e01a42dc53848e2e4915fd807ebc1fc82f Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 24 May 2018 15:10:21 -0500 Subject: PCI: shpchp: Remove get_hp_hw_control_from_firmware() wrapper get_hp_hw_control_from_firmware() is a trivial wrapper around acpi_get_hp_hw_control_from_firmware(), probably intended to be generic in case other firmware needed similar OS/platform negotiation. Remove get_hp_hw_control_from_firmware() and call acpi_get_hp_hw_control_from_firmware() directly. Add a stub for acpi_get_hp_hw_control_from_firmware() for the non-ACPI case. Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- include/linux/pci_hotplug.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 39591213a584..1f5c935eb0de 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -172,6 +172,11 @@ static inline int pci_get_hp_params(struct pci_dev *dev, { return -ENODEV; } + +static inline int acpi_get_hp_hw_control_from_firmware(struct pci_dev *bridge) +{ + return 0; +} static inline bool pciehp_is_native(struct pci_dev *bridge) { return true; } #endif #endif -- cgit v1.2.3 From b09803b5e546d553aebbb017ff30b8a54d81d1de Mon Sep 17 00:00:00 2001 From: Oza Pawandeep Date: Thu, 17 May 2018 16:44:20 -0500 Subject: PCI/DPC: Use the generic pcie_do_fatal_recovery() path Our goal is to handle ERR_FATAL errors similarly, whether they are reported via AER or via DPC. A previous commit changed AER so it handles ERR_FATAL by calling driver .remove() methods and resetting the Link. DPC already does that (although the Link reset is done automatically by hardware and happens before we call the driver .remove() methods). Restructure the DPC code so it calls the same pcie_do_fatal_recovery() interface used by AER. This makes it clearer that we want to use the same path. Implement the .reset_link() method used by pcie_do_fatal_recovery(). For DPC, the actual reset is done automatically by hardware, so we really only have to wait for the Link to be inactive, then release the Port from DPC. Signed-off-by: Oza Pawandeep [bhelgaas: changelog, DPC_FATAL is not a bitfield, can be sequential] Signed-off-by: Bjorn Helgaas --- include/linux/aer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/aer.h b/include/linux/aer.h index 8f87bbeceef4..514bffa11dbb 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -14,6 +14,7 @@ #define AER_NONFATAL 0 #define AER_FATAL 1 #define AER_CORRECTABLE 2 +#define DPC_FATAL 3 struct pci_dev; -- cgit v1.2.3 From cd4a4ae4683dc2e09380118e205e057896dcda2b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 2 Jun 2018 14:04:07 -0600 Subject: block: don't use blocking queue entered for recursive bio submits If we end up splitting a bio and the queue goes away between the initial submission and the later split submission, then we can block forever in blk_queue_enter() waiting for the reference to drop to zero. This will never happen, since we already hold a reference. Mark a split bio as already having entered the queue, so we can just use the live non-blocking queue enter variant. Thanks to Tetsuo Handa for the analysis. Reported-by: syzbot+c4f9cebf9d651f6e54de@syzkaller.appspotmail.com Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4cb970cdcd11..3c4f390aea4b 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -229,6 +229,8 @@ struct bio { * throttling rules. Don't do it again. */ #define BIO_TRACE_COMPLETION 10 /* bio_endio() should trace the final completion * of this bio. */ +#define BIO_QUEUE_ENTERED 11 /* can use blk_queue_enter_live() */ + /* See BVEC_POOL_OFFSET below before adding new flags */ /* -- cgit v1.2.3 From 06be0864c77ae6861632a678a6378511a4828d6e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 2 Jun 2018 23:06:31 +0200 Subject: bpf: test case for map pointer poison with calls/branches Add several test cases where the same or different map pointers originate from different paths in the program and execute a map lookup or tail call at a common location. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index d90abdaea94b..6fd375fe7079 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -289,6 +289,16 @@ struct xdp_buff; .off = OFF, \ .imm = 0 }) +/* Relative call */ + +#define BPF_CALL_REL(TGT) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_CALL, \ + .dst_reg = 0, \ + .src_reg = BPF_PSEUDO_CALL, \ + .off = 0, \ + .imm = TGT }) + /* Function call */ #define BPF_EMIT_CALL(FUNC) \ -- cgit v1.2.3 From 09772d92cd5ad998b0d5f6f46cd1658f8cb698cf Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 2 Jun 2018 23:06:35 +0200 Subject: bpf: avoid retpoline for lookup/update/delete calls on maps While some of the BPF map lookup helpers provide a ->map_gen_lookup() callback for inlining the map lookup altogether it is not available for every map, so the remaining ones have to call bpf_map_lookup_elem() helper which does a dispatch to map->ops->map_lookup_elem(). In times of retpolines, this will control and trap speculative execution rather than letting it do its work for the indirect call and will therefore cause a slowdown. Likewise, bpf_map_update_elem() and bpf_map_delete_elem() do not have an inlined version and need to call into their map->ops->map_update_elem() resp. map->ops->map_delete_elem() handlers. Before: # bpftool prog dump xlated id 1 0: (bf) r2 = r10 1: (07) r2 += -8 2: (7a) *(u64 *)(r2 +0) = 0 3: (18) r1 = map[id:1] 5: (85) call __htab_map_lookup_elem#232656 6: (15) if r0 == 0x0 goto pc+4 7: (71) r1 = *(u8 *)(r0 +35) 8: (55) if r1 != 0x0 goto pc+1 9: (72) *(u8 *)(r0 +35) = 1 10: (07) r0 += 56 11: (15) if r0 == 0x0 goto pc+4 12: (bf) r2 = r0 13: (18) r1 = map[id:1] 15: (85) call bpf_map_delete_elem#215008 <-- indirect call via 16: (95) exit helper After: # bpftool prog dump xlated id 1 0: (bf) r2 = r10 1: (07) r2 += -8 2: (7a) *(u64 *)(r2 +0) = 0 3: (18) r1 = map[id:1] 5: (85) call __htab_map_lookup_elem#233328 6: (15) if r0 == 0x0 goto pc+4 7: (71) r1 = *(u8 *)(r0 +35) 8: (55) if r1 != 0x0 goto pc+1 9: (72) *(u8 *)(r0 +35) = 1 10: (07) r0 += 56 11: (15) if r0 == 0x0 goto pc+4 12: (bf) r2 = r0 13: (18) r1 = map[id:1] 15: (85) call htab_lru_map_delete_elem#238240 <-- direct call 16: (95) exit In all three lookup/update/delete cases however we can use the actual address of the map callback directly if we find that there's only a single path with a map pointer leading to the helper call, meaning when the map pointer has not been poisoned from verifier side. Example code can be seen above for the delete case. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 6fd375fe7079..8e60f1e9a702 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -301,6 +301,9 @@ struct xdp_buff; /* Function call */ +#define BPF_CAST_CALL(x) \ + ((u64 (*)(u64, u64, u64, u64, u64))(x)) + #define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ -- cgit v1.2.3 From bc23105ca0abdeed98366af01c700c2c3aff5cd5 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 2 Jun 2018 23:06:39 +0200 Subject: bpf: fix context access in tracing progs on 32 bit archs Wang reported that all the testcases for BPF_PROG_TYPE_PERF_EVENT program type in test_verifier report the following errors on x86_32: 172/p unpriv: spill/fill of different pointers ldx FAIL Unexpected error message! 0: (bf) r6 = r10 1: (07) r6 += -8 2: (15) if r1 == 0x0 goto pc+3 R1=ctx(id=0,off=0,imm=0) R6=fp-8,call_-1 R10=fp0,call_-1 3: (bf) r2 = r10 4: (07) r2 += -76 5: (7b) *(u64 *)(r6 +0) = r2 6: (55) if r1 != 0x0 goto pc+1 R1=ctx(id=0,off=0,imm=0) R2=fp-76,call_-1 R6=fp-8,call_-1 R10=fp0,call_-1 fp-8=fp 7: (7b) *(u64 *)(r6 +0) = r1 8: (79) r1 = *(u64 *)(r6 +0) 9: (79) r1 = *(u64 *)(r1 +68) invalid bpf_context access off=68 size=8 378/p check bpf_perf_event_data->sample_period byte load permitted FAIL Failed to load prog 'Permission denied'! 0: (b7) r0 = 0 1: (71) r0 = *(u8 *)(r1 +68) invalid bpf_context access off=68 size=1 379/p check bpf_perf_event_data->sample_period half load permitted FAIL Failed to load prog 'Permission denied'! 0: (b7) r0 = 0 1: (69) r0 = *(u16 *)(r1 +68) invalid bpf_context access off=68 size=2 380/p check bpf_perf_event_data->sample_period word load permitted FAIL Failed to load prog 'Permission denied'! 0: (b7) r0 = 0 1: (61) r0 = *(u32 *)(r1 +68) invalid bpf_context access off=68 size=4 381/p check bpf_perf_event_data->sample_period dword load permitted FAIL Failed to load prog 'Permission denied'! 0: (b7) r0 = 0 1: (79) r0 = *(u64 *)(r1 +68) invalid bpf_context access off=68 size=8 Reason is that struct pt_regs on x86_32 doesn't fully align to 8 byte boundary due to its size of 68 bytes. Therefore, bpf_ctx_narrow_access_ok() will then bail out saying that off & (size_default - 1) which is 68 & 7 doesn't cleanly align in the case of sample_period access from struct bpf_perf_event_data, hence verifier wrongly thinks we might be doing an unaligned access here though underlying arch can handle it just fine. Therefore adjust this down to machine size and check and rewrite the offset for narrow access on that basis. We also need to fix corresponding pe_prog_is_valid_access(), since we hit the check for off % size != 0 (e.g. 68 % 8 -> 4) in the first and last test. With that in place, progs for tracing work on x86_32. Reported-by: Wang YanQing Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Tested-by: Wang YanQing Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 30 ++++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 8e60f1e9a702..45fc0f5000d8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -639,16 +639,34 @@ static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) return prog->type == BPF_PROG_TYPE_UNSPEC; } -static inline bool -bpf_ctx_narrow_access_ok(u32 off, u32 size, const u32 size_default) +static inline u32 bpf_ctx_off_adjust_machine(u32 size) +{ + const u32 size_machine = sizeof(unsigned long); + + if (size > size_machine && size % size_machine == 0) + size = size_machine; + + return size; +} + +static inline bool bpf_ctx_narrow_align_ok(u32 off, u32 size_access, + u32 size_default) { - bool off_ok; + size_default = bpf_ctx_off_adjust_machine(size_default); + size_access = bpf_ctx_off_adjust_machine(size_access); + #ifdef __LITTLE_ENDIAN - off_ok = (off & (size_default - 1)) == 0; + return (off & (size_default - 1)) == 0; #else - off_ok = (off & (size_default - 1)) + size == size_default; + return (off & (size_default - 1)) + size_access == size_default; #endif - return off_ok && size <= size_default && (size & (size - 1)) == 0; +} + +static inline bool +bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) +{ + return bpf_ctx_narrow_align_ok(off, size, size_default) && + size <= size_default && (size & (size - 1)) == 0; } #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -- cgit v1.2.3 From 8051ac7643e8d0f1dd7272042d66c0518e718347 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Thu, 31 May 2018 09:20:20 -0300 Subject: vlan: use non-archaic spelling of failes Signed-off-by: Thadeu Lima de Souza Cascardo Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 78a5a90b4267..83ea4df6ab81 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -331,7 +331,7 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features, * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len - * Returns error if skb_cow_head failes. + * Returns error if skb_cow_head fails. * * Does not change skb->protocol so this function can be used during receive. */ @@ -379,7 +379,7 @@ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload - * Returns error if skb_cow_head failes. + * Returns error if skb_cow_head fails. * * Does not change skb->protocol so this function can be used during receive. */ -- cgit v1.2.3 From 42b33468987bac0dd95c30f14820c7abac04a153 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 31 May 2018 10:59:47 +0200 Subject: xdp: add flags argument to ndo_xdp_xmit API This patch only change the API and reject any use of flags. This is an intermediate step that allows us to implement the flush flag operation later, for each individual driver in a separate patch. The plan is to implement flush operation via XDP_XMIT_FLUSH flag and then remove XDP_XMIT_FLAGS_NONE when done. Signed-off-by: Jesper Dangaard Brouer Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/netdevice.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8452f72087ef..7f17785a59d7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1185,13 +1185,13 @@ struct dev_ifalias { * This function is used to set or query state related to XDP on the * netdevice and manage BPF offload. See definition of * enum bpf_netdev_command for details. - * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp); + * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, + * u32 flags); * This function is used to submit @n XDP packets for transmit on a * netdevice. Returns number of frames successfully transmitted, frames * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. - * TODO: Consider add flag to allow sending flush operation. * void (*ndo_xdp_flush)(struct net_device *dev); * This function is used to inform the driver to flush a particular * xdp tx queue. Must be called on same CPU as xdp_xmit. @@ -1380,7 +1380,8 @@ struct net_device_ops { int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); int (*ndo_xdp_xmit)(struct net_device *dev, int n, - struct xdp_frame **xdp); + struct xdp_frame **xdp, + u32 flags); void (*ndo_xdp_flush)(struct net_device *dev); }; -- cgit v1.2.3 From 3e79bfd61cbba28ffa54ff15475495f18bcf3c7f Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Thu, 31 May 2018 12:10:59 -0500 Subject: rpmsg: Switch to SPDX license identifier Use the appropriate SPDX license identifier in the rpmsg core source files and drop the previous boilerplate license text. Signed-off-by: Suman Anna Signed-off-by: Bjorn Andersson --- include/linux/rpmsg.h | 27 +-------------------------- 1 file changed, 1 insertion(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index ca07366c4c33..9fe156d1c018 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -1,35 +1,10 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ /* * Remote processor messaging * * Copyright (C) 2011 Texas Instruments, Inc. * Copyright (C) 2011 Google, Inc. * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name Texas Instruments nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ #ifndef _LINUX_RPMSG_H -- cgit v1.2.3 From 84369fbe62a286711de27a0949f808726f810392 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Thu, 31 May 2018 12:11:02 -0500 Subject: rpmsg: glink: Switch to SPDX license identifier Use the appropriate SPDX license identifier in various rpmsg glink driver source files and drop the previous boilerplate license text. Signed-off-by: Suman Anna Signed-off-by: Bjorn Andersson --- include/linux/rpmsg/qcom_glink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rpmsg/qcom_glink.h b/include/linux/rpmsg/qcom_glink.h index a622f029836e..96e26d94719f 100644 --- a/include/linux/rpmsg/qcom_glink.h +++ b/include/linux/rpmsg/qcom_glink.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + #ifndef _LINUX_RPMSG_QCOM_GLINK_H #define _LINUX_RPMSG_QCOM_GLINK_H -- cgit v1.2.3 From bf6fa2c893c5237b48569a13fa3c673041430b6c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sun, 3 Jun 2018 15:59:41 -0700 Subject: bpf: implement bpf_get_current_cgroup_id() helper bpf has been used extensively for tracing. For example, bcc contains an almost full set of bpf-based tools to trace kernel and user functions/events. Most tracing tools are currently either filtered based on pid or system-wide. Containers have been used quite extensively in industry and cgroup is often used together to provide resource isolation and protection. Several processes may run inside the same container. It is often desirable to get container-level tracing results as well, e.g. syscall count, function count, I/O activity, etc. This patch implements a new helper, bpf_get_current_cgroup_id(), which will return cgroup id based on the cgroup within which the current task is running. The later patch will provide an example to show that userspace can get the same cgroup id so it could configure a filter or policy in the bpf program based on task cgroup id. The helper is currently implemented for tracing. It can be added to other program types as well when needed. Acked-by: Alexei Starovoitov Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bbe297436e5d..995c3b1e59bf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -746,6 +746,7 @@ extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; +extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); -- cgit v1.2.3 From d95c9760d9c8e046b09b54a3bb6dd0c9aa7a0eff Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Fri, 18 May 2018 17:24:03 +0200 Subject: mfd: stm32-timers: Fix pwm-stm32 linker issue with COMPILE_TEST This is seen when COMPILE_TEST=y and MFD_STM32_TIMERS=n. drivers/pwm/pwm-stm32.o: In function 'stm32_pwm_raw_capture': pwm-stm32.c:... undefined reference to 'stm32_timers_dma_burst_read' Fixes: 0c6609805b63 ("mfd: stm32-timers: Add support for DMAs") Signed-off-by: Fabrice Gasnier Reported-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Lee Jones --- include/linux/mfd/stm32-timers.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index 9da1d7ece079..067d14655c28 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -124,8 +124,20 @@ struct stm32_timers { struct stm32_timers_dma dma; /* Only to be used by the parent */ }; +#if IS_REACHABLE(CONFIG_MFD_STM32_TIMERS) int stm32_timers_dma_burst_read(struct device *dev, u32 *buf, enum stm32_timers_dmas id, u32 reg, unsigned int num_reg, unsigned int bursts, unsigned long tmo_ms); +#else +static inline int stm32_timers_dma_burst_read(struct device *dev, u32 *buf, + enum stm32_timers_dmas id, + u32 reg, + unsigned int num_reg, + unsigned int bursts, + unsigned long tmo_ms) +{ + return -ENODEV; +} +#endif #endif -- cgit v1.2.3 From a841b54dbd65421726caf7129f8951910c7a8ea6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 7 Apr 2018 13:50:59 -0400 Subject: NFS: Pass the inode down to the getattr() callback Allow the getattr() callback to check things like whether or not we hold a delegation so that it can adjust the attributes that it is asking for. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 09dc14ac5804..9dee3c23895d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1581,7 +1581,8 @@ struct nfs_rpc_ops { struct dentry *(*try_mount) (int, const char *, struct nfs_mount_info *, struct nfs_subversion *); int (*getattr) (struct nfs_server *, struct nfs_fh *, - struct nfs_fattr *, struct nfs4_label *); + struct nfs_fattr *, struct nfs4_label *, + struct inode *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); int (*lookup) (struct inode *, const struct qstr *, -- cgit v1.2.3 From 90cc0c3cc7092ea4c7871fdd5fb00a9ba62842e3 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 31 May 2018 11:42:11 -0500 Subject: PCI: shpchp: Add shpchp_is_native() In the same way we do for pciehp, add shpchp_is_native(), which returns true if the bridge should be handled by the native SHPC driver. Then convert the driver to use this function. Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas --- include/linux/pci_hotplug.h | 2 ++ include/linux/pci_ids.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 1f5c935eb0de..4c378368215c 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -164,6 +164,7 @@ struct hotplug_params { int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp); bool pciehp_is_native(struct pci_dev *bridge); int acpi_get_hp_hw_control_from_firmware(struct pci_dev *bridge); +bool shpchp_is_native(struct pci_dev *bridge); int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle); int acpi_pci_detect_ejectable(acpi_handle handle); #else @@ -178,5 +179,6 @@ static inline int acpi_get_hp_hw_control_from_firmware(struct pci_dev *bridge) return 0; } static inline bool pciehp_is_native(struct pci_dev *bridge) { return true; } +static inline bool shpchp_is_native(struct pci_dev *bridge) { return true; } #endif #endif diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 883cb7bf78aa..5aace6cca0d7 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -561,6 +561,7 @@ #define PCI_DEVICE_ID_AMD_OPUS_7443 0x7443 #define PCI_DEVICE_ID_AMD_VIPER_7443 0x7443 #define PCI_DEVICE_ID_AMD_OPUS_7445 0x7445 +#define PCI_DEVICE_ID_AMD_GOLAM_7450 0x7450 #define PCI_DEVICE_ID_AMD_8111_PCI 0x7460 #define PCI_DEVICE_ID_AMD_8111_LPC 0x7468 #define PCI_DEVICE_ID_AMD_8111_IDE 0x7469 -- cgit v1.2.3 From 95d969ebb3925464038a32b4a225c5c52e675ae8 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 28 May 2018 15:47:52 +0300 Subject: PCI: hotplug: Add hotplug_is_native() Add hotplug_is_native() to find out whether the OS is supposed to handle native hotplug of a given bridge. Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Reviewed-by: Andy Shevchenko --- include/linux/pci_hotplug.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 4c378368215c..cf5e22103f68 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -181,4 +181,9 @@ static inline int acpi_get_hp_hw_control_from_firmware(struct pci_dev *bridge) static inline bool pciehp_is_native(struct pci_dev *bridge) { return true; } static inline bool shpchp_is_native(struct pci_dev *bridge) { return true; } #endif + +static inline bool hotplug_is_native(struct pci_dev *bridge) +{ + return pciehp_is_native(bridge) || shpchp_is_native(bridge); +} #endif -- cgit v1.2.3 From b0966e7b894035dba6710aa4e9f18d7a3a3d5b22 Mon Sep 17 00:00:00 2001 From: Adam Manzanares Date: Mon, 4 Jun 2018 10:59:56 -0700 Subject: fs: aio ioprio add explicit block layer dependence Previously, the ioprio_check_cap function was only defined when CONFIG_BLOCK was set. Make this relationship explicit and add a stub for !CONFIG_BLOCK. Signed-off-by: Adam Manzanares Signed-off-by: Al Viro --- include/linux/ioprio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index 4a28cec49ec3..9e30ed6443db 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -77,6 +77,13 @@ extern int ioprio_best(unsigned short aprio, unsigned short bprio); extern int set_task_ioprio(struct task_struct *task, int ioprio); +#ifdef CONFIG_BLOCK extern int ioprio_check_cap(int ioprio); +#else +static inline int ioprio_check_cap(int ioprio) +{ + return -ENOTBLK; +} +#endif /* CONFIG_BLOCK */ #endif -- cgit v1.2.3 From fe943d50425b6646606f8ef1ef8b8d4975fdbee2 Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Thu, 12 Apr 2018 12:04:55 +0800 Subject: libceph, rbd: add error handling for osd_req_op_cls_init() Add proper error handling for osd_req_op_cls_init() to replace BUG_ON statement when failing from memory allocation. Signed-off-by: Chengguang Xu Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 96bb32285989..b73dd7ebe585 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -440,7 +440,7 @@ extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages); -extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req, +extern int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *class, const char *method); extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, -- cgit v1.2.3 From 49a9f4f6714ec0ca2c6ada2ce764fbdd694962ee Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Wed, 25 Apr 2018 17:30:23 +0800 Subject: ceph: always get rstat from auth mds rstat is not tracked by capability. client can't know if rstat from non-auth mds is uptodate or not. Link: http://tracker.ceph.com/issues/23538 Signed-off-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 7ecfc88314d8..4903deb0777a 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -628,6 +628,7 @@ int ceph_flags_to_mode(int flags); CEPH_CAP_XATTR_SHARED) #define CEPH_STAT_CAP_INLINE_DATA (CEPH_CAP_FILE_SHARED | \ CEPH_CAP_FILE_RD) +#define CEPH_STAT_RSTAT CEPH_CAP_FILE_WREXTEND #define CEPH_CAP_ANY_SHARED (CEPH_CAP_AUTH_SHARED | \ CEPH_CAP_LINK_SHARED | \ -- cgit v1.2.3 From 66850df58529eefc61cb96b895991508547503bf Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 15 May 2018 15:47:58 +0200 Subject: libceph: introduce ceph_osdc_abort_requests() This will be used by the filesystem for "umount -f". Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index b73dd7ebe585..874c31c01f80 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -347,6 +347,7 @@ struct ceph_osd_client { struct rb_root linger_map_checks; atomic_t num_requests; atomic_t num_homeless; + int abort_err; struct delayed_work timeout_work; struct delayed_work osds_timeout_work; #ifdef CONFIG_DEBUG_FS @@ -378,6 +379,7 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb); +void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err); extern void osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u32 flags); -- cgit v1.2.3 From 88bc1922c273c95e84a8955e657401f9bc63a80b Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 21 May 2018 16:00:29 +0200 Subject: libceph: defer __complete_request() to a workqueue In the common case, req->r_callback is called by handle_reply() on the ceph-msgr worker thread without any locks. If handle_reply() fails, it is called with both osd->lock and osdc->lock. In the map check case, it is called with just osdc->lock but held for write. Finally, if the request is aborted because of -ENOSPC or by ceph_osdc_abort_requests(), it is called directly on the submitter's thread, again with both locks. req->r_callback on the submitter's thread is relatively new (introduced in 4.12) and ripe for deadlocks -- e.g. writeback worker thread waiting on itself: inode_wait_for_writeback+0x26/0x40 evict+0xb5/0x1a0 iput+0x1d2/0x220 ceph_put_wrbuffer_cap_refs+0xe0/0x2c0 [ceph] writepages_finish+0x2d3/0x410 [ceph] __complete_request+0x26/0x60 [libceph] complete_request+0x2e/0x70 [libceph] __submit_request+0x256/0x330 [libceph] submit_request+0x2b/0x30 [libceph] ceph_osdc_start_request+0x25/0x40 [libceph] ceph_writepages_start+0xdfe/0x1320 [ceph] do_writepages+0x1f/0x70 __writeback_single_inode+0x45/0x330 writeback_sb_inodes+0x26a/0x600 __writeback_inodes_wb+0x92/0xc0 wb_writeback+0x274/0x330 wb_workfn+0x2d5/0x3b0 Defer __complete_request() to a workqueue in all failure cases so it's never on the same thread as ceph_osdc_start_request() and always called with no locks held. Link: http://tracker.ceph.com/issues/23978 Signed-off-by: Ilya Dryomov Acked-by: Jeff Layton Reviewed-by: "Yan, Zheng" --- include/linux/ceph/osd_client.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 874c31c01f80..d4191bde95a4 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -170,6 +170,7 @@ struct ceph_osd_request { u64 r_tid; /* unique for this client */ struct rb_node r_node; struct rb_node r_mc_node; /* map check */ + struct work_struct r_complete_work; struct ceph_osd *r_osd; struct ceph_osd_request_target r_t; @@ -360,6 +361,7 @@ struct ceph_osd_client { struct ceph_msgpool msgpool_op_reply; struct workqueue_struct *notify_wq; + struct workqueue_struct *completion_wq; }; static inline bool ceph_osdmap_flag(struct ceph_osd_client *osdc, int flag) -- cgit v1.2.3 From c843d13caefad9f2f182f38d6bfe492c9f00e086 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 30 May 2018 16:29:14 +0200 Subject: libceph: make abort_on_full a per-osdc setting The intent behind making it a per-request setting was that it would be set for writes, but not for reads. As it is, the flag is set for all fs/ceph requests except for pool perm check stat request (technically a read). ceph_osdc_abort_on_full() skips reads since the previous commit and I don't see a use case for marking individual requests. Signed-off-by: Ilya Dryomov Acked-by: Jeff Layton Reviewed-by: "Yan, Zheng" --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index d4191bde95a4..0d6ee04b4c41 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -202,7 +202,6 @@ struct ceph_osd_request { struct timespec r_mtime; /* ditto */ u64 r_data_offset; /* ditto */ bool r_linger; /* don't resend on failure */ - bool r_abort_on_full; /* return ENOSPC when full */ /* internal */ unsigned long r_stamp; /* jiffies, send or check time */ @@ -348,6 +347,7 @@ struct ceph_osd_client { struct rb_root linger_map_checks; atomic_t num_requests; atomic_t num_homeless; + bool abort_on_full; /* abort w/ ENOSPC when full */ int abort_err; struct delayed_work timeout_work; struct delayed_work osds_timeout_work; -- cgit v1.2.3 From a86f009f106cba322c608785e09c8b5be8ffe8bb Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 23 May 2018 14:46:53 +0200 Subject: libceph: allocate the locator string with GFP_NOFAIL calc_target() isn't supposed to fail with anything but POOL_DNE, in which case we report that the pool doesn't exist and fail the request with -ENOENT. Doing this for -ENOMEM is at the very least confusing and also harmful -- as the preceding requests complete, a short-lived locator string allocation is likely to succeed after a wait. (We used to call ceph_object_locator_to_pg() for a pi lookup. In theory that could fail with -ENOENT, hence the "ret != -ENOENT" warning being removed.) Signed-off-by: Ilya Dryomov --- include/linux/ceph/osdmap.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index e71fb222c7c3..5675b1f09bc5 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -279,10 +279,10 @@ bool ceph_osds_changed(const struct ceph_osds *old_acting, const struct ceph_osds *new_acting, bool any_change); -int __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi, - const struct ceph_object_id *oid, - const struct ceph_object_locator *oloc, - struct ceph_pg *raw_pgid); +void __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, + struct ceph_pg *raw_pgid); int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap, const struct ceph_object_id *oid, const struct ceph_object_locator *oloc, -- cgit v1.2.3 From c5e7a7ea22d5677f7c70028908372cff6948ecdc Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 4 Jun 2018 12:01:15 -0700 Subject: swait: strengthen language to discourage use We already earlier discouraged people from using this interface in commit 88796e7e5c45 ("sched/swait: Document it clearly that the swait facilities are special and shouldn't be used"), but I just got a pull request with a new broken user. So make the comment *really* clear. The swait interfaces are bad, and should not be used unless you have some *very* strong reasons that include tons of hard performance numbers on just why you want to use them, and you show that you actually understand that they aren't at all like the normal wait/wakeup interfaces. So far, every single user has been suspect. The main user is KVM, which is completely pointless (there is only ever one waiter, which avoids the interface subtleties, but also means that having a queue instead of a pointer is counter-productive and certainly not an "optimization"). So make the comments much stronger. Not that anybody likely reads them anyway, but there's always some slight hope that it will cause somebody to think twice. I'd like to remove this interface entirely, but there is the theoretical possibility that it's actually the right thing to use in some situation, most likely some deep RT use. Signed-off-by: Linus Torvalds --- include/linux/swait.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swait.h b/include/linux/swait.h index c98aaf677466..13eac825819d 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -8,7 +8,19 @@ #include /* - * Simple wait queues + * BROKEN wait-queues. + * + * These "simple" wait-queues are broken garbage, and should never be + * used. The comments below claim that they are "similar" to regular + * wait-queues, but the semantics are actually completely different, and + * every single user we have ever had has been buggy (or pointless). + * + * A "swake_up()" only wakes up _one_ waiter, which is not at all what + * "wake_up()" does, and has led to problems. In other cases, it has + * been fine, because there's only ever one waiter (kvm), but in that + * case gthe whole "simple" wait-queue is just pointless to begin with, + * since there is no "queue". Use "wake_up_process()" with a direct + * pointer instead. * * While these are very similar to regular wait queues (wait.h) the most * important difference is that the simple waitqueue allows for deterministic -- cgit v1.2.3 From 1f4c74132140c184b8cbcf0a7298beda1d3681de Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 2 Jun 2018 21:40:19 -0700 Subject: net: skbuff.h: drop unneeded does not use nor need , so drop this header file from skbuff.h. is currently #included in around 1200 C source and header files, making it the 31st most-used header file. Build tested [allmodconfig] on 20 arch-es. Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 693564a9a979..164cdedf6012 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -854,8 +854,6 @@ struct sk_buff { /* * Handling routines are only of interest to the kernel */ -#include - #define SKB_ALLOC_FCLONE 0x01 #define SKB_ALLOC_RX 0x02 -- cgit v1.2.3 From 39dbc646fd2c67ee9b71450ce172cbd714d4e7fb Mon Sep 17 00:00:00 2001 From: Yuval Bason Date: Sun, 3 Jun 2018 19:13:07 +0300 Subject: qed: Add srq core support for RoCE and iWARP This patch adds support for configuring SRQ and provides the necessary APIs for rdma upper layer driver (qedr) to enable the SRQ feature. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: Yuval Bason Signed-off-by: David S. Miller --- include/linux/qed/qed_rdma_if.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index 4dd72ba210f5..e05e320d28b7 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -485,7 +485,9 @@ enum qed_iwarp_event_type { QED_IWARP_EVENT_ACTIVE_MPA_REPLY, QED_IWARP_EVENT_LOCAL_ACCESS_ERROR, QED_IWARP_EVENT_REMOTE_OPERATION_ERROR, - QED_IWARP_EVENT_TERMINATE_RECEIVED + QED_IWARP_EVENT_TERMINATE_RECEIVED, + QED_IWARP_EVENT_SRQ_LIMIT, + QED_IWARP_EVENT_SRQ_EMPTY, }; enum qed_tcp_ip_version { @@ -646,6 +648,14 @@ struct qed_rdma_ops { int (*rdma_alloc_tid)(void *rdma_cxt, u32 *itid); void (*rdma_free_tid)(void *rdma_cxt, u32 itid); + int (*rdma_create_srq)(void *rdma_cxt, + struct qed_rdma_create_srq_in_params *iparams, + struct qed_rdma_create_srq_out_params *oparams); + int (*rdma_destroy_srq)(void *rdma_cxt, + struct qed_rdma_destroy_srq_in_params *iparams); + int (*rdma_modify_srq)(void *rdma_cxt, + struct qed_rdma_modify_srq_in_params *iparams); + int (*ll2_acquire_connection)(void *rdma_cxt, struct qed_ll2_acquire_data *data); -- cgit v1.2.3 From a9235b544a0ae95fbd56443bdbd251358c7df4c5 Mon Sep 17 00:00:00 2001 From: Vasyl Gomonovych Date: Fri, 18 May 2018 22:31:28 +0200 Subject: ring-buffer: Fix typo in comment Fix typo of the word 'been' Link: http://lkml.kernel.org/r/20180518203130.2011-1-gomonovych@gmail.com Signed-off-by: Vasyl Gomonovych Signed-off-by: Steven Rostedt (VMware) --- include/linux/ring_buffer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index a0233edc0718..b72ebdff0b77 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -65,7 +65,7 @@ u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event); /* * ring_buffer_discard_commit will remove an event that has not - * ben committed yet. If this is used, then ring_buffer_unlock_commit + * been committed yet. If this is used, then ring_buffer_unlock_commit * must not be called on the discarded event. This function * will try to remove the event from the ring buffer completely * if another event has not been written after it. -- cgit v1.2.3 From 2026d35741f2c3ece73c11eb7e4a15d7c2df9ebe Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 30 May 2018 08:19:22 -0400 Subject: branch-check: fix long->int truncation when profiling branches The function __builtin_expect returns long type (see the gcc documentation), and so do macros likely and unlikely. Unfortunatelly, when CONFIG_PROFILE_ANNOTATED_BRANCHES is selected, the macros likely and unlikely expand to __branch_check__ and __branch_check__ truncates the long type to int. This unintended truncation may cause bugs in various kernel code (we found a bug in dm-writecache because of it), so it's better to fix __branch_check__ to return long. Link: http://lkml.kernel.org/r/alpine.LRH.2.02.1805300818140.24812@file01.intranet.prod.int.rdu2.redhat.com Cc: Ingo Molnar Cc: stable@vger.kernel.org Fixes: 1f0d69a9fc815 ("tracing: profile likely and unlikely annotations") Signed-off-by: Mikulas Patocka Signed-off-by: Steven Rostedt (VMware) --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ab4711c63601..42506e4d1f53 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -21,7 +21,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define unlikely_notrace(x) __builtin_expect(!!(x), 0) #define __branch_check__(x, expect, is_constant) ({ \ - int ______r; \ + long ______r; \ static struct ftrace_likely_data \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_annotated_branch"))) \ -- cgit v1.2.3 From 97c2b5cba2044f1c0bc3f14d7102176dbcf81af0 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Mon, 21 May 2018 10:59:54 +0100 Subject: mfd: madera: Add register definitions for Cirrus Logic Madera codecs This patch adds a header file of register definitions for Cirrus Logic "Madera" class codecs. These codecs are all based off a common set of hardware IP so have a common register map (with a few minor device-to-device variations). The registers.h file is tool-generated directly from the hardware design but has been manually stripped down to reduce size (full register map is >44000 lines). All names are kept the same as datasheet names so that they can be cross-referenced between source and datasheet without confusion. The register map layout is kept fully-defined rather than factored into macros and/or block-indexing code. The major reasons for this are: - #1 is that it makes the source highly greppable, which is important. "What does the driver do with register bits XYZ" or "Where does it use register bits XYZ" are commonly types of questions. These can be quickly answered by a grep. Squashing definitions into generator macros or block- indexing code is a way of defeating grep. - most of the register definitions are used in tables, so a constant value is required. Using generator macros make the table definition clunky and obscure. - the code is clearer when it's there in the source exactly what register and field it is using - it is easier to diff the register map of a new (unsupported) codec against what is already supported and merge in differences - it makes the register map available in source for maintenance/debugging instead of having to refer back to the datasheet for a register map Signed-off-by: Richard Fitzgerald Signed-off-by: Lee Jones --- include/linux/mfd/madera/registers.h | 3917 ++++++++++++++++++++++++++++++++++ 1 file changed, 3917 insertions(+) create mode 100644 include/linux/mfd/madera/registers.h (limited to 'include/linux') diff --git a/include/linux/mfd/madera/registers.h b/include/linux/mfd/madera/registers.h new file mode 100644 index 000000000000..a6b7c4222c5e --- /dev/null +++ b/include/linux/mfd/madera/registers.h @@ -0,0 +1,3917 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Madera register definitions + * + * Copyright (C) 2015-2018 Cirrus Logic + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2. + */ + +#ifndef MADERA_REGISTERS_H +#define MADERA_REGISTERS_H + +/* + * Register Addresses. + */ +#define MADERA_SOFTWARE_RESET 0x00 +#define MADERA_HARDWARE_REVISION 0x01 +#define MADERA_CTRL_IF_CFG_1 0x08 +#define MADERA_CTRL_IF_CFG_2 0x09 +#define MADERA_CTRL_IF_CFG_3 0x0A +#define MADERA_WRITE_SEQUENCER_CTRL_0 0x16 +#define MADERA_WRITE_SEQUENCER_CTRL_1 0x17 +#define MADERA_WRITE_SEQUENCER_CTRL_2 0x18 +#define MADERA_TONE_GENERATOR_1 0x20 +#define MADERA_TONE_GENERATOR_2 0x21 +#define MADERA_TONE_GENERATOR_3 0x22 +#define MADERA_TONE_GENERATOR_4 0x23 +#define MADERA_TONE_GENERATOR_5 0x24 +#define MADERA_PWM_DRIVE_1 0x30 +#define MADERA_PWM_DRIVE_2 0x31 +#define MADERA_PWM_DRIVE_3 0x32 +#define MADERA_SEQUENCE_CONTROL 0x41 +#define MADERA_SAMPLE_RATE_SEQUENCE_SELECT_1 0x61 +#define MADERA_SAMPLE_RATE_SEQUENCE_SELECT_2 0x62 +#define MADERA_SAMPLE_RATE_SEQUENCE_SELECT_3 0x63 +#define MADERA_SAMPLE_RATE_SEQUENCE_SELECT_4 0x64 +#define MADERA_ALWAYS_ON_TRIGGERS_SEQUENCE_SELECT_1 0x66 +#define MADERA_ALWAYS_ON_TRIGGERS_SEQUENCE_SELECT_2 0x67 +#define MADERA_HAPTICS_CONTROL_1 0x90 +#define MADERA_HAPTICS_CONTROL_2 0x91 +#define MADERA_HAPTICS_PHASE_1_INTENSITY 0x92 +#define MADERA_HAPTICS_PHASE_1_DURATION 0x93 +#define MADERA_HAPTICS_PHASE_2_INTENSITY 0x94 +#define MADERA_HAPTICS_PHASE_2_DURATION 0x95 +#define MADERA_HAPTICS_PHASE_3_INTENSITY 0x96 +#define MADERA_HAPTICS_PHASE_3_DURATION 0x97 +#define MADERA_HAPTICS_STATUS 0x98 +#define MADERA_COMFORT_NOISE_GENERATOR 0xA0 +#define MADERA_CLOCK_32K_1 0x100 +#define MADERA_SYSTEM_CLOCK_1 0x101 +#define MADERA_SAMPLE_RATE_1 0x102 +#define MADERA_SAMPLE_RATE_2 0x103 +#define MADERA_SAMPLE_RATE_3 0x104 +#define MADERA_SAMPLE_RATE_1_STATUS 0x10A +#define MADERA_SAMPLE_RATE_2_STATUS 0x10B +#define MADERA_SAMPLE_RATE_3_STATUS 0x10C +#define MADERA_ASYNC_CLOCK_1 0x112 +#define MADERA_ASYNC_SAMPLE_RATE_1 0x113 +#define MADERA_ASYNC_SAMPLE_RATE_2 0x114 +#define MADERA_ASYNC_SAMPLE_RATE_1_STATUS 0x11B +#define MADERA_ASYNC_SAMPLE_RATE_2_STATUS 0x11C +#define MADERA_DSP_CLOCK_1 0x120 +#define MADERA_DSP_CLOCK_2 0x122 +#define MADERA_OUTPUT_SYSTEM_CLOCK 0x149 +#define MADERA_OUTPUT_ASYNC_CLOCK 0x14A +#define MADERA_RATE_ESTIMATOR_1 0x152 +#define MADERA_RATE_ESTIMATOR_2 0x153 +#define MADERA_RATE_ESTIMATOR_3 0x154 +#define MADERA_RATE_ESTIMATOR_4 0x155 +#define MADERA_RATE_ESTIMATOR_5 0x156 +#define MADERA_FLL1_CONTROL_1 0x171 +#define MADERA_FLL1_CONTROL_2 0x172 +#define MADERA_FLL1_CONTROL_3 0x173 +#define MADERA_FLL1_CONTROL_4 0x174 +#define MADERA_FLL1_CONTROL_5 0x175 +#define MADERA_FLL1_CONTROL_6 0x176 +#define MADERA_FLL1_LOOP_FILTER_TEST_1 0x177 +#define MADERA_FLL1_NCO_TEST_0 0x178 +#define MADERA_FLL1_CONTROL_7 0x179 +#define MADERA_FLL1_EFS_2 0x17A +#define CS47L35_FLL1_SYNCHRONISER_1 0x17F +#define CS47L35_FLL1_SYNCHRONISER_2 0x180 +#define CS47L35_FLL1_SYNCHRONISER_3 0x181 +#define CS47L35_FLL1_SYNCHRONISER_4 0x182 +#define CS47L35_FLL1_SYNCHRONISER_5 0x183 +#define CS47L35_FLL1_SYNCHRONISER_6 0x184 +#define CS47L35_FLL1_SYNCHRONISER_7 0x185 +#define CS47L35_FLL1_SPREAD_SPECTRUM 0x187 +#define CS47L35_FLL1_GPIO_CLOCK 0x188 +#define MADERA_FLL1_SYNCHRONISER_1 0x181 +#define MADERA_FLL1_SYNCHRONISER_2 0x182 +#define MADERA_FLL1_SYNCHRONISER_3 0x183 +#define MADERA_FLL1_SYNCHRONISER_4 0x184 +#define MADERA_FLL1_SYNCHRONISER_5 0x185 +#define MADERA_FLL1_SYNCHRONISER_6 0x186 +#define MADERA_FLL1_SYNCHRONISER_7 0x187 +#define MADERA_FLL1_SPREAD_SPECTRUM 0x189 +#define MADERA_FLL1_GPIO_CLOCK 0x18A +#define MADERA_FLL2_CONTROL_1 0x191 +#define MADERA_FLL2_CONTROL_2 0x192 +#define MADERA_FLL2_CONTROL_3 0x193 +#define MADERA_FLL2_CONTROL_4 0x194 +#define MADERA_FLL2_CONTROL_5 0x195 +#define MADERA_FLL2_CONTROL_6 0x196 +#define MADERA_FLL2_LOOP_FILTER_TEST_1 0x197 +#define MADERA_FLL2_NCO_TEST_0 0x198 +#define MADERA_FLL2_CONTROL_7 0x199 +#define MADERA_FLL2_EFS_2 0x19A +#define MADERA_FLL2_SYNCHRONISER_1 0x1A1 +#define MADERA_FLL2_SYNCHRONISER_2 0x1A2 +#define MADERA_FLL2_SYNCHRONISER_3 0x1A3 +#define MADERA_FLL2_SYNCHRONISER_4 0x1A4 +#define MADERA_FLL2_SYNCHRONISER_5 0x1A5 +#define MADERA_FLL2_SYNCHRONISER_6 0x1A6 +#define MADERA_FLL2_SYNCHRONISER_7 0x1A7 +#define MADERA_FLL2_SPREAD_SPECTRUM 0x1A9 +#define MADERA_FLL2_GPIO_CLOCK 0x1AA +#define MADERA_FLL3_CONTROL_1 0x1B1 +#define MADERA_FLL3_CONTROL_2 0x1B2 +#define MADERA_FLL3_CONTROL_3 0x1B3 +#define MADERA_FLL3_CONTROL_4 0x1B4 +#define MADERA_FLL3_CONTROL_5 0x1B5 +#define MADERA_FLL3_CONTROL_6 0x1B6 +#define MADERA_FLL3_LOOP_FILTER_TEST_1 0x1B7 +#define MADERA_FLL3_NCO_TEST_0 0x1B8 +#define MADERA_FLL3_CONTROL_7 0x1B9 +#define MADERA_FLL3_SYNCHRONISER_1 0x1C1 +#define MADERA_FLL3_SYNCHRONISER_2 0x1C2 +#define MADERA_FLL3_SYNCHRONISER_3 0x1C3 +#define MADERA_FLL3_SYNCHRONISER_4 0x1C4 +#define MADERA_FLL3_SYNCHRONISER_5 0x1C5 +#define MADERA_FLL3_SYNCHRONISER_6 0x1C6 +#define MADERA_FLL3_SYNCHRONISER_7 0x1C7 +#define MADERA_FLL3_SPREAD_SPECTRUM 0x1C9 +#define MADERA_FLL3_GPIO_CLOCK 0x1CA +#define MADERA_FLLAO_CONTROL_1 0x1D1 +#define MADERA_FLLAO_CONTROL_2 0x1D2 +#define MADERA_FLLAO_CONTROL_3 0x1D3 +#define MADERA_FLLAO_CONTROL_4 0x1D4 +#define MADERA_FLLAO_CONTROL_5 0x1D5 +#define MADERA_FLLAO_CONTROL_6 0x1D6 +#define MADERA_FLLAO_CONTROL_7 0x1D8 +#define MADERA_FLLAO_CONTROL_8 0x1DA +#define MADERA_FLLAO_CONTROL_9 0x1DB +#define MADERA_FLLAO_CONTROL_10 0x1DC +#define MADERA_FLLAO_CONTROL_11 0x1DD +#define MADERA_MIC_CHARGE_PUMP_1 0x200 +#define MADERA_HP_CHARGE_PUMP_8 0x20B +#define MADERA_LDO1_CONTROL_1 0x210 +#define MADERA_LDO2_CONTROL_1 0x213 +#define MADERA_MIC_BIAS_CTRL_1 0x218 +#define MADERA_MIC_BIAS_CTRL_2 0x219 +#define MADERA_MIC_BIAS_CTRL_3 0x21A +#define MADERA_MIC_BIAS_CTRL_4 0x21B +#define MADERA_MIC_BIAS_CTRL_5 0x21C +#define MADERA_MIC_BIAS_CTRL_6 0x21E +#define MADERA_HP_CTRL_1L 0x225 +#define MADERA_HP_CTRL_1R 0x226 +#define MADERA_HP_CTRL_2L 0x227 +#define MADERA_HP_CTRL_2R 0x228 +#define MADERA_HP_CTRL_3L 0x229 +#define MADERA_HP_CTRL_3R 0x22A +#define MADERA_DCS_HP1L_CONTROL 0x232 +#define MADERA_DCS_HP1R_CONTROL 0x238 +#define MADERA_EDRE_HP_STEREO_CONTROL 0x27E +#define MADERA_ACCESSORY_DETECT_MODE_1 0x293 +#define MADERA_HEADPHONE_DETECT_0 0x299 +#define MADERA_HEADPHONE_DETECT_1 0x29B +#define MADERA_HEADPHONE_DETECT_2 0x29C +#define MADERA_HEADPHONE_DETECT_3 0x29D +#define MADERA_HEADPHONE_DETECT_4 0x29E +#define MADERA_HEADPHONE_DETECT_5 0x29F +#define MADERA_MIC_DETECT_1_CONTROL_0 0x2A2 +#define MADERA_MIC_DETECT_1_CONTROL_1 0x2A3 +#define MADERA_MIC_DETECT_1_CONTROL_2 0x2A4 +#define MADERA_MIC_DETECT_1_CONTROL_3 0x2A5 +#define MADERA_MIC_DETECT_1_LEVEL_1 0x2A6 +#define MADERA_MIC_DETECT_1_LEVEL_2 0x2A7 +#define MADERA_MIC_DETECT_1_LEVEL_3 0x2A8 +#define MADERA_MIC_DETECT_1_LEVEL_4 0x2A9 +#define MADERA_MIC_DETECT_1_CONTROL_4 0x2AB +#define MADERA_MIC_DETECT_2_CONTROL_0 0x2B2 +#define MADERA_MIC_DETECT_2_CONTROL_1 0x2B3 +#define MADERA_MIC_DETECT_2_CONTROL_2 0x2B4 +#define MADERA_MIC_DETECT_2_CONTROL_3 0x2B5 +#define MADERA_MIC_DETECT_2_LEVEL_1 0x2B6 +#define MADERA_MIC_DETECT_2_LEVEL_2 0x2B7 +#define MADERA_MIC_DETECT_2_LEVEL_3 0x2B8 +#define MADERA_MIC_DETECT_2_LEVEL_4 0x2B9 +#define MADERA_MIC_DETECT_2_CONTROL_4 0x2BB +#define MADERA_MICD_CLAMP_CONTROL 0x2C6 +#define MADERA_GP_SWITCH_1 0x2C8 +#define MADERA_JACK_DETECT_ANALOGUE 0x2D3 +#define MADERA_INPUT_ENABLES 0x300 +#define MADERA_INPUT_ENABLES_STATUS 0x301 +#define MADERA_INPUT_RATE 0x308 +#define MADERA_INPUT_VOLUME_RAMP 0x309 +#define MADERA_HPF_CONTROL 0x30C +#define MADERA_IN1L_CONTROL 0x310 +#define MADERA_ADC_DIGITAL_VOLUME_1L 0x311 +#define MADERA_DMIC1L_CONTROL 0x312 +#define MADERA_IN1L_RATE_CONTROL 0x313 +#define MADERA_IN1R_CONTROL 0x314 +#define MADERA_ADC_DIGITAL_VOLUME_1R 0x315 +#define MADERA_DMIC1R_CONTROL 0x316 +#define MADERA_IN1R_RATE_CONTROL 0x317 +#define MADERA_IN2L_CONTROL 0x318 +#define MADERA_ADC_DIGITAL_VOLUME_2L 0x319 +#define MADERA_DMIC2L_CONTROL 0x31A +#define MADERA_IN2L_RATE_CONTROL 0x31B +#define MADERA_IN2R_CONTROL 0x31C +#define MADERA_ADC_DIGITAL_VOLUME_2R 0x31D +#define MADERA_DMIC2R_CONTROL 0x31E +#define MADERA_IN2R_RATE_CONTROL 0x31F +#define MADERA_IN3L_CONTROL 0x320 +#define MADERA_ADC_DIGITAL_VOLUME_3L 0x321 +#define MADERA_DMIC3L_CONTROL 0x322 +#define MADERA_IN3L_RATE_CONTROL 0x323 +#define MADERA_IN3R_CONTROL 0x324 +#define MADERA_ADC_DIGITAL_VOLUME_3R 0x325 +#define MADERA_DMIC3R_CONTROL 0x326 +#define MADERA_IN3R_RATE_CONTROL 0x327 +#define MADERA_IN4L_CONTROL 0x328 +#define MADERA_ADC_DIGITAL_VOLUME_4L 0x329 +#define MADERA_DMIC4L_CONTROL 0x32A +#define MADERA_IN4L_RATE_CONTROL 0x32B +#define MADERA_IN4R_CONTROL 0x32C +#define MADERA_ADC_DIGITAL_VOLUME_4R 0x32D +#define MADERA_DMIC4R_CONTROL 0x32E +#define MADERA_IN4R_RATE_CONTROL 0x32F +#define MADERA_IN5L_CONTROL 0x330 +#define MADERA_ADC_DIGITAL_VOLUME_5L 0x331 +#define MADERA_DMIC5L_CONTROL 0x332 +#define MADERA_IN5L_RATE_CONTROL 0x333 +#define MADERA_IN5R_CONTROL 0x334 +#define MADERA_ADC_DIGITAL_VOLUME_5R 0x335 +#define MADERA_DMIC5R_CONTROL 0x336 +#define MADERA_IN5R_RATE_CONTROL 0x337 +#define MADERA_IN6L_CONTROL 0x338 +#define MADERA_ADC_DIGITAL_VOLUME_6L 0x339 +#define MADERA_DMIC6L_CONTROL 0x33A +#define MADERA_IN6R_CONTROL 0x33C +#define MADERA_ADC_DIGITAL_VOLUME_6R 0x33D +#define MADERA_DMIC6R_CONTROL 0x33E +#define MADERA_OUTPUT_ENABLES_1 0x400 +#define MADERA_OUTPUT_STATUS_1 0x401 +#define MADERA_RAW_OUTPUT_STATUS_1 0x406 +#define MADERA_OUTPUT_RATE_1 0x408 +#define MADERA_OUTPUT_VOLUME_RAMP 0x409 +#define MADERA_OUTPUT_PATH_CONFIG_1L 0x410 +#define MADERA_DAC_DIGITAL_VOLUME_1L 0x411 +#define MADERA_OUTPUT_PATH_CONFIG_1 0x412 +#define MADERA_NOISE_GATE_SELECT_1L 0x413 +#define MADERA_OUTPUT_PATH_CONFIG_1R 0x414 +#define MADERA_DAC_DIGITAL_VOLUME_1R 0x415 +#define MADERA_NOISE_GATE_SELECT_1R 0x417 +#define MADERA_OUTPUT_PATH_CONFIG_2L 0x418 +#define MADERA_DAC_DIGITAL_VOLUME_2L 0x419 +#define MADERA_OUTPUT_PATH_CONFIG_2 0x41A +#define MADERA_NOISE_GATE_SELECT_2L 0x41B +#define MADERA_OUTPUT_PATH_CONFIG_2R 0x41C +#define MADERA_DAC_DIGITAL_VOLUME_2R 0x41D +#define MADERA_NOISE_GATE_SELECT_2R 0x41F +#define MADERA_OUTPUT_PATH_CONFIG_3L 0x420 +#define MADERA_DAC_DIGITAL_VOLUME_3L 0x421 +#define MADERA_NOISE_GATE_SELECT_3L 0x423 +#define MADERA_OUTPUT_PATH_CONFIG_3R 0x424 +#define MADERA_DAC_DIGITAL_VOLUME_3R 0x425 +#define MADERA_NOISE_GATE_SELECT_3R 0x427 +#define MADERA_OUTPUT_PATH_CONFIG_4L 0x428 +#define MADERA_DAC_DIGITAL_VOLUME_4L 0x429 +#define MADERA_NOISE_GATE_SELECT_4L 0x42B +#define MADERA_OUTPUT_PATH_CONFIG_4R 0x42C +#define MADERA_DAC_DIGITAL_VOLUME_4R 0x42D +#define MADERA_NOISE_GATE_SELECT_4R 0x42F +#define MADERA_OUTPUT_PATH_CONFIG_5L 0x430 +#define MADERA_DAC_DIGITAL_VOLUME_5L 0x431 +#define MADERA_NOISE_GATE_SELECT_5L 0x433 +#define MADERA_OUTPUT_PATH_CONFIG_5R 0x434 +#define MADERA_DAC_DIGITAL_VOLUME_5R 0x435 +#define MADERA_NOISE_GATE_SELECT_5R 0x437 +#define MADERA_OUTPUT_PATH_CONFIG_6L 0x438 +#define MADERA_DAC_DIGITAL_VOLUME_6L 0x439 +#define MADERA_NOISE_GATE_SELECT_6L 0x43B +#define MADERA_OUTPUT_PATH_CONFIG_6R 0x43C +#define MADERA_DAC_DIGITAL_VOLUME_6R 0x43D +#define MADERA_NOISE_GATE_SELECT_6R 0x43F +#define MADERA_DRE_ENABLE 0x440 +#define MADERA_EDRE_ENABLE 0x448 +#define MADERA_EDRE_MANUAL 0x44A +#define MADERA_DAC_AEC_CONTROL_1 0x450 +#define MADERA_DAC_AEC_CONTROL_2 0x451 +#define MADERA_NOISE_GATE_CONTROL 0x458 +#define MADERA_PDM_SPK1_CTRL_1 0x490 +#define MADERA_PDM_SPK1_CTRL_2 0x491 +#define MADERA_PDM_SPK2_CTRL_1 0x492 +#define MADERA_PDM_SPK2_CTRL_2 0x493 +#define MADERA_HP1_SHORT_CIRCUIT_CTRL 0x4A0 +#define MADERA_HP2_SHORT_CIRCUIT_CTRL 0x4A1 +#define MADERA_HP3_SHORT_CIRCUIT_CTRL 0x4A2 +#define MADERA_HP_TEST_CTRL_1 0x4A4 +#define MADERA_HP_TEST_CTRL_5 0x4A8 +#define MADERA_HP_TEST_CTRL_6 0x4A9 +#define MADERA_AIF1_BCLK_CTRL 0x500 +#define MADERA_AIF1_TX_PIN_CTRL 0x501 +#define MADERA_AIF1_RX_PIN_CTRL 0x502 +#define MADERA_AIF1_RATE_CTRL 0x503 +#define MADERA_AIF1_FORMAT 0x504 +#define MADERA_AIF1_RX_BCLK_RATE 0x506 +#define MADERA_AIF1_FRAME_CTRL_1 0x507 +#define MADERA_AIF1_FRAME_CTRL_2 0x508 +#define MADERA_AIF1_FRAME_CTRL_3 0x509 +#define MADERA_AIF1_FRAME_CTRL_4 0x50A +#define MADERA_AIF1_FRAME_CTRL_5 0x50B +#define MADERA_AIF1_FRAME_CTRL_6 0x50C +#define MADERA_AIF1_FRAME_CTRL_7 0x50D +#define MADERA_AIF1_FRAME_CTRL_8 0x50E +#define MADERA_AIF1_FRAME_CTRL_9 0x50F +#define MADERA_AIF1_FRAME_CTRL_10 0x510 +#define MADERA_AIF1_FRAME_CTRL_11 0x511 +#define MADERA_AIF1_FRAME_CTRL_12 0x512 +#define MADERA_AIF1_FRAME_CTRL_13 0x513 +#define MADERA_AIF1_FRAME_CTRL_14 0x514 +#define MADERA_AIF1_FRAME_CTRL_15 0x515 +#define MADERA_AIF1_FRAME_CTRL_16 0x516 +#define MADERA_AIF1_FRAME_CTRL_17 0x517 +#define MADERA_AIF1_FRAME_CTRL_18 0x518 +#define MADERA_AIF1_TX_ENABLES 0x519 +#define MADERA_AIF1_RX_ENABLES 0x51A +#define MADERA_AIF1_FORCE_WRITE 0x51B +#define MADERA_AIF2_BCLK_CTRL 0x540 +#define MADERA_AIF2_TX_PIN_CTRL 0x541 +#define MADERA_AIF2_RX_PIN_CTRL 0x542 +#define MADERA_AIF2_RATE_CTRL 0x543 +#define MADERA_AIF2_FORMAT 0x544 +#define MADERA_AIF2_RX_BCLK_RATE 0x546 +#define MADERA_AIF2_FRAME_CTRL_1 0x547 +#define MADERA_AIF2_FRAME_CTRL_2 0x548 +#define MADERA_AIF2_FRAME_CTRL_3 0x549 +#define MADERA_AIF2_FRAME_CTRL_4 0x54A +#define MADERA_AIF2_FRAME_CTRL_5 0x54B +#define MADERA_AIF2_FRAME_CTRL_6 0x54C +#define MADERA_AIF2_FRAME_CTRL_7 0x54D +#define MADERA_AIF2_FRAME_CTRL_8 0x54E +#define MADERA_AIF2_FRAME_CTRL_9 0x54F +#define MADERA_AIF2_FRAME_CTRL_10 0x550 +#define MADERA_AIF2_FRAME_CTRL_11 0x551 +#define MADERA_AIF2_FRAME_CTRL_12 0x552 +#define MADERA_AIF2_FRAME_CTRL_13 0x553 +#define MADERA_AIF2_FRAME_CTRL_14 0x554 +#define MADERA_AIF2_FRAME_CTRL_15 0x555 +#define MADERA_AIF2_FRAME_CTRL_16 0x556 +#define MADERA_AIF2_FRAME_CTRL_17 0x557 +#define MADERA_AIF2_FRAME_CTRL_18 0x558 +#define MADERA_AIF2_TX_ENABLES 0x559 +#define MADERA_AIF2_RX_ENABLES 0x55A +#define MADERA_AIF2_FORCE_WRITE 0x55B +#define MADERA_AIF3_BCLK_CTRL 0x580 +#define MADERA_AIF3_TX_PIN_CTRL 0x581 +#define MADERA_AIF3_RX_PIN_CTRL 0x582 +#define MADERA_AIF3_RATE_CTRL 0x583 +#define MADERA_AIF3_FORMAT 0x584 +#define MADERA_AIF3_RX_BCLK_RATE 0x586 +#define MADERA_AIF3_FRAME_CTRL_1 0x587 +#define MADERA_AIF3_FRAME_CTRL_2 0x588 +#define MADERA_AIF3_FRAME_CTRL_3 0x589 +#define MADERA_AIF3_FRAME_CTRL_4 0x58A +#define MADERA_AIF3_FRAME_CTRL_11 0x591 +#define MADERA_AIF3_FRAME_CTRL_12 0x592 +#define MADERA_AIF3_TX_ENABLES 0x599 +#define MADERA_AIF3_RX_ENABLES 0x59A +#define MADERA_AIF3_FORCE_WRITE 0x59B +#define MADERA_AIF4_BCLK_CTRL 0x5A0 +#define MADERA_AIF4_TX_PIN_CTRL 0x5A1 +#define MADERA_AIF4_RX_PIN_CTRL 0x5A2 +#define MADERA_AIF4_RATE_CTRL 0x5A3 +#define MADERA_AIF4_FORMAT 0x5A4 +#define MADERA_AIF4_RX_BCLK_RATE 0x5A6 +#define MADERA_AIF4_FRAME_CTRL_1 0x5A7 +#define MADERA_AIF4_FRAME_CTRL_2 0x5A8 +#define MADERA_AIF4_FRAME_CTRL_3 0x5A9 +#define MADERA_AIF4_FRAME_CTRL_4 0x5AA +#define MADERA_AIF4_FRAME_CTRL_11 0x5B1 +#define MADERA_AIF4_FRAME_CTRL_12 0x5B2 +#define MADERA_AIF4_TX_ENABLES 0x5B9 +#define MADERA_AIF4_RX_ENABLES 0x5BA +#define MADERA_AIF4_FORCE_WRITE 0x5BB +#define MADERA_SPD1_TX_CONTROL 0x5C2 +#define MADERA_SPD1_TX_CHANNEL_STATUS_1 0x5C3 +#define MADERA_SPD1_TX_CHANNEL_STATUS_2 0x5C4 +#define MADERA_SPD1_TX_CHANNEL_STATUS_3 0x5C5 +#define MADERA_SLIMBUS_FRAMER_REF_GEAR 0x5E3 +#define MADERA_SLIMBUS_RATES_1 0x5E5 +#define MADERA_SLIMBUS_RATES_2 0x5E6 +#define MADERA_SLIMBUS_RATES_3 0x5E7 +#define MADERA_SLIMBUS_RATES_4 0x5E8 +#define MADERA_SLIMBUS_RATES_5 0x5E9 +#define MADERA_SLIMBUS_RATES_6 0x5EA +#define MADERA_SLIMBUS_RATES_7 0x5EB +#define MADERA_SLIMBUS_RATES_8 0x5EC +#define MADERA_SLIMBUS_RX_CHANNEL_ENABLE 0x5F5 +#define MADERA_SLIMBUS_TX_CHANNEL_ENABLE 0x5F6 +#define MADERA_SLIMBUS_RX_PORT_STATUS 0x5F7 +#define MADERA_SLIMBUS_TX_PORT_STATUS 0x5F8 +#define MADERA_PWM1MIX_INPUT_1_SOURCE 0x640 +#define MADERA_PWM1MIX_INPUT_1_VOLUME 0x641 +#define MADERA_PWM1MIX_INPUT_2_SOURCE 0x642 +#define MADERA_PWM1MIX_INPUT_2_VOLUME 0x643 +#define MADERA_PWM1MIX_INPUT_3_SOURCE 0x644 +#define MADERA_PWM1MIX_INPUT_3_VOLUME 0x645 +#define MADERA_PWM1MIX_INPUT_4_SOURCE 0x646 +#define MADERA_PWM1MIX_INPUT_4_VOLUME 0x647 +#define MADERA_PWM2MIX_INPUT_1_SOURCE 0x648 +#define MADERA_PWM2MIX_INPUT_1_VOLUME 0x649 +#define MADERA_PWM2MIX_INPUT_2_SOURCE 0x64A +#define MADERA_PWM2MIX_INPUT_2_VOLUME 0x64B +#define MADERA_PWM2MIX_INPUT_3_SOURCE 0x64C +#define MADERA_PWM2MIX_INPUT_3_VOLUME 0x64D +#define MADERA_PWM2MIX_INPUT_4_SOURCE 0x64E +#define MADERA_PWM2MIX_INPUT_4_VOLUME 0x64F +#define MADERA_OUT1LMIX_INPUT_1_SOURCE 0x680 +#define MADERA_OUT1LMIX_INPUT_1_VOLUME 0x681 +#define MADERA_OUT1LMIX_INPUT_2_SOURCE 0x682 +#define MADERA_OUT1LMIX_INPUT_2_VOLUME 0x683 +#define MADERA_OUT1LMIX_INPUT_3_SOURCE 0x684 +#define MADERA_OUT1LMIX_INPUT_3_VOLUME 0x685 +#define MADERA_OUT1LMIX_INPUT_4_SOURCE 0x686 +#define MADERA_OUT1LMIX_INPUT_4_VOLUME 0x687 +#define MADERA_OUT1RMIX_INPUT_1_SOURCE 0x688 +#define MADERA_OUT1RMIX_INPUT_1_VOLUME 0x689 +#define MADERA_OUT1RMIX_INPUT_2_SOURCE 0x68A +#define MADERA_OUT1RMIX_INPUT_2_VOLUME 0x68B +#define MADERA_OUT1RMIX_INPUT_3_SOURCE 0x68C +#define MADERA_OUT1RMIX_INPUT_3_VOLUME 0x68D +#define MADERA_OUT1RMIX_INPUT_4_SOURCE 0x68E +#define MADERA_OUT1RMIX_INPUT_4_VOLUME 0x68F +#define MADERA_OUT2LMIX_INPUT_1_SOURCE 0x690 +#define MADERA_OUT2LMIX_INPUT_1_VOLUME 0x691 +#define MADERA_OUT2LMIX_INPUT_2_SOURCE 0x692 +#define MADERA_OUT2LMIX_INPUT_2_VOLUME 0x693 +#define MADERA_OUT2LMIX_INPUT_3_SOURCE 0x694 +#define MADERA_OUT2LMIX_INPUT_3_VOLUME 0x695 +#define MADERA_OUT2LMIX_INPUT_4_SOURCE 0x696 +#define MADERA_OUT2LMIX_INPUT_4_VOLUME 0x697 +#define MADERA_OUT2RMIX_INPUT_1_SOURCE 0x698 +#define MADERA_OUT2RMIX_INPUT_1_VOLUME 0x699 +#define MADERA_OUT2RMIX_INPUT_2_SOURCE 0x69A +#define MADERA_OUT2RMIX_INPUT_2_VOLUME 0x69B +#define MADERA_OUT2RMIX_INPUT_3_SOURCE 0x69C +#define MADERA_OUT2RMIX_INPUT_3_VOLUME 0x69D +#define MADERA_OUT2RMIX_INPUT_4_SOURCE 0x69E +#define MADERA_OUT2RMIX_INPUT_4_VOLUME 0x69F +#define MADERA_OUT3LMIX_INPUT_1_SOURCE 0x6A0 +#define MADERA_OUT3LMIX_INPUT_1_VOLUME 0x6A1 +#define MADERA_OUT3LMIX_INPUT_2_SOURCE 0x6A2 +#define MADERA_OUT3LMIX_INPUT_2_VOLUME 0x6A3 +#define MADERA_OUT3LMIX_INPUT_3_SOURCE 0x6A4 +#define MADERA_OUT3LMIX_INPUT_3_VOLUME 0x6A5 +#define MADERA_OUT3LMIX_INPUT_4_SOURCE 0x6A6 +#define MADERA_OUT3LMIX_INPUT_4_VOLUME 0x6A7 +#define MADERA_OUT3RMIX_INPUT_1_SOURCE 0x6A8 +#define MADERA_OUT3RMIX_INPUT_1_VOLUME 0x6A9 +#define MADERA_OUT3RMIX_INPUT_2_SOURCE 0x6AA +#define MADERA_OUT3RMIX_INPUT_2_VOLUME 0x6AB +#define MADERA_OUT3RMIX_INPUT_3_SOURCE 0x6AC +#define MADERA_OUT3RMIX_INPUT_3_VOLUME 0x6AD +#define MADERA_OUT3RMIX_INPUT_4_SOURCE 0x6AE +#define MADERA_OUT3RMIX_INPUT_4_VOLUME 0x6AF +#define MADERA_OUT4LMIX_INPUT_1_SOURCE 0x6B0 +#define MADERA_OUT4LMIX_INPUT_1_VOLUME 0x6B1 +#define MADERA_OUT4LMIX_INPUT_2_SOURCE 0x6B2 +#define MADERA_OUT4LMIX_INPUT_2_VOLUME 0x6B3 +#define MADERA_OUT4LMIX_INPUT_3_SOURCE 0x6B4 +#define MADERA_OUT4LMIX_INPUT_3_VOLUME 0x6B5 +#define MADERA_OUT4LMIX_INPUT_4_SOURCE 0x6B6 +#define MADERA_OUT4LMIX_INPUT_4_VOLUME 0x6B7 +#define MADERA_OUT4RMIX_INPUT_1_SOURCE 0x6B8 +#define MADERA_OUT4RMIX_INPUT_1_VOLUME 0x6B9 +#define MADERA_OUT4RMIX_INPUT_2_SOURCE 0x6BA +#define MADERA_OUT4RMIX_INPUT_2_VOLUME 0x6BB +#define MADERA_OUT4RMIX_INPUT_3_SOURCE 0x6BC +#define MADERA_OUT4RMIX_INPUT_3_VOLUME 0x6BD +#define MADERA_OUT4RMIX_INPUT_4_SOURCE 0x6BE +#define MADERA_OUT4RMIX_INPUT_4_VOLUME 0x6BF +#define MADERA_OUT5LMIX_INPUT_1_SOURCE 0x6C0 +#define MADERA_OUT5LMIX_INPUT_1_VOLUME 0x6C1 +#define MADERA_OUT5LMIX_INPUT_2_SOURCE 0x6C2 +#define MADERA_OUT5LMIX_INPUT_2_VOLUME 0x6C3 +#define MADERA_OUT5LMIX_INPUT_3_SOURCE 0x6C4 +#define MADERA_OUT5LMIX_INPUT_3_VOLUME 0x6C5 +#define MADERA_OUT5LMIX_INPUT_4_SOURCE 0x6C6 +#define MADERA_OUT5LMIX_INPUT_4_VOLUME 0x6C7 +#define MADERA_OUT5RMIX_INPUT_1_SOURCE 0x6C8 +#define MADERA_OUT5RMIX_INPUT_1_VOLUME 0x6C9 +#define MADERA_OUT5RMIX_INPUT_2_SOURCE 0x6CA +#define MADERA_OUT5RMIX_INPUT_2_VOLUME 0x6CB +#define MADERA_OUT5RMIX_INPUT_3_SOURCE 0x6CC +#define MADERA_OUT5RMIX_INPUT_3_VOLUME 0x6CD +#define MADERA_OUT5RMIX_INPUT_4_SOURCE 0x6CE +#define MADERA_OUT5RMIX_INPUT_4_VOLUME 0x6CF +#define MADERA_OUT6LMIX_INPUT_1_SOURCE 0x6D0 +#define MADERA_OUT6LMIX_INPUT_1_VOLUME 0x6D1 +#define MADERA_OUT6LMIX_INPUT_2_SOURCE 0x6D2 +#define MADERA_OUT6LMIX_INPUT_2_VOLUME 0x6D3 +#define MADERA_OUT6LMIX_INPUT_3_SOURCE 0x6D4 +#define MADERA_OUT6LMIX_INPUT_3_VOLUME 0x6D5 +#define MADERA_OUT6LMIX_INPUT_4_SOURCE 0x6D6 +#define MADERA_OUT6LMIX_INPUT_4_VOLUME 0x6D7 +#define MADERA_OUT6RMIX_INPUT_1_SOURCE 0x6D8 +#define MADERA_OUT6RMIX_INPUT_1_VOLUME 0x6D9 +#define MADERA_OUT6RMIX_INPUT_2_SOURCE 0x6DA +#define MADERA_OUT6RMIX_INPUT_2_VOLUME 0x6DB +#define MADERA_OUT6RMIX_INPUT_3_SOURCE 0x6DC +#define MADERA_OUT6RMIX_INPUT_3_VOLUME 0x6DD +#define MADERA_OUT6RMIX_INPUT_4_SOURCE 0x6DE +#define MADERA_OUT6RMIX_INPUT_4_VOLUME 0x6DF +#define MADERA_AIF1TX1MIX_INPUT_1_SOURCE 0x700 +#define MADERA_AIF1TX1MIX_INPUT_1_VOLUME 0x701 +#define MADERA_AIF1TX1MIX_INPUT_2_SOURCE 0x702 +#define MADERA_AIF1TX1MIX_INPUT_2_VOLUME 0x703 +#define MADERA_AIF1TX1MIX_INPUT_3_SOURCE 0x704 +#define MADERA_AIF1TX1MIX_INPUT_3_VOLUME 0x705 +#define MADERA_AIF1TX1MIX_INPUT_4_SOURCE 0x706 +#define MADERA_AIF1TX1MIX_INPUT_4_VOLUME 0x707 +#define MADERA_AIF1TX2MIX_INPUT_1_SOURCE 0x708 +#define MADERA_AIF1TX2MIX_INPUT_1_VOLUME 0x709 +#define MADERA_AIF1TX2MIX_INPUT_2_SOURCE 0x70A +#define MADERA_AIF1TX2MIX_INPUT_2_VOLUME 0x70B +#define MADERA_AIF1TX2MIX_INPUT_3_SOURCE 0x70C +#define MADERA_AIF1TX2MIX_INPUT_3_VOLUME 0x70D +#define MADERA_AIF1TX2MIX_INPUT_4_SOURCE 0x70E +#define MADERA_AIF1TX2MIX_INPUT_4_VOLUME 0x70F +#define MADERA_AIF1TX3MIX_INPUT_1_SOURCE 0x710 +#define MADERA_AIF1TX3MIX_INPUT_1_VOLUME 0x711 +#define MADERA_AIF1TX3MIX_INPUT_2_SOURCE 0x712 +#define MADERA_AIF1TX3MIX_INPUT_2_VOLUME 0x713 +#define MADERA_AIF1TX3MIX_INPUT_3_SOURCE 0x714 +#define MADERA_AIF1TX3MIX_INPUT_3_VOLUME 0x715 +#define MADERA_AIF1TX3MIX_INPUT_4_SOURCE 0x716 +#define MADERA_AIF1TX3MIX_INPUT_4_VOLUME 0x717 +#define MADERA_AIF1TX4MIX_INPUT_1_SOURCE 0x718 +#define MADERA_AIF1TX4MIX_INPUT_1_VOLUME 0x719 +#define MADERA_AIF1TX4MIX_INPUT_2_SOURCE 0x71A +#define MADERA_AIF1TX4MIX_INPUT_2_VOLUME 0x71B +#define MADERA_AIF1TX4MIX_INPUT_3_SOURCE 0x71C +#define MADERA_AIF1TX4MIX_INPUT_3_VOLUME 0x71D +#define MADERA_AIF1TX4MIX_INPUT_4_SOURCE 0x71E +#define MADERA_AIF1TX4MIX_INPUT_4_VOLUME 0x71F +#define MADERA_AIF1TX5MIX_INPUT_1_SOURCE 0x720 +#define MADERA_AIF1TX5MIX_INPUT_1_VOLUME 0x721 +#define MADERA_AIF1TX5MIX_INPUT_2_SOURCE 0x722 +#define MADERA_AIF1TX5MIX_INPUT_2_VOLUME 0x723 +#define MADERA_AIF1TX5MIX_INPUT_3_SOURCE 0x724 +#define MADERA_AIF1TX5MIX_INPUT_3_VOLUME 0x725 +#define MADERA_AIF1TX5MIX_INPUT_4_SOURCE 0x726 +#define MADERA_AIF1TX5MIX_INPUT_4_VOLUME 0x727 +#define MADERA_AIF1TX6MIX_INPUT_1_SOURCE 0x728 +#define MADERA_AIF1TX6MIX_INPUT_1_VOLUME 0x729 +#define MADERA_AIF1TX6MIX_INPUT_2_SOURCE 0x72A +#define MADERA_AIF1TX6MIX_INPUT_2_VOLUME 0x72B +#define MADERA_AIF1TX6MIX_INPUT_3_SOURCE 0x72C +#define MADERA_AIF1TX6MIX_INPUT_3_VOLUME 0x72D +#define MADERA_AIF1TX6MIX_INPUT_4_SOURCE 0x72E +#define MADERA_AIF1TX6MIX_INPUT_4_VOLUME 0x72F +#define MADERA_AIF1TX7MIX_INPUT_1_SOURCE 0x730 +#define MADERA_AIF1TX7MIX_INPUT_1_VOLUME 0x731 +#define MADERA_AIF1TX7MIX_INPUT_2_SOURCE 0x732 +#define MADERA_AIF1TX7MIX_INPUT_2_VOLUME 0x733 +#define MADERA_AIF1TX7MIX_INPUT_3_SOURCE 0x734 +#define MADERA_AIF1TX7MIX_INPUT_3_VOLUME 0x735 +#define MADERA_AIF1TX7MIX_INPUT_4_SOURCE 0x736 +#define MADERA_AIF1TX7MIX_INPUT_4_VOLUME 0x737 +#define MADERA_AIF1TX8MIX_INPUT_1_SOURCE 0x738 +#define MADERA_AIF1TX8MIX_INPUT_1_VOLUME 0x739 +#define MADERA_AIF1TX8MIX_INPUT_2_SOURCE 0x73A +#define MADERA_AIF1TX8MIX_INPUT_2_VOLUME 0x73B +#define MADERA_AIF1TX8MIX_INPUT_3_SOURCE 0x73C +#define MADERA_AIF1TX8MIX_INPUT_3_VOLUME 0x73D +#define MADERA_AIF1TX8MIX_INPUT_4_SOURCE 0x73E +#define MADERA_AIF1TX8MIX_INPUT_4_VOLUME 0x73F +#define MADERA_AIF2TX1MIX_INPUT_1_SOURCE 0x740 +#define MADERA_AIF2TX1MIX_INPUT_1_VOLUME 0x741 +#define MADERA_AIF2TX1MIX_INPUT_2_SOURCE 0x742 +#define MADERA_AIF2TX1MIX_INPUT_2_VOLUME 0x743 +#define MADERA_AIF2TX1MIX_INPUT_3_SOURCE 0x744 +#define MADERA_AIF2TX1MIX_INPUT_3_VOLUME 0x745 +#define MADERA_AIF2TX1MIX_INPUT_4_SOURCE 0x746 +#define MADERA_AIF2TX1MIX_INPUT_4_VOLUME 0x747 +#define MADERA_AIF2TX2MIX_INPUT_1_SOURCE 0x748 +#define MADERA_AIF2TX2MIX_INPUT_1_VOLUME 0x749 +#define MADERA_AIF2TX2MIX_INPUT_2_SOURCE 0x74A +#define MADERA_AIF2TX2MIX_INPUT_2_VOLUME 0x74B +#define MADERA_AIF2TX2MIX_INPUT_3_SOURCE 0x74C +#define MADERA_AIF2TX2MIX_INPUT_3_VOLUME 0x74D +#define MADERA_AIF2TX2MIX_INPUT_4_SOURCE 0x74E +#define MADERA_AIF2TX2MIX_INPUT_4_VOLUME 0x74F +#define MADERA_AIF2TX3MIX_INPUT_1_SOURCE 0x750 +#define MADERA_AIF2TX3MIX_INPUT_1_VOLUME 0x751 +#define MADERA_AIF2TX3MIX_INPUT_2_SOURCE 0x752 +#define MADERA_AIF2TX3MIX_INPUT_2_VOLUME 0x753 +#define MADERA_AIF2TX3MIX_INPUT_3_SOURCE 0x754 +#define MADERA_AIF2TX3MIX_INPUT_3_VOLUME 0x755 +#define MADERA_AIF2TX3MIX_INPUT_4_SOURCE 0x756 +#define MADERA_AIF2TX3MIX_INPUT_4_VOLUME 0x757 +#define MADERA_AIF2TX4MIX_INPUT_1_SOURCE 0x758 +#define MADERA_AIF2TX4MIX_INPUT_1_VOLUME 0x759 +#define MADERA_AIF2TX4MIX_INPUT_2_SOURCE 0x75A +#define MADERA_AIF2TX4MIX_INPUT_2_VOLUME 0x75B +#define MADERA_AIF2TX4MIX_INPUT_3_SOURCE 0x75C +#define MADERA_AIF2TX4MIX_INPUT_3_VOLUME 0x75D +#define MADERA_AIF2TX4MIX_INPUT_4_SOURCE 0x75E +#define MADERA_AIF2TX4MIX_INPUT_4_VOLUME 0x75F +#define MADERA_AIF2TX5MIX_INPUT_1_SOURCE 0x760 +#define MADERA_AIF2TX5MIX_INPUT_1_VOLUME 0x761 +#define MADERA_AIF2TX5MIX_INPUT_2_SOURCE 0x762 +#define MADERA_AIF2TX5MIX_INPUT_2_VOLUME 0x763 +#define MADERA_AIF2TX5MIX_INPUT_3_SOURCE 0x764 +#define MADERA_AIF2TX5MIX_INPUT_3_VOLUME 0x765 +#define MADERA_AIF2TX5MIX_INPUT_4_SOURCE 0x766 +#define MADERA_AIF2TX5MIX_INPUT_4_VOLUME 0x767 +#define MADERA_AIF2TX6MIX_INPUT_1_SOURCE 0x768 +#define MADERA_AIF2TX6MIX_INPUT_1_VOLUME 0x769 +#define MADERA_AIF2TX6MIX_INPUT_2_SOURCE 0x76A +#define MADERA_AIF2TX6MIX_INPUT_2_VOLUME 0x76B +#define MADERA_AIF2TX6MIX_INPUT_3_SOURCE 0x76C +#define MADERA_AIF2TX6MIX_INPUT_3_VOLUME 0x76D +#define MADERA_AIF2TX6MIX_INPUT_4_SOURCE 0x76E +#define MADERA_AIF2TX6MIX_INPUT_4_VOLUME 0x76F +#define MADERA_AIF2TX7MIX_INPUT_1_SOURCE 0x770 +#define MADERA_AIF2TX7MIX_INPUT_1_VOLUME 0x771 +#define MADERA_AIF2TX7MIX_INPUT_2_SOURCE 0x772 +#define MADERA_AIF2TX7MIX_INPUT_2_VOLUME 0x773 +#define MADERA_AIF2TX7MIX_INPUT_3_SOURCE 0x774 +#define MADERA_AIF2TX7MIX_INPUT_3_VOLUME 0x775 +#define MADERA_AIF2TX7MIX_INPUT_4_SOURCE 0x776 +#define MADERA_AIF2TX7MIX_INPUT_4_VOLUME 0x777 +#define MADERA_AIF2TX8MIX_INPUT_1_SOURCE 0x778 +#define MADERA_AIF2TX8MIX_INPUT_1_VOLUME 0x779 +#define MADERA_AIF2TX8MIX_INPUT_2_SOURCE 0x77A +#define MADERA_AIF2TX8MIX_INPUT_2_VOLUME 0x77B +#define MADERA_AIF2TX8MIX_INPUT_3_SOURCE 0x77C +#define MADERA_AIF2TX8MIX_INPUT_3_VOLUME 0x77D +#define MADERA_AIF2TX8MIX_INPUT_4_SOURCE 0x77E +#define MADERA_AIF2TX8MIX_INPUT_4_VOLUME 0x77F +#define MADERA_AIF3TX1MIX_INPUT_1_SOURCE 0x780 +#define MADERA_AIF3TX1MIX_INPUT_1_VOLUME 0x781 +#define MADERA_AIF3TX1MIX_INPUT_2_SOURCE 0x782 +#define MADERA_AIF3TX1MIX_INPUT_2_VOLUME 0x783 +#define MADERA_AIF3TX1MIX_INPUT_3_SOURCE 0x784 +#define MADERA_AIF3TX1MIX_INPUT_3_VOLUME 0x785 +#define MADERA_AIF3TX1MIX_INPUT_4_SOURCE 0x786 +#define MADERA_AIF3TX1MIX_INPUT_4_VOLUME 0x787 +#define MADERA_AIF3TX2MIX_INPUT_1_SOURCE 0x788 +#define MADERA_AIF3TX2MIX_INPUT_1_VOLUME 0x789 +#define MADERA_AIF3TX2MIX_INPUT_2_SOURCE 0x78A +#define MADERA_AIF3TX2MIX_INPUT_2_VOLUME 0x78B +#define MADERA_AIF3TX2MIX_INPUT_3_SOURCE 0x78C +#define MADERA_AIF3TX2MIX_INPUT_3_VOLUME 0x78D +#define MADERA_AIF3TX2MIX_INPUT_4_SOURCE 0x78E +#define MADERA_AIF3TX2MIX_INPUT_4_VOLUME 0x78F +#define MADERA_AIF4TX1MIX_INPUT_1_SOURCE 0x7A0 +#define MADERA_AIF4TX1MIX_INPUT_1_VOLUME 0x7A1 +#define MADERA_AIF4TX1MIX_INPUT_2_SOURCE 0x7A2 +#define MADERA_AIF4TX1MIX_INPUT_2_VOLUME 0x7A3 +#define MADERA_AIF4TX1MIX_INPUT_3_SOURCE 0x7A4 +#define MADERA_AIF4TX1MIX_INPUT_3_VOLUME 0x7A5 +#define MADERA_AIF4TX1MIX_INPUT_4_SOURCE 0x7A6 +#define MADERA_AIF4TX1MIX_INPUT_4_VOLUME 0x7A7 +#define MADERA_AIF4TX2MIX_INPUT_1_SOURCE 0x7A8 +#define MADERA_AIF4TX2MIX_INPUT_1_VOLUME 0x7A9 +#define MADERA_AIF4TX2MIX_INPUT_2_SOURCE 0x7AA +#define MADERA_AIF4TX2MIX_INPUT_2_VOLUME 0x7AB +#define MADERA_AIF4TX2MIX_INPUT_3_SOURCE 0x7AC +#define MADERA_AIF4TX2MIX_INPUT_3_VOLUME 0x7AD +#define MADERA_AIF4TX2MIX_INPUT_4_SOURCE 0x7AE +#define MADERA_AIF4TX2MIX_INPUT_4_VOLUME 0x7AF +#define MADERA_SLIMTX1MIX_INPUT_1_SOURCE 0x7C0 +#define MADERA_SLIMTX1MIX_INPUT_1_VOLUME 0x7C1 +#define MADERA_SLIMTX1MIX_INPUT_2_SOURCE 0x7C2 +#define MADERA_SLIMTX1MIX_INPUT_2_VOLUME 0x7C3 +#define MADERA_SLIMTX1MIX_INPUT_3_SOURCE 0x7C4 +#define MADERA_SLIMTX1MIX_INPUT_3_VOLUME 0x7C5 +#define MADERA_SLIMTX1MIX_INPUT_4_SOURCE 0x7C6 +#define MADERA_SLIMTX1MIX_INPUT_4_VOLUME 0x7C7 +#define MADERA_SLIMTX2MIX_INPUT_1_SOURCE 0x7C8 +#define MADERA_SLIMTX2MIX_INPUT_1_VOLUME 0x7C9 +#define MADERA_SLIMTX2MIX_INPUT_2_SOURCE 0x7CA +#define MADERA_SLIMTX2MIX_INPUT_2_VOLUME 0x7CB +#define MADERA_SLIMTX2MIX_INPUT_3_SOURCE 0x7CC +#define MADERA_SLIMTX2MIX_INPUT_3_VOLUME 0x7CD +#define MADERA_SLIMTX2MIX_INPUT_4_SOURCE 0x7CE +#define MADERA_SLIMTX2MIX_INPUT_4_VOLUME 0x7CF +#define MADERA_SLIMTX3MIX_INPUT_1_SOURCE 0x7D0 +#define MADERA_SLIMTX3MIX_INPUT_1_VOLUME 0x7D1 +#define MADERA_SLIMTX3MIX_INPUT_2_SOURCE 0x7D2 +#define MADERA_SLIMTX3MIX_INPUT_2_VOLUME 0x7D3 +#define MADERA_SLIMTX3MIX_INPUT_3_SOURCE 0x7D4 +#define MADERA_SLIMTX3MIX_INPUT_3_VOLUME 0x7D5 +#define MADERA_SLIMTX3MIX_INPUT_4_SOURCE 0x7D6 +#define MADERA_SLIMTX3MIX_INPUT_4_VOLUME 0x7D7 +#define MADERA_SLIMTX4MIX_INPUT_1_SOURCE 0x7D8 +#define MADERA_SLIMTX4MIX_INPUT_1_VOLUME 0x7D9 +#define MADERA_SLIMTX4MIX_INPUT_2_SOURCE 0x7DA +#define MADERA_SLIMTX4MIX_INPUT_2_VOLUME 0x7DB +#define MADERA_SLIMTX4MIX_INPUT_3_SOURCE 0x7DC +#define MADERA_SLIMTX4MIX_INPUT_3_VOLUME 0x7DD +#define MADERA_SLIMTX4MIX_INPUT_4_SOURCE 0x7DE +#define MADERA_SLIMTX4MIX_INPUT_4_VOLUME 0x7DF +#define MADERA_SLIMTX5MIX_INPUT_1_SOURCE 0x7E0 +#define MADERA_SLIMTX5MIX_INPUT_1_VOLUME 0x7E1 +#define MADERA_SLIMTX5MIX_INPUT_2_SOURCE 0x7E2 +#define MADERA_SLIMTX5MIX_INPUT_2_VOLUME 0x7E3 +#define MADERA_SLIMTX5MIX_INPUT_3_SOURCE 0x7E4 +#define MADERA_SLIMTX5MIX_INPUT_3_VOLUME 0x7E5 +#define MADERA_SLIMTX5MIX_INPUT_4_SOURCE 0x7E6 +#define MADERA_SLIMTX5MIX_INPUT_4_VOLUME 0x7E7 +#define MADERA_SLIMTX6MIX_INPUT_1_SOURCE 0x7E8 +#define MADERA_SLIMTX6MIX_INPUT_1_VOLUME 0x7E9 +#define MADERA_SLIMTX6MIX_INPUT_2_SOURCE 0x7EA +#define MADERA_SLIMTX6MIX_INPUT_2_VOLUME 0x7EB +#define MADERA_SLIMTX6MIX_INPUT_3_SOURCE 0x7EC +#define MADERA_SLIMTX6MIX_INPUT_3_VOLUME 0x7ED +#define MADERA_SLIMTX6MIX_INPUT_4_SOURCE 0x7EE +#define MADERA_SLIMTX6MIX_INPUT_4_VOLUME 0x7EF +#define MADERA_SLIMTX7MIX_INPUT_1_SOURCE 0x7F0 +#define MADERA_SLIMTX7MIX_INPUT_1_VOLUME 0x7F1 +#define MADERA_SLIMTX7MIX_INPUT_2_SOURCE 0x7F2 +#define MADERA_SLIMTX7MIX_INPUT_2_VOLUME 0x7F3 +#define MADERA_SLIMTX7MIX_INPUT_3_SOURCE 0x7F4 +#define MADERA_SLIMTX7MIX_INPUT_3_VOLUME 0x7F5 +#define MADERA_SLIMTX7MIX_INPUT_4_SOURCE 0x7F6 +#define MADERA_SLIMTX7MIX_INPUT_4_VOLUME 0x7F7 +#define MADERA_SLIMTX8MIX_INPUT_1_SOURCE 0x7F8 +#define MADERA_SLIMTX8MIX_INPUT_1_VOLUME 0x7F9 +#define MADERA_SLIMTX8MIX_INPUT_2_SOURCE 0x7FA +#define MADERA_SLIMTX8MIX_INPUT_2_VOLUME 0x7FB +#define MADERA_SLIMTX8MIX_INPUT_3_SOURCE 0x7FC +#define MADERA_SLIMTX8MIX_INPUT_3_VOLUME 0x7FD +#define MADERA_SLIMTX8MIX_INPUT_4_SOURCE 0x7FE +#define MADERA_SLIMTX8MIX_INPUT_4_VOLUME 0x7FF +#define MADERA_SPDIF1TX1MIX_INPUT_1_SOURCE 0x800 +#define MADERA_SPDIF1TX1MIX_INPUT_1_VOLUME 0x801 +#define MADERA_SPDIF1TX2MIX_INPUT_1_SOURCE 0x808 +#define MADERA_SPDIF1TX2MIX_INPUT_1_VOLUME 0x809 +#define MADERA_EQ1MIX_INPUT_1_SOURCE 0x880 +#define MADERA_EQ1MIX_INPUT_1_VOLUME 0x881 +#define MADERA_EQ1MIX_INPUT_2_SOURCE 0x882 +#define MADERA_EQ1MIX_INPUT_2_VOLUME 0x883 +#define MADERA_EQ1MIX_INPUT_3_SOURCE 0x884 +#define MADERA_EQ1MIX_INPUT_3_VOLUME 0x885 +#define MADERA_EQ1MIX_INPUT_4_SOURCE 0x886 +#define MADERA_EQ1MIX_INPUT_4_VOLUME 0x887 +#define MADERA_EQ2MIX_INPUT_1_SOURCE 0x888 +#define MADERA_EQ2MIX_INPUT_1_VOLUME 0x889 +#define MADERA_EQ2MIX_INPUT_2_SOURCE 0x88A +#define MADERA_EQ2MIX_INPUT_2_VOLUME 0x88B +#define MADERA_EQ2MIX_INPUT_3_SOURCE 0x88C +#define MADERA_EQ2MIX_INPUT_3_VOLUME 0x88D +#define MADERA_EQ2MIX_INPUT_4_SOURCE 0x88E +#define MADERA_EQ2MIX_INPUT_4_VOLUME 0x88F +#define MADERA_EQ3MIX_INPUT_1_SOURCE 0x890 +#define MADERA_EQ3MIX_INPUT_1_VOLUME 0x891 +#define MADERA_EQ3MIX_INPUT_2_SOURCE 0x892 +#define MADERA_EQ3MIX_INPUT_2_VOLUME 0x893 +#define MADERA_EQ3MIX_INPUT_3_SOURCE 0x894 +#define MADERA_EQ3MIX_INPUT_3_VOLUME 0x895 +#define MADERA_EQ3MIX_INPUT_4_SOURCE 0x896 +#define MADERA_EQ3MIX_INPUT_4_VOLUME 0x897 +#define MADERA_EQ4MIX_INPUT_1_SOURCE 0x898 +#define MADERA_EQ4MIX_INPUT_1_VOLUME 0x899 +#define MADERA_EQ4MIX_INPUT_2_SOURCE 0x89A +#define MADERA_EQ4MIX_INPUT_2_VOLUME 0x89B +#define MADERA_EQ4MIX_INPUT_3_SOURCE 0x89C +#define MADERA_EQ4MIX_INPUT_3_VOLUME 0x89D +#define MADERA_EQ4MIX_INPUT_4_SOURCE 0x89E +#define MADERA_EQ4MIX_INPUT_4_VOLUME 0x89F +#define MADERA_DRC1LMIX_INPUT_1_SOURCE 0x8C0 +#define MADERA_DRC1LMIX_INPUT_1_VOLUME 0x8C1 +#define MADERA_DRC1LMIX_INPUT_2_SOURCE 0x8C2 +#define MADERA_DRC1LMIX_INPUT_2_VOLUME 0x8C3 +#define MADERA_DRC1LMIX_INPUT_3_SOURCE 0x8C4 +#define MADERA_DRC1LMIX_INPUT_3_VOLUME 0x8C5 +#define MADERA_DRC1LMIX_INPUT_4_SOURCE 0x8C6 +#define MADERA_DRC1LMIX_INPUT_4_VOLUME 0x8C7 +#define MADERA_DRC1RMIX_INPUT_1_SOURCE 0x8C8 +#define MADERA_DRC1RMIX_INPUT_1_VOLUME 0x8C9 +#define MADERA_DRC1RMIX_INPUT_2_SOURCE 0x8CA +#define MADERA_DRC1RMIX_INPUT_2_VOLUME 0x8CB +#define MADERA_DRC1RMIX_INPUT_3_SOURCE 0x8CC +#define MADERA_DRC1RMIX_INPUT_3_VOLUME 0x8CD +#define MADERA_DRC1RMIX_INPUT_4_SOURCE 0x8CE +#define MADERA_DRC1RMIX_INPUT_4_VOLUME 0x8CF +#define MADERA_DRC2LMIX_INPUT_1_SOURCE 0x8D0 +#define MADERA_DRC2LMIX_INPUT_1_VOLUME 0x8D1 +#define MADERA_DRC2LMIX_INPUT_2_SOURCE 0x8D2 +#define MADERA_DRC2LMIX_INPUT_2_VOLUME 0x8D3 +#define MADERA_DRC2LMIX_INPUT_3_SOURCE 0x8D4 +#define MADERA_DRC2LMIX_INPUT_3_VOLUME 0x8D5 +#define MADERA_DRC2LMIX_INPUT_4_SOURCE 0x8D6 +#define MADERA_DRC2LMIX_INPUT_4_VOLUME 0x8D7 +#define MADERA_DRC2RMIX_INPUT_1_SOURCE 0x8D8 +#define MADERA_DRC2RMIX_INPUT_1_VOLUME 0x8D9 +#define MADERA_DRC2RMIX_INPUT_2_SOURCE 0x8DA +#define MADERA_DRC2RMIX_INPUT_2_VOLUME 0x8DB +#define MADERA_DRC2RMIX_INPUT_3_SOURCE 0x8DC +#define MADERA_DRC2RMIX_INPUT_3_VOLUME 0x8DD +#define MADERA_DRC2RMIX_INPUT_4_SOURCE 0x8DE +#define MADERA_DRC2RMIX_INPUT_4_VOLUME 0x8DF +#define MADERA_HPLP1MIX_INPUT_1_SOURCE 0x900 +#define MADERA_HPLP1MIX_INPUT_1_VOLUME 0x901 +#define MADERA_HPLP1MIX_INPUT_2_SOURCE 0x902 +#define MADERA_HPLP1MIX_INPUT_2_VOLUME 0x903 +#define MADERA_HPLP1MIX_INPUT_3_SOURCE 0x904 +#define MADERA_HPLP1MIX_INPUT_3_VOLUME 0x905 +#define MADERA_HPLP1MIX_INPUT_4_SOURCE 0x906 +#define MADERA_HPLP1MIX_INPUT_4_VOLUME 0x907 +#define MADERA_HPLP2MIX_INPUT_1_SOURCE 0x908 +#define MADERA_HPLP2MIX_INPUT_1_VOLUME 0x909 +#define MADERA_HPLP2MIX_INPUT_2_SOURCE 0x90A +#define MADERA_HPLP2MIX_INPUT_2_VOLUME 0x90B +#define MADERA_HPLP2MIX_INPUT_3_SOURCE 0x90C +#define MADERA_HPLP2MIX_INPUT_3_VOLUME 0x90D +#define MADERA_HPLP2MIX_INPUT_4_SOURCE 0x90E +#define MADERA_HPLP2MIX_INPUT_4_VOLUME 0x90F +#define MADERA_HPLP3MIX_INPUT_1_SOURCE 0x910 +#define MADERA_HPLP3MIX_INPUT_1_VOLUME 0x911 +#define MADERA_HPLP3MIX_INPUT_2_SOURCE 0x912 +#define MADERA_HPLP3MIX_INPUT_2_VOLUME 0x913 +#define MADERA_HPLP3MIX_INPUT_3_SOURCE 0x914 +#define MADERA_HPLP3MIX_INPUT_3_VOLUME 0x915 +#define MADERA_HPLP3MIX_INPUT_4_SOURCE 0x916 +#define MADERA_HPLP3MIX_INPUT_4_VOLUME 0x917 +#define MADERA_HPLP4MIX_INPUT_1_SOURCE 0x918 +#define MADERA_HPLP4MIX_INPUT_1_VOLUME 0x919 +#define MADERA_HPLP4MIX_INPUT_2_SOURCE 0x91A +#define MADERA_HPLP4MIX_INPUT_2_VOLUME 0x91B +#define MADERA_HPLP4MIX_INPUT_3_SOURCE 0x91C +#define MADERA_HPLP4MIX_INPUT_3_VOLUME 0x91D +#define MADERA_HPLP4MIX_INPUT_4_SOURCE 0x91E +#define MADERA_HPLP4MIX_INPUT_4_VOLUME 0x91F +#define MADERA_DSP1LMIX_INPUT_1_SOURCE 0x940 +#define MADERA_DSP1LMIX_INPUT_1_VOLUME 0x941 +#define MADERA_DSP1LMIX_INPUT_2_SOURCE 0x942 +#define MADERA_DSP1LMIX_INPUT_2_VOLUME 0x943 +#define MADERA_DSP1LMIX_INPUT_3_SOURCE 0x944 +#define MADERA_DSP1LMIX_INPUT_3_VOLUME 0x945 +#define MADERA_DSP1LMIX_INPUT_4_SOURCE 0x946 +#define MADERA_DSP1LMIX_INPUT_4_VOLUME 0x947 +#define MADERA_DSP1RMIX_INPUT_1_SOURCE 0x948 +#define MADERA_DSP1RMIX_INPUT_1_VOLUME 0x949 +#define MADERA_DSP1RMIX_INPUT_2_SOURCE 0x94A +#define MADERA_DSP1RMIX_INPUT_2_VOLUME 0x94B +#define MADERA_DSP1RMIX_INPUT_3_SOURCE 0x94C +#define MADERA_DSP1RMIX_INPUT_3_VOLUME 0x94D +#define MADERA_DSP1RMIX_INPUT_4_SOURCE 0x94E +#define MADERA_DSP1RMIX_INPUT_4_VOLUME 0x94F +#define MADERA_DSP1AUX1MIX_INPUT_1_SOURCE 0x950 +#define MADERA_DSP1AUX2MIX_INPUT_1_SOURCE 0x958 +#define MADERA_DSP1AUX3MIX_INPUT_1_SOURCE 0x960 +#define MADERA_DSP1AUX4MIX_INPUT_1_SOURCE 0x968 +#define MADERA_DSP1AUX5MIX_INPUT_1_SOURCE 0x970 +#define MADERA_DSP1AUX6MIX_INPUT_1_SOURCE 0x978 +#define MADERA_DSP2LMIX_INPUT_1_SOURCE 0x980 +#define MADERA_DSP2LMIX_INPUT_1_VOLUME 0x981 +#define MADERA_DSP2LMIX_INPUT_2_SOURCE 0x982 +#define MADERA_DSP2LMIX_INPUT_2_VOLUME 0x983 +#define MADERA_DSP2LMIX_INPUT_3_SOURCE 0x984 +#define MADERA_DSP2LMIX_INPUT_3_VOLUME 0x985 +#define MADERA_DSP2LMIX_INPUT_4_SOURCE 0x986 +#define MADERA_DSP2LMIX_INPUT_4_VOLUME 0x987 +#define MADERA_DSP2RMIX_INPUT_1_SOURCE 0x988 +#define MADERA_DSP2RMIX_INPUT_1_VOLUME 0x989 +#define MADERA_DSP2RMIX_INPUT_2_SOURCE 0x98A +#define MADERA_DSP2RMIX_INPUT_2_VOLUME 0x98B +#define MADERA_DSP2RMIX_INPUT_3_SOURCE 0x98C +#define MADERA_DSP2RMIX_INPUT_3_VOLUME 0x98D +#define MADERA_DSP2RMIX_INPUT_4_SOURCE 0x98E +#define MADERA_DSP2RMIX_INPUT_4_VOLUME 0x98F +#define MADERA_DSP2AUX1MIX_INPUT_1_SOURCE 0x990 +#define MADERA_DSP2AUX2MIX_INPUT_1_SOURCE 0x998 +#define MADERA_DSP2AUX3MIX_INPUT_1_SOURCE 0x9A0 +#define MADERA_DSP2AUX4MIX_INPUT_1_SOURCE 0x9A8 +#define MADERA_DSP2AUX5MIX_INPUT_1_SOURCE 0x9B0 +#define MADERA_DSP2AUX6MIX_INPUT_1_SOURCE 0x9B8 +#define MADERA_DSP3LMIX_INPUT_1_SOURCE 0x9C0 +#define MADERA_DSP3LMIX_INPUT_1_VOLUME 0x9C1 +#define MADERA_DSP3LMIX_INPUT_2_SOURCE 0x9C2 +#define MADERA_DSP3LMIX_INPUT_2_VOLUME 0x9C3 +#define MADERA_DSP3LMIX_INPUT_3_SOURCE 0x9C4 +#define MADERA_DSP3LMIX_INPUT_3_VOLUME 0x9C5 +#define MADERA_DSP3LMIX_INPUT_4_SOURCE 0x9C6 +#define MADERA_DSP3LMIX_INPUT_4_VOLUME 0x9C7 +#define MADERA_DSP3RMIX_INPUT_1_SOURCE 0x9C8 +#define MADERA_DSP3RMIX_INPUT_1_VOLUME 0x9C9 +#define MADERA_DSP3RMIX_INPUT_2_SOURCE 0x9CA +#define MADERA_DSP3RMIX_INPUT_2_VOLUME 0x9CB +#define MADERA_DSP3RMIX_INPUT_3_SOURCE 0x9CC +#define MADERA_DSP3RMIX_INPUT_3_VOLUME 0x9CD +#define MADERA_DSP3RMIX_INPUT_4_SOURCE 0x9CE +#define MADERA_DSP3RMIX_INPUT_4_VOLUME 0x9CF +#define MADERA_DSP3AUX1MIX_INPUT_1_SOURCE 0x9D0 +#define MADERA_DSP3AUX2MIX_INPUT_1_SOURCE 0x9D8 +#define MADERA_DSP3AUX3MIX_INPUT_1_SOURCE 0x9E0 +#define MADERA_DSP3AUX4MIX_INPUT_1_SOURCE 0x9E8 +#define MADERA_DSP3AUX5MIX_INPUT_1_SOURCE 0x9F0 +#define MADERA_DSP3AUX6MIX_INPUT_1_SOURCE 0x9F8 +#define MADERA_DSP4LMIX_INPUT_1_SOURCE 0xA00 +#define MADERA_DSP4LMIX_INPUT_1_VOLUME 0xA01 +#define MADERA_DSP4LMIX_INPUT_2_SOURCE 0xA02 +#define MADERA_DSP4LMIX_INPUT_2_VOLUME 0xA03 +#define MADERA_DSP4LMIX_INPUT_3_SOURCE 0xA04 +#define MADERA_DSP4LMIX_INPUT_3_VOLUME 0xA05 +#define MADERA_DSP4LMIX_INPUT_4_SOURCE 0xA06 +#define MADERA_DSP4LMIX_INPUT_4_VOLUME 0xA07 +#define MADERA_DSP4RMIX_INPUT_1_SOURCE 0xA08 +#define MADERA_DSP4RMIX_INPUT_1_VOLUME 0xA09 +#define MADERA_DSP4RMIX_INPUT_2_SOURCE 0xA0A +#define MADERA_DSP4RMIX_INPUT_2_VOLUME 0xA0B +#define MADERA_DSP4RMIX_INPUT_3_SOURCE 0xA0C +#define MADERA_DSP4RMIX_INPUT_3_VOLUME 0xA0D +#define MADERA_DSP4RMIX_INPUT_4_SOURCE 0xA0E +#define MADERA_DSP4RMIX_INPUT_4_VOLUME 0xA0F +#define MADERA_DSP4AUX1MIX_INPUT_1_SOURCE 0xA10 +#define MADERA_DSP4AUX2MIX_INPUT_1_SOURCE 0xA18 +#define MADERA_DSP4AUX3MIX_INPUT_1_SOURCE 0xA20 +#define MADERA_DSP4AUX4MIX_INPUT_1_SOURCE 0xA28 +#define MADERA_DSP4AUX5MIX_INPUT_1_SOURCE 0xA30 +#define MADERA_DSP4AUX6MIX_INPUT_1_SOURCE 0xA38 +#define MADERA_DSP5LMIX_INPUT_1_SOURCE 0xA40 +#define MADERA_DSP5LMIX_INPUT_1_VOLUME 0xA41 +#define MADERA_DSP5LMIX_INPUT_2_SOURCE 0xA42 +#define MADERA_DSP5LMIX_INPUT_2_VOLUME 0xA43 +#define MADERA_DSP5LMIX_INPUT_3_SOURCE 0xA44 +#define MADERA_DSP5LMIX_INPUT_3_VOLUME 0xA45 +#define MADERA_DSP5LMIX_INPUT_4_SOURCE 0xA46 +#define MADERA_DSP5LMIX_INPUT_4_VOLUME 0xA47 +#define MADERA_DSP5RMIX_INPUT_1_SOURCE 0xA48 +#define MADERA_DSP5RMIX_INPUT_1_VOLUME 0xA49 +#define MADERA_DSP5RMIX_INPUT_2_SOURCE 0xA4A +#define MADERA_DSP5RMIX_INPUT_2_VOLUME 0xA4B +#define MADERA_DSP5RMIX_INPUT_3_SOURCE 0xA4C +#define MADERA_DSP5RMIX_INPUT_3_VOLUME 0xA4D +#define MADERA_DSP5RMIX_INPUT_4_SOURCE 0xA4E +#define MADERA_DSP5RMIX_INPUT_4_VOLUME 0xA4F +#define MADERA_DSP5AUX1MIX_INPUT_1_SOURCE 0xA50 +#define MADERA_DSP5AUX2MIX_INPUT_1_SOURCE 0xA58 +#define MADERA_DSP5AUX3MIX_INPUT_1_SOURCE 0xA60 +#define MADERA_DSP5AUX4MIX_INPUT_1_SOURCE 0xA68 +#define MADERA_DSP5AUX5MIX_INPUT_1_SOURCE 0xA70 +#define MADERA_DSP5AUX6MIX_INPUT_1_SOURCE 0xA78 +#define MADERA_ASRC1_1LMIX_INPUT_1_SOURCE 0xA80 +#define MADERA_ASRC1_1RMIX_INPUT_1_SOURCE 0xA88 +#define MADERA_ASRC1_2LMIX_INPUT_1_SOURCE 0xA90 +#define MADERA_ASRC1_2RMIX_INPUT_1_SOURCE 0xA98 +#define MADERA_ASRC2_1LMIX_INPUT_1_SOURCE 0xAA0 +#define MADERA_ASRC2_1RMIX_INPUT_1_SOURCE 0xAA8 +#define MADERA_ASRC2_2LMIX_INPUT_1_SOURCE 0xAB0 +#define MADERA_ASRC2_2RMIX_INPUT_1_SOURCE 0xAB8 +#define MADERA_ISRC1DEC1MIX_INPUT_1_SOURCE 0xB00 +#define MADERA_ISRC1DEC2MIX_INPUT_1_SOURCE 0xB08 +#define MADERA_ISRC1DEC3MIX_INPUT_1_SOURCE 0xB10 +#define MADERA_ISRC1DEC4MIX_INPUT_1_SOURCE 0xB18 +#define MADERA_ISRC1INT1MIX_INPUT_1_SOURCE 0xB20 +#define MADERA_ISRC1INT2MIX_INPUT_1_SOURCE 0xB28 +#define MADERA_ISRC1INT3MIX_INPUT_1_SOURCE 0xB30 +#define MADERA_ISRC1INT4MIX_INPUT_1_SOURCE 0xB38 +#define MADERA_ISRC2DEC1MIX_INPUT_1_SOURCE 0xB40 +#define MADERA_ISRC2DEC2MIX_INPUT_1_SOURCE 0xB48 +#define MADERA_ISRC2DEC3MIX_INPUT_1_SOURCE 0xB50 +#define MADERA_ISRC2DEC4MIX_INPUT_1_SOURCE 0xB58 +#define MADERA_ISRC2INT1MIX_INPUT_1_SOURCE 0xB60 +#define MADERA_ISRC2INT2MIX_INPUT_1_SOURCE 0xB68 +#define MADERA_ISRC2INT3MIX_INPUT_1_SOURCE 0xB70 +#define MADERA_ISRC2INT4MIX_INPUT_1_SOURCE 0xB78 +#define MADERA_ISRC3DEC1MIX_INPUT_1_SOURCE 0xB80 +#define MADERA_ISRC3DEC2MIX_INPUT_1_SOURCE 0xB88 +#define MADERA_ISRC3DEC3MIX_INPUT_1_SOURCE 0xB90 +#define MADERA_ISRC3DEC4MIX_INPUT_1_SOURCE 0xB98 +#define MADERA_ISRC3INT1MIX_INPUT_1_SOURCE 0xBA0 +#define MADERA_ISRC3INT2MIX_INPUT_1_SOURCE 0xBA8 +#define MADERA_ISRC3INT3MIX_INPUT_1_SOURCE 0xBB0 +#define MADERA_ISRC3INT4MIX_INPUT_1_SOURCE 0xBB8 +#define MADERA_ISRC4DEC1MIX_INPUT_1_SOURCE 0xBC0 +#define MADERA_ISRC4DEC2MIX_INPUT_1_SOURCE 0xBC8 +#define MADERA_ISRC4INT1MIX_INPUT_1_SOURCE 0xBE0 +#define MADERA_ISRC4INT2MIX_INPUT_1_SOURCE 0xBE8 +#define MADERA_DSP6LMIX_INPUT_1_SOURCE 0xC00 +#define MADERA_DSP6LMIX_INPUT_1_VOLUME 0xC01 +#define MADERA_DSP6LMIX_INPUT_2_SOURCE 0xC02 +#define MADERA_DSP6LMIX_INPUT_2_VOLUME 0xC03 +#define MADERA_DSP6LMIX_INPUT_3_SOURCE 0xC04 +#define MADERA_DSP6LMIX_INPUT_3_VOLUME 0xC05 +#define MADERA_DSP6LMIX_INPUT_4_SOURCE 0xC06 +#define MADERA_DSP6LMIX_INPUT_4_VOLUME 0xC07 +#define MADERA_DSP6RMIX_INPUT_1_SOURCE 0xC08 +#define MADERA_DSP6RMIX_INPUT_1_VOLUME 0xC09 +#define MADERA_DSP6RMIX_INPUT_2_SOURCE 0xC0A +#define MADERA_DSP6RMIX_INPUT_2_VOLUME 0xC0B +#define MADERA_DSP6RMIX_INPUT_3_SOURCE 0xC0C +#define MADERA_DSP6RMIX_INPUT_3_VOLUME 0xC0D +#define MADERA_DSP6RMIX_INPUT_4_SOURCE 0xC0E +#define MADERA_DSP6RMIX_INPUT_4_VOLUME 0xC0F +#define MADERA_DSP6AUX1MIX_INPUT_1_SOURCE 0xC10 +#define MADERA_DSP6AUX2MIX_INPUT_1_SOURCE 0xC18 +#define MADERA_DSP6AUX3MIX_INPUT_1_SOURCE 0xC20 +#define MADERA_DSP6AUX4MIX_INPUT_1_SOURCE 0xC28 +#define MADERA_DSP6AUX5MIX_INPUT_1_SOURCE 0xC30 +#define MADERA_DSP6AUX6MIX_INPUT_1_SOURCE 0xC38 +#define MADERA_DSP7LMIX_INPUT_1_SOURCE 0xC40 +#define MADERA_DSP7LMIX_INPUT_1_VOLUME 0xC41 +#define MADERA_DSP7LMIX_INPUT_2_SOURCE 0xC42 +#define MADERA_DSP7LMIX_INPUT_2_VOLUME 0xC43 +#define MADERA_DSP7LMIX_INPUT_3_SOURCE 0xC44 +#define MADERA_DSP7LMIX_INPUT_3_VOLUME 0xC45 +#define MADERA_DSP7LMIX_INPUT_4_SOURCE 0xC46 +#define MADERA_DSP7LMIX_INPUT_4_VOLUME 0xC47 +#define MADERA_DSP7RMIX_INPUT_1_SOURCE 0xC48 +#define MADERA_DSP7RMIX_INPUT_1_VOLUME 0xC49 +#define MADERA_DSP7RMIX_INPUT_2_SOURCE 0xC4A +#define MADERA_DSP7RMIX_INPUT_2_VOLUME 0xC4B +#define MADERA_DSP7RMIX_INPUT_3_SOURCE 0xC4C +#define MADERA_DSP7RMIX_INPUT_3_VOLUME 0xC4D +#define MADERA_DSP7RMIX_INPUT_4_SOURCE 0xC4E +#define MADERA_DSP7RMIX_INPUT_4_VOLUME 0xC4F +#define MADERA_DSP7AUX1MIX_INPUT_1_SOURCE 0xC50 +#define MADERA_DSP7AUX2MIX_INPUT_1_SOURCE 0xC58 +#define MADERA_DSP7AUX3MIX_INPUT_1_SOURCE 0xC60 +#define MADERA_DSP7AUX4MIX_INPUT_1_SOURCE 0xC68 +#define MADERA_DSP7AUX5MIX_INPUT_1_SOURCE 0xC70 +#define MADERA_DSP7AUX6MIX_INPUT_1_SOURCE 0xC78 +#define MADERA_DFC1MIX_INPUT_1_SOURCE 0xDC0 +#define MADERA_DFC2MIX_INPUT_1_SOURCE 0xDC8 +#define MADERA_DFC3MIX_INPUT_1_SOURCE 0xDD0 +#define MADERA_DFC4MIX_INPUT_1_SOURCE 0xDD8 +#define MADERA_DFC5MIX_INPUT_1_SOURCE 0xDE0 +#define MADERA_DFC6MIX_INPUT_1_SOURCE 0xDE8 +#define MADERA_DFC7MIX_INPUT_1_SOURCE 0xDF0 +#define MADERA_DFC8MIX_INPUT_1_SOURCE 0xDF8 +#define MADERA_FX_CTRL1 0xE00 +#define MADERA_FX_CTRL2 0xE01 +#define MADERA_EQ1_1 0xE10 +#define MADERA_EQ1_2 0xE11 +#define MADERA_EQ1_21 0xE24 +#define MADERA_EQ2_1 0xE26 +#define MADERA_EQ2_2 0xE27 +#define MADERA_EQ2_21 0xE3A +#define MADERA_EQ3_1 0xE3C +#define MADERA_EQ3_2 0xE3D +#define MADERA_EQ3_21 0xE50 +#define MADERA_EQ4_1 0xE52 +#define MADERA_EQ4_2 0xE53 +#define MADERA_EQ4_21 0xE66 +#define MADERA_DRC1_CTRL1 0xE80 +#define MADERA_DRC1_CTRL2 0xE81 +#define MADERA_DRC1_CTRL3 0xE82 +#define MADERA_DRC1_CTRL4 0xE83 +#define MADERA_DRC1_CTRL5 0xE84 +#define MADERA_DRC2_CTRL1 0xE88 +#define MADERA_DRC2_CTRL2 0xE89 +#define MADERA_DRC2_CTRL3 0xE8A +#define MADERA_DRC2_CTRL4 0xE8B +#define MADERA_DRC2_CTRL5 0xE8C +#define MADERA_HPLPF1_1 0xEC0 +#define MADERA_HPLPF1_2 0xEC1 +#define MADERA_HPLPF2_1 0xEC4 +#define MADERA_HPLPF2_2 0xEC5 +#define MADERA_HPLPF3_1 0xEC8 +#define MADERA_HPLPF3_2 0xEC9 +#define MADERA_HPLPF4_1 0xECC +#define MADERA_HPLPF4_2 0xECD +#define MADERA_ASRC2_ENABLE 0xED0 +#define MADERA_ASRC2_STATUS 0xED1 +#define MADERA_ASRC2_RATE1 0xED2 +#define MADERA_ASRC2_RATE2 0xED3 +#define MADERA_ASRC1_ENABLE 0xEE0 +#define MADERA_ASRC1_STATUS 0xEE1 +#define MADERA_ASRC1_RATE1 0xEE2 +#define MADERA_ASRC1_RATE2 0xEE3 +#define MADERA_ISRC_1_CTRL_1 0xEF0 +#define MADERA_ISRC_1_CTRL_2 0xEF1 +#define MADERA_ISRC_1_CTRL_3 0xEF2 +#define MADERA_ISRC_2_CTRL_1 0xEF3 +#define MADERA_ISRC_2_CTRL_2 0xEF4 +#define MADERA_ISRC_2_CTRL_3 0xEF5 +#define MADERA_ISRC_3_CTRL_1 0xEF6 +#define MADERA_ISRC_3_CTRL_2 0xEF7 +#define MADERA_ISRC_3_CTRL_3 0xEF8 +#define MADERA_ISRC_4_CTRL_1 0xEF9 +#define MADERA_ISRC_4_CTRL_2 0xEFA +#define MADERA_ISRC_4_CTRL_3 0xEFB +#define MADERA_CLOCK_CONTROL 0xF00 +#define MADERA_ANC_SRC 0xF01 +#define MADERA_DSP_STATUS 0xF02 +#define MADERA_ANC_COEFF_START 0xF08 +#define MADERA_ANC_COEFF_END 0xF12 +#define MADERA_FCL_FILTER_CONTROL 0xF15 +#define MADERA_FCL_ADC_REFORMATTER_CONTROL 0xF17 +#define MADERA_FCL_COEFF_START 0xF18 +#define MADERA_FCL_COEFF_END 0xF69 +#define MADERA_FCR_FILTER_CONTROL 0xF71 +#define MADERA_FCR_ADC_REFORMATTER_CONTROL 0xF73 +#define MADERA_FCR_COEFF_START 0xF74 +#define MADERA_FCR_COEFF_END 0xFC5 +#define MADERA_DAC_COMP_1 0x1300 +#define MADERA_DAC_COMP_2 0x1302 +#define MADERA_FRF_COEFFICIENT_1L_1 0x1380 +#define MADERA_FRF_COEFFICIENT_1L_2 0x1381 +#define MADERA_FRF_COEFFICIENT_1L_3 0x1382 +#define MADERA_FRF_COEFFICIENT_1L_4 0x1383 +#define MADERA_FRF_COEFFICIENT_1R_1 0x1390 +#define MADERA_FRF_COEFFICIENT_1R_2 0x1391 +#define MADERA_FRF_COEFFICIENT_1R_3 0x1392 +#define MADERA_FRF_COEFFICIENT_1R_4 0x1393 +#define MADERA_FRF_COEFFICIENT_2L_1 0x13A0 +#define MADERA_FRF_COEFFICIENT_2L_2 0x13A1 +#define MADERA_FRF_COEFFICIENT_2L_3 0x13A2 +#define MADERA_FRF_COEFFICIENT_2L_4 0x13A3 +#define MADERA_FRF_COEFFICIENT_2R_1 0x13B0 +#define MADERA_FRF_COEFFICIENT_2R_2 0x13B1 +#define MADERA_FRF_COEFFICIENT_2R_3 0x13B2 +#define MADERA_FRF_COEFFICIENT_2R_4 0x13B3 +#define MADERA_FRF_COEFFICIENT_3L_1 0x13C0 +#define MADERA_FRF_COEFFICIENT_3L_2 0x13C1 +#define MADERA_FRF_COEFFICIENT_3L_3 0x13C2 +#define MADERA_FRF_COEFFICIENT_3L_4 0x13C3 +#define MADERA_FRF_COEFFICIENT_3R_1 0x13D0 +#define MADERA_FRF_COEFFICIENT_3R_2 0x13D1 +#define MADERA_FRF_COEFFICIENT_3R_3 0x13D2 +#define MADERA_FRF_COEFFICIENT_3R_4 0x13D3 +#define MADERA_FRF_COEFFICIENT_4L_1 0x13E0 +#define MADERA_FRF_COEFFICIENT_4L_2 0x13E1 +#define MADERA_FRF_COEFFICIENT_4L_3 0x13E2 +#define MADERA_FRF_COEFFICIENT_4L_4 0x13E3 +#define MADERA_FRF_COEFFICIENT_4R_1 0x13F0 +#define MADERA_FRF_COEFFICIENT_4R_2 0x13F1 +#define MADERA_FRF_COEFFICIENT_4R_3 0x13F2 +#define MADERA_FRF_COEFFICIENT_4R_4 0x13F3 +#define CS47L35_FRF_COEFFICIENT_4L_1 0x13A0 +#define CS47L35_FRF_COEFFICIENT_4L_2 0x13A1 +#define CS47L35_FRF_COEFFICIENT_4L_3 0x13A2 +#define CS47L35_FRF_COEFFICIENT_4L_4 0x13A3 +#define CS47L35_FRF_COEFFICIENT_5L_1 0x13B0 +#define CS47L35_FRF_COEFFICIENT_5L_2 0x13B1 +#define CS47L35_FRF_COEFFICIENT_5L_3 0x13B2 +#define CS47L35_FRF_COEFFICIENT_5L_4 0x13B3 +#define CS47L35_FRF_COEFFICIENT_5R_1 0x13C0 +#define CS47L35_FRF_COEFFICIENT_5R_2 0x13C1 +#define CS47L35_FRF_COEFFICIENT_5R_3 0x13C2 +#define CS47L35_FRF_COEFFICIENT_5R_4 0x13C3 +#define MADERA_FRF_COEFFICIENT_5L_1 0x1400 +#define MADERA_FRF_COEFFICIENT_5L_2 0x1401 +#define MADERA_FRF_COEFFICIENT_5L_3 0x1402 +#define MADERA_FRF_COEFFICIENT_5L_4 0x1403 +#define MADERA_FRF_COEFFICIENT_5R_1 0x1410 +#define MADERA_FRF_COEFFICIENT_5R_2 0x1411 +#define MADERA_FRF_COEFFICIENT_5R_3 0x1412 +#define MADERA_FRF_COEFFICIENT_5R_4 0x1413 +#define MADERA_FRF_COEFFICIENT_6L_1 0x1420 +#define MADERA_FRF_COEFFICIENT_6L_2 0x1421 +#define MADERA_FRF_COEFFICIENT_6L_3 0x1422 +#define MADERA_FRF_COEFFICIENT_6L_4 0x1423 +#define MADERA_FRF_COEFFICIENT_6R_1 0x1430 +#define MADERA_FRF_COEFFICIENT_6R_2 0x1431 +#define MADERA_FRF_COEFFICIENT_6R_3 0x1432 +#define MADERA_FRF_COEFFICIENT_6R_4 0x1433 +#define MADERA_DFC1_CTRL 0x1480 +#define MADERA_DFC1_RX 0x1482 +#define MADERA_DFC1_TX 0x1484 +#define MADERA_DFC2_CTRL 0x1486 +#define MADERA_DFC2_RX 0x1488 +#define MADERA_DFC2_TX 0x148A +#define MADERA_DFC3_CTRL 0x148C +#define MADERA_DFC3_RX 0x148E +#define MADERA_DFC3_TX 0x1490 +#define MADERA_DFC4_CTRL 0x1492 +#define MADERA_DFC4_RX 0x1494 +#define MADERA_DFC4_TX 0x1496 +#define MADERA_DFC5_CTRL 0x1498 +#define MADERA_DFC5_RX 0x149A +#define MADERA_DFC5_TX 0x149C +#define MADERA_DFC6_CTRL 0x149E +#define MADERA_DFC6_RX 0x14A0 +#define MADERA_DFC6_TX 0x14A2 +#define MADERA_DFC7_CTRL 0x14A4 +#define MADERA_DFC7_RX 0x14A6 +#define MADERA_DFC7_TX 0x14A8 +#define MADERA_DFC8_CTRL 0x14AA +#define MADERA_DFC8_RX 0x14AC +#define MADERA_DFC8_TX 0x14AE +#define MADERA_DFC_STATUS 0x14B6 +#define MADERA_ADSP2_IRQ0 0x1600 +#define MADERA_ADSP2_IRQ1 0x1601 +#define MADERA_ADSP2_IRQ2 0x1602 +#define MADERA_ADSP2_IRQ3 0x1603 +#define MADERA_ADSP2_IRQ4 0x1604 +#define MADERA_ADSP2_IRQ5 0x1605 +#define MADERA_ADSP2_IRQ6 0x1606 +#define MADERA_ADSP2_IRQ7 0x1607 +#define MADERA_GPIO1_CTRL_1 0x1700 +#define MADERA_GPIO1_CTRL_2 0x1701 +#define MADERA_GPIO2_CTRL_1 0x1702 +#define MADERA_GPIO2_CTRL_2 0x1703 +#define MADERA_GPIO16_CTRL_1 0x171E +#define MADERA_GPIO16_CTRL_2 0x171F +#define MADERA_GPIO38_CTRL_1 0x174A +#define MADERA_GPIO38_CTRL_2 0x174B +#define MADERA_GPIO40_CTRL_1 0x174E +#define MADERA_GPIO40_CTRL_2 0x174F +#define MADERA_IRQ1_STATUS_1 0x1800 +#define MADERA_IRQ1_STATUS_2 0x1801 +#define MADERA_IRQ1_STATUS_6 0x1805 +#define MADERA_IRQ1_STATUS_7 0x1806 +#define MADERA_IRQ1_STATUS_9 0x1808 +#define MADERA_IRQ1_STATUS_11 0x180A +#define MADERA_IRQ1_STATUS_12 0x180B +#define MADERA_IRQ1_STATUS_15 0x180E +#define MADERA_IRQ1_STATUS_33 0x1820 +#define MADERA_IRQ1_MASK_1 0x1840 +#define MADERA_IRQ1_MASK_2 0x1841 +#define MADERA_IRQ1_MASK_33 0x1860 +#define MADERA_IRQ1_RAW_STATUS_1 0x1880 +#define MADERA_IRQ1_RAW_STATUS_2 0x1881 +#define MADERA_IRQ1_RAW_STATUS_15 0x188E +#define MADERA_IRQ1_RAW_STATUS_33 0x18A0 +#define MADERA_INTERRUPT_DEBOUNCE_7 0x1A06 +#define MADERA_INTERRUPT_DEBOUNCE_15 0x1A0E +#define MADERA_IRQ1_CTRL 0x1A80 +#define MADERA_IRQ2_CTRL 0x1A82 +#define MADERA_INTERRUPT_RAW_STATUS_1 0x1AA0 +#define MADERA_WSEQ_SEQUENCE_1 0x3000 +#define MADERA_WSEQ_SEQUENCE_252 0x31F6 +#define CS47L35_OTP_HPDET_CAL_1 0x31F8 +#define CS47L35_OTP_HPDET_CAL_2 0x31FA +#define MADERA_WSEQ_SEQUENCE_508 0x33F6 +#define CS47L85_OTP_HPDET_CAL_1 0x33F8 +#define CS47L85_OTP_HPDET_CAL_2 0x33FA +#define MADERA_OTP_HPDET_CAL_1 0x20004 +#define MADERA_OTP_HPDET_CAL_2 0x20006 +#define MADERA_DSP1_CONFIG_1 0x0FFE00 +#define MADERA_DSP1_CONFIG_2 0x0FFE02 +#define MADERA_DSP1_SCRATCH_1 0x0FFE40 +#define MADERA_DSP1_SCRATCH_2 0x0FFE42 +#define MADERA_DSP1_PMEM_ERR_ADDR___XMEM_ERR_ADDR 0xFFE7C +#define MADERA_DSP2_CONFIG_1 0x17FE00 +#define MADERA_DSP2_CONFIG_2 0x17FE02 +#define MADERA_DSP2_SCRATCH_1 0x17FE40 +#define MADERA_DSP2_SCRATCH_2 0x17FE42 +#define MADERA_DSP2_PMEM_ERR_ADDR___XMEM_ERR_ADDR 0x17FE7C +#define MADERA_DSP3_CONFIG_1 0x1FFE00 +#define MADERA_DSP3_CONFIG_2 0x1FFE02 +#define MADERA_DSP3_SCRATCH_1 0x1FFE40 +#define MADERA_DSP3_SCRATCH_2 0x1FFE42 +#define MADERA_DSP3_PMEM_ERR_ADDR___XMEM_ERR_ADDR 0x1FFE7C +#define MADERA_DSP4_CONFIG_1 0x27FE00 +#define MADERA_DSP4_CONFIG_2 0x27FE02 +#define MADERA_DSP4_SCRATCH_1 0x27FE40 +#define MADERA_DSP4_SCRATCH_2 0x27FE42 +#define MADERA_DSP4_PMEM_ERR_ADDR___XMEM_ERR_ADDR 0x27FE7C +#define MADERA_DSP5_CONFIG_1 0x2FFE00 +#define MADERA_DSP5_CONFIG_2 0x2FFE02 +#define MADERA_DSP5_SCRATCH_1 0x2FFE40 +#define MADERA_DSP5_SCRATCH_2 0x2FFE42 +#define MADERA_DSP5_PMEM_ERR_ADDR___XMEM_ERR_ADDR 0x2FFE7C +#define MADERA_DSP6_CONFIG_1 0x37FE00 +#define MADERA_DSP6_CONFIG_2 0x37FE02 +#define MADERA_DSP6_SCRATCH_1 0x37FE40 +#define MADERA_DSP6_SCRATCH_2 0x37FE42 +#define MADERA_DSP6_PMEM_ERR_ADDR___XMEM_ERR_ADDR 0x37FE7C +#define MADERA_DSP7_CONFIG_1 0x3FFE00 +#define MADERA_DSP7_CONFIG_2 0x3FFE02 +#define MADERA_DSP7_SCRATCH_1 0x3FFE40 +#define MADERA_DSP7_SCRATCH_2 0x3FFE42 +#define MADERA_DSP7_PMEM_ERR_ADDR___XMEM_ERR_ADDR 0x3FFE7C + +/* (0x0000) Software_Reset */ +#define MADERA_SW_RST_DEV_ID1_MASK 0xFFFF +#define MADERA_SW_RST_DEV_ID1_SHIFT 0 +#define MADERA_SW_RST_DEV_ID1_WIDTH 16 + +/* (0x0001) Hardware_Revision */ +#define MADERA_HW_REVISION_MASK 0x00FF +#define MADERA_HW_REVISION_SHIFT 0 +#define MADERA_HW_REVISION_WIDTH 8 + +/* (0x0020) Tone_Generator_1 */ +#define MADERA_TONE2_ENA 0x0002 +#define MADERA_TONE2_ENA_MASK 0x0002 +#define MADERA_TONE2_ENA_SHIFT 1 +#define MADERA_TONE2_ENA_WIDTH 1 +#define MADERA_TONE1_ENA 0x0001 +#define MADERA_TONE1_ENA_MASK 0x0001 +#define MADERA_TONE1_ENA_SHIFT 0 +#define MADERA_TONE1_ENA_WIDTH 1 + +/* (0x0021) Tone_Generator_2 */ +#define MADERA_TONE1_LVL_0_MASK 0xFFFF +#define MADERA_TONE1_LVL_0_SHIFT 0 +#define MADERA_TONE1_LVL_0_WIDTH 16 + +/* (0x0022) Tone_Generator_3 */ +#define MADERA_TONE1_LVL_MASK 0x00FF +#define MADERA_TONE1_LVL_SHIFT 0 +#define MADERA_TONE1_LVL_WIDTH 8 + +/* (0x0023) Tone_Generator_4 */ +#define MADERA_TONE2_LVL_0_MASK 0xFFFF +#define MADERA_TONE2_LVL_0_SHIFT 0 +#define MADERA_TONE2_LVL_0_WIDTH 16 + +/* (0x0024) Tone_Generator_5 */ +#define MADERA_TONE2_LVL_MASK 0x00FF +#define MADERA_TONE2_LVL_SHIFT 0 +#define MADERA_TONE2_LVL_WIDTH 8 + +/* (0x0030) PWM_Drive_1 */ +#define MADERA_PWM2_ENA 0x0002 +#define MADERA_PWM2_ENA_MASK 0x0002 +#define MADERA_PWM2_ENA_SHIFT 1 +#define MADERA_PWM2_ENA_WIDTH 1 +#define MADERA_PWM1_ENA 0x0001 +#define MADERA_PWM1_ENA_MASK 0x0001 +#define MADERA_PWM1_ENA_SHIFT 0 +#define MADERA_PWM1_ENA_WIDTH 1 + +/* (0x00A0) Comfort_Noise_Generator */ +#define MADERA_NOISE_GEN_ENA 0x0020 +#define MADERA_NOISE_GEN_ENA_MASK 0x0020 +#define MADERA_NOISE_GEN_ENA_SHIFT 5 +#define MADERA_NOISE_GEN_ENA_WIDTH 1 +#define MADERA_NOISE_GEN_GAIN_MASK 0x001F +#define MADERA_NOISE_GEN_GAIN_SHIFT 0 +#define MADERA_NOISE_GEN_GAIN_WIDTH 5 + +/* (0x0100) Clock_32k_1 */ +#define MADERA_CLK_32K_ENA 0x0040 +#define MADERA_CLK_32K_ENA_MASK 0x0040 +#define MADERA_CLK_32K_ENA_SHIFT 6 +#define MADERA_CLK_32K_ENA_WIDTH 1 +#define MADERA_CLK_32K_SRC_MASK 0x0003 +#define MADERA_CLK_32K_SRC_SHIFT 0 +#define MADERA_CLK_32K_SRC_WIDTH 2 + +/* (0x0101) System_Clock_1 */ +#define MADERA_SYSCLK_FRAC 0x8000 +#define MADERA_SYSCLK_FRAC_MASK 0x8000 +#define MADERA_SYSCLK_FRAC_SHIFT 15 +#define MADERA_SYSCLK_FRAC_WIDTH 1 +#define MADERA_SYSCLK_FREQ_MASK 0x0700 +#define MADERA_SYSCLK_FREQ_SHIFT 8 +#define MADERA_SYSCLK_FREQ_WIDTH 3 +#define MADERA_SYSCLK_ENA 0x0040 +#define MADERA_SYSCLK_ENA_MASK 0x0040 +#define MADERA_SYSCLK_ENA_SHIFT 6 +#define MADERA_SYSCLK_ENA_WIDTH 1 +#define MADERA_SYSCLK_SRC_MASK 0x000F +#define MADERA_SYSCLK_SRC_SHIFT 0 +#define MADERA_SYSCLK_SRC_WIDTH 4 + +/* (0x0102) Sample_rate_1 */ +#define MADERA_SAMPLE_RATE_1_MASK 0x001F +#define MADERA_SAMPLE_RATE_1_SHIFT 0 +#define MADERA_SAMPLE_RATE_1_WIDTH 5 + +/* (0x0103) Sample_rate_2 */ +#define MADERA_SAMPLE_RATE_2_MASK 0x001F +#define MADERA_SAMPLE_RATE_2_SHIFT 0 +#define MADERA_SAMPLE_RATE_2_WIDTH 5 + +/* (0x0104) Sample_rate_3 */ +#define MADERA_SAMPLE_RATE_3_MASK 0x001F +#define MADERA_SAMPLE_RATE_3_SHIFT 0 +#define MADERA_SAMPLE_RATE_3_WIDTH 5 + +/* (0x0112) Async_clock_1 */ +#define MADERA_ASYNC_CLK_FREQ_MASK 0x0700 +#define MADERA_ASYNC_CLK_FREQ_SHIFT 8 +#define MADERA_ASYNC_CLK_FREQ_WIDTH 3 +#define MADERA_ASYNC_CLK_ENA 0x0040 +#define MADERA_ASYNC_CLK_ENA_MASK 0x0040 +#define MADERA_ASYNC_CLK_ENA_SHIFT 6 +#define MADERA_ASYNC_CLK_ENA_WIDTH 1 +#define MADERA_ASYNC_CLK_SRC_MASK 0x000F +#define MADERA_ASYNC_CLK_SRC_SHIFT 0 +#define MADERA_ASYNC_CLK_SRC_WIDTH 4 + +/* (0x0113) Async_sample_rate_1 */ +#define MADERA_ASYNC_SAMPLE_RATE_1_MASK 0x001F +#define MADERA_ASYNC_SAMPLE_RATE_1_SHIFT 0 +#define MADERA_ASYNC_SAMPLE_RATE_1_WIDTH 5 + +/* (0x0114) Async_sample_rate_2 */ +#define MADERA_ASYNC_SAMPLE_RATE_2_MASK 0x001F +#define MADERA_ASYNC_SAMPLE_RATE_2_SHIFT 0 +#define MADERA_ASYNC_SAMPLE_RATE_2_WIDTH 5 + +/* (0x0120) DSP_Clock_1 */ +#define MADERA_DSP_CLK_FREQ_LEGACY 0x0700 +#define MADERA_DSP_CLK_FREQ_LEGACY_MASK 0x0700 +#define MADERA_DSP_CLK_FREQ_LEGACY_SHIFT 8 +#define MADERA_DSP_CLK_FREQ_LEGACY_WIDTH 3 +#define MADERA_DSP_CLK_ENA 0x0040 +#define MADERA_DSP_CLK_ENA_MASK 0x0040 +#define MADERA_DSP_CLK_ENA_SHIFT 6 +#define MADERA_DSP_CLK_ENA_WIDTH 1 +#define MADERA_DSP_CLK_SRC 0x000F +#define MADERA_DSP_CLK_SRC_MASK 0x000F +#define MADERA_DSP_CLK_SRC_SHIFT 0 +#define MADERA_DSP_CLK_SRC_WIDTH 4 + +/* (0x0122) DSP_Clock_2 */ +#define MADERA_DSP_CLK_FREQ_MASK 0x03FF +#define MADERA_DSP_CLK_FREQ_SHIFT 0 +#define MADERA_DSP_CLK_FREQ_WIDTH 10 + +/* (0x0149) Output_system_clock */ +#define MADERA_OPCLK_ENA 0x8000 +#define MADERA_OPCLK_ENA_MASK 0x8000 +#define MADERA_OPCLK_ENA_SHIFT 15 +#define MADERA_OPCLK_ENA_WIDTH 1 +#define MADERA_OPCLK_DIV_MASK 0x00F8 +#define MADERA_OPCLK_DIV_SHIFT 3 +#define MADERA_OPCLK_DIV_WIDTH 5 +#define MADERA_OPCLK_SEL_MASK 0x0007 +#define MADERA_OPCLK_SEL_SHIFT 0 +#define MADERA_OPCLK_SEL_WIDTH 3 + +/* (0x014A) Output_async_clock */ +#define MADERA_OPCLK_ASYNC_ENA 0x8000 +#define MADERA_OPCLK_ASYNC_ENA_MASK 0x8000 +#define MADERA_OPCLK_ASYNC_ENA_SHIFT 15 +#define MADERA_OPCLK_ASYNC_ENA_WIDTH 1 +#define MADERA_OPCLK_ASYNC_DIV_MASK 0x00F8 +#define MADERA_OPCLK_ASYNC_DIV_SHIFT 3 +#define MADERA_OPCLK_ASYNC_DIV_WIDTH 5 +#define MADERA_OPCLK_ASYNC_SEL_MASK 0x0007 +#define MADERA_OPCLK_ASYNC_SEL_SHIFT 0 +#define MADERA_OPCLK_ASYNC_SEL_WIDTH 3 + +/* (0x0171) FLL1_Control_1 */ +#define MADERA_FLL1_FREERUN 0x0002 +#define MADERA_FLL1_FREERUN_MASK 0x0002 +#define MADERA_FLL1_FREERUN_SHIFT 1 +#define MADERA_FLL1_FREERUN_WIDTH 1 +#define MADERA_FLL1_ENA 0x0001 +#define MADERA_FLL1_ENA_MASK 0x0001 +#define MADERA_FLL1_ENA_SHIFT 0 +#define MADERA_FLL1_ENA_WIDTH 1 + +/* (0x0172) FLL1_Control_2 */ +#define MADERA_FLL1_CTRL_UPD 0x8000 +#define MADERA_FLL1_CTRL_UPD_MASK 0x8000 +#define MADERA_FLL1_CTRL_UPD_SHIFT 15 +#define MADERA_FLL1_CTRL_UPD_WIDTH 1 +#define MADERA_FLL1_N_MASK 0x03FF +#define MADERA_FLL1_N_SHIFT 0 +#define MADERA_FLL1_N_WIDTH 10 + +/* (0x0173) FLL1_Control_3 */ +#define MADERA_FLL1_THETA_MASK 0xFFFF +#define MADERA_FLL1_THETA_SHIFT 0 +#define MADERA_FLL1_THETA_WIDTH 16 + +/* (0x0174) FLL1_Control_4 */ +#define MADERA_FLL1_LAMBDA_MASK 0xFFFF +#define MADERA_FLL1_LAMBDA_SHIFT 0 +#define MADERA_FLL1_LAMBDA_WIDTH 16 + +/* (0x0175) FLL1_Control_5 */ +#define MADERA_FLL1_FRATIO_MASK 0x0F00 +#define MADERA_FLL1_FRATIO_SHIFT 8 +#define MADERA_FLL1_FRATIO_WIDTH 4 + +/* (0x0176) FLL1_Control_6 */ +#define MADERA_FLL1_REFCLK_DIV_MASK 0x00C0 +#define MADERA_FLL1_REFCLK_DIV_SHIFT 6 +#define MADERA_FLL1_REFCLK_DIV_WIDTH 2 +#define MADERA_FLL1_REFCLK_SRC_MASK 0x000F +#define MADERA_FLL1_REFCLK_SRC_SHIFT 0 +#define MADERA_FLL1_REFCLK_SRC_WIDTH 4 + +/* (0x0177) FLL1_Loop_Filter_Test_1 */ +#define MADERA_FLL1_FRC_INTEG_UPD 0x8000 +#define MADERA_FLL1_FRC_INTEG_UPD_MASK 0x8000 +#define MADERA_FLL1_FRC_INTEG_UPD_SHIFT 15 +#define MADERA_FLL1_FRC_INTEG_UPD_WIDTH 1 +#define MADERA_FLL1_FRC_INTEG_VAL_MASK 0x0FFF +#define MADERA_FLL1_FRC_INTEG_VAL_SHIFT 0 +#define MADERA_FLL1_FRC_INTEG_VAL_WIDTH 12 + +/* (0x0179) FLL1_Control_7 */ +#define MADERA_FLL1_GAIN_MASK 0x003c +#define MADERA_FLL1_GAIN_SHIFT 2 +#define MADERA_FLL1_GAIN_WIDTH 4 + +/* (0x017A) FLL1_EFS_2 */ +#define MADERA_FLL1_PHASE_GAIN_MASK 0xF000 +#define MADERA_FLL1_PHASE_GAIN_SHIFT 12 +#define MADERA_FLL1_PHASE_GAIN_WIDTH 4 +#define MADERA_FLL1_PHASE_ENA_MASK 0x0800 +#define MADERA_FLL1_PHASE_ENA_SHIFT 11 +#define MADERA_FLL1_PHASE_ENA_WIDTH 1 + +/* (0x0181) FLL1_Synchroniser_1 */ +#define MADERA_FLL1_SYNC_ENA 0x0001 +#define MADERA_FLL1_SYNC_ENA_MASK 0x0001 +#define MADERA_FLL1_SYNC_ENA_SHIFT 0 +#define MADERA_FLL1_SYNC_ENA_WIDTH 1 + +/* (0x0182) FLL1_Synchroniser_2 */ +#define MADERA_FLL1_SYNC_N_MASK 0x03FF +#define MADERA_FLL1_SYNC_N_SHIFT 0 +#define MADERA_FLL1_SYNC_N_WIDTH 10 + +/* (0x0183) FLL1_Synchroniser_3 */ +#define MADERA_FLL1_SYNC_THETA_MASK 0xFFFF +#define MADERA_FLL1_SYNC_THETA_SHIFT 0 +#define MADERA_FLL1_SYNC_THETA_WIDTH 16 + +/* (0x0184) FLL1_Synchroniser_4 */ +#define MADERA_FLL1_SYNC_LAMBDA_MASK 0xFFFF +#define MADERA_FLL1_SYNC_LAMBDA_SHIFT 0 +#define MADERA_FLL1_SYNC_LAMBDA_WIDTH 16 + +/* (0x0185) FLL1_Synchroniser_5 */ +#define MADERA_FLL1_SYNC_FRATIO_MASK 0x0700 +#define MADERA_FLL1_SYNC_FRATIO_SHIFT 8 +#define MADERA_FLL1_SYNC_FRATIO_WIDTH 3 + +/* (0x0186) FLL1_Synchroniser_6 */ +#define MADERA_FLL1_SYNCCLK_DIV_MASK 0x00C0 +#define MADERA_FLL1_SYNCCLK_DIV_SHIFT 6 +#define MADERA_FLL1_SYNCCLK_DIV_WIDTH 2 +#define MADERA_FLL1_SYNCCLK_SRC_MASK 0x000F +#define MADERA_FLL1_SYNCCLK_SRC_SHIFT 0 +#define MADERA_FLL1_SYNCCLK_SRC_WIDTH 4 + +/* (0x0187) FLL1_Synchroniser_7 */ +#define MADERA_FLL1_SYNC_GAIN_MASK 0x003c +#define MADERA_FLL1_SYNC_GAIN_SHIFT 2 +#define MADERA_FLL1_SYNC_GAIN_WIDTH 4 +#define MADERA_FLL1_SYNC_DFSAT 0x0001 +#define MADERA_FLL1_SYNC_DFSAT_MASK 0x0001 +#define MADERA_FLL1_SYNC_DFSAT_SHIFT 0 +#define MADERA_FLL1_SYNC_DFSAT_WIDTH 1 + +/* (0x01D1) FLL_AO_Control_1 */ +#define MADERA_FLL_AO_HOLD 0x0004 +#define MADERA_FLL_AO_HOLD_MASK 0x0004 +#define MADERA_FLL_AO_HOLD_SHIFT 2 +#define MADERA_FLL_AO_HOLD_WIDTH 1 +#define MADERA_FLL_AO_FREERUN 0x0002 +#define MADERA_FLL_AO_FREERUN_MASK 0x0002 +#define MADERA_FLL_AO_FREERUN_SHIFT 1 +#define MADERA_FLL_AO_FREERUN_WIDTH 1 +#define MADERA_FLL_AO_ENA 0x0001 +#define MADERA_FLL_AO_ENA_MASK 0x0001 +#define MADERA_FLL_AO_ENA_SHIFT 0 +#define MADERA_FLL_AO_ENA_WIDTH 1 + +/* (0x01D2) FLL_AO_Control_2 */ +#define MADERA_FLL_AO_CTRL_UPD 0x8000 +#define MADERA_FLL_AO_CTRL_UPD_MASK 0x8000 +#define MADERA_FLL_AO_CTRL_UPD_SHIFT 15 +#define MADERA_FLL_AO_CTRL_UPD_WIDTH 1 + +/* (0x01D6) FLL_AO_Control_6 */ +#define MADERA_FLL_AO_REFCLK_SRC_MASK 0x000F +#define MADERA_FLL_AO_REFCLK_SRC_SHIFT 0 +#define MADERA_FLL_AO_REFCLK_SRC_WIDTH 4 + +/* (0x0200) Mic_Charge_Pump_1 */ +#define MADERA_CPMIC_BYPASS 0x0002 +#define MADERA_CPMIC_BYPASS_MASK 0x0002 +#define MADERA_CPMIC_BYPASS_SHIFT 1 +#define MADERA_CPMIC_BYPASS_WIDTH 1 +#define MADERA_CPMIC_ENA 0x0001 +#define MADERA_CPMIC_ENA_MASK 0x0001 +#define MADERA_CPMIC_ENA_SHIFT 0 +#define MADERA_CPMIC_ENA_WIDTH 1 + +/* (0x0210) LDO1_Control_1 */ +#define MADERA_LDO1_VSEL_MASK 0x07E0 +#define MADERA_LDO1_VSEL_SHIFT 5 +#define MADERA_LDO1_VSEL_WIDTH 6 +#define MADERA_LDO1_FAST 0x0010 +#define MADERA_LDO1_FAST_MASK 0x0010 +#define MADERA_LDO1_FAST_SHIFT 4 +#define MADERA_LDO1_FAST_WIDTH 1 +#define MADERA_LDO1_DISCH 0x0004 +#define MADERA_LDO1_DISCH_MASK 0x0004 +#define MADERA_LDO1_DISCH_SHIFT 2 +#define MADERA_LDO1_DISCH_WIDTH 1 +#define MADERA_LDO1_BYPASS 0x0002 +#define MADERA_LDO1_BYPASS_MASK 0x0002 +#define MADERA_LDO1_BYPASS_SHIFT 1 +#define MADERA_LDO1_BYPASS_WIDTH 1 +#define MADERA_LDO1_ENA 0x0001 +#define MADERA_LDO1_ENA_MASK 0x0001 +#define MADERA_LDO1_ENA_SHIFT 0 +#define MADERA_LDO1_ENA_WIDTH 1 + +/* (0x0213) LDO2_Control_1 */ +#define MADERA_LDO2_VSEL_MASK 0x07E0 +#define MADERA_LDO2_VSEL_SHIFT 5 +#define MADERA_LDO2_VSEL_WIDTH 6 +#define MADERA_LDO2_FAST 0x0010 +#define MADERA_LDO2_FAST_MASK 0x0010 +#define MADERA_LDO2_FAST_SHIFT 4 +#define MADERA_LDO2_FAST_WIDTH 1 +#define MADERA_LDO2_DISCH 0x0004 +#define MADERA_LDO2_DISCH_MASK 0x0004 +#define MADERA_LDO2_DISCH_SHIFT 2 +#define MADERA_LDO2_DISCH_WIDTH 1 +#define MADERA_LDO2_BYPASS 0x0002 +#define MADERA_LDO2_BYPASS_MASK 0x0002 +#define MADERA_LDO2_BYPASS_SHIFT 1 +#define MADERA_LDO2_BYPASS_WIDTH 1 +#define MADERA_LDO2_ENA 0x0001 +#define MADERA_LDO2_ENA_MASK 0x0001 +#define MADERA_LDO2_ENA_SHIFT 0 +#define MADERA_LDO2_ENA_WIDTH 1 + +/* (0x0218) Mic_Bias_Ctrl_1 */ +#define MADERA_MICB1_ENA 0x0001 +#define MADERA_MICB1_ENA_MASK 0x0001 +#define MADERA_MICB1_ENA_SHIFT 0 +#define MADERA_MICB1_ENA_WIDTH 1 + +/* (0x021C) Mic_Bias_Ctrl_5 */ +#define MADERA_MICB1D_ENA 0x1000 +#define MADERA_MICB1D_ENA_MASK 0x1000 +#define MADERA_MICB1D_ENA_SHIFT 12 +#define MADERA_MICB1D_ENA_WIDTH 1 +#define MADERA_MICB1C_ENA 0x0100 +#define MADERA_MICB1C_ENA_MASK 0x0100 +#define MADERA_MICB1C_ENA_SHIFT 8 +#define MADERA_MICB1C_ENA_WIDTH 1 +#define MADERA_MICB1B_ENA 0x0010 +#define MADERA_MICB1B_ENA_MASK 0x0010 +#define MADERA_MICB1B_ENA_SHIFT 4 +#define MADERA_MICB1B_ENA_WIDTH 1 +#define MADERA_MICB1A_ENA 0x0001 +#define MADERA_MICB1A_ENA_MASK 0x0001 +#define MADERA_MICB1A_ENA_SHIFT 0 +#define MADERA_MICB1A_ENA_WIDTH 1 + +/* (0x021E) Mic_Bias_Ctrl_6 */ +#define MADERA_MICB2D_ENA 0x1000 +#define MADERA_MICB2D_ENA_MASK 0x1000 +#define MADERA_MICB2D_ENA_SHIFT 12 +#define MADERA_MICB2D_ENA_WIDTH 1 +#define MADERA_MICB2C_ENA 0x0100 +#define MADERA_MICB2C_ENA_MASK 0x0100 +#define MADERA_MICB2C_ENA_SHIFT 8 +#define MADERA_MICB2C_ENA_WIDTH 1 +#define MADERA_MICB2B_ENA 0x0010 +#define MADERA_MICB2B_ENA_MASK 0x0010 +#define MADERA_MICB2B_ENA_SHIFT 4 +#define MADERA_MICB2B_ENA_WIDTH 1 +#define MADERA_MICB2A_ENA 0x0001 +#define MADERA_MICB2A_ENA_MASK 0x0001 +#define MADERA_MICB2A_ENA_SHIFT 0 +#define MADERA_MICB2A_ENA_WIDTH 1 + +/* (0x0293) Accessory_Detect_Mode_1 */ +#define MADERA_ACCDET_SRC 0x2000 +#define MADERA_ACCDET_SRC_MASK 0x2000 +#define MADERA_ACCDET_SRC_SHIFT 13 +#define MADERA_ACCDET_SRC_WIDTH 1 +#define MADERA_ACCDET_POLARITY_INV_ENA 0x0080 +#define MADERA_ACCDET_POLARITY_INV_ENA_MASK 0x0080 +#define MADERA_ACCDET_POLARITY_INV_ENA_SHIFT 7 +#define MADERA_ACCDET_POLARITY_INV_ENA_WIDTH 1 +#define MADERA_ACCDET_MODE_MASK 0x0007 +#define MADERA_ACCDET_MODE_SHIFT 0 +#define MADERA_ACCDET_MODE_WIDTH 3 + +/* (0x0299) Headphone_Detect_0 */ +#define MADERA_HPD_GND_SEL 0x0007 +#define MADERA_HPD_GND_SEL_MASK 0x0007 +#define MADERA_HPD_GND_SEL_SHIFT 0 +#define MADERA_HPD_GND_SEL_WIDTH 3 +#define MADERA_HPD_SENSE_SEL 0x00F0 +#define MADERA_HPD_SENSE_SEL_MASK 0x00F0 +#define MADERA_HPD_SENSE_SEL_SHIFT 4 +#define MADERA_HPD_SENSE_SEL_WIDTH 4 +#define MADERA_HPD_FRC_SEL 0x0F00 +#define MADERA_HPD_FRC_SEL_MASK 0x0F00 +#define MADERA_HPD_FRC_SEL_SHIFT 8 +#define MADERA_HPD_FRC_SEL_WIDTH 4 +#define MADERA_HPD_OUT_SEL 0x7000 +#define MADERA_HPD_OUT_SEL_MASK 0x7000 +#define MADERA_HPD_OUT_SEL_SHIFT 12 +#define MADERA_HPD_OUT_SEL_WIDTH 3 +#define MADERA_HPD_OVD_ENA_SEL 0x8000 +#define MADERA_HPD_OVD_ENA_SEL_MASK 0x8000 +#define MADERA_HPD_OVD_ENA_SEL_SHIFT 15 +#define MADERA_HPD_OVD_ENA_SEL_WIDTH 1 + +/* (0x029B) Headphone_Detect_1 */ +#define MADERA_HP_IMPEDANCE_RANGE_MASK 0x0600 +#define MADERA_HP_IMPEDANCE_RANGE_SHIFT 9 +#define MADERA_HP_IMPEDANCE_RANGE_WIDTH 2 +#define MADERA_HP_STEP_SIZE 0x0100 +#define MADERA_HP_STEP_SIZE_MASK 0x0100 +#define MADERA_HP_STEP_SIZE_SHIFT 8 +#define MADERA_HP_STEP_SIZE_WIDTH 1 +#define MADERA_HP_CLK_DIV_MASK 0x0018 +#define MADERA_HP_CLK_DIV_SHIFT 3 +#define MADERA_HP_CLK_DIV_WIDTH 2 +#define MADERA_HP_RATE_MASK 0x0006 +#define MADERA_HP_RATE_SHIFT 1 +#define MADERA_HP_RATE_WIDTH 2 +#define MADERA_HP_POLL 0x0001 +#define MADERA_HP_POLL_MASK 0x0001 +#define MADERA_HP_POLL_SHIFT 0 +#define MADERA_HP_POLL_WIDTH 1 + +/* (0x029C) Headphone_Detect_2 */ +#define MADERA_HP_DONE_MASK 0x8000 +#define MADERA_HP_DONE_SHIFT 15 +#define MADERA_HP_DONE_WIDTH 1 +#define MADERA_HP_LVL_MASK 0x7FFF +#define MADERA_HP_LVL_SHIFT 0 +#define MADERA_HP_LVL_WIDTH 15 + +/* (0x029D) Headphone_Detect_3 */ +#define MADERA_HP_DACVAL_MASK 0x03FF +#define MADERA_HP_DACVAL_SHIFT 0 +#define MADERA_HP_DACVAL_WIDTH 10 + +/* (0x029F) - Headphone Detect 5 */ +#define MADERA_HP_DACVAL_DOWN_MASK 0x03FF +#define MADERA_HP_DACVAL_DOWN_SHIFT 0 +#define MADERA_HP_DACVAL_DOWN_WIDTH 10 + +/* (0x02A2) Mic_Detect_1_Control_0 */ +#define MADERA_MICD1_GND_MASK 0x0007 +#define MADERA_MICD1_GND_SHIFT 0 +#define MADERA_MICD1_GND_WIDTH 3 +#define MADERA_MICD1_SENSE_MASK 0x00F0 +#define MADERA_MICD1_SENSE_SHIFT 4 +#define MADERA_MICD1_SENSE_WIDTH 4 +#define MADERA_MICD1_ADC_MODE_MASK 0x8000 +#define MADERA_MICD1_ADC_MODE_SHIFT 15 +#define MADERA_MICD1_ADC_MODE_WIDTH 1 + +/* (0x02A3) Mic_Detect_1_Control_1 */ +#define MADERA_MICD_BIAS_STARTTIME_MASK 0xF000 +#define MADERA_MICD_BIAS_STARTTIME_SHIFT 12 +#define MADERA_MICD_BIAS_STARTTIME_WIDTH 4 +#define MADERA_MICD_RATE_MASK 0x0F00 +#define MADERA_MICD_RATE_SHIFT 8 +#define MADERA_MICD_RATE_WIDTH 4 +#define MADERA_MICD_BIAS_SRC_MASK 0x00F0 +#define MADERA_MICD_BIAS_SRC_SHIFT 4 +#define MADERA_MICD_BIAS_SRC_WIDTH 4 +#define MADERA_MICD_DBTIME 0x0002 +#define MADERA_MICD_DBTIME_MASK 0x0002 +#define MADERA_MICD_DBTIME_SHIFT 1 +#define MADERA_MICD_DBTIME_WIDTH 1 +#define MADERA_MICD_ENA 0x0001 +#define MADERA_MICD_ENA_MASK 0x0001 +#define MADERA_MICD_ENA_SHIFT 0 +#define MADERA_MICD_ENA_WIDTH 1 + +/* (0x02A4) Mic_Detect_1_Control_2 */ +#define MADERA_MICD_LVL_SEL_MASK 0x00FF +#define MADERA_MICD_LVL_SEL_SHIFT 0 +#define MADERA_MICD_LVL_SEL_WIDTH 8 + +/* (0x02A5) Mic_Detect_1_Control_3 */ +#define MADERA_MICD_LVL_0 0x0004 +#define MADERA_MICD_LVL_1 0x0008 +#define MADERA_MICD_LVL_2 0x0010 +#define MADERA_MICD_LVL_3 0x0020 +#define MADERA_MICD_LVL_4 0x0040 +#define MADERA_MICD_LVL_5 0x0080 +#define MADERA_MICD_LVL_6 0x0100 +#define MADERA_MICD_LVL_7 0x0200 +#define MADERA_MICD_LVL_8 0x0400 +#define MADERA_MICD_LVL_MASK 0x07FC +#define MADERA_MICD_LVL_SHIFT 2 +#define MADERA_MICD_LVL_WIDTH 9 +#define MADERA_MICD_VALID 0x0002 +#define MADERA_MICD_VALID_MASK 0x0002 +#define MADERA_MICD_VALID_SHIFT 1 +#define MADERA_MICD_VALID_WIDTH 1 +#define MADERA_MICD_STS 0x0001 +#define MADERA_MICD_STS_MASK 0x0001 +#define MADERA_MICD_STS_SHIFT 0 +#define MADERA_MICD_STS_WIDTH 1 + +/* (0x02AB) Mic_Detect_1_Control_4 */ +#define MADERA_MICDET_ADCVAL_DIFF_MASK 0xFF00 +#define MADERA_MICDET_ADCVAL_DIFF_SHIFT 8 +#define MADERA_MICDET_ADCVAL_DIFF_WIDTH 8 +#define MADERA_MICDET_ADCVAL_MASK 0x007F +#define MADERA_MICDET_ADCVAL_SHIFT 0 +#define MADERA_MICDET_ADCVAL_WIDTH 7 + +/* (0x02C6) Micd_Clamp_control */ +#define MADERA_MICD_CLAMP_OVD 0x0010 +#define MADERA_MICD_CLAMP_OVD_MASK 0x0010 +#define MADERA_MICD_CLAMP_OVD_SHIFT 4 +#define MADERA_MICD_CLAMP_OVD_WIDTH 1 +#define MADERA_MICD_CLAMP_MODE_MASK 0x000F +#define MADERA_MICD_CLAMP_MODE_SHIFT 0 +#define MADERA_MICD_CLAMP_MODE_WIDTH 4 + +/* (0x02C8) GP_Switch_1 */ +#define MADERA_SW2_MODE_MASK 0x000C +#define MADERA_SW2_MODE_SHIFT 2 +#define MADERA_SW2_MODE_WIDTH 2 +#define MADERA_SW1_MODE_MASK 0x0003 +#define MADERA_SW1_MODE_SHIFT 0 +#define MADERA_SW1_MODE_WIDTH 2 + +/* (0x02D3) Jack_detect_analogue */ +#define MADERA_JD2_ENA 0x0002 +#define MADERA_JD2_ENA_MASK 0x0002 +#define MADERA_JD2_ENA_SHIFT 1 +#define MADERA_JD2_ENA_WIDTH 1 +#define MADERA_JD1_ENA 0x0001 +#define MADERA_JD1_ENA_MASK 0x0001 +#define MADERA_JD1_ENA_SHIFT 0 +#define MADERA_JD1_ENA_WIDTH 1 + +/* (0x0300) Input_Enables */ +#define MADERA_IN6L_ENA 0x0800 +#define MADERA_IN6L_ENA_MASK 0x0800 +#define MADERA_IN6L_ENA_SHIFT 11 +#define MADERA_IN6L_ENA_WIDTH 1 +#define MADERA_IN6R_ENA 0x0400 +#define MADERA_IN6R_ENA_MASK 0x0400 +#define MADERA_IN6R_ENA_SHIFT 10 +#define MADERA_IN6R_ENA_WIDTH 1 +#define MADERA_IN5L_ENA 0x0200 +#define MADERA_IN5L_ENA_MASK 0x0200 +#define MADERA_IN5L_ENA_SHIFT 9 +#define MADERA_IN5L_ENA_WIDTH 1 +#define MADERA_IN5R_ENA 0x0100 +#define MADERA_IN5R_ENA_MASK 0x0100 +#define MADERA_IN5R_ENA_SHIFT 8 +#define MADERA_IN5R_ENA_WIDTH 1 +#define MADERA_IN4L_ENA 0x0080 +#define MADERA_IN4L_ENA_MASK 0x0080 +#define MADERA_IN4L_ENA_SHIFT 7 +#define MADERA_IN4L_ENA_WIDTH 1 +#define MADERA_IN4R_ENA 0x0040 +#define MADERA_IN4R_ENA_MASK 0x0040 +#define MADERA_IN4R_ENA_SHIFT 6 +#define MADERA_IN4R_ENA_WIDTH 1 +#define MADERA_IN3L_ENA 0x0020 +#define MADERA_IN3L_ENA_MASK 0x0020 +#define MADERA_IN3L_ENA_SHIFT 5 +#define MADERA_IN3L_ENA_WIDTH 1 +#define MADERA_IN3R_ENA 0x0010 +#define MADERA_IN3R_ENA_MASK 0x0010 +#define MADERA_IN3R_ENA_SHIFT 4 +#define MADERA_IN3R_ENA_WIDTH 1 +#define MADERA_IN2L_ENA 0x0008 +#define MADERA_IN2L_ENA_MASK 0x0008 +#define MADERA_IN2L_ENA_SHIFT 3 +#define MADERA_IN2L_ENA_WIDTH 1 +#define MADERA_IN2R_ENA 0x0004 +#define MADERA_IN2R_ENA_MASK 0x0004 +#define MADERA_IN2R_ENA_SHIFT 2 +#define MADERA_IN2R_ENA_WIDTH 1 +#define MADERA_IN1L_ENA 0x0002 +#define MADERA_IN1L_ENA_MASK 0x0002 +#define MADERA_IN1L_ENA_SHIFT 1 +#define MADERA_IN1L_ENA_WIDTH 1 +#define MADERA_IN1R_ENA 0x0001 +#define MADERA_IN1R_ENA_MASK 0x0001 +#define MADERA_IN1R_ENA_SHIFT 0 +#define MADERA_IN1R_ENA_WIDTH 1 + +/* (0x0308) Input_Rate */ +#define MADERA_IN_RATE_MASK 0xF800 +#define MADERA_IN_RATE_SHIFT 11 +#define MADERA_IN_RATE_WIDTH 5 +#define MADERA_IN_MODE_MASK 0x0400 +#define MADERA_IN_MODE_SHIFT 10 +#define MADERA_IN_MODE_WIDTH 1 + +/* (0x0309) Input_Volume_Ramp */ +#define MADERA_IN_VD_RAMP_MASK 0x0070 +#define MADERA_IN_VD_RAMP_SHIFT 4 +#define MADERA_IN_VD_RAMP_WIDTH 3 +#define MADERA_IN_VI_RAMP_MASK 0x0007 +#define MADERA_IN_VI_RAMP_SHIFT 0 +#define MADERA_IN_VI_RAMP_WIDTH 3 + +/* (0x030C) HPF_Control */ +#define MADERA_IN_HPF_CUT_MASK 0x0007 +#define MADERA_IN_HPF_CUT_SHIFT 0 +#define MADERA_IN_HPF_CUT_WIDTH 3 + +/* (0x0310) IN1L_Control */ +#define MADERA_IN1L_HPF_MASK 0x8000 +#define MADERA_IN1L_HPF_SHIFT 15 +#define MADERA_IN1L_HPF_WIDTH 1 +#define MADERA_IN1_DMIC_SUP_MASK 0x1800 +#define MADERA_IN1_DMIC_SUP_SHIFT 11 +#define MADERA_IN1_DMIC_SUP_WIDTH 2 +#define MADERA_IN1_MODE_MASK 0x0400 +#define MADERA_IN1_MODE_SHIFT 10 +#define MADERA_IN1_MODE_WIDTH 1 +#define MADERA_IN1L_PGA_VOL_MASK 0x00FE +#define MADERA_IN1L_PGA_VOL_SHIFT 1 +#define MADERA_IN1L_PGA_VOL_WIDTH 7 + +/* (0x0311) ADC_Digital_Volume_1L */ +#define MADERA_IN1L_SRC_MASK 0x4000 +#define MADERA_IN1L_SRC_SHIFT 14 +#define MADERA_IN1L_SRC_WIDTH 1 +#define MADERA_IN1L_SRC_SE_MASK 0x2000 +#define MADERA_IN1L_SRC_SE_SHIFT 13 +#define MADERA_IN1L_SRC_SE_WIDTH 1 +#define MADERA_IN1L_LP_MODE 0x0800 +#define MADERA_IN1L_LP_MODE_MASK 0x0800 +#define MADERA_IN1L_LP_MODE_SHIFT 11 +#define MADERA_IN1L_LP_MODE_WIDTH 1 +#define MADERA_IN_VU 0x0200 +#define MADERA_IN_VU_MASK 0x0200 +#define MADERA_IN_VU_SHIFT 9 +#define MADERA_IN_VU_WIDTH 1 +#define MADERA_IN1L_MUTE 0x0100 +#define MADERA_IN1L_MUTE_MASK 0x0100 +#define MADERA_IN1L_MUTE_SHIFT 8 +#define MADERA_IN1L_MUTE_WIDTH 1 +#define MADERA_IN1L_DIG_VOL_MASK 0x00FF +#define MADERA_IN1L_DIG_VOL_SHIFT 0 +#define MADERA_IN1L_DIG_VOL_WIDTH 8 + +/* (0x0312) DMIC1L_Control */ +#define MADERA_IN1_OSR_MASK 0x0700 +#define MADERA_IN1_OSR_SHIFT 8 +#define MADERA_IN1_OSR_WIDTH 3 + +/* (0x0313) IN1L_Rate_Control */ +#define MADERA_IN1L_RATE_MASK 0xF800 +#define MADERA_IN1L_RATE_SHIFT 11 +#define MADERA_IN1L_RATE_WIDTH 5 + +/* (0x0314) IN1R_Control */ +#define MADERA_IN1R_HPF_MASK 0x8000 +#define MADERA_IN1R_HPF_SHIFT 15 +#define MADERA_IN1R_HPF_WIDTH 1 +#define MADERA_IN1R_PGA_VOL_MASK 0x00FE +#define MADERA_IN1R_PGA_VOL_SHIFT 1 +#define MADERA_IN1R_PGA_VOL_WIDTH 7 +#define MADERA_IN1_DMICCLK_SRC_MASK 0x1800 +#define MADERA_IN1_DMICCLK_SRC_SHIFT 11 +#define MADERA_IN1_DMICCLK_SRC_WIDTH 2 + +/* (0x0315) ADC_Digital_Volume_1R */ +#define MADERA_IN1R_SRC_MASK 0x4000 +#define MADERA_IN1R_SRC_SHIFT 14 +#define MADERA_IN1R_SRC_WIDTH 1 +#define MADERA_IN1R_SRC_SE_MASK 0x2000 +#define MADERA_IN1R_SRC_SE_SHIFT 13 +#define MADERA_IN1R_SRC_SE_WIDTH 1 +#define MADERA_IN1R_LP_MODE 0x0800 +#define MADERA_IN1R_LP_MODE_MASK 0x0800 +#define MADERA_IN1R_LP_MODE_SHIFT 11 +#define MADERA_IN1R_LP_MODE_WIDTH 1 +#define MADERA_IN1R_MUTE 0x0100 +#define MADERA_IN1R_MUTE_MASK 0x0100 +#define MADERA_IN1R_MUTE_SHIFT 8 +#define MADERA_IN1R_MUTE_WIDTH 1 +#define MADERA_IN1R_DIG_VOL_MASK 0x00FF +#define MADERA_IN1R_DIG_VOL_SHIFT 0 +#define MADERA_IN1R_DIG_VOL_WIDTH 8 + +/* (0x0317) IN1R_Rate_Control */ +#define MADERA_IN1R_RATE_MASK 0xF800 +#define MADERA_IN1R_RATE_SHIFT 11 +#define MADERA_IN1R_RATE_WIDTH 5 + +/* (0x0318) IN2L_Control */ +#define MADERA_IN2L_HPF_MASK 0x8000 +#define MADERA_IN2L_HPF_SHIFT 15 +#define MADERA_IN2L_HPF_WIDTH 1 +#define MADERA_IN2_DMIC_SUP_MASK 0x1800 +#define MADERA_IN2_DMIC_SUP_SHIFT 11 +#define MADERA_IN2_DMIC_SUP_WIDTH 2 +#define MADERA_IN2_MODE_MASK 0x0400 +#define MADERA_IN2_MODE_SHIFT 10 +#define MADERA_IN2_MODE_WIDTH 1 +#define MADERA_IN2L_PGA_VOL_MASK 0x00FE +#define MADERA_IN2L_PGA_VOL_SHIFT 1 +#define MADERA_IN2L_PGA_VOL_WIDTH 7 + +/* (0x0319) ADC_Digital_Volume_2L */ +#define MADERA_IN2L_SRC_MASK 0x4000 +#define MADERA_IN2L_SRC_SHIFT 14 +#define MADERA_IN2L_SRC_WIDTH 1 +#define MADERA_IN2L_SRC_SE_MASK 0x2000 +#define MADERA_IN2L_SRC_SE_SHIFT 13 +#define MADERA_IN2L_SRC_SE_WIDTH 1 +#define MADERA_IN2L_LP_MODE 0x0800 +#define MADERA_IN2L_LP_MODE_MASK 0x0800 +#define MADERA_IN2L_LP_MODE_SHIFT 11 +#define MADERA_IN2L_LP_MODE_WIDTH 1 +#define MADERA_IN2L_MUTE 0x0100 +#define MADERA_IN2L_MUTE_MASK 0x0100 +#define MADERA_IN2L_MUTE_SHIFT 8 +#define MADERA_IN2L_MUTE_WIDTH 1 +#define MADERA_IN2L_DIG_VOL_MASK 0x00FF +#define MADERA_IN2L_DIG_VOL_SHIFT 0 +#define MADERA_IN2L_DIG_VOL_WIDTH 8 + +/* (0x031A) DMIC2L_Control */ +#define MADERA_IN2_OSR_MASK 0x0700 +#define MADERA_IN2_OSR_SHIFT 8 +#define MADERA_IN2_OSR_WIDTH 3 + +/* (0x031C) IN2R_Control */ +#define MADERA_IN2R_HPF_MASK 0x8000 +#define MADERA_IN2R_HPF_SHIFT 15 +#define MADERA_IN2R_HPF_WIDTH 1 +#define MADERA_IN2R_PGA_VOL_MASK 0x00FE +#define MADERA_IN2R_PGA_VOL_SHIFT 1 +#define MADERA_IN2R_PGA_VOL_WIDTH 7 +#define MADERA_IN2_DMICCLK_SRC_MASK 0x1800 +#define MADERA_IN2_DMICCLK_SRC_SHIFT 11 +#define MADERA_IN2_DMICCLK_SRC_WIDTH 2 + +/* (0x031D) ADC_Digital_Volume_2R */ +#define MADERA_IN2R_SRC_MASK 0x4000 +#define MADERA_IN2R_SRC_SHIFT 14 +#define MADERA_IN2R_SRC_WIDTH 1 +#define MADERA_IN2R_SRC_SE_MASK 0x2000 +#define MADERA_IN2R_SRC_SE_SHIFT 13 +#define MADERA_IN2R_SRC_SE_WIDTH 1 +#define MADERA_IN2R_LP_MODE 0x0800 +#define MADERA_IN2R_LP_MODE_MASK 0x0800 +#define MADERA_IN2R_LP_MODE_SHIFT 11 +#define MADERA_IN2R_LP_MODE_WIDTH 1 +#define MADERA_IN2R_MUTE 0x0100 +#define MADERA_IN2R_MUTE_MASK 0x0100 +#define MADERA_IN2R_MUTE_SHIFT 8 +#define MADERA_IN2R_MUTE_WIDTH 1 +#define MADERA_IN2R_DIG_VOL_MASK 0x00FF +#define MADERA_IN2R_DIG_VOL_SHIFT 0 +#define MADERA_IN2R_DIG_VOL_WIDTH 8 + +/* (0x0320) IN3L_Control */ +#define MADERA_IN3L_HPF_MASK 0x8000 +#define MADERA_IN3L_HPF_SHIFT 15 +#define MADERA_IN3L_HPF_WIDTH 1 +#define MADERA_IN3_DMIC_SUP_MASK 0x1800 +#define MADERA_IN3_DMIC_SUP_SHIFT 11 +#define MADERA_IN3_DMIC_SUP_WIDTH 2 +#define MADERA_IN3_MODE_MASK 0x0400 +#define MADERA_IN3_MODE_SHIFT 10 +#define MADERA_IN3_MODE_WIDTH 1 +#define MADERA_IN3L_PGA_VOL_MASK 0x00FE +#define MADERA_IN3L_PGA_VOL_SHIFT 1 +#define MADERA_IN3L_PGA_VOL_WIDTH 7 + +/* (0x0321) ADC_Digital_Volume_3L */ +#define MADERA_IN3L_MUTE 0x0100 +#define MADERA_IN3L_MUTE_MASK 0x0100 +#define MADERA_IN3L_MUTE_SHIFT 8 +#define MADERA_IN3L_MUTE_WIDTH 1 +#define MADERA_IN3L_DIG_VOL_MASK 0x00FF +#define MADERA_IN3L_DIG_VOL_SHIFT 0 +#define MADERA_IN3L_DIG_VOL_WIDTH 8 + +/* (0x0322) DMIC3L_Control */ +#define MADERA_IN3_OSR_MASK 0x0700 +#define MADERA_IN3_OSR_SHIFT 8 +#define MADERA_IN3_OSR_WIDTH 3 + +/* (0x0324) IN3R_Control */ +#define MADERA_IN3R_HPF_MASK 0x8000 +#define MADERA_IN3R_HPF_SHIFT 15 +#define MADERA_IN3R_HPF_WIDTH 1 +#define MADERA_IN3R_PGA_VOL_MASK 0x00FE +#define MADERA_IN3R_PGA_VOL_SHIFT 1 +#define MADERA_IN3R_PGA_VOL_WIDTH 7 +#define MADERA_IN3_DMICCLK_SRC_MASK 0x1800 +#define MADERA_IN3_DMICCLK_SRC_SHIFT 11 +#define MADERA_IN3_DMICCLK_SRC_WIDTH 2 + +/* (0x0325) ADC_Digital_Volume_3R */ +#define MADERA_IN3R_MUTE 0x0100 +#define MADERA_IN3R_MUTE_MASK 0x0100 +#define MADERA_IN3R_MUTE_SHIFT 8 +#define MADERA_IN3R_MUTE_WIDTH 1 +#define MADERA_IN3R_DIG_VOL_MASK 0x00FF +#define MADERA_IN3R_DIG_VOL_SHIFT 0 +#define MADERA_IN3R_DIG_VOL_WIDTH 8 + +/* (0x0328) IN4L_Control */ +#define MADERA_IN4L_HPF_MASK 0x8000 +#define MADERA_IN4L_HPF_SHIFT 15 +#define MADERA_IN4L_HPF_WIDTH 1 +#define MADERA_IN4_DMIC_SUP_MASK 0x1800 +#define MADERA_IN4_DMIC_SUP_SHIFT 11 +#define MADERA_IN4_DMIC_SUP_WIDTH 2 + +/* (0x0329) ADC_Digital_Volume_4L */ +#define MADERA_IN4L_MUTE 0x0100 +#define MADERA_IN4L_MUTE_MASK 0x0100 +#define MADERA_IN4L_MUTE_SHIFT 8 +#define MADERA_IN4L_MUTE_WIDTH 1 +#define MADERA_IN4L_DIG_VOL_MASK 0x00FF +#define MADERA_IN4L_DIG_VOL_SHIFT 0 +#define MADERA_IN4L_DIG_VOL_WIDTH 8 + +/* (0x032A) DMIC4L_Control */ +#define MADERA_IN4_OSR_MASK 0x0700 +#define MADERA_IN4_OSR_SHIFT 8 +#define MADERA_IN4_OSR_WIDTH 3 + +/* (0x032C) IN4R_Control */ +#define MADERA_IN4R_HPF_MASK 0x8000 +#define MADERA_IN4R_HPF_SHIFT 15 +#define MADERA_IN4R_HPF_WIDTH 1 +#define MADERA_IN4_DMICCLK_SRC_MASK 0x1800 +#define MADERA_IN4_DMICCLK_SRC_SHIFT 11 +#define MADERA_IN4_DMICCLK_SRC_WIDTH 2 + +/* (0x032D) ADC_Digital_Volume_4R */ +#define MADERA_IN4R_MUTE 0x0100 +#define MADERA_IN4R_MUTE_MASK 0x0100 +#define MADERA_IN4R_MUTE_SHIFT 8 +#define MADERA_IN4R_MUTE_WIDTH 1 +#define MADERA_IN4R_DIG_VOL_MASK 0x00FF +#define MADERA_IN4R_DIG_VOL_SHIFT 0 +#define MADERA_IN4R_DIG_VOL_WIDTH 8 + +/* (0x0330) IN5L_Control */ +#define MADERA_IN5L_HPF_MASK 0x8000 +#define MADERA_IN5L_HPF_SHIFT 15 +#define MADERA_IN5L_HPF_WIDTH 1 +#define MADERA_IN5_DMIC_SUP_MASK 0x1800 +#define MADERA_IN5_DMIC_SUP_SHIFT 11 +#define MADERA_IN5_DMIC_SUP_WIDTH 2 + +/* (0x0331) ADC_Digital_Volume_5L */ +#define MADERA_IN5L_MUTE 0x0100 +#define MADERA_IN5L_MUTE_MASK 0x0100 +#define MADERA_IN5L_MUTE_SHIFT 8 +#define MADERA_IN5L_MUTE_WIDTH 1 +#define MADERA_IN5L_DIG_VOL_MASK 0x00FF +#define MADERA_IN5L_DIG_VOL_SHIFT 0 +#define MADERA_IN5L_DIG_VOL_WIDTH 8 + +/* (0x0332) DMIC5L_Control */ +#define MADERA_IN5_OSR_MASK 0x0700 +#define MADERA_IN5_OSR_SHIFT 8 +#define MADERA_IN5_OSR_WIDTH 3 + +/* (0x0334) IN5R_Control */ +#define MADERA_IN5R_HPF_MASK 0x8000 +#define MADERA_IN5R_HPF_SHIFT 15 +#define MADERA_IN5R_HPF_WIDTH 1 +#define MADERA_IN5_DMICCLK_SRC_MASK 0x1800 +#define MADERA_IN5_DMICCLK_SRC_SHIFT 11 +#define MADERA_IN5_DMICCLK_SRC_WIDTH 2 + +/* (0x0335) ADC_Digital_Volume_5R */ +#define MADERA_IN5R_MUTE 0x0100 +#define MADERA_IN5R_MUTE_MASK 0x0100 +#define MADERA_IN5R_MUTE_SHIFT 8 +#define MADERA_IN5R_MUTE_WIDTH 1 +#define MADERA_IN5R_DIG_VOL_MASK 0x00FF +#define MADERA_IN5R_DIG_VOL_SHIFT 0 +#define MADERA_IN5R_DIG_VOL_WIDTH 8 + +/* (0x0338) IN6L_Control */ +#define MADERA_IN6L_HPF_MASK 0x8000 +#define MADERA_IN6L_HPF_SHIFT 15 +#define MADERA_IN6L_HPF_WIDTH 1 +#define MADERA_IN6_DMIC_SUP_MASK 0x1800 +#define MADERA_IN6_DMIC_SUP_SHIFT 11 +#define MADERA_IN6_DMIC_SUP_WIDTH 2 + +/* (0x0339) ADC_Digital_Volume_6L */ +#define MADERA_IN6L_MUTE 0x0100 +#define MADERA_IN6L_MUTE_MASK 0x0100 +#define MADERA_IN6L_MUTE_SHIFT 8 +#define MADERA_IN6L_MUTE_WIDTH 1 +#define MADERA_IN6L_DIG_VOL_MASK 0x00FF +#define MADERA_IN6L_DIG_VOL_SHIFT 0 +#define MADERA_IN6L_DIG_VOL_WIDTH 8 + +/* (0x033A) DMIC6L_Control */ +#define MADERA_IN6_OSR_MASK 0x0700 +#define MADERA_IN6_OSR_SHIFT 8 +#define MADERA_IN6_OSR_WIDTH 3 + +/* (0x033C) IN6R_Control */ +#define MADERA_IN6R_HPF_MASK 0x8000 +#define MADERA_IN6R_HPF_SHIFT 15 +#define MADERA_IN6R_HPF_WIDTH 1 + +/* (0x033D) ADC_Digital_Volume_6R */ +#define MADERA_IN6R_MUTE 0x0100 +#define MADERA_IN6R_MUTE_MASK 0x0100 +#define MADERA_IN6R_MUTE_SHIFT 8 +#define MADERA_IN6R_MUTE_WIDTH 1 +#define MADERA_IN6R_DIG_VOL_MASK 0x00FF +#define MADERA_IN6R_DIG_VOL_SHIFT 0 +#define MADERA_IN6R_DIG_VOL_WIDTH 8 + +/* (0x033E) DMIC6R_Control */ +#define MADERA_IN6_DMICCLK_SRC_MASK 0x1800 +#define MADERA_IN6_DMICCLK_SRC_SHIFT 11 +#define MADERA_IN6_DMICCLK_SRC_WIDTH 2 + +/* (0x0400) Output_Enables_1 */ +#define MADERA_EP_SEL 0x8000 +#define MADERA_EP_SEL_MASK 0x8000 +#define MADERA_EP_SEL_SHIFT 15 +#define MADERA_EP_SEL_WIDTH 1 +#define MADERA_OUT6L_ENA 0x0800 +#define MADERA_OUT6L_ENA_MASK 0x0800 +#define MADERA_OUT6L_ENA_SHIFT 11 +#define MADERA_OUT6L_ENA_WIDTH 1 +#define MADERA_OUT6R_ENA 0x0400 +#define MADERA_OUT6R_ENA_MASK 0x0400 +#define MADERA_OUT6R_ENA_SHIFT 10 +#define MADERA_OUT6R_ENA_WIDTH 1 +#define MADERA_OUT5L_ENA 0x0200 +#define MADERA_OUT5L_ENA_MASK 0x0200 +#define MADERA_OUT5L_ENA_SHIFT 9 +#define MADERA_OUT5L_ENA_WIDTH 1 +#define MADERA_OUT5R_ENA 0x0100 +#define MADERA_OUT5R_ENA_MASK 0x0100 +#define MADERA_OUT5R_ENA_SHIFT 8 +#define MADERA_OUT5R_ENA_WIDTH 1 +#define MADERA_OUT4L_ENA 0x0080 +#define MADERA_OUT4L_ENA_MASK 0x0080 +#define MADERA_OUT4L_ENA_SHIFT 7 +#define MADERA_OUT4L_ENA_WIDTH 1 +#define MADERA_OUT4R_ENA 0x0040 +#define MADERA_OUT4R_ENA_MASK 0x0040 +#define MADERA_OUT4R_ENA_SHIFT 6 +#define MADERA_OUT4R_ENA_WIDTH 1 +#define MADERA_OUT3L_ENA 0x0020 +#define MADERA_OUT3L_ENA_MASK 0x0020 +#define MADERA_OUT3L_ENA_SHIFT 5 +#define MADERA_OUT3L_ENA_WIDTH 1 +#define MADERA_OUT3R_ENA 0x0010 +#define MADERA_OUT3R_ENA_MASK 0x0010 +#define MADERA_OUT3R_ENA_SHIFT 4 +#define MADERA_OUT3R_ENA_WIDTH 1 +#define MADERA_OUT2L_ENA 0x0008 +#define MADERA_OUT2L_ENA_MASK 0x0008 +#define MADERA_OUT2L_ENA_SHIFT 3 +#define MADERA_OUT2L_ENA_WIDTH 1 +#define MADERA_OUT2R_ENA 0x0004 +#define MADERA_OUT2R_ENA_MASK 0x0004 +#define MADERA_OUT2R_ENA_SHIFT 2 +#define MADERA_OUT2R_ENA_WIDTH 1 +#define MADERA_OUT1L_ENA 0x0002 +#define MADERA_OUT1L_ENA_MASK 0x0002 +#define MADERA_OUT1L_ENA_SHIFT 1 +#define MADERA_OUT1L_ENA_WIDTH 1 +#define MADERA_OUT1R_ENA 0x0001 +#define MADERA_OUT1R_ENA_MASK 0x0001 +#define MADERA_OUT1R_ENA_SHIFT 0 +#define MADERA_OUT1R_ENA_WIDTH 1 + +/* (0x0409) Output_Volume_Ramp */ +#define MADERA_OUT_VD_RAMP_MASK 0x0070 +#define MADERA_OUT_VD_RAMP_SHIFT 4 +#define MADERA_OUT_VD_RAMP_WIDTH 3 +#define MADERA_OUT_VI_RAMP_MASK 0x0007 +#define MADERA_OUT_VI_RAMP_SHIFT 0 +#define MADERA_OUT_VI_RAMP_WIDTH 3 + +/* (0x0410) Output_Path_Config_1L */ +#define MADERA_OUT1_MONO 0x1000 +#define MADERA_OUT1_MONO_MASK 0x1000 +#define MADERA_OUT1_MONO_SHIFT 12 +#define MADERA_OUT1_MONO_WIDTH 1 +#define MADERA_OUT1L_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT1L_ANC_SRC_SHIFT 10 +#define MADERA_OUT1L_ANC_SRC_WIDTH 2 + +/* (0x0411) DAC_Digital_Volume_1L */ +#define MADERA_OUT1L_VU 0x0200 +#define MADERA_OUT1L_VU_MASK 0x0200 +#define MADERA_OUT1L_VU_SHIFT 9 +#define MADERA_OUT1L_VU_WIDTH 1 +#define MADERA_OUT1L_MUTE 0x0100 +#define MADERA_OUT1L_MUTE_MASK 0x0100 +#define MADERA_OUT1L_MUTE_SHIFT 8 +#define MADERA_OUT1L_MUTE_WIDTH 1 +#define MADERA_OUT1L_VOL_MASK 0x00FF +#define MADERA_OUT1L_VOL_SHIFT 0 +#define MADERA_OUT1L_VOL_WIDTH 8 + +/* (0x0412) Output_Path_Config_1 */ +#define MADERA_HP1_GND_SEL_MASK 0x0007 +#define MADERA_HP1_GND_SEL_SHIFT 0 +#define MADERA_HP1_GND_SEL_WIDTH 3 + +/* (0x0414) Output_Path_Config_1R */ +#define MADERA_OUT1R_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT1R_ANC_SRC_SHIFT 10 +#define MADERA_OUT1R_ANC_SRC_WIDTH 2 + +/* (0x0415) DAC_Digital_Volume_1R */ +#define MADERA_OUT1R_MUTE 0x0100 +#define MADERA_OUT1R_MUTE_MASK 0x0100 +#define MADERA_OUT1R_MUTE_SHIFT 8 +#define MADERA_OUT1R_MUTE_WIDTH 1 +#define MADERA_OUT1R_VOL_MASK 0x00FF +#define MADERA_OUT1R_VOL_SHIFT 0 +#define MADERA_OUT1R_VOL_WIDTH 8 + +/* (0x0418) Output_Path_Config_2L */ +#define MADERA_OUT2L_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT2L_ANC_SRC_SHIFT 10 +#define MADERA_OUT2L_ANC_SRC_WIDTH 2 + +/* (0x0419) DAC_Digital_Volume_2L */ +#define MADERA_OUT2L_MUTE 0x0100 +#define MADERA_OUT2L_MUTE_MASK 0x0100 +#define MADERA_OUT2L_MUTE_SHIFT 8 +#define MADERA_OUT2L_MUTE_WIDTH 1 +#define MADERA_OUT2L_VOL_MASK 0x00FF +#define MADERA_OUT2L_VOL_SHIFT 0 +#define MADERA_OUT2L_VOL_WIDTH 8 + +/* (0x041A) Output_Path_Config_2 */ +#define MADERA_HP2_GND_SEL_MASK 0x0007 +#define MADERA_HP2_GND_SEL_SHIFT 0 +#define MADERA_HP2_GND_SEL_WIDTH 3 + +/* (0x041C) Output_Path_Config_2R */ +#define MADERA_OUT2R_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT2R_ANC_SRC_SHIFT 10 +#define MADERA_OUT2R_ANC_SRC_WIDTH 2 + +/* (0x041D) DAC_Digital_Volume_2R */ +#define MADERA_OUT2R_MUTE 0x0100 +#define MADERA_OUT2R_MUTE_MASK 0x0100 +#define MADERA_OUT2R_MUTE_SHIFT 8 +#define MADERA_OUT2R_MUTE_WIDTH 1 +#define MADERA_OUT2R_VOL_MASK 0x00FF +#define MADERA_OUT2R_VOL_SHIFT 0 +#define MADERA_OUT2R_VOL_WIDTH 8 + +/* (0x0420) Output_Path_Config_3L */ +#define MADERA_OUT3L_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT3L_ANC_SRC_SHIFT 10 +#define MADERA_OUT3L_ANC_SRC_WIDTH 2 + +/* (0x0421) DAC_Digital_Volume_3L */ +#define MADERA_OUT3L_MUTE 0x0100 +#define MADERA_OUT3L_MUTE_MASK 0x0100 +#define MADERA_OUT3L_MUTE_SHIFT 8 +#define MADERA_OUT3L_MUTE_WIDTH 1 +#define MADERA_OUT3L_VOL_MASK 0x00FF +#define MADERA_OUT3L_VOL_SHIFT 0 +#define MADERA_OUT3L_VOL_WIDTH 8 + +/* (0x0424) Output_Path_Config_3R */ +#define MADERA_OUT3R_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT3R_ANC_SRC_SHIFT 10 +#define MADERA_OUT3R_ANC_SRC_WIDTH 2 + +/* (0x0425) DAC_Digital_Volume_3R */ +#define MADERA_OUT3R_MUTE 0x0100 +#define MADERA_OUT3R_MUTE_MASK 0x0100 +#define MADERA_OUT3R_MUTE_SHIFT 8 +#define MADERA_OUT3R_MUTE_WIDTH 1 +#define MADERA_OUT3R_VOL_MASK 0x00FF +#define MADERA_OUT3R_VOL_SHIFT 0 +#define MADERA_OUT3R_VOL_WIDTH 8 + +/* (0x0428) Output_Path_Config_4L */ +#define MADERA_OUT4L_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT4L_ANC_SRC_SHIFT 10 +#define MADERA_OUT4L_ANC_SRC_WIDTH 2 + +/* (0x0429) DAC_Digital_Volume_4L */ +#define MADERA_OUT4L_MUTE 0x0100 +#define MADERA_OUT4L_MUTE_MASK 0x0100 +#define MADERA_OUT4L_MUTE_SHIFT 8 +#define MADERA_OUT4L_MUTE_WIDTH 1 +#define MADERA_OUT4L_VOL_MASK 0x00FF +#define MADERA_OUT4L_VOL_SHIFT 0 +#define MADERA_OUT4L_VOL_WIDTH 8 + +/* (0x042C) Output_Path_Config_4R */ +#define MADERA_OUT4R_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT4R_ANC_SRC_SHIFT 10 +#define MADERA_OUT4R_ANC_SRC_WIDTH 2 + +/* (0x042D) DAC_Digital_Volume_4R */ +#define MADERA_OUT4R_MUTE 0x0100 +#define MADERA_OUT4R_MUTE_MASK 0x0100 +#define MADERA_OUT4R_MUTE_SHIFT 8 +#define MADERA_OUT4R_MUTE_WIDTH 1 +#define MADERA_OUT4R_VOL_MASK 0x00FF +#define MADERA_OUT4R_VOL_SHIFT 0 +#define MADERA_OUT4R_VOL_WIDTH 8 + +/* (0x0430) Output_Path_Config_5L */ +#define MADERA_OUT5_OSR 0x2000 +#define MADERA_OUT5_OSR_MASK 0x2000 +#define MADERA_OUT5_OSR_SHIFT 13 +#define MADERA_OUT5_OSR_WIDTH 1 +#define MADERA_OUT5L_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT5L_ANC_SRC_SHIFT 10 +#define MADERA_OUT5L_ANC_SRC_WIDTH 2 + +/* (0x0431) DAC_Digital_Volume_5L */ +#define MADERA_OUT5L_MUTE 0x0100 +#define MADERA_OUT5L_MUTE_MASK 0x0100 +#define MADERA_OUT5L_MUTE_SHIFT 8 +#define MADERA_OUT5L_MUTE_WIDTH 1 +#define MADERA_OUT5L_VOL_MASK 0x00FF +#define MADERA_OUT5L_VOL_SHIFT 0 +#define MADERA_OUT5L_VOL_WIDTH 8 + +/* (0x0434) Output_Path_Config_5R */ +#define MADERA_OUT5R_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT5R_ANC_SRC_SHIFT 10 +#define MADERA_OUT5R_ANC_SRC_WIDTH 2 + +/* (0x0435) DAC_Digital_Volume_5R */ +#define MADERA_OUT5R_MUTE 0x0100 +#define MADERA_OUT5R_MUTE_MASK 0x0100 +#define MADERA_OUT5R_MUTE_SHIFT 8 +#define MADERA_OUT5R_MUTE_WIDTH 1 +#define MADERA_OUT5R_VOL_MASK 0x00FF +#define MADERA_OUT5R_VOL_SHIFT 0 +#define MADERA_OUT5R_VOL_WIDTH 8 + +/* (0x0438) Output_Path_Config_6L */ +#define MADERA_OUT6_OSR 0x2000 +#define MADERA_OUT6_OSR_MASK 0x2000 +#define MADERA_OUT6_OSR_SHIFT 13 +#define MADERA_OUT6_OSR_WIDTH 1 +#define MADERA_OUT6L_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT6L_ANC_SRC_SHIFT 10 +#define MADERA_OUT6L_ANC_SRC_WIDTH 2 + +/* (0x0439) DAC_Digital_Volume_6L */ +#define MADERA_OUT6L_MUTE 0x0100 +#define MADERA_OUT6L_MUTE_MASK 0x0100 +#define MADERA_OUT6L_MUTE_SHIFT 8 +#define MADERA_OUT6L_MUTE_WIDTH 1 +#define MADERA_OUT6L_VOL_MASK 0x00FF +#define MADERA_OUT6L_VOL_SHIFT 0 +#define MADERA_OUT6L_VOL_WIDTH 8 + +/* (0x043C) Output_Path_Config_6R */ +#define MADERA_OUT6R_ANC_SRC_MASK 0x0C00 +#define MADERA_OUT6R_ANC_SRC_SHIFT 10 +#define MADERA_OUT6R_ANC_SRC_WIDTH 2 + +/* (0x043D) DAC_Digital_Volume_6R */ +#define MADERA_OUT6R_MUTE 0x0100 +#define MADERA_OUT6R_MUTE_MASK 0x0100 +#define MADERA_OUT6R_MUTE_SHIFT 8 +#define MADERA_OUT6R_MUTE_WIDTH 1 +#define MADERA_OUT6R_VOL_MASK 0x00FF +#define MADERA_OUT6R_VOL_SHIFT 0 +#define MADERA_OUT6R_VOL_WIDTH 8 + +/* (0x0450) - DAC AEC Control 1 */ +#define MADERA_AEC1_LOOPBACK_SRC_MASK 0x003C +#define MADERA_AEC1_LOOPBACK_SRC_SHIFT 2 +#define MADERA_AEC1_LOOPBACK_SRC_WIDTH 4 +#define MADERA_AEC1_ENA_STS 0x0002 +#define MADERA_AEC1_ENA_STS_MASK 0x0002 +#define MADERA_AEC1_ENA_STS_SHIFT 1 +#define MADERA_AEC1_ENA_STS_WIDTH 1 +#define MADERA_AEC1_LOOPBACK_ENA 0x0001 +#define MADERA_AEC1_LOOPBACK_ENA_MASK 0x0001 +#define MADERA_AEC1_LOOPBACK_ENA_SHIFT 0 +#define MADERA_AEC1_LOOPBACK_ENA_WIDTH 1 + +/* (0x0451) DAC_AEC_Control_2 */ +#define MADERA_AEC2_LOOPBACK_SRC_MASK 0x003C +#define MADERA_AEC2_LOOPBACK_SRC_SHIFT 2 +#define MADERA_AEC2_LOOPBACK_SRC_WIDTH 4 +#define MADERA_AEC2_ENA_STS 0x0002 +#define MADERA_AEC2_ENA_STS_MASK 0x0002 +#define MADERA_AEC2_ENA_STS_SHIFT 1 +#define MADERA_AEC2_ENA_STS_WIDTH 1 +#define MADERA_AEC2_LOOPBACK_ENA 0x0001 +#define MADERA_AEC2_LOOPBACK_ENA_MASK 0x0001 +#define MADERA_AEC2_LOOPBACK_ENA_SHIFT 0 +#define MADERA_AEC2_LOOPBACK_ENA_WIDTH 1 + +/* (0x0458) Noise_Gate_Control */ +#define MADERA_NGATE_HOLD_MASK 0x0030 +#define MADERA_NGATE_HOLD_SHIFT 4 +#define MADERA_NGATE_HOLD_WIDTH 2 +#define MADERA_NGATE_THR_MASK 0x000E +#define MADERA_NGATE_THR_SHIFT 1 +#define MADERA_NGATE_THR_WIDTH 3 +#define MADERA_NGATE_ENA 0x0001 +#define MADERA_NGATE_ENA_MASK 0x0001 +#define MADERA_NGATE_ENA_SHIFT 0 +#define MADERA_NGATE_ENA_WIDTH 1 + +/* (0x0490) PDM_SPK1_CTRL_1 */ +#define MADERA_SPK1R_MUTE 0x2000 +#define MADERA_SPK1R_MUTE_MASK 0x2000 +#define MADERA_SPK1R_MUTE_SHIFT 13 +#define MADERA_SPK1R_MUTE_WIDTH 1 +#define MADERA_SPK1L_MUTE 0x1000 +#define MADERA_SPK1L_MUTE_MASK 0x1000 +#define MADERA_SPK1L_MUTE_SHIFT 12 +#define MADERA_SPK1L_MUTE_WIDTH 1 +#define MADERA_SPK1_MUTE_ENDIAN 0x0100 +#define MADERA_SPK1_MUTE_ENDIAN_MASK 0x0100 +#define MADERA_SPK1_MUTE_ENDIAN_SHIFT 8 +#define MADERA_SPK1_MUTE_ENDIAN_WIDTH 1 +#define MADERA_SPK1_MUTE_SEQ1_MASK 0x00FF +#define MADERA_SPK1_MUTE_SEQ1_SHIFT 0 +#define MADERA_SPK1_MUTE_SEQ1_WIDTH 8 + +/* (0x0491) PDM_SPK1_CTRL_2 */ +#define MADERA_SPK1_FMT 0x0001 +#define MADERA_SPK1_FMT_MASK 0x0001 +#define MADERA_SPK1_FMT_SHIFT 0 +#define MADERA_SPK1_FMT_WIDTH 1 + +/* (0x0492) PDM_SPK2_CTRL_1 */ +#define MADERA_SPK2R_MUTE 0x2000 +#define MADERA_SPK2R_MUTE_MASK 0x2000 +#define MADERA_SPK2R_MUTE_SHIFT 13 +#define MADERA_SPK2R_MUTE_WIDTH 1 +#define MADERA_SPK2L_MUTE 0x1000 +#define MADERA_SPK2L_MUTE_MASK 0x1000 +#define MADERA_SPK2L_MUTE_SHIFT 12 +#define MADERA_SPK2L_MUTE_WIDTH 1 + +/* (0x04A0) - HP1 Short Circuit Ctrl */ +#define MADERA_HP1_SC_ENA 0x1000 +#define MADERA_HP1_SC_ENA_MASK 0x1000 +#define MADERA_HP1_SC_ENA_SHIFT 12 +#define MADERA_HP1_SC_ENA_WIDTH 1 + +/* (0x04A1) - HP2 Short Circuit Ctrl */ +#define MADERA_HP2_SC_ENA 0x1000 +#define MADERA_HP2_SC_ENA_MASK 0x1000 +#define MADERA_HP2_SC_ENA_SHIFT 12 +#define MADERA_HP2_SC_ENA_WIDTH 1 + +/* (0x04A2) - HP3 Short Circuit Ctrl */ +#define MADERA_HP3_SC_ENA 0x1000 +#define MADERA_HP3_SC_ENA_MASK 0x1000 +#define MADERA_HP3_SC_ENA_SHIFT 12 +#define MADERA_HP3_SC_ENA_WIDTH 1 + +/* (0x04A8) - HP_Test_Ctrl_5 */ +#define MADERA_HP1L_ONEFLT 0x0100 +#define MADERA_HP1L_ONEFLT_MASK 0x0100 +#define MADERA_HP1L_ONEFLT_SHIFT 8 +#define MADERA_HP1L_ONEFLT_WIDTH 1 + +/* (0x04A9) - HP_Test_Ctrl_6 */ +#define MADERA_HP1R_ONEFLT 0x0100 +#define MADERA_HP1R_ONEFLT_MASK 0x0100 +#define MADERA_HP1R_ONEFLT_SHIFT 8 +#define MADERA_HP1R_ONEFLT_WIDTH 1 + +/* (0x0500) AIF1_BCLK_Ctrl */ +#define MADERA_AIF1_BCLK_INV 0x0080 +#define MADERA_AIF1_BCLK_INV_MASK 0x0080 +#define MADERA_AIF1_BCLK_INV_SHIFT 7 +#define MADERA_AIF1_BCLK_INV_WIDTH 1 +#define MADERA_AIF1_BCLK_MSTR 0x0020 +#define MADERA_AIF1_BCLK_MSTR_MASK 0x0020 +#define MADERA_AIF1_BCLK_MSTR_SHIFT 5 +#define MADERA_AIF1_BCLK_MSTR_WIDTH 1 +#define MADERA_AIF1_BCLK_FREQ_MASK 0x001F +#define MADERA_AIF1_BCLK_FREQ_SHIFT 0 +#define MADERA_AIF1_BCLK_FREQ_WIDTH 5 + +/* (0x0501) AIF1_Tx_Pin_Ctrl */ +#define MADERA_AIF1TX_LRCLK_SRC 0x0008 +#define MADERA_AIF1TX_LRCLK_SRC_MASK 0x0008 +#define MADERA_AIF1TX_LRCLK_SRC_SHIFT 3 +#define MADERA_AIF1TX_LRCLK_SRC_WIDTH 1 +#define MADERA_AIF1TX_LRCLK_INV 0x0004 +#define MADERA_AIF1TX_LRCLK_INV_MASK 0x0004 +#define MADERA_AIF1TX_LRCLK_INV_SHIFT 2 +#define MADERA_AIF1TX_LRCLK_INV_WIDTH 1 +#define MADERA_AIF1TX_LRCLK_MSTR 0x0001 +#define MADERA_AIF1TX_LRCLK_MSTR_MASK 0x0001 +#define MADERA_AIF1TX_LRCLK_MSTR_SHIFT 0 +#define MADERA_AIF1TX_LRCLK_MSTR_WIDTH 1 + +/* (0x0502) AIF1_Rx_Pin_Ctrl */ +#define MADERA_AIF1RX_LRCLK_INV 0x0004 +#define MADERA_AIF1RX_LRCLK_INV_MASK 0x0004 +#define MADERA_AIF1RX_LRCLK_INV_SHIFT 2 +#define MADERA_AIF1RX_LRCLK_INV_WIDTH 1 +#define MADERA_AIF1RX_LRCLK_FRC 0x0002 +#define MADERA_AIF1RX_LRCLK_FRC_MASK 0x0002 +#define MADERA_AIF1RX_LRCLK_FRC_SHIFT 1 +#define MADERA_AIF1RX_LRCLK_FRC_WIDTH 1 +#define MADERA_AIF1RX_LRCLK_MSTR 0x0001 +#define MADERA_AIF1RX_LRCLK_MSTR_MASK 0x0001 +#define MADERA_AIF1RX_LRCLK_MSTR_SHIFT 0 +#define MADERA_AIF1RX_LRCLK_MSTR_WIDTH 1 + +/* (0x0503) AIF1_Rate_Ctrl */ +#define MADERA_AIF1_RATE_MASK 0xF800 +#define MADERA_AIF1_RATE_SHIFT 11 +#define MADERA_AIF1_RATE_WIDTH 5 +#define MADERA_AIF1_TRI 0x0040 +#define MADERA_AIF1_TRI_MASK 0x0040 +#define MADERA_AIF1_TRI_SHIFT 6 +#define MADERA_AIF1_TRI_WIDTH 1 + +/* (0x0504) AIF1_Format */ +#define MADERA_AIF1_FMT_MASK 0x0007 +#define MADERA_AIF1_FMT_SHIFT 0 +#define MADERA_AIF1_FMT_WIDTH 3 + +/* (0x0506) AIF1_Rx_BCLK_Rate */ +#define MADERA_AIF1RX_BCPF_MASK 0x1FFF +#define MADERA_AIF1RX_BCPF_SHIFT 0 +#define MADERA_AIF1RX_BCPF_WIDTH 13 + +/* (0x0507) AIF1_Frame_Ctrl_1 */ +#define MADERA_AIF1TX_WL_MASK 0x3F00 +#define MADERA_AIF1TX_WL_SHIFT 8 +#define MADERA_AIF1TX_WL_WIDTH 6 +#define MADERA_AIF1TX_SLOT_LEN_MASK 0x00FF +#define MADERA_AIF1TX_SLOT_LEN_SHIFT 0 +#define MADERA_AIF1TX_SLOT_LEN_WIDTH 8 + +/* (0x0508) AIF1_Frame_Ctrl_2 */ +#define MADERA_AIF1RX_WL_MASK 0x3F00 +#define MADERA_AIF1RX_WL_SHIFT 8 +#define MADERA_AIF1RX_WL_WIDTH 6 +#define MADERA_AIF1RX_SLOT_LEN_MASK 0x00FF +#define MADERA_AIF1RX_SLOT_LEN_SHIFT 0 +#define MADERA_AIF1RX_SLOT_LEN_WIDTH 8 + +/* (0x0509) AIF1_Frame_Ctrl_3 */ +#define MADERA_AIF1TX1_SLOT_MASK 0x003F +#define MADERA_AIF1TX1_SLOT_SHIFT 0 +#define MADERA_AIF1TX1_SLOT_WIDTH 6 + +/* (0x0519) AIF1_Tx_Enables */ +#define MADERA_AIF1TX8_ENA 0x0080 +#define MADERA_AIF1TX8_ENA_MASK 0x0080 +#define MADERA_AIF1TX8_ENA_SHIFT 7 +#define MADERA_AIF1TX8_ENA_WIDTH 1 +#define MADERA_AIF1TX7_ENA 0x0040 +#define MADERA_AIF1TX7_ENA_MASK 0x0040 +#define MADERA_AIF1TX7_ENA_SHIFT 6 +#define MADERA_AIF1TX7_ENA_WIDTH 1 +#define MADERA_AIF1TX6_ENA 0x0020 +#define MADERA_AIF1TX6_ENA_MASK 0x0020 +#define MADERA_AIF1TX6_ENA_SHIFT 5 +#define MADERA_AIF1TX6_ENA_WIDTH 1 +#define MADERA_AIF1TX5_ENA 0x0010 +#define MADERA_AIF1TX5_ENA_MASK 0x0010 +#define MADERA_AIF1TX5_ENA_SHIFT 4 +#define MADERA_AIF1TX5_ENA_WIDTH 1 +#define MADERA_AIF1TX4_ENA 0x0008 +#define MADERA_AIF1TX4_ENA_MASK 0x0008 +#define MADERA_AIF1TX4_ENA_SHIFT 3 +#define MADERA_AIF1TX4_ENA_WIDTH 1 +#define MADERA_AIF1TX3_ENA 0x0004 +#define MADERA_AIF1TX3_ENA_MASK 0x0004 +#define MADERA_AIF1TX3_ENA_SHIFT 2 +#define MADERA_AIF1TX3_ENA_WIDTH 1 +#define MADERA_AIF1TX2_ENA 0x0002 +#define MADERA_AIF1TX2_ENA_MASK 0x0002 +#define MADERA_AIF1TX2_ENA_SHIFT 1 +#define MADERA_AIF1TX2_ENA_WIDTH 1 +#define MADERA_AIF1TX1_ENA 0x0001 +#define MADERA_AIF1TX1_ENA_MASK 0x0001 +#define MADERA_AIF1TX1_ENA_SHIFT 0 +#define MADERA_AIF1TX1_ENA_WIDTH 1 + +/* (0x051A) AIF1_Rx_Enables */ +#define MADERA_AIF1RX8_ENA 0x0080 +#define MADERA_AIF1RX8_ENA_MASK 0x0080 +#define MADERA_AIF1RX8_ENA_SHIFT 7 +#define MADERA_AIF1RX8_ENA_WIDTH 1 +#define MADERA_AIF1RX7_ENA 0x0040 +#define MADERA_AIF1RX7_ENA_MASK 0x0040 +#define MADERA_AIF1RX7_ENA_SHIFT 6 +#define MADERA_AIF1RX7_ENA_WIDTH 1 +#define MADERA_AIF1RX6_ENA 0x0020 +#define MADERA_AIF1RX6_ENA_MASK 0x0020 +#define MADERA_AIF1RX6_ENA_SHIFT 5 +#define MADERA_AIF1RX6_ENA_WIDTH 1 +#define MADERA_AIF1RX5_ENA 0x0010 +#define MADERA_AIF1RX5_ENA_MASK 0x0010 +#define MADERA_AIF1RX5_ENA_SHIFT 4 +#define MADERA_AIF1RX5_ENA_WIDTH 1 +#define MADERA_AIF1RX4_ENA 0x0008 +#define MADERA_AIF1RX4_ENA_MASK 0x0008 +#define MADERA_AIF1RX4_ENA_SHIFT 3 +#define MADERA_AIF1RX4_ENA_WIDTH 1 +#define MADERA_AIF1RX3_ENA 0x0004 +#define MADERA_AIF1RX3_ENA_MASK 0x0004 +#define MADERA_AIF1RX3_ENA_SHIFT 2 +#define MADERA_AIF1RX3_ENA_WIDTH 1 +#define MADERA_AIF1RX2_ENA 0x0002 +#define MADERA_AIF1RX2_ENA_MASK 0x0002 +#define MADERA_AIF1RX2_ENA_SHIFT 1 +#define MADERA_AIF1RX2_ENA_WIDTH 1 +#define MADERA_AIF1RX1_ENA 0x0001 +#define MADERA_AIF1RX1_ENA_MASK 0x0001 +#define MADERA_AIF1RX1_ENA_SHIFT 0 +#define MADERA_AIF1RX1_ENA_WIDTH 1 + +/* (0x0559) AIF2_Tx_Enables */ +#define MADERA_AIF2TX8_ENA 0x0080 +#define MADERA_AIF2TX8_ENA_MASK 0x0080 +#define MADERA_AIF2TX8_ENA_SHIFT 7 +#define MADERA_AIF2TX8_ENA_WIDTH 1 +#define MADERA_AIF2TX7_ENA 0x0040 +#define MADERA_AIF2TX7_ENA_MASK 0x0040 +#define MADERA_AIF2TX7_ENA_SHIFT 6 +#define MADERA_AIF2TX7_ENA_WIDTH 1 +#define MADERA_AIF2TX6_ENA 0x0020 +#define MADERA_AIF2TX6_ENA_MASK 0x0020 +#define MADERA_AIF2TX6_ENA_SHIFT 5 +#define MADERA_AIF2TX6_ENA_WIDTH 1 +#define MADERA_AIF2TX5_ENA 0x0010 +#define MADERA_AIF2TX5_ENA_MASK 0x0010 +#define MADERA_AIF2TX5_ENA_SHIFT 4 +#define MADERA_AIF2TX5_ENA_WIDTH 1 +#define MADERA_AIF2TX4_ENA 0x0008 +#define MADERA_AIF2TX4_ENA_MASK 0x0008 +#define MADERA_AIF2TX4_ENA_SHIFT 3 +#define MADERA_AIF2TX4_ENA_WIDTH 1 +#define MADERA_AIF2TX3_ENA 0x0004 +#define MADERA_AIF2TX3_ENA_MASK 0x0004 +#define MADERA_AIF2TX3_ENA_SHIFT 2 +#define MADERA_AIF2TX3_ENA_WIDTH 1 +#define MADERA_AIF2TX2_ENA 0x0002 +#define MADERA_AIF2TX2_ENA_MASK 0x0002 +#define MADERA_AIF2TX2_ENA_SHIFT 1 +#define MADERA_AIF2TX2_ENA_WIDTH 1 +#define MADERA_AIF2TX1_ENA 0x0001 +#define MADERA_AIF2TX1_ENA_MASK 0x0001 +#define MADERA_AIF2TX1_ENA_SHIFT 0 +#define MADERA_AIF2TX1_ENA_WIDTH 1 + +/* (0x055A) AIF2_Rx_Enables */ +#define MADERA_AIF2RX8_ENA 0x0080 +#define MADERA_AIF2RX8_ENA_MASK 0x0080 +#define MADERA_AIF2RX8_ENA_SHIFT 7 +#define MADERA_AIF2RX8_ENA_WIDTH 1 +#define MADERA_AIF2RX7_ENA 0x0040 +#define MADERA_AIF2RX7_ENA_MASK 0x0040 +#define MADERA_AIF2RX7_ENA_SHIFT 6 +#define MADERA_AIF2RX7_ENA_WIDTH 1 +#define MADERA_AIF2RX6_ENA 0x0020 +#define MADERA_AIF2RX6_ENA_MASK 0x0020 +#define MADERA_AIF2RX6_ENA_SHIFT 5 +#define MADERA_AIF2RX6_ENA_WIDTH 1 +#define MADERA_AIF2RX5_ENA 0x0010 +#define MADERA_AIF2RX5_ENA_MASK 0x0010 +#define MADERA_AIF2RX5_ENA_SHIFT 4 +#define MADERA_AIF2RX5_ENA_WIDTH 1 +#define MADERA_AIF2RX4_ENA 0x0008 +#define MADERA_AIF2RX4_ENA_MASK 0x0008 +#define MADERA_AIF2RX4_ENA_SHIFT 3 +#define MADERA_AIF2RX4_ENA_WIDTH 1 +#define MADERA_AIF2RX3_ENA 0x0004 +#define MADERA_AIF2RX3_ENA_MASK 0x0004 +#define MADERA_AIF2RX3_ENA_SHIFT 2 +#define MADERA_AIF2RX3_ENA_WIDTH 1 +#define MADERA_AIF2RX2_ENA 0x0002 +#define MADERA_AIF2RX2_ENA_MASK 0x0002 +#define MADERA_AIF2RX2_ENA_SHIFT 1 +#define MADERA_AIF2RX2_ENA_WIDTH 1 +#define MADERA_AIF2RX1_ENA 0x0001 +#define MADERA_AIF2RX1_ENA_MASK 0x0001 +#define MADERA_AIF2RX1_ENA_SHIFT 0 +#define MADERA_AIF2RX1_ENA_WIDTH 1 + +/* (0x0599) AIF3_Tx_Enables */ +#define MADERA_AIF3TX2_ENA 0x0002 +#define MADERA_AIF3TX2_ENA_MASK 0x0002 +#define MADERA_AIF3TX2_ENA_SHIFT 1 +#define MADERA_AIF3TX2_ENA_WIDTH 1 +#define MADERA_AIF3TX1_ENA 0x0001 +#define MADERA_AIF3TX1_ENA_MASK 0x0001 +#define MADERA_AIF3TX1_ENA_SHIFT 0 +#define MADERA_AIF3TX1_ENA_WIDTH 1 + +/* (0x059A) AIF3_Rx_Enables */ +#define MADERA_AIF3RX2_ENA 0x0002 +#define MADERA_AIF3RX2_ENA_MASK 0x0002 +#define MADERA_AIF3RX2_ENA_SHIFT 1 +#define MADERA_AIF3RX2_ENA_WIDTH 1 +#define MADERA_AIF3RX1_ENA 0x0001 +#define MADERA_AIF3RX1_ENA_MASK 0x0001 +#define MADERA_AIF3RX1_ENA_SHIFT 0 +#define MADERA_AIF3RX1_ENA_WIDTH 1 + +/* (0x05B9) AIF4_Tx_Enables */ +#define MADERA_AIF4TX2_ENA 0x0002 +#define MADERA_AIF4TX2_ENA_MASK 0x0002 +#define MADERA_AIF4TX2_ENA_SHIFT 1 +#define MADERA_AIF4TX2_ENA_WIDTH 1 +#define MADERA_AIF4TX1_ENA 0x0001 +#define MADERA_AIF4TX1_ENA_MASK 0x0001 +#define MADERA_AIF4TX1_ENA_SHIFT 0 +#define MADERA_AIF4TX1_ENA_WIDTH 1 + +/* (0x05BA) AIF4_Rx_Enables */ +#define MADERA_AIF4RX2_ENA 0x0002 +#define MADERA_AIF4RX2_ENA_MASK 0x0002 +#define MADERA_AIF4RX2_ENA_SHIFT 1 +#define MADERA_AIF4RX2_ENA_WIDTH 1 +#define MADERA_AIF4RX1_ENA 0x0001 +#define MADERA_AIF4RX1_ENA_MASK 0x0001 +#define MADERA_AIF4RX1_ENA_SHIFT 0 +#define MADERA_AIF4RX1_ENA_WIDTH 1 + +/* (0x05C2) SPD1_TX_Control */ +#define MADERA_SPD1_VAL2 0x2000 +#define MADERA_SPD1_VAL2_MASK 0x2000 +#define MADERA_SPD1_VAL2_SHIFT 13 +#define MADERA_SPD1_VAL2_WIDTH 1 +#define MADERA_SPD1_VAL1 0x1000 +#define MADERA_SPD1_VAL1_MASK 0x1000 +#define MADERA_SPD1_VAL1_SHIFT 12 +#define MADERA_SPD1_VAL1_WIDTH 1 +#define MADERA_SPD1_RATE_MASK 0x00F0 +#define MADERA_SPD1_RATE_SHIFT 4 +#define MADERA_SPD1_RATE_WIDTH 4 +#define MADERA_SPD1_ENA 0x0001 +#define MADERA_SPD1_ENA_MASK 0x0001 +#define MADERA_SPD1_ENA_SHIFT 0 +#define MADERA_SPD1_ENA_WIDTH 1 + +/* (0x05F5) SLIMbus_RX_Channel_Enable */ +#define MADERA_SLIMRX8_ENA 0x0080 +#define MADERA_SLIMRX8_ENA_MASK 0x0080 +#define MADERA_SLIMRX8_ENA_SHIFT 7 +#define MADERA_SLIMRX8_ENA_WIDTH 1 +#define MADERA_SLIMRX7_ENA 0x0040 +#define MADERA_SLIMRX7_ENA_MASK 0x0040 +#define MADERA_SLIMRX7_ENA_SHIFT 6 +#define MADERA_SLIMRX7_ENA_WIDTH 1 +#define MADERA_SLIMRX6_ENA 0x0020 +#define MADERA_SLIMRX6_ENA_MASK 0x0020 +#define MADERA_SLIMRX6_ENA_SHIFT 5 +#define MADERA_SLIMRX6_ENA_WIDTH 1 +#define MADERA_SLIMRX5_ENA 0x0010 +#define MADERA_SLIMRX5_ENA_MASK 0x0010 +#define MADERA_SLIMRX5_ENA_SHIFT 4 +#define MADERA_SLIMRX5_ENA_WIDTH 1 +#define MADERA_SLIMRX4_ENA 0x0008 +#define MADERA_SLIMRX4_ENA_MASK 0x0008 +#define MADERA_SLIMRX4_ENA_SHIFT 3 +#define MADERA_SLIMRX4_ENA_WIDTH 1 +#define MADERA_SLIMRX3_ENA 0x0004 +#define MADERA_SLIMRX3_ENA_MASK 0x0004 +#define MADERA_SLIMRX3_ENA_SHIFT 2 +#define MADERA_SLIMRX3_ENA_WIDTH 1 +#define MADERA_SLIMRX2_ENA 0x0002 +#define MADERA_SLIMRX2_ENA_MASK 0x0002 +#define MADERA_SLIMRX2_ENA_SHIFT 1 +#define MADERA_SLIMRX2_ENA_WIDTH 1 +#define MADERA_SLIMRX1_ENA 0x0001 +#define MADERA_SLIMRX1_ENA_MASK 0x0001 +#define MADERA_SLIMRX1_ENA_SHIFT 0 +#define MADERA_SLIMRX1_ENA_WIDTH 1 + +/* (0x05F6) SLIMbus_TX_Channel_Enable */ +#define MADERA_SLIMTX8_ENA 0x0080 +#define MADERA_SLIMTX8_ENA_MASK 0x0080 +#define MADERA_SLIMTX8_ENA_SHIFT 7 +#define MADERA_SLIMTX8_ENA_WIDTH 1 +#define MADERA_SLIMTX7_ENA 0x0040 +#define MADERA_SLIMTX7_ENA_MASK 0x0040 +#define MADERA_SLIMTX7_ENA_SHIFT 6 +#define MADERA_SLIMTX7_ENA_WIDTH 1 +#define MADERA_SLIMTX6_ENA 0x0020 +#define MADERA_SLIMTX6_ENA_MASK 0x0020 +#define MADERA_SLIMTX6_ENA_SHIFT 5 +#define MADERA_SLIMTX6_ENA_WIDTH 1 +#define MADERA_SLIMTX5_ENA 0x0010 +#define MADERA_SLIMTX5_ENA_MASK 0x0010 +#define MADERA_SLIMTX5_ENA_SHIFT 4 +#define MADERA_SLIMTX5_ENA_WIDTH 1 +#define MADERA_SLIMTX4_ENA 0x0008 +#define MADERA_SLIMTX4_ENA_MASK 0x0008 +#define MADERA_SLIMTX4_ENA_SHIFT 3 +#define MADERA_SLIMTX4_ENA_WIDTH 1 +#define MADERA_SLIMTX3_ENA 0x0004 +#define MADERA_SLIMTX3_ENA_MASK 0x0004 +#define MADERA_SLIMTX3_ENA_SHIFT 2 +#define MADERA_SLIMTX3_ENA_WIDTH 1 +#define MADERA_SLIMTX2_ENA 0x0002 +#define MADERA_SLIMTX2_ENA_MASK 0x0002 +#define MADERA_SLIMTX2_ENA_SHIFT 1 +#define MADERA_SLIMTX2_ENA_WIDTH 1 +#define MADERA_SLIMTX1_ENA 0x0001 +#define MADERA_SLIMTX1_ENA_MASK 0x0001 +#define MADERA_SLIMTX1_ENA_SHIFT 0 +#define MADERA_SLIMTX1_ENA_WIDTH 1 + +/* (0x0E10) EQ1_1 */ +#define MADERA_EQ1_B1_GAIN_MASK 0xF800 +#define MADERA_EQ1_B1_GAIN_SHIFT 11 +#define MADERA_EQ1_B1_GAIN_WIDTH 5 +#define MADERA_EQ1_B2_GAIN_MASK 0x07C0 +#define MADERA_EQ1_B2_GAIN_SHIFT 6 +#define MADERA_EQ1_B2_GAIN_WIDTH 5 +#define MADERA_EQ1_B3_GAIN_MASK 0x003E +#define MADERA_EQ1_B3_GAIN_SHIFT 1 +#define MADERA_EQ1_B3_GAIN_WIDTH 5 +#define MADERA_EQ1_ENA 0x0001 +#define MADERA_EQ1_ENA_MASK 0x0001 +#define MADERA_EQ1_ENA_SHIFT 0 +#define MADERA_EQ1_ENA_WIDTH 1 + +/* (0x0E11) EQ1_2 */ +#define MADERA_EQ1_B4_GAIN_MASK 0xF800 +#define MADERA_EQ1_B4_GAIN_SHIFT 11 +#define MADERA_EQ1_B4_GAIN_WIDTH 5 +#define MADERA_EQ1_B5_GAIN_MASK 0x07C0 +#define MADERA_EQ1_B5_GAIN_SHIFT 6 +#define MADERA_EQ1_B5_GAIN_WIDTH 5 +#define MADERA_EQ1_B1_MODE 0x0001 +#define MADERA_EQ1_B1_MODE_MASK 0x0001 +#define MADERA_EQ1_B1_MODE_SHIFT 0 +#define MADERA_EQ1_B1_MODE_WIDTH 1 + +/* (0x0E26) EQ2_1 */ +#define MADERA_EQ2_B1_GAIN_MASK 0xF800 +#define MADERA_EQ2_B1_GAIN_SHIFT 11 +#define MADERA_EQ2_B1_GAIN_WIDTH 5 +#define MADERA_EQ2_B2_GAIN_MASK 0x07C0 +#define MADERA_EQ2_B2_GAIN_SHIFT 6 +#define MADERA_EQ2_B2_GAIN_WIDTH 5 +#define MADERA_EQ2_B3_GAIN_MASK 0x003E +#define MADERA_EQ2_B3_GAIN_SHIFT 1 +#define MADERA_EQ2_B3_GAIN_WIDTH 5 +#define MADERA_EQ2_ENA 0x0001 +#define MADERA_EQ2_ENA_MASK 0x0001 +#define MADERA_EQ2_ENA_SHIFT 0 +#define MADERA_EQ2_ENA_WIDTH 1 + +/* (0x0E27) EQ2_2 */ +#define MADERA_EQ2_B4_GAIN_MASK 0xF800 +#define MADERA_EQ2_B4_GAIN_SHIFT 11 +#define MADERA_EQ2_B4_GAIN_WIDTH 5 +#define MADERA_EQ2_B5_GAIN_MASK 0x07C0 +#define MADERA_EQ2_B5_GAIN_SHIFT 6 +#define MADERA_EQ2_B5_GAIN_WIDTH 5 +#define MADERA_EQ2_B1_MODE 0x0001 +#define MADERA_EQ2_B1_MODE_MASK 0x0001 +#define MADERA_EQ2_B1_MODE_SHIFT 0 +#define MADERA_EQ2_B1_MODE_WIDTH 1 + +/* (0x0E3C) EQ3_1 */ +#define MADERA_EQ3_B1_GAIN_MASK 0xF800 +#define MADERA_EQ3_B1_GAIN_SHIFT 11 +#define MADERA_EQ3_B1_GAIN_WIDTH 5 +#define MADERA_EQ3_B2_GAIN_MASK 0x07C0 +#define MADERA_EQ3_B2_GAIN_SHIFT 6 +#define MADERA_EQ3_B2_GAIN_WIDTH 5 +#define MADERA_EQ3_B3_GAIN_MASK 0x003E +#define MADERA_EQ3_B3_GAIN_SHIFT 1 +#define MADERA_EQ3_B3_GAIN_WIDTH 5 +#define MADERA_EQ3_ENA 0x0001 +#define MADERA_EQ3_ENA_MASK 0x0001 +#define MADERA_EQ3_ENA_SHIFT 0 +#define MADERA_EQ3_ENA_WIDTH 1 + +/* (0x0E3D) EQ3_2 */ +#define MADERA_EQ3_B4_GAIN_MASK 0xF800 +#define MADERA_EQ3_B4_GAIN_SHIFT 11 +#define MADERA_EQ3_B4_GAIN_WIDTH 5 +#define MADERA_EQ3_B5_GAIN_MASK 0x07C0 +#define MADERA_EQ3_B5_GAIN_SHIFT 6 +#define MADERA_EQ3_B5_GAIN_WIDTH 5 +#define MADERA_EQ3_B1_MODE 0x0001 +#define MADERA_EQ3_B1_MODE_MASK 0x0001 +#define MADERA_EQ3_B1_MODE_SHIFT 0 +#define MADERA_EQ3_B1_MODE_WIDTH 1 + +/* (0x0E52) EQ4_1 */ +#define MADERA_EQ4_B1_GAIN_MASK 0xF800 +#define MADERA_EQ4_B1_GAIN_SHIFT 11 +#define MADERA_EQ4_B1_GAIN_WIDTH 5 +#define MADERA_EQ4_B2_GAIN_MASK 0x07C0 +#define MADERA_EQ4_B2_GAIN_SHIFT 6 +#define MADERA_EQ4_B2_GAIN_WIDTH 5 +#define MADERA_EQ4_B3_GAIN_MASK 0x003E +#define MADERA_EQ4_B3_GAIN_SHIFT 1 +#define MADERA_EQ4_B3_GAIN_WIDTH 5 +#define MADERA_EQ4_ENA 0x0001 +#define MADERA_EQ4_ENA_MASK 0x0001 +#define MADERA_EQ4_ENA_SHIFT 0 +#define MADERA_EQ4_ENA_WIDTH 1 + +/* (0x0E53) EQ4_2 */ +#define MADERA_EQ4_B4_GAIN_MASK 0xF800 +#define MADERA_EQ4_B4_GAIN_SHIFT 11 +#define MADERA_EQ4_B4_GAIN_WIDTH 5 +#define MADERA_EQ4_B5_GAIN_MASK 0x07C0 +#define MADERA_EQ4_B5_GAIN_SHIFT 6 +#define MADERA_EQ4_B5_GAIN_WIDTH 5 +#define MADERA_EQ4_B1_MODE 0x0001 +#define MADERA_EQ4_B1_MODE_MASK 0x0001 +#define MADERA_EQ4_B1_MODE_SHIFT 0 +#define MADERA_EQ4_B1_MODE_WIDTH 1 + +/* (0x0E80) DRC1_ctrl1 */ +#define MADERA_DRC1L_ENA 0x0002 +#define MADERA_DRC1L_ENA_MASK 0x0002 +#define MADERA_DRC1L_ENA_SHIFT 1 +#define MADERA_DRC1L_ENA_WIDTH 1 +#define MADERA_DRC1R_ENA 0x0001 +#define MADERA_DRC1R_ENA_MASK 0x0001 +#define MADERA_DRC1R_ENA_SHIFT 0 +#define MADERA_DRC1R_ENA_WIDTH 1 + +/* (0x0E88) DRC2_ctrl1 */ +#define MADERA_DRC2L_ENA 0x0002 +#define MADERA_DRC2L_ENA_MASK 0x0002 +#define MADERA_DRC2L_ENA_SHIFT 1 +#define MADERA_DRC2L_ENA_WIDTH 1 +#define MADERA_DRC2R_ENA 0x0001 +#define MADERA_DRC2R_ENA_MASK 0x0001 +#define MADERA_DRC2R_ENA_SHIFT 0 +#define MADERA_DRC2R_ENA_WIDTH 1 + +/* (0x0EC0) HPLPF1_1 */ +#define MADERA_LHPF1_MODE 0x0002 +#define MADERA_LHPF1_MODE_MASK 0x0002 +#define MADERA_LHPF1_MODE_SHIFT 1 +#define MADERA_LHPF1_MODE_WIDTH 1 +#define MADERA_LHPF1_ENA 0x0001 +#define MADERA_LHPF1_ENA_MASK 0x0001 +#define MADERA_LHPF1_ENA_SHIFT 0 +#define MADERA_LHPF1_ENA_WIDTH 1 + +/* (0x0EC1) HPLPF1_2 */ +#define MADERA_LHPF1_COEFF_MASK 0xFFFF +#define MADERA_LHPF1_COEFF_SHIFT 0 +#define MADERA_LHPF1_COEFF_WIDTH 16 + +/* (0x0EC4) HPLPF2_1 */ +#define MADERA_LHPF2_MODE 0x0002 +#define MADERA_LHPF2_MODE_MASK 0x0002 +#define MADERA_LHPF2_MODE_SHIFT 1 +#define MADERA_LHPF2_MODE_WIDTH 1 +#define MADERA_LHPF2_ENA 0x0001 +#define MADERA_LHPF2_ENA_MASK 0x0001 +#define MADERA_LHPF2_ENA_SHIFT 0 +#define MADERA_LHPF2_ENA_WIDTH 1 + +/* (0x0EC5) HPLPF2_2 */ +#define MADERA_LHPF2_COEFF_MASK 0xFFFF +#define MADERA_LHPF2_COEFF_SHIFT 0 +#define MADERA_LHPF2_COEFF_WIDTH 16 + +/* (0x0EC8) HPLPF3_1 */ +#define MADERA_LHPF3_MODE 0x0002 +#define MADERA_LHPF3_MODE_MASK 0x0002 +#define MADERA_LHPF3_MODE_SHIFT 1 +#define MADERA_LHPF3_MODE_WIDTH 1 +#define MADERA_LHPF3_ENA 0x0001 +#define MADERA_LHPF3_ENA_MASK 0x0001 +#define MADERA_LHPF3_ENA_SHIFT 0 +#define MADERA_LHPF3_ENA_WIDTH 1 + +/* (0x0EC9) HPLPF3_2 */ +#define MADERA_LHPF3_COEFF_MASK 0xFFFF +#define MADERA_LHPF3_COEFF_SHIFT 0 +#define MADERA_LHPF3_COEFF_WIDTH 16 + +/* (0x0ECC) HPLPF4_1 */ +#define MADERA_LHPF4_MODE 0x0002 +#define MADERA_LHPF4_MODE_MASK 0x0002 +#define MADERA_LHPF4_MODE_SHIFT 1 +#define MADERA_LHPF4_MODE_WIDTH 1 +#define MADERA_LHPF4_ENA 0x0001 +#define MADERA_LHPF4_ENA_MASK 0x0001 +#define MADERA_LHPF4_ENA_SHIFT 0 +#define MADERA_LHPF4_ENA_WIDTH 1 + +/* (0x0ECD) HPLPF4_2 */ +#define MADERA_LHPF4_COEFF_MASK 0xFFFF +#define MADERA_LHPF4_COEFF_SHIFT 0 +#define MADERA_LHPF4_COEFF_WIDTH 16 + +/* (0x0ED0) ASRC2_ENABLE */ +#define MADERA_ASRC2_IN2L_ENA 0x0008 +#define MADERA_ASRC2_IN2L_ENA_MASK 0x0008 +#define MADERA_ASRC2_IN2L_ENA_SHIFT 3 +#define MADERA_ASRC2_IN2L_ENA_WIDTH 1 +#define MADERA_ASRC2_IN2R_ENA 0x0004 +#define MADERA_ASRC2_IN2R_ENA_MASK 0x0004 +#define MADERA_ASRC2_IN2R_ENA_SHIFT 2 +#define MADERA_ASRC2_IN2R_ENA_WIDTH 1 +#define MADERA_ASRC2_IN1L_ENA 0x0002 +#define MADERA_ASRC2_IN1L_ENA_MASK 0x0002 +#define MADERA_ASRC2_IN1L_ENA_SHIFT 1 +#define MADERA_ASRC2_IN1L_ENA_WIDTH 1 +#define MADERA_ASRC2_IN1R_ENA 0x0001 +#define MADERA_ASRC2_IN1R_ENA_MASK 0x0001 +#define MADERA_ASRC2_IN1R_ENA_SHIFT 0 +#define MADERA_ASRC2_IN1R_ENA_WIDTH 1 + +/* (0x0ED2) ASRC2_RATE1 */ +#define MADERA_ASRC2_RATE1_MASK 0xF800 +#define MADERA_ASRC2_RATE1_SHIFT 11 +#define MADERA_ASRC2_RATE1_WIDTH 5 + +/* (0x0ED3) ASRC2_RATE2 */ +#define MADERA_ASRC2_RATE2_MASK 0xF800 +#define MADERA_ASRC2_RATE2_SHIFT 11 +#define MADERA_ASRC2_RATE2_WIDTH 5 + +/* (0x0EE0) ASRC1_ENABLE */ +#define MADERA_ASRC1_IN2L_ENA 0x0008 +#define MADERA_ASRC1_IN2L_ENA_MASK 0x0008 +#define MADERA_ASRC1_IN2L_ENA_SHIFT 3 +#define MADERA_ASRC1_IN2L_ENA_WIDTH 1 +#define MADERA_ASRC1_IN2R_ENA 0x0004 +#define MADERA_ASRC1_IN2R_ENA_MASK 0x0004 +#define MADERA_ASRC1_IN2R_ENA_SHIFT 2 +#define MADERA_ASRC1_IN2R_ENA_WIDTH 1 +#define MADERA_ASRC1_IN1L_ENA 0x0002 +#define MADERA_ASRC1_IN1L_ENA_MASK 0x0002 +#define MADERA_ASRC1_IN1L_ENA_SHIFT 1 +#define MADERA_ASRC1_IN1L_ENA_WIDTH 1 +#define MADERA_ASRC1_IN1R_ENA 0x0001 +#define MADERA_ASRC1_IN1R_ENA_MASK 0x0001 +#define MADERA_ASRC1_IN1R_ENA_SHIFT 0 +#define MADERA_ASRC1_IN1R_ENA_WIDTH 1 + +/* (0x0EE2) ASRC1_RATE1 */ +#define MADERA_ASRC1_RATE1_MASK 0xF800 +#define MADERA_ASRC1_RATE1_SHIFT 11 +#define MADERA_ASRC1_RATE1_WIDTH 5 + +/* (0x0EE3) ASRC1_RATE2 */ +#define MADERA_ASRC1_RATE2_MASK 0xF800 +#define MADERA_ASRC1_RATE2_SHIFT 11 +#define MADERA_ASRC1_RATE2_WIDTH 5 + +/* (0x0EF0) - ISRC1 CTRL 1 */ +#define MADERA_ISRC1_FSH_MASK 0xF800 +#define MADERA_ISRC1_FSH_SHIFT 11 +#define MADERA_ISRC1_FSH_WIDTH 5 +#define MADERA_ISRC1_CLK_SEL_MASK 0x0700 +#define MADERA_ISRC1_CLK_SEL_SHIFT 8 +#define MADERA_ISRC1_CLK_SEL_WIDTH 3 + +/* (0x0EF1) ISRC1_CTRL_2 */ +#define MADERA_ISRC1_FSL_MASK 0xF800 +#define MADERA_ISRC1_FSL_SHIFT 11 +#define MADERA_ISRC1_FSL_WIDTH 5 + +/* (0x0EF2) ISRC1_CTRL_3 */ +#define MADERA_ISRC1_INT1_ENA 0x8000 +#define MADERA_ISRC1_INT1_ENA_MASK 0x8000 +#define MADERA_ISRC1_INT1_ENA_SHIFT 15 +#define MADERA_ISRC1_INT1_ENA_WIDTH 1 +#define MADERA_ISRC1_INT2_ENA 0x4000 +#define MADERA_ISRC1_INT2_ENA_MASK 0x4000 +#define MADERA_ISRC1_INT2_ENA_SHIFT 14 +#define MADERA_ISRC1_INT2_ENA_WIDTH 1 +#define MADERA_ISRC1_INT3_ENA 0x2000 +#define MADERA_ISRC1_INT3_ENA_MASK 0x2000 +#define MADERA_ISRC1_INT3_ENA_SHIFT 13 +#define MADERA_ISRC1_INT3_ENA_WIDTH 1 +#define MADERA_ISRC1_INT4_ENA 0x1000 +#define MADERA_ISRC1_INT4_ENA_MASK 0x1000 +#define MADERA_ISRC1_INT4_ENA_SHIFT 12 +#define MADERA_ISRC1_INT4_ENA_WIDTH 1 +#define MADERA_ISRC1_DEC1_ENA 0x0200 +#define MADERA_ISRC1_DEC1_ENA_MASK 0x0200 +#define MADERA_ISRC1_DEC1_ENA_SHIFT 9 +#define MADERA_ISRC1_DEC1_ENA_WIDTH 1 +#define MADERA_ISRC1_DEC2_ENA 0x0100 +#define MADERA_ISRC1_DEC2_ENA_MASK 0x0100 +#define MADERA_ISRC1_DEC2_ENA_SHIFT 8 +#define MADERA_ISRC1_DEC2_ENA_WIDTH 1 +#define MADERA_ISRC1_DEC3_ENA 0x0080 +#define MADERA_ISRC1_DEC3_ENA_MASK 0x0080 +#define MADERA_ISRC1_DEC3_ENA_SHIFT 7 +#define MADERA_ISRC1_DEC3_ENA_WIDTH 1 +#define MADERA_ISRC1_DEC4_ENA 0x0040 +#define MADERA_ISRC1_DEC4_ENA_MASK 0x0040 +#define MADERA_ISRC1_DEC4_ENA_SHIFT 6 +#define MADERA_ISRC1_DEC4_ENA_WIDTH 1 +#define MADERA_ISRC1_NOTCH_ENA 0x0001 +#define MADERA_ISRC1_NOTCH_ENA_MASK 0x0001 +#define MADERA_ISRC1_NOTCH_ENA_SHIFT 0 +#define MADERA_ISRC1_NOTCH_ENA_WIDTH 1 + +/* (0x0EF3) ISRC2_CTRL_1 */ +#define MADERA_ISRC2_FSH_MASK 0xF800 +#define MADERA_ISRC2_FSH_SHIFT 11 +#define MADERA_ISRC2_FSH_WIDTH 5 +#define MADERA_ISRC2_CLK_SEL_MASK 0x0700 +#define MADERA_ISRC2_CLK_SEL_SHIFT 8 +#define MADERA_ISRC2_CLK_SEL_WIDTH 3 + +/* (0x0EF4) ISRC2_CTRL_2 */ +#define MADERA_ISRC2_FSL_MASK 0xF800 +#define MADERA_ISRC2_FSL_SHIFT 11 +#define MADERA_ISRC2_FSL_WIDTH 5 + +/* (0x0EF5) ISRC2_CTRL_3 */ +#define MADERA_ISRC2_INT1_ENA 0x8000 +#define MADERA_ISRC2_INT1_ENA_MASK 0x8000 +#define MADERA_ISRC2_INT1_ENA_SHIFT 15 +#define MADERA_ISRC2_INT1_ENA_WIDTH 1 +#define MADERA_ISRC2_INT2_ENA 0x4000 +#define MADERA_ISRC2_INT2_ENA_MASK 0x4000 +#define MADERA_ISRC2_INT2_ENA_SHIFT 14 +#define MADERA_ISRC2_INT2_ENA_WIDTH 1 +#define MADERA_ISRC2_INT3_ENA 0x2000 +#define MADERA_ISRC2_INT3_ENA_MASK 0x2000 +#define MADERA_ISRC2_INT3_ENA_SHIFT 13 +#define MADERA_ISRC2_INT3_ENA_WIDTH 1 +#define MADERA_ISRC2_INT4_ENA 0x1000 +#define MADERA_ISRC2_INT4_ENA_MASK 0x1000 +#define MADERA_ISRC2_INT4_ENA_SHIFT 12 +#define MADERA_ISRC2_INT4_ENA_WIDTH 1 +#define MADERA_ISRC2_DEC1_ENA 0x0200 +#define MADERA_ISRC2_DEC1_ENA_MASK 0x0200 +#define MADERA_ISRC2_DEC1_ENA_SHIFT 9 +#define MADERA_ISRC2_DEC1_ENA_WIDTH 1 +#define MADERA_ISRC2_DEC2_ENA 0x0100 +#define MADERA_ISRC2_DEC2_ENA_MASK 0x0100 +#define MADERA_ISRC2_DEC2_ENA_SHIFT 8 +#define MADERA_ISRC2_DEC2_ENA_WIDTH 1 +#define MADERA_ISRC2_DEC3_ENA 0x0080 +#define MADERA_ISRC2_DEC3_ENA_MASK 0x0080 +#define MADERA_ISRC2_DEC3_ENA_SHIFT 7 +#define MADERA_ISRC2_DEC3_ENA_WIDTH 1 +#define MADERA_ISRC2_DEC4_ENA 0x0040 +#define MADERA_ISRC2_DEC4_ENA_MASK 0x0040 +#define MADERA_ISRC2_DEC4_ENA_SHIFT 6 +#define MADERA_ISRC2_DEC4_ENA_WIDTH 1 +#define MADERA_ISRC2_NOTCH_ENA 0x0001 +#define MADERA_ISRC2_NOTCH_ENA_MASK 0x0001 +#define MADERA_ISRC2_NOTCH_ENA_SHIFT 0 +#define MADERA_ISRC2_NOTCH_ENA_WIDTH 1 + +/* (0x0EF6) ISRC3_CTRL_1 */ +#define MADERA_ISRC3_FSH_MASK 0xF800 +#define MADERA_ISRC3_FSH_SHIFT 11 +#define MADERA_ISRC3_FSH_WIDTH 5 +#define MADERA_ISRC3_CLK_SEL_MASK 0x0700 +#define MADERA_ISRC3_CLK_SEL_SHIFT 8 +#define MADERA_ISRC3_CLK_SEL_WIDTH 3 + +/* (0x0EF7) ISRC3_CTRL_2 */ +#define MADERA_ISRC3_FSL_MASK 0xF800 +#define MADERA_ISRC3_FSL_SHIFT 11 +#define MADERA_ISRC3_FSL_WIDTH 5 + +/* (0x0EF8) ISRC3_CTRL_3 */ +#define MADERA_ISRC3_INT1_ENA 0x8000 +#define MADERA_ISRC3_INT1_ENA_MASK 0x8000 +#define MADERA_ISRC3_INT1_ENA_SHIFT 15 +#define MADERA_ISRC3_INT1_ENA_WIDTH 1 +#define MADERA_ISRC3_INT2_ENA 0x4000 +#define MADERA_ISRC3_INT2_ENA_MASK 0x4000 +#define MADERA_ISRC3_INT2_ENA_SHIFT 14 +#define MADERA_ISRC3_INT2_ENA_WIDTH 1 +#define MADERA_ISRC3_INT3_ENA 0x2000 +#define MADERA_ISRC3_INT3_ENA_MASK 0x2000 +#define MADERA_ISRC3_INT3_ENA_SHIFT 13 +#define MADERA_ISRC3_INT3_ENA_WIDTH 1 +#define MADERA_ISRC3_INT4_ENA 0x1000 +#define MADERA_ISRC3_INT4_ENA_MASK 0x1000 +#define MADERA_ISRC3_INT4_ENA_SHIFT 12 +#define MADERA_ISRC3_INT4_ENA_WIDTH 1 +#define MADERA_ISRC3_DEC1_ENA 0x0200 +#define MADERA_ISRC3_DEC1_ENA_MASK 0x0200 +#define MADERA_ISRC3_DEC1_ENA_SHIFT 9 +#define MADERA_ISRC3_DEC1_ENA_WIDTH 1 +#define MADERA_ISRC3_DEC2_ENA 0x0100 +#define MADERA_ISRC3_DEC2_ENA_MASK 0x0100 +#define MADERA_ISRC3_DEC2_ENA_SHIFT 8 +#define MADERA_ISRC3_DEC2_ENA_WIDTH 1 +#define MADERA_ISRC3_DEC3_ENA 0x0080 +#define MADERA_ISRC3_DEC3_ENA_MASK 0x0080 +#define MADERA_ISRC3_DEC3_ENA_SHIFT 7 +#define MADERA_ISRC3_DEC3_ENA_WIDTH 1 +#define MADERA_ISRC3_DEC4_ENA 0x0040 +#define MADERA_ISRC3_DEC4_ENA_MASK 0x0040 +#define MADERA_ISRC3_DEC4_ENA_SHIFT 6 +#define MADERA_ISRC3_DEC4_ENA_WIDTH 1 +#define MADERA_ISRC3_NOTCH_ENA 0x0001 +#define MADERA_ISRC3_NOTCH_ENA_MASK 0x0001 +#define MADERA_ISRC3_NOTCH_ENA_SHIFT 0 +#define MADERA_ISRC3_NOTCH_ENA_WIDTH 1 + +/* (0x0EF9) ISRC4_CTRL_1 */ +#define MADERA_ISRC4_FSH_MASK 0xF800 +#define MADERA_ISRC4_FSH_SHIFT 11 +#define MADERA_ISRC4_FSH_WIDTH 5 +#define MADERA_ISRC4_CLK_SEL_MASK 0x0700 +#define MADERA_ISRC4_CLK_SEL_SHIFT 8 +#define MADERA_ISRC4_CLK_SEL_WIDTH 3 + +/* (0x0EFA) ISRC4_CTRL_2 */ +#define MADERA_ISRC4_FSL_MASK 0xF800 +#define MADERA_ISRC4_FSL_SHIFT 11 +#define MADERA_ISRC4_FSL_WIDTH 5 + +/* (0x0EFB) ISRC4_CTRL_3 */ +#define MADERA_ISRC4_INT1_ENA 0x8000 +#define MADERA_ISRC4_INT1_ENA_MASK 0x8000 +#define MADERA_ISRC4_INT1_ENA_SHIFT 15 +#define MADERA_ISRC4_INT1_ENA_WIDTH 1 +#define MADERA_ISRC4_INT2_ENA 0x4000 +#define MADERA_ISRC4_INT2_ENA_MASK 0x4000 +#define MADERA_ISRC4_INT2_ENA_SHIFT 14 +#define MADERA_ISRC4_INT2_ENA_WIDTH 1 +#define MADERA_ISRC4_INT3_ENA 0x2000 +#define MADERA_ISRC4_INT3_ENA_MASK 0x2000 +#define MADERA_ISRC4_INT3_ENA_SHIFT 13 +#define MADERA_ISRC4_INT3_ENA_WIDTH 1 +#define MADERA_ISRC4_INT4_ENA 0x1000 +#define MADERA_ISRC4_INT4_ENA_MASK 0x1000 +#define MADERA_ISRC4_INT4_ENA_SHIFT 12 +#define MADERA_ISRC4_INT4_ENA_WIDTH 1 +#define MADERA_ISRC4_DEC1_ENA 0x0200 +#define MADERA_ISRC4_DEC1_ENA_MASK 0x0200 +#define MADERA_ISRC4_DEC1_ENA_SHIFT 9 +#define MADERA_ISRC4_DEC1_ENA_WIDTH 1 +#define MADERA_ISRC4_DEC2_ENA 0x0100 +#define MADERA_ISRC4_DEC2_ENA_MASK 0x0100 +#define MADERA_ISRC4_DEC2_ENA_SHIFT 8 +#define MADERA_ISRC4_DEC2_ENA_WIDTH 1 +#define MADERA_ISRC4_DEC3_ENA 0x0080 +#define MADERA_ISRC4_DEC3_ENA_MASK 0x0080 +#define MADERA_ISRC4_DEC3_ENA_SHIFT 7 +#define MADERA_ISRC4_DEC3_ENA_WIDTH 1 +#define MADERA_ISRC4_DEC4_ENA 0x0040 +#define MADERA_ISRC4_DEC4_ENA_MASK 0x0040 +#define MADERA_ISRC4_DEC4_ENA_SHIFT 6 +#define MADERA_ISRC4_DEC4_ENA_WIDTH 1 +#define MADERA_ISRC4_NOTCH_ENA 0x0001 +#define MADERA_ISRC4_NOTCH_ENA_MASK 0x0001 +#define MADERA_ISRC4_NOTCH_ENA_SHIFT 0 +#define MADERA_ISRC4_NOTCH_ENA_WIDTH 1 + +/* (0x0F00) Clock_Control */ +#define MADERA_EXT_NG_SEL_CLR 0x0080 +#define MADERA_EXT_NG_SEL_CLR_MASK 0x0080 +#define MADERA_EXT_NG_SEL_CLR_SHIFT 7 +#define MADERA_EXT_NG_SEL_CLR_WIDTH 1 +#define MADERA_EXT_NG_SEL_SET 0x0040 +#define MADERA_EXT_NG_SEL_SET_MASK 0x0040 +#define MADERA_EXT_NG_SEL_SET_SHIFT 6 +#define MADERA_EXT_NG_SEL_SET_WIDTH 1 +#define MADERA_CLK_R_ENA_CLR 0x0020 +#define MADERA_CLK_R_ENA_CLR_MASK 0x0020 +#define MADERA_CLK_R_ENA_CLR_SHIFT 5 +#define MADERA_CLK_R_ENA_CLR_WIDTH 1 +#define MADERA_CLK_R_ENA_SET 0x0010 +#define MADERA_CLK_R_ENA_SET_MASK 0x0010 +#define MADERA_CLK_R_ENA_SET_SHIFT 4 +#define MADERA_CLK_R_ENA_SET_WIDTH 1 +#define MADERA_CLK_NG_ENA_CLR 0x0008 +#define MADERA_CLK_NG_ENA_CLR_MASK 0x0008 +#define MADERA_CLK_NG_ENA_CLR_SHIFT 3 +#define MADERA_CLK_NG_ENA_CLR_WIDTH 1 +#define MADERA_CLK_NG_ENA_SET 0x0004 +#define MADERA_CLK_NG_ENA_SET_MASK 0x0004 +#define MADERA_CLK_NG_ENA_SET_SHIFT 2 +#define MADERA_CLK_NG_ENA_SET_WIDTH 1 +#define MADERA_CLK_L_ENA_CLR 0x0002 +#define MADERA_CLK_L_ENA_CLR_MASK 0x0002 +#define MADERA_CLK_L_ENA_CLR_SHIFT 1 +#define MADERA_CLK_L_ENA_CLR_WIDTH 1 +#define MADERA_CLK_L_ENA_SET 0x0001 +#define MADERA_CLK_L_ENA_SET_MASK 0x0001 +#define MADERA_CLK_L_ENA_SET_SHIFT 0 +#define MADERA_CLK_L_ENA_SET_WIDTH 1 + +/* (0x0F01) ANC_SRC */ +#define MADERA_IN_RXANCR_SEL_MASK 0x0070 +#define MADERA_IN_RXANCR_SEL_SHIFT 4 +#define MADERA_IN_RXANCR_SEL_WIDTH 3 +#define MADERA_IN_RXANCL_SEL_MASK 0x0007 +#define MADERA_IN_RXANCL_SEL_SHIFT 0 +#define MADERA_IN_RXANCL_SEL_WIDTH 3 + +/* (0x0F17) FCL_ADC_reformatter_control */ +#define MADERA_FCL_MIC_MODE_SEL 0x000C +#define MADERA_FCL_MIC_MODE_SEL_SHIFT 2 +#define MADERA_FCL_MIC_MODE_SEL_WIDTH 2 + +/* (0x0F73) FCR_ADC_reformatter_control */ +#define MADERA_FCR_MIC_MODE_SEL 0x000C +#define MADERA_FCR_MIC_MODE_SEL_SHIFT 2 +#define MADERA_FCR_MIC_MODE_SEL_WIDTH 2 + +/* (0x1480) DFC1_CTRL_W0 */ +#define MADERA_DFC1_RATE_MASK 0x007C +#define MADERA_DFC1_RATE_SHIFT 2 +#define MADERA_DFC1_RATE_WIDTH 5 +#define MADERA_DFC1_DITH_ENA 0x0002 +#define MADERA_DFC1_DITH_ENA_MASK 0x0002 +#define MADERA_DFC1_DITH_ENA_SHIFT 1 +#define MADERA_DFC1_DITH_ENA_WIDTH 1 +#define MADERA_DFC1_ENA 0x0001 +#define MADERA_DFC1_ENA_MASK 0x0001 +#define MADERA_DFC1_ENA_SHIFT 0 +#define MADERA_DFC1_ENA_WIDTH 1 + +/* (0x1482) DFC1_RX_W0 */ +#define MADERA_DFC1_RX_DATA_WIDTH_MASK 0x1F00 +#define MADERA_DFC1_RX_DATA_WIDTH_SHIFT 8 +#define MADERA_DFC1_RX_DATA_WIDTH_WIDTH 5 + +#define MADERA_DFC1_RX_DATA_TYPE_MASK 0x0007 +#define MADERA_DFC1_RX_DATA_TYPE_SHIFT 0 +#define MADERA_DFC1_RX_DATA_TYPE_WIDTH 3 + +/* (0x1484) DFC1_TX_W0 */ +#define MADERA_DFC1_TX_DATA_WIDTH_MASK 0x1F00 +#define MADERA_DFC1_TX_DATA_WIDTH_SHIFT 8 +#define MADERA_DFC1_TX_DATA_WIDTH_WIDTH 5 + +#define MADERA_DFC1_TX_DATA_TYPE_MASK 0x0007 +#define MADERA_DFC1_TX_DATA_TYPE_SHIFT 0 +#define MADERA_DFC1_TX_DATA_TYPE_WIDTH 3 + +/* (0x1600) ADSP2_IRQ0 */ +#define MADERA_DSP_IRQ2 0x0002 +#define MADERA_DSP_IRQ1 0x0001 + +/* (0x1601) ADSP2_IRQ1 */ +#define MADERA_DSP_IRQ4 0x0002 +#define MADERA_DSP_IRQ3 0x0001 + +/* (0x1602) ADSP2_IRQ2 */ +#define MADERA_DSP_IRQ6 0x0002 +#define MADERA_DSP_IRQ5 0x0001 + +/* (0x1603) ADSP2_IRQ3 */ +#define MADERA_DSP_IRQ8 0x0002 +#define MADERA_DSP_IRQ7 0x0001 + +/* (0x1604) ADSP2_IRQ4 */ +#define MADERA_DSP_IRQ10 0x0002 +#define MADERA_DSP_IRQ9 0x0001 + +/* (0x1605) ADSP2_IRQ5 */ +#define MADERA_DSP_IRQ12 0x0002 +#define MADERA_DSP_IRQ11 0x0001 + +/* (0x1606) ADSP2_IRQ6 */ +#define MADERA_DSP_IRQ14 0x0002 +#define MADERA_DSP_IRQ13 0x0001 + +/* (0x1607) ADSP2_IRQ7 */ +#define MADERA_DSP_IRQ16 0x0002 +#define MADERA_DSP_IRQ15 0x0001 + +/* (0x1700) GPIO1_CTRL_1 */ +#define MADERA_GP1_LVL 0x8000 +#define MADERA_GP1_LVL_MASK 0x8000 +#define MADERA_GP1_LVL_SHIFT 15 +#define MADERA_GP1_LVL_WIDTH 1 +#define MADERA_GP1_OP_CFG 0x4000 +#define MADERA_GP1_OP_CFG_MASK 0x4000 +#define MADERA_GP1_OP_CFG_SHIFT 14 +#define MADERA_GP1_OP_CFG_WIDTH 1 +#define MADERA_GP1_DB 0x2000 +#define MADERA_GP1_DB_MASK 0x2000 +#define MADERA_GP1_DB_SHIFT 13 +#define MADERA_GP1_DB_WIDTH 1 +#define MADERA_GP1_POL 0x1000 +#define MADERA_GP1_POL_MASK 0x1000 +#define MADERA_GP1_POL_SHIFT 12 +#define MADERA_GP1_POL_WIDTH 1 +#define MADERA_GP1_IP_CFG 0x0800 +#define MADERA_GP1_IP_CFG_MASK 0x0800 +#define MADERA_GP1_IP_CFG_SHIFT 11 +#define MADERA_GP1_IP_CFG_WIDTH 1 +#define MADERA_GP1_FN_MASK 0x03FF +#define MADERA_GP1_FN_SHIFT 0 +#define MADERA_GP1_FN_WIDTH 10 + +/* (0x1701) GPIO1_CTRL_2 */ +#define MADERA_GP1_DIR 0x8000 +#define MADERA_GP1_DIR_MASK 0x8000 +#define MADERA_GP1_DIR_SHIFT 15 +#define MADERA_GP1_DIR_WIDTH 1 +#define MADERA_GP1_PU 0x4000 +#define MADERA_GP1_PU_MASK 0x4000 +#define MADERA_GP1_PU_SHIFT 14 +#define MADERA_GP1_PU_WIDTH 1 +#define MADERA_GP1_PD 0x2000 +#define MADERA_GP1_PD_MASK 0x2000 +#define MADERA_GP1_PD_SHIFT 13 +#define MADERA_GP1_PD_WIDTH 1 +#define MADERA_GP1_DRV_STR_MASK 0x1800 +#define MADERA_GP1_DRV_STR_SHIFT 11 +#define MADERA_GP1_DRV_STR_WIDTH 2 + +/* (0x1800) IRQ1_Status_1 */ +#define MADERA_CTRLIF_ERR_EINT1 0x1000 +#define MADERA_CTRLIF_ERR_EINT1_MASK 0x1000 +#define MADERA_CTRLIF_ERR_EINT1_SHIFT 12 +#define MADERA_CTRLIF_ERR_EINT1_WIDTH 1 +#define MADERA_SYSCLK_FAIL_EINT1 0x0200 +#define MADERA_SYSCLK_FAIL_EINT1_MASK 0x0200 +#define MADERA_SYSCLK_FAIL_EINT1_SHIFT 9 +#define MADERA_SYSCLK_FAIL_EINT1_WIDTH 1 +#define MADERA_CLOCK_DETECT_EINT1 0x0100 +#define MADERA_CLOCK_DETECT_EINT1_MASK 0x0100 +#define MADERA_CLOCK_DETECT_EINT1_SHIFT 8 +#define MADERA_CLOCK_DETECT_EINT1_WIDTH 1 +#define MADERA_BOOT_DONE_EINT1 0x0080 +#define MADERA_BOOT_DONE_EINT1_MASK 0x0080 +#define MADERA_BOOT_DONE_EINT1_SHIFT 7 +#define MADERA_BOOT_DONE_EINT1_WIDTH 1 + +/* (0x1801) IRQ1_Status_2 */ +#define MADERA_FLLAO_LOCK_EINT1 0x0800 +#define MADERA_FLLAO_LOCK_EINT1_MASK 0x0800 +#define MADERA_FLLAO_LOCK_EINT1_SHIFT 11 +#define MADERA_FLLAO_LOCK_EINT1_WIDTH 1 +#define MADERA_FLL3_LOCK_EINT1 0x0400 +#define MADERA_FLL3_LOCK_EINT1_MASK 0x0400 +#define MADERA_FLL3_LOCK_EINT1_SHIFT 10 +#define MADERA_FLL3_LOCK_EINT1_WIDTH 1 +#define MADERA_FLL2_LOCK_EINT1 0x0200 +#define MADERA_FLL2_LOCK_EINT1_MASK 0x0200 +#define MADERA_FLL2_LOCK_EINT1_SHIFT 9 +#define MADERA_FLL2_LOCK_EINT1_WIDTH 1 +#define MADERA_FLL1_LOCK_EINT1 0x0100 +#define MADERA_FLL1_LOCK_EINT1_MASK 0x0100 +#define MADERA_FLL1_LOCK_EINT1_SHIFT 8 +#define MADERA_FLL1_LOCK_EINT1_WIDTH 1 + +/* (0x1805) IRQ1_Status_6 */ +#define MADERA_MICDET2_EINT1 0x0200 +#define MADERA_MICDET2_EINT1_MASK 0x0200 +#define MADERA_MICDET2_EINT1_SHIFT 9 +#define MADERA_MICDET2_EINT1_WIDTH 1 +#define MADERA_MICDET1_EINT1 0x0100 +#define MADERA_MICDET1_EINT1_MASK 0x0100 +#define MADERA_MICDET1_EINT1_SHIFT 8 +#define MADERA_MICDET1_EINT1_WIDTH 1 +#define MADERA_HPDET_EINT1 0x0001 +#define MADERA_HPDET_EINT1_MASK 0x0001 +#define MADERA_HPDET_EINT1_SHIFT 0 +#define MADERA_HPDET_EINT1_WIDTH 1 + +/* (0x1806) IRQ1_Status_7 */ +#define MADERA_MICD_CLAMP_FALL_EINT1 0x0020 +#define MADERA_MICD_CLAMP_FALL_EINT1_MASK 0x0020 +#define MADERA_MICD_CLAMP_FALL_EINT1_SHIFT 5 +#define MADERA_MICD_CLAMP_FALL_EINT1_WIDTH 1 +#define MADERA_MICD_CLAMP_RISE_EINT1 0x0010 +#define MADERA_MICD_CLAMP_RISE_EINT1_MASK 0x0010 +#define MADERA_MICD_CLAMP_RISE_EINT1_SHIFT 4 +#define MADERA_MICD_CLAMP_RISE_EINT1_WIDTH 1 +#define MADERA_JD2_FALL_EINT1 0x0008 +#define MADERA_JD2_FALL_EINT1_MASK 0x0008 +#define MADERA_JD2_FALL_EINT1_SHIFT 3 +#define MADERA_JD2_FALL_EINT1_WIDTH 1 +#define MADERA_JD2_RISE_EINT1 0x0004 +#define MADERA_JD2_RISE_EINT1_MASK 0x0004 +#define MADERA_JD2_RISE_EINT1_SHIFT 2 +#define MADERA_JD2_RISE_EINT1_WIDTH 1 +#define MADERA_JD1_FALL_EINT1 0x0002 +#define MADERA_JD1_FALL_EINT1_MASK 0x0002 +#define MADERA_JD1_FALL_EINT1_SHIFT 1 +#define MADERA_JD1_FALL_EINT1_WIDTH 1 +#define MADERA_JD1_RISE_EINT1 0x0001 +#define MADERA_JD1_RISE_EINT1_MASK 0x0001 +#define MADERA_JD1_RISE_EINT1_SHIFT 0 +#define MADERA_JD1_RISE_EINT1_WIDTH 1 + +/* (0x1808) IRQ1_Status_9 */ +#define MADERA_ASRC2_IN2_LOCK_EINT1 0x0800 +#define MADERA_ASRC2_IN2_LOCK_EINT1_MASK 0x0800 +#define MADERA_ASRC2_IN2_LOCK_EINT1_SHIFT 11 +#define MADERA_ASRC2_IN2_LOCK_EINT1_WIDTH 1 +#define MADERA_ASRC2_IN1_LOCK_EINT1 0x0400 +#define MADERA_ASRC2_IN1_LOCK_EINT1_MASK 0x0400 +#define MADERA_ASRC2_IN1_LOCK_EINT1_SHIFT 10 +#define MADERA_ASRC2_IN1_LOCK_EINT1_WIDTH 1 +#define MADERA_ASRC1_IN2_LOCK_EINT1 0x0200 +#define MADERA_ASRC1_IN2_LOCK_EINT1_MASK 0x0200 +#define MADERA_ASRC1_IN2_LOCK_EINT1_SHIFT 9 +#define MADERA_ASRC1_IN2_LOCK_EINT1_WIDTH 1 +#define MADERA_ASRC1_IN1_LOCK_EINT1 0x0100 +#define MADERA_ASRC1_IN1_LOCK_EINT1_MASK 0x0100 +#define MADERA_ASRC1_IN1_LOCK_EINT1_SHIFT 8 +#define MADERA_ASRC1_IN1_LOCK_EINT1_WIDTH 1 +#define MADERA_DRC2_SIG_DET_EINT1 0x0002 +#define MADERA_DRC2_SIG_DET_EINT1_MASK 0x0002 +#define MADERA_DRC2_SIG_DET_EINT1_SHIFT 1 +#define MADERA_DRC2_SIG_DET_EINT1_WIDTH 1 +#define MADERA_DRC1_SIG_DET_EINT1 0x0001 +#define MADERA_DRC1_SIG_DET_EINT1_MASK 0x0001 +#define MADERA_DRC1_SIG_DET_EINT1_SHIFT 0 +#define MADERA_DRC1_SIG_DET_EINT1_WIDTH 1 + +/* (0x180A) IRQ1_Status_11 */ +#define MADERA_DSP_IRQ16_EINT1 0x8000 +#define MADERA_DSP_IRQ16_EINT1_MASK 0x8000 +#define MADERA_DSP_IRQ16_EINT1_SHIFT 15 +#define MADERA_DSP_IRQ16_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ15_EINT1 0x4000 +#define MADERA_DSP_IRQ15_EINT1_MASK 0x4000 +#define MADERA_DSP_IRQ15_EINT1_SHIFT 14 +#define MADERA_DSP_IRQ15_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ14_EINT1 0x2000 +#define MADERA_DSP_IRQ14_EINT1_MASK 0x2000 +#define MADERA_DSP_IRQ14_EINT1_SHIFT 13 +#define MADERA_DSP_IRQ14_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ13_EINT1 0x1000 +#define MADERA_DSP_IRQ13_EINT1_MASK 0x1000 +#define MADERA_DSP_IRQ13_EINT1_SHIFT 12 +#define MADERA_DSP_IRQ13_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ12_EINT1 0x0800 +#define MADERA_DSP_IRQ12_EINT1_MASK 0x0800 +#define MADERA_DSP_IRQ12_EINT1_SHIFT 11 +#define MADERA_DSP_IRQ12_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ11_EINT1 0x0400 +#define MADERA_DSP_IRQ11_EINT1_MASK 0x0400 +#define MADERA_DSP_IRQ11_EINT1_SHIFT 10 +#define MADERA_DSP_IRQ11_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ10_EINT1 0x0200 +#define MADERA_DSP_IRQ10_EINT1_MASK 0x0200 +#define MADERA_DSP_IRQ10_EINT1_SHIFT 9 +#define MADERA_DSP_IRQ10_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ9_EINT1 0x0100 +#define MADERA_DSP_IRQ9_EINT1_MASK 0x0100 +#define MADERA_DSP_IRQ9_EINT1_SHIFT 8 +#define MADERA_DSP_IRQ9_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ8_EINT1 0x0080 +#define MADERA_DSP_IRQ8_EINT1_MASK 0x0080 +#define MADERA_DSP_IRQ8_EINT1_SHIFT 7 +#define MADERA_DSP_IRQ8_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ7_EINT1 0x0040 +#define MADERA_DSP_IRQ7_EINT1_MASK 0x0040 +#define MADERA_DSP_IRQ7_EINT1_SHIFT 6 +#define MADERA_DSP_IRQ7_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ6_EINT1 0x0020 +#define MADERA_DSP_IRQ6_EINT1_MASK 0x0020 +#define MADERA_DSP_IRQ6_EINT1_SHIFT 5 +#define MADERA_DSP_IRQ6_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ5_EINT1 0x0010 +#define MADERA_DSP_IRQ5_EINT1_MASK 0x0010 +#define MADERA_DSP_IRQ5_EINT1_SHIFT 4 +#define MADERA_DSP_IRQ5_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ4_EINT1 0x0008 +#define MADERA_DSP_IRQ4_EINT1_MASK 0x0008 +#define MADERA_DSP_IRQ4_EINT1_SHIFT 3 +#define MADERA_DSP_IRQ4_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ3_EINT1 0x0004 +#define MADERA_DSP_IRQ3_EINT1_MASK 0x0004 +#define MADERA_DSP_IRQ3_EINT1_SHIFT 2 +#define MADERA_DSP_IRQ3_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ2_EINT1 0x0002 +#define MADERA_DSP_IRQ2_EINT1_MASK 0x0002 +#define MADERA_DSP_IRQ2_EINT1_SHIFT 1 +#define MADERA_DSP_IRQ2_EINT1_WIDTH 1 +#define MADERA_DSP_IRQ1_EINT1 0x0001 +#define MADERA_DSP_IRQ1_EINT1_MASK 0x0001 +#define MADERA_DSP_IRQ1_EINT1_SHIFT 0 +#define MADERA_DSP_IRQ1_EINT1_WIDTH 1 + +/* (0x180B) IRQ1_Status_12 */ +#define MADERA_SPKOUTR_SC_EINT1 0x0080 +#define MADERA_SPKOUTR_SC_EINT1_MASK 0x0080 +#define MADERA_SPKOUTR_SC_EINT1_SHIFT 7 +#define MADERA_SPKOUTR_SC_EINT1_WIDTH 1 +#define MADERA_SPKOUTL_SC_EINT1 0x0040 +#define MADERA_SPKOUTL_SC_EINT1_MASK 0x0040 +#define MADERA_SPKOUTL_SC_EINT1_SHIFT 6 +#define MADERA_SPKOUTL_SC_EINT1_WIDTH 1 +#define MADERA_HP3R_SC_EINT1 0x0020 +#define MADERA_HP3R_SC_EINT1_MASK 0x0020 +#define MADERA_HP3R_SC_EINT1_SHIFT 5 +#define MADERA_HP3R_SC_EINT1_WIDTH 1 +#define MADERA_HP3L_SC_EINT1 0x0010 +#define MADERA_HP3L_SC_EINT1_MASK 0x0010 +#define MADERA_HP3L_SC_EINT1_SHIFT 4 +#define MADERA_HP3L_SC_EINT1_WIDTH 1 +#define MADERA_HP2R_SC_EINT1 0x0008 +#define MADERA_HP2R_SC_EINT1_MASK 0x0008 +#define MADERA_HP2R_SC_EINT1_SHIFT 3 +#define MADERA_HP2R_SC_EINT1_WIDTH 1 +#define MADERA_HP2L_SC_EINT1 0x0004 +#define MADERA_HP2L_SC_EINT1_MASK 0x0004 +#define MADERA_HP2L_SC_EINT1_SHIFT 2 +#define MADERA_HP2L_SC_EINT1_WIDTH 1 +#define MADERA_HP1R_SC_EINT1 0x0002 +#define MADERA_HP1R_SC_EINT1_MASK 0x0002 +#define MADERA_HP1R_SC_EINT1_SHIFT 1 +#define MADERA_HP1R_SC_EINT1_WIDTH 1 +#define MADERA_HP1L_SC_EINT1 0x0001 +#define MADERA_HP1L_SC_EINT1_MASK 0x0001 +#define MADERA_HP1L_SC_EINT1_SHIFT 0 +#define MADERA_HP1L_SC_EINT1_WIDTH 1 + +/* (0x180E) IRQ1_Status_15 */ +#define MADERA_SPK_OVERHEAT_WARN_EINT1 0x0004 +#define MADERA_SPK_OVERHEAT_WARN_EINT1_MASK 0x0004 +#define MADERA_SPK_OVERHEAT_WARN_EINT1_SHIFT 2 +#define MADERA_SPK_OVERHEAT_WARN_EINT1_WIDTH 1 +#define MADERA_SPK_OVERHEAT_EINT1 0x0002 +#define MADERA_SPK_OVERHEAT_EINT1_MASK 0x0002 +#define MADERA_SPK_OVERHEAT_EINT1_SHIFT 1 +#define MADERA_SPK_OVERHEAT_EINT1_WIDTH 1 +#define MADERA_SPK_SHUTDOWN_EINT1 0x0001 +#define MADERA_SPK_SHUTDOWN_EINT1_MASK 0x0001 +#define MADERA_SPK_SHUTDOWN_EINT1_SHIFT 0 +#define MADERA_SPK_SHUTDOWN_EINT1_WIDTH 1 + +/* (0x1820) - IRQ1 Status 33 */ +#define MADERA_DSP7_BUS_ERR_EINT1 0x0040 +#define MADERA_DSP7_BUS_ERR_EINT1_MASK 0x0040 +#define MADERA_DSP7_BUS_ERR_EINT1_SHIFT 6 +#define MADERA_DSP7_BUS_ERR_EINT1_WIDTH 1 +#define MADERA_DSP6_BUS_ERR_EINT1 0x0020 +#define MADERA_DSP6_BUS_ERR_EINT1_MASK 0x0020 +#define MADERA_DSP6_BUS_ERR_EINT1_SHIFT 5 +#define MADERA_DSP6_BUS_ERR_EINT1_WIDTH 1 +#define MADERA_DSP5_BUS_ERR_EINT1 0x0010 +#define MADERA_DSP5_BUS_ERR_EINT1_MASK 0x0010 +#define MADERA_DSP5_BUS_ERR_EINT1_SHIFT 4 +#define MADERA_DSP5_BUS_ERR_EINT1_WIDTH 1 +#define MADERA_DSP4_BUS_ERR_EINT1 0x0008 +#define MADERA_DSP4_BUS_ERR_EINT1_MASK 0x0008 +#define MADERA_DSP4_BUS_ERR_EINT1_SHIFT 3 +#define MADERA_DSP4_BUS_ERR_EINT1_WIDTH 1 +#define MADERA_DSP3_BUS_ERR_EINT1 0x0004 +#define MADERA_DSP3_BUS_ERR_EINT1_MASK 0x0004 +#define MADERA_DSP3_BUS_ERR_EINT1_SHIFT 2 +#define MADERA_DSP3_BUS_ERR_EINT1_WIDTH 1 +#define MADERA_DSP2_BUS_ERR_EINT1 0x0002 +#define MADERA_DSP2_BUS_ERR_EINT1_MASK 0x0002 +#define MADERA_DSP2_BUS_ERR_EINT1_SHIFT 1 +#define MADERA_DSP2_BUS_ERR_EINT1_WIDTH 1 +#define MADERA_DSP1_BUS_ERR_EINT1 0x0001 +#define MADERA_DSP1_BUS_ERR_EINT1_MASK 0x0001 +#define MADERA_DSP1_BUS_ERR_EINT1_SHIFT 0 +#define MADERA_DSP1_BUS_ERR_EINT1_WIDTH 1 + +/* (0x184E) IRQ1_Mask_15 */ +#define MADERA_IM_SPK_OVERHEAT_WARN_EINT1 0x0004 +#define MADERA_IM_SPK_OVERHEAT_WARN_EINT1_MASK 0x0004 +#define MADERA_IM_SPK_OVERHEAT_WARN_EINT1_SHIFT 2 +#define MADERA_IM_SPK_OVERHEAT_WARN_EINT1_WIDTH 1 +#define MADERA_IM_SPK_OVERHEAT_EINT1 0x0002 +#define MADERA_IM_SPK_OVERHEAT_EINT1_MASK 0x0002 +#define MADERA_IM_SPK_OVERHEAT_EINT1_SHIFT 1 +#define MADERA_IM_SPK_OVERHEAT_EINT1_WIDTH 1 +#define MADERA_IM_SPK_SHUTDOWN_EINT1 0x0001 +#define MADERA_IM_SPK_SHUTDOWN_EINT1_MASK 0x0001 +#define MADERA_IM_SPK_SHUTDOWN_EINT1_SHIFT 0 +#define MADERA_IM_SPK_SHUTDOWN_EINT1_WIDTH 1 + +/* (0x1880) - IRQ1 Raw Status 1 */ +#define MADERA_CTRLIF_ERR_STS1 0x1000 +#define MADERA_CTRLIF_ERR_STS1_MASK 0x1000 +#define MADERA_CTRLIF_ERR_STS1_SHIFT 12 +#define MADERA_CTRLIF_ERR_STS1_WIDTH 1 +#define MADERA_SYSCLK_FAIL_STS1 0x0200 +#define MADERA_SYSCLK_FAIL_STS1_MASK 0x0200 +#define MADERA_SYSCLK_FAIL_STS1_SHIFT 9 +#define MADERA_SYSCLK_FAIL_STS1_WIDTH 1 +#define MADERA_CLOCK_DETECT_STS1 0x0100 +#define MADERA_CLOCK_DETECT_STS1_MASK 0x0100 +#define MADERA_CLOCK_DETECT_STS1_SHIFT 8 +#define MADERA_CLOCK_DETECT_STS1_WIDTH 1 +#define MADERA_BOOT_DONE_STS1 0x0080 +#define MADERA_BOOT_DONE_STS1_MASK 0x0080 +#define MADERA_BOOT_DONE_STS1_SHIFT 7 +#define MADERA_BOOT_DONE_STS1_WIDTH 1 + +/* (0x1881) - IRQ1 Raw Status 2 */ +#define MADERA_FLL3_LOCK_STS1 0x0400 +#define MADERA_FLL3_LOCK_STS1_MASK 0x0400 +#define MADERA_FLL3_LOCK_STS1_SHIFT 10 +#define MADERA_FLL3_LOCK_STS1_WIDTH 1 +#define MADERA_FLL2_LOCK_STS1 0x0200 +#define MADERA_FLL2_LOCK_STS1_MASK 0x0200 +#define MADERA_FLL2_LOCK_STS1_SHIFT 9 +#define MADERA_FLL2_LOCK_STS1_WIDTH 1 +#define MADERA_FLL1_LOCK_STS1 0x0100 +#define MADERA_FLL1_LOCK_STS1_MASK 0x0100 +#define MADERA_FLL1_LOCK_STS1_SHIFT 8 +#define MADERA_FLL1_LOCK_STS1_WIDTH 1 + +/* (0x1886) - IRQ1 Raw Status 7 */ +#define MADERA_MICD_CLAMP_FALL_STS1 0x0020 +#define MADERA_MICD_CLAMP_FALL_STS1_MASK 0x0020 +#define MADERA_MICD_CLAMP_FALL_STS1_SHIFT 5 +#define MADERA_MICD_CLAMP_FALL_STS1_WIDTH 1 +#define MADERA_MICD_CLAMP_RISE_STS1 0x0010 +#define MADERA_MICD_CLAMP_RISE_STS1_MASK 0x0010 +#define MADERA_MICD_CLAMP_RISE_STS1_SHIFT 4 +#define MADERA_MICD_CLAMP_RISE_STS1_WIDTH 1 +#define MADERA_JD2_FALL_STS1 0x0008 +#define MADERA_JD2_FALL_STS1_MASK 0x0008 +#define MADERA_JD2_FALL_STS1_SHIFT 3 +#define MADERA_JD2_FALL_STS1_WIDTH 1 +#define MADERA_JD2_RISE_STS1 0x0004 +#define MADERA_JD2_RISE_STS1_MASK 0x0004 +#define MADERA_JD2_RISE_STS1_SHIFT 2 +#define MADERA_JD2_RISE_STS1_WIDTH 1 +#define MADERA_JD1_FALL_STS1 0x0002 +#define MADERA_JD1_FALL_STS1_MASK 0x0002 +#define MADERA_JD1_FALL_STS1_SHIFT 1 +#define MADERA_JD1_FALL_STS1_WIDTH 1 +#define MADERA_JD1_RISE_STS1 0x0001 +#define MADERA_JD1_RISE_STS1_MASK 0x0001 +#define MADERA_JD1_RISE_STS1_SHIFT 0 +#define MADERA_JD1_RISE_STS1_WIDTH 1 + +/* (0x188E) - IRQ1 Raw Status 15 */ +#define MADERA_SPK_OVERHEAT_WARN_STS1 0x0004 +#define MADERA_SPK_OVERHEAT_WARN_STS1_MASK 0x0004 +#define MADERA_SPK_OVERHEAT_WARN_STS1_SHIFT 2 +#define MADERA_SPK_OVERHEAT_WARN_STS1_WIDTH 1 +#define MADERA_SPK_OVERHEAT_STS1 0x0002 +#define MADERA_SPK_OVERHEAT_STS1_MASK 0x0002 +#define MADERA_SPK_OVERHEAT_STS1_SHIFT 1 +#define MADERA_SPK_OVERHEAT_STS1_WIDTH 1 +#define MADERA_SPK_SHUTDOWN_STS1 0x0001 +#define MADERA_SPK_SHUTDOWN_STS1_MASK 0x0001 +#define MADERA_SPK_SHUTDOWN_STS1_SHIFT 0 +#define MADERA_SPK_SHUTDOWN_STS1_WIDTH 1 + +/* (0x1A06) Interrupt_Debounce_7 */ +#define MADERA_MICD_CLAMP_DB 0x0010 +#define MADERA_MICD_CLAMP_DB_MASK 0x0010 +#define MADERA_MICD_CLAMP_DB_SHIFT 4 +#define MADERA_MICD_CLAMP_DB_WIDTH 1 +#define MADERA_JD2_DB 0x0004 +#define MADERA_JD2_DB_MASK 0x0004 +#define MADERA_JD2_DB_SHIFT 2 +#define MADERA_JD2_DB_WIDTH 1 +#define MADERA_JD1_DB 0x0001 +#define MADERA_JD1_DB_MASK 0x0001 +#define MADERA_JD1_DB_SHIFT 0 +#define MADERA_JD1_DB_WIDTH 1 + +/* (0x1A0E) Interrupt_Debounce_15 */ +#define MADERA_SPK_OVERHEAT_WARN_DB 0x0004 +#define MADERA_SPK_OVERHEAT_WARN_DB_MASK 0x0004 +#define MADERA_SPK_OVERHEAT_WARN_DB_SHIFT 2 +#define MADERA_SPK_OVERHEAT_WARN_DB_WIDTH 1 +#define MADERA_SPK_OVERHEAT_DB 0x0002 +#define MADERA_SPK_OVERHEAT_DB_MASK 0x0002 +#define MADERA_SPK_OVERHEAT_DB_SHIFT 1 +#define MADERA_SPK_OVERHEAT_DB_WIDTH 1 + +/* (0x1A80) IRQ1_CTRL */ +#define MADERA_IM_IRQ1 0x0800 +#define MADERA_IM_IRQ1_MASK 0x0800 +#define MADERA_IM_IRQ1_SHIFT 11 +#define MADERA_IM_IRQ1_WIDTH 1 +#define MADERA_IRQ_POL 0x0400 +#define MADERA_IRQ_POL_MASK 0x0400 +#define MADERA_IRQ_POL_SHIFT 10 +#define MADERA_IRQ_POL_WIDTH 1 + +/* (0x20004) OTP_HPDET_Cal_1 */ +#define MADERA_OTP_HPDET_CALIB_OFFSET_11 0xFF000000 +#define MADERA_OTP_HPDET_CALIB_OFFSET_11_MASK 0xFF000000 +#define MADERA_OTP_HPDET_CALIB_OFFSET_11_SHIFT 24 +#define MADERA_OTP_HPDET_CALIB_OFFSET_11_WIDTH 8 +#define MADERA_OTP_HPDET_CALIB_OFFSET_10 0x00FF0000 +#define MADERA_OTP_HPDET_CALIB_OFFSET_10_MASK 0x00FF0000 +#define MADERA_OTP_HPDET_CALIB_OFFSET_10_SHIFT 16 +#define MADERA_OTP_HPDET_CALIB_OFFSET_10_WIDTH 8 +#define MADERA_OTP_HPDET_CALIB_OFFSET_01 0x0000FF00 +#define MADERA_OTP_HPDET_CALIB_OFFSET_01_MASK 0x0000FF00 +#define MADERA_OTP_HPDET_CALIB_OFFSET_01_SHIFT 8 +#define MADERA_OTP_HPDET_CALIB_OFFSET_01_WIDTH 8 +#define MADERA_OTP_HPDET_CALIB_OFFSET_00 0x000000FF +#define MADERA_OTP_HPDET_CALIB_OFFSET_00_MASK 0x000000FF +#define MADERA_OTP_HPDET_CALIB_OFFSET_00_SHIFT 0 +#define MADERA_OTP_HPDET_CALIB_OFFSET_00_WIDTH 8 + +/* (0x20006) OTP_HPDET_Cal_2 */ +#define MADERA_OTP_HPDET_GRADIENT_1X 0x0000FF00 +#define MADERA_OTP_HPDET_GRADIENT_1X_MASK 0x0000FF00 +#define MADERA_OTP_HPDET_GRADIENT_1X_SHIFT 8 +#define MADERA_OTP_HPDET_GRADIENT_1X_WIDTH 8 +#define MADERA_OTP_HPDET_GRADIENT_0X 0x000000FF +#define MADERA_OTP_HPDET_GRADIENT_0X_MASK 0x000000FF +#define MADERA_OTP_HPDET_GRADIENT_0X_SHIFT 0 +#define MADERA_OTP_HPDET_GRADIENT_0X_WIDTH 8 + +#endif -- cgit v1.2.3 From 16b27467f46c1e0dbf093f53971aeb5decbaff4e Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Mon, 21 May 2018 10:59:56 +0100 Subject: mfd: madera: Add common support for Cirrus Logic Madera codecs This adds the generic core support for Cirrus Logic "Madera" class codecs. These are complex audio codec SoCs with a variety of digital and analogue I/O, onboard audio processing and DSPs, and other features. These codecs are all based off a common set of hardware IP so can be supported by a core of common code (with a few minor device-to-device variations). Signed-off-by: Charles Keepax Signed-off-by: Nikesh Oswal Signed-off-by: Richard Fitzgerald Signed-off-by: Lee Jones --- include/linux/mfd/madera/core.h | 187 +++++++++++++++++++++++++++++++++++++++ include/linux/mfd/madera/pdata.h | 59 ++++++++++++ 2 files changed, 246 insertions(+) create mode 100644 include/linux/mfd/madera/core.h create mode 100644 include/linux/mfd/madera/pdata.h (limited to 'include/linux') diff --git a/include/linux/mfd/madera/core.h b/include/linux/mfd/madera/core.h new file mode 100644 index 000000000000..c332681848ef --- /dev/null +++ b/include/linux/mfd/madera/core.h @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * MFD internals for Cirrus Logic Madera codecs + * + * Copyright (C) 2015-2018 Cirrus Logic + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2. + */ + +#ifndef MADERA_CORE_H +#define MADERA_CORE_H + +#include +#include +#include +#include +#include +#include + +enum madera_type { + /* 0 is reserved for indicating failure to identify */ + CS47L35 = 1, + CS47L85 = 2, + CS47L90 = 3, + CS47L91 = 4, + WM1840 = 7, +}; + +#define MADERA_MAX_CORE_SUPPLIES 2 +#define MADERA_MAX_GPIOS 40 + +#define CS47L35_NUM_GPIOS 16 +#define CS47L85_NUM_GPIOS 40 +#define CS47L90_NUM_GPIOS 38 + +#define MADERA_MAX_MICBIAS 4 + +/* Notifier events */ +#define MADERA_NOTIFY_VOICE_TRIGGER 0x1 +#define MADERA_NOTIFY_HPDET 0x2 +#define MADERA_NOTIFY_MICDET 0x4 + +/* GPIO Function Definitions */ +#define MADERA_GP_FN_ALTERNATE 0x00 +#define MADERA_GP_FN_GPIO 0x01 +#define MADERA_GP_FN_DSP_GPIO 0x02 +#define MADERA_GP_FN_IRQ1 0x03 +#define MADERA_GP_FN_IRQ2 0x04 +#define MADERA_GP_FN_FLL1_CLOCK 0x10 +#define MADERA_GP_FN_FLL2_CLOCK 0x11 +#define MADERA_GP_FN_FLL3_CLOCK 0x12 +#define MADERA_GP_FN_FLLAO_CLOCK 0x13 +#define MADERA_GP_FN_FLL1_LOCK 0x18 +#define MADERA_GP_FN_FLL2_LOCK 0x19 +#define MADERA_GP_FN_FLL3_LOCK 0x1A +#define MADERA_GP_FN_FLLAO_LOCK 0x1B +#define MADERA_GP_FN_OPCLK_OUT 0x40 +#define MADERA_GP_FN_OPCLK_ASYNC_OUT 0x41 +#define MADERA_GP_FN_PWM1 0x48 +#define MADERA_GP_FN_PWM2 0x49 +#define MADERA_GP_FN_SPDIF_OUT 0x4C +#define MADERA_GP_FN_HEADPHONE_DET 0x50 +#define MADERA_GP_FN_MIC_DET 0x58 +#define MADERA_GP_FN_DRC1_SIGNAL_DETECT 0x80 +#define MADERA_GP_FN_DRC2_SIGNAL_DETECT 0x81 +#define MADERA_GP_FN_ASRC1_IN1_LOCK 0x88 +#define MADERA_GP_FN_ASRC1_IN2_LOCK 0x89 +#define MADERA_GP_FN_ASRC2_IN1_LOCK 0x8A +#define MADERA_GP_FN_ASRC2_IN2_LOCK 0x8B +#define MADERA_GP_FN_DSP_IRQ1 0xA0 +#define MADERA_GP_FN_DSP_IRQ2 0xA1 +#define MADERA_GP_FN_DSP_IRQ3 0xA2 +#define MADERA_GP_FN_DSP_IRQ4 0xA3 +#define MADERA_GP_FN_DSP_IRQ5 0xA4 +#define MADERA_GP_FN_DSP_IRQ6 0xA5 +#define MADERA_GP_FN_DSP_IRQ7 0xA6 +#define MADERA_GP_FN_DSP_IRQ8 0xA7 +#define MADERA_GP_FN_DSP_IRQ9 0xA8 +#define MADERA_GP_FN_DSP_IRQ10 0xA9 +#define MADERA_GP_FN_DSP_IRQ11 0xAA +#define MADERA_GP_FN_DSP_IRQ12 0xAB +#define MADERA_GP_FN_DSP_IRQ13 0xAC +#define MADERA_GP_FN_DSP_IRQ14 0xAD +#define MADERA_GP_FN_DSP_IRQ15 0xAE +#define MADERA_GP_FN_DSP_IRQ16 0xAF +#define MADERA_GP_FN_HPOUT1L_SC 0xB0 +#define MADERA_GP_FN_HPOUT1R_SC 0xB1 +#define MADERA_GP_FN_HPOUT2L_SC 0xB2 +#define MADERA_GP_FN_HPOUT2R_SC 0xB3 +#define MADERA_GP_FN_HPOUT3L_SC 0xB4 +#define MADERA_GP_FN_HPOUT4R_SC 0xB5 +#define MADERA_GP_FN_SPKOUTL_SC 0xB6 +#define MADERA_GP_FN_SPKOUTR_SC 0xB7 +#define MADERA_GP_FN_HPOUT1L_ENA 0xC0 +#define MADERA_GP_FN_HPOUT1R_ENA 0xC1 +#define MADERA_GP_FN_HPOUT2L_ENA 0xC2 +#define MADERA_GP_FN_HPOUT2R_ENA 0xC3 +#define MADERA_GP_FN_HPOUT3L_ENA 0xC4 +#define MADERA_GP_FN_HPOUT4R_ENA 0xC5 +#define MADERA_GP_FN_SPKOUTL_ENA 0xC6 +#define MADERA_GP_FN_SPKOUTR_ENA 0xC7 +#define MADERA_GP_FN_HPOUT1L_DIS 0xD0 +#define MADERA_GP_FN_HPOUT1R_DIS 0xD1 +#define MADERA_GP_FN_HPOUT2L_DIS 0xD2 +#define MADERA_GP_FN_HPOUT2R_DIS 0xD3 +#define MADERA_GP_FN_HPOUT3L_DIS 0xD4 +#define MADERA_GP_FN_HPOUT4R_DIS 0xD5 +#define MADERA_GP_FN_SPKOUTL_DIS 0xD6 +#define MADERA_GP_FN_SPKOUTR_DIS 0xD7 +#define MADERA_GP_FN_SPK_SHUTDOWN 0xE0 +#define MADERA_GP_FN_SPK_OVH_SHUTDOWN 0xE1 +#define MADERA_GP_FN_SPK_OVH_WARN 0xE2 +#define MADERA_GP_FN_TIMER1_STATUS 0x140 +#define MADERA_GP_FN_TIMER2_STATUS 0x141 +#define MADERA_GP_FN_TIMER3_STATUS 0x142 +#define MADERA_GP_FN_TIMER4_STATUS 0x143 +#define MADERA_GP_FN_TIMER5_STATUS 0x144 +#define MADERA_GP_FN_TIMER6_STATUS 0x145 +#define MADERA_GP_FN_TIMER7_STATUS 0x146 +#define MADERA_GP_FN_TIMER8_STATUS 0x147 +#define MADERA_GP_FN_EVENTLOG1_FIFO_STS 0x150 +#define MADERA_GP_FN_EVENTLOG2_FIFO_STS 0x151 +#define MADERA_GP_FN_EVENTLOG3_FIFO_STS 0x152 +#define MADERA_GP_FN_EVENTLOG4_FIFO_STS 0x153 +#define MADERA_GP_FN_EVENTLOG5_FIFO_STS 0x154 +#define MADERA_GP_FN_EVENTLOG6_FIFO_STS 0x155 +#define MADERA_GP_FN_EVENTLOG7_FIFO_STS 0x156 +#define MADERA_GP_FN_EVENTLOG8_FIFO_STS 0x157 + +struct snd_soc_dapm_context; + +/* + * struct madera - internal data shared by the set of Madera drivers + * + * This should not be used by anything except child drivers of the Madera MFD + * + * @regmap: pointer to the regmap instance for 16-bit registers + * @regmap_32bit: pointer to the regmap instance for 32-bit registers + * @dev: pointer to the MFD device + * @type: type of codec + * @rev: silicon revision + * @type_name: display name of this codec + * @num_core_supplies: number of core supply regulators + * @core_supplies: list of core supplies that are always required + * @dcvdd: pointer to DCVDD regulator + * @internal_dcvdd: true if DCVDD is supplied from the internal LDO1 + * @pdata: our pdata + * @irq_dev: the irqchip child driver device + * @irq: host irq number from SPI or I2C configuration + * @out_clamp: indicates output clamp state for each analogue output + * @out_shorted: indicates short circuit state for each analogue output + * @hp_ena: bitflags of enable state for the headphone outputs + * @num_micbias: number of MICBIAS outputs + * @num_childbias: number of child biases for each MICBIAS + * @dapm: pointer to codec driver DAPM context + * @notifier: notifier for signalling events to ASoC machine driver + */ +struct madera { + struct regmap *regmap; + struct regmap *regmap_32bit; + + struct device *dev; + + enum madera_type type; + unsigned int rev; + const char *type_name; + + int num_core_supplies; + struct regulator_bulk_data core_supplies[MADERA_MAX_CORE_SUPPLIES]; + struct regulator *dcvdd; + bool internal_dcvdd; + + struct madera_pdata pdata; + + struct device *irq_dev; + int irq; + + unsigned int num_micbias; + unsigned int num_childbias[MADERA_MAX_MICBIAS]; + + struct snd_soc_dapm_context *dapm; + + struct blocking_notifier_head notifier; +}; +#endif diff --git a/include/linux/mfd/madera/pdata.h b/include/linux/mfd/madera/pdata.h new file mode 100644 index 000000000000..0b311f39c8f4 --- /dev/null +++ b/include/linux/mfd/madera/pdata.h @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Platform data for Cirrus Logic Madera codecs + * + * Copyright (C) 2015-2018 Cirrus Logic + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2. + */ + +#ifndef MADERA_PDATA_H +#define MADERA_PDATA_H + +#include +#include +#include +#include + +#define MADERA_MAX_MICBIAS 4 +#define MADERA_MAX_CHILD_MICBIAS 4 + +#define MADERA_MAX_GPSW 2 + +struct gpio_desc; +struct pinctrl_map; +struct madera_irqchip_pdata; +struct madera_codec_pdata; + +/** + * struct madera_pdata - Configuration data for Madera devices + * + * @reset: GPIO controlling /RESET (NULL = none) + * @ldo1: Substruct of pdata for the LDO1 regulator + * @micvdd: Substruct of pdata for the MICVDD regulator + * @irq_flags: Mode for primary IRQ (defaults to active low) + * @gpio_base: Base GPIO number + * @gpio_configs: Array of GPIO configurations (See Documentation/pinctrl.txt) + * @n_gpio_configs: Number of entries in gpio_configs + * @gpsw: General purpose switch mode setting. Depends on the external + * hardware connected to the switch. (See the SW1_MODE field + * in the datasheet for the available values for your codec) + */ +struct madera_pdata { + struct gpio_desc *reset; + + struct arizona_ldo1_pdata ldo1; + struct arizona_micsupp_pdata micvdd; + + unsigned int irq_flags; + int gpio_base; + + const struct pinctrl_map *gpio_configs; + int n_gpio_configs; + + u32 gpsw[MADERA_MAX_GPSW]; +}; + +#endif -- cgit v1.2.3 From 189454e868c45ce3476bfac03ace921dec34208a Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 5 Jun 2018 13:55:50 +0200 Subject: net: remove net_device operation ndo_xdp_flush All drivers are cleaned up and no references to ndo_xdp_flush are left in drivers, it is time to remove the net_device_ops operation ndo_xdp_flush. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann --- include/linux/netdevice.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7f17785a59d7..42c6ea35a6f2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1192,9 +1192,6 @@ struct dev_ifalias { * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. - * void (*ndo_xdp_flush)(struct net_device *dev); - * This function is used to inform the driver to flush a particular - * xdp tx queue. Must be called on same CPU as xdp_xmit. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1382,7 +1379,6 @@ struct net_device_ops { int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, u32 flags); - void (*ndo_xdp_flush)(struct net_device *dev); }; /** -- cgit v1.2.3 From 9107c05e2e55c1c7abd02ab38f7694e0da08b643 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 2 Jun 2018 22:37:24 +0200 Subject: net: phy: remove PM ops from MDIO bus Current implementation of MDIO bus PM ops doesn't actually implement bus-specific PM ops but just calls PM ops defined on a device level what doesn't seem to be fully in line with the core PM model. When looking e.g. at __device_suspend() the PM core looks for PM ops of a device in a specific order: 1. device PM domain 2. device type 3. device class 4. device bus I think it has good reason that there's no PM ops on device level. Now that a device type representation of PHY's as special type of MDIO devices was added (only user of MDIO bus PM ops), the MDIO bus PM ops can be removed including member pm of struct mdio_device. If for some other type of MDIO device PM ops are needed, it should be modeled as struct device_type as well. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/mdio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 2cfffe586885..bfa7114167d7 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -29,7 +29,6 @@ enum mdio_mutex_lock_class { struct mdio_device { struct device dev; - const struct dev_pm_ops *pm_ops; struct mii_bus *bus; char modalias[MDIO_NAME_SIZE]; -- cgit v1.2.3 From 69e2ecccd0bee6b186d0d42f8093109bfca7e990 Mon Sep 17 00:00:00 2001 From: Kun Yi Date: Mon, 4 Jun 2018 13:17:04 -0700 Subject: net: phy: broadcom: Enable 125 MHz clock on LED4 pin for BCM54612E by default. BCM54612E have 4 multi-functional LED pins that can be configured through register setting; the LED4 pin can be configured to a 125MHz reference clock output by setting the spare register. Since the dedicated CLK125 reference clock pin is not brought out on the 48-Pin MLP, the LED4 pin is the only pin to provide such function in this package, and therefore it is beneficial to just enable the reference clock by default. Signed-off-by: Kun Yi Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index b324e01ccf2d..daa9234a9baf 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -85,6 +85,7 @@ #define MII_BCM54XX_EXP_SEL 0x17 /* Expansion register select */ #define MII_BCM54XX_EXP_SEL_SSD 0x0e00 /* Secondary SerDes select */ #define MII_BCM54XX_EXP_SEL_ER 0x0f00 /* Expansion register select */ +#define MII_BCM54XX_EXP_SEL_ETC 0x0d00 /* Expansion register spare + 2k mem */ #define MII_BCM54XX_AUX_CTL 0x18 /* Auxiliary control register */ #define MII_BCM54XX_ISR 0x1a /* BCM54xx interrupt status register */ @@ -219,6 +220,9 @@ #define BCM54810_SHD_CLK_CTL 0x3 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9) +/* BCM54612E Registers */ +#define BCM54612E_EXP_SPARE0 (MII_BCM54XX_EXP_SEL_ETC + 0x34) +#define BCM54612E_LED4_CLK125OUT_EN (1 << 1) /*****************************************************************************/ /* Fast Ethernet Transceiver definitions. */ -- cgit v1.2.3 From 74515c5750f30244a901c3c0c82a2fe534b3c9c5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Mon, 4 Jun 2018 14:05:53 +0200 Subject: net: xdp: added bpf_netdev_command XDP_{QUERY, SETUP}_XSK_UMEM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extend ndo_bpf with two new commands used for query zero-copy support and register an UMEM to a queue_id of a netdev. Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 42c6ea35a6f2..cc4ea7ab6d24 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -817,10 +817,13 @@ enum bpf_netdev_command { BPF_OFFLOAD_DESTROY, BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, + XDP_QUERY_XSK_UMEM, + XDP_SETUP_XSK_UMEM, }; struct bpf_prog_offload_ops; struct netlink_ext_ack; +struct xdp_umem; struct netdev_bpf { enum bpf_netdev_command command; @@ -851,6 +854,11 @@ struct netdev_bpf { struct { struct bpf_offloaded_map *offmap; }; + /* XDP_SETUP_XSK_UMEM */ + struct { + struct xdp_umem *umem; + u16 queue_id; + } xsk; }; }; -- cgit v1.2.3 From e3760c7e50ac6cdf1188fec44938dd7e6e6eef61 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Mon, 4 Jun 2018 14:05:56 +0200 Subject: net: added netdevice operation for Tx Added ndo_xsk_async_xmit. This ndo "kicks" the netdev to start to pull userland AF_XDP Tx frames from a NAPI context. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cc4ea7ab6d24..03ffeadf8a41 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1387,6 +1387,8 @@ struct net_device_ops { int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, u32 flags); + int (*ndo_xsk_async_xmit)(struct net_device *dev, + u32 queue_id); }; /** -- cgit v1.2.3 From d52c89f120de849575f6b2e5948038f2be12ce6f Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Tue, 5 Jun 2018 13:11:16 +0300 Subject: qed*: Utilize FW 8.37.2.0 This FW contains several fixes and features. RDMA - Several modifications and fixes for Memory Windows - drop vlan and tcp timestamp from mss calculation in driver for this FW - Fix SQ completion flow when local ack timeout is infinite - Modifications in t10dif support ETH - Fix aRFS for tunneled traffic without inner IP. - Fix chip configuration which may fail under heavy traffic conditions. - Support receiving any-VNI in VXLAN and GENEVE RX classification. iSCSI / FcoE - Fix iSCSI recovery flow - Drop vlan and tcp timestamp from mss calc for fw 8.37.2.0 Misc - Several registers (split registers) won't read correctly with ethtool -d Signed-off-by: Ariel Elior Signed-off-by: Manish Rangankar Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 4 ++-- include/linux/qed/iscsi_common.h | 8 ++++---- include/linux/qed/qed_rdma_if.h | 4 +--- include/linux/qed/roce_common.h | 1 + 4 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 13c8ab171437..0081fa6d1268 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -109,8 +109,8 @@ #define MAX_NUM_LL2_TX_STATS_COUNTERS 48 #define FW_MAJOR_VERSION 8 -#define FW_MINOR_VERSION 33 -#define FW_REVISION_VERSION 11 +#define FW_MINOR_VERSION 37 +#define FW_REVISION_VERSION 2 #define FW_ENGINEERING_VERSION 0 /***********************/ diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index 938df614cb6a..b34c573f2b30 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -799,8 +799,8 @@ struct e4_mstorm_iscsi_task_ag_ctx { #define E4_MSTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 #define E4_MSTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 #define E4_MSTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_BIT1_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_BIT1_SHIFT 5 +#define E4_MSTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define E4_MSTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 #define E4_MSTORM_ISCSI_TASK_AG_CTX_VALID_MASK 0x1 #define E4_MSTORM_ISCSI_TASK_AG_CTX_VALID_SHIFT 6 #define E4_MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_FLAG_MASK 0x1 @@ -849,8 +849,8 @@ struct e4_ustorm_iscsi_task_ag_ctx { #define E4_USTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 #define E4_USTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 #define E4_USTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 -#define E4_USTORM_ISCSI_TASK_AG_CTX_BIT1_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_BIT1_SHIFT 5 +#define E4_USTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define E4_USTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 #define E4_USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_MASK 0x3 #define E4_USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_SHIFT 6 u8 flags1; diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index e05e320d28b7..df4d13f7e191 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -65,8 +65,7 @@ enum qed_roce_qp_state { enum qed_rdma_tid_type { QED_RDMA_TID_REGISTERED_MR, QED_RDMA_TID_FMR, - QED_RDMA_TID_MW_TYPE1, - QED_RDMA_TID_MW_TYPE2A + QED_RDMA_TID_MW }; struct qed_rdma_events { @@ -280,7 +279,6 @@ struct qed_rdma_register_tid_in_params { bool dif_enabled; u64 dif_error_addr; - u64 dif_runt_addr; }; struct qed_rdma_create_cq_in_params { diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h index 193bcef302e1..473fba76aa77 100644 --- a/include/linux/qed/roce_common.h +++ b/include/linux/qed/roce_common.h @@ -43,6 +43,7 @@ #define ROCE_MAX_QPS (32 * 1024) #define ROCE_DCQCN_NP_MAX_QPS (64) #define ROCE_DCQCN_RP_MAX_QPS (64) +#define ROCE_LKEY_MW_DIF_EN_BIT (28) /* Affiliated asynchronous events / errors enumeration */ enum roce_async_events_type { -- cgit v1.2.3 From e783bb00ad86d9d1f01d9d3a750713070036358e Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 5 Jun 2018 15:02:00 +0200 Subject: ipmr: fix error path when ipmr_new_table fails commit 0bbbf0e7d0e7 ("ipmr, ip6mr: Unite creation of new mr_table") refactored ipmr_new_table, so that it now returns NULL when mr_table_alloc fails. Unfortunately, all callers of ipmr_new_table expect an ERR_PTR. This can result in NULL deref, for example when ipmr_rules_exit calls ipmr_free_table with NULL net->ipv4.mrt in the !CONFIG_IP_MROUTE_MULTIPLE_TABLES version. This patch makes mr_table_alloc return errors, and changes ip6mr_new_table and its callers to return/expect error pointers as well. It also removes the version of mr_table_alloc defined under !CONFIG_IP_MROUTE_COMMON, since it is never used. Fixes: 0bbbf0e7d0e7 ("ipmr, ip6mr: Unite creation of new mr_table") Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- include/linux/mroute_base.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index d617fe45543e..d633f737b3c6 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -307,16 +307,6 @@ static inline void vif_device_init(struct vif_device *v, { } -static inline void * -mr_table_alloc(struct net *net, u32 id, - struct mr_table_ops *ops, - void (*expire_func)(struct timer_list *t), - void (*table_set)(struct mr_table *mrt, - struct net *net)) -{ - return NULL; -} - static inline void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent) { -- cgit v1.2.3 From 2520e627dbeecf7ccccc50c969504b59e1a3294b Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 5 Jun 2018 15:35:03 +0100 Subject: ACPI / PPTT: fix build when CONFIG_ACPI_PPTT is not enabled Though CONFIG_ACPI_PPTT is selected by platforms and nor user visible, it may be useful to support the build with CONFIG_ACPI_PPTT disabled. This patch adds the missing dummy/boiler plate implementation to fix the build. Acked-by: "Rafael J. Wysocki" Signed-off-by: Sudeep Holla Signed-off-by: Catalin Marinas --- include/linux/acpi.h | 15 +++++++++++++++ include/linux/cacheinfo.h | 2 +- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 032e12a2fdc2..d2639cd2eafc 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1297,8 +1297,23 @@ static inline int lpit_read_residency_count_address(u64 *address) } #endif +#ifdef CONFIG_ACPI_PPTT int find_acpi_cpu_topology(unsigned int cpu, int level); int find_acpi_cpu_topology_package(unsigned int cpu); int find_acpi_cpu_cache_topology(unsigned int cpu, int level); +#else +static inline int find_acpi_cpu_topology(unsigned int cpu, int level) +{ + return -EINVAL; +} +static inline int find_acpi_cpu_topology_package(unsigned int cpu) +{ + return -EINVAL; +} +static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level) +{ + return -EINVAL; +} +#endif #endif /*_LINUX_ACPI_H*/ diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 89397e30e269..70e19bc6cc9f 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -98,7 +98,7 @@ struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu); int init_cache_level(unsigned int cpu); int populate_cache_leaves(unsigned int cpu); int cache_setup_acpi(unsigned int cpu); -#ifndef CONFIG_ACPI +#ifndef CONFIG_ACPI_PPTT /* * acpi_find_last_cache_level is only called on ACPI enabled * platforms using the PPTT for topology. This means that if -- cgit v1.2.3 From 610b15c50e86eb1e4b77274fabcaea29ac72d6a8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 7 May 2018 16:47:02 -0700 Subject: overflow.h: Add allocation size calculation helpers In preparation for replacing unchecked overflows for memory allocations, this creates helpers for the 3 most common calculations: array_size(a, b): 2-dimensional array array3_size(a, b, c): 3-dimensional array struct_size(ptr, member, n): struct followed by n-many trailing members Each of these return SIZE_MAX on overflow instead of wrapping around. (Additionally renames a variable named "array_size" to avoid future collision.) Co-developed-by: Matthew Wilcox Signed-off-by: Kees Cook --- include/linux/overflow.h | 73 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) (limited to 'include/linux') diff --git a/include/linux/overflow.h b/include/linux/overflow.h index c8890ec358a7..8712ff70995f 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -202,4 +202,77 @@ #endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ +/** + * array_size() - Calculate size of 2-dimensional array. + * + * @a: dimension one + * @b: dimension two + * + * Calculates size of 2-dimensional array: @a * @b. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +static inline __must_check size_t array_size(size_t a, size_t b) +{ + size_t bytes; + + if (check_mul_overflow(a, b, &bytes)) + return SIZE_MAX; + + return bytes; +} + +/** + * array3_size() - Calculate size of 3-dimensional array. + * + * @a: dimension one + * @b: dimension two + * @c: dimension three + * + * Calculates size of 3-dimensional array: @a * @b * @c. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +static inline __must_check size_t array3_size(size_t a, size_t b, size_t c) +{ + size_t bytes; + + if (check_mul_overflow(a, b, &bytes)) + return SIZE_MAX; + if (check_mul_overflow(bytes, c, &bytes)) + return SIZE_MAX; + + return bytes; +} + +static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c) +{ + size_t bytes; + + if (check_mul_overflow(n, size, &bytes)) + return SIZE_MAX; + if (check_add_overflow(bytes, c, &bytes)) + return SIZE_MAX; + + return bytes; +} + +/** + * struct_size() - Calculate size of structure with trailing array. + * @p: Pointer to the structure. + * @member: Name of the array member. + * @n: Number of elements in the array. + * + * Calculates size of memory needed for structure @p followed by an + * array of @n @member elements. + * + * Return: number of bytes needed or SIZE_MAX on overflow. + */ +#define struct_size(p, member, n) \ + __ab_c_size(n, \ + sizeof(*(p)->member) + __must_be_array((p)->member),\ + sizeof(*(p))) + #endif /* __LINUX_OVERFLOW_H */ -- cgit v1.2.3 From 49b7f8983aa78581bfd511a26891b26cd734e293 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 8 May 2018 12:52:32 -0700 Subject: mm: Use overflow helpers in kmalloc_array*() Instead of open-coded multiplication and bounds checking, use the new overflow helper. Suggested-by: Rasmus Villemoes Signed-off-by: Kees Cook --- include/linux/slab.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 81ebd71f8c03..4d759e1ddc33 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -13,6 +13,7 @@ #define _LINUX_SLAB_H #include +#include #include #include @@ -624,11 +625,13 @@ int memcg_update_all_caches(int num_memcgs); */ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) { - if (size != 0 && n > SIZE_MAX / size) + size_t bytes; + + if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) - return kmalloc(n * size, flags); - return __kmalloc(n * size, flags); + return kmalloc(bytes, flags); + return __kmalloc(bytes, flags); } /** @@ -657,11 +660,13 @@ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long); static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, int node) { - if (size != 0 && n > SIZE_MAX / size) + size_t bytes; + + if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) - return kmalloc_node(n * size, flags, node); - return __kmalloc_node(n * size, flags, node); + return kmalloc_node(bytes, flags, node); + return __kmalloc_node(bytes, flags, node); } static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) -- cgit v1.2.3 From 3b3b1a29eb89ba93f91213cbebb332a2ac31fa8b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 8 May 2018 12:55:26 -0700 Subject: mm: Use overflow helpers in kvmalloc() Instead of open-coded multiplication and bounds checking, use the new overflow helper. Additionally prepare for vmalloc() users to add array_size()-family helpers in the future. Signed-off-by: Kees Cook --- include/linux/mm.h | 7 +++++-- include/linux/vmalloc.h | 1 + 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1ac1f06a4be6..7cb1c6a6bf82 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -25,6 +25,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -560,10 +561,12 @@ static inline void *kvzalloc(size_t size, gfp_t flags) static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) { - if (size != 0 && n > SIZE_MAX / size) + size_t bytes; + + if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; - return kvmalloc(n * size, flags); + return kvmalloc(bytes, flags); } extern void kvfree(const void *addr); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 1e5d8c392f15..398e9c95cd61 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -8,6 +8,7 @@ #include #include /* pgprot_t */ #include +#include struct vm_area_struct; /* vma defining user mapping in mm_types.h */ struct notifier_block; /* in notifier.h */ -- cgit v1.2.3 From 2509b561f7c6599907c08cb364c86b8c45466e4f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 8 May 2018 22:29:52 -0700 Subject: device: Use overflow helpers for devm_kmalloc() Use the overflow helpers both in existing multiplication-using inlines as well as the addition-overflow case in the core allocation routine. Signed-off-by: Kees Cook --- include/linux/device.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 477956990f5e..897efa647203 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -25,6 +25,7 @@ #include #include #include +#include #include struct device; @@ -668,9 +669,12 @@ static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) static inline void *devm_kmalloc_array(struct device *dev, size_t n, size_t size, gfp_t flags) { - if (size != 0 && n > SIZE_MAX / size) + size_t bytes; + + if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; - return devm_kmalloc(dev, n * size, flags); + + return devm_kmalloc(dev, bytes, flags); } static inline void *devm_kcalloc(struct device *dev, size_t n, size_t size, gfp_t flags) -- cgit v1.2.3 From 7aaa822ed060719bd4ea012609883b6bc6950508 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 14 May 2018 15:50:52 -0700 Subject: pstore: Convert internal records to timespec64 This prepares pstore for converting the VFS layer to timespec64. Signed-off-by: Kees Cook Signed-off-by: Deepa Dinamani --- include/linux/pstore.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 61f806a7fe29..a15bc4d48752 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -71,7 +71,7 @@ struct pstore_record { struct pstore_info *psi; enum pstore_type_id type; u64 id; - struct timespec time; + struct timespec64 time; char *buf; ssize_t size; ssize_t ecc_notice_size; -- cgit v1.2.3 From 95582b00838837fc07e042979320caf917ce3fe6 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Tue, 8 May 2018 19:36:02 -0700 Subject: vfs: change inode times to use struct timespec64 struct timespec is not y2038 safe. Transition vfs to use y2038 safe struct timespec64 instead. The change was made with the help of the following cocinelle script. This catches about 80% of the changes. All the header file and logic changes are included in the first 5 rules. The rest are trivial substitutions. I avoid changing any of the function signatures or any other filesystem specific data structures to keep the patch simple for review. The script can be a little shorter by combining different cases. But, this version was sufficient for my usecase. virtual patch @ depends on patch @ identifier now; @@ - struct timespec + struct timespec64 current_time ( ... ) { - struct timespec now = current_kernel_time(); + struct timespec64 now = current_kernel_time64(); ... - return timespec_trunc( + return timespec64_trunc( ... ); } @ depends on patch @ identifier xtime; @@ struct \( iattr \| inode \| kstat \) { ... - struct timespec xtime; + struct timespec64 xtime; ... } @ depends on patch @ identifier t; @@ struct inode_operations { ... int (*update_time) (..., - struct timespec t, + struct timespec64 t, ...); ... } @ depends on patch @ identifier t; identifier fn_update_time =~ "update_time$"; @@ fn_update_time (..., - struct timespec *t, + struct timespec64 *t, ...) { ... } @ depends on patch @ identifier t; @@ lease_get_mtime( ... , - struct timespec *t + struct timespec64 *t ) { ... } @te depends on patch forall@ identifier ts; local idexpression struct inode *inode_node; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn_update_time =~ "update_time$"; identifier fn; expression e, E3; local idexpression struct inode *node1; local idexpression struct inode *node2; local idexpression struct iattr *attr1; local idexpression struct iattr *attr2; local idexpression struct iattr attr; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; @@ ( ( - struct timespec ts; + struct timespec64 ts; | - struct timespec ts = current_time(inode_node); + struct timespec64 ts = current_time(inode_node); ) <+... when != ts ( - timespec_equal(&inode_node->i_xtime, &ts) + timespec64_equal(&inode_node->i_xtime, &ts) | - timespec_equal(&ts, &inode_node->i_xtime) + timespec64_equal(&ts, &inode_node->i_xtime) | - timespec_compare(&inode_node->i_xtime, &ts) + timespec64_compare(&inode_node->i_xtime, &ts) | - timespec_compare(&ts, &inode_node->i_xtime) + timespec64_compare(&ts, &inode_node->i_xtime) | ts = current_time(e) | fn_update_time(..., &ts,...) | inode_node->i_xtime = ts | node1->i_xtime = ts | ts = inode_node->i_xtime | <+... attr1->ia_xtime ...+> = ts | ts = attr1->ia_xtime | ts.tv_sec | ts.tv_nsec | btrfs_set_stack_timespec_sec(..., ts.tv_sec) | btrfs_set_stack_timespec_nsec(..., ts.tv_nsec) | - ts = timespec64_to_timespec( + ts = ... -) | - ts = ktime_to_timespec( + ts = ktime_to_timespec64( ...) | - ts = E3 + ts = timespec_to_timespec64(E3) | - ktime_get_real_ts(&ts) + ktime_get_real_ts64(&ts) | fn(..., - ts + timespec64_to_timespec(ts) ,...) ) ...+> ( <... when != ts - return ts; + return timespec64_to_timespec(ts); ...> ) | - timespec_equal(&node1->i_xtime1, &node2->i_xtime2) + timespec64_equal(&node1->i_xtime2, &node2->i_xtime2) | - timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2) + timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2) | - timespec_compare(&node1->i_xtime1, &node2->i_xtime2) + timespec64_compare(&node1->i_xtime1, &node2->i_xtime2) | node1->i_xtime1 = - timespec_trunc(attr1->ia_xtime1, + timespec64_trunc(attr1->ia_xtime1, ...) | - attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2, + attr1->ia_xtime1 = timespec64_trunc(attr2->ia_xtime2, ...) | - ktime_get_real_ts(&attr1->ia_xtime1) + ktime_get_real_ts64(&attr1->ia_xtime1) | - ktime_get_real_ts(&attr.ia_xtime1) + ktime_get_real_ts64(&attr.ia_xtime1) ) @ depends on patch @ struct inode *node; struct iattr *attr; identifier fn; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; expression e; @@ ( - fn(node->i_xtime); + fn(timespec64_to_timespec(node->i_xtime)); | fn(..., - node->i_xtime); + timespec64_to_timespec(node->i_xtime)); | - e = fn(attr->ia_xtime); + e = fn(timespec64_to_timespec(attr->ia_xtime)); ) @ depends on patch forall @ struct inode *node; struct iattr *attr; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); fn (..., - &attr->ia_xtime, + &ts, ...); ) ...+> } @ depends on patch forall @ struct inode *node; struct iattr *attr; struct kstat *stat; identifier ia_xtime =~ "^ia_[acm]time$"; identifier i_xtime =~ "^i_[acm]time$"; identifier xtime =~ "^[acm]time$"; identifier fn, ret; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime); + &ts); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime); + &ts); | + ts = timespec64_to_timespec(stat->xtime); ret = fn (..., - &stat->xtime); + &ts); ) ...+> } @ depends on patch @ struct inode *node; struct inode *node2; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier i_xtime3 =~ "^i_[acm]time$"; struct iattr *attrp; struct iattr *attrp2; struct iattr attr ; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; struct kstat *stat; struct kstat stat1; struct timespec64 ts; identifier xtime =~ "^[acmb]time$"; expression e; @@ ( ( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1 ; | node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | stat->xtime = node2->i_xtime1; | stat1.xtime = node2->i_xtime1; | ( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1 ; | ( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2; | - e = node->i_xtime1; + e = timespec64_to_timespec( node->i_xtime1 ); | - e = attrp->ia_xtime1; + e = timespec64_to_timespec( attrp->ia_xtime1 ); | node->i_xtime1 = current_time(...); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | - node->i_xtime1 = e; + node->i_xtime1 = timespec_to_timespec64(e); ) Signed-off-by: Deepa Dinamani Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: --- include/linux/fs.h | 23 ++++++++++++----------- include/linux/stat.h | 8 ++++---- 2 files changed, 16 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7f6997e0dabf..f15329aa9cad 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -206,9 +206,9 @@ struct iattr { kuid_t ia_uid; kgid_t ia_gid; loff_t ia_size; - struct timespec ia_atime; - struct timespec ia_mtime; - struct timespec ia_ctime; + struct timespec64 ia_atime; + struct timespec64 ia_mtime; + struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to @@ -602,9 +602,9 @@ struct inode { }; dev_t i_rdev; loff_t i_size; - struct timespec i_atime; - struct timespec i_mtime; - struct timespec i_ctime; + struct timespec64 i_atime; + struct timespec64 i_mtime; + struct timespec64 i_ctime; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; unsigned int i_blkbits; @@ -1091,7 +1091,7 @@ extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); -extern void lease_get_mtime(struct inode *, struct timespec *time); +extern void lease_get_mtime(struct inode *, struct timespec64 *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); extern int vfs_setlease(struct file *, long, struct file_lock **, void **); extern int lease_modify(struct file_lock *, int, struct list_head *); @@ -1206,7 +1206,8 @@ static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned return 0; } -static inline void lease_get_mtime(struct inode *inode, struct timespec *time) +static inline void lease_get_mtime(struct inode *inode, + struct timespec64 *time) { return; } @@ -1477,7 +1478,7 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) } extern struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran); -extern struct timespec current_time(struct inode *inode); +extern struct timespec64 current_time(struct inode *inode); /* * Snapshotting support. @@ -1765,7 +1766,7 @@ struct inode_operations { ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); - int (*update_time)(struct inode *, struct timespec *, int); + int (*update_time)(struct inode *, struct timespec64 *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode, int *opened); @@ -2199,7 +2200,7 @@ extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); -extern int generic_update_time(struct inode *, struct timespec *, int); +extern int generic_update_time(struct inode *, struct timespec64 *, int); /* /sys/fs */ extern struct kobject *fs_kobj; diff --git a/include/linux/stat.h b/include/linux/stat.h index 22484e44544d..765573dc17d6 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -41,10 +41,10 @@ struct kstat { kuid_t uid; kgid_t gid; loff_t size; - struct timespec atime; - struct timespec mtime; - struct timespec ctime; - struct timespec btime; /* File creation time */ + struct timespec64 atime; + struct timespec64 mtime; + struct timespec64 ctime; + struct timespec64 btime; /* File creation time */ u64 blocks; }; -- cgit v1.2.3 From 3c095f32a92be4d07f3172a777dab1aacdb6a728 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 31 May 2018 12:59:58 +0200 Subject: PM / Domains: Add support for multi PM domains per device to genpd To support devices being partitioned across multiple PM domains, let's begin with extending genpd to cope with these kind of configurations. Therefore, add a new exported function genpd_dev_pm_attach_by_id(), which is similar to the existing genpd_dev_pm_attach(), but with the difference that it allows its callers to provide an index to the PM domain that it wants to attach. Note that, genpd_dev_pm_attach_by_id() shall only be called by the driver core / PM core, similar to how the existing dev_pm_domain_attach() makes use of genpd_dev_pm_attach(). However, this is implemented by following changes on top. Because, only one PM domain can be attached per device, genpd needs to create a virtual device that it can attach/detach instead. More precisely, let the new function genpd_dev_pm_attach_by_id() register a virtual struct device via calling device_register(). Then let it attach this device to the corresponding PM domain, rather than the one that is provided by the caller. The actual attaching is done via re-using the existing genpd OF functions. At successful attachment, genpd_dev_pm_attach_by_id() returns the created virtual device, which allows the caller to operate on it to deal with power management. Following changes on top, provides more details in this regards. To deal with detaching of a PM domain for the multiple PM domains case, let's also extend the existing genpd_dev_pm_detach() function, to cover the cleanup of the created virtual device, via make it call device_unregister() on it. In this way, there is no need to introduce a new function to deal with detach for the multiple PM domain case, but instead the existing one is re-used. Signed-off-by: Ulf Hansson Acked-by: Jon Hunter Tested-by: Jon Hunter Reviewed-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 42e0d649e653..82458e8e2e01 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -237,6 +237,8 @@ unsigned int of_genpd_opp_to_performance_state(struct device *dev, struct device_node *opp_node); int genpd_dev_pm_attach(struct device *dev); +struct device *genpd_dev_pm_attach_by_id(struct device *dev, + unsigned int index); #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */ static inline int of_genpd_add_provider_simple(struct device_node *np, struct generic_pm_domain *genpd) @@ -282,6 +284,12 @@ static inline int genpd_dev_pm_attach(struct device *dev) return 0; } +static inline struct device *genpd_dev_pm_attach_by_id(struct device *dev, + unsigned int index) +{ + return NULL; +} + static inline struct generic_pm_domain *of_genpd_remove_last(struct device_node *np) { -- cgit v1.2.3 From 82e12d9e0bd59f3d24be9c735258e2e98e4f54f6 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 31 May 2018 12:59:59 +0200 Subject: PM / Domains: Add dev_pm_domain_attach_by_id() to manage multi PM domains The existing dev_pm_domain_attach() function, allows a single PM domain to be attached per device. To be able to support devices that are partitioned across multiple PM domains, let's introduce a new interface, dev_pm_domain_attach_by_id(). The dev_pm_domain_attach_by_id() returns a new allocated struct device with the corresponding attached PM domain. This enables for example a driver to operate on the new device from a power management point of view. The driver may then also benefit from using the received device, to set up so called device-links towards its original device. Depending on the situation, these links may then be dynamically changed. The new interface is typically called by drivers during their probe phase, in case they manages devices which uses multiple PM domains. If that is the case, the driver also becomes responsible of managing the detaching of the PM domains, which typically should be done at the remove phase. Detaching is done by calling the existing dev_pm_domain_detach() function and for each of the received devices from dev_pm_domain_attach_by_id(). Note, currently its only genpd that supports multiple PM domains per device, but dev_pm_domain_attach_by_id() can easily by extended to cover other PM domain types, if/when needed. Signed-off-by: Ulf Hansson Acked-by: Jon Hunter Tested-by: Jon Hunter Reviewed-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 82458e8e2e01..9206a4fef9ac 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -299,6 +299,8 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np) #ifdef CONFIG_PM int dev_pm_domain_attach(struct device *dev, bool power_on); +struct device *dev_pm_domain_attach_by_id(struct device *dev, + unsigned int index); void dev_pm_domain_detach(struct device *dev, bool power_off); void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd); #else @@ -306,6 +308,11 @@ static inline int dev_pm_domain_attach(struct device *dev, bool power_on) { return 0; } +static inline struct device *dev_pm_domain_attach_by_id(struct device *dev, + unsigned int index) +{ + return NULL; +} static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {} static inline void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd) {} -- cgit v1.2.3 From d7822b1e24f2df5df98c76f0e94a5416349ff759 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Sat, 2 Jun 2018 08:43:54 -0400 Subject: rseq: Introduce restartable sequences system call Expose a new system call allowing each thread to register one userspace memory area to be used as an ABI between kernel and user-space for two purposes: user-space restartable sequences and quick access to read the current CPU number value from user-space. * Restartable sequences (per-cpu atomics) Restartables sequences allow user-space to perform update operations on per-cpu data without requiring heavy-weight atomic operations. The restartable critical sections (percpu atomics) work has been started by Paul Turner and Andrew Hunter. It lets the kernel handle restart of critical sections. [1] [2] The re-implementation proposed here brings a few simplifications to the ABI which facilitates porting to other architectures and speeds up the user-space fast path. Here are benchmarks of various rseq use-cases. Test hardware: arm32: ARMv7 Processor rev 4 (v7l) "Cubietruck", 2-core x86-64: Intel E5-2630 v3@2.40GHz, 16-core, hyperthreading The following benchmarks were all performed on a single thread. * Per-CPU statistic counter increment getcpu+atomic (ns/op) rseq (ns/op) speedup arm32: 344.0 31.4 11.0 x86-64: 15.3 2.0 7.7 * LTTng-UST: write event 32-bit header, 32-bit payload into tracer per-cpu buffer getcpu+atomic (ns/op) rseq (ns/op) speedup arm32: 2502.0 2250.0 1.1 x86-64: 117.4 98.0 1.2 * liburcu percpu: lock-unlock pair, dereference, read/compare word getcpu+atomic (ns/op) rseq (ns/op) speedup arm32: 751.0 128.5 5.8 x86-64: 53.4 28.6 1.9 * jemalloc memory allocator adapted to use rseq Using rseq with per-cpu memory pools in jemalloc at Facebook (based on rseq 2016 implementation): The production workload response-time has 1-2% gain avg. latency, and the P99 overall latency drops by 2-3%. * Reading the current CPU number Speeding up reading the current CPU number on which the caller thread is running is done by keeping the current CPU number up do date within the cpu_id field of the memory area registered by the thread. This is done by making scheduler preemption set the TIF_NOTIFY_RESUME flag on the current thread. Upon return to user-space, a notify-resume handler updates the current CPU value within the registered user-space memory area. User-space can then read the current CPU number directly from memory. Keeping the current cpu id in a memory area shared between kernel and user-space is an improvement over current mechanisms available to read the current CPU number, which has the following benefits over alternative approaches: - 35x speedup on ARM vs system call through glibc - 20x speedup on x86 compared to calling glibc, which calls vdso executing a "lsl" instruction, - 14x speedup on x86 compared to inlined "lsl" instruction, - Unlike vdso approaches, this cpu_id value can be read from an inline assembly, which makes it a useful building block for restartable sequences. - The approach of reading the cpu id through memory mapping shared between kernel and user-space is portable (e.g. ARM), which is not the case for the lsl-based x86 vdso. On x86, yet another possible approach would be to use the gs segment selector to point to user-space per-cpu data. This approach performs similarly to the cpu id cache, but it has two disadvantages: it is not portable, and it is incompatible with existing applications already using the gs segment selector for other purposes. Benchmarking various approaches for reading the current CPU number: ARMv7 Processor rev 4 (v7l) Machine model: Cubietruck - Baseline (empty loop): 8.4 ns - Read CPU from rseq cpu_id: 16.7 ns - Read CPU from rseq cpu_id (lazy register): 19.8 ns - glibc 2.19-0ubuntu6.6 getcpu: 301.8 ns - getcpu system call: 234.9 ns x86-64 Intel(R) Xeon(R) CPU E5-2630 v3 @ 2.40GHz: - Baseline (empty loop): 0.8 ns - Read CPU from rseq cpu_id: 0.8 ns - Read CPU from rseq cpu_id (lazy register): 0.8 ns - Read using gs segment selector: 0.8 ns - "lsl" inline assembly: 13.0 ns - glibc 2.19-0ubuntu6 getcpu: 16.6 ns - getcpu system call: 53.9 ns - Speed (benchmark taken on v8 of patchset) Running 10 runs of hackbench -l 100000 seems to indicate, contrary to expectations, that enabling CONFIG_RSEQ slightly accelerates the scheduler: Configuration: 2 sockets * 8-core Intel(R) Xeon(R) CPU E5-2630 v3 @ 2.40GHz (directly on hardware, hyperthreading disabled in BIOS, energy saving disabled in BIOS, turboboost disabled in BIOS, cpuidle.off=1 kernel parameter), with a Linux v4.6 defconfig+localyesconfig, restartable sequences series applied. * CONFIG_RSEQ=n avg.: 41.37 s std.dev.: 0.36 s * CONFIG_RSEQ=y avg.: 40.46 s std.dev.: 0.33 s - Size On x86-64, between CONFIG_RSEQ=n/y, the text size increase of vmlinux is 567 bytes, and the data size increase of vmlinux is 5696 bytes. [1] https://lwn.net/Articles/650333/ [2] http://www.linuxplumbersconf.org/2013/ocw/system/presentations/1695/original/LPC%20-%20PerCpu%20Atomics.pdf Signed-off-by: Mathieu Desnoyers Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Joel Fernandes Cc: Catalin Marinas Cc: Dave Watson Cc: Will Deacon Cc: Andi Kleen Cc: "H . Peter Anvin" Cc: Chris Lameter Cc: Russell King Cc: Andrew Hunter Cc: Michael Kerrisk Cc: "Paul E . McKenney" Cc: Paul Turner Cc: Boqun Feng Cc: Josh Triplett Cc: Steven Rostedt Cc: Ben Maurer Cc: Alexander Viro Cc: linux-api@vger.kernel.org Cc: Andy Lutomirski Cc: Andrew Morton Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20151027235635.16059.11630.stgit@pjt-glaptop.roam.corp.google.com Link: http://lkml.kernel.org/r/20150624222609.6116.86035.stgit@kitami.mtv.corp.google.com Link: https://lkml.kernel.org/r/20180602124408.8430-3-mathieu.desnoyers@efficios.com --- include/linux/sched.h | 134 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/syscalls.h | 4 +- 2 files changed, 137 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 14e4f9c12337..3aa4fcb74e76 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -27,6 +27,7 @@ #include #include #include +#include /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; @@ -1047,6 +1048,17 @@ struct task_struct { unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_RSEQ + struct rseq __user *rseq; + u32 rseq_len; + u32 rseq_sig; + /* + * RmW on rseq_event_mask must be performed atomically + * with respect to preemption. + */ + unsigned long rseq_event_mask; +#endif + struct tlbflush_unmap_batch tlb_ubc; struct rcu_head rcu; @@ -1757,4 +1769,126 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #define TASK_SIZE_OF(tsk) TASK_SIZE #endif +#ifdef CONFIG_RSEQ + +/* + * Map the event mask on the user-space ABI enum rseq_cs_flags + * for direct mask checks. + */ +enum rseq_event_mask_bits { + RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, + RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, + RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, +}; + +enum rseq_event_mask { + RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), + RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), + RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), +}; + +static inline void rseq_set_notify_resume(struct task_struct *t) +{ + if (t->rseq) + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); +} + +void __rseq_handle_notify_resume(struct pt_regs *regs); + +static inline void rseq_handle_notify_resume(struct pt_regs *regs) +{ + if (current->rseq) + __rseq_handle_notify_resume(regs); +} + +static inline void rseq_signal_deliver(struct pt_regs *regs) +{ + preempt_disable(); + __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); + preempt_enable(); + rseq_handle_notify_resume(regs); +} + +/* rseq_preempt() requires preemption to be disabled. */ +static inline void rseq_preempt(struct task_struct *t) +{ + __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); + rseq_set_notify_resume(t); +} + +/* rseq_migrate() requires preemption to be disabled. */ +static inline void rseq_migrate(struct task_struct *t) +{ + __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); + rseq_set_notify_resume(t); +} + +/* + * If parent process has a registered restartable sequences area, the + * child inherits. Only applies when forking a process, not a thread. In + * case a parent fork() in the middle of a restartable sequence, set the + * resume notifier to force the child to retry. + */ +static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +{ + if (clone_flags & CLONE_THREAD) { + t->rseq = NULL; + t->rseq_len = 0; + t->rseq_sig = 0; + t->rseq_event_mask = 0; + } else { + t->rseq = current->rseq; + t->rseq_len = current->rseq_len; + t->rseq_sig = current->rseq_sig; + t->rseq_event_mask = current->rseq_event_mask; + rseq_preempt(t); + } +} + +static inline void rseq_execve(struct task_struct *t) +{ + t->rseq = NULL; + t->rseq_len = 0; + t->rseq_sig = 0; + t->rseq_event_mask = 0; +} + +#else + +static inline void rseq_set_notify_resume(struct task_struct *t) +{ +} +static inline void rseq_handle_notify_resume(struct pt_regs *regs) +{ +} +static inline void rseq_signal_deliver(struct pt_regs *regs) +{ +} +static inline void rseq_preempt(struct task_struct *t) +{ +} +static inline void rseq_migrate(struct task_struct *t) +{ +} +static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +{ +} +static inline void rseq_execve(struct task_struct *t) +{ +} + +#endif + +#ifdef CONFIG_DEBUG_RSEQ + +void rseq_syscall(struct pt_regs *regs); + +#else + +static inline void rseq_syscall(struct pt_regs *regs) +{ +} + +#endif + #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 390e814fdc8d..73810808cdf2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -66,6 +66,7 @@ struct old_linux_dirent; struct perf_event_attr; struct file_handle; struct sigaltstack; +struct rseq; union bpf_attr; #include @@ -897,7 +898,8 @@ asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val); asmlinkage long sys_pkey_free(int pkey); asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, unsigned mask, struct statx __user *buffer); - +asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len, + int flags, uint32_t sig); /* * Architecture-specific system calls -- cgit v1.2.3 From bd975e691486ba52790ba23cc9b4fecab7bc0d31 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 31 May 2018 18:45:21 +0200 Subject: netfilter: ipset: List timing out entries with "timeout 1" instead of zero When listing sets with timeout support, there's a probability that just timing out entries with "0" timeout value is listed/saved. However when restoring the saved list, the zero timeout value means permanent elelements. The new behaviour is that timing out entries are listed with "timeout 1" instead of zero. Fixes netfilter bugzilla #1258. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set_timeout.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h index bfb3531fd88a..7ad8ddf9ca8a 100644 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -65,8 +65,14 @@ ip_set_timeout_set(unsigned long *timeout, u32 value) static inline u32 ip_set_timeout_get(const unsigned long *timeout) { - return *timeout == IPSET_ELEM_PERMANENT ? 0 : - jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; + u32 t; + + if (*timeout == IPSET_ELEM_PERMANENT) + return 0; + + t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; + /* Zero value in userspace means no timeout */ + return t == 0 ? 1 : t; } #endif /* __KERNEL__ */ -- cgit v1.2.3 From 30a2e107108c66cbcb7776b58cbcd7db223a1cc9 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 5 Jun 2018 11:53:35 +0200 Subject: netfilter: ipset: Limit max timeout value Due to the negative value condition in msecs_to_jiffies(), the real max possible timeout value must be set to (UINT_MAX >> 1)/MSEC_PER_SEC. Neutron Soutmun proposed the proper fix, but an insufficient one was applied, see https://patchwork.ozlabs.org/patch/400405/. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set_timeout.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h index 7ad8ddf9ca8a..8ce271e187b6 100644 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -23,6 +23,9 @@ /* Set is defined with timeout support: timeout value may be 0 */ #define IPSET_NO_TIMEOUT UINT_MAX +/* Max timeout value, see msecs_to_jiffies() in jiffies.h */ +#define IPSET_MAX_TIMEOUT (UINT_MAX >> 1)/MSEC_PER_SEC + #define ip_set_adt_opt_timeout(opt, set) \ ((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (set)->timeout) @@ -32,11 +35,10 @@ ip_set_timeout_uget(struct nlattr *tb) unsigned int timeout = ip_set_get_h32(tb); /* Normalize to fit into jiffies */ - if (timeout > UINT_MAX/MSEC_PER_SEC) - timeout = UINT_MAX/MSEC_PER_SEC; + if (timeout > IPSET_MAX_TIMEOUT) + timeout = IPSET_MAX_TIMEOUT; - /* Userspace supplied TIMEOUT parameter: adjust crazy size */ - return timeout == IPSET_NO_TIMEOUT ? IPSET_NO_TIMEOUT - 1 : timeout; + return timeout; } static inline bool -- cgit v1.2.3 From d340ebd696f921d3ad01b8c0c29dd38f2ad2bf3e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 6 Jun 2018 14:46:59 +0200 Subject: genirq/migration: Avoid out of line call if pending is not set The upcoming fix for the -EBUSY return from affinity settings requires to use the irq_move_irq() functionality even on irq remapped interrupts. To avoid the out of line call, move the check for the pending bit into an inline helper. Preparatory change for the real fix. No functional change. Fixes: dccfe3147b42 ("x86/vector: Simplify vector move cleanup") Signed-off-by: Thomas Gleixner Cc: Joerg Roedel Cc: Peter Zijlstra Cc: Song Liu Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: stable@vger.kernel.org Cc: Mike Travis Cc: Borislav Petkov Cc: Tariq Toukan Cc: Dou Liyang Link: https://lkml.kernel.org/r/20180604162224.471925894@linutronix.de --- include/linux/irq.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 65916a305f3d..4e66378f290b 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -551,7 +551,12 @@ extern int irq_affinity_online_cpu(unsigned int cpu); #endif #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ) -void irq_move_irq(struct irq_data *data); +void __irq_move_irq(struct irq_data *data); +static inline void irq_move_irq(struct irq_data *data) +{ + if (unlikely(irqd_is_setaffinity_pending(data))) + __irq_move_irq(data); +} void irq_move_masked_irq(struct irq_data *data); void irq_force_complete_move(struct irq_desc *desc); #else -- cgit v1.2.3 From e536700ef5bf9788af185bf890a52f296d055ed7 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 7 Jun 2018 14:10:56 +0100 Subject: regulator: gpio: Revert regulator: fixed/gpio: Revert GPIO descriptor changes due to platform breakage Commit 6059577cb28 "regulator: fixed: Convert to use GPIO descriptor only" broke at least the ams-delta platform since the lookup tables added to the board files use the function name "enable" while the driver uses NULL causing the regulator to not acquire and control the enable GPIOs. Revert that and a couple of other commits that are caught up with it to fix the issue: 2b6c00c157c5bf80 "ARM: pxa, regulator: fix building ezx e680" 6059577cb28d8b15 "regulator: fixed: Convert to use GPIO descriptor only" 37bed97f00734ce3 "regulator: gpio: Get enable GPIO using GPIO descriptor" Reported-by: Janusz Krzysztofik Signed-off-by: Mark Brown --- include/linux/regulator/fixed.h | 3 +++ include/linux/regulator/gpio-regulator.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h index 1a4340ed8e2b..48918be649d4 100644 --- a/include/linux/regulator/fixed.h +++ b/include/linux/regulator/fixed.h @@ -24,6 +24,8 @@ struct regulator_init_data; * @supply_name: Name of the regulator supply * @input_supply: Name of the input regulator supply * @microvolts: Output voltage of regulator + * @gpio: GPIO to use for enable control + * set to -EINVAL if not used * @startup_delay: Start-up time in microseconds * @gpio_is_open_drain: Gpio pin is open drain or normal type. * If it is open drain type then HIGH will be set @@ -47,6 +49,7 @@ struct fixed_voltage_config { const char *supply_name; const char *input_supply; int microvolts; + int gpio; unsigned startup_delay; unsigned gpio_is_open_drain:1; unsigned enable_high:1; diff --git a/include/linux/regulator/gpio-regulator.h b/include/linux/regulator/gpio-regulator.h index 536cab86f2d5..19fbd267406d 100644 --- a/include/linux/regulator/gpio-regulator.h +++ b/include/linux/regulator/gpio-regulator.h @@ -44,6 +44,8 @@ struct gpio_regulator_state { /** * struct gpio_regulator_config - config structure * @supply_name: Name of the regulator supply + * @enable_gpio: GPIO to use for enable control + * set to -EINVAL if not used * @enable_high: Polarity of enable GPIO * 1 = Active high, 0 = Active low * @enabled_at_boot: Whether regulator has been enabled at @@ -67,6 +69,7 @@ struct gpio_regulator_state { struct gpio_regulator_config { const char *supply_name; + int enable_gpio; unsigned enable_high:1; unsigned enabled_at_boot:1; unsigned startup_delay; -- cgit v1.2.3 From 55e49dc43a835b19567e62142cb1c87dc7db7b3c Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 19 Apr 2018 20:29:41 +0300 Subject: virtio_ring: switch to dma_XX barriers for rpmsg virtio is using barriers to order memory accesses, thus dma_wmb/rmb is a good match. Before [mst@tuck linux]$ size drivers/virtio/virtio_ring.o text data bss dec hex filename 11392 820 0 12212 2fb4 drivers/virtio/virtio_ring.o After mst@tuck linux]$ size drivers/virtio/virtio_ring.o text data bss dec hex filename 11284 820 0 12104 2f48 drivers/virtio/virtio_ring.o Cc: Ohad Ben-Cohen Cc: Bjorn Andersson Cc: linux-remoteproc@vger.kernel.org Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_ring.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index bbf32524ab27..fab02133a919 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -35,7 +35,7 @@ static inline void virtio_rmb(bool weak_barriers) if (weak_barriers) virt_rmb(); else - rmb(); + dma_rmb(); } static inline void virtio_wmb(bool weak_barriers) @@ -43,7 +43,7 @@ static inline void virtio_wmb(bool weak_barriers) if (weak_barriers) virt_wmb(); else - wmb(); + dma_wmb(); } static inline void virtio_store_mb(bool weak_barriers, -- cgit v1.2.3 From fd3a88625844907151737fc3b4201676effa6d27 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 6 Jun 2018 11:23:01 -0400 Subject: net: in virtio_net_hdr only add VLAN_HLEN to csum_start if payload holds vlan Tun, tap, virtio, packet and uml vector all use struct virtio_net_hdr to communicate packet metadata to userspace. For skbuffs with vlan, the first two return the packet as it may have existed on the wire, inserting the VLAN tag in the user buffer. Then virtio_net_hdr.csum_start needs to be adjusted by VLAN_HLEN bytes. Commit f09e2249c4f5 ("macvtap: restore vlan header on user read") added this feature to macvtap. Commit 3ce9b20f1971 ("macvtap: Fix csum_start when VLAN tags are present") then fixed up csum_start. Virtio, packet and uml do not insert the vlan header in the user buffer. When introducing virtio_net_hdr_from_skb to deduplicate filling in the virtio_net_hdr, the variant from macvtap which adds VLAN_HLEN was applied uniformly, breaking csum offset for packets with vlan on virtio and packet. Make insertion of VLAN_HLEN optional. Convert the callers to pass it when needed. Fixes: e858fae2b0b8f4 ("virtio_net: use common code for virtio_net_hdr and skb GSO conversion") Fixes: 1276f24eeef2 ("packet: use common code for virtio_net_hdr and skb GSO conversion") Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index f144216febc6..9397628a1967 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -58,7 +58,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian, - bool has_data_valid) + bool has_data_valid, + int vlan_hlen) { memset(hdr, 0, sizeof(*hdr)); /* no info leak */ @@ -83,12 +84,8 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_PARTIAL) { hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; - if (skb_vlan_tag_present(skb)) - hdr->csum_start = __cpu_to_virtio16(little_endian, - skb_checksum_start_offset(skb) + VLAN_HLEN); - else - hdr->csum_start = __cpu_to_virtio16(little_endian, - skb_checksum_start_offset(skb)); + hdr->csum_start = __cpu_to_virtio16(little_endian, + skb_checksum_start_offset(skb) + vlan_hlen); hdr->csum_offset = __cpu_to_virtio16(little_endian, skb->csum_offset); } else if (has_data_valid && -- cgit v1.2.3 From ab77dab46210bb630e06c6803c5d84074bacd351 Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Thu, 7 Jun 2018 17:04:29 -0700 Subject: fs/dax.c: use new return type vm_fault_t Use new return type vm_fault_t for fault handler. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. commit 1c8f422059ae ("mm: change return type to vm_fault_t") There was an existing bug inside dax_load_hole() if vm_insert_mixed had failed to allocate a page table, we'd return VM_FAULT_NOPAGE instead of VM_FAULT_OOM. With new vmf_insert_mixed() this issue is addressed. vm_insert_mixed_mkwrite has inefficiency when it returns an error value, driver has to convert it to vm_fault_t type. With new vmf_insert_mixed_mkwrite() this limitation will be addressed. Link: http://lkml.kernel.org/r/20180510181121.GA15239@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Jan Kara Reviewed-by: Matthew Wilcox Reviewed-by: Ross Zwisler Cc: Alexander Viro Cc: Dan Williams Cc: Michal Hocko Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dax.h | 4 ++-- include/linux/mm.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index c99692ddd4b5..88504e87cd6c 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -125,8 +125,8 @@ ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, pfn_t *pfnp, int *errp, const struct iomap_ops *ops); -int dax_finish_sync_fault(struct vm_fault *vmf, enum page_entry_size pe_size, - pfn_t pfn); +vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, + enum page_entry_size pe_size, pfn_t pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); diff --git a/include/linux/mm.h b/include/linux/mm.h index 0495e6f97fae..b7012bb1d218 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2431,8 +2431,8 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); -int vm_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn); +vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, + unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, -- cgit v1.2.3 From 05fec35ebb0e0e1f4603cc241fdf65fd3abb3092 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Thu, 7 Jun 2018 17:05:24 -0700 Subject: slab: clean up the code comment in slab kmem_cache struct In commit 3b0efdfa1e7 ("mm, sl[aou]b: Extract common fields from struct kmem_cache") the variable 'obj_size' was moved above, however the related code comment is not updated accordingly. Do it here. Link: http://lkml.kernel.org/r/20180603032402.27526-1-bhe@redhat.com Signed-off-by: Baoquan He Reviewed-by: Andrew Morton Acked-by: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab_def.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index d9228e4d0320..3485c58cfd1c 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -67,9 +67,10 @@ struct kmem_cache { /* * If debugging is enabled, then the allocator can add additional - * fields and/or padding to every object. size contains the total - * object size including these internal fields, the following two - * variables contain the offset to the user object and its size. + * fields and/or padding to every object. 'size' contains the total + * object size including these internal fields, while 'obj_offset' + * and 'object_size' contain the offset to the user object and its + * size. */ int obj_offset; #endif /* CONFIG_DEBUG_SLAB */ -- cgit v1.2.3 From 88aa7cc688d48ddd84558b41d5905a0db9535c4b Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 7 Jun 2018 17:05:28 -0700 Subject: mm: introduce arg_lock to protect arg_start|end and env_start|end in mm_struct mmap_sem is on the hot path of kernel, and it very contended, but it is abused too. It is used to protect arg_start|end and evn_start|end when reading /proc/$PID/cmdline and /proc/$PID/environ, but it doesn't make sense since those proc files just expect to read 4 values atomically and not related to VM, they could be set to arbitrary values by C/R. And, the mmap_sem contention may cause unexpected issue like below: INFO: task ps:14018 blocked for more than 120 seconds. Tainted: G E 4.9.79-009.ali3000.alios7.x86_64 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. ps D 0 14018 1 0x00000004 Call Trace: schedule+0x36/0x80 rwsem_down_read_failed+0xf0/0x150 call_rwsem_down_read_failed+0x18/0x30 down_read+0x20/0x40 proc_pid_cmdline_read+0xd9/0x4e0 __vfs_read+0x37/0x150 vfs_read+0x96/0x130 SyS_read+0x55/0xc0 entry_SYSCALL_64_fastpath+0x1a/0xc5 Both Alexey Dobriyan and Michal Hocko suggested to use dedicated lock for them to mitigate the abuse of mmap_sem. So, introduce a new spinlock in mm_struct to protect the concurrent access to arg_start|end, env_start|end and others, as well as replace write map_sem to read to protect the race condition between prctl and sys_brk which might break check_data_rlimit(), and makes prctl more friendly to other VM operations. This patch just eliminates the abuse of mmap_sem, but it can't resolve the above hung task warning completely since the later access_remote_vm() call needs acquire mmap_sem. The mmap_sem scalability issue will be solved in the future. [yang.shi@linux.alibaba.com: add comment about mmap_sem and arg_lock] Link: http://lkml.kernel.org/r/1524077799-80690-1-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1523730291-109696-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Reviewed-by: Cyrill Gorcunov Acked-by: Michal Hocko Cc: Alexey Dobriyan Cc: Matthew Wilcox Cc: Mateusz Guzik Cc: Kirill Tkhai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 21612347d311..49dd59ea90f7 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -413,6 +413,8 @@ struct mm_struct { unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags; + + spinlock_t arg_lock; /* protect the below fields */ unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; -- cgit v1.2.3 From f3a53a3a1e5b3b9bc114b5b7930fbe89d9ffed5d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 7 Jun 2018 17:05:35 -0700 Subject: mm, memcontrol: implement memory.swap.events Add swap max and fail events so that userland can monitor and respond to running out of swap. I'm not too sure about the fail event. Right now, it's a bit confusing which stats / events are recursive and which aren't and also which ones reflect events which originate from a given cgroup and which targets the cgroup. No idea what the right long term solution is and it could just be that growing them organically is actually the only right thing to do. Link: http://lkml.kernel.org/r/20180416231151.GI1911913@devbig577.frc2.facebook.com Signed-off-by: Tejun Heo Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Roman Gushchin Cc: Rik van Riel Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d99b71bc2c66..517096c3cc99 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -53,6 +53,8 @@ enum memcg_memory_event { MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, + MEMCG_SWAP_MAX, + MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, }; @@ -208,6 +210,9 @@ struct mem_cgroup { atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; struct cgroup_file events_file; + /* handle for "memory.swap.events" */ + struct cgroup_file swap_events_file; + /* protect arrays of thresholds */ struct mutex thresholds_lock; -- cgit v1.2.3 From 5d752600a8c373382264392f5b573b2fc9c0e8ea Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Thu, 7 Jun 2018 17:06:01 -0700 Subject: mm: restructure memfd code With the addition of memfd hugetlbfs support, we now have the situation where memfd depends on TMPFS -or- HUGETLBFS. Previously, memfd was only supported on tmpfs, so it made sense that the code resided in shmem.c. In the current code, memfd is only functional if TMPFS is defined. If HUGETLFS is defined and TMPFS is not defined, then memfd functionality will not be available for hugetlbfs. This does not cause BUGs, just a lack of potentially desired functionality. Code is restructured in the following way: - include/linux/memfd.h is a new file containing memfd specific definitions previously contained in shmem_fs.h. - mm/memfd.c is a new file containing memfd specific code previously contained in shmem.c. - memfd specific code is removed from shmem_fs.h and shmem.c. - A new config option MEMFD_CREATE is added that is defined if TMPFS or HUGETLBFS is defined. No functional changes are made to the code: restructuring only. Link: http://lkml.kernel.org/r/20180415182119.4517-4-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Khalid Aziz Cc: Andrea Arcangeli Cc: David Herrmann Cc: Hugh Dickins Cc: Marc-Andr Lureau Cc: Matthew Wilcox Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memfd.h | 16 ++++++++++++++++ include/linux/shmem_fs.h | 13 ------------- 2 files changed, 16 insertions(+), 13 deletions(-) create mode 100644 include/linux/memfd.h (limited to 'include/linux') diff --git a/include/linux/memfd.h b/include/linux/memfd.h new file mode 100644 index 000000000000..4f1600413f91 --- /dev/null +++ b/include/linux/memfd.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_MEMFD_H +#define __LINUX_MEMFD_H + +#include + +#ifdef CONFIG_MEMFD_CREATE +extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg); +#else +static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned long a) +{ + return -EINVAL; +} +#endif + +#endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 73b5e655a76e..f155dc607112 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -110,19 +110,6 @@ static inline bool shmem_file(struct file *file) extern bool shmem_charge(struct inode *inode, long pages); extern void shmem_uncharge(struct inode *inode, long pages); -#ifdef CONFIG_TMPFS - -extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg); - -#else - -static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned long a) -{ - return -EINVAL; -} - -#endif - #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE extern bool shmem_huge_enabled(struct vm_area_struct *vma); #else -- cgit v1.2.3 From 3010a5ea665a089361e435093bd737399123fcc4 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Thu, 7 Jun 2018 17:06:08 -0700 Subject: mm: introduce ARCH_HAS_PTE_SPECIAL Currently the PTE special supports is turned on in per architecture header files. Most of the time, it is defined in arch/*/include/asm/pgtable.h depending or not on some other per architecture static definition. This patch introduce a new configuration variable to manage this directly in the Kconfig files. It would later replace __HAVE_ARCH_PTE_SPECIAL. Here notes for some architecture where the definition of __HAVE_ARCH_PTE_SPECIAL is not obvious: arm __HAVE_ARCH_PTE_SPECIAL which is currently defined in arch/arm/include/asm/pgtable-3level.h which is included by arch/arm/include/asm/pgtable.h when CONFIG_ARM_LPAE is set. So select ARCH_HAS_PTE_SPECIAL if ARM_LPAE. powerpc __HAVE_ARCH_PTE_SPECIAL is defined in 2 files: - arch/powerpc/include/asm/book3s/64/pgtable.h - arch/powerpc/include/asm/pte-common.h The first one is included if (PPC_BOOK3S & PPC64) while the second is included in all the other cases. So select ARCH_HAS_PTE_SPECIAL all the time. sparc: __HAVE_ARCH_PTE_SPECIAL is defined if defined(__sparc__) && defined(__arch64__) which are defined through the compiler in sparc/Makefile if !SPARC32 which I assume to be if SPARC64. So select ARCH_HAS_PTE_SPECIAL if SPARC64 There is no functional change introduced by this patch. Link: http://lkml.kernel.org/r/1523433816-14460-2-git-send-email-ldufour@linux.vnet.ibm.com Signed-off-by: Laurent Dufour Suggested-by: Jerome Glisse Reviewed-by: Jerome Glisse Acked-by: David Rientjes Cc: Michal Hocko Cc: "Aneesh Kumar K . V" Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Jonathan Corbet Cc: Catalin Marinas Cc: Will Deacon Cc: Yoshinori Sato Cc: Rich Felker Cc: David S. Miller Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Vineet Gupta Cc: Palmer Dabbelt Cc: Albert Ou Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: David Rientjes Cc: Robin Murphy Cc: Christophe LEROY Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pfn_t.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index a03c2642a87c..21713dc14ce2 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -122,7 +122,7 @@ pud_t pud_mkdevmap(pud_t pud); #endif #endif /* __HAVE_ARCH_PTE_DEVMAP */ -#ifdef __HAVE_ARCH_PTE_SPECIAL +#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL static inline bool pfn_t_special(pfn_t pfn) { return (pfn.val & PFN_SPECIAL) == PFN_SPECIAL; @@ -132,5 +132,5 @@ static inline bool pfn_t_special(pfn_t pfn) { return false; } -#endif /* __HAVE_ARCH_PTE_SPECIAL */ +#endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ #endif /* _LINUX_PFN_T_H_ */ -- cgit v1.2.3 From 1c4bc43ddfd52cbe5a08bb86ae636f55d2799424 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Thu, 7 Jun 2018 17:06:15 -0700 Subject: mm/memblock: introduce PHYS_ADDR_MAX So far code was using ULLONG_MAX and type casting to obtain a phys_addr_t with all bits set. The typecast is necessary to silence compiler warnings on 32-bit platforms. Use the simpler but still type safe approach "~(phys_addr_t)0" to create a preprocessor define for all bits set. Link: http://lkml.kernel.org/r/20180406213809.566-1-stefan@agner.ch Signed-off-by: Stefan Agner Suggested-by: Linus Torvalds Acked-by: Michal Hocko Reviewed-by: Andrew Morton Cc: Catalin Marinas Cc: Pavel Tatashin Cc: Ard Biesheuvel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7aed92624531..7c4e8f1f72d8 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -29,6 +29,7 @@ #define LLONG_MIN (-LLONG_MAX - 1) #define ULLONG_MAX (~0ULL) #define SIZE_MAX (~(size_t)0) +#define PHYS_ADDR_MAX (~(phys_addr_t)0) #define U8_MAX ((u8)~0U) #define S8_MAX ((s8)(U8_MAX>>1)) -- cgit v1.2.3 From bbec2e15170aae3e084d7d9afc730aeebe01b654 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 7 Jun 2018 17:06:18 -0700 Subject: mm: rename page_counter's count/limit into usage/max This patch renames struct page_counter fields: count -> usage limit -> max and the corresponding functions: page_counter_limit() -> page_counter_set_max() mem_cgroup_get_limit() -> mem_cgroup_get_max() mem_cgroup_resize_limit() -> mem_cgroup_resize_max() memcg_update_kmem_limit() -> memcg_update_kmem_max() memcg_update_tcp_limit() -> memcg_update_tcp_max() The idea behind this renaming is to have the direct matching between memory cgroup knobs (low, high, max) and page_counters API. This is pure renaming, this patch doesn't bring any functional change. Link: http://lkml.kernel.org/r/20180405185921.4942-1-guro@fb.com Signed-off-by: Roman Gushchin Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 4 ++-- include/linux/page_counter.h | 12 ++++++------ 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 517096c3cc99..577a19a6a93b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -467,7 +467,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, void mem_cgroup_handle_over_high(void); -unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg); +unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p); @@ -858,7 +858,7 @@ mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, return 0; } -static inline unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg) +static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { return 0; } diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index c15ab80ad32d..94029dad9317 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -7,8 +7,8 @@ #include struct page_counter { - atomic_long_t count; - unsigned long limit; + atomic_long_t usage; + unsigned long max; struct page_counter *parent; /* legacy */ @@ -25,14 +25,14 @@ struct page_counter { static inline void page_counter_init(struct page_counter *counter, struct page_counter *parent) { - atomic_long_set(&counter->count, 0); - counter->limit = PAGE_COUNTER_MAX; + atomic_long_set(&counter->usage, 0); + counter->max = PAGE_COUNTER_MAX; counter->parent = parent; } static inline unsigned long page_counter_read(struct page_counter *counter) { - return atomic_long_read(&counter->count); + return atomic_long_read(&counter->usage); } void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages); @@ -41,7 +41,7 @@ bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail); void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); -int page_counter_limit(struct page_counter *counter, unsigned long limit); +int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages); int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages); -- cgit v1.2.3 From 230671533d64631116be3ff9d407bd9ca5a58e1b Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 7 Jun 2018 17:06:22 -0700 Subject: mm: memory.low hierarchical behavior This patch aims to address an issue in current memory.low semantics, which makes it hard to use it in a hierarchy, where some leaf memory cgroups are more valuable than others. For example, there are memcgs A, A/B, A/C, A/D and A/E: A A/memory.low = 2G, A/memory.current = 6G //\\ BC DE B/memory.low = 3G B/memory.current = 2G C/memory.low = 1G C/memory.current = 2G D/memory.low = 0 D/memory.current = 2G E/memory.low = 10G E/memory.current = 0 If we apply memory pressure, B, C and D are reclaimed at the same pace while A's usage exceeds 2G. This is obviously wrong, as B's usage is fully below B's memory.low, and C has 1G of protection as well. Also, A is pushed to the size, which is less than A's 2G memory.low, which is also wrong. A simple bash script (provided below) can be used to reproduce the problem. Current results are: A: 1430097920 A/B: 711929856 A/C: 717426688 A/D: 741376 A/E: 0 To address the issue a concept of effective memory.low is introduced. Effective memory.low is always equal or less than original memory.low. In a case, when there is no memory.low overcommittment (and also for top-level cgroups), these two values are equal. Otherwise it's a part of parent's effective memory.low, calculated as a cgroup's memory.low usage divided by sum of sibling's memory.low usages (under memory.low usage I mean the size of actually protected memory: memory.current if memory.current < memory.low, 0 otherwise). It's necessary to track the actual usage, because otherwise an empty cgroup with memory.low set (A/E in my example) will affect actual memory distribution, which makes no sense. To avoid traversing the cgroup tree twice, page_counters code is reused. Calculating effective memory.low can be done in the reclaim path, as we conveniently traversing the cgroup tree from top to bottom and check memory.low on each level. So, it's a perfect place to calculate effective memory low and save it to use it for children cgroups. This also eliminates a need to traverse the cgroup tree from bottom to top each time to check if parent's guarantee is not exceeded. Setting/resetting effective memory.low is intentionally racy, but it's fine and shouldn't lead to any significant differences in actual memory distribution. With this patch applied results are matching the expectations: A: 2147930112 A/B: 1428721664 A/C: 718393344 A/D: 815104 A/E: 0 Test script: #!/bin/bash CGPATH="/sys/fs/cgroup" truncate /file1 --size 2G truncate /file2 --size 2G truncate /file3 --size 2G truncate /file4 --size 50G mkdir "${CGPATH}/A" echo "+memory" > "${CGPATH}/A/cgroup.subtree_control" mkdir "${CGPATH}/A/B" "${CGPATH}/A/C" "${CGPATH}/A/D" "${CGPATH}/A/E" echo 2G > "${CGPATH}/A/memory.low" echo 3G > "${CGPATH}/A/B/memory.low" echo 1G > "${CGPATH}/A/C/memory.low" echo 0 > "${CGPATH}/A/D/memory.low" echo 10G > "${CGPATH}/A/E/memory.low" echo $$ > "${CGPATH}/A/B/cgroup.procs" && vmtouch -qt /file1 echo $$ > "${CGPATH}/A/C/cgroup.procs" && vmtouch -qt /file2 echo $$ > "${CGPATH}/A/D/cgroup.procs" && vmtouch -qt /file3 echo $$ > "${CGPATH}/cgroup.procs" && vmtouch -qt /file4 echo "A: " `cat "${CGPATH}/A/memory.current"` echo "A/B: " `cat "${CGPATH}/A/B/memory.current"` echo "A/C: " `cat "${CGPATH}/A/C/memory.current"` echo "A/D: " `cat "${CGPATH}/A/D/memory.current"` echo "A/E: " `cat "${CGPATH}/A/E/memory.current"` rmdir "${CGPATH}/A/B" "${CGPATH}/A/C" "${CGPATH}/A/D" "${CGPATH}/A/E" rmdir "${CGPATH}/A" rm /file1 /file2 /file3 /file4 Link: http://lkml.kernel.org/r/20180405185921.4942-2-guro@fb.com Signed-off-by: Roman Gushchin Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- include/linux/page_counter.h | 7 +++++++ 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 577a19a6a93b..891945507044 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -181,8 +181,7 @@ struct mem_cgroup { struct page_counter kmem; struct page_counter tcpmem; - /* Normal memory consumption range */ - unsigned long low; + /* Upper bound of normal memory consumption range */ unsigned long high; /* Range enforcement for interrupt charges */ diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 94029dad9317..7902a727d3b6 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -9,8 +9,14 @@ struct page_counter { atomic_long_t usage; unsigned long max; + unsigned long low; struct page_counter *parent; + /* effective memory.low and memory.low usage tracking */ + unsigned long elow; + atomic_long_t low_usage; + atomic_long_t children_low_usage; + /* legacy */ unsigned long watermark; unsigned long failcnt; @@ -42,6 +48,7 @@ bool page_counter_try_charge(struct page_counter *counter, struct page_counter **fail); void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages); +void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages); int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages); -- cgit v1.2.3 From 93781325da6e07af57a21f111d1f2b9f128fa397 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 7 Jun 2018 17:07:02 -0700 Subject: lockdep: fix fs_reclaim annotation While revisiting my Btrfs swapfile series [1], I introduced a situation in which reclaim would lock i_rwsem, and even though the swapon() path clearly made GFP_KERNEL allocations while holding i_rwsem, I got no complaints from lockdep. It turns out that the rework of the fs_reclaim annotation was broken: if the current task has PF_MEMALLOC set, we don't acquire the dummy fs_reclaim lock, but when reclaiming we always check this _after_ we've just set the PF_MEMALLOC flag. In most cases, we can fix this by moving the fs_reclaim_{acquire,release}() outside of the memalloc_noreclaim_{save,restore}(), althought kswapd is slightly different. After applying this, I got the expected lockdep splats. 1: https://lwn.net/Articles/625412/ Link: http://lkml.kernel.org/r/9f8aa70652a98e98d7c4de0fc96a4addcee13efe.1523778026.git.osandov@fb.com Fixes: d92a8cfcb37e ("locking/lockdep: Rework FS_RECLAIM annotation") Signed-off-by: Omar Sandoval Reviewed-by: Andrew Morton Cc: Peter Zijlstra Cc: Tetsuo Handa Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 76a8cb4ef178..44d356f5e47c 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -163,9 +163,13 @@ static inline gfp_t current_gfp_context(gfp_t flags) } #ifdef CONFIG_LOCKDEP +extern void __fs_reclaim_acquire(void); +extern void __fs_reclaim_release(void); extern void fs_reclaim_acquire(gfp_t gfp_mask); extern void fs_reclaim_release(gfp_t gfp_mask); #else +static inline void __fs_reclaim_acquire(void) { } +static inline void __fs_reclaim_release(void) { } static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif -- cgit v1.2.3 From 48f49e1f66854ef44439b84a5cf47179539f3804 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 7 Jun 2018 17:07:07 -0700 Subject: mm/ksm: remove unused page_referenced_ksm declaration Commit 9f32624be943 ("mm/rmap: use rmap_walk() in page_referenced()") removed the declaration of page_referenced_ksm for the case CONFIG_KSM=y, but left one for CONFIG_KSM=n. Remove the unused leftover. Link: http://lkml.kernel.org/r/1524552106-7356-2-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Reviewed-by: Andrew Morton Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ksm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 44368b19b27e..bbdfca3db6e1 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -89,12 +89,6 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, return page; } -static inline int page_referenced_ksm(struct page *page, - struct mem_cgroup *memcg, unsigned long *vm_flags) -{ - return 0; -} - static inline void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) { -- cgit v1.2.3 From 88484826bc67844eeae1855ebe32cce9edd937c9 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 7 Jun 2018 17:07:11 -0700 Subject: mm/ksm: move [set_]page_stable_node from ksm.h to ksm.c page_stable_node() and set_page_stable_node() are only used in mm/ksm.c and there is no point to keep them in the include/linux/ksm.h [akpm@linux-foundation.org: fix SYSFS=n build] Link: http://lkml.kernel.org/r/1524552106-7356-3-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Reviewed-by: Andrew Morton Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ksm.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index bbdfca3db6e1..161e8164abcf 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -37,17 +37,6 @@ static inline void ksm_exit(struct mm_struct *mm) __ksm_exit(mm); } -static inline struct stable_node *page_stable_node(struct page *page) -{ - return PageKsm(page) ? page_rmapping(page) : NULL; -} - -static inline void set_page_stable_node(struct page *page, - struct stable_node *stable_node) -{ - page->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); -} - /* * When do_swap_page() first faults in from swap what used to be a KSM page, * no problem, it will be assigned to this vma's anon_vma; but thereafter, -- cgit v1.2.3 From 9ccc361716362e8abb01d9944f8df97b4aac3e23 Mon Sep 17 00:00:00 2001 From: Wang Long Date: Thu, 7 Jun 2018 17:07:19 -0700 Subject: memcg: writeback: use memcg->cgwb_list directly mem_cgroup_cgwb_list is a very simple wrapper and it will never be used outside of code under CONFIG_CGROUP_WRITEBACK. so use memcg->cgwb_list directly. Link: http://lkml.kernel.org/r/1524406173-212182-1-git-send-email-wanglong19@meituan.com Signed-off-by: Wang Long Reviewed-by: Jan Kara Acked-by: Tejun Heo Acked-by: Michal Hocko Reviewed-by: Andrew Morton Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 891945507044..10d741e8fe51 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1097,7 +1097,6 @@ static inline void dec_lruvec_page_state(struct page *page, #ifdef CONFIG_CGROUP_WRITEBACK -struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg); struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, -- cgit v1.2.3 From fb52bbaee598f58352d8732637ebe7013b2df79f Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Thu, 7 Jun 2018 17:07:43 -0700 Subject: mm: move is_pageblock_removable_nolock() to mm/memory_hotplug.c is_pageblock_removable_nolock() is not used outside of mm/memory_hotplug.c. Move it next to unique caller is_mem_section_removable() and make it static. Remove prototype in to silence gcc warning (W=1): mm/page_alloc.c:7704:6: warning: no previous prototype for `is_pageblock_removable_nolock' [-Wmissing-prototypes] Link: http://lkml.kernel.org/r/20180509190001.24789-1-malat@debian.org Signed-off-by: Mathieu Malaterre Suggested-by: Michal Hocko Reviewed-by: Andrew Morton Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 2b0265265c28..4e9828cda7a2 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -107,7 +107,6 @@ static inline bool movable_node_is_enabled(void) } #ifdef CONFIG_MEMORY_HOTREMOVE -extern bool is_pageblock_removable_nolock(struct page *page); extern int arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap); extern int __remove_pages(struct zone *zone, unsigned long start_pfn, -- cgit v1.2.3 From bf8d5d52ffe89aac5b46ddb39dd1a4351fae5df4 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 7 Jun 2018 17:07:46 -0700 Subject: memcg: introduce memory.min Memory controller implements the memory.low best-effort memory protection mechanism, which works perfectly in many cases and allows protecting working sets of important workloads from sudden reclaim. But its semantics has a significant limitation: it works only as long as there is a supply of reclaimable memory. This makes it pretty useless against any sort of slow memory leaks or memory usage increases. This is especially true for swapless systems. If swap is enabled, memory soft protection effectively postpones problems, allowing a leaking application to fill all swap area, which makes no sense. The only effective way to guarantee the memory protection in this case is to invoke the OOM killer. It's possible to handle this case in userspace by reacting on MEMCG_LOW events; but there is still a place for a fail-safe in-kernel mechanism to provide stronger guarantees. This patch introduces the memory.min interface for cgroup v2 memory controller. It works very similarly to memory.low (sharing the same hierarchical behavior), except that it's not disabled if there is no more reclaimable memory in the system. If cgroup is not populated, its memory.min is ignored, because otherwise even the OOM killer wouldn't be able to reclaim the protected memory, and the system can stall. [guro@fb.com: s/low/min/ in docs] Link: http://lkml.kernel.org/r/20180510130758.GA9129@castle.DHCP.thefacebook.com Link: http://lkml.kernel.org/r/20180509180734.GA4856@castle.DHCP.thefacebook.com Signed-off-by: Roman Gushchin Reviewed-by: Randy Dunlap Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 15 +++++++++++---- include/linux/page_counter.h | 11 +++++++++-- 2 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 10d741e8fe51..9c04cf8e6487 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -58,6 +58,12 @@ enum memcg_memory_event { MEMCG_NR_MEMORY_EVENTS, }; +enum mem_cgroup_protection { + MEMCG_PROT_NONE, + MEMCG_PROT_LOW, + MEMCG_PROT_MIN, +}; + struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; int priority; @@ -289,7 +295,8 @@ static inline bool mem_cgroup_disabled(void) return !cgroup_subsys_enabled(memory_cgrp_subsys); } -bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg); +enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, + struct mem_cgroup *memcg); int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp, @@ -734,10 +741,10 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg, { } -static inline bool mem_cgroup_low(struct mem_cgroup *root, - struct mem_cgroup *memcg) +static inline enum mem_cgroup_protection mem_cgroup_protected( + struct mem_cgroup *root, struct mem_cgroup *memcg) { - return false; + return MEMCG_PROT_NONE; } static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 7902a727d3b6..bab7e57f659b 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -8,10 +8,16 @@ struct page_counter { atomic_long_t usage; - unsigned long max; + unsigned long min; unsigned long low; + unsigned long max; struct page_counter *parent; + /* effective memory.min and memory.min usage tracking */ + unsigned long emin; + atomic_long_t min_usage; + atomic_long_t children_min_usage; + /* effective memory.low and memory.low usage tracking */ unsigned long elow; atomic_long_t low_usage; @@ -47,8 +53,9 @@ bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail); void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); -int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages); +void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages); void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages); +int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages); int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages); -- cgit v1.2.3 From 2bcd6454bae78775632e1848ce1eabf65c6fbd4f Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Thu, 7 Jun 2018 17:08:00 -0700 Subject: mm: use new return type vm_fault_t Use new return type vm_fault_t for fault handler in struct vm_operations_struct. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. Link: http://lkml.kernel.org/r/20180511190542.GA2412@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Matthew Wilcox Cc: Dan Williams Cc: Jan Kara Cc: Ross Zwisler Cc: Rik van Riel Cc: Matthew Wilcox Cc: Hugh Dickins Cc: Pavel Tatashin Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b7012bb1d218..d1dc618a56bf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2303,10 +2303,10 @@ extern void truncate_inode_pages_range(struct address_space *, extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ -extern int filemap_fault(struct vm_fault *vmf); +extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern void filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); -extern int filemap_page_mkwrite(struct vm_fault *vmf); +extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); /* mm/page-writeback.c */ int __must_check write_one_page(struct page *page); -- cgit v1.2.3 From b3ec9f33acb8d3a6173515d3d547be969dc70566 Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Thu, 7 Jun 2018 17:08:04 -0700 Subject: mm: change return type to vm_fault_t Use new return type vm_fault_t for fault handler in struct vm_operations_struct. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. See commit 1c8f422059ae ("mm: change return type to vm_fault_t") Link: http://lkml.kernel.org/r/20180512063745.GA26866@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Joe Perches Cc: Michal Hocko Cc: Hugh Dickins Cc: Dan Williams Cc: David Rientjes Cc: Mike Kravetz Cc: Naoya Horiguchi Cc: Aneesh Kumar K.V Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 49dd59ea90f7..eb9da245286d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -629,9 +629,9 @@ struct vm_special_mapping { * If non-NULL, then this is called to resolve page faults * on the special mapping. If used, .pages is not checked. */ - int (*fault)(const struct vm_special_mapping *sm, - struct vm_area_struct *vma, - struct vm_fault *vmf); + vm_fault_t (*fault)(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, + struct vm_fault *vmf); int (*mremap)(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma); -- cgit v1.2.3 From e67d4ca79aaf9d13a00d229b1b1c96b86828e8ba Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 7 Jun 2018 17:08:11 -0700 Subject: mm: save two stranded bits in gfp_mask ___GFP_COLD and ___GFP_OTHER_NODE were removed but their bits were stranded. Fill the gaps by moving the existing gfp masks around. Link: http://lkml.kernel.org/r/20180516211439.177440-1-shakeelb@google.com Signed-off-by: Shakeel Butt Suggested-by: Vlastimil Babka Acked-by: Michal Hocko Acked-by: Vlastimil Babka Reviewed-by: Andrew Morton Cc: Greg Thelen Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fc5ab85278d5..7f860ea29ec6 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -24,6 +24,7 @@ struct vm_area_struct; #define ___GFP_HIGH 0x20u #define ___GFP_IO 0x40u #define ___GFP_FS 0x80u +#define ___GFP_WRITE 0x100u #define ___GFP_NOWARN 0x200u #define ___GFP_RETRY_MAYFAIL 0x400u #define ___GFP_NOFAIL 0x800u @@ -36,11 +37,10 @@ struct vm_area_struct; #define ___GFP_THISNODE 0x40000u #define ___GFP_ATOMIC 0x80000u #define ___GFP_ACCOUNT 0x100000u -#define ___GFP_DIRECT_RECLAIM 0x400000u -#define ___GFP_WRITE 0x800000u -#define ___GFP_KSWAPD_RECLAIM 0x1000000u +#define ___GFP_DIRECT_RECLAIM 0x200000u +#define ___GFP_KSWAPD_RECLAIM 0x400000u #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x2000000u +#define ___GFP_NOLOCKDEP 0x800000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -205,7 +205,7 @@ struct vm_area_struct; #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /* -- cgit v1.2.3 From 6e292b9be7f4358985ce33ae1f59ab30a8c09e08 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:08:18 -0700 Subject: mm: split page_type out from _mapcount MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We're already using a union of many fields here, so stop abusing the _mapcount and make page_type its own field. That implies renaming some of the machinery that creates PageBuddy, PageBalloon and PageKmemcg; bring back the PG_buddy, PG_balloon and PG_kmemcg names. As suggested by Kirill, make page_type a bitmask. Because it starts out life as -1 (thanks to sharing the storage with _mapcount), setting a page flag means clearing the appropriate bit. This gives us space for probably twenty or so extra bits (depending how paranoid we want to be about _mapcount underflow). Link: http://lkml.kernel.org/r/20180518194519.3820-3-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 13 ++++++++----- include/linux/page-flags.h | 45 ++++++++++++++++++++++++++------------------- 2 files changed, 34 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index eb9da245286d..3a554fdf45c2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -96,6 +96,14 @@ struct page { }; union { + /* + * If the page is neither PageSlab nor mappable to userspace, + * the value stored here may help determine what this page + * is used for. See page-flags.h for a list of page types + * which are currently stored here. + */ + unsigned int page_type; + _slub_counter_t counters; unsigned int active; /* SLAB */ struct { /* SLUB */ @@ -109,11 +117,6 @@ struct page { /* * Count of ptes mapped in mms, to show when * page is mapped & limit reverse map searches. - * - * Extra information about page type may be - * stored here for pages that are never mapped, - * in which case the value MUST BE <= -2. - * See page-flags.h for more details. */ atomic_t _mapcount; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e34a27727b9a..8c25b28a35aa 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -642,49 +642,56 @@ PAGEFLAG_FALSE(DoubleMap) #endif /* - * For pages that are never mapped to userspace, page->mapcount may be - * used for storing extra information about page type. Any value used - * for this purpose must be <= -2, but it's better start not too close - * to -2 so that an underflow of the page_mapcount() won't be mistaken - * for a special page. + * For pages that are never mapped to userspace (and aren't PageSlab), + * page_type may be used. Because it is initialised to -1, we invert the + * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and + * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and + * low bits so that an underflow or overflow of page_mapcount() won't be + * mistaken for a page type value. */ -#define PAGE_MAPCOUNT_OPS(uname, lname) \ + +#define PAGE_TYPE_BASE 0xf0000000 +/* Reserve 0x0000007f to catch underflows of page_mapcount */ +#define PG_buddy 0x00000080 +#define PG_balloon 0x00000100 +#define PG_kmemcg 0x00000200 + +#define PageType(page, flag) \ + ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) + +#define PAGE_TYPE_OPS(uname, lname) \ static __always_inline int Page##uname(struct page *page) \ { \ - return atomic_read(&page->_mapcount) == \ - PAGE_##lname##_MAPCOUNT_VALUE; \ + return PageType(page, PG_##lname); \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ - VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page); \ - atomic_set(&page->_mapcount, PAGE_##lname##_MAPCOUNT_VALUE); \ + VM_BUG_ON_PAGE(!PageType(page, 0), page); \ + page->page_type &= ~PG_##lname; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ - atomic_set(&page->_mapcount, -1); \ + page->page_type |= PG_##lname; \ } /* - * PageBuddy() indicate that the page is free and in the buddy system + * PageBuddy() indicates that the page is free and in the buddy system * (see mm/page_alloc.c). */ -#define PAGE_BUDDY_MAPCOUNT_VALUE (-128) -PAGE_MAPCOUNT_OPS(Buddy, BUDDY) +PAGE_TYPE_OPS(Buddy, buddy) /* - * PageBalloon() is set on pages that are on the balloon page list + * PageBalloon() is true for pages that are on the balloon page list * (see mm/balloon_compaction.c). */ -#define PAGE_BALLOON_MAPCOUNT_VALUE (-256) -PAGE_MAPCOUNT_OPS(Balloon, BALLOON) +PAGE_TYPE_OPS(Balloon, balloon) /* * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on * pages allocated with __GFP_ACCOUNT. It gets cleared on page free. */ -#define PAGE_KMEMCG_MAPCOUNT_VALUE (-512) -PAGE_MAPCOUNT_OPS(Kmemcg, KMEMCG) +PAGE_TYPE_OPS(Kmemcg, kmemcg) extern bool is_free_buddy_page(struct page *page); -- cgit v1.2.3 From 1d40a5ea01d53251c23c7be541d3f4a656cfc537 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:08:23 -0700 Subject: mm: mark pages in use for page tables MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define a new PageTable bit in the page_type and use it to mark pages in use as page tables. This can be helpful when debugging crashdumps or analysing memory fragmentation. Add a KPF flag to report these pages to userspace and update page-types.c to interpret that flag. Note that only pages currently accounted as NR_PAGETABLES are tracked as PageTable; this does not include pgd/p4d/pud/pmd pages. Those will be the subject of a later patch. Link: http://lkml.kernel.org/r/20180518194519.3820-4-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ include/linux/page-flags.h | 6 ++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d1dc618a56bf..1dd588b7c649 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1851,6 +1851,7 @@ static inline bool pgtable_page_ctor(struct page *page) { if (!ptlock_init(page)) return false; + __SetPageTable(page); inc_zone_page_state(page, NR_PAGETABLE); return true; } @@ -1858,6 +1859,7 @@ static inline bool pgtable_page_ctor(struct page *page) static inline void pgtable_page_dtor(struct page *page) { pte_lock_deinit(page); + __ClearPageTable(page); dec_zone_page_state(page, NR_PAGETABLE); } diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 8c25b28a35aa..901943e4754b 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -655,6 +655,7 @@ PAGEFLAG_FALSE(DoubleMap) #define PG_buddy 0x00000080 #define PG_balloon 0x00000100 #define PG_kmemcg 0x00000200 +#define PG_table 0x00000400 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) @@ -693,6 +694,11 @@ PAGE_TYPE_OPS(Balloon, balloon) */ PAGE_TYPE_OPS(Kmemcg, kmemcg) +/* + * Marks pages in use as page tables. + */ +PAGE_TYPE_OPS(Table, table) + extern bool is_free_buddy_page(struct page *page); __PAGEFLAG(Isolated, isolated, PF_ANY); -- cgit v1.2.3 From d4fc5069a39405d67937b25c0dc9249a9b6c50f1 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:08:26 -0700 Subject: mm: switch s_mem and slab_cache in struct page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This will allow us to store slub's counters in the same bits as slab's s_mem. slub now needs to set page->mapping to NULL as it frees the page, just like slab does. Link: http://lkml.kernel.org/r/20180518194519.3820-5-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Christoph Lameter Acked-by: Vlastimil Babka Cc: Dave Hansen Cc: Jérôme Glisse Cc: "Kirill A . Shutemov" Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3a554fdf45c2..6f153f2fab50 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -83,7 +83,7 @@ struct page { /* See page-flags.h for the definition of PAGE_MAPPING_FLAGS */ struct address_space *mapping; - void *s_mem; /* slab first object */ + struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */ atomic_t compound_mapcount; /* first tail page */ /* page_deferred_list().next -- second tail page */ }; @@ -194,7 +194,7 @@ struct page { spinlock_t ptl; #endif #endif - struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */ + void *s_mem; /* slab first object */ }; #ifdef CONFIG_MEMCG -- cgit v1.2.3 From 7d27a04bb2b5bd665f147439d18ae236080eef32 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:08:31 -0700 Subject: mm: move 'private' union within struct page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit By moving page->private to the fourth word of struct page, we can put the SLUB counters in the same word as SLAB's s_mem and still do the cmpxchg_double trick. Now the SLUB counters no longer overlap with the mapcount or refcount so we can drop the call to page_mapcount_reset() and simplify set_page_slub_counters() to a single line. Link: http://lkml.kernel.org/r/20180518194519.3820-6-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 56 +++++++++++++++++++++--------------------------- 1 file changed, 25 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6f153f2fab50..bcc5ee8b7b07 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -65,15 +65,9 @@ struct hmm; */ #ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE #define _struct_page_alignment __aligned(2 * sizeof(unsigned long)) -#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) -#define _slub_counter_t unsigned long #else -#define _slub_counter_t unsigned int -#endif -#else /* !CONFIG_HAVE_ALIGNED_STRUCT_PAGE */ #define _struct_page_alignment -#define _slub_counter_t unsigned int -#endif /* !CONFIG_HAVE_ALIGNED_STRUCT_PAGE */ +#endif struct page { /* First double word block */ @@ -95,6 +89,30 @@ struct page { /* page_deferred_list().prev -- second tail page */ }; + union { + /* + * Mapping-private opaque data: + * Usually used for buffer_heads if PagePrivate + * Used for swp_entry_t if PageSwapCache + * Indicates order in the buddy system if PageBuddy + */ + unsigned long private; +#if USE_SPLIT_PTE_PTLOCKS +#if ALLOC_SPLIT_PTLOCKS + spinlock_t *ptl; +#else + spinlock_t ptl; +#endif +#endif + void *s_mem; /* slab first object */ + unsigned long counters; /* SLUB */ + struct { /* SLUB */ + unsigned inuse:16; + unsigned objects:15; + unsigned frozen:1; + }; + }; + union { /* * If the page is neither PageSlab nor mappable to userspace, @@ -104,13 +122,7 @@ struct page { */ unsigned int page_type; - _slub_counter_t counters; unsigned int active; /* SLAB */ - struct { /* SLUB */ - unsigned inuse:16; - unsigned objects:15; - unsigned frozen:1; - }; int units; /* SLOB */ struct { /* Page cache */ @@ -179,24 +191,6 @@ struct page { #endif }; - union { - /* - * Mapping-private opaque data: - * Usually used for buffer_heads if PagePrivate - * Used for swp_entry_t if PageSwapCache - * Indicates order in the buddy system if PageBuddy - */ - unsigned long private; -#if USE_SPLIT_PTE_PTLOCKS -#if ALLOC_SPLIT_PTLOCKS - spinlock_t *ptl; -#else - spinlock_t ptl; -#endif -#endif - void *s_mem; /* slab first object */ - }; - #ifdef CONFIG_MEMCG struct mem_cgroup *mem_cgroup; #endif -- cgit v1.2.3 From b21999da02f891aafa362252f4db7ba5c34a9a8d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:08:35 -0700 Subject: mm: move _refcount out of struct page union MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Keeping the refcount in the union only encourages people to put something else in the union which will overlap with _refcount and eventually explode messily. pahole reports no fields change location. Link: http://lkml.kernel.org/r/20180518194519.3820-7-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 25 ++++++++++--------------- 1 file changed, 10 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bcc5ee8b7b07..0b0c0e224011 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -113,7 +113,13 @@ struct page { }; }; - union { + union { /* This union is 4 bytes in size. */ + /* + * If the page can be mapped to userspace, encodes the number + * of times this page is referenced by a page table. + */ + atomic_t _mapcount; + /* * If the page is neither PageSlab nor mappable to userspace, * the value stored here may help determine what this page @@ -124,22 +130,11 @@ struct page { unsigned int active; /* SLAB */ int units; /* SLOB */ - - struct { /* Page cache */ - /* - * Count of ptes mapped in mms, to show when - * page is mapped & limit reverse map searches. - */ - atomic_t _mapcount; - - /* - * Usage count, *USE WRAPPER FUNCTION* when manual - * accounting. See page_ref.h - */ - atomic_t _refcount; - }; }; + /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ + atomic_t _refcount; + /* * WARNING: bit 0 of the first word encode PageTail(). That means * the rest users of the storage space MUST NOT use the bit to -- cgit v1.2.3 From 66a6ffd2af42b0bafaecccbd7c1c30d386de21ab Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:08:39 -0700 Subject: mm: combine first three unions in struct page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit By combining these three one-word unions into one three-word union, we make it easier for users to add their own multi-word fields to struct page, as well as making it obvious that SLUB needs to keep its double-word alignment for its freelist & counters. No field moves position; verified with pahole. Link: http://lkml.kernel.org/r/20180518194519.3820-8-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 66 ++++++++++++++++++++++++------------------------ 1 file changed, 33 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0b0c0e224011..158f9693f865 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -70,46 +70,46 @@ struct hmm; #endif struct page { - /* First double word block */ unsigned long flags; /* Atomic flags, some possibly * updated asynchronously */ + /* Three words (12/24 bytes) are available in this union. */ union { - /* See page-flags.h for the definition of PAGE_MAPPING_FLAGS */ - struct address_space *mapping; - - struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */ + struct { /* Page cache and anonymous pages */ + /* See page-flags.h for PAGE_MAPPING_FLAGS */ + struct address_space *mapping; + pgoff_t index; /* Our offset within mapping. */ + /** + * @private: Mapping-private opaque data. + * Usually used for buffer_heads if PagePrivate. + * Used for swp_entry_t if PageSwapCache. + * Indicates order in the buddy system if PageBuddy. + */ + unsigned long private; + }; + struct { /* slab, slob and slub */ + struct kmem_cache *slab_cache; /* not slob */ + /* Double-word boundary */ + void *freelist; /* first free object */ + union { + void *s_mem; /* slab: first object */ + unsigned long counters; /* SLUB */ + struct { /* SLUB */ + unsigned inuse:16; + unsigned objects:15; + unsigned frozen:1; + }; + }; + }; atomic_t compound_mapcount; /* first tail page */ - /* page_deferred_list().next -- second tail page */ - }; - - /* Second double word */ - union { - pgoff_t index; /* Our offset within mapping. */ - void *freelist; /* sl[aou]b first free object */ - /* page_deferred_list().prev -- second tail page */ - }; - - union { - /* - * Mapping-private opaque data: - * Usually used for buffer_heads if PagePrivate - * Used for swp_entry_t if PageSwapCache - * Indicates order in the buddy system if PageBuddy - */ - unsigned long private; -#if USE_SPLIT_PTE_PTLOCKS + struct list_head deferred_list; /* second tail page */ + struct { /* Page table pages */ + unsigned long _pt_pad_2; /* mapping */ + unsigned long _pt_pad_3; #if ALLOC_SPLIT_PTLOCKS - spinlock_t *ptl; + spinlock_t *ptl; #else - spinlock_t ptl; -#endif + spinlock_t ptl; #endif - void *s_mem; /* slab first object */ - unsigned long counters; /* SLUB */ - struct { /* SLUB */ - unsigned inuse:16; - unsigned objects:15; - unsigned frozen:1; }; }; -- cgit v1.2.3 From b7ccc7f8c643de0b71cd2da3245d0c27038a8dd7 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:08:46 -0700 Subject: mm: move lru union within struct page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since the LRU is two words, this does not affect the double-word alignment of SLUB's freelist. Link: http://lkml.kernel.org/r/20180518194519.3820-10-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 102 +++++++++++++++++++++++------------------------ 1 file changed, 51 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 158f9693f865..5b97bd445ada 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -72,6 +72,57 @@ struct hmm; struct page { unsigned long flags; /* Atomic flags, some possibly * updated asynchronously */ + /* + * WARNING: bit 0 of the first word encode PageTail(). That means + * the rest users of the storage space MUST NOT use the bit to + * avoid collision and false-positive PageTail(). + */ + union { + struct list_head lru; /* Pageout list, eg. active_list + * protected by zone_lru_lock ! + * Can be used as a generic list + * by the page owner. + */ + struct dev_pagemap *pgmap; /* ZONE_DEVICE pages are never on an + * lru or handled by a slab + * allocator, this points to the + * hosting device page map. + */ + struct { /* slub per cpu partial pages */ + struct page *next; /* Next partial slab */ +#ifdef CONFIG_64BIT + int pages; /* Nr of partial slabs left */ + int pobjects; /* Approximate # of objects */ +#else + short int pages; + short int pobjects; +#endif + }; + + struct rcu_head rcu_head; /* Used by SLAB + * when destroying via RCU + */ + /* Tail pages of compound page */ + struct { + unsigned long compound_head; /* If bit zero is set */ + + /* First tail page only */ + unsigned char compound_dtor; + unsigned char compound_order; + /* two/six bytes available here */ + }; + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS + struct { + unsigned long __pad; /* do not overlay pmd_huge_pte + * with compound_head to avoid + * possible bit 0 collision. + */ + pgtable_t pmd_huge_pte; /* protected by page->ptl */ + }; +#endif + }; + /* Three words (12/24 bytes) are available in this union. */ union { struct { /* Page cache and anonymous pages */ @@ -135,57 +186,6 @@ struct page { /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ atomic_t _refcount; - /* - * WARNING: bit 0 of the first word encode PageTail(). That means - * the rest users of the storage space MUST NOT use the bit to - * avoid collision and false-positive PageTail(). - */ - union { - struct list_head lru; /* Pageout list, eg. active_list - * protected by zone_lru_lock ! - * Can be used as a generic list - * by the page owner. - */ - struct dev_pagemap *pgmap; /* ZONE_DEVICE pages are never on an - * lru or handled by a slab - * allocator, this points to the - * hosting device page map. - */ - struct { /* slub per cpu partial pages */ - struct page *next; /* Next partial slab */ -#ifdef CONFIG_64BIT - int pages; /* Nr of partial slabs left */ - int pobjects; /* Approximate # of objects */ -#else - short int pages; - short int pobjects; -#endif - }; - - struct rcu_head rcu_head; /* Used by SLAB - * when destroying via RCU - */ - /* Tail pages of compound page */ - struct { - unsigned long compound_head; /* If bit zero is set */ - - /* First tail page only */ - unsigned char compound_dtor; - unsigned char compound_order; - /* two/six bytes available here */ - }; - -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS - struct { - unsigned long __pad; /* do not overlay pmd_huge_pte - * with compound_head to avoid - * possible bit 0 collision. - */ - pgtable_t pmd_huge_pte; /* protected by page->ptl */ - }; -#endif - }; - #ifdef CONFIG_MEMCG struct mem_cgroup *mem_cgroup; #endif -- cgit v1.2.3 From 4da1984edbbed0ffc961006d265d78a7b0095ea4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:08:50 -0700 Subject: mm: combine LRU and main union in struct page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This gives us five words of space in a single union in struct page. The compound_mapcount moves position (from offset 24 to offset 20) on 64-bit systems, but that does not seem likely to cause any trouble. Link: http://lkml.kernel.org/r/20180518194519.3820-11-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 97 +++++++++++++++++++++++------------------------- 1 file changed, 46 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5b97bd445ada..dfe6d648e055 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -73,59 +73,19 @@ struct page { unsigned long flags; /* Atomic flags, some possibly * updated asynchronously */ /* - * WARNING: bit 0 of the first word encode PageTail(). That means - * the rest users of the storage space MUST NOT use the bit to + * Five words (20/40 bytes) are available in this union. + * WARNING: bit 0 of the first word is used for PageTail(). That + * means the other users of this union MUST NOT use the bit to * avoid collision and false-positive PageTail(). */ - union { - struct list_head lru; /* Pageout list, eg. active_list - * protected by zone_lru_lock ! - * Can be used as a generic list - * by the page owner. - */ - struct dev_pagemap *pgmap; /* ZONE_DEVICE pages are never on an - * lru or handled by a slab - * allocator, this points to the - * hosting device page map. - */ - struct { /* slub per cpu partial pages */ - struct page *next; /* Next partial slab */ -#ifdef CONFIG_64BIT - int pages; /* Nr of partial slabs left */ - int pobjects; /* Approximate # of objects */ -#else - short int pages; - short int pobjects; -#endif - }; - - struct rcu_head rcu_head; /* Used by SLAB - * when destroying via RCU - */ - /* Tail pages of compound page */ - struct { - unsigned long compound_head; /* If bit zero is set */ - - /* First tail page only */ - unsigned char compound_dtor; - unsigned char compound_order; - /* two/six bytes available here */ - }; - -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS - struct { - unsigned long __pad; /* do not overlay pmd_huge_pte - * with compound_head to avoid - * possible bit 0 collision. - */ - pgtable_t pmd_huge_pte; /* protected by page->ptl */ - }; -#endif - }; - - /* Three words (12/24 bytes) are available in this union. */ union { struct { /* Page cache and anonymous pages */ + /** + * @lru: Pageout list, eg. active_list protected by + * zone_lru_lock. Sometimes used as a generic list + * by the page owner. + */ + struct list_head lru; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; pgoff_t index; /* Our offset within mapping. */ @@ -138,6 +98,19 @@ struct page { unsigned long private; }; struct { /* slab, slob and slub */ + union { + struct list_head slab_list; /* uses lru */ + struct { /* Partial pages */ + struct page *next; +#ifdef CONFIG_64BIT + int pages; /* Nr of pages left */ + int pobjects; /* Approximate count */ +#else + short int pages; + short int pobjects; +#endif + }; + }; struct kmem_cache *slab_cache; /* not slob */ /* Double-word boundary */ void *freelist; /* first free object */ @@ -151,9 +124,22 @@ struct page { }; }; }; - atomic_t compound_mapcount; /* first tail page */ - struct list_head deferred_list; /* second tail page */ + struct { /* Tail pages of compound page */ + unsigned long compound_head; /* Bit zero is set */ + + /* First tail page only */ + unsigned char compound_dtor; + unsigned char compound_order; + atomic_t compound_mapcount; + }; + struct { /* Second tail page of compound page */ + unsigned long _compound_pad_1; /* compound_head */ + unsigned long _compound_pad_2; + struct list_head deferred_list; + }; struct { /* Page table pages */ + unsigned long _pt_pad_1; /* compound_head */ + pgtable_t pmd_huge_pte; /* protected by page->ptl */ unsigned long _pt_pad_2; /* mapping */ unsigned long _pt_pad_3; #if ALLOC_SPLIT_PTLOCKS @@ -162,6 +148,15 @@ struct page { spinlock_t ptl; #endif }; + + /** @rcu_head: You can use this to free a page by RCU. */ + struct rcu_head rcu_head; + + /** + * @pgmap: For ZONE_DEVICE pages, this points to the hosting + * device page map. + */ + struct dev_pagemap *pgmap; }; union { /* This union is 4 bytes in size. */ -- cgit v1.2.3 From 97b4a671987123009724dfbdf188ec6e122573d4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:08:53 -0700 Subject: mm: improve struct page documentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rewrite the documentation to describe what you can use in struct page rather than what you can't. Link: http://lkml.kernel.org/r/20180518194519.3820-12-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Randy Dunlap Acked-by: Vlastimil Babka Cc: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: "Kirill A . Shutemov" Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 40 +++++++++++++++++++--------------------- 1 file changed, 19 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index dfe6d648e055..9b45760cc797 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -33,29 +33,27 @@ struct hmm; * it to keep track of whatever it is we are using the page for at the * moment. Note that we have no way to track which tasks are using * a page, though if it is a pagecache page, rmap structures can tell us - * who is mapping it. If you allocate the page using alloc_pages(), you - * can use some of the space in struct page for your own purposes. + * who is mapping it. * - * Pages that were once in the page cache may be found under the RCU lock - * even after they have been recycled to a different purpose. The page - * cache reads and writes some of the fields in struct page to pin the - * page before checking that it's still in the page cache. It is vital - * that all users of struct page: - * 1. Use the first word as PageFlags. - * 2. Clear or preserve bit 0 of page->compound_head. It is used as - * PageTail for compound pages, and the page cache must not see false - * positives. Some users put a pointer here (guaranteed to be at least - * 4-byte aligned), other users avoid using the field altogether. - * 3. page->_refcount must either not be used, or must be used in such a - * way that other CPUs temporarily incrementing and then decrementing the - * refcount does not cause problems. On receiving the page from - * alloc_pages(), the refcount will be positive. - * 4. Either preserve page->_mapcount or restore it to -1 before freeing it. + * If you allocate the page using alloc_pages(), you can use some of the + * space in struct page for your own purposes. The five words in the main + * union are available, except for bit 0 of the first word which must be + * kept clear. Many users use this word to store a pointer to an object + * which is guaranteed to be aligned. If you use the same storage as + * page->mapping, you must restore it to NULL before freeing the page. * - * If you allocate pages of order > 0, you can use the fields in the struct - * page associated with each page, but bear in mind that the pages may have - * been inserted individually into the page cache, so you must use the above - * four fields in a compatible way for each struct page. + * If your page will not be mapped to userspace, you can also use the four + * bytes in the mapcount union, but you must call page_mapcount_reset() + * before freeing it. + * + * If you want to use the refcount field, it must be used in such a way + * that other CPUs temporarily incrementing and then decrementing the + * refcount does not cause problems. On receiving the page from + * alloc_pages(), the refcount will be positive. + * + * If you allocate pages of order > 0, you can use some of the fields + * in each subpage, but you may need to restore some of their values + * afterwards. * * SLUB uses cmpxchg_double() to atomically update its freelist and * counters. That requires that freelist & counters be adjacent and -- cgit v1.2.3 From a052f0a5168ef99c517f6638aaec59f39060f81d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:08:57 -0700 Subject: mm: add pt_mm to struct page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For pgd page table pages, x86 overloads the page->index field to store a pointer to the mm_struct. Rename this to pt_mm so it's visible to other users. Link: http://lkml.kernel.org/r/20180518194519.3820-13-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Vlastimil Babka Cc: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: "Kirill A . Shutemov" Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 9b45760cc797..811aa0c71e1a 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -139,7 +139,7 @@ struct page { unsigned long _pt_pad_1; /* compound_head */ pgtable_t pmd_huge_pte; /* protected by page->ptl */ unsigned long _pt_pad_2; /* mapping */ - unsigned long _pt_pad_3; + struct mm_struct *pt_mm; /* x86 pgds only */ #if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else -- cgit v1.2.3 From 50e7fbc3bf0c3e41af0075f17a9e4ddefa82e1b5 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:09:01 -0700 Subject: mm: add hmm_data to struct page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make hmm_data an explicit member of the struct page union. Link: http://lkml.kernel.org/r/20180518194519.3820-14-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Vlastimil Babka Cc: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: "Kirill A . Shutemov" Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 8 ++------ include/linux/mm_types.h | 12 ++++++------ 2 files changed, 8 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 2f1327c37a63..4c92e3ba3e16 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -522,9 +522,7 @@ void hmm_devmem_remove(struct hmm_devmem *devmem); static inline void hmm_devmem_page_set_drvdata(struct page *page, unsigned long data) { - unsigned long *drvdata = (unsigned long *)&page->pgmap; - - drvdata[1] = data; + page->hmm_data = data; } /* @@ -535,9 +533,7 @@ static inline void hmm_devmem_page_set_drvdata(struct page *page, */ static inline unsigned long hmm_devmem_page_get_drvdata(const struct page *page) { - const unsigned long *drvdata = (const unsigned long *)&page->pgmap; - - return drvdata[1]; + return page->hmm_data; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 811aa0c71e1a..99ce070e7dcb 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -146,15 +146,15 @@ struct page { spinlock_t ptl; #endif }; + struct { /* ZONE_DEVICE pages */ + /** @pgmap: Points to the hosting device page map. */ + struct dev_pagemap *pgmap; + unsigned long hmm_data; + unsigned long _zd_pad_1; /* uses mapping */ + }; /** @rcu_head: You can use this to free a page by RCU. */ struct rcu_head rcu_head; - - /** - * @pgmap: For ZONE_DEVICE pages, this points to the hosting - * device page map. - */ - struct dev_pagemap *pgmap; }; union { /* This union is 4 bytes in size. */ -- cgit v1.2.3 From 9736d2a95e36ac3f60b063f498961103f3d4f165 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 7 Jun 2018 17:09:10 -0700 Subject: slub: remove kmem_cache->reserved MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The reserved field was only used for embedding an rcu_head in the data structure. With the previous commit, we no longer need it. That lets us remove the 'reserved' argument to a lot of functions. Link: http://lkml.kernel.org/r/20180518194519.3820-16-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Christoph Lameter Cc: Dave Hansen Cc: Jérôme Glisse Cc: "Kirill A . Shutemov" Cc: Lai Jiangshan Cc: Martin Schwidefsky Cc: Pekka Enberg Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 3773e26c08c1..09fa2c6f0e68 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -101,7 +101,6 @@ struct kmem_cache { void (*ctor)(void *); unsigned int inuse; /* Offset to metadata */ unsigned int align; /* Alignment */ - unsigned int reserved; /* Reserved bytes at the end of slabs */ unsigned int red_left_pad; /* Left redzone padding size */ const char *name; /* Name (only for display!) */ struct list_head list; /* List of slab caches */ -- cgit v1.2.3 From df2cc96e77011cf7989208b206da9817e0321028 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 7 Jun 2018 17:09:25 -0700 Subject: userfaultfd: prevent non-cooperative events vs mcopy_atomic races If a process monitored with userfaultfd changes it's memory mappings or forks() at the same time as uffd monitor fills the process memory with UFFDIO_COPY, the actual creation of page table entries and copying of the data in mcopy_atomic may happen either before of after the memory mapping modifications and there is no way for the uffd monitor to maintain consistent view of the process memory layout. For instance, let's consider fork() running in parallel with userfaultfd_copy(): process | uffd monitor ---------------------------------+------------------------------ fork() | userfaultfd_copy() ... | ... dup_mmap() | down_read(mmap_sem) down_write(mmap_sem) | /* create PTEs, copy data */ dup_uffd() | up_read(mmap_sem) copy_page_range() | up_write(mmap_sem) | dup_uffd_complete() | /* notify monitor */ | If the userfaultfd_copy() takes the mmap_sem first, the new page(s) will be present by the time copy_page_range() is called and they will appear in the child's memory mappings. However, if the fork() is the first to take the mmap_sem, the new pages won't be mapped in the child's address space. If the pages are not present and child tries to access them, the monitor will get page fault notification and everything is fine. However, if the pages *are present*, the child can access them without uffd noticing. And if we copy them into child it'll see the wrong data. Since we are talking about background copy, we'd need to decide whether the pages should be copied or not regardless #PF notifications. Since userfaultfd monitor has no way to determine what was the order, let's disallow userfaultfd_copy in parallel with the non-cooperative events. In such case we return -EAGAIN and the uffd monitor can understand that userfaultfd_copy() clashed with a non-cooperative event and take an appropriate action. Link: http://lkml.kernel.org/r/1527061324-19949-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Pavel Emelyanov Cc: Andrea Arcangeli Cc: Mike Kravetz Cc: Andrei Vagin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/userfaultfd_k.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index f2f3b68ba910..e091f0a11b11 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -31,10 +31,12 @@ extern int handle_userfault(struct vm_fault *vmf, unsigned long reason); extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long src_start, unsigned long len); + unsigned long src_start, unsigned long len, + bool *mmap_changing); extern ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long len); + unsigned long len, + bool *mmap_changing); /* mm helpers */ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, -- cgit v1.2.3 From 4b33b6959581d5093af2badb489d914911d99eaf Mon Sep 17 00:00:00 2001 From: Huaisheng Ye Date: Thu, 7 Jun 2018 17:09:36 -0700 Subject: include/linux/gfp.h: fix the annotation of GFP_ZONE_TABLE When bit is equal to 0x4, it means OPT_ZONE_DMA32 should be got from GFP_ZONE_TABLE. OPT_ZONE_DMA32 shall be equal to ZONE_DMA32 or ZONE_NORMAL according to the status of CONFIG_ZONE_DMA32. Similarly, when bit is equal to 0xc, that means OPT_ZONE_DMA32 should be got with an allocation policy GFP_MOVABLE. So ZONE_DMA32 or ZONE_NORMAL is the possible result value. Link: http://lkml.kernel.org/r/20180601163403.1032-1-yehs2007@zoho.com Signed-off-by: Huaisheng Ye Reviewed-by: Andrew Morton Cc: Vlastimil Babka Cc: Michal Hocko Cc: Mel Gorman Cc: Kate Stewart Cc: "Levin, Alexander (Sasha Levin)" Cc: Greg Kroah-Hartman Cc: Christoph Hellwig Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 7f860ea29ec6..a6afcec53795 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -343,7 +343,7 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) * 0x1 => DMA or NORMAL * 0x2 => HIGHMEM or NORMAL * 0x3 => BAD (DMA+HIGHMEM) - * 0x4 => DMA32 or DMA or NORMAL + * 0x4 => DMA32 or NORMAL * 0x5 => BAD (DMA+DMA32) * 0x6 => BAD (HIGHMEM+DMA32) * 0x7 => BAD (HIGHMEM+DMA32+DMA) @@ -351,7 +351,7 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) * 0x9 => DMA or NORMAL (MOVABLE+DMA) * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too) * 0xb => BAD (MOVABLE+HIGHMEM+DMA) - * 0xc => DMA32 (MOVABLE+DMA32) + * 0xc => DMA32 or NORMAL (MOVABLE+DMA32) * 0xd => BAD (MOVABLE+DMA32+DMA) * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) -- cgit v1.2.3 From e81bf9793b1861d74953ef041b4f6c7faecc2dbd Mon Sep 17 00:00:00 2001 From: Aaron Lu Date: Thu, 7 Jun 2018 17:09:44 -0700 Subject: mem_cgroup: make sure moving_account, move_lock_task and stat_cpu in the same cacheline The LKP robot found a 27% will-it-scale/page_fault3 performance regression regarding commit e27be240df53("mm: memcg: make sure memory.events is uptodate when waking pollers"). What the test does is: 1 mkstemp() a 128M file on a tmpfs; 2 start $nr_cpu processes, each to loop the following: 2.1 mmap() this file in shared write mode; 2.2 write 0 to this file in a PAGE_SIZE step till the end of the file; 2.3 unmap() this file and repeat this process. 3 After 5 minutes, check how many loops they managed to complete, the higher the better. The commit itself looks innocent enough as it merely changed some event counting mechanism and this test didn't trigger those events at all. Perf shows increased cycles spent on accessing root_mem_cgroup->stat_cpu in count_memcg_event_mm()(called by handle_mm_fault()) and in __mod_memcg_state() called by page_add_file_rmap(). So it's likely due to the changed layout of 'struct mem_cgroup' that either make stat_cpu falling into a constantly modifying cacheline or some hot fields stop being in the same cacheline. I verified this by moving memory_events[] back to where it was: : --- a/include/linux/memcontrol.h : +++ b/include/linux/memcontrol.h : @@ -205,7 +205,6 @@ struct mem_cgroup { : int oom_kill_disable; : : /* memory.events */ : - atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; : struct cgroup_file events_file; : : /* protect arrays of thresholds */ : @@ -238,6 +237,7 @@ struct mem_cgroup { : struct mem_cgroup_stat_cpu __percpu *stat_cpu; : atomic_long_t stat[MEMCG_NR_STAT]; : atomic_long_t events[NR_VM_EVENT_ITEMS]; : + atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; : : unsigned long socket_pressure; And performance restored. Later investigation found that as long as the following 3 fields moving_account, move_lock_task and stat_cpu are in the same cacheline, performance will be good. To avoid future performance surprise by other commits changing the layout of 'struct mem_cgroup', this patch makes sure the 3 fields stay in the same cacheline. One concern of this approach is, moving_account and move_lock_task could be modified when a process changes memory cgroup while stat_cpu is a always read field, it might hurt to place them in the same cacheline. I assume it is rare for a process to change memory cgroup so this should be OK. Link: https://lkml.kernel.org/r/20180528114019.GF9904@yexl-desktop Link: http://lkml.kernel.org/r/20180601071115.GA27302@intel.com Signed-off-by: Aaron Lu Reported-by: kernel test robot Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9c04cf8e6487..4f52ec755725 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -166,6 +166,15 @@ enum memcg_kmem_state { KMEM_ONLINE, }; +#if defined(CONFIG_SMP) +struct memcg_padding { + char x[0]; +} ____cacheline_internodealigned_in_smp; +#define MEMCG_PADDING(name) struct memcg_padding name; +#else +#define MEMCG_PADDING(name) +#endif + /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide @@ -212,7 +221,6 @@ struct mem_cgroup { int oom_kill_disable; /* memory.events */ - atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; struct cgroup_file events_file; /* handle for "memory.swap.events" */ @@ -235,19 +243,26 @@ struct mem_cgroup { * mem_cgroup ? And what type of charges should we move ? */ unsigned long move_charge_at_immigrate; + /* taken only while moving_account > 0 */ + spinlock_t move_lock; + unsigned long move_lock_flags; + + MEMCG_PADDING(_pad1_); + /* * set > 0 if pages under this cgroup are moving to other cgroup. */ atomic_t moving_account; - /* taken only while moving_account > 0 */ - spinlock_t move_lock; struct task_struct *move_lock_task; - unsigned long move_lock_flags; /* memory.stat */ struct mem_cgroup_stat_cpu __percpu *stat_cpu; + + MEMCG_PADDING(_pad2_); + atomic_long_t stat[MEMCG_NR_STAT]; atomic_long_t events[NR_VM_EVENT_ITEMS]; + atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; unsigned long socket_pressure; -- cgit v1.2.3 From 72eb7de9c1580cf5705d4f592aca21a8438fde22 Mon Sep 17 00:00:00 2001 From: Sahara Date: Thu, 7 Jun 2018 17:09:48 -0700 Subject: mm: remove page_is_poisoned() from linux/mm.h When commit bd33ef368135 ("mm: enable page poisoning early at boot") got rid of the PAGE_EXT_DEBUG_POISON, page_is_poisoned in the header left behind. This patch cleans up the leftovers under the table. Link: http://lkml.kernel.org/r/1528101069-21637-1-git-send-email-kpark3469@gmail.com Signed-off-by: Sahara Acked-by: Michal Hocko Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1dd588b7c649..f0f3905f8bb8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2532,12 +2532,10 @@ extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); extern void kernel_poison_pages(struct page *page, int numpages, int enable); -extern bool page_is_poisoned(struct page *page); #else static inline bool page_poisoning_enabled(void) { return false; } static inline void kernel_poison_pages(struct page *page, int numpages, int enable) { } -static inline bool page_is_poisoned(struct page *page) { return false; } #endif #ifdef CONFIG_DEBUG_PAGEALLOC -- cgit v1.2.3 From 6d0e8d53849fb491549a01893d786bf33d4b28df Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 7 Jun 2018 17:10:27 -0700 Subject: include/linux/types.h: define aligned_ types based on uapi header has the same typedefs except that it prefixes them with double-underscore for user space. Use them for the kernel space typedefs. Link: http://lkml.kernel.org/r/1526350925-14922-2-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Reviewed-by: Andrew Morton Cc: Geert Uytterhoeven Cc: Alexey Dobriyan Cc: Lihao Liang Cc: Philippe Ombredanne Cc: Pekka Enberg Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/types.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/types.h b/include/linux/types.h index ec13d02b3481..be1589763e0a 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -115,9 +115,9 @@ typedef __s64 int64_t; #endif /* this is a special 64bit data type that is 8-byte aligned */ -#define aligned_u64 __u64 __attribute__((aligned(8))) -#define aligned_be64 __be64 __attribute__((aligned(8))) -#define aligned_le64 __le64 __attribute__((aligned(8))) +#define aligned_u64 __aligned_u64 +#define aligned_be64 __aligned_be64 +#define aligned_le64 __aligned_le64 /** * The type used for indexing onto a disc or disc partition. -- cgit v1.2.3 From b22f22a3c199b3282b05a927c60eb8edbe42d25d Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 7 Jun 2018 17:10:30 -0700 Subject: include/linux/types.h: use fixed width types without double-underscore prefix This header file is not exported. It is safe to reference types without double-underscore prefix. Link: http://lkml.kernel.org/r/1526350925-14922-3-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Cc: Geert Uytterhoeven Cc: Alexey Dobriyan Cc: Lihao Liang Cc: Philippe Ombredanne Cc: Pekka Enberg Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/types.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/types.h b/include/linux/types.h index be1589763e0a..9834e90aa010 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -10,14 +10,14 @@ #define DECLARE_BITMAP(name,bits) \ unsigned long name[BITS_TO_LONGS(bits)] -typedef __u32 __kernel_dev_t; +typedef u32 __kernel_dev_t; typedef __kernel_fd_set fd_set; typedef __kernel_dev_t dev_t; typedef __kernel_ino_t ino_t; typedef __kernel_mode_t mode_t; typedef unsigned short umode_t; -typedef __u32 nlink_t; +typedef u32 nlink_t; typedef __kernel_off_t off_t; typedef __kernel_pid_t pid_t; typedef __kernel_daddr_t daddr_t; @@ -95,23 +95,23 @@ typedef unsigned long ulong; #ifndef __BIT_TYPES_DEFINED__ #define __BIT_TYPES_DEFINED__ -typedef __u8 u_int8_t; -typedef __s8 int8_t; -typedef __u16 u_int16_t; -typedef __s16 int16_t; -typedef __u32 u_int32_t; -typedef __s32 int32_t; +typedef u8 u_int8_t; +typedef s8 int8_t; +typedef u16 u_int16_t; +typedef s16 int16_t; +typedef u32 u_int32_t; +typedef s32 int32_t; #endif /* !(__BIT_TYPES_DEFINED__) */ -typedef __u8 uint8_t; -typedef __u16 uint16_t; -typedef __u32 uint32_t; +typedef u8 uint8_t; +typedef u16 uint16_t; +typedef u32 uint32_t; #if defined(__GNUC__) -typedef __u64 uint64_t; -typedef __u64 u_int64_t; -typedef __s64 int64_t; +typedef u64 uint64_t; +typedef u64 u_int64_t; +typedef s64 int64_t; #endif /* this is a special 64bit data type that is 8-byte aligned */ -- cgit v1.2.3 From cbdc61ae1fa5d824fcfd59282b040f21144999ab Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 7 Jun 2018 17:10:51 -0700 Subject: lib/mpi: headers cleanup MPI headers contain definitions for huge number of non-existing functions. Most part of these functions was removed in 2012 by Dmitry Kasatkin - 7cf4206a99d1 ("Remove unused code from MPI library") - 9e235dcaf4f6 ("Revert "crypto: GnuPG based MPI lib - additional ...") - bc95eeadf5c6 ("lib/mpi: removed unused functions") however headers wwere not updated properly. Also I deleted some unused macros. Link: http://lkml.kernel.org/r/fb2fc1ef-1185-f0a3-d8d0-173d2f97bbaf@virtuozzo.com Signed-off-by: Vasily Averin Reviewed-by: Andrew Morton Cc: Dmitry Kasatkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mpi.h | 61 ----------------------------------------------------- 1 file changed, 61 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mpi.h b/include/linux/mpi.h index 1cc5ffb769af..7cd1473c64a4 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -53,93 +53,32 @@ struct gcry_mpi { typedef struct gcry_mpi *MPI; #define mpi_get_nlimbs(a) ((a)->nlimbs) -#define mpi_is_neg(a) ((a)->sign) /*-- mpiutil.c --*/ MPI mpi_alloc(unsigned nlimbs); -MPI mpi_alloc_secure(unsigned nlimbs); -MPI mpi_alloc_like(MPI a); void mpi_free(MPI a); int mpi_resize(MPI a, unsigned nlimbs); -int mpi_copy(MPI *copy, const MPI a); -void mpi_clear(MPI a); -int mpi_set(MPI w, MPI u); -int mpi_set_ui(MPI w, ulong u); -MPI mpi_alloc_set_ui(unsigned long u); -void mpi_m_check(MPI a); -void mpi_swap(MPI a, MPI b); /*-- mpicoder.c --*/ -MPI do_encode_md(const void *sha_buffer, unsigned nbits); MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes); MPI mpi_read_from_buffer(const void *buffer, unsigned *ret_nread); MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int len); -int mpi_fromstr(MPI val, const char *str); -u32 mpi_get_keyid(MPI a, u32 *keyid); void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign); int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes, int *sign); -void *mpi_get_secure_buffer(MPI a, unsigned *nbytes, int *sign); int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned nbytes, int *sign); -#define log_mpidump g10_log_mpidump - -/*-- mpi-add.c --*/ -int mpi_add_ui(MPI w, MPI u, ulong v); -int mpi_add(MPI w, MPI u, MPI v); -int mpi_addm(MPI w, MPI u, MPI v, MPI m); -int mpi_sub_ui(MPI w, MPI u, ulong v); -int mpi_sub(MPI w, MPI u, MPI v); -int mpi_subm(MPI w, MPI u, MPI v, MPI m); - -/*-- mpi-mul.c --*/ -int mpi_mul_ui(MPI w, MPI u, ulong v); -int mpi_mul_2exp(MPI w, MPI u, ulong cnt); -int mpi_mul(MPI w, MPI u, MPI v); -int mpi_mulm(MPI w, MPI u, MPI v, MPI m); - -/*-- mpi-div.c --*/ -ulong mpi_fdiv_r_ui(MPI rem, MPI dividend, ulong divisor); -int mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor); -int mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor); -int mpi_fdiv_qr(MPI quot, MPI rem, MPI dividend, MPI divisor); -int mpi_tdiv_r(MPI rem, MPI num, MPI den); -int mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den); -int mpi_tdiv_q_2exp(MPI w, MPI u, unsigned count); -int mpi_divisible_ui(const MPI dividend, ulong divisor); - -/*-- mpi-gcd.c --*/ -int mpi_gcd(MPI g, const MPI a, const MPI b); - /*-- mpi-pow.c --*/ -int mpi_pow(MPI w, MPI u, MPI v); int mpi_powm(MPI res, MPI base, MPI exp, MPI mod); -/*-- mpi-mpow.c --*/ -int mpi_mulpowm(MPI res, MPI *basearray, MPI *exparray, MPI mod); - /*-- mpi-cmp.c --*/ int mpi_cmp_ui(MPI u, ulong v); int mpi_cmp(MPI u, MPI v); -/*-- mpi-scan.c --*/ -int mpi_getbyte(MPI a, unsigned idx); -void mpi_putbyte(MPI a, unsigned idx, int value); -unsigned mpi_trailing_zeros(MPI a); - /*-- mpi-bit.c --*/ void mpi_normalize(MPI a); unsigned mpi_get_nbits(MPI a); -int mpi_test_bit(MPI a, unsigned n); -int mpi_set_bit(MPI a, unsigned n); -int mpi_set_highbit(MPI a, unsigned n); -void mpi_clear_highbit(MPI a, unsigned n); -void mpi_clear_bit(MPI a, unsigned n); -int mpi_rshift(MPI x, MPI a, unsigned n); - -/*-- mpi-inv.c --*/ -int mpi_invm(MPI x, MPI u, MPI v); /* inline functions */ -- cgit v1.2.3 From 28e89fd914a22e8a64f05ae2f0048b06165f371b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 7 Jun 2018 14:42:05 -0600 Subject: block: add bioset_init_from_src() helper Add a helper that allows a caller to initialize a new bio_set, using the settings from an existing bio_set. Reported-by: Venkat R.B Tested-by: Venkat R.B Tested-by: Li Wang Reviewed-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 810a8bee8f85..84abd1706dcb 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -417,6 +417,7 @@ enum { extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); +extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *); extern void bio_put(struct bio *); -- cgit v1.2.3 From ec84b27f9b3b569f9235413d1945a2006b97b0aa Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Fri, 25 May 2018 11:05:06 +0200 Subject: rcu: Update documentation of rcu_read_unlock() Since commit b4abf91047cf ("rtmutex: Make wait_lock irq safe") the explanation in rcu_read_unlock() documentation about irq unsafe rtmutex wait_lock is no longer valid. Remove it to prevent kernel developers reading the documentation to rely on it. Suggested-by: Eric W. Biederman Signed-off-by: Anna-Maria Gleixner Signed-off-by: Thomas Gleixner Reviewed-by: Paul E. McKenney Acked-by: "Eric W. Biederman" Cc: bigeasy@linutronix.de Link: https://lkml.kernel.org/r/20180525090507.22248-2-anna-maria@linutronix.de --- include/linux/rcupdate.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e679b175b411..65163aa0bb04 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -652,9 +652,7 @@ static inline void rcu_read_lock(void) * Unfortunately, this function acquires the scheduler's runqueue and * priority-inheritance spinlocks. This means that deadlock could result * if the caller of rcu_read_unlock() already holds one of these locks or - * any lock that is ever acquired while holding them; or any lock which - * can be taken from interrupt context because rcu_boost()->rt_mutex_lock() - * does not disable irqs while taking ->wait_lock. + * any lock that is ever acquired while holding them. * * That said, RCU readers are never priority boosted unless they were * preempted. Therefore, one way to avoid deadlock is to make sure -- cgit v1.2.3 From d5318d302e7cf6583ec85a2a8bfbb3a3910ae372 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 20 Nov 2017 11:45:47 +0100 Subject: backlight: as3711_bl: Fix Device Tree node leaks Two framebuffer device-node names were looked up during probe, but were only used as flags to indicate the presence of two framebuffer device. Drop the unused framebuffer name along with a likewise unused device pointer from the driver data, and update the platform data to pass in booleans instead of the framebuffer strings. This allows us do drop the node references acquired during probe, which would otherwise leak. Note that there are no other in-kernel users of the modified platform-data fields. Fixes: 59eb2b5e57ea ("drivers/video/backlight/as3711_bl.c: add OF support") Signed-off-by: Johan Hovold Acked-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/mfd/as3711.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/as3711.h b/include/linux/mfd/as3711.h index 34cc85864be5..ddd0b953323b 100644 --- a/include/linux/mfd/as3711.h +++ b/include/linux/mfd/as3711.h @@ -108,9 +108,9 @@ struct as3711_regulator_pdata { }; struct as3711_bl_pdata { - const char *su1_fb; + bool su1_fb; int su1_max_uA; - const char *su2_fb; + bool su2_fb; int su2_max_uA; enum as3711_su2_feedback su2_feedback; enum as3711_su2_fbprot su2_fbprot; -- cgit v1.2.3 From 9f4a8a2d7f9d71093f41c4bb0ef8707e8145bad3 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 17 May 2018 15:58:00 +1000 Subject: fsi/sbefifo: Add driver for the SBE FIFO This driver provides an in-kernel and a user API for accessing the command FIFO of the SBE (Self Boot Engine) of the POWER9 processor, via the FSI bus. It provides an in-kernel interface to submit command and receive responses, along with a helper to locate and analyse the response status block. It's a simple synchronous submit() type API. The user interface uses the write/read interface that an earlier version of this driver already provided, however it has some specific limitations in order to keep the driver simple and avoid using up a lot of kernel memory: - The user should perform a single write() with the command and a single read() to get the response (with a buffer big enough to hold the entire response). - On a write() the command is simply "stored" into a kernel buffer, it is submitted as one operation on the subsequent read(). This allows to have the code write directly from the FIFO into the user buffer and avoid hogging the SBE between the write() and read() syscall as it's critical that the SBE be freed asap to respond to the host. An extra write() will simply replace the previously written command. - A write of a single 4 bytes containing the value 0x52534554 in big endian will trigger a reset request. No read is necessary, the write() call will return when the reset has been acknowledged or times out. - The command is limited to 4K bytes. Signed-off-by: Benjamin Herrenschmidt Tested-by: Joel Stanley --- --- include/linux/fsi-sbefifo.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) create mode 100644 include/linux/fsi-sbefifo.h (limited to 'include/linux') diff --git a/include/linux/fsi-sbefifo.h b/include/linux/fsi-sbefifo.h new file mode 100644 index 000000000000..13f9ebeaa25e --- /dev/null +++ b/include/linux/fsi-sbefifo.h @@ -0,0 +1,33 @@ +/* + * SBEFIFO FSI Client device driver + * + * Copyright (C) IBM Corporation 2017 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERGCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef LINUX_FSI_SBEFIFO_H +#define LINUX_FSI_SBEFIFO_H + +#define SBEFIFO_CMD_PUT_OCC_SRAM 0xa404 +#define SBEFIFO_CMD_GET_OCC_SRAM 0xa403 +#define SBEFIFO_CMD_GET_SBE_FFDC 0xa801 + +#define SBEFIFO_MAX_FFDC_SIZE 0x2000 + +struct device; + +int sbefifo_submit(struct device *dev, const __be32 *command, size_t cmd_len, + __be32 *response, size_t *resp_len); + +int sbefifo_parse_status(struct device *dev, u16 cmd, __be32 *response, + size_t resp_len, size_t *data_len); + +#endif /* LINUX_FSI_SBEFIFO_H */ -- cgit v1.2.3 From b06c0b2f087ab498d51d50f5ae353133b602f614 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 12 Jun 2018 10:24:13 +0200 Subject: Revert "PM / runtime: Fixup reference counting of device link suppliers at probe" Revert commit 1e8378619841 (PM / runtime: Fixup reference counting of device link suppliers at probe), as it has introduced a regression and the condition it was designed to address should be covered by the existing code. Reported-by: Marek Szyprowski Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index db5dbbf7a48d..f0fc4700b6ff 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -56,7 +56,8 @@ extern void pm_runtime_update_max_time_suspended(struct device *dev, s64 delta_ns); extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); extern void pm_runtime_clean_up_links(struct device *dev); -extern void pm_runtime_resume_suppliers(struct device *dev); +extern void pm_runtime_get_suppliers(struct device *dev); +extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device *dev); @@ -172,7 +173,8 @@ static inline unsigned long pm_runtime_autosuspend_expiration( static inline void pm_runtime_set_memalloc_noio(struct device *dev, bool enable){} static inline void pm_runtime_clean_up_links(struct device *dev) {} -static inline void pm_runtime_resume_suppliers(struct device *dev) {} +static inline void pm_runtime_get_suppliers(struct device *dev) {} +static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device *dev) {} -- cgit v1.2.3 From 00979ce4fcc90d488c7f27f750097adc6b11bd07 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 11 Jun 2018 11:35:26 +0900 Subject: linux/linkage.h: replace VMLINUX_SYMBOL_STR() with __stringify() With the special case handling for Blackfin and Metag was removed by commit 94e58e0ac312 ("export.h: remove code for prefixing symbols with underscore"), VMLINUX_SYMBOL_STR() is now equivalent to __stringify(). Replace the remaining usages in to prepare for the entire removal of VMLINUX_SYMBOL_STR(). Signed-off-by: Masahiro Yamada --- include/linux/linkage.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index f68db9e450eb..d7618c41f74c 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -24,16 +24,16 @@ #ifndef cond_syscall #define cond_syscall(x) asm( \ - ".weak " VMLINUX_SYMBOL_STR(x) "\n\t" \ - ".set " VMLINUX_SYMBOL_STR(x) "," \ - VMLINUX_SYMBOL_STR(sys_ni_syscall)) + ".weak " __stringify(x) "\n\t" \ + ".set " __stringify(x) "," \ + __stringify(sys_ni_syscall)) #endif #ifndef SYSCALL_ALIAS #define SYSCALL_ALIAS(alias, name) asm( \ - ".globl " VMLINUX_SYMBOL_STR(alias) "\n\t" \ - ".set " VMLINUX_SYMBOL_STR(alias) "," \ - VMLINUX_SYMBOL_STR(name)) + ".globl " __stringify(alias) "\n\t" \ + ".set " __stringify(alias) "," \ + __stringify(name)) #endif #define __page_aligned_data __section(.data..page_aligned) __aligned(PAGE_SIZE) -- cgit v1.2.3 From 155fb5c5fae72d1faa2067d6fa0a5be12279c689 Mon Sep 17 00:00:00 2001 From: Prashant Bhole Date: Mon, 28 May 2018 18:14:49 +0900 Subject: netfilter: fix null-ptr-deref in nf_nat_decode_session Add null check for nat_hook in nf_nat_decode_session() [ 195.648098] UBSAN: Undefined behaviour in ./include/linux/netfilter.h:348:14 [ 195.651366] BUG: KASAN: null-ptr-deref in __xfrm_policy_check+0x208/0x1d70 [ 195.653888] member access within null pointer of type 'struct nf_nat_hook' [ 195.653896] CPU: 3 PID: 0 Comm: swapper/3 Not tainted 4.17.0-rc6+ #5 [ 195.656320] Read of size 8 at addr 0000000000000008 by task ping/2469 [ 195.658715] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 195.658721] Call Trace: [ 195.661087] [ 195.669341] [ 195.670574] dump_stack+0xc6/0x150 [ 195.672156] ? dump_stack_print_info.cold.0+0x1b/0x1b [ 195.674121] ? ubsan_prologue+0x31/0x92 [ 195.676546] ubsan_epilogue+0x9/0x49 [ 195.678159] handle_null_ptr_deref+0x11a/0x130 [ 195.679800] ? sprint_OID+0x1a0/0x1a0 [ 195.681322] __ubsan_handle_type_mismatch_v1+0xd5/0x11d [ 195.683146] ? ubsan_prologue+0x92/0x92 [ 195.684642] __xfrm_policy_check+0x18ef/0x1d70 [ 195.686294] ? rt_cache_valid+0x118/0x180 [ 195.687804] ? __xfrm_route_forward+0x410/0x410 [ 195.689463] ? fib_multipath_hash+0x700/0x700 [ 195.691109] ? kvm_sched_clock_read+0x23/0x40 [ 195.692805] ? pvclock_clocksource_read+0xf6/0x280 [ 195.694409] ? graph_lock+0xa0/0xa0 [ 195.695824] ? pvclock_clocksource_read+0xf6/0x280 [ 195.697508] ? pvclock_read_flags+0x80/0x80 [ 195.698981] ? kvm_sched_clock_read+0x23/0x40 [ 195.700347] ? sched_clock+0x5/0x10 [ 195.701525] ? sched_clock_cpu+0x18/0x1a0 [ 195.702846] tcp_v4_rcv+0x1d32/0x1de0 [ 195.704115] ? lock_repin_lock+0x70/0x270 [ 195.707072] ? pvclock_read_flags+0x80/0x80 [ 195.709302] ? tcp_v4_early_demux+0x4b0/0x4b0 [ 195.711833] ? lock_acquire+0x195/0x380 [ 195.714222] ? ip_local_deliver_finish+0xfc/0x770 [ 195.716967] ? raw_rcv+0x2b0/0x2b0 [ 195.718856] ? lock_release+0xa00/0xa00 [ 195.720938] ip_local_deliver_finish+0x1b9/0x770 [...] Fixes: 2c205dd3981f ("netfilter: add struct nf_nat_hook and use it") Signed-off-by: Prashant Bhole Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 04551af2ff23..dd2052f0efb7 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -345,7 +345,7 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) rcu_read_lock(); nat_hook = rcu_dereference(nf_nat_hook); - if (nat_hook->decode_session) + if (nat_hook && nat_hook->decode_session) nat_hook->decode_session(skb, fl); rcu_read_unlock(); #endif -- cgit v1.2.3 From ccfbb5bed407053b27492a9adc06064d949a9aa6 Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Tue, 12 Jun 2018 18:16:20 +0200 Subject: atomic: Add irqsave variant of atomic_dec_and_lock() There are in-tree users of atomic_dec_and_lock() which must acquire the spin lock with interrupts disabled. To workaround the lack of an irqsave variant of atomic_dec_and_lock() they use local_irq_save() at the call site. This causes extra code and creates in some places unneeded long interrupt disabled times. These places need also extra treatment for PREEMPT_RT due to the disconnect of the irq disabling and the lock function. Implement the missing irqsave variant of the function. Signed-off-by: Anna-Maria Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r20180612161621.22645-3-bigeasy@linutronix.de --- include/linux/spinlock.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 1e8a46435838..fd57888d4942 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -427,6 +427,11 @@ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); #define atomic_dec_and_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) +extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, + unsigned long *flags); +#define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ + __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) + int alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp); -- cgit v1.2.3 From 7ea959c45769612aa92557fb6464679f5fec7d9e Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Tue, 12 Jun 2018 18:16:21 +0200 Subject: locking/refcounts: Implement refcount_dec_and_lock_irqsave() There are in-tree users of refcount_dec_and_lock() which must acquire the spin lock with interrupts disabled. To workaround the lack of an irqsave variant of refcount_dec_and_lock() they use local_irq_save() at the call site. This causes extra code and creates in some places unneeded long interrupt disabled times. These places need also extra treatment for PREEMPT_RT due to the disconnect of the irq disabling and the lock function. Implement the missing irqsave variant of the function. Signed-off-by: Anna-Maria Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r20180612161621.22645-4-bigeasy@linutronix.de [bigeasy: s@atomic_dec_and_lock@refcount_dec_and_lock@g] --- include/linux/refcount.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 4193c41e383a..a685da2c4522 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -98,5 +98,7 @@ extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock); - +extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, + spinlock_t *lock, + unsigned long *flags); #endif /* _LINUX_REFCOUNT_H */ -- cgit v1.2.3 From 1c542f38ab8d30d9c852a16d49ac5a15267bbf1f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 11 Jun 2018 14:35:55 -0700 Subject: mm: Introduce kvcalloc() The kv*alloc()-family was missing kvcalloc(). Adding this allows for 2-argument multiplication conversions of kvzalloc(a * b, ...) into kvcalloc(a, b, ...). Signed-off-by: Kees Cook --- include/linux/mm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0e493884e6e1..a0fbb9ffe380 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -575,6 +575,11 @@ static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) return kvmalloc(bytes, flags); } +static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) +{ + return kvmalloc_array(n, size, flags | __GFP_ZERO); +} + extern void kvfree(const void *addr); static inline atomic_t *compound_mapcount_ptr(struct page *page) -- cgit v1.2.3 From 050e9baa9dc9fbd9ce2b27f0056990fc9e0a08a0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 14 Jun 2018 12:21:18 +0900 Subject: Kbuild: rename CC_STACKPROTECTOR[_STRONG] config variables The changes to automatically test for working stack protector compiler support in the Kconfig files removed the special STACKPROTECTOR_AUTO option that picked the strongest stack protector that the compiler supported. That was all a nice cleanup - it makes no sense to have the AUTO case now that the Kconfig phase can just determine the compiler support directly. HOWEVER. It also meant that doing "make oldconfig" would now _disable_ the strong stackprotector if you had AUTO enabled, because in a legacy config file, the sane stack protector configuration would look like CONFIG_HAVE_CC_STACKPROTECTOR=y # CONFIG_CC_STACKPROTECTOR_NONE is not set # CONFIG_CC_STACKPROTECTOR_REGULAR is not set # CONFIG_CC_STACKPROTECTOR_STRONG is not set CONFIG_CC_STACKPROTECTOR_AUTO=y and when you ran this through "make oldconfig" with the Kbuild changes, it would ask you about the regular CONFIG_CC_STACKPROTECTOR (that had been renamed from CONFIG_CC_STACKPROTECTOR_REGULAR to just CONFIG_CC_STACKPROTECTOR), but it would think that the STRONG version used to be disabled (because it was really enabled by AUTO), and would disable it in the new config, resulting in: CONFIG_HAVE_CC_STACKPROTECTOR=y CONFIG_CC_HAS_STACKPROTECTOR_NONE=y CONFIG_CC_STACKPROTECTOR=y # CONFIG_CC_STACKPROTECTOR_STRONG is not set CONFIG_CC_HAS_SANE_STACKPROTECTOR=y That's dangerously subtle - people could suddenly find themselves with the weaker stack protector setup without even realizing. The solution here is to just rename not just the old RECULAR stack protector option, but also the strong one. This does that by just removing the CC_ prefix entirely for the user choices, because it really is not about the compiler support (the compiler support now instead automatially impacts _visibility_ of the options to users). This results in "make oldconfig" actually asking the user for their choice, so that we don't have any silent subtle security model changes. The end result would generally look like this: CONFIG_HAVE_CC_STACKPROTECTOR=y CONFIG_CC_HAS_STACKPROTECTOR_NONE=y CONFIG_STACKPROTECTOR=y CONFIG_STACKPROTECTOR_STRONG=y CONFIG_CC_HAS_SANE_STACKPROTECTOR=y where the "CC_" versions really are about internal compiler infrastructure, not the user selections. Acked-by: Masahiro Yamada Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- include/linux/stackprotector.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 16e4d984fe51..cfb7da88c217 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -742,7 +742,7 @@ struct task_struct { pid_t pid; pid_t tgid; -#ifdef CONFIG_CC_STACKPROTECTOR +#ifdef CONFIG_STACKPROTECTOR /* Canary value for the -fstack-protector GCC feature: */ unsigned long stack_canary; #endif diff --git a/include/linux/stackprotector.h b/include/linux/stackprotector.h index 03696c729fb4..6b792d080eee 100644 --- a/include/linux/stackprotector.h +++ b/include/linux/stackprotector.h @@ -6,7 +6,7 @@ #include #include -#ifdef CONFIG_CC_STACKPROTECTOR +#ifdef CONFIG_STACKPROTECTOR # include #else static inline void boot_init_stack_canary(void) -- cgit v1.2.3 From cf65a0f6f6ff7631ba0ac0513a14ca5b65320d80 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Jun 2018 19:01:45 +0200 Subject: dma-mapping: move all DMA mapping code to kernel/dma Currently the code is split over various files with dma- prefixes in the lib/ and drives/base directories, and the number of files keeps growing. Move them into a single directory to keep the code together and remove the file name prefixes. To match the irq infrastructure this directory is placed under the kernel/ directory. Signed-off-by: Christoph Hellwig --- include/linux/dma-contiguous.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index b67bf6ac907d..3c5a4cb3eb95 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -48,7 +48,7 @@ * CMA should not be used by the device drivers directly. It is * only a helper framework for dma-mapping subsystem. * - * For more information, see kernel-docs in drivers/base/dma-contiguous.c + * For more information, see kernel-docs in kernel/dma/contiguous.c */ #ifdef __KERNEL__ -- cgit v1.2.3 From da661267398869a553b7f67d739d360aaa1361b6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 14 Jun 2018 13:58:45 +0200 Subject: blk-mq: don't time out requests again that are in the timeout handler We can currently call the timeout handler again on a request that has already been handed over to the timeout handler. Prevent that with a new flag. Fixes: 12f5b931 ("blk-mq: Remove generation seqeunce") Reported-by: Andrew Randrianasulu Tested-by: Andrew Randrianasulu Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bca3a92eb55f..fa6f11751430 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -127,6 +127,8 @@ typedef __u32 __bitwise req_flags_t; #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) /* already slept for hybrid poll */ #define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) +/* ->timeout has been called, don't expire again */ +#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ -- cgit v1.2.3 From e6c3456aa897c9799de5423b28550efad14a51b0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 14 Jun 2018 14:26:47 +0200 Subject: blk-mq: remove blk_mq_tagset_iter Unused now that nvme stopped using it. Signed-off-by: Christoph Hellwig Reviewed-by: Jens Axboe --- include/linux/blk-mq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index fb355173f3c7..e3147eb74222 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -281,8 +281,6 @@ void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); -int blk_mq_tagset_iter(struct blk_mq_tag_set *set, void *data, - int (reinit_request)(void *, struct request *)); int blk_mq_map_queues(struct blk_mq_tag_set *set); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); -- cgit v1.2.3 From 92ee383f6daab4da5471b86f6fdaba775e6928f6 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 14 Jun 2018 15:26:27 -0700 Subject: mm: fix race between kmem_cache destroy, create and deactivate The memcg kmem cache creation and deactivation (SLUB only) is asynchronous. If a root kmem cache is destroyed whose memcg cache is in the process of creation or deactivation, the kernel may crash. Example of one such crash: general protection fault: 0000 [#1] SMP PTI CPU: 1 PID: 1721 Comm: kworker/14:1 Not tainted 4.17.0-smp ... Workqueue: memcg_kmem_cache kmemcg_deactivate_workfn RIP: 0010:has_cpu_slab ... Call Trace: ? on_each_cpu_cond __kmem_cache_shrink kmemcg_cache_deact_after_rcu kmemcg_deactivate_workfn process_one_work worker_thread kthread ret_from_fork+0x35/0x40 To fix this race, on root kmem cache destruction, mark the cache as dying and flush the workqueue used for memcg kmem cache creation and deactivation. SLUB's memcg kmem cache deactivation also includes RCU callback and thus make sure all previous registered RCU callbacks have completed as well. [shakeelb@google.com: handle the RCU callbacks for SLUB deactivation] Link: http://lkml.kernel.org/r/20180611192951.195727-1-shakeelb@google.com [shakeelb@google.com: add more documentation, rename fields for readability] Link: http://lkml.kernel.org/r/20180522201336.196994-1-shakeelb@google.com [akpm@linux-foundation.org: fix build, per Shakeel] [shakeelb@google.com: v3. Instead of refcount, flush the workqueue] Link: http://lkml.kernel.org/r/20180530001204.183758-1-shakeelb@google.com Link: http://lkml.kernel.org/r/20180521174116.171846-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Vladimir Davydov Cc: Michal Hocko Cc: Greg Thelen Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Johannes Weiner Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 4d759e1ddc33..14e3fe4bd6a1 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -600,6 +600,7 @@ struct memcg_cache_params { struct memcg_cache_array __rcu *memcg_caches; struct list_head __root_caches_node; struct list_head children; + bool dying; }; struct { struct mem_cgroup *memcg; -- cgit v1.2.3 From 0ed557aa813922f6f32adec69e266532091c895b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 14 Jun 2018 15:27:41 -0700 Subject: sched/core / kcov: avoid kcov_area during task switch During a context switch, we first switch_mm() to the next task's mm, then switch_to() that new task. This means that vmalloc'd regions which had previously been faulted in can transiently disappear in the context of the prev task. Functions instrumented by KCOV may try to access a vmalloc'd kcov_area during this window, and as the fault handling code is instrumented, this results in a recursive fault. We must avoid accessing any kcov_area during this window. We can do so with a new flag in kcov_mode, set prior to switching the mm, and cleared once the new task is live. Since task_struct::kcov_mode isn't always a specific enum kcov_mode value, this is made an unsigned int. The manipulation is hidden behind kcov_{prepare,finish}_switch() helpers, which are empty for !CONFIG_KCOV kernels. The code uses macros because I can't use static inline functions without a circular include dependency between and , since the definition of task_struct uses things defined in Link: http://lkml.kernel.org/r/20180504135535.53744-4-mark.rutland@arm.com Signed-off-by: Mark Rutland Acked-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kcov.h | 14 ++++++++++++++ include/linux/sched.h | 2 +- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kcov.h b/include/linux/kcov.h index 3ecf6f5e3a5f..b76a1807028d 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -22,13 +22,27 @@ enum kcov_mode { KCOV_MODE_TRACE_CMP = 3, }; +#define KCOV_IN_CTXSW (1 << 30) + void kcov_task_init(struct task_struct *t); void kcov_task_exit(struct task_struct *t); +#define kcov_prepare_switch(t) \ +do { \ + (t)->kcov_mode |= KCOV_IN_CTXSW; \ +} while (0) + +#define kcov_finish_switch(t) \ +do { \ + (t)->kcov_mode &= ~KCOV_IN_CTXSW; \ +} while (0) + #else static inline void kcov_task_init(struct task_struct *t) {} static inline void kcov_task_exit(struct task_struct *t) {} +static inline void kcov_prepare_switch(struct task_struct *t) {} +static inline void kcov_finish_switch(struct task_struct *t) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index cfb7da88c217..87bf02d93a27 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1130,7 +1130,7 @@ struct task_struct { #ifdef CONFIG_KCOV /* Coverage collection mode enabled for this task (0 if disabled): */ - enum kcov_mode kcov_mode; + unsigned int kcov_mode; /* Size of the kcov_area: */ unsigned int kcov_size; -- cgit v1.2.3 From fe6bdfc8e1e131720abbe77a2eb990c94c9024cb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 14 Jun 2018 15:28:05 -0700 Subject: mm: fix oom_kill event handling Commit e27be240df53 ("mm: memcg: make sure memory.events is uptodate when waking pollers") converted most of memcg event counters to per-memcg atomics, which made them less confusing for a user. The "oom_kill" counter remained untouched, so now it behaves differently than other counters (including "oom"). This adds nothing but confusion. Let's fix this by adding the MEMCG_OOM_KILL event, and follow the MEMCG_OOM approach. This also removes a hack from count_memcg_event_mm(), introduced earlier specially for the OOM_KILL counter. [akpm@linux-foundation.org: fix for droppage of memcg-replace-mm-owner-with-mm-memcg.patch] Link: http://lkml.kernel.org/r/20180508124637.29984-1-guro@fb.com Signed-off-by: Roman Gushchin Acked-by: Konstantin Khlebnikov Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 4f52ec755725..6c6fb116e925 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -53,6 +53,7 @@ enum memcg_memory_event { MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, + MEMCG_OOM_KILL, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, @@ -720,11 +721,8 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (likely(memcg)) { + if (likely(memcg)) count_memcg_events(memcg, idx, 1); - if (idx == OOM_KILL) - cgroup_file_notify(&memcg->events_file); - } rcu_read_unlock(); } @@ -735,6 +733,21 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg, cgroup_file_notify(&memcg->events_file); } +static inline void memcg_memory_event_mm(struct mm_struct *mm, + enum memcg_memory_event event) +{ + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return; + + rcu_read_lock(); + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (likely(memcg)) + memcg_memory_event(memcg, event); + rcu_read_unlock(); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE void mem_cgroup_split_huge_fixup(struct page *head); #endif @@ -756,6 +769,11 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg, { } +static inline void memcg_memory_event_mm(struct mm_struct *mm, + enum memcg_memory_event event) +{ +} + static inline enum mem_cgroup_protection mem_cgroup_protected( struct mem_cgroup *root, struct mem_cgroup *memcg) { -- cgit v1.2.3 From 2d4f545cb14fa2d9865124183f3100d46dc9b3b5 Mon Sep 17 00:00:00 2001 From: Peter Meerwald Date: Mon, 4 Jun 2018 23:34:06 +0200 Subject: rfkill: Fixes and cleanup of kernel-doc in the header file Fixes kerneldoc parameter names to match implementation, rfkill_set_hw_state(), rfkill_set_sw_state(). Fix description of rfkill_resume_polling(). Fix typos in documentation of rfkill_find_type(). Consistently start kerneldoc description with uppercase letter. Signed-off-by: Peter Meerwald-Stadler Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index e6a0031d1b1f..8ad2487a86d5 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -66,7 +66,7 @@ struct rfkill_ops { #if defined(CONFIG_RFKILL) || defined(CONFIG_RFKILL_MODULE) /** - * rfkill_alloc - allocate rfkill structure + * rfkill_alloc - Allocate rfkill structure * @name: name of the struct -- the string is not copied internally * @parent: device that has rf switch on it * @type: type of the switch (RFKILL_TYPE_*) @@ -112,7 +112,7 @@ void rfkill_pause_polling(struct rfkill *rfkill); /** * rfkill_resume_polling(struct rfkill *rfkill) * - * Pause polling -- say transmitter is off for other reasons. + * Resume polling * NOTE: not necessary for suspend/resume -- in that case the * core stops polling anyway */ @@ -130,7 +130,7 @@ void rfkill_resume_polling(struct rfkill *rfkill); void rfkill_unregister(struct rfkill *rfkill); /** - * rfkill_destroy - free rfkill structure + * rfkill_destroy - Free rfkill structure * @rfkill: rfkill structure to be destroyed * * Destroys the rfkill structure. @@ -140,7 +140,7 @@ void rfkill_destroy(struct rfkill *rfkill); /** * rfkill_set_hw_state - Set the internal rfkill hardware block state * @rfkill: pointer to the rfkill class to modify. - * @state: the current hardware block state to set + * @blocked: the current hardware block state to set * * rfkill drivers that get events when the hard-blocked state changes * use this function to notify the rfkill core (and through that also @@ -161,7 +161,7 @@ bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked); /** * rfkill_set_sw_state - Set the internal rfkill software block state * @rfkill: pointer to the rfkill class to modify. - * @state: the current software block state to set + * @blocked: the current software block state to set * * rfkill drivers that get events when the soft-blocked state changes * (yes, some platforms directly act on input but allow changing again) @@ -183,7 +183,7 @@ bool rfkill_set_sw_state(struct rfkill *rfkill, bool blocked); /** * rfkill_init_sw_state - Initialize persistent software block state * @rfkill: pointer to the rfkill class to modify. - * @state: the current software block state to set + * @blocked: the current software block state to set * * rfkill drivers that preserve their software block state over power off * use this function to notify the rfkill core (and through that also @@ -208,17 +208,17 @@ void rfkill_init_sw_state(struct rfkill *rfkill, bool blocked); void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw); /** - * rfkill_blocked - query rfkill block + * rfkill_blocked - Query rfkill block state * * @rfkill: rfkill struct to query */ bool rfkill_blocked(struct rfkill *rfkill); /** - * rfkill_find_type - Helpper for finding rfkill type by name + * rfkill_find_type - Helper for finding rfkill type by name * @name: the name of the type * - * Returns enum rfkill_type that conrresponds the name. + * Returns enum rfkill_type that corresponds to the name. */ enum rfkill_type rfkill_find_type(const char *name); @@ -296,7 +296,7 @@ static inline enum rfkill_type rfkill_find_type(const char *name) const char *rfkill_get_led_trigger_name(struct rfkill *rfkill); /** - * rfkill_set_led_trigger_name -- set the LED trigger name + * rfkill_set_led_trigger_name - Set the LED trigger name * @rfkill: rfkill struct * @name: LED trigger name * -- cgit v1.2.3 From c4cbaf7973a794839af080f13748335976cf3f3f Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Sat, 9 Jun 2018 09:14:42 +0300 Subject: cfg80211: Add support for HE Add support for the HE in cfg80211 and also add userspace API to nl80211 to send rate information out, conforming with P802.11ax_D2.0. Signed-off-by: Liad Kaufman Signed-off-by: Johannes Berg Signed-off-by: Ilan Peer Signed-off-by: Ido Yariv Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 427 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 427 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 8fe7e4306816..e6a6503bfa33 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1539,6 +1539,106 @@ struct ieee80211_vht_operation { __le16 basic_mcs_set; } __packed; +/** + * struct ieee80211_he_cap_elem - HE capabilities element + * + * This structure is the "HE capabilities element" fixed fields as + * described in P802.11ax_D2.0 section 9.4.2.237.2 and 9.4.2.237.3 + */ +struct ieee80211_he_cap_elem { + u8 mac_cap_info[5]; + u8 phy_cap_info[9]; +} __packed; + +#define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 + +/** + * enum ieee80211_he_mcs_support - HE MCS support definitions + * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the + * number of streams + * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported + * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported + * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported + * + * These definitions are used in each 2-bit subfield of the rx_mcs_* + * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are + * both split into 8 subfields by number of streams. These values indicate + * which MCSes are supported for the number of streams the value appears + * for. + */ +enum ieee80211_he_mcs_support { + IEEE80211_HE_MCS_SUPPORT_0_7 = 0, + IEEE80211_HE_MCS_SUPPORT_0_9 = 1, + IEEE80211_HE_MCS_SUPPORT_0_11 = 2, + IEEE80211_HE_MCS_NOT_SUPPORTED = 3, +}; + +/** + * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field + * + * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field + * described in P802.11ax_D2.0 section 9.4.2.237.4 + * + * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel + * widths less than 80MHz. + * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel + * widths less than 80MHz. + * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel + * width 160MHz. + * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel + * width 160MHz. + * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for + * channel width 80p80MHz. + * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for + * channel width 80p80MHz. + */ +struct ieee80211_he_mcs_nss_supp { + __le16 rx_mcs_80; + __le16 tx_mcs_80; + __le16 rx_mcs_160; + __le16 tx_mcs_160; + __le16 rx_mcs_80p80; + __le16 tx_mcs_80p80; +} __packed; + +/** + * struct ieee80211_he_operation - HE capabilities element + * + * This structure is the "HE operation element" fields as + * described in P802.11ax_D2.0 section 9.4.2.238 + */ +struct ieee80211_he_operation { + __le32 he_oper_params; + __le16 he_mcs_nss_set; + /* Optional 0,1,3 or 4 bytes: depends on @he_oper_params */ + u8 optional[0]; +} __packed; + +/** + * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field + * + * This structure is the "MU AC Parameter Record" fields as + * described in P802.11ax_D2.0 section 9.4.2.240 + */ +struct ieee80211_he_mu_edca_param_ac_rec { + u8 aifsn; + u8 ecw_min_max; + u8 mu_edca_timer; +} __packed; + +/** + * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element + * + * This structure is the "MU EDCA Parameter Set element" fields as + * described in P802.11ax_D2.0 section 9.4.2.240 + */ +struct ieee80211_mu_edca_param_set { + u8 mu_qos_info; + struct ieee80211_he_mu_edca_param_ac_rec ac_be; + struct ieee80211_he_mu_edca_param_ac_rec ac_bk; + struct ieee80211_he_mu_edca_param_ac_rec ac_vi; + struct ieee80211_he_mu_edca_param_ac_rec ac_vo; +} __packed; /* 802.11ac VHT Capabilities */ #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 @@ -1577,6 +1677,328 @@ struct ieee80211_vht_operation { #define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 #define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 +/* 802.11ax HE MAC capabilities */ +#define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 +#define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 +#define IEEE80211_HE_MAC_CAP0_TWT_RES 0x04 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP 0x00 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1 0x08 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2 0x10 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3 0x18 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK 0x18 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1 0x00 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2 0x20 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4 0x40 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8 0x60 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16 0x80 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32 0xa0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64 0xc0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED 0xe0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK 0xe0 + +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED 0x00 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128 0x01 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256 0x02 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512 0x03 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK 0x03 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US 0x00 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_1 0x00 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_2 0x10 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_3 0x20 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_4 0x30 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_5 0x40 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_6 0x50 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_7 0x60 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_MASK 0x70 + +/* Link adaptation is split between byte HE_MAC_CAP1 and + * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE + * in which case the following values apply: + * 0 = No feedback. + * 1 = reserved. + * 2 = Unsolicited feedback. + * 3 = both + */ +#define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION 0x80 + +#define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 +#define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 +#define IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED 0x04 +#define IEEE80211_HE_MAC_CAP2_BSR 0x08 +#define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 +#define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 +#define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 +#define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 + +#define IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU 0x01 +#define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 +#define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 + +/* The maximum length of an A-MDPU is defined by the combination of the Maximum + * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the + * same field in the HE capabilities. + */ +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_USE_VHT 0x00 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_1 0x08 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2 0x10 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_RESERVED 0x18 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_MASK 0x18 +#define IEEE80211_HE_MAC_CAP3_A_AMSDU_FRAG 0x20 +#define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 +#define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 + +#define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 +#define IEEE80211_HE_MAC_CAP4_QTP 0x02 +#define IEEE80211_HE_MAC_CAP4_BQR 0x04 +#define IEEE80211_HE_MAC_CAP4_SR_RESP 0x08 +#define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 +#define IEEE80211_HE_MAC_CAP4_OPS 0x20 +#define IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU 0x40 + +/* 802.11ax HE PHY capabilities */ +#define IEEE80211_HE_PHY_CAP0_DUAL_BAND 0x01 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe + +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ 0x01 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ 0x02 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ 0x04 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ 0x08 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK 0x0f +#define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 +#define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 +#define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 +/* Midamble RX Max NSTS is split between byte #2 and byte #3 */ +#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS 0x80 + +#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS 0x01 +#define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 +#define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 +#define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 +#define IEEE80211_HE_PHY_CAP2_DOPPLER_TX 0x10 +#define IEEE80211_HE_PHY_CAP2_DOPPLER_RX 0x20 + +/* Note that the meaning of UL MU below is different between an AP and a non-AP + * sta, where in the AP case it indicates support for Rx and in the non-AP sta + * case it indicates support for Tx. + */ +#define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO 0x40 +#define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO 0x80 + +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK 0x01 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK 0x02 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM 0x03 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK 0x03 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2 0x04 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK 0x08 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK 0x10 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM 0x18 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK 0x18 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2 0x20 +#define IEEE80211_HE_PHY_CAP3_RX_HE_MU_PPDU_FROM_NON_AP_STA 0x40 +#define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER 0x80 + +#define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE 0x01 +#define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER 0x02 + +/* Minimal allowed value of Max STS under 80MHz is 3 */ +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 0x0c +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 0x10 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6 0x14 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7 0x18 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8 0x1c +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK 0x1c + +/* Minimal allowed value of Max STS above 80MHz is 3 */ +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 0x60 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5 0x80 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6 0xa0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7 0xc0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 0xe0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK 0xe0 + +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1 0x00 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 0x01 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3 0x02 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4 0x03 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5 0x04 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6 0x05 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7 0x06 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8 0x07 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK 0x07 + +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1 0x00 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 0x08 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3 0x10 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4 0x18 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5 0x20 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6 0x28 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7 0x30 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8 0x38 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK 0x38 + +#define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK 0x40 +#define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK 0x80 + +#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU 0x01 +#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU 0x02 +#define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMER_FB 0x04 +#define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMER_FB 0x08 +#define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB 0x10 +#define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE 0x20 +#define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO 0x40 +#define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT 0x80 + +#define IEEE80211_HE_PHY_CAP7_SRP_BASED_SR 0x01 +#define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR 0x02 +#define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI 0x04 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_1 0x08 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_2 0x10 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_3 0x18 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_4 0x20 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_5 0x28 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_6 0x30 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_7 0x38 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK 0x38 +#define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ 0x40 +#define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ 0x80 + +#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI 0x01 +#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G 0x02 +#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 +#define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 +#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 +#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_2X_AND_1XLTF 0x20 + +/* 802.11ax HE TX/RX MCS NSS Support */ +#define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS (11) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK 0x07c0 +#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK 0xf800 + +/* TX/RX HE MCS Support field Highest MCS subfield encoding */ +enum ieee80211_he_highest_mcs_supported_subfield_enc { + HIGHEST_MCS_SUPPORTED_MCS7 = 0, + HIGHEST_MCS_SUPPORTED_MCS8, + HIGHEST_MCS_SUPPORTED_MCS9, + HIGHEST_MCS_SUPPORTED_MCS10, + HIGHEST_MCS_SUPPORTED_MCS11, +}; + +/* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */ +static inline u8 +ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap) +{ + u8 count = 4; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) + count += 4; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) + count += 4; + + return count; +} + +/* 802.11ax HE PPE Thresholds */ +#define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS (1) +#define IEEE80211_PPE_THRES_NSS_POS (0) +#define IEEE80211_PPE_THRES_NSS_MASK (7) +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU \ + (BIT(5) | BIT(6)) +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78 +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3) +#define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3) + +/* + * Calculate 802.11ax HE capabilities IE PPE field size + * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8* + */ +static inline u8 +ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) +{ + u8 n; + + if ((phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0) + return 0; + + n = hweight8(ppe_thres_hdr & + IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >> + IEEE80211_PPE_THRES_NSS_POS)); + + /* + * Each pair is 6 bits, and we need to add the 7 "header" bits to the + * total size. + */ + n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7; + n = DIV_ROUND_UP(n, 8); + + return n; +} + +/* HE Operation defines */ +#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x0000003f +#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x000001c0 +#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET 6 +#define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000200 +#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x000ffc00 +#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 10 +#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x000100000 +#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x000200000 +#define IEEE80211_HE_OPERATION_MULTI_BSSID_AP 0x10000000 +#define IEEE80211_HE_OPERATION_TX_BSSID_INDICATOR 0x20000000 +#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x40000000 + +/* + * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size + * @he_oper_ie: byte data of the He Operations IE, stating from the the byte + * after the ext ID byte. It is assumed that he_oper_ie has at least + * sizeof(struct ieee80211_he_operation) bytes, checked already in + * ieee802_11_parse_elems_crc() + * @return the actual size of the IE data (not including header), or 0 on error + */ +static inline u8 +ieee80211_he_oper_size(const u8 *he_oper_ie) +{ + struct ieee80211_he_operation *he_oper = (void *)he_oper_ie; + u8 oper_len = sizeof(struct ieee80211_he_operation); + u32 he_oper_params; + + /* Make sure the input is not NULL */ + if (!he_oper_ie) + return 0; + + /* Calc required length */ + he_oper_params = le32_to_cpu(he_oper->he_oper_params); + if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) + oper_len += 3; + if (he_oper_params & IEEE80211_HE_OPERATION_MULTI_BSSID_AP) + oper_len++; + + /* Add the first byte (extension ID) to the total length */ + oper_len++; + + return oper_len; +} + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 @@ -1992,6 +2414,11 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_FILS_WRAPPED_DATA = 8, WLAN_EID_EXT_FILS_PUBLIC_KEY = 12, WLAN_EID_EXT_FILS_NONCE = 13, + WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE = 14, + WLAN_EID_EXT_HE_CAPABILITY = 35, + WLAN_EID_EXT_HE_OPERATION = 36, + WLAN_EID_EXT_UORA = 37, + WLAN_EID_EXT_HE_MU_EDCA = 38, }; /* Action category code */ -- cgit v1.2.3 From be7f99c536c5aeebad29082b7d8dce32077fea14 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Jun 2018 13:55:07 +0200 Subject: block: remov blk_queue_invalidate_tags This function is entirely unused, so remove it and the tag_queue_busy member of struct request_queue. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index fa6f11751430..9154570edf29 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -562,7 +562,6 @@ struct request_queue { unsigned int dma_alignment; struct blk_queue_tag *queue_tags; - struct list_head tag_busy_list; unsigned int nr_sorted; unsigned int in_flight[2]; @@ -1375,7 +1374,6 @@ extern void blk_queue_end_tag(struct request_queue *, struct request *); extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int); extern void blk_queue_free_tags(struct request_queue *); extern int blk_queue_resize_tags(struct request_queue *, int); -extern void blk_queue_invalidate_tags(struct request_queue *); extern struct blk_queue_tag *blk_init_tags(int, int); extern void blk_free_tags(struct blk_queue_tag *); -- cgit v1.2.3 From 0da0b7fd73e4f20e1a987dfade0b36bb4813cf10 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 15 Jun 2018 15:19:22 +0100 Subject: afs: Display manually added cells in dynamic root mount Alter the dynroot mount so that cells created by manipulation of /proc/fs/afs/cells and /proc/fs/afs/rootcell and by specification of a root cell as a module parameter will cause directories for those cells to be created in the dynamic root superblock for the network namespace[*]. To this end: (1) Only one dynamic root superblock is now created per network namespace and this is shared between all attempts to mount it. This makes it easier to find the superblock to modify. (2) When a dynamic root superblock is created, the list of cells is walked and directories created for each cell already defined. (3) When a new cell is added, if a dynamic root superblock exists, a directory is created for it. (4) When a cell is destroyed, the directory is removed. (5) These directories are created by calling lookup_one_len() on the root dir which automatically creates them if they don't exist. [*] Inasmuch as network namespaces are currently supported here. Signed-off-by: David Howells --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index a982bb7cd480..a78606e8e3df 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -81,6 +81,7 @@ extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int); +extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); -- cgit v1.2.3 From 7d1982b4e335c1b184406b7566f6041bfe313c35 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 15 Jun 2018 02:30:47 +0200 Subject: bpf: fix panic in prog load calls cleanup While testing I found that when hitting error path in bpf_prog_load() where we jump to free_used_maps and prog contained BPF to BPF calls that were JITed earlier, then we never clean up the bpf_prog_kallsyms_add() done under jit_subprogs(). Add proper API to make BPF kallsyms deletion more clear and fix that. Fixes: 1c2a088a6626 ("bpf: x64: add JIT support for multi-function programs") Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 45fc0f5000d8..297c56fa9cee 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -961,6 +961,9 @@ static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) } #endif /* CONFIG_BPF_JIT */ +void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp); +void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); + #define BPF_ANC BIT(15) static inline bool bpf_needs_clear_a(const struct sock_filter *first) -- cgit v1.2.3 From 9facc336876f7ecf9edba4c67b90426fde4ec898 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 15 Jun 2018 02:30:48 +0200 Subject: bpf: reject any prog that failed read-only lock We currently lock any JITed image as read-only via bpf_jit_binary_lock_ro() as well as the BPF image as read-only through bpf_prog_lock_ro(). In the case any of these would fail we throw a WARN_ON_ONCE() in order to yell loudly to the log. Perhaps, to some extend, this may be comparable to an allocation where __GFP_NOWARN is explicitly not set. Added via 65869a47f348 ("bpf: improve read-only handling"), this behavior is slightly different compared to any of the other in-kernel set_memory_ro() users who do not check the return code of set_memory_ro() and friends /at all/ (e.g. in the case of module_enable_ro() / module_disable_ro()). Given in BPF this is mandatory hardening step, we want to know whether there are any issues that would leave both BPF data writable. So it happens that syzkaller enabled fault injection and it triggered memory allocation failure deep inside x86's change_page_attr_set_clr() which was triggered from set_memory_ro(). Now, there are two options: i) leaving everything as is, and ii) reworking the image locking code in order to have a final checkpoint out of the central bpf_prog_select_runtime() which probes whether any of the calls during prog setup weren't successful, and then bailing out with an error. Option ii) is a better approach since this additional paranoia avoids altogether leaving any potential W+X pages from BPF side in the system. Therefore, lets be strict about it, and reject programs in such unlikely occasion. While testing I noticed also that one bpf_prog_lock_ro() call was missing on the outer dummy prog in case of calls, e.g. in the destructor we call bpf_prog_free_deferred() on the main prog where we try to bpf_prog_unlock_free() the program, and since we go via bpf_prog_select_runtime() do that as well. Reported-by: syzbot+3b889862e65a98317058@syzkaller.appspotmail.com Reported-by: syzbot+9e762b52dd17e616a7a5@syzkaller.appspotmail.com Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 60 ++++++++++++++++++++++++++++++++------------------ 1 file changed, 38 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 297c56fa9cee..108f9812e196 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -469,7 +469,8 @@ struct sock_fprog_kern { }; struct bpf_binary_header { - unsigned int pages; + u16 pages; + u16 locked:1; u8 image[]; }; @@ -671,15 +672,18 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -#ifdef CONFIG_ARCH_HAS_SET_MEMORY static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { +#ifdef CONFIG_ARCH_HAS_SET_MEMORY fp->locked = 1; - WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages)); + if (set_memory_ro((unsigned long)fp, fp->pages)) + fp->locked = 0; +#endif } static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) { +#ifdef CONFIG_ARCH_HAS_SET_MEMORY if (fp->locked) { WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages)); /* In case set_memory_rw() fails, we want to be the first @@ -687,34 +691,30 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) */ fp->locked = 0; } +#endif } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { - WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages)); -} - -static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) -{ - WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages)); -} -#else -static inline void bpf_prog_lock_ro(struct bpf_prog *fp) -{ -} - -static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) -{ -} - -static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) -{ +#ifdef CONFIG_ARCH_HAS_SET_MEMORY + hdr->locked = 1; + if (set_memory_ro((unsigned long)hdr, hdr->pages)) + hdr->locked = 0; +#endif } static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) { +#ifdef CONFIG_ARCH_HAS_SET_MEMORY + if (hdr->locked) { + WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages)); + /* In case set_memory_rw() fails, we want to be the first + * to crash here instead of some random place later on. + */ + hdr->locked = 0; + } +#endif } -#endif /* CONFIG_ARCH_HAS_SET_MEMORY */ static inline struct bpf_binary_header * bpf_jit_binary_hdr(const struct bpf_prog *fp) @@ -725,6 +725,22 @@ bpf_jit_binary_hdr(const struct bpf_prog *fp) return (void *)addr; } +#ifdef CONFIG_ARCH_HAS_SET_MEMORY +static inline int bpf_prog_check_pages_ro_single(const struct bpf_prog *fp) +{ + if (!fp->locked) + return -ENOLCK; + if (fp->jited) { + const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); + + if (!hdr->locked) + return -ENOLCK; + } + + return 0; +} +#endif + int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { -- cgit v1.2.3 From ec15872daa0ac3f5cbe7cb6f1734c493d74301ac Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 8 May 2018 18:54:36 -0300 Subject: docs: fix broken references with multiple hints The script: ./scripts/documentation-file-ref-check --fix Gives multiple hints for broken references on some files. Manually use the one that applies for some files. Acked-by: Steven Rostedt (VMware) Acked-by: James Morris Signed-off-by: Mauro Carvalho Chehab Acked-by: Jonathan Corbet --- include/linux/tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index c94f466d57ef..19a690b559ca 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -4,7 +4,7 @@ /* * Kernel Tracepoint API. * - * See Documentation/trace/tracepoints.txt. + * See Documentation/trace/tracepoints.rst. * * Copyright (C) 2008-2014 Mathieu Desnoyers * -- cgit v1.2.3 From 5fb94e9ca333f0fe1d96de06704a79942b3832c3 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 8 May 2018 15:14:57 -0300 Subject: docs: Fix some broken references As we move stuff around, some doc references are broken. Fix some of them via this script: ./scripts/documentation-file-ref-check --fix Manually checked if the produced result is valid, removing a few false-positives. Acked-by: Takashi Iwai Acked-by: Masami Hiramatsu Acked-by: Stephen Boyd Acked-by: Charles Keepax Acked-by: Mathieu Poirier Reviewed-by: Coly Li Signed-off-by: Mauro Carvalho Chehab Acked-by: Jonathan Corbet --- include/linux/assoc_array.h | 2 +- include/linux/assoc_array_priv.h | 2 +- include/linux/circ_buf.h | 2 +- include/linux/ftrace.h | 2 +- include/linux/rculist_nulls.h | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/assoc_array.h b/include/linux/assoc_array.h index a89df3be1686..65e3832f96b2 100644 --- a/include/linux/assoc_array.h +++ b/include/linux/assoc_array.h @@ -1,6 +1,6 @@ /* Generic associative array implementation. * - * See Documentation/assoc_array.txt for information. + * See Documentation/core-api/assoc_array.rst for information. * * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) diff --git a/include/linux/assoc_array_priv.h b/include/linux/assoc_array_priv.h index 711275e6681c..a00a06550c10 100644 --- a/include/linux/assoc_array_priv.h +++ b/include/linux/assoc_array_priv.h @@ -1,6 +1,6 @@ /* Private definitions for the generic associative array implementation. * - * See Documentation/assoc_array.txt for information. + * See Documentation/core-api/assoc_array.rst for information. * * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) diff --git a/include/linux/circ_buf.h b/include/linux/circ_buf.h index 7cf262a421c3..b3233e8202f9 100644 --- a/include/linux/circ_buf.h +++ b/include/linux/circ_buf.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * See Documentation/circular-buffers.txt for more information. + * See Documentation/core-api/circular-buffers.rst for more information. */ #ifndef _LINUX_CIRC_BUF_H diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9c3c9a319e48..8154f4920fcb 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Ftrace header. For implementation details beyond the random comments - * scattered below, see: Documentation/trace/ftrace-design.txt + * scattered below, see: Documentation/trace/ftrace-design.rst */ #ifndef _LINUX_FTRACE_H diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index e4b257ff881b..bc8206a8f30e 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -109,7 +109,7 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, * * The barrier() is needed to make sure compiler doesn't cache first element [1], * as this loop can be restarted [2] - * [1] Documentation/atomic_ops.txt around line 114 + * [1] Documentation/core-api/atomic_ops.rst around line 114 * [2] Documentation/RCU/rculist_nulls.txt around line 146 */ #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \ -- cgit v1.2.3 From 44348e8ac145d78171c5a6f4a8bdb01b70969fc2 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jun 2018 12:34:32 -0300 Subject: fix a series of Documentation/ broken file name references As files move around, their previous links break. Fix the references for them. Acked-by: Andy Shevchenko Signed-off-by: Mauro Carvalho Chehab Acked-by: Jonathan Corbet --- include/linux/platform_data/sc18is602.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/sc18is602.h b/include/linux/platform_data/sc18is602.h index 997b06634152..18602cab7799 100644 --- a/include/linux/platform_data/sc18is602.h +++ b/include/linux/platform_data/sc18is602.h @@ -7,7 +7,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. * - * For further information, see the Documentation/spi/sc18is602 file. + * For further information, see the Documentation/spi/spi-sc18is602 file. */ /** -- cgit v1.2.3 From 6d5fc1957989266006db6ef3dfb9159b42cf0189 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Thu, 14 Jun 2018 11:07:42 +0900 Subject: xdp: Fix handling of devmap in generic XDP Commit 67f29e07e131 ("bpf: devmap introduce dev_map_enqueue") changed the return value type of __devmap_lookup_elem() from struct net_device * to struct bpf_dtab_netdev * but forgot to modify generic XDP code accordingly. Thus generic XDP incorrectly used struct bpf_dtab_netdev where struct net_device is expected, then skb->dev was set to invalid value. v2: - Fix compiler warning without CONFIG_BPF_SYSCALL. Fixes: 67f29e07e131 ("bpf: devmap introduce dev_map_enqueue") Signed-off-by: Toshiaki Makita Acked-by: Yonghong Song Acked-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 12 ++++++++++++ include/linux/filter.h | 16 ++++++++++++++++ 2 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 995c3b1e59bf..7df32a3200f7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -488,12 +488,15 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); /* Map specifics */ struct xdp_buff; +struct sk_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); +int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, + struct bpf_prog *xdp_prog); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); @@ -586,6 +589,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, return 0; } +struct sk_buff; + +static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, + struct sk_buff *skb, + struct bpf_prog *xdp_prog) +{ + return 0; +} + static inline struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) { diff --git a/include/linux/filter.h b/include/linux/filter.h index 108f9812e196..b615df57b7d5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -19,6 +19,7 @@ #include #include #include +#include #include @@ -802,6 +803,21 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, + struct net_device *fwd) +{ + unsigned int len; + + if (unlikely(!(fwd->flags & IFF_UP))) + return -ENETDOWN; + + len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; + if (skb->len > len) + return -EMSGSIZE; + + return 0; +} + /* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is -- cgit v1.2.3 From 9bbe60a67be5a1c6f79b3c9be5003481a50529ff Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 16 Jun 2018 11:55:44 +0100 Subject: atm: Preserve value of skb->truesize when accounting to vcc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ATM accounts for in-flight TX packets in sk_wmem_alloc of the VCC on which they are to be sent. But it doesn't take ownership of those packets from the sock (if any) which originally owned them. They should remain owned by their actual sender until they've left the box. There's a hack in pskb_expand_head() to avoid adjusting skb->truesize for certain skbs, precisely to avoid messing up sk_wmem_alloc accounting. Ideally that hack would cover the ATM use case too, but it doesn't — skbs which aren't owned by any sock, for example PPP control frames, still get their truesize adjusted when the low-level ATM driver adds headroom. This has always been an issue, it seems. The truesize of a packet increases, and sk_wmem_alloc on the VCC goes negative. But this wasn't for normal traffic, only for control frames. So I think we just got away with it, and we probably needed to send 2GiB of LCP echo frames before the misaccounting would ever have caused a problem and caused atm_may_send() to start refusing packets. Commit 14afee4b609 ("net: convert sock.sk_wmem_alloc from atomic_t to refcount_t") did exactly what it was intended to do, and turned this mostly-theoretical problem into a real one, causing PPPoATM to fail immediately as sk_wmem_alloc underflows and atm_may_send() *immediately* starts refusing to allow new packets. The least intrusive solution to this problem is to stash the value of skb->truesize that was accounted to the VCC, in a new member of the ATM_SKB(skb) structure. Then in atm_pop_raw() subtract precisely that value instead of the then-current value of skb->truesize. Fixes: 158f323b9868 ("net: adjust skb->truesize in pskb_expand_head()") Signed-off-by: David Woodhouse Tested-by: Kevin Darbyshire-Bryant Signed-off-by: David S. Miller --- include/linux/atmdev.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 0c27515d2cf6..8124815eb121 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -214,6 +214,7 @@ struct atmphy_ops { struct atm_skb_data { struct atm_vcc *vcc; /* ATM VCC */ unsigned long atm_options; /* ATM layer options */ + unsigned int acct_truesize; /* truesize accounted to vcc */ }; #define VCC_HTABLE_SIZE 32 @@ -241,6 +242,20 @@ void vcc_insert_socket(struct sock *sk); void atm_dev_release_vccs(struct atm_dev *dev); +static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb) +{ + /* + * Because ATM skbs may not belong to a sock (and we don't + * necessarily want to), skb->truesize may be adjusted, + * escaping the hack in pskb_expand_head() which avoids + * doing so for some cases. So stash the value of truesize + * at the time we accounted it, and atm_pop_raw() can use + * that value later, in case it changes. + */ + refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + ATM_SKB(skb)->acct_truesize = skb->truesize; + ATM_SKB(skb)->atm_options = vcc->atm_options; +} static inline void atm_force_charge(struct atm_vcc *vcc,int truesize) { -- cgit v1.2.3 From b23908d3c48a37c46c6a26df2cdeab1610b360ba Mon Sep 17 00:00:00 2001 From: Simon Glass Date: Sun, 17 Jun 2018 14:09:42 +0200 Subject: firmware: dmi: Add access to the SKU ID string This is used in some systems from user space for determining the identity of the device. Expose this as a file so that that user-space tools don't need to read from /sys/firmware/dmi/tables/DMI Signed-off-by: Simon Glass Signed-off-by: Jean Delvare --- include/linux/mod_devicetable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 7d361be2e24f..61fbfbc03e5b 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -490,6 +490,7 @@ enum dmi_field { DMI_PRODUCT_VERSION, DMI_PRODUCT_SERIAL, DMI_PRODUCT_UUID, + DMI_PRODUCT_SKU, DMI_PRODUCT_FAMILY, DMI_BOARD_VENDOR, DMI_BOARD_NAME, -- cgit v1.2.3 From a85857633b04d57f4524cca0a2bfaf87b2543f9f Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Wed, 25 Apr 2018 13:26:23 -0400 Subject: nfsd4: support change_attr_type attribute The change attribute is what is used by clients to revalidate their caches. Our server may use i_version or ctime for that purpose. Those choices behave slightly differently, and it may be useful to the client to know which we're using. This attribute tells the client that. The Linux client doesn't yet use this attribute yet, though. Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 57ffaa20d564..0877ed333733 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -374,6 +374,13 @@ enum lock_type4 { NFS4_WRITEW_LT = 4 }; +enum change_attr_type4 { + NFS4_CHANGE_TYPE_IS_MONOTONIC_INCR = 0, + NFS4_CHANGE_TYPE_IS_VERSION_COUNTER = 1, + NFS4_CHANGE_TYPE_IS_VERSION_COUNTER_NOPNFS = 2, + NFS4_CHANGE_TYPE_IS_TIME_METADATA = 3, + NFS4_CHANGE_TYPE_IS_UNDEFINED = 4 +}; /* Mandatory Attributes */ #define FATTR4_WORD0_SUPPORTED_ATTRS (1UL << 0) @@ -441,6 +448,7 @@ enum lock_type4 { #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) #define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) #define FATTR4_WORD2_CLONE_BLKSIZE (1UL << 13) +#define FATTR4_WORD2_CHANGE_ATTR_TYPE (1UL << 15) #define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) #define FATTR4_WORD2_MODE_UMASK (1UL << 17) -- cgit v1.2.3 From eb3744a2dd01cb07ce9f556d56d6fe451f0c313a Mon Sep 17 00:00:00 2001 From: Keerthy Date: Wed, 13 Jun 2018 09:10:37 +0530 Subject: gpio: davinci: Do not assume continuous IRQ numbering Currently the driver assumes that the interrupts are continuous and does platform_get_irq only once and assumes the rest are continuous, instead call platform_get_irq for all the interrupts and store them in an array for later use. Signed-off-by: Keerthy Reviewed-by: Grygorii Strashko Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-davinci.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index 90ae19ca828f..57a5a35e0073 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -22,6 +22,7 @@ #include #define MAX_REGS_BANKS 5 +#define MAX_INT_PER_BANK 32 struct davinci_gpio_platform_data { u32 ngpio; @@ -41,7 +42,7 @@ struct davinci_gpio_controller { spinlock_t lock; void __iomem *regs[MAX_REGS_BANKS]; int gpio_unbanked; - unsigned int base_irq; + int irqs[MAX_INT_PER_BANK]; unsigned int base; }; -- cgit v1.2.3 From 90b39402e9f31c4aab48dc1a43d85a724065793f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 1 Jun 2018 13:21:27 +0200 Subject: gpio: Add API to explicitly name a consumer The GPIO (descriptor) API registers a "label" naming what is currently using the GPIO line. Typically this is taken from things like the device tree node, so "reset-gpios" will result in he line being labeled "reset". The technical effect is pretty much zero: the use is for debug and introspection, such as "lsgpio" and debugfs files. However sometimes the user want this cuddly feeling of listing all GPIO lines and seeing exactly what they are for and it gives a very fulfilling sense of control. Especially in the cases when the device tree node doesn't provide a good name, or anonymous GPIO lines assigned just to "gpios" in the device tree because the usage is implicit. For these cases it may be nice to be able to label the line directly and explicitly. Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 243112c7fa7d..e8aaf34dd65d 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -145,6 +145,7 @@ int gpiod_is_active_low(const struct gpio_desc *desc); int gpiod_cansleep(const struct gpio_desc *desc); int gpiod_to_irq(const struct gpio_desc *desc); +void gpiod_set_consumer_name(struct gpio_desc *desc, const char *name); /* Convert between the old gpio_ and new gpiod_ interfaces */ struct gpio_desc *gpio_to_desc(unsigned gpio); @@ -467,6 +468,12 @@ static inline int gpiod_to_irq(const struct gpio_desc *desc) return -EINVAL; } +static inline void gpiod_set_consumer_name(struct gpio_desc *desc, const char *name) +{ + /* GPIO can never have been requested */ + WARN_ON(1); +} + static inline struct gpio_desc *gpio_to_desc(unsigned gpio) { return ERR_PTR(-EINVAL); -- cgit v1.2.3 From f2b1d2f94af887c91bb8a0cfb495e546331bc5ed Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 30 May 2018 17:25:13 +0200 Subject: soc: renesas: rcar-sysc: Provide helpers to power up/down CPUs Provide helpers to control CPU power areas from platform code, taking just a CPU index. This will avoid having to pass full CPU power area parameter blocks, and thus duplicating information already provided by SoC-specific SYSC drivers. This will be used on R-Car H1 only. Later R-Car generations rely on APMU/RST for CPU power area control. Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- include/linux/soc/renesas/rcar-sysc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/renesas/rcar-sysc.h b/include/linux/soc/renesas/rcar-sysc.h index 8a6086d2e9c3..9020da2111fd 100644 --- a/include/linux/soc/renesas/rcar-sysc.h +++ b/include/linux/soc/renesas/rcar-sysc.h @@ -13,5 +13,7 @@ struct rcar_sysc_ch { int rcar_sysc_power_down(const struct rcar_sysc_ch *sysc_ch); int rcar_sysc_power_up(const struct rcar_sysc_ch *sysc_ch); void rcar_sysc_init(phys_addr_t base, u32 syscier); +int rcar_sysc_power_down_cpu(unsigned int cpu); +int rcar_sysc_power_up_cpu(unsigned int cpu); #endif /* __LINUX_SOC_RENESAS_RCAR_SYSC_H__ */ -- cgit v1.2.3 From 7e8a50df26f4e7003d09f7e8d1e57fbbb7ebb750 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 30 May 2018 17:25:16 +0200 Subject: soc: renesas: rcar-sysc: Drop legacy handling Now the R-Car platform code no longer supports DTBs lacking a SYSC device node in DT, all legacy handling can be dropped from the R-Car SYSC driver: - Make rcar_sysc_ch private to the driver, - Make rcar_sysc_power_{down,up}() static (they have been replaced by rcar_sysc_power_{down,up}_cpu()), - Remove the legacy wrapper rcar_sysc_init(), and the check for double initialization (only the early_initcall is left). Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- include/linux/soc/renesas/rcar-sysc.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/renesas/rcar-sysc.h b/include/linux/soc/renesas/rcar-sysc.h index 9020da2111fd..00fae6fd234d 100644 --- a/include/linux/soc/renesas/rcar-sysc.h +++ b/include/linux/soc/renesas/rcar-sysc.h @@ -2,17 +2,6 @@ #ifndef __LINUX_SOC_RENESAS_RCAR_SYSC_H__ #define __LINUX_SOC_RENESAS_RCAR_SYSC_H__ -#include - -struct rcar_sysc_ch { - u16 chan_offs; - u8 chan_bit; - u8 isr_bit; -}; - -int rcar_sysc_power_down(const struct rcar_sysc_ch *sysc_ch); -int rcar_sysc_power_up(const struct rcar_sysc_ch *sysc_ch); -void rcar_sysc_init(phys_addr_t base, u32 syscier); int rcar_sysc_power_down_cpu(unsigned int cpu); int rcar_sysc_power_up_cpu(unsigned int cpu); -- cgit v1.2.3 From 297101ab85841319aac2c7843ca755d650c1964f Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Fri, 15 Jun 2018 13:44:53 +0200 Subject: regulator: pfuze100: add pfuze3001 support This extends the pfuze100 driver with pfuze3001 support. Latest datasheet: https://www.nxp.com/docs/en/data-sheet/PF3001.pdf Signed-off-by: Robin Gong Signed-off-by: Stefan Wahren Signed-off-by: Mark Brown --- include/linux/regulator/pfuze100.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h index e0ccf46f66cf..cb5aecd40f07 100644 --- a/include/linux/regulator/pfuze100.h +++ b/include/linux/regulator/pfuze100.h @@ -64,6 +64,17 @@ #define PFUZE3000_VLDO3 11 #define PFUZE3000_VLDO4 12 +#define PFUZE3001_SW1 0 +#define PFUZE3001_SW2 1 +#define PFUZE3001_SW3 2 +#define PFUZE3001_VSNVS 3 +#define PFUZE3001_VLDO1 4 +#define PFUZE3001_VLDO2 5 +#define PFUZE3001_VCCSD 6 +#define PFUZE3001_V33 7 +#define PFUZE3001_VLDO3 8 +#define PFUZE3001_VLDO4 9 + struct regulator_init_data; struct pfuze_regulator_platform_data { -- cgit v1.2.3 From 7bd0c7ba62e8a9840f15fc4ff0122b29fe1b6413 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Thu, 7 Jun 2018 16:51:38 -0700 Subject: regulator: Fix typo in comment of struct regulator_linear_range regulator_map_linar_range() => regulator_map_linear_range() Signed-off-by: Matthias Kaehlcke Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index fc2dc8df476f..dea96ee39fdc 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -46,7 +46,7 @@ enum regulator_status { /** * struct regulator_linear_range - specify linear voltage ranges * - * Specify a range of voltages for regulator_map_linar_range() and + * Specify a range of voltages for regulator_map_linear_range() and * regulator_list_linear_range(). * * @min_uV: Lowest voltage in range -- cgit v1.2.3 From 3e247b0fb540a9a503a71ef6b918a3443e49655f Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 7 Jun 2018 19:40:32 +0000 Subject: spi: remove unused adi_spi3.h header include/linux/spi/adi_spi3.h is unused since commit 47838669de9d ("spi: remove blackfin related host drivers") Finish the cleaning by removing it. Signed-off-by: Corentin Labbe Signed-off-by: Mark Brown --- include/linux/spi/adi_spi3.h | 254 ------------------------------------------- 1 file changed, 254 deletions(-) delete mode 100644 include/linux/spi/adi_spi3.h (limited to 'include/linux') diff --git a/include/linux/spi/adi_spi3.h b/include/linux/spi/adi_spi3.h deleted file mode 100644 index c84123aa1d06..000000000000 --- a/include/linux/spi/adi_spi3.h +++ /dev/null @@ -1,254 +0,0 @@ -/* - * Analog Devices SPI3 controller driver - * - * Copyright (c) 2014 Analog Devices Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef _ADI_SPI3_H_ -#define _ADI_SPI3_H_ - -#include - -/* SPI_CONTROL */ -#define SPI_CTL_EN 0x00000001 /* Enable */ -#define SPI_CTL_MSTR 0x00000002 /* Master/Slave */ -#define SPI_CTL_PSSE 0x00000004 /* controls modf error in master mode */ -#define SPI_CTL_ODM 0x00000008 /* Open Drain Mode */ -#define SPI_CTL_CPHA 0x00000010 /* Clock Phase */ -#define SPI_CTL_CPOL 0x00000020 /* Clock Polarity */ -#define SPI_CTL_ASSEL 0x00000040 /* Slave Select Pin Control */ -#define SPI_CTL_SELST 0x00000080 /* Slave Select Polarity in-between transfers */ -#define SPI_CTL_EMISO 0x00000100 /* Enable MISO */ -#define SPI_CTL_SIZE 0x00000600 /* Word Transfer Size */ -#define SPI_CTL_SIZE08 0x00000000 /* SIZE: 8 bits */ -#define SPI_CTL_SIZE16 0x00000200 /* SIZE: 16 bits */ -#define SPI_CTL_SIZE32 0x00000400 /* SIZE: 32 bits */ -#define SPI_CTL_LSBF 0x00001000 /* LSB First */ -#define SPI_CTL_FCEN 0x00002000 /* Flow-Control Enable */ -#define SPI_CTL_FCCH 0x00004000 /* Flow-Control Channel Selection */ -#define SPI_CTL_FCPL 0x00008000 /* Flow-Control Polarity */ -#define SPI_CTL_FCWM 0x00030000 /* Flow-Control Water-Mark */ -#define SPI_CTL_FIFO0 0x00000000 /* FCWM: TFIFO empty or RFIFO Full */ -#define SPI_CTL_FIFO1 0x00010000 /* FCWM: TFIFO 75% or more empty or RFIFO 75% or more full */ -#define SPI_CTL_FIFO2 0x00020000 /* FCWM: TFIFO 50% or more empty or RFIFO 50% or more full */ -#define SPI_CTL_FMODE 0x00040000 /* Fast-mode Enable */ -#define SPI_CTL_MIOM 0x00300000 /* Multiple I/O Mode */ -#define SPI_CTL_MIO_DIS 0x00000000 /* MIOM: Disable */ -#define SPI_CTL_MIO_DUAL 0x00100000 /* MIOM: Enable DIOM (Dual I/O Mode) */ -#define SPI_CTL_MIO_QUAD 0x00200000 /* MIOM: Enable QUAD (Quad SPI Mode) */ -#define SPI_CTL_SOSI 0x00400000 /* Start on MOSI */ -/* SPI_RX_CONTROL */ -#define SPI_RXCTL_REN 0x00000001 /* Receive Channel Enable */ -#define SPI_RXCTL_RTI 0x00000004 /* Receive Transfer Initiate */ -#define SPI_RXCTL_RWCEN 0x00000008 /* Receive Word Counter Enable */ -#define SPI_RXCTL_RDR 0x00000070 /* Receive Data Request */ -#define SPI_RXCTL_RDR_DIS 0x00000000 /* RDR: Disabled */ -#define SPI_RXCTL_RDR_NE 0x00000010 /* RDR: RFIFO not empty */ -#define SPI_RXCTL_RDR_25 0x00000020 /* RDR: RFIFO 25% full */ -#define SPI_RXCTL_RDR_50 0x00000030 /* RDR: RFIFO 50% full */ -#define SPI_RXCTL_RDR_75 0x00000040 /* RDR: RFIFO 75% full */ -#define SPI_RXCTL_RDR_FULL 0x00000050 /* RDR: RFIFO full */ -#define SPI_RXCTL_RDO 0x00000100 /* Receive Data Over-Run */ -#define SPI_RXCTL_RRWM 0x00003000 /* FIFO Regular Water-Mark */ -#define SPI_RXCTL_RWM_0 0x00000000 /* RRWM: RFIFO Empty */ -#define SPI_RXCTL_RWM_25 0x00001000 /* RRWM: RFIFO 25% full */ -#define SPI_RXCTL_RWM_50 0x00002000 /* RRWM: RFIFO 50% full */ -#define SPI_RXCTL_RWM_75 0x00003000 /* RRWM: RFIFO 75% full */ -#define SPI_RXCTL_RUWM 0x00070000 /* FIFO Urgent Water-Mark */ -#define SPI_RXCTL_UWM_DIS 0x00000000 /* RUWM: Disabled */ -#define SPI_RXCTL_UWM_25 0x00010000 /* RUWM: RFIFO 25% full */ -#define SPI_RXCTL_UWM_50 0x00020000 /* RUWM: RFIFO 50% full */ -#define SPI_RXCTL_UWM_75 0x00030000 /* RUWM: RFIFO 75% full */ -#define SPI_RXCTL_UWM_FULL 0x00040000 /* RUWM: RFIFO full */ -/* SPI_TX_CONTROL */ -#define SPI_TXCTL_TEN 0x00000001 /* Transmit Channel Enable */ -#define SPI_TXCTL_TTI 0x00000004 /* Transmit Transfer Initiate */ -#define SPI_TXCTL_TWCEN 0x00000008 /* Transmit Word Counter Enable */ -#define SPI_TXCTL_TDR 0x00000070 /* Transmit Data Request */ -#define SPI_TXCTL_TDR_DIS 0x00000000 /* TDR: Disabled */ -#define SPI_TXCTL_TDR_NF 0x00000010 /* TDR: TFIFO not full */ -#define SPI_TXCTL_TDR_25 0x00000020 /* TDR: TFIFO 25% empty */ -#define SPI_TXCTL_TDR_50 0x00000030 /* TDR: TFIFO 50% empty */ -#define SPI_TXCTL_TDR_75 0x00000040 /* TDR: TFIFO 75% empty */ -#define SPI_TXCTL_TDR_EMPTY 0x00000050 /* TDR: TFIFO empty */ -#define SPI_TXCTL_TDU 0x00000100 /* Transmit Data Under-Run */ -#define SPI_TXCTL_TRWM 0x00003000 /* FIFO Regular Water-Mark */ -#define SPI_TXCTL_RWM_FULL 0x00000000 /* TRWM: TFIFO full */ -#define SPI_TXCTL_RWM_25 0x00001000 /* TRWM: TFIFO 25% empty */ -#define SPI_TXCTL_RWM_50 0x00002000 /* TRWM: TFIFO 50% empty */ -#define SPI_TXCTL_RWM_75 0x00003000 /* TRWM: TFIFO 75% empty */ -#define SPI_TXCTL_TUWM 0x00070000 /* FIFO Urgent Water-Mark */ -#define SPI_TXCTL_UWM_DIS 0x00000000 /* TUWM: Disabled */ -#define SPI_TXCTL_UWM_25 0x00010000 /* TUWM: TFIFO 25% empty */ -#define SPI_TXCTL_UWM_50 0x00020000 /* TUWM: TFIFO 50% empty */ -#define SPI_TXCTL_UWM_75 0x00030000 /* TUWM: TFIFO 75% empty */ -#define SPI_TXCTL_UWM_EMPTY 0x00040000 /* TUWM: TFIFO empty */ -/* SPI_CLOCK */ -#define SPI_CLK_BAUD 0x0000FFFF /* Baud Rate */ -/* SPI_DELAY */ -#define SPI_DLY_STOP 0x000000FF /* Transfer delay time in multiples of SCK period */ -#define SPI_DLY_LEADX 0x00000100 /* Extended (1 SCK) LEAD Control */ -#define SPI_DLY_LAGX 0x00000200 /* Extended (1 SCK) LAG control */ -/* SPI_SSEL */ -#define SPI_SLVSEL_SSE1 0x00000002 /* SPISSEL1 Enable */ -#define SPI_SLVSEL_SSE2 0x00000004 /* SPISSEL2 Enable */ -#define SPI_SLVSEL_SSE3 0x00000008 /* SPISSEL3 Enable */ -#define SPI_SLVSEL_SSE4 0x00000010 /* SPISSEL4 Enable */ -#define SPI_SLVSEL_SSE5 0x00000020 /* SPISSEL5 Enable */ -#define SPI_SLVSEL_SSE6 0x00000040 /* SPISSEL6 Enable */ -#define SPI_SLVSEL_SSE7 0x00000080 /* SPISSEL7 Enable */ -#define SPI_SLVSEL_SSEL1 0x00000200 /* SPISSEL1 Value */ -#define SPI_SLVSEL_SSEL2 0x00000400 /* SPISSEL2 Value */ -#define SPI_SLVSEL_SSEL3 0x00000800 /* SPISSEL3 Value */ -#define SPI_SLVSEL_SSEL4 0x00001000 /* SPISSEL4 Value */ -#define SPI_SLVSEL_SSEL5 0x00002000 /* SPISSEL5 Value */ -#define SPI_SLVSEL_SSEL6 0x00004000 /* SPISSEL6 Value */ -#define SPI_SLVSEL_SSEL7 0x00008000 /* SPISSEL7 Value */ -/* SPI_RWC */ -#define SPI_RWC_VALUE 0x0000FFFF /* Received Word-Count */ -/* SPI_RWCR */ -#define SPI_RWCR_VALUE 0x0000FFFF /* Received Word-Count Reload */ -/* SPI_TWC */ -#define SPI_TWC_VALUE 0x0000FFFF /* Transmitted Word-Count */ -/* SPI_TWCR */ -#define SPI_TWCR_VALUE 0x0000FFFF /* Transmitted Word-Count Reload */ -/* SPI_IMASK */ -#define SPI_IMSK_RUWM 0x00000002 /* Receive Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_TUWM 0x00000004 /* Transmit Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_ROM 0x00000010 /* Receive Over-Run Error Interrupt Mask */ -#define SPI_IMSK_TUM 0x00000020 /* Transmit Under-Run Error Interrupt Mask */ -#define SPI_IMSK_TCM 0x00000040 /* Transmit Collision Error Interrupt Mask */ -#define SPI_IMSK_MFM 0x00000080 /* Mode Fault Error Interrupt Mask */ -#define SPI_IMSK_RSM 0x00000100 /* Receive Start Interrupt Mask */ -#define SPI_IMSK_TSM 0x00000200 /* Transmit Start Interrupt Mask */ -#define SPI_IMSK_RFM 0x00000400 /* Receive Finish Interrupt Mask */ -#define SPI_IMSK_TFM 0x00000800 /* Transmit Finish Interrupt Mask */ -/* SPI_IMASKCL */ -#define SPI_IMSK_CLR_RUW 0x00000002 /* Receive Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_CLR_TUWM 0x00000004 /* Transmit Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_CLR_ROM 0x00000010 /* Receive Over-Run Error Interrupt Mask */ -#define SPI_IMSK_CLR_TUM 0x00000020 /* Transmit Under-Run Error Interrupt Mask */ -#define SPI_IMSK_CLR_TCM 0x00000040 /* Transmit Collision Error Interrupt Mask */ -#define SPI_IMSK_CLR_MFM 0x00000080 /* Mode Fault Error Interrupt Mask */ -#define SPI_IMSK_CLR_RSM 0x00000100 /* Receive Start Interrupt Mask */ -#define SPI_IMSK_CLR_TSM 0x00000200 /* Transmit Start Interrupt Mask */ -#define SPI_IMSK_CLR_RFM 0x00000400 /* Receive Finish Interrupt Mask */ -#define SPI_IMSK_CLR_TFM 0x00000800 /* Transmit Finish Interrupt Mask */ -/* SPI_IMASKST */ -#define SPI_IMSK_SET_RUWM 0x00000002 /* Receive Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_SET_TUWM 0x00000004 /* Transmit Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_SET_ROM 0x00000010 /* Receive Over-Run Error Interrupt Mask */ -#define SPI_IMSK_SET_TUM 0x00000020 /* Transmit Under-Run Error Interrupt Mask */ -#define SPI_IMSK_SET_TCM 0x00000040 /* Transmit Collision Error Interrupt Mask */ -#define SPI_IMSK_SET_MFM 0x00000080 /* Mode Fault Error Interrupt Mask */ -#define SPI_IMSK_SET_RSM 0x00000100 /* Receive Start Interrupt Mask */ -#define SPI_IMSK_SET_TSM 0x00000200 /* Transmit Start Interrupt Mask */ -#define SPI_IMSK_SET_RFM 0x00000400 /* Receive Finish Interrupt Mask */ -#define SPI_IMSK_SET_TFM 0x00000800 /* Transmit Finish Interrupt Mask */ -/* SPI_STATUS */ -#define SPI_STAT_SPIF 0x00000001 /* SPI Finished */ -#define SPI_STAT_RUWM 0x00000002 /* Receive Urgent Water-Mark Breached */ -#define SPI_STAT_TUWM 0x00000004 /* Transmit Urgent Water-Mark Breached */ -#define SPI_STAT_ROE 0x00000010 /* Receive Over-Run Error Indication */ -#define SPI_STAT_TUE 0x00000020 /* Transmit Under-Run Error Indication */ -#define SPI_STAT_TCE 0x00000040 /* Transmit Collision Error Indication */ -#define SPI_STAT_MODF 0x00000080 /* Mode Fault Error Indication */ -#define SPI_STAT_RS 0x00000100 /* Receive Start Indication */ -#define SPI_STAT_TS 0x00000200 /* Transmit Start Indication */ -#define SPI_STAT_RF 0x00000400 /* Receive Finish Indication */ -#define SPI_STAT_TF 0x00000800 /* Transmit Finish Indication */ -#define SPI_STAT_RFS 0x00007000 /* SPI_RFIFO status */ -#define SPI_STAT_RFIFO_EMPTY 0x00000000 /* RFS: RFIFO Empty */ -#define SPI_STAT_RFIFO_25 0x00001000 /* RFS: RFIFO 25% Full */ -#define SPI_STAT_RFIFO_50 0x00002000 /* RFS: RFIFO 50% Full */ -#define SPI_STAT_RFIFO_75 0x00003000 /* RFS: RFIFO 75% Full */ -#define SPI_STAT_RFIFO_FULL 0x00004000 /* RFS: RFIFO Full */ -#define SPI_STAT_TFS 0x00070000 /* SPI_TFIFO status */ -#define SPI_STAT_TFIFO_FULL 0x00000000 /* TFS: TFIFO full */ -#define SPI_STAT_TFIFO_25 0x00010000 /* TFS: TFIFO 25% empty */ -#define SPI_STAT_TFIFO_50 0x00020000 /* TFS: TFIFO 50% empty */ -#define SPI_STAT_TFIFO_75 0x00030000 /* TFS: TFIFO 75% empty */ -#define SPI_STAT_TFIFO_EMPTY 0x00040000 /* TFS: TFIFO empty */ -#define SPI_STAT_FCS 0x00100000 /* Flow-Control Stall Indication */ -#define SPI_STAT_RFE 0x00400000 /* SPI_RFIFO Empty */ -#define SPI_STAT_TFF 0x00800000 /* SPI_TFIFO Full */ -/* SPI_ILAT */ -#define SPI_ILAT_RUWMI 0x00000002 /* Receive Urgent Water Mark Interrupt */ -#define SPI_ILAT_TUWMI 0x00000004 /* Transmit Urgent Water Mark Interrupt */ -#define SPI_ILAT_ROI 0x00000010 /* Receive Over-Run Error Indication */ -#define SPI_ILAT_TUI 0x00000020 /* Transmit Under-Run Error Indication */ -#define SPI_ILAT_TCI 0x00000040 /* Transmit Collision Error Indication */ -#define SPI_ILAT_MFI 0x00000080 /* Mode Fault Error Indication */ -#define SPI_ILAT_RSI 0x00000100 /* Receive Start Indication */ -#define SPI_ILAT_TSI 0x00000200 /* Transmit Start Indication */ -#define SPI_ILAT_RFI 0x00000400 /* Receive Finish Indication */ -#define SPI_ILAT_TFI 0x00000800 /* Transmit Finish Indication */ -/* SPI_ILATCL */ -#define SPI_ILAT_CLR_RUWMI 0x00000002 /* Receive Urgent Water Mark Interrupt */ -#define SPI_ILAT_CLR_TUWMI 0x00000004 /* Transmit Urgent Water Mark Interrupt */ -#define SPI_ILAT_CLR_ROI 0x00000010 /* Receive Over-Run Error Indication */ -#define SPI_ILAT_CLR_TUI 0x00000020 /* Transmit Under-Run Error Indication */ -#define SPI_ILAT_CLR_TCI 0x00000040 /* Transmit Collision Error Indication */ -#define SPI_ILAT_CLR_MFI 0x00000080 /* Mode Fault Error Indication */ -#define SPI_ILAT_CLR_RSI 0x00000100 /* Receive Start Indication */ -#define SPI_ILAT_CLR_TSI 0x00000200 /* Transmit Start Indication */ -#define SPI_ILAT_CLR_RFI 0x00000400 /* Receive Finish Indication */ -#define SPI_ILAT_CLR_TFI 0x00000800 /* Transmit Finish Indication */ - -/* - * adi spi3 registers layout - */ -struct adi_spi_regs { - u32 revid; - u32 control; - u32 rx_control; - u32 tx_control; - u32 clock; - u32 delay; - u32 ssel; - u32 rwc; - u32 rwcr; - u32 twc; - u32 twcr; - u32 reserved0; - u32 emask; - u32 emaskcl; - u32 emaskst; - u32 reserved1; - u32 status; - u32 elat; - u32 elatcl; - u32 reserved2; - u32 rfifo; - u32 reserved3; - u32 tfifo; -}; - -#define MAX_CTRL_CS 8 /* cs in spi controller */ - -/* device.platform_data for SSP controller devices */ -struct adi_spi3_master { - u16 num_chipselect; - u16 pin_req[7]; -}; - -/* spi_board_info.controller_data for SPI slave devices, - * copied to spi_device.platform_data ... mostly for dma tuning - */ -struct adi_spi3_chip { - u32 control; - u16 cs_chg_udelay; /* Some devices require 16-bit delays */ - u32 tx_dummy_val; /* tx value for rx only transfer */ - bool enable_dma; -}; - -#endif /* _ADI_SPI3_H_ */ -- cgit v1.2.3 From cf85ec88701610f0de2e959ac447d9613462fbc7 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Sat, 9 Jun 2018 16:18:16 +0300 Subject: removed extra extern file_fdatawait_range Jeff added this extern twice in commit a823e4589e68 Fixes: a823e4589e68 ("mm: add file_fdatawait_range and file_write_and_wait") Signed-off-by: Vasily Averin Signed-off-by: Al Viro --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5c91108846db..f140c11d35dd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2623,8 +2623,6 @@ static inline int filemap_fdatawait(struct address_space *mapping) extern bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); -extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, - loff_t lend); extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); -- cgit v1.2.3 From 3c60e868c31e4ff144776bf53ff0dfe9e9e4ec15 Mon Sep 17 00:00:00 2001 From: "willy@infradead.org" Date: Wed, 13 Jun 2018 11:45:55 -0700 Subject: IDR: Expose the XArray lock Allow users of the IDR to use the XArray lock for their own synchronisation purposes. The IDR continues to rely on the caller to handle locking, but this lets the caller use the lock embedded in the IDR data structure instead of allocating their own lock. Signed-off-by: Matthew Wilcox Signed-off-by: Jason Gunthorpe --- include/linux/idr.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index e856f4e0ab35..3e8215b2c371 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -98,6 +98,17 @@ static inline void idr_set_cursor(struct idr *idr, unsigned int val) * period). */ +#define idr_lock(idr) xa_lock(&(idr)->idr_rt) +#define idr_unlock(idr) xa_unlock(&(idr)->idr_rt) +#define idr_lock_bh(idr) xa_lock_bh(&(idr)->idr_rt) +#define idr_unlock_bh(idr) xa_unlock_bh(&(idr)->idr_rt) +#define idr_lock_irq(idr) xa_lock_irq(&(idr)->idr_rt) +#define idr_unlock_irq(idr) xa_unlock_irq(&(idr)->idr_rt) +#define idr_lock_irqsave(idr, flags) \ + xa_lock_irqsave(&(idr)->idr_rt, flags) +#define idr_unlock_irqrestore(idr, flags) \ + xa_unlock_irqrestore(&(idr)->idr_rt, flags) + void idr_preload(gfp_t gfp_mask); int idr_alloc(struct idr *, void *ptr, int start, int end, gfp_t); -- cgit v1.2.3 From aece27a2f01be4bb7683790f69cd1bed3a0929a2 Mon Sep 17 00:00:00 2001 From: Samuel Morris Date: Tue, 29 May 2018 10:06:12 +0000 Subject: ata: ahci_platform: allow disabling of hotplug to save power A number of resources remain powered to support hotplug. On platforms I've worked with, allowing the ahci_platform to suspend saves about 150mW. This patch enables rpm and allows the device to be auto-suspended through sysfs. Signed-off-by: Samuel Morris Signed-off-by: Tejun Heo --- include/linux/ahci_platform.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 1b0a17b22cd3..6396e6982103 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -42,5 +42,7 @@ int ahci_platform_suspend_host(struct device *dev); int ahci_platform_resume_host(struct device *dev); int ahci_platform_suspend(struct device *dev); int ahci_platform_resume(struct device *dev); +int ahci_platform_runtime_suspend(struct device *dev); +int ahci_platform_runtime_resume(struct device *dev); #endif /* _AHCI_PLATFORM_H */ -- cgit v1.2.3 From 420c0117db25db38b72b6230223f7a976d3070ea Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sun, 17 Jun 2018 19:02:04 +0200 Subject: dmaengine: pxa: use a dma slave map In order to remove the specific knowledge of the dma mapping from PXA drivers, add a default slave map for pxa architectures. This won't impact MMP architecture, but is aimed only at all PXA boards. This is the first step, and once all drivers are converted, pxad_filter_fn() will be made static, and the DMA resources removed from device.c. Signed-off-by: Robert Jarzmik Reported-by: Arnd Bergmann Acked-by: Vinod Koul --- include/linux/platform_data/mmp_dma.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mmp_dma.h b/include/linux/platform_data/mmp_dma.h index d1397c8ed94e..6397b9c8149a 100644 --- a/include/linux/platform_data/mmp_dma.h +++ b/include/linux/platform_data/mmp_dma.h @@ -12,9 +12,13 @@ #ifndef MMP_DMA_H #define MMP_DMA_H +struct dma_slave_map; + struct mmp_dma_platdata { int dma_channels; int nb_requestors; + int slave_map_cnt; + const struct dma_slave_map *slave_map; }; #endif /* MMP_DMA_H */ -- cgit v1.2.3 From b6d1a17f4729e4fda5740a855da91d202db2c118 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sun, 17 Jun 2018 19:02:14 +0200 Subject: dmaengine: pxa: document pxad_param Add some documentation for the pxad_param structure, and describe the contract behind the minimal required priority of a DMA channel. Signed-off-by: Robert Jarzmik Acked-by: Vinod Koul --- include/linux/dma/pxa-dma.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma/pxa-dma.h b/include/linux/dma/pxa-dma.h index e56ec7af4fd7..9fc594f69eff 100644 --- a/include/linux/dma/pxa-dma.h +++ b/include/linux/dma/pxa-dma.h @@ -9,6 +9,15 @@ enum pxad_chan_prio { PXAD_PRIO_LOWEST, }; +/** + * struct pxad_param - dma channel request parameters + * @drcmr: requestor line number + * @prio: minimal mandatory priority of the channel + * + * If a requested channel is granted, its priority will be at least @prio, + * ie. if PXAD_PRIO_LOW is required, the requested channel will be either + * PXAD_PRIO_LOW, PXAD_PRIO_NORMAL or PXAD_PRIO_HIGHEST. + */ struct pxad_param { unsigned int drcmr; enum pxad_chan_prio prio; -- cgit v1.2.3 From cd31b80736852d34bc1072f3e579a6fd73a244e7 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sun, 17 Jun 2018 19:02:17 +0200 Subject: ARM: pxa: change SSP DMA channels allocation Now the dma_slave_map is available for PXA architecture, switch the SSP device to it. This specifically means that : - for platform data based machines, the DMA requestor channels are extracted from the slave map, where pxa-ssp-dai. is a 1-1 match to ssp., and the channels are either "rx" or "tx". - for device tree platforms, the dma node should be hooked into the pxa2xx-ac97 or pxa-ssp-dai node. Signed-off-by: Robert Jarzmik Acked-by: Daniel Mack --- include/linux/pxa2xx_ssp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 8461b18e4608..03a7ca46735b 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -212,8 +212,6 @@ struct ssp_device { int type; int use_count; int irq; - int drcmr_rx; - int drcmr_tx; struct device_node *of_node; }; -- cgit v1.2.3 From b8042b3da925f390c1482bf9dc0898dc0b3ea7b5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 18 Jun 2018 22:39:29 +0200 Subject: ieee80211: bump IEEE80211_MAX_AMPDU_BUF to support HE Bump the IEEE80211_MAX_AMPDU_BUF size to 0x100 for HE support and - for now - use IEEE80211_MAX_AMPDU_BUF_HT everywhere. This is derived from my internal patch, parts of which Luca had sent upstream. Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e6a6503bfa33..9c03a7d5e400 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1433,11 +1433,13 @@ struct ieee80211_ht_operation { #define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800 /* - * A-PMDU buffer sizes - * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2) + * A-MPDU buffer sizes + * According to HT size varies from 8 to 64 frames + * HE adds the ability to have up to 256 frames. */ -#define IEEE80211_MIN_AMPDU_BUF 0x8 -#define IEEE80211_MAX_AMPDU_BUF 0x40 +#define IEEE80211_MIN_AMPDU_BUF 0x8 +#define IEEE80211_MAX_AMPDU_BUF_HT 0x40 +#define IEEE80211_MAX_AMPDU_BUF 0x100 /* Spatial Multiplexing Power Save Modes (for capability) */ -- cgit v1.2.3 From 0e622e80191e75c99b6ecc265c140a37d81e7a63 Mon Sep 17 00:00:00 2001 From: Sricharan R Date: Mon, 4 Jun 2018 13:30:35 -0700 Subject: remoteproc: qcom: mdt_loader: Make the firmware authentication optional qcom_mdt_load function loads the mdt type firmware and initialises the secure memory as well. Make the initialisation only when requested by the caller, so that the function can be used by self-authenticating remoteproc as well. Acked-by: Andy Gross Signed-off-by: Sricharan R Signed-off-by: Bjorn Andersson --- include/linux/soc/qcom/mdt_loader.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h index 5b98bbdabc25..944b06aefb0f 100644 --- a/include/linux/soc/qcom/mdt_loader.h +++ b/include/linux/soc/qcom/mdt_loader.h @@ -17,4 +17,8 @@ int qcom_mdt_load(struct device *dev, const struct firmware *fw, phys_addr_t mem_phys, size_t mem_size, phys_addr_t *reloc_base); +int qcom_mdt_load_no_init(struct device *dev, const struct firmware *fw, + const char *fw_name, int pas_id, void *mem_region, + phys_addr_t mem_phys, size_t mem_size, + phys_addr_t *reloc_base); #endif -- cgit v1.2.3 From 42f86b44a4d356edba626171dfe0be061fc695af Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 18 Jun 2018 19:07:24 -0400 Subject: pNFS/flexfiles: Don't tie up all the rpciod threads in resends We do not want to have rpciod threads perform recursive calls into the RPC layer since that can deadlock. In particular, having to wait for a layoutget can be nasty... We want rather to defer scheduling those retries until we're in the rpc_release() callback, since that is called from the nfsiod workqueue. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9dee3c23895d..712eed156d09 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1438,6 +1438,8 @@ enum { NFS_IOHDR_EOF, NFS_IOHDR_REDO, NFS_IOHDR_STAT, + NFS_IOHDR_RESEND_PNFS, + NFS_IOHDR_RESEND_MDS, }; struct nfs_io_completion; -- cgit v1.2.3 From f7859590d97614815b35a755c8213dfb8f2766bd Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 5 Jun 2018 19:20:39 -0400 Subject: audit: eliminate audit_enabled magic number comparison Remove comparison of audit_enabled to magic numbers outside of audit. Related: https://github.com/linux-audit/audit-kernel/issues/86 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 69c78477590b..9334fbef7bae 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -117,6 +117,9 @@ struct filename; extern void audit_log_session_info(struct audit_buffer *ab); +#define AUDIT_OFF 0 +#define AUDIT_ON 1 +#define AUDIT_LOCKED 2 #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ @@ -202,7 +205,7 @@ static inline int audit_log_task_context(struct audit_buffer *ab) static inline void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) { } -#define audit_enabled 0 +#define audit_enabled AUDIT_OFF #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC -- cgit v1.2.3 From 6362f0a290023bafd7f991089e81dd9278f154b8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 19 Jun 2018 10:12:48 -0600 Subject: libata: add command iterator helpers Now that we have the internal tag as a special (higher) value tag, it gets a bit tricky to iterate the internal commands as some loops will exceed ATA_MAX_QUEUE. Add explicit helpers for iterating pending commands, both inflight and internal. Signed-off-by: Jens Axboe Signed-off-by: Tejun Heo --- include/linux/libata.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 8b8946dd63b9..a2257e380789 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1495,6 +1495,29 @@ static inline bool ata_tag_valid(unsigned int tag) return tag < ATA_MAX_QUEUE || ata_tag_internal(tag); } +#define __ata_qc_for_each(ap, qc, tag, max_tag, fn) \ + for ((tag) = 0; (tag) < (max_tag) && \ + ({ qc = fn((ap), (tag)); 1; }); (tag)++) \ + +/* + * Internal use only, iterate commands ignoring error handling and + * status of 'qc'. + */ +#define ata_qc_for_each_raw(ap, qc, tag) \ + __ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE, __ata_qc_from_tag) + +/* + * Iterate all potential commands that can be queued + */ +#define ata_qc_for_each(ap, qc, tag) \ + __ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE, ata_qc_from_tag) + +/* + * Like ata_qc_for_each, but with the internal tag included + */ +#define ata_qc_for_each_with_internal(ap, qc, tag) \ + __ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE + 1, ata_qc_from_tag) + /* * device helpers */ -- cgit v1.2.3 From 38b7ca927d6a12bf4466be22a90b7d998f5ae69a Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 8 Mar 2018 14:36:27 +0200 Subject: net/mlx5: Expose DEVX specification This patch updates the mlx5_ifc structures and command interface to support DEVX. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/device.h | 3 ++ include/linux/mlx5/mlx5_ifc.h | 67 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 69 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 02f72ebf31a7..f8671c0a43aa 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1071,6 +1071,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_GEN(mdev, cap) \ MLX5_GET(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap) +#define MLX5_CAP_GEN_64(mdev, cap) \ + MLX5_GET64(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap) + #define MLX5_CAP_GEN_MAX(mdev, cap) \ MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 27134c4fcb76..f810772e80c0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -75,6 +75,15 @@ enum { MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, }; +enum { + MLX5_GENERAL_OBJ_TYPES_CAP_UCTX = (1ULL << 4), + MLX5_GENERAL_OBJ_TYPES_CAP_UMEM = (1ULL << 5), +}; + +enum { + MLX5_OBJ_TYPE_UCTX = 0x0004, +}; + enum { MLX5_CMD_OP_QUERY_HCA_CAP = 0x100, MLX5_CMD_OP_QUERY_ADAPTER = 0x101, @@ -242,6 +251,8 @@ enum { MLX5_CMD_OP_FPGA_QUERY_QP = 0x962, MLX5_CMD_OP_FPGA_DESTROY_QP = 0x963, MLX5_CMD_OP_FPGA_QUERY_QP_COUNTERS = 0x964, + MLX5_CMD_OP_CREATE_GENERAL_OBJECT = 0xa00, + MLX5_CMD_OP_DESTROY_GENERAL_OBJECT = 0xa03, MLX5_CMD_OP_MAX }; @@ -1113,7 +1124,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_3f8[0x3]; u8 log_max_current_uc_list[0x5]; - u8 reserved_at_400[0x80]; + u8 general_obj_types[0x40]; + + u8 reserved_at_440[0x40]; u8 reserved_at_480[0x3]; u8 log_max_l2_table[0x5]; @@ -9115,4 +9128,56 @@ struct mlx5_ifc_dealloc_memic_out_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_general_obj_in_cmd_hdr_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 obj_type[0x10]; + + u8 obj_id[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_general_obj_out_cmd_hdr_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 obj_id[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_umem_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x5b]; + u8 log_page_size[0x5]; + + u8 page_offset[0x20]; + + u8 num_of_mtt[0x40]; + + struct mlx5_ifc_mtt_bits mtt[0]; +}; + +struct mlx5_ifc_uctx_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x1c0]; +}; + +struct mlx5_ifc_create_umem_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_umem_bits umem; +}; + +struct mlx5_ifc_create_uctx_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_uctx_bits uctx; +}; + #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From e662e14d801b01a976e58bc3f8d9fe49b9fcec3a Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 17 Jun 2018 13:00:02 +0300 Subject: IB/mlx5: Add DEVX support for modify and query commands Add support in DEVX for modify and query commands, the required lock is taken (i.e. READ/WRITE) by the KABI infrastructure accordingly. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/mlx5_ifc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f810772e80c0..ac24ed87c67e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -246,12 +246,15 @@ enum { MLX5_CMD_OP_DEALLOC_ENCAP_HEADER = 0x93e, MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT = 0x940, MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941, + MLX5_CMD_OP_QUERY_MODIFY_HEADER_CONTEXT = 0x942, MLX5_CMD_OP_FPGA_CREATE_QP = 0x960, MLX5_CMD_OP_FPGA_MODIFY_QP = 0x961, MLX5_CMD_OP_FPGA_QUERY_QP = 0x962, MLX5_CMD_OP_FPGA_DESTROY_QP = 0x963, MLX5_CMD_OP_FPGA_QUERY_QP_COUNTERS = 0x964, MLX5_CMD_OP_CREATE_GENERAL_OBJECT = 0xa00, + MLX5_CMD_OP_MODIFY_GENERAL_OBJECT = 0xa01, + MLX5_CMD_OP_QUERY_GENERAL_OBJECT = 0xa02, MLX5_CMD_OP_DESTROY_GENERAL_OBJECT = 0xa03, MLX5_CMD_OP_MAX }; -- cgit v1.2.3 From aeae94579caf77406a8a235ea33fdb67abe9a57e Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 17 Jun 2018 13:00:04 +0300 Subject: IB/mlx5: Add DEVX support for memory registration Add support to register a memory with the firmware via the DEVX interface. The driver translates a given user address to ib_umem then it will register the physical addresses with the firmware and get a unique id for this registration to be used for this virtual address. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/mlx5_ifc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ac24ed87c67e..00b539303f5d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -82,6 +82,7 @@ enum { enum { MLX5_OBJ_TYPE_UCTX = 0x0004, + MLX5_OBJ_TYPE_UMEM = 0x0005, }; enum { -- cgit v1.2.3 From 9fba738a53dda20e748d6ee240b6c017c8146b4b Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Tue, 19 Jun 2018 16:41:41 +0200 Subject: clk: add duty cycle support Add the possibility to apply and query the clock signal duty cycle ratio. This is useful when the duty cycle of the clock signal depends on some other parameters controlled by the clock framework. For example, the duty cycle of a divider may depends on the raw divider setting (ratio = N / div) , which is controlled by the CCF. In such case, going through the pwm framework to control the duty cycle ratio of this clock would be a burden. A clock provider is not required to implement the operation to set and get the duty cycle. If it does not implement .get_duty_cycle(), the ratio is assumed to be 50%. This change also adds a new flag, CLK_DUTY_CYCLE_PARENT. This flag should be used to indicate that a clock, such as gates and muxes, may inherit the duty cycle ratio of its parent clock. If a clock does not provide a get_duty_cycle() callback and has CLK_DUTY_CYCLE_PARENT, then the call will be directly forwarded to its parent clock, if any. For set_duty_cycle(), the clock should also have CLK_SET_RATE_PARENT for the call to be forwarded Signed-off-by: Jerome Brunet Signed-off-by: Michael Turquette Link: lkml.kernel.org/r/20180619144141.8506-1-jbrunet@baylibre.com --- include/linux/clk-provider.h | 26 ++++++++++++++++++++++++++ include/linux/clk.h | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index b7cfa037e593..08b1aa70a38d 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -38,6 +38,8 @@ #define CLK_IS_CRITICAL BIT(11) /* do not gate, ever */ /* parents need enable during gate/ungate, set rate and re-parent */ #define CLK_OPS_PARENT_ENABLE BIT(12) +/* duty cycle call may be forwarded to the parent clock */ +#define CLK_DUTY_CYCLE_PARENT BIT(13) struct clk; struct clk_hw; @@ -66,6 +68,17 @@ struct clk_rate_request { struct clk_hw *best_parent_hw; }; +/** + * struct clk_duty - Struture encoding the duty cycle ratio of a clock + * + * @num: Numerator of the duty cycle ratio + * @den: Denominator of the duty cycle ratio + */ +struct clk_duty { + unsigned int num; + unsigned int den; +}; + /** * struct clk_ops - Callback operations for hardware clocks; these are to * be provided by the clock implementation, and will be called by drivers @@ -169,6 +182,15 @@ struct clk_rate_request { * by the second argument. Valid values for degrees are * 0-359. Return 0 on success, otherwise -EERROR. * + * @get_duty_cycle: Queries the hardware to get the current duty cycle ratio + * of a clock. Returned values denominator cannot be 0 and must be + * superior or equal to the numerator. + * + * @set_duty_cycle: Apply the duty cycle ratio to this clock signal specified by + * the numerator (2nd argurment) and denominator (3rd argument). + * Argument must be a valid ratio (denominator > 0 + * and >= numerator) Return 0 on success, otherwise -EERROR. + * * @init: Perform platform-specific initialization magic. * This is not not used by any of the basic clock types. * Please consider other ways of solving initialization problems @@ -218,6 +240,10 @@ struct clk_ops { unsigned long parent_accuracy); int (*get_phase)(struct clk_hw *hw); int (*set_phase)(struct clk_hw *hw, int degrees); + int (*get_duty_cycle)(struct clk_hw *hw, + struct clk_duty *duty); + int (*set_duty_cycle)(struct clk_hw *hw, + struct clk_duty *duty); void (*init)(struct clk_hw *hw); void (*debug_init)(struct clk_hw *hw, struct dentry *dentry); }; diff --git a/include/linux/clk.h b/include/linux/clk.h index 0dbd0885b2c2..4f750c481b82 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -141,6 +141,27 @@ int clk_set_phase(struct clk *clk, int degrees); */ int clk_get_phase(struct clk *clk); +/** + * clk_set_duty_cycle - adjust the duty cycle ratio of a clock signal + * @clk: clock signal source + * @num: numerator of the duty cycle ratio to be applied + * @den: denominator of the duty cycle ratio to be applied + * + * Adjust the duty cycle of a clock signal by the specified ratio. Returns 0 on + * success, -EERROR otherwise. + */ +int clk_set_duty_cycle(struct clk *clk, unsigned int num, unsigned int den); + +/** + * clk_get_duty_cycle - return the duty cycle ratio of a clock signal + * @clk: clock signal source + * @scale: scaling factor to be applied to represent the ratio as an integer + * + * Returns the duty cycle ratio multiplied by the scale provided, otherwise + * returns -EERROR. + */ +int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale); + /** * clk_is_match - check if two clk's point to the same hardware clock * @p: clk compared against q @@ -183,6 +204,18 @@ static inline long clk_get_phase(struct clk *clk) return -ENOTSUPP; } +static inline int clk_set_duty_cycle(struct clk *clk, unsigned int num, + unsigned int den) +{ + return -ENOTSUPP; +} + +static inline unsigned int clk_get_scaled_duty_cycle(struct clk *clk, + unsigned int scale) +{ + return 0; +} + static inline bool clk_is_match(const struct clk *p, const struct clk *q) { return p == q; -- cgit v1.2.3 From 19e0c58f6552638c86395f0717210326fdf14fd2 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 19 Jun 2018 15:10:56 -0700 Subject: iomap: generic inline data handling Add generic inline data handling by adding a pointer to the inline data region to struct iomap. When handling a buffered IOMAP_INLINE write, iomap_write_begin will copy the current inline data from the inline data region into the page cache, and iomap_write_end will copy the changes in the page cache back to the inline data region. This doesn't cover inline data reads and direct I/O yet because so far, we have no users. Signed-off-by: Andreas Gruenbacher [hch: small cleanups to better fit in with other iomap work] Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index a044a824da85..10d6cff7f69a 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -55,6 +55,7 @@ struct iomap { u16 flags; /* flags for mapping */ struct block_device *bdev; /* block device for I/O */ struct dax_device *dax_dev; /* dax_dev for dax operations */ + void *inline_data; }; /* -- cgit v1.2.3 From 63899c6f8851c32214b19390254fa1ae90b582df Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jun 2018 15:10:56 -0700 Subject: iomap: add a page_done callback This will be used by gfs2 to attach data to transactions for the journaled data mode. But the concept is generic enough that we might be able to use it for other purposes like encryption/integrity post-processing in the future. Based on a patch from Andreas Gruenbacher. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 10d6cff7f69a..45f43865b0f0 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -9,6 +9,7 @@ struct fiemap_extent_info; struct inode; struct iov_iter; struct kiocb; +struct page; struct vm_area_struct; struct vm_fault; @@ -56,6 +57,14 @@ struct iomap { struct block_device *bdev; /* block device for I/O */ struct dax_device *dax_dev; /* dax_dev for dax operations */ void *inline_data; + + /* + * Called when finished processing a page in the mapping returned in + * this iomap. At least for now this is only supported in the buffered + * write path. + */ + void (*page_done)(struct inode *inode, loff_t pos, unsigned copied, + struct page *page, struct iomap *iomap); }; /* -- cgit v1.2.3 From e184fde6f3f5353040dd4b5637f823fc87436e55 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 19 Jun 2018 15:10:57 -0700 Subject: iomap: add private pointer to struct iomap Add a private pointer to struct iomap to allow filesystems to pass data from iomap_begin to iomap_end. Will be used by gfs2 for passing on the on-disk inode buffer head. Signed-off-by: Andreas Gruenbacher Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 45f43865b0f0..1f36523d448a 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -57,6 +57,7 @@ struct iomap { struct block_device *bdev; /* block device for I/O */ struct dax_device *dax_dev; /* dax_dev for dax operations */ void *inline_data; + void *private; /* filesystem private */ /* * Called when finished processing a page in the mapping returned in -- cgit v1.2.3 From 72b4daa241295440f98e80ae21294a67b27ca091 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jun 2018 15:10:57 -0700 Subject: iomap: add an iomap-based readpage and readpages implementation Simply use iomap_apply to iterate over the file and a submit a bio for each non-uptodate but mapped region and zero everything else. Note that as-is this can not be used for file systems with a blocksize smaller than the page size, but that support will be added later. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 1f36523d448a..30d314407f66 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -99,6 +99,9 @@ struct iomap_ops { ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); +int iomap_readpage(struct page *page, const struct iomap_ops *ops); +int iomap_readpages(struct address_space *mapping, struct list_head *pages, + unsigned nr_pages, const struct iomap_ops *ops); int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, -- cgit v1.2.3 From 693ba15c9202fe0283404abe4066e1b986e284eb Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 12 Jun 2018 12:05:45 -0700 Subject: scsi: Remove percpu_ida With its one user gone, remove the library code. Signed-off-by: Matthew Wilcox Reviewed-by: Jens Axboe Signed-off-by: Martin K. Petersen --- include/linux/percpu_ida.h | 83 ---------------------------------------------- 1 file changed, 83 deletions(-) delete mode 100644 include/linux/percpu_ida.h (limited to 'include/linux') diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h deleted file mode 100644 index 07d78e4653bc..000000000000 --- a/include/linux/percpu_ida.h +++ /dev/null @@ -1,83 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PERCPU_IDA_H__ -#define __PERCPU_IDA_H__ - -#include -#include -#include -#include -#include -#include -#include - -struct percpu_ida_cpu; - -struct percpu_ida { - /* - * number of tags available to be allocated, as passed to - * percpu_ida_init() - */ - unsigned nr_tags; - unsigned percpu_max_size; - unsigned percpu_batch_size; - - struct percpu_ida_cpu __percpu *tag_cpu; - - /* - * Bitmap of cpus that (may) have tags on their percpu freelists: - * steal_tags() uses this to decide when to steal tags, and which cpus - * to try stealing from. - * - * It's ok for a freelist to be empty when its bit is set - steal_tags() - * will just keep looking - but the bitmap _must_ be set whenever a - * percpu freelist does have tags. - */ - cpumask_t cpus_have_tags; - - struct { - spinlock_t lock; - /* - * When we go to steal tags from another cpu (see steal_tags()), - * we want to pick a cpu at random. Cycling through them every - * time we steal is a bit easier and more or less equivalent: - */ - unsigned cpu_last_stolen; - - /* For sleeping on allocation failure */ - wait_queue_head_t wait; - - /* - * Global freelist - it's a stack where nr_free points to the - * top - */ - unsigned nr_free; - unsigned *freelist; - } ____cacheline_aligned_in_smp; -}; - -/* - * Number of tags we move between the percpu freelist and the global freelist at - * a time - */ -#define IDA_DEFAULT_PCPU_BATCH_MOVE 32U -/* Max size of percpu freelist, */ -#define IDA_DEFAULT_PCPU_SIZE ((IDA_DEFAULT_PCPU_BATCH_MOVE * 3) / 2) - -int percpu_ida_alloc(struct percpu_ida *pool, int state); -void percpu_ida_free(struct percpu_ida *pool, unsigned tag); - -void percpu_ida_destroy(struct percpu_ida *pool); -int __percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags, - unsigned long max_size, unsigned long batch_size); -static inline int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags) -{ - return __percpu_ida_init(pool, nr_tags, IDA_DEFAULT_PCPU_SIZE, - IDA_DEFAULT_PCPU_BATCH_MOVE); -} - -typedef int (*percpu_ida_cb)(unsigned, void *); -int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn, - void *data); - -unsigned percpu_ida_free_tags(struct percpu_ida *pool, int cpu); -#endif /* __PERCPU_IDA_H__ */ -- cgit v1.2.3 From 2fa4a32613c9182b00e46872755b0662374424a7 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Thu, 10 May 2018 11:05:16 +0800 Subject: scsi: libsas: dynamically allocate and free ata host Commit 2623c7a5f2 ("libata: add refcounting to ata_host") v4.17+ introduced refcounting to ata_host and will increase or decrease the refcount when adding or deleting transport ATA port. Now the ata host for libsas is embedded in domain_device, and the ->kref member is not initialized. Afer we add ata transport class, ata_host_get() will be called when adding transport ATA port and a warning will be triggered as below: refcount_t: increment on 0; use-after-free. WARNING: CPU: 2 PID: 103 at lib/refcount.c:153 refcount_inc+0x40/0x48 ...... Call trace: refcount_inc+0x40/0x48 ata_host_get+0x10/0x18 ata_tport_add+0x40/0x120 ata_sas_tport_add+0xc/0x14 sas_ata_init+0x7c/0xc8 sas_discover_domain+0x380/0x53c process_one_work+0x12c/0x288 worker_thread+0x58/0x3f0 kthread+0xfc/0x128 ret_from_fork+0x10/0x18 And also when removing transport ATA port ata_host_put() will be called and another similar warning will be triggered. If the refcount decreased to zero, the ata host will be freed. But this ata host is only part of domain_device, it cannot be freed directly. So we have to change this embedded static ata host to a dynamically allocated ata host and initialize the ->kref member. To use ata_host_get() and ata_host_put() in libsas, we need to move the declaration of these functions to the public libata.h and export them. Fixes: b6240a4df018 ("scsi: libsas: add transport class for ATA devices") Signed-off-by: Jason Yan CC: John Garry CC: Taras Kondratiuk CC: Tejun Heo Acked-by: Tejun Heo Signed-off-by: Martin K. Petersen --- include/linux/libata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 8b8946dd63b9..33e9718397e2 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1110,6 +1110,8 @@ extern struct ata_host *ata_host_alloc(struct device *dev, int max_ports); extern struct ata_host *ata_host_alloc_pinfo(struct device *dev, const struct ata_port_info * const * ppi, int n_ports); extern int ata_slave_link_init(struct ata_port *ap); +extern void ata_host_get(struct ata_host *host); +extern void ata_host_put(struct ata_host *host); extern int ata_host_start(struct ata_host *host); extern int ata_host_register(struct ata_host *host, struct scsi_host_template *sht); -- cgit v1.2.3 From 6519750210d9d3330e85d12e0128652edde448d2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 12 Jun 2018 10:34:50 +0200 Subject: sched/swait: Remove __prepare_to_swait There is no public user of this API, remove it. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: Linus Torvalds Cc: bigeasy@linutronix.de Cc: oleg@redhat.com Cc: paulmck@linux.vnet.ibm.com Cc: pbonzini@redhat.com Link: https://lkml.kernel.org/r/20180612083909.157076812@infradead.org --- include/linux/swait.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swait.h b/include/linux/swait.h index bf8cb0dee23c..d6a5e949e4ca 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -161,7 +161,6 @@ extern void swake_up(struct swait_queue_head *q); extern void swake_up_all(struct swait_queue_head *q); extern void swake_up_locked(struct swait_queue_head *q); -extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait); extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state); -- cgit v1.2.3 From 0abf17bc7790dd0467ed0e38522242f23c5da1c4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 12 Jun 2018 10:34:51 +0200 Subject: sched/swait: Switch to full exclusive mode Linus noted that swait basically implements exclusive mode -- because swake_up() only wakes a single waiter. And because of that it should take care to properly deal with the interruptible case. In short, the problem is that swake_up() can race with a signal. In this this case it is possible the swake_up() 'wakes' the waiter that is already on the way out because it just got a signal and the wakeup gets lost. The normal wait code is very careful and avoids this situation, make sure we do too. Copy the exact exclusive semantics from wait. Suggested-by: Linus Torvalds Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: Linus Torvalds Cc: bigeasy@linutronix.de Cc: oleg@redhat.com Cc: paulmck@linux.vnet.ibm.com Cc: pbonzini@redhat.com Link: https://lkml.kernel.org/r/20180612083909.209762413@infradead.org --- include/linux/swait.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swait.h b/include/linux/swait.h index d6a5e949e4ca..dd032061112d 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -38,8 +38,8 @@ * all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right * sleeper state. * - * - the exclusive mode; because this requires preserving the list order - * and this is hard. + * - the !exclusive mode; because that leads to O(n) wakeups, everything is + * exclusive. * * - custom wake callback functions; because you cannot give any guarantees * about random code. This also allows swait to be used in RT, such that @@ -167,9 +167,10 @@ extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queu extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait); extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); -/* as per ___wait_event() but for swait, therefore "exclusive == 0" */ +/* as per ___wait_event() but for swait, therefore "exclusive == 1" */ #define ___swait_event(wq, condition, state, ret, cmd) \ ({ \ + __label__ __out; \ struct swait_queue __wait; \ long __ret = ret; \ \ @@ -182,13 +183,13 @@ extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ - break; \ + goto __out; \ } \ \ cmd; \ } \ finish_swait(&wq, &__wait); \ - __ret; \ +__out: __ret; \ }) #define __swait_event(wq, condition) \ -- cgit v1.2.3 From b3dae109fa89d67334bf3349babab3ad9b6f233f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 12 Jun 2018 10:34:52 +0200 Subject: sched/swait: Rename to exclusive Since swait basically implemented exclusive waits only, make sure the API reflects that. $ git grep -l -e "\" -e "\" | while read file; do sed -i -e 's/\/&_one/g' -e 's/\/&_exclusive/g' $file; done With a few manual touch-ups. Suggested-by: Linus Torvalds Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: Linus Torvalds Cc: bigeasy@linutronix.de Cc: oleg@redhat.com Cc: paulmck@linux.vnet.ibm.com Cc: pbonzini@redhat.com Link: https://lkml.kernel.org/r/20180612083909.261946548@infradead.org --- include/linux/swait.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swait.h b/include/linux/swait.h index dd032061112d..73e06e9986d4 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -16,7 +16,7 @@ * wait-queues, but the semantics are actually completely different, and * every single user we have ever had has been buggy (or pointless). * - * A "swake_up()" only wakes up _one_ waiter, which is not at all what + * A "swake_up_one()" only wakes up _one_ waiter, which is not at all what * "wake_up()" does, and has led to problems. In other cases, it has * been fine, because there's only ever one waiter (kvm), but in that * case gthe whole "simple" wait-queue is just pointless to begin with, @@ -115,7 +115,7 @@ extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name * CPU0 - waker CPU1 - waiter * * for (;;) { - * @cond = true; prepare_to_swait(&wq_head, &wait, state); + * @cond = true; prepare_to_swait_exclusive(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() * if (swait_active(wq_head)) if (@cond) * wake_up(wq_head); break; @@ -157,11 +157,11 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq) return swait_active(wq); } -extern void swake_up(struct swait_queue_head *q); +extern void swake_up_one(struct swait_queue_head *q); extern void swake_up_all(struct swait_queue_head *q); extern void swake_up_locked(struct swait_queue_head *q); -extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); +extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state); extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state); extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait); @@ -196,7 +196,7 @@ __out: __ret; \ (void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \ schedule()) -#define swait_event(wq, condition) \ +#define swait_event_exclusive(wq, condition) \ do { \ if (condition) \ break; \ @@ -208,7 +208,7 @@ do { \ TASK_UNINTERRUPTIBLE, timeout, \ __ret = schedule_timeout(__ret)) -#define swait_event_timeout(wq, condition, timeout) \ +#define swait_event_timeout_exclusive(wq, condition, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ @@ -220,7 +220,7 @@ do { \ ___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0, \ schedule()) -#define swait_event_interruptible(wq, condition) \ +#define swait_event_interruptible_exclusive(wq, condition) \ ({ \ int __ret = 0; \ if (!(condition)) \ @@ -233,7 +233,7 @@ do { \ TASK_INTERRUPTIBLE, timeout, \ __ret = schedule_timeout(__ret)) -#define swait_event_interruptible_timeout(wq, condition, timeout) \ +#define swait_event_interruptible_timeout_exclusive(wq, condition, timeout)\ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ @@ -246,7 +246,7 @@ do { \ (void)___swait_event(wq, condition, TASK_IDLE, 0, schedule()) /** - * swait_event_idle - wait without system load contribution + * swait_event_idle_exclusive - wait without system load contribution * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @@ -257,7 +257,7 @@ do { \ * condition and doesn't want to contribute to system load. Signals are * ignored. */ -#define swait_event_idle(wq, condition) \ +#define swait_event_idle_exclusive(wq, condition) \ do { \ if (condition) \ break; \ @@ -270,7 +270,7 @@ do { \ __ret = schedule_timeout(__ret)) /** - * swait_event_idle_timeout - wait up to timeout without load contribution + * swait_event_idle_timeout_exclusive - wait up to timeout without load contribution * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout at which we'll give up in jiffies @@ -288,7 +288,7 @@ do { \ * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ -#define swait_event_idle_timeout(wq, condition, timeout) \ +#define swait_event_idle_timeout_exclusive(wq, condition, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ -- cgit v1.2.3 From a19741e5e5a9f1f02f8e3c037bde7d73d4bfae9c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 28 May 2018 11:47:52 +0200 Subject: dma_buf: remove device parameter from attach callback v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The device parameter is completely unused because it is available in the attachment structure as well. v2: fix kerneldoc as well Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/226643/ --- include/linux/dma-buf.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 88917fa796e4..c0ad5bf61188 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -55,11 +55,11 @@ struct dma_buf_ops { * @attach: * * This is called from dma_buf_attach() to make sure that a given - * &device can access the provided &dma_buf. Exporters which support - * buffer objects in special locations like VRAM or device-specific - * carveout areas should check whether the buffer could be move to - * system memory (or directly accessed by the provided device), and - * otherwise need to fail the attach operation. + * &dma_buf_attachment.dev can access the provided &dma_buf. Exporters + * which support buffer objects in special locations like VRAM or + * device-specific carveout areas should check whether the buffer could + * be move to system memory (or directly accessed by the provided + * device), and otherwise need to fail the attach operation. * * The exporter should also in general check whether the current * allocation fullfills the DMA constraints of the new device. If this @@ -77,8 +77,7 @@ struct dma_buf_ops { * to signal that backing storage is already allocated and incompatible * with the requirements of requesting device. */ - int (*attach)(struct dma_buf *, struct device *, - struct dma_buf_attachment *); + int (*attach)(struct dma_buf *, struct dma_buf_attachment *); /** * @detach: -- cgit v1.2.3 From f664a52695429b68afb4e130a0f69cd5fd1fec86 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 28 May 2018 13:34:01 +0200 Subject: dma-buf: remove kmap_atomic interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Neither used nor correctly implemented anywhere. Just completely remove the interface. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Acked-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/226645/ --- include/linux/dma-buf.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index c0ad5bf61188..58725f890b5b 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -205,8 +205,6 @@ struct dma_buf_ops { * to be restarted. */ int (*end_cpu_access)(struct dma_buf *, enum dma_data_direction); - void *(*map_atomic)(struct dma_buf *, unsigned long); - void (*unmap_atomic)(struct dma_buf *, unsigned long, void *); void *(*map)(struct dma_buf *, unsigned long); void (*unmap)(struct dma_buf *, unsigned long, void *); @@ -394,8 +392,6 @@ int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); int dma_buf_end_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); -void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long); -void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *); void *dma_buf_kmap(struct dma_buf *, unsigned long); void dma_buf_kunmap(struct dma_buf *, unsigned long, void *); -- cgit v1.2.3 From c03cea42149de56fbae2301d7123daaa2cfe80e2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jun 2018 15:10:58 -0700 Subject: iomap: add initial support for writes without buffer heads For now just limited to blocksize == PAGE_SIZE, where we can simply read in the full page in write begin, and just set the whole page dirty after copying data into it. This code is enabled by default and XFS will now be feed pages without buffer heads in ->writepage and ->writepages. If a file system sets the IOMAP_F_BUFFER_HEAD flag on the iomap the old path will still be used, this both helps the transition in XFS and prepares for the gfs2 migration to the iomap infrastructure. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 30d314407f66..5eb9ca8d7ce5 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -30,6 +30,7 @@ struct vm_fault; */ #define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */ #define IOMAP_F_DIRTY 0x02 /* uncommitted metadata */ +#define IOMAP_F_BUFFER_HEAD 0x04 /* file system requires buffer heads */ /* * Flags that only need to be reported for IOMAP_REPORT requests: @@ -102,6 +103,7 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, int iomap_readpage(struct page *page, const struct iomap_ops *ops); int iomap_readpages(struct address_space *mapping, struct list_head *pages, unsigned nr_pages, const struct iomap_ops *ops); +int iomap_set_page_dirty(struct page *page); int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, -- cgit v1.2.3 From 17dbca119312b4e8173d4e25ff64262119fcef38 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 13 Jun 2018 15:48:26 -0700 Subject: x86/speculation/l1tf: Add sysfs reporting for l1tf L1TF core kernel workarounds are cheap and normally always enabled, However they still should be reported in sysfs if the system is vulnerable or mitigated. Add the necessary CPU feature/bug bits. - Extend the existing checks for Meltdowns to determine if the system is vulnerable. All CPUs which are not vulnerable to Meltdown are also not vulnerable to L1TF - Check for 32bit non PAE and emit a warning as there is no practical way for mitigation due to the limited physical address bits - If the system has more than MAX_PA/2 physical memory the invert page workarounds don't protect the system against the L1TF attack anymore, because an inverted physical address will also point to valid memory. Print a warning in this case and report that the system is vulnerable. Add a function which returns the PFN limit for the L1TF mitigation, which will be used in follow up patches for sanity and range checks. [ tglx: Renamed the CPU feature bit to L1TF_PTEINV ] Signed-off-by: Andi Kleen Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Acked-by: Dave Hansen --- include/linux/cpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a97a63eef59f..d3da5184aa1c 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -55,6 +55,8 @@ extern ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_l1tf(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, -- cgit v1.2.3 From 377eeaa8e11fe815b1d07c81c4a0e2843a8c15eb Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 13 Jun 2018 15:48:28 -0700 Subject: x86/speculation/l1tf: Limit swap file size to MAX_PA/2 For the L1TF workaround its necessary to limit the swap file size to below MAX_PA/2, so that the higher bits of the swap offset inverted never point to valid memory. Add a mechanism for the architecture to override the swap file size check in swapfile.c and add a x86 specific max swapfile check function that enforces that limit. The check is only enabled if the CPU is vulnerable to L1TF. In VMs with 42bit MAX_PA the typical limit is 2TB now, on a native system with 46bit PA it is 32TB. The limit is only per individual swap file, so it's always possible to exceed these limits with multiple swap files or partitions. Signed-off-by: Andi Kleen Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Acked-by: Michal Hocko Acked-by: Dave Hansen --- include/linux/swapfile.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index 06bd7b096167..e06febf62978 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -10,5 +10,7 @@ extern spinlock_t swap_lock; extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; extern int try_to_unuse(unsigned int, bool, unsigned long); +extern unsigned long generic_max_swapfile_size(void); +extern unsigned long max_swapfile_size(void); #endif /* _LINUX_SWAPFILE_H */ -- cgit v1.2.3 From 9262478220eac908ae6e168c3df2c453c87e2da3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 20 Jun 2018 17:24:09 -0700 Subject: bpf: enforce correct alignment for instructions After commit 9facc336876f ("bpf: reject any prog that failed read-only lock") offsetof(struct bpf_binary_header, image) became 3 instead of 4, breaking powerpc BPF badly, since instructions need to be word aligned. Fixes: 9facc336876f ("bpf: reject any prog that failed read-only lock") Signed-off-by: Eric Dumazet Cc: Daniel Borkmann Cc: Martin KaFai Lau Cc: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index b615df57b7d5..20f2659dd829 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -472,7 +472,9 @@ struct sock_fprog_kern { struct bpf_binary_header { u16 pages; u16 locked:1; - u8 image[]; + + /* Some arches need word alignment for their instructions */ + u8 image[] __aligned(4); }; struct bpf_prog { -- cgit v1.2.3 From 5a6cf77f5e35e7af35d36a1e7dc21a42f6412e4f Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 20 Jun 2018 01:05:07 +0900 Subject: kprobes: Remove jprobe API implementation Remove functionally empty jprobe API implementations and test cases. Signed-off-by: Masami Hiramatsu Acked-by: Thomas Gleixner Cc: Ananth N Mavinakayanahalli Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Rostedt Cc: linux-arch@vger.kernel.org Link: https://lore.kernel.org/lkml/152942430705.15209.2307050500995264322.stgit@devbox Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 9440a2fc8893..b520baa65682 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -389,9 +389,6 @@ int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); void unregister_kprobes(struct kprobe **kps, int num); -int setjmp_pre_handler(struct kprobe *, struct pt_regs *); -int longjmp_break_handler(struct kprobe *, struct pt_regs *); -void jprobe_return(void); unsigned long arch_deref_entry_point(void *); int register_kretprobe(struct kretprobe *rp); -- cgit v1.2.3 From 4de58696de076d9bd2745d1cbe0930635c3f5ac9 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 20 Jun 2018 01:17:15 +0900 Subject: kprobes: Remove jprobe stub API Remove jprobe stub APIs from linux/kprobes.h since the jprobe implementation was completely gone. Signed-off-by: Masami Hiramatsu Acked-by: Thomas Gleixner Cc: Ananth N Mavinakayanahalli Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Rostedt Cc: linux-arch@vger.kernel.org Link: https://lore.kernel.org/lkml/152942503572.15209.1652552217914694917.stgit@devbox Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 50 ------------------------------------------------- 1 file changed, 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index b520baa65682..e909413e4e38 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -63,7 +63,6 @@ struct pt_regs; struct kretprobe; struct kretprobe_instance; typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *); -typedef int (*kprobe_break_handler_t) (struct kprobe *, struct pt_regs *); typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *, unsigned long flags); typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *, @@ -101,12 +100,6 @@ struct kprobe { */ kprobe_fault_handler_t fault_handler; - /* - * ... called if breakpoint trap occurs in probe handler. - * Return 1 if it handled break, otherwise kernel will see it. - */ - kprobe_break_handler_t break_handler; - /* Saved opcode (which has been replaced with breakpoint) */ kprobe_opcode_t opcode; @@ -154,24 +147,6 @@ static inline int kprobe_ftrace(struct kprobe *p) return p->flags & KPROBE_FLAG_FTRACE; } -/* - * Special probe type that uses setjmp-longjmp type tricks to resume - * execution at a specified entry with a matching prototype corresponding - * to the probed function - a trick to enable arguments to become - * accessible seamlessly by probe handling logic. - * Note: - * Because of the way compilers allocate stack space for local variables - * etc upfront, regardless of sub-scopes within a function, this mirroring - * principle currently works only for probes placed on function entry points. - */ -struct jprobe { - struct kprobe kp; - void *entry; /* probe handling code to jump to */ -}; - -/* For backward compatibility with old code using JPROBE_ENTRY() */ -#define JPROBE_ENTRY(handler) (handler) - /* * Function-return probe - * Note: @@ -436,9 +411,6 @@ static inline void unregister_kprobe(struct kprobe *p) static inline void unregister_kprobes(struct kprobe **kps, int num) { } -static inline void jprobe_return(void) -{ -} static inline int register_kretprobe(struct kretprobe *rp) { return -ENOSYS; @@ -465,20 +437,6 @@ static inline int enable_kprobe(struct kprobe *kp) return -ENOSYS; } #endif /* CONFIG_KPROBES */ -static inline int register_jprobe(struct jprobe *p) -{ - return -ENOSYS; -} -static inline int register_jprobes(struct jprobe **jps, int num) -{ - return -ENOSYS; -} -static inline void unregister_jprobe(struct jprobe *p) -{ -} -static inline void unregister_jprobes(struct jprobe **jps, int num) -{ -} static inline int disable_kretprobe(struct kretprobe *rp) { return disable_kprobe(&rp->kp); @@ -487,14 +445,6 @@ static inline int enable_kretprobe(struct kretprobe *rp) { return enable_kprobe(&rp->kp); } -static inline int disable_jprobe(struct jprobe *jp) -{ - return -ENOSYS; -} -static inline int enable_jprobe(struct jprobe *jp) -{ - return -ENOSYS; -} #ifndef CONFIG_KPROBES static inline bool is_kprobe_insn_slot(unsigned long addr) -- cgit v1.2.3 From 9a789fcfe8605417f7a1a970355f5efa4fe88c64 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 19 Jun 2018 09:32:30 -0400 Subject: rseq/cleanup: Do not abort rseq c.s. in child on fork() Considering that we explicitly forbid system calls in rseq critical sections, it is not valid to issue a fork or clone system call within a rseq critical section, so rseq_fork() is not required to restart an active rseq c.s. in the child process. Signed-off-by: Mathieu Desnoyers Cc: Andrew Morton Cc: Andy Lutomirski Cc: Ben Maurer Cc: Boqun Feng Cc: Catalin Marinas Cc: Chris Lameter Cc: Dave Watson Cc: Joel Fernandes Cc: Josh Triplett Cc: Linus Torvalds Cc: Michael Kerrisk Cc: Paul E . McKenney Cc: Paul Turner Cc: Peter Zijlstra Cc: Russell King Cc: Shuah Khan Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-api@vger.kernel.org Cc: linux-kselftest@vger.kernel.org Link: https://lore.kernel.org/lkml/20180619133230.4087-4-mathieu.desnoyers@efficios.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 87bf02d93a27..c1882643d455 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1831,9 +1831,7 @@ static inline void rseq_migrate(struct task_struct *t) /* * If parent process has a registered restartable sequences area, the - * child inherits. Only applies when forking a process, not a thread. In - * case a parent fork() in the middle of a restartable sequence, set the - * resume notifier to force the child to retry. + * child inherits. Only applies when forking a process, not a thread. */ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { @@ -1847,7 +1845,6 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) t->rseq_len = current->rseq_len; t->rseq_sig = current->rseq_sig; t->rseq_event_mask = current->rseq_event_mask; - rseq_preempt(t); } } -- cgit v1.2.3 From 8bd9cb51daac89337295b6f037b0486911e1b408 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 19 Jun 2018 13:53:08 +0100 Subject: locking/atomics, asm-generic: Move some macros from to a new file In preparation for implementing the asm-generic atomic bitops in terms of atomic_long_*(), we need to prevent implementations from pulling in . A common reason for this include is for the BITS_PER_BYTE definition, so move this and some other BIT() and masking macros into a new header file, . Signed-off-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Cc: yamada.masahiro@socionext.com Link: https://lore.kernel.org/lkml/1529412794-17720-4-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- include/linux/bitops.h | 22 +--------------------- include/linux/bits.h | 26 ++++++++++++++++++++++++++ 2 files changed, 27 insertions(+), 21 deletions(-) create mode 100644 include/linux/bits.h (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 4cac4e1a72ff..af419012d77d 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -2,29 +2,9 @@ #ifndef _LINUX_BITOPS_H #define _LINUX_BITOPS_H #include +#include -#ifdef __KERNEL__ -#define BIT(nr) (1UL << (nr)) -#define BIT_ULL(nr) (1ULL << (nr)) -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) -#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) -#define BITS_PER_BYTE 8 #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) -#endif - -/* - * Create a contiguous bitmask starting at bit position @l and ending at - * position @h. For example - * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. - */ -#define GENMASK(h, l) \ - (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) - -#define GENMASK_ULL(h, l) \ - (((~0ULL) - (1ULL << (l)) + 1) & \ - (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); diff --git a/include/linux/bits.h b/include/linux/bits.h new file mode 100644 index 000000000000..2b7b532c1d51 --- /dev/null +++ b/include/linux/bits.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_BITS_H +#define __LINUX_BITS_H +#include + +#define BIT(nr) (1UL << (nr)) +#define BIT_ULL(nr) (1ULL << (nr)) +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) +#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) +#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) +#define BITS_PER_BYTE 8 + +/* + * Create a contiguous bitmask starting at bit position @l and ending at + * position @h. For example + * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. + */ +#define GENMASK(h, l) \ + (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + +#define GENMASK_ULL(h, l) \ + (((~0ULL) - (1ULL << (l)) + 1) & \ + (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) + +#endif /* __LINUX_BITS_H */ -- cgit v1.2.3 From 05736e4ac13c08a4a9b1ef2de26dd31a32cbee57 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 29 May 2018 17:48:27 +0200 Subject: cpu/hotplug: Provide knobs to control SMT Provide a command line and a sysfs knob to control SMT. The command line options are: 'nosmt': Enumerate secondary threads, but do not online them 'nosmt=force': Ignore secondary threads completely during enumeration via MP table and ACPI/MADT. The sysfs control file has the following states (read/write): 'on': SMT is enabled. Secondary threads can be freely onlined 'off': SMT is disabled. Secondary threads, even if enumerated cannot be onlined 'forceoff': SMT is permanentely disabled. Writes to the control file are rejected. 'notsupported': SMT is not supported by the CPU The command line option 'nosmt' sets the sysfs control to 'off'. This can be changed to 'on' to reenable SMT during runtime. The command line option 'nosmt=force' sets the sysfs control to 'forceoff'. This cannot be changed during runtime. When SMT is 'on' and the control file is changed to 'off' then all online secondary threads are offlined and attempts to online a secondary thread later on are rejected. When SMT is 'off' and the control file is changed to 'on' then secondary threads can be onlined again. The 'off' -> 'on' transition does not automatically online the secondary threads. When the control file is set to 'forceoff', the behaviour is the same as setting it to 'off', but the operation is irreversible and later writes to the control file are rejected. When the control status is 'notsupported' then writes to the control file are rejected. Signed-off-by: Thomas Gleixner Reviewed-by: Konrad Rzeszutek Wilk Acked-by: Ingo Molnar --- include/linux/cpu.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index d3da5184aa1c..7532cbf27b1d 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -168,4 +168,17 @@ void cpuhp_report_idle_dead(void); static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +enum cpuhp_smt_control { + CPU_SMT_ENABLED, + CPU_SMT_DISABLED, + CPU_SMT_FORCE_DISABLED, + CPU_SMT_NOT_SUPPORTED, +}; + +#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) +extern enum cpuhp_smt_control cpu_smt_control; +#else +# define cpu_smt_control (CPU_SMT_ENABLED) +#endif + #endif /* _LINUX_CPU_H_ */ -- cgit v1.2.3 From bfc18e389c7a09fbbbed6bf4032396685b14246e Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:04 +0100 Subject: atomics/treewide: Rename __atomic_add_unless() => atomic_fetch_add_unless() While __atomic_add_unless() was originally intended as a building-block for atomic_add_unless(), it's now used in a number of places around the kernel. It's the only common atomic operation named __atomic*(), rather than atomic_*(), and for consistency it would be better named atomic_fetch_add_unless(). This lack of consistency is slightly confusing, and gets in the way of scripting atomics. Given that, let's clean things up and promote it to an official part of the atomics API, in the form of atomic_fetch_add_unless(). This patch converts definitions and invocations over to the new name, including the instrumented version, using the following script: ---- git grep -w __atomic_add_unless | while read line; do sed -i '{s/\<__atomic_add_unless\>/atomic_fetch_add_unless/}' "${line%%:*}"; done git grep -w __arch_atomic_add_unless | while read line; do sed -i '{s/\<__arch_atomic_add_unless\>/arch_atomic_fetch_add_unless/}' "${line%%:*}"; done ---- Note that we do not have atomic{64,_long}_fetch_add_unless(), which will be introduced by later patches. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Palmer Dabbelt Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-2-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 01ce3997cb42..9cc982936675 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -530,7 +530,7 @@ */ static inline int atomic_add_unless(atomic_t *v, int a, int u) { - return __atomic_add_unless(v, a, u) != u; + return atomic_fetch_add_unless(v, a, u) != u; } /** -- cgit v1.2.3 From f74445b6dd6b8f33ed34e005d19ecbb49171dabf Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:06 +0100 Subject: atomics/treewide: Remove atomic_inc_not_zero_hint() While documentation suggests atomic_inc_not_zero_hint() will perform better than atomic_inc_not_zero(), this is unlikely to be the case. No architectures implement atomic_inc_not_zero_hint() directly, and thus it either falls back to atomic_inc_not_zero(), or a loop using atomic_cmpxchg(). Whenever the hint does not match the value in memory, the repeated use of atomic_cmpxchg() will be more expensive than the read that atomic_inc_not_zero_hint() attempts to avoid. For architectures with LL/SC atomics, a read cannot be avoided, and it would always be better to use atomic_inc_not_zero() directly. For other architectures, their own atomic_inc_not_zero() is likely to be more optimal than an atomic_cmpxchg() loop regardless. Generally, atomic_inc_not_zero_hint() is liable to perform worse than atomic_inc_not_zero(). Further, atomic_inc_not_zero_hint() only exists for atomic_t, and not atomic64_t or atomic_long_t, and there is only one user in the kernel tree. Given all this, let's remove atomic_inc_not_zero_hint(), and migrate the existing user over to atomic_inc_not_zero(). There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-4-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 32 -------------------------------- 1 file changed, 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 9cc982936675..5c5620ae5a35 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -571,38 +571,6 @@ static inline int atomic_fetch_andnot_release(int i, atomic_t *v) } #endif -/** - * atomic_inc_not_zero_hint - increment if not null - * @v: pointer of type atomic_t - * @hint: probable value of the atomic before the increment - * - * This version of atomic_inc_not_zero() gives a hint of probable - * value of the atomic. This helps processor to not read the memory - * before doing the atomic read/modify/write cycle, lowering - * number of bus transactions on some arches. - * - * Returns: 0 if increment was not done, 1 otherwise. - */ -#ifndef atomic_inc_not_zero_hint -static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint) -{ - int val, c = hint; - - /* sanity test, should be removed by compiler if hint is a constant */ - if (!hint) - return atomic_inc_not_zero(v); - - do { - val = atomic_cmpxchg(v, c, c + 1); - if (val == c) - return 1; - c = val; - } while (c); - - return 0; -} -#endif - #ifndef atomic_inc_unless_negative static inline int atomic_inc_unless_negative(atomic_t *p) { -- cgit v1.2.3 From ade5ef9280c33993099199c51e2e27c2c4013afd Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:07 +0100 Subject: atomics: Make conditional ops return 'bool' Some of the atomics return a status value, which is a boolean value describing whether the operation was performed. To make it clear that this is a boolean value, let's update the common fallbacks to return bool, fixing up the return values and comments likewise. At the same time, let's simplify the description of the operations in their respective comments. The instrumented atomics and generic atomic64 implementation are updated accordingly. Note that atomic64_dec_if_positive() doesn't follow the usual test op pattern, and returns the would-be decremented value. This is not changed. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Boqun Feng Cc: Linus Torvalds Cc: Michael Ellerman Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-5-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 5c5620ae5a35..307a7f6d619a 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -2,6 +2,8 @@ /* Atomic operations usable in machine independent code */ #ifndef _LINUX_ATOMIC_H #define _LINUX_ATOMIC_H +#include + #include #include @@ -525,10 +527,10 @@ * @a: the amount to add to v... * @u: ...unless v is equal to u. * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns non-zero if @v was not @u, and zero otherwise. + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. */ -static inline int atomic_add_unless(atomic_t *v, int a, int u) +static inline bool atomic_add_unless(atomic_t *v, int a, int u) { return atomic_fetch_add_unless(v, a, u) != u; } @@ -537,8 +539,8 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) * atomic_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic_t * - * Atomically increments @v by 1, so long as @v is non-zero. - * Returns non-zero if @v was non-zero, and zero otherwise. + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. */ #ifndef atomic_inc_not_zero #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) @@ -572,28 +574,28 @@ static inline int atomic_fetch_andnot_release(int i, atomic_t *v) #endif #ifndef atomic_inc_unless_negative -static inline int atomic_inc_unless_negative(atomic_t *p) +static inline bool atomic_inc_unless_negative(atomic_t *p) { int v, v1; for (v = 0; v >= 0; v = v1) { v1 = atomic_cmpxchg(p, v, v + 1); if (likely(v1 == v)) - return 1; + return true; } - return 0; + return false; } #endif #ifndef atomic_dec_unless_positive -static inline int atomic_dec_unless_positive(atomic_t *p) +static inline bool atomic_dec_unless_positive(atomic_t *p) { int v, v1; for (v = 0; v <= 0; v = v1) { v1 = atomic_cmpxchg(p, v, v - 1); if (likely(v1 == v)) - return 1; + return true; } - return 0; + return false; } #endif -- cgit v1.2.3 From bef828204a1bc7a0fd3a24551c4265e9c2ab95ed Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:08 +0100 Subject: atomics/treewide: Make atomic64_inc_not_zero() optional We define a trivial fallback for atomic_inc_not_zero(), but don't do the same for atomic64_inc_not_zero(), leading most architectures to define the same boilerplate. Let's add a fallback in , and remove the redundant implementations. Note that atomic64_add_unless() is always defined in , and promotes its arguments to the requisite types, so we need not do this explicitly. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Acked-by: Palmer Dabbelt Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-6-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 307a7f6d619a..ae3f30923d05 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -1019,6 +1019,17 @@ static inline int atomic_dec_if_positive(atomic_t *v) #define atomic64_try_cmpxchg_release atomic64_try_cmpxchg #endif /* atomic64_try_cmpxchg */ +/** + * atomic64_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +#ifndef atomic64_inc_not_zero +#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +#endif + #ifndef atomic64_andnot static inline void atomic64_andnot(long long i, atomic64_t *v) { -- cgit v1.2.3 From eccc2da8c03f316bba202e15af2be4615f461900 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:09 +0100 Subject: atomics/treewide: Make atomic_fetch_add_unless() optional Several architectures these have a near-identical implementation based on atomic_read() and atomic_cmpxchg() which we can instead define in , so let's do so, using something close to the existing x86 implementation with try_cmpxchg(). Where an architecture provides its own atomic_fetch_add_unless(), it must define a preprocessor symbol for it. The instrumented atomics are updated accordingly. Note that arch/arc's existing atomic_fetch_add_unless() had redundant barriers, as these are already present in its atomic_cmpxchg() implementation. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Geert Uytterhoeven Reviewed-by: Will Deacon Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Palmer Dabbelt Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Cc: Vineet Gupta Link: https://lore.kernel.org/lkml/20180621121321.4761-7-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index ae3f30923d05..b89ba36cab94 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -521,6 +521,29 @@ #endif #endif /* xchg_relaxed */ +/** + * atomic_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns the original value of @v. + */ +#ifndef atomic_fetch_add_unless +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int c = atomic_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!atomic_try_cmpxchg(v, &c, c + a)); + + return c; +} +#endif + /** * atomic_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t -- cgit v1.2.3 From 0ae1d994020d75ac065fd42ac4cbf5ac6ce9b255 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:10 +0100 Subject: atomics: Prepare for atomic64_fetch_add_unless() Currently all architectures must implement atomic_fetch_add_unless(), with common code providing atomic_add_unless(). Architectures must also implement atomic64_add_unless() directly, with no corresponding atomic64_fetch_add_unless(). This divergence is unfortunate, and means that the APIs for atomic_t, atomic64_t, and atomic_long_t differ. In preparation for unifying things, with architectures providing atomic64_fetch_add_unless, this patch adds a generic atomic64_add_unless() which will use atomic64_fetch_add_unless(). The instrumented atomics are updated to take this case into account. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Albert Ou Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Boqun Feng Cc: Ivan Kokshaysky Cc: Linus Torvalds Cc: Matt Turner Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Richard Henderson Cc: Russell King Cc: Thomas Gleixner Cc: Vineet Gupta Link: https://lore.kernel.org/lkml/20180621121321.4761-8-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index b89ba36cab94..3c03de648007 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -1042,6 +1042,22 @@ static inline int atomic_dec_if_positive(atomic_t *v) #define atomic64_try_cmpxchg_release atomic64_try_cmpxchg #endif /* atomic64_try_cmpxchg */ +/** + * atomic64_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +#ifdef atomic64_fetch_add_unless +static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u) +{ + return atomic64_fetch_add_unless(v, a, u) != u; +} +#endif + /** * atomic64_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic64_t -- cgit v1.2.3 From 356701329fb391184618eda7b7fb68cb35271506 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:17 +0100 Subject: atomics/treewide: Make atomic64_fetch_add_unless() optional Architectures with atomic64_fetch_add_unless() provide a preprocessor symbol if they do so, and all other architectures have trivial C implementations of atomic64_add_unless() which are near-identical. Let's unify the trivial definitions of atomic64_fetch_add_unless() in , so that we always have both atomic64_fetch_add_unless() and atomic64_add_unless() with less boilerplate code. This means that atomic64_add_unless() is always implemented in core code, and the instrumented atomics are updated accordingly. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-15-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 3c03de648007..530562ac7909 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -1042,6 +1042,30 @@ static inline int atomic_dec_if_positive(atomic_t *v) #define atomic64_try_cmpxchg_release atomic64_try_cmpxchg #endif /* atomic64_try_cmpxchg */ +/** + * atomic64_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns the original value of @v. + */ +#ifndef atomic64_fetch_add_unless +static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, + long long u) +{ + long long c = atomic64_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!atomic64_try_cmpxchg(v, &c, c + a)); + + return c; +} +#endif + /** * atomic64_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t @@ -1051,12 +1075,10 @@ static inline int atomic_dec_if_positive(atomic_t *v) * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ -#ifdef atomic64_fetch_add_unless static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u) { return atomic64_fetch_add_unless(v, a, u) != u; } -#endif /** * atomic64_inc_not_zero - increment unless the number is zero -- cgit v1.2.3 From 18cc1814d4e7560412c9c8c6d28f9d6782c8b402 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:18 +0100 Subject: atomics/treewide: Make test ops optional Some of the atomics return the result of a test applied after the atomic operation, and almost all architectures implement these as trivial wrappers around the underlying atomic. Specifically: * _inc_and_test(v) is (_inc_return(v) == 0) * _dec_and_test(v) is (_dec_return(v) == 0) * _sub_and_test(i, v) is (_sub_return(i, v) == 0) * _add_negative(i, v) is (_add_return(i, v) < 0) Rather than have these definitions duplicated in all architectures, with minor inconsistencies in formatting and documentation, let's make these operations optional, with default fallbacks as above. Implementations must now provide a preprocessor symbol. The instrumented atomics are updated accordingly. Both x86 and m68k have custom implementations, which are left as-is, given preprocessor symbols to avoid being overridden. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Palmer Dabbelt Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-16-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 124 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 124 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 530562ac7909..3ee8da9023cd 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -569,6 +569,68 @@ static inline bool atomic_add_unless(atomic_t *v, int a, int u) #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) #endif +/** + * atomic_inc_and_test - increment and test + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic_inc_and_test +static inline bool atomic_inc_and_test(atomic_t *v) +{ + return atomic_inc_return(v) == 0; +} +#endif + +/** + * atomic_dec_and_test - decrement and test + * @v: pointer of type atomic_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +#ifndef atomic_dec_and_test +static inline bool atomic_dec_and_test(atomic_t *v) +{ + return atomic_dec_return(v) == 0; +} +#endif + +/** + * atomic_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic_sub_and_test +static inline bool atomic_sub_and_test(int i, atomic_t *v) +{ + return atomic_sub_return(i, v) == 0; +} +#endif + +/** + * atomic_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +#ifndef atomic_add_negative +static inline bool atomic_add_negative(int i, atomic_t *v) +{ + return atomic_add_return(i, v) < 0; +} +#endif + #ifndef atomic_andnot static inline void atomic_andnot(int i, atomic_t *v) { @@ -1091,6 +1153,68 @@ static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u) #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) #endif +/** + * atomic64_inc_and_test - increment and test + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic64_inc_and_test +static inline bool atomic64_inc_and_test(atomic64_t *v) +{ + return atomic64_inc_return(v) == 0; +} +#endif + +/** + * atomic64_dec_and_test - decrement and test + * @v: pointer of type atomic64_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +#ifndef atomic64_dec_and_test +static inline bool atomic64_dec_and_test(atomic64_t *v) +{ + return atomic64_dec_return(v) == 0; +} +#endif + +/** + * atomic64_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic64_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic64_sub_and_test +static inline bool atomic64_sub_and_test(long long i, atomic64_t *v) +{ + return atomic64_sub_return(i, v) == 0; +} +#endif + +/** + * atomic64_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +#ifndef atomic64_add_negative +static inline bool atomic64_add_negative(long long i, atomic64_t *v) +{ + return atomic64_add_return(i, v) < 0; +} +#endif + #ifndef atomic64_andnot static inline void atomic64_andnot(long long i, atomic64_t *v) { -- cgit v1.2.3 From 9837559d8eb01ce834e56fc9a567c1d94ebd3698 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:19 +0100 Subject: atomics/treewide: Make unconditional inc/dec ops optional Many of the inc/dec ops are mandatory, but for most architectures inc/dec are simply trivial wrappers around their corresponding add/sub ops. Let's make all the inc/dec ops optional, so that we can get rid of these boilerplate wrappers. The instrumented atomics are updated accordingly. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Acked-by: Palmer Dabbelt Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-17-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 3ee8da9023cd..24f345df7ba6 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -97,11 +97,23 @@ #endif #endif /* atomic_add_return_relaxed */ +#ifndef atomic_inc +#define atomic_inc(v) atomic_add(1, (v)) +#endif + /* atomic_inc_return_relaxed */ #ifndef atomic_inc_return_relaxed + +#ifndef atomic_inc_return +#define atomic_inc_return(v) atomic_add_return(1, (v)) +#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v)) +#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v)) +#define atomic_inc_return_release(v) atomic_add_return_release(1, (v)) +#else /* atomic_inc_return */ #define atomic_inc_return_relaxed atomic_inc_return #define atomic_inc_return_acquire atomic_inc_return #define atomic_inc_return_release atomic_inc_return +#endif /* atomic_inc_return */ #else /* atomic_inc_return_relaxed */ @@ -145,11 +157,23 @@ #endif #endif /* atomic_sub_return_relaxed */ +#ifndef atomic_dec +#define atomic_dec(v) atomic_sub(1, (v)) +#endif + /* atomic_dec_return_relaxed */ #ifndef atomic_dec_return_relaxed + +#ifndef atomic_dec_return +#define atomic_dec_return(v) atomic_sub_return(1, (v)) +#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v)) +#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v)) +#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v)) +#else /* atomic_dec_return */ #define atomic_dec_return_relaxed atomic_dec_return #define atomic_dec_return_acquire atomic_dec_return #define atomic_dec_return_release atomic_dec_return +#endif /* atomic_dec_return */ #else /* atomic_dec_return_relaxed */ @@ -748,11 +772,23 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_add_return_relaxed */ +#ifndef atomic64_inc +#define atomic64_inc(v) atomic64_add(1, (v)) +#endif + /* atomic64_inc_return_relaxed */ #ifndef atomic64_inc_return_relaxed + +#ifndef atomic64_inc_return +#define atomic64_inc_return(v) atomic64_add_return(1, (v)) +#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v)) +#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v)) +#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v)) +#else /* atomic64_inc_return */ #define atomic64_inc_return_relaxed atomic64_inc_return #define atomic64_inc_return_acquire atomic64_inc_return #define atomic64_inc_return_release atomic64_inc_return +#endif /* atomic64_inc_return */ #else /* atomic64_inc_return_relaxed */ @@ -797,11 +833,23 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_sub_return_relaxed */ +#ifndef atomic64_dec +#define atomic64_dec(v) atomic64_sub(1, (v)) +#endif + /* atomic64_dec_return_relaxed */ #ifndef atomic64_dec_return_relaxed + +#ifndef atomic64_dec_return +#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) +#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v)) +#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v)) +#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v)) +#else /* atomic64_dec_return */ #define atomic64_dec_return_relaxed atomic64_dec_return #define atomic64_dec_return_acquire atomic64_dec_return #define atomic64_dec_return_release atomic64_dec_return +#endif /* atomic64_dec_return */ #else /* atomic64_dec_return_relaxed */ -- cgit v1.2.3 From b3a2a05f9111de0b79312e577608a27b0318c0a1 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:20 +0100 Subject: atomics/treewide: Make conditional inc/dec ops optional The conditional inc/dec ops differ for atomic_t and atomic64_t: - atomic_inc_unless_positive() is optional for atomic_t, and doesn't exist for atomic64_t. - atomic_dec_unless_negative() is optional for atomic_t, and doesn't exist for atomic64_t. - atomic_dec_if_positive is optional for atomic_t, and is mandatory for atomic64_t. Let's make these consistently optional for both. At the same time, let's clean up the existing fallbacks to use atomic_try_cmpxchg(). The instrumented atomics are updated accordingly. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-18-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 97 +++++++++++++++++++++++++++++++++++++------------- 1 file changed, 73 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 24f345df7ba6..93fe5b4041e1 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -683,28 +683,30 @@ static inline int atomic_fetch_andnot_release(int i, atomic_t *v) #endif #ifndef atomic_inc_unless_negative -static inline bool atomic_inc_unless_negative(atomic_t *p) +static inline bool atomic_inc_unless_negative(atomic_t *v) { - int v, v1; - for (v = 0; v >= 0; v = v1) { - v1 = atomic_cmpxchg(p, v, v + 1); - if (likely(v1 == v)) - return true; - } - return false; + int c = atomic_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!atomic_try_cmpxchg(v, &c, c + 1)); + + return true; } #endif #ifndef atomic_dec_unless_positive -static inline bool atomic_dec_unless_positive(atomic_t *p) +static inline bool atomic_dec_unless_positive(atomic_t *v) { - int v, v1; - for (v = 0; v <= 0; v = v1) { - v1 = atomic_cmpxchg(p, v, v - 1); - if (likely(v1 == v)) - return true; - } - return false; + int c = atomic_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!atomic_try_cmpxchg(v, &c, c - 1)); + + return true; } #endif @@ -718,17 +720,14 @@ static inline bool atomic_dec_unless_positive(atomic_t *p) #ifndef atomic_dec_if_positive static inline int atomic_dec_if_positive(atomic_t *v) { - int c, old, dec; - c = atomic_read(v); - for (;;) { + int dec, c = atomic_read(v); + + do { dec = c - 1; if (unlikely(dec < 0)) break; - old = atomic_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } + } while (!atomic_try_cmpxchg(v, &c, dec)); + return dec; } #endif @@ -1290,6 +1289,56 @@ static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v } #endif +#ifndef atomic64_inc_unless_negative +static inline bool atomic64_inc_unless_negative(atomic64_t *v) +{ + long long c = atomic64_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!atomic64_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#endif + +#ifndef atomic64_dec_unless_positive +static inline bool atomic64_dec_unless_positive(atomic64_t *v) +{ + long long c = atomic64_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!atomic64_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#endif + +/* + * atomic64_dec_if_positive - decrement by 1 if old value positive + * @v: pointer of type atomic64_t + * + * The function returns the old value of *v minus 1, even if + * the atomic64 variable, v, was not decremented. + */ +#ifndef atomic64_dec_if_positive +static inline long long atomic64_dec_if_positive(atomic64_t *v) +{ + long long dec, c = atomic64_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!atomic64_try_cmpxchg(v, &c, dec)); + + return dec; +} +#endif + #define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) #define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) -- cgit v1.2.3 From 7cc7eaad49c30ac165ecf84d95b26f7e0d53bd97 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:21 +0100 Subject: atomics/treewide: Clean up '*_andnot()' ifdeffery The ifdeffery for atomic*_{fetch_,}andnot() is unlike that for all the other atomics. If atomic*_andnot() is not defined, the corresponding atomic*_fetch_andnot() is assumed to not be defined. Additionally, the fallbacks for the various ordering cases are written much later in atomic.h as static inlines. This isn't problematic today, but gets in the way of scripting the generation of atomics. To prepare for scripting, this patch: * Switches to separate ifdefs for atomic*_andnot() and atomic*_fetch_andnot(), updating implementations as appropriate. * Moves the fallbacks into the standards ifdefs, as macro expansions rather than static inlines. * Removes trivial andnot implementations from architectures, where these are superseded by core code. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-19-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 96 ++++++++++++++++---------------------------------- 1 file changed, 30 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 93fe5b4041e1..8e04f1f69bd9 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -354,12 +354,22 @@ #endif #endif /* atomic_fetch_and_relaxed */ -#ifdef atomic_andnot -/* atomic_fetch_andnot_relaxed */ +#ifndef atomic_andnot +#define atomic_andnot(i, v) atomic_and(~(int)(i), (v)) +#endif + #ifndef atomic_fetch_andnot_relaxed -#define atomic_fetch_andnot_relaxed atomic_fetch_andnot -#define atomic_fetch_andnot_acquire atomic_fetch_andnot -#define atomic_fetch_andnot_release atomic_fetch_andnot + +#ifndef atomic_fetch_andnot +#define atomic_fetch_andnot(i, v) atomic_fetch_and(~(int)(i), (v)) +#define atomic_fetch_andnot_relaxed(i, v) atomic_fetch_and_relaxed(~(int)(i), (v)) +#define atomic_fetch_andnot_acquire(i, v) atomic_fetch_and_acquire(~(int)(i), (v)) +#define atomic_fetch_andnot_release(i, v) atomic_fetch_and_release(~(int)(i), (v)) +#else /* atomic_fetch_andnot */ +#define atomic_fetch_andnot_relaxed atomic_fetch_andnot +#define atomic_fetch_andnot_acquire atomic_fetch_andnot +#define atomic_fetch_andnot_release atomic_fetch_andnot +#endif /* atomic_fetch_andnot */ #else /* atomic_fetch_andnot_relaxed */ @@ -378,7 +388,6 @@ __atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__) #endif #endif /* atomic_fetch_andnot_relaxed */ -#endif /* atomic_andnot */ /* atomic_fetch_xor_relaxed */ #ifndef atomic_fetch_xor_relaxed @@ -655,33 +664,6 @@ static inline bool atomic_add_negative(int i, atomic_t *v) } #endif -#ifndef atomic_andnot -static inline void atomic_andnot(int i, atomic_t *v) -{ - atomic_and(~i, v); -} - -static inline int atomic_fetch_andnot(int i, atomic_t *v) -{ - return atomic_fetch_and(~i, v); -} - -static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) -{ - return atomic_fetch_and_relaxed(~i, v); -} - -static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) -{ - return atomic_fetch_and_acquire(~i, v); -} - -static inline int atomic_fetch_andnot_release(int i, atomic_t *v) -{ - return atomic_fetch_and_release(~i, v); -} -#endif - #ifndef atomic_inc_unless_negative static inline bool atomic_inc_unless_negative(atomic_t *v) { @@ -1029,12 +1011,22 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_fetch_and_relaxed */ -#ifdef atomic64_andnot -/* atomic64_fetch_andnot_relaxed */ +#ifndef atomic64_andnot +#define atomic64_andnot(i, v) atomic64_and(~(long long)(i), (v)) +#endif + #ifndef atomic64_fetch_andnot_relaxed -#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot -#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot -#define atomic64_fetch_andnot_release atomic64_fetch_andnot + +#ifndef atomic64_fetch_andnot +#define atomic64_fetch_andnot(i, v) atomic64_fetch_and(~(long long)(i), (v)) +#define atomic64_fetch_andnot_relaxed(i, v) atomic64_fetch_and_relaxed(~(long long)(i), (v)) +#define atomic64_fetch_andnot_acquire(i, v) atomic64_fetch_and_acquire(~(long long)(i), (v)) +#define atomic64_fetch_andnot_release(i, v) atomic64_fetch_and_release(~(long long)(i), (v)) +#else /* atomic64_fetch_andnot */ +#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot +#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot +#define atomic64_fetch_andnot_release atomic64_fetch_andnot +#endif /* atomic64_fetch_andnot */ #else /* atomic64_fetch_andnot_relaxed */ @@ -1053,7 +1045,6 @@ static inline int atomic_dec_if_positive(atomic_t *v) __atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__) #endif #endif /* atomic64_fetch_andnot_relaxed */ -#endif /* atomic64_andnot */ /* atomic64_fetch_xor_relaxed */ #ifndef atomic64_fetch_xor_relaxed @@ -1262,33 +1253,6 @@ static inline bool atomic64_add_negative(long long i, atomic64_t *v) } #endif -#ifndef atomic64_andnot -static inline void atomic64_andnot(long long i, atomic64_t *v) -{ - atomic64_and(~i, v); -} - -static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v) -{ - return atomic64_fetch_and(~i, v); -} - -static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v) -{ - return atomic64_fetch_and_relaxed(~i, v); -} - -static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v) -{ - return atomic64_fetch_and_acquire(~i, v); -} - -static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v) -{ - return atomic64_fetch_and_release(~i, v); -} -#endif - #ifndef atomic64_inc_unless_negative static inline bool atomic64_inc_unless_negative(atomic64_t *v) { -- cgit v1.2.3 From f642fb5864a6e3645edce6f85ffe7b44d5e9b990 Mon Sep 17 00:00:00 2001 From: "mike.travis@hpe.com" Date: Thu, 24 May 2018 15:17:12 -0500 Subject: x86/platform/UV: Add adjustable set memory block size function Add a new function to "adjust" the current fixed UV memory block size of 2GB so it can be changed to a different physical boundary. This is out of necessity so arch dependent code can accommodate specific BIOS requirements which can align these new PMEM modules at less than the default boundaries. A "set order" type of function was used to insure that the memory block size will be a power of two value without requiring a validity check. 64GB was chosen as the upper limit for memory block size values to accommodate upcoming 4PB systems which have 6 more bits of physical address space (46 becoming 52). Signed-off-by: Mike Travis Reviewed-by: Andrew Banman Cc: Andrew Morton Cc: Dimitri Sivanich Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Russ Anderson Cc: Thomas Gleixner Cc: dan.j.williams@intel.com Cc: jgross@suse.com Cc: kirill.shutemov@linux.intel.com Cc: mhocko@suse.com Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/lkml/20180524201711.609546602@stormcage.americas.sgi.com Signed-off-by: Ingo Molnar --- include/linux/memory.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 31ca3e28b0eb..a6ddefc60517 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -38,6 +38,7 @@ struct memory_block { int arch_get_memory_phys_device(unsigned long start_pfn); unsigned long memory_block_size_bytes(void); +int set_memory_block_size_order(unsigned int order); /* These states are exposed to userspace as text strings in sysfs */ #define MEM_ONLINE (1<<0) /* exposed to userspace */ -- cgit v1.2.3 From 8730662d7b2582f65dd6c59ab1e0b7fa461c79b0 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 24 Apr 2018 14:22:38 -0700 Subject: kernel.h: Fix a typo in comment Signed-off-by: Wei Wang Cc: Andrew Morton Cc: Borislav Petkov Cc: Crt Mori Cc: Josh Poimboeuf Cc: Kees Cook Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Steven Rostedt Cc: Thomas Gleixner Cc: gregkh@linuxfoundation.org Cc: wei.vince.wang@gmail.com Link: https://lkml.kernel.org/lkml/20180424212241.16013-1-wvw@google.com Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d23123238534..941dc0a5a877 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -666,7 +666,7 @@ do { \ * your code. (Extra memory is used for special buffers that are * allocated when trace_printk() is used.) * - * A little optization trick is done here. If there's only one + * A little optimization trick is done here. If there's only one * argument, there's no need to scan the string for printf formats. * The trace_puts() will suffice. But how can we take advantage of * using trace_puts() when trace_printk() has only one argument? -- cgit v1.2.3 From 75a040ff14d9a99fc041f5e1d8f09541cab13ba4 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 1 Apr 2018 01:00:36 +0300 Subject: locking/refcounts: Include fewer headers in Debloat 's dependencies: - is not needed, but is. - is not needed, only a forward declaration of "struct mutex". - is not needed, is enough. Signed-off-by: Alexey Dobriyan Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: https://lkml.kernel.org/lkml/20180331220036.GA7676@avx2 Signed-off-by: Ingo Molnar --- include/linux/refcount.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 4193c41e383a..c36addd27dd5 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -3,9 +3,10 @@ #define _LINUX_REFCOUNT_H #include -#include -#include -#include +#include +#include + +struct mutex; /** * struct refcount_t - variant of atomic_t specialized for reference counts -- cgit v1.2.3 From 0af5107cd0640ee3424e337b492e4b11b450ce28 Mon Sep 17 00:00:00 2001 From: Talat Batheesh Date: Thu, 17 May 2018 11:14:18 +0300 Subject: net/mlx5: Add RoCE RX ICRC encapsulated counter Add capability bit in PCAM register and RoCE ICRC error counter to PPCNT register. Signed-off-by: Talat Batheesh Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f810772e80c0..deb3a459a22e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1681,7 +1681,11 @@ struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits { u8 rx_buffer_full_low[0x20]; - u8 reserved_at_1c0[0x600]; + u8 rx_icrc_encapsulated_high[0x20]; + + u8 rx_icrc_encapsulated_low[0x20]; + + u8 reserved_at_200[0x5c0]; }; struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits { @@ -8044,8 +8048,9 @@ struct mlx5_ifc_peir_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x76]; - + u8 reserved_at_0[0x6d]; + u8 rx_icrc_encapsulated_counter[0x1]; + u8 reserved_at_6e[0x8]; u8 pfcc_mask[0x1]; u8 reserved_at_77[0x4]; u8 rx_buffer_fullness_counters[0x1]; -- cgit v1.2.3 From 0eb71a9da5796851fa87ddc1a534066c0fe54055 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 18 Jun 2018 12:52:50 +1000 Subject: rhashtable: split rhashtable.h Due to the use of rhashtables in net namespaces, rhashtable.h is included in lots of the kernel, so a small changes can required a large recompilation. This makes development painful. This patch splits out rhashtable-types.h which just includes the major type declarations, and does not include (non-trivial) inline code. rhashtable.h is no longer included by anything in the include/ directory. Common include files only include rhashtable-types.h so a large recompilation is only triggered when that changes. Acked-by: Herbert Xu Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/ipc.h | 2 +- include/linux/ipc_namespace.h | 2 +- include/linux/mroute_base.h | 2 +- include/linux/rhashtable-types.h | 139 +++++++++++++++++++++++++++++++++++++++ include/linux/rhashtable.h | 127 +---------------------------------- 5 files changed, 144 insertions(+), 128 deletions(-) create mode 100644 include/linux/rhashtable-types.h (limited to 'include/linux') diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 6cc2df7f7ac9..e1c9eea6015b 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -4,7 +4,7 @@ #include #include -#include +#include #include #include diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index b5630c8eb2f3..6cea726612b7 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -9,7 +9,7 @@ #include #include #include -#include +#include struct user_namespace; diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index d633f737b3c6..fd436cdd4725 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -2,7 +2,7 @@ #define __LINUX_MROUTE_BASE_H #include -#include +#include #include #include #include diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h new file mode 100644 index 000000000000..9740063ff13b --- /dev/null +++ b/include/linux/rhashtable-types.h @@ -0,0 +1,139 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Resizable, Scalable, Concurrent Hash Table + * + * Simple structures that might be needed in include + * files. + */ + +#ifndef _LINUX_RHASHTABLE_TYPES_H +#define _LINUX_RHASHTABLE_TYPES_H + +#include +#include +#include +#include + +struct rhash_head { + struct rhash_head __rcu *next; +}; + +struct rhlist_head { + struct rhash_head rhead; + struct rhlist_head __rcu *next; +}; + +struct bucket_table; + +/** + * struct rhashtable_compare_arg - Key for the function rhashtable_compare + * @ht: Hash table + * @key: Key to compare against + */ +struct rhashtable_compare_arg { + struct rhashtable *ht; + const void *key; +}; + +typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); +typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed); +typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, + const void *obj); + +/** + * struct rhashtable_params - Hash table construction parameters + * @nelem_hint: Hint on number of elements, should be 75% of desired size + * @key_len: Length of key + * @key_offset: Offset of key in struct to be hashed + * @head_offset: Offset of rhash_head in struct to be hashed + * @max_size: Maximum size while expanding + * @min_size: Minimum size while shrinking + * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) + * @automatic_shrinking: Enable automatic shrinking of tables + * @nulls_base: Base value to generate nulls marker + * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) + * @obj_hashfn: Function to hash object + * @obj_cmpfn: Function to compare key with object + */ +struct rhashtable_params { + u16 nelem_hint; + u16 key_len; + u16 key_offset; + u16 head_offset; + unsigned int max_size; + u16 min_size; + bool automatic_shrinking; + u8 locks_mul; + u32 nulls_base; + rht_hashfn_t hashfn; + rht_obj_hashfn_t obj_hashfn; + rht_obj_cmpfn_t obj_cmpfn; +}; + +/** + * struct rhashtable - Hash table handle + * @tbl: Bucket table + * @key_len: Key length for hashfn + * @max_elems: Maximum number of elements in table + * @p: Configuration parameters + * @rhlist: True if this is an rhltable + * @run_work: Deferred worker to expand/shrink asynchronously + * @mutex: Mutex to protect current/future table swapping + * @lock: Spin lock to protect walker list + * @nelems: Number of elements in table + */ +struct rhashtable { + struct bucket_table __rcu *tbl; + unsigned int key_len; + unsigned int max_elems; + struct rhashtable_params p; + bool rhlist; + struct work_struct run_work; + struct mutex mutex; + spinlock_t lock; + atomic_t nelems; +}; + +/** + * struct rhltable - Hash table with duplicate objects in a list + * @ht: Underlying rhtable + */ +struct rhltable { + struct rhashtable ht; +}; + +/** + * struct rhashtable_walker - Hash table walker + * @list: List entry on list of walkers + * @tbl: The table that we were walking over + */ +struct rhashtable_walker { + struct list_head list; + struct bucket_table *tbl; +}; + +/** + * struct rhashtable_iter - Hash table iterator + * @ht: Table to iterate through + * @p: Current pointer + * @list: Current hash list pointer + * @walker: Associated rhashtable walker + * @slot: Current slot + * @skip: Number of entries to skip in slot + */ +struct rhashtable_iter { + struct rhashtable *ht; + struct rhash_head *p; + struct rhlist_head *list; + struct rhashtable_walker walker; + unsigned int slot; + unsigned int skip; + bool end_of_table; +}; + +int rhashtable_init(struct rhashtable *ht, + const struct rhashtable_params *params); +int rhltable_init(struct rhltable *hlt, + const struct rhashtable_params *params); + +#endif /* _LINUX_RHASHTABLE_TYPES_H */ diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 4e1f535c2034..48754ab07cdf 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Resizable, Scalable, Concurrent Hash Table * @@ -17,16 +18,14 @@ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H -#include -#include #include #include #include #include #include -#include #include +#include /* * The end of the chain is marked with a special nulls marks which has * the following format: @@ -64,15 +63,6 @@ */ #define RHT_ELASTICITY 16u -struct rhash_head { - struct rhash_head __rcu *next; -}; - -struct rhlist_head { - struct rhash_head rhead; - struct rhlist_head __rcu *next; -}; - /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets @@ -102,114 +92,6 @@ struct bucket_table { struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; -/** - * struct rhashtable_compare_arg - Key for the function rhashtable_compare - * @ht: Hash table - * @key: Key to compare against - */ -struct rhashtable_compare_arg { - struct rhashtable *ht; - const void *key; -}; - -typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); -typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed); -typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, - const void *obj); - -struct rhashtable; - -/** - * struct rhashtable_params - Hash table construction parameters - * @nelem_hint: Hint on number of elements, should be 75% of desired size - * @key_len: Length of key - * @key_offset: Offset of key in struct to be hashed - * @head_offset: Offset of rhash_head in struct to be hashed - * @max_size: Maximum size while expanding - * @min_size: Minimum size while shrinking - * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) - * @automatic_shrinking: Enable automatic shrinking of tables - * @nulls_base: Base value to generate nulls marker - * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) - * @obj_hashfn: Function to hash object - * @obj_cmpfn: Function to compare key with object - */ -struct rhashtable_params { - u16 nelem_hint; - u16 key_len; - u16 key_offset; - u16 head_offset; - unsigned int max_size; - u16 min_size; - bool automatic_shrinking; - u8 locks_mul; - u32 nulls_base; - rht_hashfn_t hashfn; - rht_obj_hashfn_t obj_hashfn; - rht_obj_cmpfn_t obj_cmpfn; -}; - -/** - * struct rhashtable - Hash table handle - * @tbl: Bucket table - * @key_len: Key length for hashfn - * @max_elems: Maximum number of elements in table - * @p: Configuration parameters - * @rhlist: True if this is an rhltable - * @run_work: Deferred worker to expand/shrink asynchronously - * @mutex: Mutex to protect current/future table swapping - * @lock: Spin lock to protect walker list - * @nelems: Number of elements in table - */ -struct rhashtable { - struct bucket_table __rcu *tbl; - unsigned int key_len; - unsigned int max_elems; - struct rhashtable_params p; - bool rhlist; - struct work_struct run_work; - struct mutex mutex; - spinlock_t lock; - atomic_t nelems; -}; - -/** - * struct rhltable - Hash table with duplicate objects in a list - * @ht: Underlying rhtable - */ -struct rhltable { - struct rhashtable ht; -}; - -/** - * struct rhashtable_walker - Hash table walker - * @list: List entry on list of walkers - * @tbl: The table that we were walking over - */ -struct rhashtable_walker { - struct list_head list; - struct bucket_table *tbl; -}; - -/** - * struct rhashtable_iter - Hash table iterator - * @ht: Table to iterate through - * @p: Current pointer - * @list: Current hash list pointer - * @walker: Associated rhashtable walker - * @slot: Current slot - * @skip: Number of entries to skip in slot - */ -struct rhashtable_iter { - struct rhashtable *ht; - struct rhash_head *p; - struct rhlist_head *list; - struct rhashtable_walker walker; - unsigned int slot; - unsigned int skip; - bool end_of_table; -}; - static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash) { return NULLS_MARKER(ht->p.nulls_base + hash); @@ -376,11 +258,6 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, } #endif /* CONFIG_PROVE_LOCKING */ -int rhashtable_init(struct rhashtable *ht, - const struct rhashtable_params *params); -int rhltable_init(struct rhltable *hlt, - const struct rhashtable_params *params); - void *rhashtable_insert_slow(struct rhashtable *ht, const void *key, struct rhash_head *obj); -- cgit v1.2.3 From 9f9a707738aa7a8b9f78a641b83927ada256a626 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 18 Jun 2018 12:52:50 +1000 Subject: rhashtable: remove nulls_base and related code. This "feature" is unused, undocumented, and untested and so doesn't really belong. A patch is under development to properly implement support for detecting when a search gets diverted down a different chain, which the common purpose of nulls markers. This patch actually fixes a bug too. The table resizing allows a table to grow to 2^31 buckets, but the hash is truncated to 27 bits - any growth beyond 2^27 is wasteful an ineffective. This patch results in NULLS_MARKER(0) being used for all chains, and leaves the use of rht_is_a_null() to test for it. Acked-by: Herbert Xu Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable-types.h | 2 -- include/linux/rhashtable.h | 33 +++------------------------------ 2 files changed, 3 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h index 9740063ff13b..763d613ce2c2 100644 --- a/include/linux/rhashtable-types.h +++ b/include/linux/rhashtable-types.h @@ -50,7 +50,6 @@ typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, * @min_size: Minimum size while shrinking * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) * @automatic_shrinking: Enable automatic shrinking of tables - * @nulls_base: Base value to generate nulls marker * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) * @obj_hashfn: Function to hash object * @obj_cmpfn: Function to compare key with object @@ -64,7 +63,6 @@ struct rhashtable_params { u16 min_size; bool automatic_shrinking; u8 locks_mul; - u32 nulls_base; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; rht_obj_cmpfn_t obj_cmpfn; diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 48754ab07cdf..d9f719af7936 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -28,25 +28,8 @@ #include /* * The end of the chain is marked with a special nulls marks which has - * the following format: - * - * +-------+-----------------------------------------------------+-+ - * | Base | Hash |1| - * +-------+-----------------------------------------------------+-+ - * - * Base (4 bits) : Reserved to distinguish between multiple tables. - * Specified via &struct rhashtable_params.nulls_base. - * Hash (27 bits): Full hash (unmasked) of first element added to bucket - * 1 (1 bit) : Nulls marker (always set) - * - * The remaining bits of the next pointer remain unused for now. + * the least significant bit set. */ -#define RHT_BASE_BITS 4 -#define RHT_HASH_BITS 27 -#define RHT_BASE_SHIFT RHT_HASH_BITS - -/* Base bits plus 1 bit for nulls marker */ -#define RHT_HASH_RESERVED_SPACE (RHT_BASE_BITS + 1) /* Maximum chain length before rehash * @@ -92,24 +75,14 @@ struct bucket_table { struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; -static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash) -{ - return NULLS_MARKER(ht->p.nulls_base + hash); -} - #define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \ - ((ptr) = (typeof(ptr)) rht_marker(ht, hash)) + ((ptr) = (typeof(ptr)) NULLS_MARKER(0)) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) { return ((unsigned long) ptr & 1); } -static inline unsigned long rht_get_nulls_value(const struct rhash_head *ptr) -{ - return ((unsigned long) ptr) >> 1; -} - static inline void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he) { @@ -119,7 +92,7 @@ static inline void *rht_obj(const struct rhashtable *ht, static inline unsigned int rht_bucket_index(const struct bucket_table *tbl, unsigned int hash) { - return (hash >> RHT_HASH_RESERVED_SPACE) & (tbl->size - 1); + return hash & (tbl->size - 1); } static inline unsigned int rht_key_get_hash(struct rhashtable *ht, -- cgit v1.2.3 From 9b4f64a227b6f462482a8cc68c7134dc6e26f1c1 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 18 Jun 2018 12:52:50 +1000 Subject: rhashtable: simplify INIT_RHT_NULLS_HEAD() The 'ht' and 'hash' arguments to INIT_RHT_NULLS_HEAD() are no longer used - so drop them. This allows us to also remove the nhash argument from nested_table_alloc(). Acked-by: Herbert Xu Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index d9f719af7936..3f3a182bd0b4 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -75,7 +75,7 @@ struct bucket_table { struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; -#define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \ +#define INIT_RHT_NULLS_HEAD(ptr) \ ((ptr) = (typeof(ptr)) NULLS_MARKER(0)) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) -- cgit v1.2.3 From c0690016a73fe6bd456887bbbe6e10c7f0096554 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 18 Jun 2018 12:52:50 +1000 Subject: rhashtable: clean up dereference of ->future_tbl. Using rht_dereference_bucket() to dereference ->future_tbl looks like a type error, and could be confusing. Using rht_dereference_rcu() to test a pointer for NULL adds an unnecessary barrier - rcu_access_pointer() is preferred for NULL tests when no lock is held. This uses 3 different ways to access ->future_tbl. - if we know the mutex is held, use rht_dereference() - if we don't hold the mutex, and are only testing for NULL, use rcu_access_pointer() - otherwise (using RCU protection for true dereference), use rht_dereference_rcu(). Note that this includes a simplification of the call to rhashtable_last_table() - we don't do an extra dereference before the call any more. Acked-by: Herbert Xu Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 3f3a182bd0b4..eb7111039247 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -595,7 +595,7 @@ static inline void *__rhashtable_insert_fast( lock = rht_bucket_lock(tbl, hash); spin_lock_bh(lock); - if (unlikely(rht_dereference_bucket(tbl->future_tbl, tbl, hash))) { + if (unlikely(rcu_access_pointer(tbl->future_tbl))) { slow_path: spin_unlock_bh(lock); rcu_read_unlock(); -- cgit v1.2.3 From 3f6c65d6255a872846c44182c82c78d3dc6239f5 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 19 Jun 2018 21:42:50 -0700 Subject: tcp: ignore rcv_rtt sample with old ts ecr value When receiving multiple packets with the same ts ecr value, only try to compute rcv_rtt sample with the earliest received packet. This is because the rcv_rtt calculated by later received packets could possibly include long idle time or other types of delay. For example: (1) server sends last packet of reply with TS val V1 (2) client ACKs last packet of reply with TS ecr V1 (3) long idle time passes (4) client sends next request data packet with TS ecr V1 (again!) At this time, the rcv_rtt computed on server with TS ecr V1 will be inflated with the idle time and should get ignored. Signed-off-by: Wei Wang Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 72705eaf4b84..3dbea6610304 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -350,6 +350,7 @@ struct tcp_sock { #endif /* Receiver side RTT estimation */ + u32 rcv_rtt_last_tsecr; struct { u32 rtt_us; u32 seq; -- cgit v1.2.3 From 72a8edc2d9134c2895eac2fec5eecf8230a05c96 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 22 Jun 2018 10:52:48 +0100 Subject: genirq/debugfs: Add missing IRQCHIP_SUPPORTS_LEVEL_MSI debug Debug is missing the IRQCHIP_SUPPORTS_LEVEL_MSI debug entry, making debugfs slightly less useful. Take this opportunity to also add a missing comment in the definition of IRQCHIP_SUPPORTS_LEVEL_MSI. Fixes: 6988e0e0d283 ("genirq/msi: Limit level-triggered MSI to platform devices") Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Cc: Jason Cooper Cc: Alexandre Belloni Cc: Yang Yingliang Cc: Sumit Garg Link: https://lkml.kernel.org/r/20180622095254.5906-2-marc.zyngier@arm.com --- include/linux/irq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 4bd2f34947f4..201de12a9957 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -503,6 +503,7 @@ struct irq_chip { * IRQCHIP_SKIP_SET_WAKE: Skip chip.irq_set_wake(), for this irq chip * IRQCHIP_ONESHOT_SAFE: One shot does not require mask/unmask * IRQCHIP_EOI_THREADED: Chip requires eoi() on unmask in threaded mode + * IRQCHIP_SUPPORTS_LEVEL_MSI Chip can provide two doorbells for Level MSIs */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), -- cgit v1.2.3 From bed9df97b39e73a4607189f2c4b9fb89cc3f7f59 Mon Sep 17 00:00:00 2001 From: John Garry Date: Fri, 22 Jun 2018 19:35:33 +0800 Subject: irqdesc: Delete irq_desc_get_msi_desc() Function irq_desc_get_msi_desc() is not referenced in the kernel (and does not seem to have been referenced since e39758e0ea76, 3 years ago), so delete it. Signed-off-by: John Garry Signed-off-by: Thomas Gleixner Cc: Cc: Cc: Cc: Cc: Cc: Link: https://lkml.kernel.org/r/1529667333-92959-1-git-send-email-john.garry@huawei.com --- include/linux/irqdesc.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 25b33b664537..dd1e40ddac7d 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -145,11 +145,6 @@ static inline void *irq_desc_get_handler_data(struct irq_desc *desc) return desc->irq_common_data.handler_data; } -static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) -{ - return desc->irq_common_data.msi_desc; -} - /* * Architectures call this to let the generic IRQ layer * handle an interrupt. -- cgit v1.2.3 From 784e0300fe9fe4aa81bd7df9d59e138f56bb605b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 22 Jun 2018 11:45:07 +0100 Subject: rseq: Avoid infinite recursion when delivering SIGSEGV When delivering a signal to a task that is using rseq, we call into __rseq_handle_notify_resume() so that the registers pushed in the sigframe are updated to reflect the state of the restartable sequence (for example, ensuring that the signal returns to the abort handler if necessary). However, if the rseq management fails due to an unrecoverable fault when accessing userspace or certain combinations of RSEQ_CS_* flags, then we will attempt to deliver a SIGSEGV. This has the potential for infinite recursion if the rseq code continuously fails on signal delivery. Avoid this problem by using force_sigsegv() instead of force_sig(), which is explicitly designed to reset the SEGV handler to SIG_DFL in the case of a recursive fault. In doing so, remove rseq_signal_deliver() from the internal rseq API and have an optional struct ksignal * parameter to rseq_handle_notify_resume() instead. Signed-off-by: Will Deacon Signed-off-by: Thomas Gleixner Acked-by: Mathieu Desnoyers Cc: peterz@infradead.org Cc: paulmck@linux.vnet.ibm.com Cc: boqun.feng@gmail.com Link: https://lkml.kernel.org/r/1529664307-983-1-git-send-email-will.deacon@arm.com --- include/linux/sched.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c1882643d455..9256118bd40c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1799,20 +1799,22 @@ static inline void rseq_set_notify_resume(struct task_struct *t) set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); } -void __rseq_handle_notify_resume(struct pt_regs *regs); +void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); -static inline void rseq_handle_notify_resume(struct pt_regs *regs) +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) { if (current->rseq) - __rseq_handle_notify_resume(regs); + __rseq_handle_notify_resume(ksig, regs); } -static inline void rseq_signal_deliver(struct pt_regs *regs) +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) { preempt_disable(); __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); preempt_enable(); - rseq_handle_notify_resume(regs); + rseq_handle_notify_resume(ksig, regs); } /* rseq_preempt() requires preemption to be disabled. */ @@ -1861,10 +1863,12 @@ static inline void rseq_execve(struct task_struct *t) static inline void rseq_set_notify_resume(struct task_struct *t) { } -static inline void rseq_handle_notify_resume(struct pt_regs *regs) +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) { } -static inline void rseq_signal_deliver(struct pt_regs *regs) +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) { } static inline void rseq_preempt(struct task_struct *t) -- cgit v1.2.3 From 3ee7e8697d5860b173132606d80a9cd35e7113ee Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 18 Jun 2018 15:46:58 +0200 Subject: bdi: Fix another oops in wb_workfn() syzbot is reporting NULL pointer dereference at wb_workfn() [1] due to wb->bdi->dev being NULL. And Dmitry confirmed that wb->state was WB_shutting_down after wb->bdi->dev became NULL. This indicates that unregister_bdi() failed to call wb_shutdown() on one of wb objects. The problem is in cgwb_bdi_unregister() which does cgwb_kill() and thus drops bdi's reference to wb structures before going through the list of wbs again and calling wb_shutdown() on each of them. This way the loop iterating through all wbs can easily miss a wb if that wb has already passed through cgwb_remove_from_bdi_list() called from wb_shutdown() from cgwb_release_workfn() and as a result fully shutdown bdi although wb_workfn() for this wb structure is still running. In fact there are also other ways cgwb_bdi_unregister() can race with cgwb_release_workfn() leading e.g. to use-after-free issues: CPU1 CPU2 cgwb_bdi_unregister() cgwb_kill(*slot); cgwb_release() queue_work(cgwb_release_wq, &wb->release_work); cgwb_release_workfn() wb = list_first_entry(&bdi->wb_list, ...) spin_unlock_irq(&cgwb_lock); wb_shutdown(wb); ... kfree_rcu(wb, rcu); wb_shutdown(wb); -> oops use-after-free We solve these issues by synchronizing writeback structure shutdown from cgwb_bdi_unregister() with cgwb_release_workfn() using a new mutex. That way we also no longer need synchronization using WB_shutting_down as the mutex provides it for CONFIG_CGROUP_WRITEBACK case and without CONFIG_CGROUP_WRITEBACK wb_shutdown() can be called only once from bdi_unregister(). Reported-by: syzbot Acked-by: Tejun Heo Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 0bd432a4d7bd..24251762c20c 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -22,7 +22,6 @@ struct dentry; */ enum wb_state { WB_registered, /* bdi_register() was done */ - WB_shutting_down, /* wb_shutdown() in progress */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ WB_start_all, /* nr_pages == 0 (all) work pending */ @@ -189,6 +188,7 @@ struct backing_dev_info { #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ + struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ #else struct bdi_writeback_congested *wb_congested; #endif -- cgit v1.2.3 From 63a67a926e214dac94e29147c0f3d11499f655a1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jun 2018 17:16:44 -0400 Subject: kill dentry_update_name_case() the last user is gone Spotted-by: Richard Weinberger Signed-off-by: Al Viro --- include/linux/dcache.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 66c6e17e61e5..cee70bf207fc 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -271,8 +271,6 @@ extern void d_rehash(struct dentry *); extern void d_add(struct dentry *, struct inode *); -extern void dentry_update_name_case(struct dentry *, const struct qstr *); - /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); extern void d_exchange(struct dentry *, struct dentry *); -- cgit v1.2.3 From d0dd63a8aee1ef89f2e48e554b796b9f9e4fcadb Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 16 Jun 2018 22:11:42 -0700 Subject: time: Introduce struct __kernel_itimerspec struct itimerspec is not y2038-safe. Introduce a new struct __kernel_itimerspec based on the kernel internal y2038-safe struct itimerspec64. The definition of struct __kernel_itimerspec includes two struct __kernel_timespec. Since struct __kernel_timespec has the same representation in native and compat modes, so does struct __kernel_itimerspec. This helps have a common entry point for syscalls using struct __kernel_itimerspec. New y2038-safe syscalls will use this new type. Since most of the new syscalls are just an update to the native syscalls with the type update, place the new definition under CONFIG_64BIT_TIME. This helps architectures that do not support the above config to keep using the old definition of struct itimerspec. Also change the get/put_itimerspec64 to use struct__kernel_itimerspec. This will help 32 bit architectures to use the new syscalls when architectures select CONFIG_64BIT_TIME. Signed-off-by: Deepa Dinamani Signed-off-by: Thomas Gleixner Cc: arnd@arndb.de Cc: viro@zeniv.linux.org.uk Cc: linux-fsdevel@vger.kernel.org Cc: linux-api@vger.kernel.org Cc: y2038@lists.linaro.org Link: https://lkml.kernel.org/r/20180617051144.29756-2-deepa.kernel@gmail.com --- include/linux/time.h | 4 ++-- include/linux/time64.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index aed74463592d..27d83fd2ae61 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -14,9 +14,9 @@ int get_timespec64(struct timespec64 *ts, int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts); int get_itimerspec64(struct itimerspec64 *it, - const struct itimerspec __user *uit); + const struct __kernel_itimerspec __user *uit); int put_itimerspec64(const struct itimerspec64 *it, - struct itimerspec __user *uit); + struct __kernel_itimerspec __user *uit); extern time64_t mktime64(const unsigned int year, const unsigned int mon, const unsigned int day, const unsigned int hour, diff --git a/include/linux/time64.h b/include/linux/time64.h index 0a7b2f79cec7..05634afba0db 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -12,6 +12,7 @@ typedef __u64 timeu64_t; */ #ifndef CONFIG_64BIT_TIME #define __kernel_timespec timespec +#define __kernel_itimerspec itimerspec #endif #include -- cgit v1.2.3 From afef05cf238cfcecdc5ea9b06f31027b13ce6214 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 16 Jun 2018 22:11:43 -0700 Subject: time: Enable get/put_compat_itimerspec64 always This will aid in enabling the compat syscalls on 32-bit architectures later on. Also move compat_itimerspec and related defines to compat_time.h. The compat_time.h file will eventually be deleted. Signed-off-by: Deepa Dinamani Signed-off-by: Thomas Gleixner Cc: arnd@arndb.de Cc: viro@zeniv.linux.org.uk Cc: linux-fsdevel@vger.kernel.org Cc: linux-api@vger.kernel.org Cc: y2038@lists.linaro.org Link: https://lkml.kernel.org/r/20180617051144.29756-3-deepa.kernel@gmail.com --- include/linux/compat.h | 9 --------- include/linux/compat_time.h | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index b1a5562b3215..18a13f2df14b 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -109,11 +109,6 @@ typedef compat_ulong_t compat_aio_context_t; struct compat_sel_arg_struct; struct rusage; -struct compat_itimerspec { - struct compat_timespec it_interval; - struct compat_timespec it_value; -}; - struct compat_utimbuf { compat_time_t actime; compat_time_t modtime; @@ -294,10 +289,6 @@ extern int compat_get_timespec(struct timespec *, const void __user *); extern int compat_put_timespec(const struct timespec *, void __user *); extern int compat_get_timeval(struct timeval *, const void __user *); extern int compat_put_timeval(const struct timeval *, void __user *); -extern int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits); -extern int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits); struct compat_iovec { compat_uptr_t iov_base; diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h index 31f2774f1994..e70bfd1d2c3f 100644 --- a/include/linux/compat_time.h +++ b/include/linux/compat_time.h @@ -17,7 +17,16 @@ struct compat_timeval { s32 tv_usec; }; +struct compat_itimerspec { + struct compat_timespec it_interval; + struct compat_timespec it_value; +}; + extern int compat_get_timespec64(struct timespec64 *, const void __user *); extern int compat_put_timespec64(const struct timespec64 *, void __user *); +extern int get_compat_itimerspec64(struct itimerspec64 *its, + const struct compat_itimerspec __user *uits); +extern int put_compat_itimerspec64(const struct itimerspec64 *its, + struct compat_itimerspec __user *uits); #endif /* _LINUX_COMPAT_TIME_H */ -- cgit v1.2.3 From 6ff84735070276d72af716e21c3214ee20d60e70 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 16 Jun 2018 22:11:44 -0700 Subject: time: Change types to new y2038 safe __kernel_itimerspec timer_set/gettime and timerfd_set/get apis use struct itimerspec at the user interface layer. struct itimerspec is not y2038-safe. Change these interfaces to use y2038-safe struct __kernel_itimerspec instead. This will help define new syscalls when 32bit architectures select CONFIG_64BIT_TIME. Signed-off-by: Deepa Dinamani Signed-off-by: Thomas Gleixner Cc: arnd@arndb.de Cc: viro@zeniv.linux.org.uk Cc: linux-fsdevel@vger.kernel.org Cc: linux-api@vger.kernel.org Cc: y2038@lists.linaro.org Link: https://lkml.kernel.org/r/20180617051144.29756-4-deepa.kernel@gmail.com --- include/linux/syscalls.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 73810808cdf2..38b9ec152024 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -501,9 +501,9 @@ asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes, /* fs/timerfd.c */ asmlinkage long sys_timerfd_create(int clockid, int flags); asmlinkage long sys_timerfd_settime(int ufd, int flags, - const struct itimerspec __user *utmr, - struct itimerspec __user *otmr); -asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); + const struct __kernel_itimerspec __user *utmr, + struct __kernel_itimerspec __user *otmr); +asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user *otmr); /* fs/utimes.c */ asmlinkage long sys_utimensat(int dfd, const char __user *filename, @@ -568,10 +568,10 @@ asmlinkage long sys_timer_create(clockid_t which_clock, struct sigevent __user *timer_event_spec, timer_t __user * created_timer_id); asmlinkage long sys_timer_gettime(timer_t timer_id, - struct itimerspec __user *setting); + struct __kernel_itimerspec __user *setting); asmlinkage long sys_timer_getoverrun(timer_t timer_id); asmlinkage long sys_timer_settime(timer_t timer_id, int flags, - const struct itimerspec __user *new_setting, + const struct __kernel_itimerspec __user *new_setting, struct itimerspec __user *old_setting); asmlinkage long sys_timer_delete(timer_t timer_id); asmlinkage long sys_clock_settime(clockid_t which_clock, -- cgit v1.2.3 From 92397a6c38d139d50fabbe9e2dc09b61d53b2377 Mon Sep 17 00:00:00 2001 From: Phil Reid Date: Tue, 5 Jun 2018 14:15:10 +0800 Subject: iio: buffer: fix the function signature to match implementation linux/iio/buffer-dma.h was not updated to when length was changed to unsigned int. Fixes: c043ec1ca5ba ("iio:buffer: make length types match kfifo types") Signed-off-by: Phil Reid Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer-dma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index 767467d886de..67c75372b691 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -141,7 +141,7 @@ int iio_dma_buffer_read(struct iio_buffer *buffer, size_t n, char __user *user_buffer); size_t iio_dma_buffer_data_available(struct iio_buffer *buffer); int iio_dma_buffer_set_bytes_per_datum(struct iio_buffer *buffer, size_t bpd); -int iio_dma_buffer_set_length(struct iio_buffer *buffer, int length); +int iio_dma_buffer_set_length(struct iio_buffer *buffer, unsigned int length); int iio_dma_buffer_request_update(struct iio_buffer *buffer); int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue, -- cgit v1.2.3 From faef87723ace12e5f685437c1e68cbecb69a7a89 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Jun 2018 13:08:51 +0200 Subject: dma-noncoherent: add a arch_sync_dma_for_cpu_all hook The MIPS bmips platform needs a global flush when transferring ownership back to the CPU. Add a hook for that to the dma-noncoherent implementation. Signed-off-by: Christoph Hellwig Patchwork: https://patchwork.linux-mips.org/patch/19549/ Signed-off-by: Paul Burton Cc: Florian Fainelli Cc: David Daney Cc: Kevin Cernekee Cc: Jiaxun Yang Cc: Tom Bogendoerfer Cc: Huacai Chen Cc: iommu@lists.linux-foundation.org Cc: linux-mips@linux-mips.org --- include/linux/dma-noncoherent.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 10b2654d549b..a0aa00cc909d 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -44,4 +44,12 @@ static inline void arch_sync_dma_for_cpu(struct device *dev, } #endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */ +#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL +void arch_sync_dma_for_cpu_all(struct device *dev); +#else +static inline void arch_sync_dma_for_cpu_all(struct device *dev) +{ +} +#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */ + #endif /* _LINUX_DMA_NONCOHERENT_H */ -- cgit v1.2.3 From 5e03aa61a7f3cb99852bc3ad6925f5fa3c0dcc93 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 14 Jun 2018 10:53:34 +0530 Subject: PM / Domains: Fix return value of of_genpd_opp_to_performance_state() of_genpd_opp_to_performance_state() should return 0 for errors, but the dummy routine isn't doing that. Fix it. Signed-off-by: Viresh Kumar Acked-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 9206a4fef9ac..139f79c8477a 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -276,7 +276,7 @@ static inline unsigned int of_genpd_opp_to_performance_state(struct device *dev, struct device_node *opp_node) { - return -ENODEV; + return 0; } static inline int genpd_dev_pm_attach(struct device *dev) -- cgit v1.2.3 From ad6384ba3ac98ad524194e37de379c1fe503870b Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 20 Jun 2018 11:45:37 +0530 Subject: PM / Domains: Rename opp_node to np The DT node passed here isn't necessarily an OPP node, as this routine can also be used for cases where the "required-opps" property is present directly in the device's node. Rename it. This also removes a stale comment. Acked-by: Ulf Hansson Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 139f79c8477a..cb8d84090cfb 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -234,7 +234,7 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np); int of_genpd_parse_idle_states(struct device_node *dn, struct genpd_power_state **states, int *n); unsigned int of_genpd_opp_to_performance_state(struct device *dev, - struct device_node *opp_node); + struct device_node *np); int genpd_dev_pm_attach(struct device *dev); struct device *genpd_dev_pm_attach_by_id(struct device *dev, @@ -274,7 +274,7 @@ static inline int of_genpd_parse_idle_states(struct device_node *dn, static inline unsigned int of_genpd_opp_to_performance_state(struct device *dev, - struct device_node *opp_node) + struct device_node *np) { return 0; } -- cgit v1.2.3 From 996302c5e85650722f1e5aeaeaaac12f9f362bf8 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 24 Jun 2018 00:37:44 +0900 Subject: module: replace VMLINUX_SYMBOL_STR() with __stringify() or string literal With the special case handling for Blackfin and Metag was removed by commit 94e58e0ac312 ("export.h: remove code for prefixing symbols with underscore"), VMLINUX_SYMBOL_STR() is now equivalent to __stringify(). Replace the remaining usages to prepare for the entire removal of VMLINUX_SYMBOL_STR(). Signed-off-by: Masahiro Yamada Signed-off-by: Jessica Yu --- include/linux/module.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index d44df9b2c131..f807f15bebbe 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -266,7 +266,7 @@ extern int modules_disabled; /* for sysctl */ /* Get/put a kernel symbol (calls must be symmetric) */ void *__symbol_get(const char *symbol); void *__symbol_get_gpl(const char *symbol); -#define symbol_get(x) ((typeof(&x))(__symbol_get(VMLINUX_SYMBOL_STR(x)))) +#define symbol_get(x) ((typeof(&x))(__symbol_get(__stringify(x)))) /* modules using other modules: kdb wants to see this. */ struct module_use { @@ -575,7 +575,7 @@ extern void __noreturn __module_put_and_exit(struct module *mod, #ifdef CONFIG_MODULE_UNLOAD int module_refcount(struct module *mod); void __symbol_put(const char *symbol); -#define symbol_put(x) __symbol_put(VMLINUX_SYMBOL_STR(x)) +#define symbol_put(x) __symbol_put(__stringify(x)) void symbol_put_addr(void *addr); /* Sometimes we know we already have a refcount, and it's easier not -- cgit v1.2.3 From 6136f97cd2dd2b5a88d62bd73cc663a803124c09 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 21 Jun 2018 19:27:17 -0700 Subject: HID: i2c-hid: Add vddl regulator control Some wacom w9013 devices have a vddl supply for "low valtage" requirements. Add support in this driver to turn on this low voltage supply. We can also drop a handful of error messages because the regulator core is already printing an error when bulk regulators fail to enable or disable. Cc: Benjamin Tissoires Cc: Hans de Goede Cc: Andy Shevchenko Cc: Dmitry Torokhov Cc: Doug Anderson Acked-by: Rob Herring Cc: Signed-off-by: Stephen Boyd Acked-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/platform_data/i2c-hid.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/i2c-hid.h b/include/linux/platform_data/i2c-hid.h index 1fb088239d12..c628bb5e1061 100644 --- a/include/linux/platform_data/i2c-hid.h +++ b/include/linux/platform_data/i2c-hid.h @@ -12,14 +12,13 @@ #ifndef __LINUX_I2C_HID_H #define __LINUX_I2C_HID_H +#include #include -struct regulator; - /** * struct i2chid_platform_data - used by hid over i2c implementation. * @hid_descriptor_address: i2c register where the HID descriptor is stored. - * @supply: regulator for powering on the device. + * @supplies: regulators for powering on the device. * @post_power_delay_ms: delay after powering on before device is usable. * * Note that it is the responsibility of the platform driver (or the acpi 5.0 @@ -35,7 +34,7 @@ struct regulator; */ struct i2c_hid_platform_data { u16 hid_descriptor_address; - struct regulator *supply; + struct regulator_bulk_data supplies[2]; int post_power_delay_ms; }; -- cgit v1.2.3 From 8f732850df1b2b4d8d719f7e606dfb3050e7ea11 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 31 May 2018 13:49:29 +0200 Subject: HID: core: allow concurrent registration of drivers Detected on the Dell XPS 9365. The laptop has 2 devices that benefit from the hid-generic auto-unbinding. When those 2 devices are presented to the userspace, udev loads both wacom and hid-multitouch. When this happens, the code in __hid_bus_reprobe_drivers() is called concurrently and the second device gets reprobed twice. An other bug in the power_supply subsystem prevent to remove the wacom driver if it just finished its initialization, which basically kills the wacom node. [jkosina@suse.cz: reformat changelog a bit] Fixes c17a7476e4c4 ("HID: core: rewrite the hid-generic automatic unbind") Cc: stable@vger.kernel.org # v4.17 Tested-by: Mario Limonciello Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 41a3d5775394..773bcb1d4044 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -511,6 +511,7 @@ struct hid_output_fifo { #define HID_STAT_ADDED BIT(0) #define HID_STAT_PARSED BIT(1) #define HID_STAT_DUP_DETECTED BIT(2) +#define HID_STAT_REPROBED BIT(3) struct hid_input { struct list_head list; @@ -579,7 +580,7 @@ struct hid_device { /* device report descriptor */ bool battery_avoid_query; #endif - unsigned int status; /* see STAT flags above */ + unsigned long status; /* see STAT flags above */ unsigned claimed; /* Claimed by hidinput, hiddev? */ unsigned quirks; /* Various quirks the device can pull on us */ bool io_started; /* If IO has started */ -- cgit v1.2.3 From d2d2e3c46be5d6dd8001d0eebdf7cafb9bc7006b Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Thu, 21 Jun 2018 16:43:17 +0300 Subject: acpi: Add helper for deactivating memory region Sometimes memory resource may be overlapping with SystemMemory Operation Region by design, for example if the memory region is used as a mailbox for communication with a firmware in the system. One occasion of such mailboxes is USB Type-C Connector System Software Interface (UCSI). With regions like that, it is important that the driver is able to map the memory with the requirements it has. For example, the driver should be allowed to map the memory as non-cached memory. However, if the operation region has been accessed before the driver has mapped the memory, the memory has been marked as write-back by the time the driver is loaded. That means the driver will fail to map the memory if it expects non-cached memory. To work around the problem, introducing helper that the drivers can use to temporarily deactivate (unmap) SystemMemory Operation Regions that overlap with their IO memory. Fixes: 8243edf44152 ("usb: typec: ucsi: Add ACPI driver") Cc: stable@vger.kernel.org Reviewed-by: Rafael J. Wysocki Signed-off-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/acpi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 4b35a66383f9..e54f40974eb0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -443,6 +443,9 @@ int acpi_check_resource_conflict(const struct resource *res); int acpi_check_region(resource_size_t start, resource_size_t n, const char *name); +acpi_status acpi_release_memory(acpi_handle handle, struct resource *res, + u32 level); + int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION -- cgit v1.2.3 From 379cacc5e566f7197bdeb1ea3e99219d3e880c0a Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 8 Jun 2018 16:59:37 -0400 Subject: USB: Report wakeup events on root-hub ports When a USB device attached to a root-hub port sends a wakeup request to a sleeping system, we do not report the wakeup event to the PM core. This is because a system resume involves waking up all suspended USB ports as quickly as possible; without the normal USB_RESUME_TIMEOUT delay, the host controller driver doesn't set the USB_PORT_STAT_C_SUSPEND flag and so usb_port_resume() doesn't realize that a wakeup request was received. However, some environments (such as Chrome OS) want to have all wakeup events reported so they can be ascribed to the appropriate device. To accommodate these environments, this patch adds a new routine to the hub driver and a corresponding new HCD method to be used when a root hub resumes. The HCD method returns a bitmap of ports that have initiated a wakeup signal but not yet completed resuming. The hub driver can then report to the PM core that the child devices attached to these ports initiated a wakeup event. Signed-off-by: Alan Stern Suggested-by: Anshuman Gupta Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 34a6ded6f319..97e2ddec18b1 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -322,6 +322,7 @@ struct hc_driver { int (*bus_suspend)(struct usb_hcd *); int (*bus_resume)(struct usb_hcd *); int (*start_port_reset)(struct usb_hcd *, unsigned port_num); + unsigned long (*get_resuming_ports)(struct usb_hcd *); /* force handover of high-speed port to full-speed companion */ void (*relinquish_port)(struct usb_hcd *, int); -- cgit v1.2.3 From 8793bb7f4a9dd1396575d2e9337d331662cb7555 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 19 Jun 2018 13:14:56 -0700 Subject: kbuild: add macro for controlling warnings to linux/compiler.h I have occasionally run into a situation where it would make sense to control a compiler warning from a source file rather than doing so from a Makefile using the $(cc-disable-warning, ...) or $(cc-option, ...) helpers. The approach here is similar to what glibc uses, using __diag() and related macros to encapsulate a _Pragma("GCC diagnostic ...") statement that gets turned into the respective "#pragma GCC diagnostic ..." by the preprocessor when the macro gets expanded. Like glibc, I also have an argument to pass the affected compiler version, but decided to actually evaluate that one. For now, this supports GCC_4_6, GCC_4_7, GCC_4_8, GCC_4_9, GCC_5, GCC_6, GCC_7, GCC_8 and GCC_9. Adding support for CLANG_5 and other interesting versions is straightforward here. GNU compilers starting with gcc-4.2 could support it in principle, but "#pragma GCC diagnostic push" was only added in gcc-4.6, so it seems simpler to not deal with those at all. The same versions show a large number of warnings already, so it seems easier to just leave it at that and not do a more fine-grained control for them. The use cases I found so far include: - turning off the gcc-8 -Wattribute-alias warning inside of the SYSCALL_DEFINEx() macro without having to do it globally. - Reducing the build time for a simple re-make after a change, once we move the warnings from ./Makefile and ./scripts/Makefile.extrawarn into linux/compiler.h - More control over the warnings based on other configurations, using preprocessor syntax instead of Makefile syntax. This should make it easier for the average developer to understand and change things. - Adding an easy way to turn the W=1 option on unconditionally for a subdirectory or a specific file. This has been requested by several developers in the past that want to have their subsystems W=1 clean. - Integrating clang better into the build systems. Clang supports more warnings than GCC, and we probably want to classify them as default, W=1, W=2 etc, but there are cases in which the warnings should be classified differently due to excessive false positives from one or the other compiler. - Adding a way to turn the default warnings into errors (e.g. using a new "make E=0" tag) while not also turning the W=1 warnings into errors. This patch for now just adds the minimal infrastructure in order to do the first of the list above. As the #pragma GCC diagnostic takes precedence over command line options, the next step would be to convert a lot of the individual Makefiles that set nonstandard options to use __diag() instead. [paul.burton@mips.com: - Rebase atop current master. - Add __diag_GCC, or more generally __diag_, abstraction to avoid code outside of linux/compiler-gcc.h needing to duplicate knowledge about different GCC versions. - Add a comment argument to __diag_{ignore,warn,error} which isn't used in the expansion of the macros but serves to push people to document the reason for using them - per feedback from Kees Cook. - Translate severity to GCC-specific pragmas in linux/compiler-gcc.h rather than using GCC-specific in linux/compiler_types.h. - Drop all but GCC 8 macros, since we only need to define macros for versions that we need to introduce pragmas for, and as of this series that's just GCC 8. - Capitalize comments in linux/compiler-gcc.h to match the style of the rest of the file. - Line up macro definitions with tabs in linux/compiler-gcc.h.] Signed-off-by: Arnd Bergmann Signed-off-by: Paul Burton Tested-by: Christophe Leroy Tested-by: Stafford Horne Signed-off-by: Masahiro Yamada --- include/linux/compiler-gcc.h | 25 +++++++++++++++++++++++++ include/linux/compiler_types.h | 18 ++++++++++++++++++ 2 files changed, 43 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index f1a7492a5cc8..fd282c7d3e5e 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -347,3 +347,28 @@ #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif + +/* + * Turn individual warnings and errors on and off locally, depending + * on version. + */ +#define __diag_GCC(version, severity, s) \ + __diag_GCC_ ## version(__diag_GCC_ ## severity s) + +/* Severity used in pragma directives */ +#define __diag_GCC_ignore ignored +#define __diag_GCC_warn warning +#define __diag_GCC_error error + +/* Compilers before gcc-4.6 do not understand "#pragma GCC diagnostic push" */ +#if GCC_VERSION >= 40600 +#define __diag_str1(s) #s +#define __diag_str(s) __diag_str1(s) +#define __diag(s) _Pragma(__diag_str(GCC diagnostic s)) +#endif + +#if GCC_VERSION >= 80000 +#define __diag_GCC_8(s) __diag(s) +#else +#define __diag_GCC_8(s) +#endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 6b79a9bba9a7..a8ba6b04152c 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -271,4 +271,22 @@ struct ftrace_likely_data { # define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) #endif +#ifndef __diag +#define __diag(string) +#endif + +#ifndef __diag_GCC +#define __diag_GCC(version, severity, string) +#endif + +#define __diag_push() __diag(push) +#define __diag_pop() __diag(pop) + +#define __diag_ignore(compiler, version, option, comment) \ + __diag_ ## compiler(version, ignore, option) +#define __diag_warn(compiler, version, option, comment) \ + __diag_ ## compiler(version, warn, option) +#define __diag_error(compiler, version, option, comment) \ + __diag_ ## compiler(version, error, option) + #endif /* __LINUX_COMPILER_TYPES_H */ -- cgit v1.2.3 From bee20031772af3debe8cbaa234528f24c7892e8f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 19 Jun 2018 13:14:57 -0700 Subject: disable -Wattribute-alias warning for SYSCALL_DEFINEx() gcc-8 warns for every single definition of a system call entry point, e.g.: include/linux/compat.h:56:18: error: 'compat_sys_rt_sigprocmask' alias between functions of incompatible types 'long int(int, compat_sigset_t *, compat_sigset_t *, compat_size_t)' {aka 'long int(int, struct *, struct *, unsigned int)'} and 'long int(long int, long int, long int, long int)' [-Werror=attribute-alias] asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))\ ^~~~~~~~~~ include/linux/compat.h:45:2: note: in expansion of macro 'COMPAT_SYSCALL_DEFINEx' COMPAT_SYSCALL_DEFINEx(4, _##name, __VA_ARGS__) ^~~~~~~~~~~~~~~~~~~~~~ kernel/signal.c:2601:1: note: in expansion of macro 'COMPAT_SYSCALL_DEFINE4' COMPAT_SYSCALL_DEFINE4(rt_sigprocmask, int, how, compat_sigset_t __user *, nset, ^~~~~~~~~~~~~~~~~~~~~~ include/linux/compat.h:60:18: note: aliased declaration here asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))\ ^~~~~~~~~~ The new warning seems reasonable in principle, but it doesn't help us here, since we rely on the type mismatch to sanitize the system call arguments. After I reported this as GCC PR82435, a new -Wno-attribute-alias option was added that could be used to turn the warning off globally on the command line, but I'd prefer to do it a little more fine-grained. Interestingly, turning a warning off and on again inside of a single macro doesn't always work, in this case I had to add an extra statement inbetween and decided to copy the __SC_TEST one from the native syscall to the compat syscall macro. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83256 for more details about this. [paul.burton@mips.com: - Rebase atop current master. - Split GCC & version arguments to __diag_ignore() in order to match changes to the preceding patch. - Add the comment argument to match the preceding patch.] Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82435 Signed-off-by: Arnd Bergmann Signed-off-by: Paul Burton Tested-by: Christophe Leroy Tested-by: Stafford Horne Signed-off-by: Masahiro Yamada --- include/linux/compat.h | 8 +++++++- include/linux/syscalls.h | 4 ++++ 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index b1a5562b3215..c68acc47da57 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -72,6 +72,9 @@ */ #ifndef COMPAT_SYSCALL_DEFINEx #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ + __diag_push(); \ + __diag_ignore(GCC, 8, "-Wattribute-alias", \ + "Type aliasing is used to sanitize syscall arguments");\ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ __attribute__((alias(__stringify(__se_compat_sys##name)))); \ @@ -80,8 +83,11 @@ asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ - return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\ + long ret = __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\ + __MAP(x,__SC_TEST,__VA_ARGS__); \ + return ret; \ } \ + __diag_pop(); \ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* COMPAT_SYSCALL_DEFINEx */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 73810808cdf2..a368a68cb667 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -231,6 +231,9 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) */ #ifndef __SYSCALL_DEFINEx #define __SYSCALL_DEFINEx(x, name, ...) \ + __diag_push(); \ + __diag_ignore(GCC, 8, "-Wattribute-alias", \ + "Type aliasing is used to sanitize syscall arguments");\ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ __attribute__((alias(__stringify(__se_sys##name)))); \ ALLOW_ERROR_INJECTION(sys##name, ERRNO); \ @@ -243,6 +246,7 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ return ret; \ } \ + __diag_pop(); \ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* __SYSCALL_DEFINEx */ -- cgit v1.2.3 From fd55a281adf6c9b9723d369203fdd92e5ea62a09 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 27 Apr 2018 10:06:03 -0700 Subject: srcu: Introduce srcu_read_{un,}lock_notrace() Joel Fernandes is using SRCU to protect from-idle tracepoints, which requires notrace variants of srcu_read_lock() and srcu_read_unlock() in order to avoid problems with tracepoints in lockdep. This commit therefore adds srcu_read_lock_notrace() and srcu_read_unlock_notrace(). [1] http://lkml.kernel.org/r/20180427042656.190746-1-joelaf@google.com Reported-by: Joel Fernandes Intermittently-reported-by: Steven Rostedt Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 91494d7e8e41..3e72a291c401 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -195,6 +195,16 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) return retval; } +/* Used by tracing, cannot be traced and cannot invoke lockdep. */ +static inline notrace int +srcu_read_lock_notrace(struct srcu_struct *sp) __acquires(sp) +{ + int retval; + + retval = __srcu_read_lock(sp); + return retval; +} + /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @sp: srcu_struct in which to unregister the old reader. @@ -209,6 +219,13 @@ static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) __srcu_read_unlock(sp, idx); } +/* Used by tracing, cannot be traced and cannot call lockdep. */ +static inline notrace void +srcu_read_unlock_notrace(struct srcu_struct *sp, int idx) __releases(sp) +{ + __srcu_read_unlock(sp, idx); +} + /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * -- cgit v1.2.3 From 90127d605f403d814f4986436871210bf8ceb335 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 9 May 2018 10:29:18 -0700 Subject: torture: Make online/offline messages appear only for verbose=2 Some bugs reproduce quickly only at high CPU-hotplug rates, so the rcutorture TREE03 scenario now has only 200 milliseconds spacing between CPU-hotplug operations. At this rate, the torture-test pair of console messages per operation becomes a bit voluminous. This commit therefore converts the torture-test set of "verbose" kernel-boot arguments from bool to int, and prints the extra console messages only when verbose=2. The default is still verbose=1. Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/torture.h b/include/linux/torture.h index 66272862070b..a55e80817dae 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -79,7 +79,7 @@ void stutter_wait(const char *title); int torture_stutter_init(int s); /* Initialization and cleanup. */ -bool torture_init_begin(char *ttype, bool v); +bool torture_init_begin(char *ttype, int v); void torture_init_end(void); bool torture_cleanup_begin(void); void torture_cleanup_end(void); -- cgit v1.2.3 From d4546c2509b1e9cd082e3682dcec98472e37ee5a Mon Sep 17 00:00:00 2001 From: David Miller Date: Sun, 24 Jun 2018 14:13:49 +0900 Subject: net: Convert GRO SKB handling to list_head. Manage pending per-NAPI GRO packets via list_head. Return an SKB pointer from the GRO receive handlers. When GRO receive handlers return non-NULL, it means that this SKB needs to be completed at this time and removed from the NAPI queue. Several operations are greatly simplified by this transformation, especially timing out the oldest SKB in the list when gro_count exceeds MAX_GRO_SKBS, and napi_gro_flush() which walks the queue in reverse order. Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 3 +-- include/linux/netdevice.h | 32 ++++++++++++++++---------------- include/linux/skbuff.h | 3 ++- include/linux/udp.h | 4 ++-- 4 files changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 79563840c295..572e11bb8696 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -59,8 +59,7 @@ struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv, unsigned int rxqs); #define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1) -struct sk_buff **eth_gro_receive(struct sk_buff **head, - struct sk_buff *skb); +struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb); int eth_gro_complete(struct sk_buff *skb, int nhoff); /* Reserved Ethernet Addresses per IEEE 802.1Q */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ec9850c7936..f176d9873910 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -322,7 +322,7 @@ struct napi_struct { int poll_owner; #endif struct net_device *dev; - struct sk_buff *gro_list; + struct list_head gro_list; struct sk_buff *skb; struct hrtimer timer; struct list_head dev_list; @@ -2255,10 +2255,10 @@ static inline int gro_recursion_inc_test(struct sk_buff *skb) return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; } -typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *); -static inline struct sk_buff **call_gro_receive(gro_receive_t cb, - struct sk_buff **head, - struct sk_buff *skb) +typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); +static inline struct sk_buff *call_gro_receive(gro_receive_t cb, + struct list_head *head, + struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; @@ -2268,12 +2268,12 @@ static inline struct sk_buff **call_gro_receive(gro_receive_t cb, return cb(head, skb); } -typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **, - struct sk_buff *); -static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb, - struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, + struct sk_buff *); +static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, + struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; @@ -2299,8 +2299,8 @@ struct packet_type { struct offload_callbacks { struct sk_buff *(*gso_segment)(struct sk_buff *skb, netdev_features_t features); - struct sk_buff **(*gro_receive)(struct sk_buff **head, - struct sk_buff *skb); + struct sk_buff *(*gro_receive)(struct list_head *head, + struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb, int nhoff); }; @@ -2568,7 +2568,7 @@ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); -int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb); +int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { @@ -2784,13 +2784,13 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, } #ifdef CONFIG_XFRM_OFFLOAD -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { if (PTR_ERR(pp) != -EINPROGRESS) NAPI_GRO_CB(skb)->flush |= flush; } #else -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c86885954994..7ccc601b55d9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -677,7 +677,8 @@ struct sk_buff { int ip_defrag_offset; }; }; - struct rb_node rbnode; /* used in netem & tcp stack */ + struct rb_node rbnode; /* used in netem & tcp stack */ + struct list_head list; }; struct sock *sk; diff --git a/include/linux/udp.h b/include/linux/udp.h index ca840345571b..320d49d85484 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -74,8 +74,8 @@ struct udp_sock { void (*encap_destroy)(struct sock *sk); /* GRO functions for UDP socket */ - struct sk_buff ** (*gro_receive)(struct sock *sk, - struct sk_buff **head, + struct sk_buff * (*gro_receive)(struct sock *sk, + struct list_head *head, struct sk_buff *skb); int (*gro_complete)(struct sock *sk, struct sk_buff *skb, -- cgit v1.2.3 From 07d78363dcffd9cb1bf6f06a6cac0e0847f3c1de Mon Sep 17 00:00:00 2001 From: David Miller Date: Sun, 24 Jun 2018 14:14:02 +0900 Subject: net: Convert NAPI gro list into a small hash table. Improve the performance of GRO receive by splitting flows into multiple hash chains. Suggested-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f176d9873910..c6b377a15869 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -305,6 +305,7 @@ int __init netdev_boot_setup(char *str); /* * Structure for NAPI scheduling similar to tasklet but with weighting */ +#define GRO_HASH_BUCKETS 8 struct napi_struct { /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means @@ -322,7 +323,7 @@ struct napi_struct { int poll_owner; #endif struct net_device *dev; - struct list_head gro_list; + struct list_head gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; struct hrtimer timer; struct list_head dev_list; -- cgit v1.2.3 From fdb5c4531c1e0e50e609df83f736b6f3a02896e2 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Tue, 19 Jun 2018 00:04:24 +0100 Subject: bpf: fix attach type BPF_LIRC_MODE2 dependency wrt CONFIG_CGROUP_BPF If the kernel is compiled with CONFIG_CGROUP_BPF not enabled, it is not possible to attach, detach or query IR BPF programs to /dev/lircN devices, making them impossible to use. For embedded devices, it should be possible to use IR decoding without cgroups or CONFIG_CGROUP_BPF enabled. This change requires some refactoring, since bpf_prog_{attach,detach,query} functions are now always compiled, but their code paths for cgroups need moving out. Rather than a #ifdef CONFIG_CGROUP_BPF in kernel/bpf/syscall.c, moving them to kernel/bpf/cgroup.c and kernel/bpf/sockmap.c does not require #ifdefs since that is already conditionally compiled. Fixes: f4364dcfc86d ("media: rc: introduce BPF_PROG_LIRC_MODE2") Signed-off-by: Sean Young Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 26 ++++++++++++++++++++++++++ include/linux/bpf.h | 8 ++++++++ include/linux/bpf_lirc.h | 5 +++-- 3 files changed, 37 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 975fb4cf1bb7..79795c5fa7c3 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -188,12 +188,38 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, \ __ret; \ }) +int cgroup_bpf_prog_attach(const union bpf_attr *attr, + enum bpf_prog_type ptype, struct bpf_prog *prog); +int cgroup_bpf_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype); +int cgroup_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); #else +struct bpf_prog; struct cgroup_bpf {}; static inline void cgroup_bpf_put(struct cgroup *cgrp) {} static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } +static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr, + enum bpf_prog_type ptype, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) +{ + return -EINVAL; +} + +static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} + #define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7df32a3200f7..8827e797ff97 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -696,6 +696,8 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key); int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); +int sockmap_get_from_fd(const union bpf_attr *attr, int type, + struct bpf_prog *prog); #else static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) { @@ -714,6 +716,12 @@ static inline int sock_map_prog(struct bpf_map *map, { return -EOPNOTSUPP; } + +static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type, + struct bpf_prog *prog) +{ + return -EINVAL; +} #endif #if defined(CONFIG_XDP_SOCKETS) diff --git a/include/linux/bpf_lirc.h b/include/linux/bpf_lirc.h index 5f8a4283092d..9d9ff755ec29 100644 --- a/include/linux/bpf_lirc.h +++ b/include/linux/bpf_lirc.h @@ -5,11 +5,12 @@ #include #ifdef CONFIG_BPF_LIRC_MODE2 -int lirc_prog_attach(const union bpf_attr *attr); +int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int lirc_prog_detach(const union bpf_attr *attr); int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); #else -static inline int lirc_prog_attach(const union bpf_attr *attr) +static inline int lirc_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) { return -EINVAL; } -- cgit v1.2.3 From a8f62d0c6fe533e07cd1acce7588278f9d6e7720 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 25 Jun 2018 20:37:08 +0800 Subject: ptp: support DPAA FMan 1588 timer in ptp_qoriq This patch is to support DPAA (Data Path Acceleration Architecture) 1588 timer by adding "fsl,fman-ptp-timer" compatible, sharing interrupt with FMan, adding FSL_DPAA_ETH dependency, and fixing up register offset. Signed-off-by: Yangbo Lu Acked-by: Richard Cochran Acked-by: Madalin Bucur Signed-off-by: David S. Miller --- include/linux/fsl/ptp_qoriq.h | 38 +++++++++++++++++++++++++++++++------- 1 file changed, 31 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index b462d9ea8007..dc3dac40f069 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -11,9 +11,8 @@ /* * qoriq ptp registers - * Generated by regen.tcl on Thu May 13 01:38:57 PM CEST 2010 */ -struct qoriq_ptp_registers { +struct ctrl_regs { u32 tmr_ctrl; /* Timer control register */ u32 tmr_tevent; /* Timestamp event register */ u32 tmr_temask; /* Timer event mask register */ @@ -28,22 +27,47 @@ struct qoriq_ptp_registers { u8 res1[4]; u32 tmroff_h; /* Timer offset high */ u32 tmroff_l; /* Timer offset low */ - u8 res2[8]; +}; + +struct alarm_regs { u32 tmr_alarm1_h; /* Timer alarm 1 high register */ u32 tmr_alarm1_l; /* Timer alarm 1 high register */ u32 tmr_alarm2_h; /* Timer alarm 2 high register */ u32 tmr_alarm2_l; /* Timer alarm 2 high register */ - u8 res3[48]; +}; + +struct fiper_regs { u32 tmr_fiper1; /* Timer fixed period interval */ u32 tmr_fiper2; /* Timer fixed period interval */ u32 tmr_fiper3; /* Timer fixed period interval */ - u8 res4[20]; +}; + +struct etts_regs { u32 tmr_etts1_h; /* Timestamp of general purpose external trigger */ u32 tmr_etts1_l; /* Timestamp of general purpose external trigger */ u32 tmr_etts2_h; /* Timestamp of general purpose external trigger */ u32 tmr_etts2_l; /* Timestamp of general purpose external trigger */ }; +struct qoriq_ptp_registers { + struct ctrl_regs __iomem *ctrl_regs; + struct alarm_regs __iomem *alarm_regs; + struct fiper_regs __iomem *fiper_regs; + struct etts_regs __iomem *etts_regs; +}; + +/* Offset definitions for the four register groups */ +#define CTRL_REGS_OFFSET 0x0 +#define ALARM_REGS_OFFSET 0x40 +#define FIPER_REGS_OFFSET 0x80 +#define ETTS_REGS_OFFSET 0xa0 + +#define FMAN_CTRL_REGS_OFFSET 0x80 +#define FMAN_ALARM_REGS_OFFSET 0xb8 +#define FMAN_FIPER_REGS_OFFSET 0xd0 +#define FMAN_ETTS_REGS_OFFSET 0xe0 + + /* Bit definitions for the TMR_CTRL register */ #define ALM1P (1<<31) /* Alarm1 output polarity */ #define ALM2P (1<<30) /* Alarm2 output polarity */ @@ -105,10 +129,10 @@ struct qoriq_ptp_registers { #define DRIVER "ptp_qoriq" #define DEFAULT_CKSEL 1 #define N_EXT_TS 2 -#define REG_SIZE sizeof(struct qoriq_ptp_registers) struct qoriq_ptp { - struct qoriq_ptp_registers __iomem *regs; + void __iomem *base; + struct qoriq_ptp_registers regs; spinlock_t lock; /* protects regs */ struct ptp_clock *clock; struct ptp_clock_info caps; -- cgit v1.2.3 From 15bfd21fbc5d35834b9ea383dc458a1f0c9e3434 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 26 Jun 2018 09:14:58 -0600 Subject: block: Fix transfer when chunk sectors exceeds max A device may have boundary restrictions where the number of sectors between boundaries exceeds its max transfer size. In this case, we need to cap the max size to the smaller of the two limits. Reported-by: Jitendra Bhivare Tested-by: Jitendra Bhivare Cc: Reviewed-by: Martin K. Petersen Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9154570edf29..79226ca8f80f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1119,8 +1119,8 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q, if (!q->limits.chunk_sectors) return q->limits.max_sectors; - return q->limits.chunk_sectors - - (offset & (q->limits.chunk_sectors - 1)); + return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors - + (offset & (q->limits.chunk_sectors - 1)))); } static inline unsigned int blk_rq_get_max_sectors(struct request *rq, -- cgit v1.2.3 From 5560f70cad996e7d90d1c141bcbca0df214eefc9 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 22 Jun 2018 16:08:58 +0800 Subject: hwspinlock: Add one new API to support getting a specific hwlock by the name The hardware spinlock binding already supplied the 'hwlock-names' property to match and get a specific hwlock, but did not supply one API for users to get a specific hwlock by the hwlock name. So this patch introduces one API to support this requirement. Signed-off-by: Baolin Wang Signed-off-by: Bjorn Andersson --- include/linux/hwspinlock.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h index 57537e67b468..2b6f389a3133 100644 --- a/include/linux/hwspinlock.h +++ b/include/linux/hwspinlock.h @@ -66,6 +66,7 @@ int __hwspin_lock_timeout(struct hwspinlock *, unsigned int, int, unsigned long *); int __hwspin_trylock(struct hwspinlock *, int, unsigned long *); void __hwspin_unlock(struct hwspinlock *, int, unsigned long *); +int of_hwspin_lock_get_id_byname(struct device_node *np, const char *name); #else /* !CONFIG_HWSPINLOCK */ @@ -125,6 +126,12 @@ static inline int hwspin_lock_get_id(struct hwspinlock *hwlock) return 0; } +static inline +int of_hwspin_lock_get_id_byname(struct device_node *np, const char *name) +{ + return 0; +} + #endif /* !CONFIG_HWSPINLOCK */ /** -- cgit v1.2.3 From 4f1acd758b08d93306d13010c74d38dd8d9f5768 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 22 Jun 2018 16:08:59 +0800 Subject: hwspinlock: Add devm_xxx() APIs to request/free hwlock This patch introduces some devm_xxx() APIs to help to request or free the hwlocks, which will help to simplify the cleanup code for drivers requesting one hwlock, ensuring that the hwlock is automatically freed whenever the device is unbound. Signed-off-by: Baolin Wang Signed-off-by: Bjorn Andersson --- include/linux/hwspinlock.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h index 2b6f389a3133..dfd05938a3cb 100644 --- a/include/linux/hwspinlock.h +++ b/include/linux/hwspinlock.h @@ -67,6 +67,10 @@ int __hwspin_lock_timeout(struct hwspinlock *, unsigned int, int, int __hwspin_trylock(struct hwspinlock *, int, unsigned long *); void __hwspin_unlock(struct hwspinlock *, int, unsigned long *); int of_hwspin_lock_get_id_byname(struct device_node *np, const char *name); +int devm_hwspin_lock_free(struct device *dev, struct hwspinlock *hwlock); +struct hwspinlock *devm_hwspin_lock_request(struct device *dev); +struct hwspinlock *devm_hwspin_lock_request_specific(struct device *dev, + unsigned int id); #else /* !CONFIG_HWSPINLOCK */ @@ -132,6 +136,24 @@ int of_hwspin_lock_get_id_byname(struct device_node *np, const char *name) return 0; } +static inline +int devm_hwspin_lock_free(struct device *dev, struct hwspinlock *hwlock) +{ + return 0; +} + +static inline struct hwspinlock *devm_hwspin_lock_request(struct device *dev) +{ + return ERR_PTR(-ENODEV); +} + +static inline +struct hwspinlock *devm_hwspin_lock_request_specific(struct device *dev, + unsigned int id) +{ + return ERR_PTR(-ENODEV); +} + #endif /* !CONFIG_HWSPINLOCK */ /** -- cgit v1.2.3 From b03799b0cb35dbc39e89602b1203863e2a6e06bf Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 25 Jun 2018 16:49:06 -0500 Subject: PCI: shpchp: Separate existence of SHPC and permission to use it The shpchp driver registers for all PCI bridge devices. Its probe method should fail if either (1) the bridge doesn't have an SHPC or (2) the OS isn't allowed to use it (the platform firmware may be operating the SHPC itself). Separate these two tests into: - A new shpc_capable() that looks for the SHPC hardware and is applicable on all systems (ACPI and non-ACPI), and - A simplified acpi_get_hp_hw_control_from_firmware() that we call only when we already know an SHPC exists and there may be ACPI methods to either request permission to use it (_OSC) or transfer control to the OS (OSHP). acpi_get_hp_hw_control_from_firmware() is implemented when CONFIG_ACPI=y, but does nothing if the current platform doesn't support ACPI. Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..f776a1cce120 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -388,6 +388,7 @@ struct pci_dev { unsigned int is_virtfn:1; unsigned int reset_fn:1; unsigned int is_hotplug_bridge:1; + unsigned int shpc_managed:1; /* SHPC owned by shpchp */ unsigned int is_thunderbolt:1; /* Thunderbolt controller */ unsigned int __aer_firmware_first_valid:1; unsigned int __aer_firmware_first:1; -- cgit v1.2.3 From c102780acdbc22e5f664cfaf760eaccffbd6c385 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 22 Jun 2018 16:09:00 +0800 Subject: hwspinlock: Add devm_xxx() APIs to register/unregister one hwlock controller This patch introduces devm_hwspin_lock_register() and devm_hwspin_lock_unregister() interfaces to help to register or unregister one hardware spinlock controller, that will help to simplify the cleanup code for hwspinlock drivers. Signed-off-by: Baolin Wang Signed-off-by: Bjorn Andersson --- include/linux/hwspinlock.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h index dfd05938a3cb..94064cce6962 100644 --- a/include/linux/hwspinlock.h +++ b/include/linux/hwspinlock.h @@ -71,6 +71,12 @@ int devm_hwspin_lock_free(struct device *dev, struct hwspinlock *hwlock); struct hwspinlock *devm_hwspin_lock_request(struct device *dev); struct hwspinlock *devm_hwspin_lock_request_specific(struct device *dev, unsigned int id); +int devm_hwspin_lock_unregister(struct device *dev, + struct hwspinlock_device *bank); +int devm_hwspin_lock_register(struct device *dev, + struct hwspinlock_device *bank, + const struct hwspinlock_ops *ops, + int base_id, int num_locks); #else /* !CONFIG_HWSPINLOCK */ -- cgit v1.2.3 From 2ceda54c44530b8e46363b0b12201855da5fd631 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 22 Jun 2018 16:09:01 +0800 Subject: hwspinlock: Remove redundant config The hardware core can not be built as a module, so remove the redundant CONFIG_HWSPINLOCK_MODULE config. Signed-off-by: Baolin Wang Signed-off-by: Bjorn Andersson --- include/linux/hwspinlock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h index 94064cce6962..0afe693be5f4 100644 --- a/include/linux/hwspinlock.h +++ b/include/linux/hwspinlock.h @@ -52,7 +52,7 @@ struct hwspinlock_pdata { int base_id; }; -#if defined(CONFIG_HWSPINLOCK) || defined(CONFIG_HWSPINLOCK_MODULE) +#ifdef CONFIG_HWSPINLOCK int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev, const struct hwspinlock_ops *ops, int base_id, int num_locks); -- cgit v1.2.3 From 618fcff3742b4c62fea24bea1f01a2f002ed4b37 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 26 Jun 2018 07:11:55 -0500 Subject: remoteproc: Rename subdev functions to start/stop "start" and "stop" are more suitable names for how these two operations are used, and they fit better with the upcoming introduction of two additional operations in the struct. Tested-by: Fabien Dessenne Signed-off-by: Bjorn Andersson [elder@linaro.org: minor comment edits] Signed-off-by Alex Elder Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index dfdaede9139e..bf55bf2a5ee1 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -477,15 +477,15 @@ struct rproc { /** * struct rproc_subdev - subdevice tied to a remoteproc * @node: list node related to the rproc subdevs list - * @probe: probe function, called as the rproc is started - * @remove: remove function, called as the rproc is being stopped, the @crashed - * parameter indicates if this originates from the a recovery + * @start: start function, called after the rproc has been started + * @stop: stop function, called before the rproc is stopped; the @crashed + * parameter indicates if this originates from a recovery */ struct rproc_subdev { struct list_head node; - int (*probe)(struct rproc_subdev *subdev); - void (*remove)(struct rproc_subdev *subdev, bool crashed); + int (*start)(struct rproc_subdev *subdev); + void (*stop)(struct rproc_subdev *subdev, bool crashed); }; /* we currently support only two vrings per rvdev */ @@ -568,8 +568,8 @@ static inline struct rproc *vdev_to_rproc(struct virtio_device *vdev) void rproc_add_subdev(struct rproc *rproc, struct rproc_subdev *subdev, - int (*probe)(struct rproc_subdev *subdev), - void (*remove)(struct rproc_subdev *subdev, bool crashed)); + int (*start)(struct rproc_subdev *subdev), + void (*stop)(struct rproc_subdev *subdev, bool crashed)); void rproc_remove_subdev(struct rproc *rproc, struct rproc_subdev *subdev); -- cgit v1.2.3 From 4902676f04acc20fe12e49f5f4916f2659c2a7bc Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 26 Jun 2018 07:11:57 -0500 Subject: remoteproc: Make client initialize ops in rproc_subdev In preparation of adding the additional prepare and unprepare operations make the client responsible for filling out the function pointers of the rproc_subdev. This makes the arguments to rproc_add_subdev() more manageable, in particular when some of the functions are left out. Tested-by: Fabien Dessenne Signed-off-by: Bjorn Andersson [elder@linaro.org: added comment about assigning function pointers] Signed-off-by Alex Elder Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index bf55bf2a5ee1..8f1426330cca 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -566,10 +566,7 @@ static inline struct rproc *vdev_to_rproc(struct virtio_device *vdev) return rvdev->rproc; } -void rproc_add_subdev(struct rproc *rproc, - struct rproc_subdev *subdev, - int (*start)(struct rproc_subdev *subdev), - void (*stop)(struct rproc_subdev *subdev, bool crashed)); +void rproc_add_subdev(struct rproc *rproc, struct rproc_subdev *subdev); void rproc_remove_subdev(struct rproc *rproc, struct rproc_subdev *subdev); -- cgit v1.2.3 From c455daa4af3c3ee6e841fc9ed42024d6b8d50d66 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 26 Jun 2018 07:11:59 -0500 Subject: remoteproc: Introduce prepare and unprepare for subdevices On rare occasions a subdevice might need to prepare some hardware resources before a remote processor is booted, and clean up some state after it has been shut down. One such example is the IP Accelerator found in various Qualcomm platforms, which is accessed directly from both the modem remoteproc and the application subsystem and requires an intricate lockstep process when bringing the modem up and down. Tested-by: Fabien Dessenne Signed-off-by: Bjorn Andersson [elder@linaro.org: minor description and comment edits] Signed-off-by Alex Elder Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 8f1426330cca..e3c5d856b6da 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -477,15 +477,19 @@ struct rproc { /** * struct rproc_subdev - subdevice tied to a remoteproc * @node: list node related to the rproc subdevs list + * @prepare: prepare function, called before the rproc is started * @start: start function, called after the rproc has been started * @stop: stop function, called before the rproc is stopped; the @crashed * parameter indicates if this originates from a recovery + * @unprepare: unprepare function, called after the rproc has been stopped */ struct rproc_subdev { struct list_head node; + int (*prepare)(struct rproc_subdev *subdev); int (*start)(struct rproc_subdev *subdev); void (*stop)(struct rproc_subdev *subdev, bool crashed); + void (*unprepare)(struct rproc_subdev *subdev); }; /* we currently support only two vrings per rvdev */ -- cgit v1.2.3 From 0efc8562491b7d36f6bbc4fbc8f3348cb6641e9c Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 31 May 2018 11:16:18 +0300 Subject: net/mlx5: E-Switch, Avoid setup attempt if not being e-switch manager In smartnic env, the host (PF) driver might not be an e-switch manager, hence the FW will err on driver attempts to deal with setting/unsetting the eswitch and as a result the overall setup of sriov will fail. Fix that by avoiding the operation if e-switch management is not allowed for this driver instance. While here, move to use the correct name for the esw manager capability name. Fixes: 81848731ff40 ('net/mlx5: E-Switch, Add SR-IOV (FDB) support') Signed-off-by: Or Gerlitz Reported-by: Guy Kushnir Reviewed-by: Eli Cohen Tested-by: Eli Cohen Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 2 ++ include/linux/mlx5/mlx5_ifc.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index d3c9db492b30..fab5121ffb8f 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -8,6 +8,8 @@ #include +#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager) + enum { SRIOV_NONE, SRIOV_LEGACY, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 27134c4fcb76..ac281f5ec9b8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -922,7 +922,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vnic_env_queue_counters[0x1]; u8 ets[0x1]; u8 nic_flow_table[0x1]; - u8 eswitch_flow_table[0x1]; + u8 eswitch_manager[0x1]; u8 device_memory[0x1]; u8 mcam_reg[0x1]; u8 pcam_reg[0x1]; -- cgit v1.2.3 From 77bc8c28ddac90287bc42c129002eb703288d550 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 18 Jun 2018 17:32:30 +0200 Subject: ARM: mvebu: convert secondary CPU clock sync to hotplug state The current call site in boot_secondary is causing sleep in invalid context warnings, as this part of the code is running with interrrupts disabled and some of the calls into the clock framework might sleep on a mutex. Convert the secondary CPU clock sync to a hotplug state, which allows to call it from a sleepable context. Signed-off-by: Lucas Stach Signed-off-by: Gregory CLEMENT --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 8796ba387152..fa54e5fbea38 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -143,6 +143,7 @@ enum cpuhp_state { CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, CPUHP_AP_IRQ_AFFINITY_ONLINE, + CPUHP_AP_ARM_MVEBU_SYNC_CLOCKS, CPUHP_AP_PERF_ONLINE, CPUHP_AP_PERF_X86_ONLINE, CPUHP_AP_PERF_X86_UNCORE_ONLINE, -- cgit v1.2.3 From 9b6e543450dc03635899ba56b1c39cc593694560 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 23 Jun 2018 17:54:47 +0300 Subject: fsnotify: use typedef fsnotify_connp_t for brevity The object marks manipulation functions fsnotify_destroy_marks() fsnotify_find_mark() and their helpers take an argument of type struct fsnotify_mark_connector __rcu ** to dereference the connector pointer. use a typedef to describe this type for brevity. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b38964a7a521..e7cd7fc6e3cf 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -268,6 +268,8 @@ struct fsnotify_mark_connector { struct hlist_head list; }; +typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; + /* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events @@ -394,9 +396,8 @@ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* Find mark belonging to given group in the list of marks */ -extern struct fsnotify_mark *fsnotify_find_mark( - struct fsnotify_mark_connector __rcu **connp, - struct fsnotify_group *group); +extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, + struct fsnotify_group *group); /* attach the mark to the inode or vfsmount */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct inode *inode, struct vfsmount *mnt, int allow_dups); -- cgit v1.2.3 From b812a9f5896379b6cff2ac168ddb5b89037d8e78 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 23 Jun 2018 17:54:48 +0300 Subject: fsnotify: pass connp and object type to fsnotify_add_mark() Instead of passing inode and vfsmount arguments to fsnotify_add_mark() and its _locked variant, pass an abstract object pointer and the object type. The helpers fsnotify_obj_{inode,mount} are added to get the concrete object pointer from abstract object pointer. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index e7cd7fc6e3cf..8efb8663453d 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -210,6 +210,11 @@ enum fsnotify_obj_type { #define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) #define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) +static inline bool fsnotify_valid_obj_type(unsigned int type) +{ + return (type < FSNOTIFY_OBJ_TYPE_COUNT); +} + struct fsnotify_iter_info { struct fsnotify_mark *marks[FSNOTIFY_OBJ_TYPE_COUNT]; unsigned int report_mask; @@ -398,24 +403,27 @@ extern void fsnotify_init_mark(struct fsnotify_mark *mark, /* Find mark belonging to given group in the list of marks */ extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, struct fsnotify_group *group); -/* attach the mark to the inode or vfsmount */ -extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct inode *inode, - struct vfsmount *mnt, int allow_dups); +/* attach the mark to the object */ +extern int fsnotify_add_mark(struct fsnotify_mark *mark, + fsnotify_connp_t *connp, unsigned int type, + int allow_dups); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, - struct inode *inode, struct vfsmount *mnt, + fsnotify_connp_t *connp, unsigned int type, int allow_dups); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, int allow_dups) { - return fsnotify_add_mark(mark, inode, NULL, allow_dups); + return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, + FSNOTIFY_OBJ_TYPE_INODE, allow_dups); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int allow_dups) { - return fsnotify_add_mark_locked(mark, inode, NULL, allow_dups); + return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, + FSNOTIFY_OBJ_TYPE_INODE, allow_dups); } /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, -- cgit v1.2.3 From 36f10f55ff1d2867bfc48ed898a9cc0dc6b49dd2 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 23 Jun 2018 17:54:49 +0300 Subject: fsnotify: let connector point to an abstract object Make the code to attach/detach a connector to object more generic by letting the fsnotify connector point to an abstract fsnotify_connp_t. Code that needs to dereference an inode or mount object now uses the helpers fsnotify_conn_{inode,mount}. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8efb8663453d..381cfb0e67fa 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -255,6 +255,13 @@ FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) #define fsnotify_foreach_obj_type(type) \ for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++) +/* + * fsnotify_connp_t is what we embed in objects which connector can be attached + * to. fsnotify_connp_t * is how we refer from connector back to object. + */ +struct fsnotify_mark_connector; +typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; + /* * Inode / vfsmount point to this structure which tracks all marks attached to * the inode / vfsmount. The reference to inode / vfsmount is held by this @@ -264,17 +271,15 @@ FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) struct fsnotify_mark_connector { spinlock_t lock; unsigned int type; /* Type of object [lock] */ - union { /* Object pointer [lock] */ - struct inode *inode; - struct vfsmount *mnt; + union { + /* Object pointer [lock] */ + fsnotify_connp_t *obj; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; struct hlist_head list; }; -typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; - /* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events -- cgit v1.2.3 From 3ac70bfcde812b1b97d8a88a832df59941fa293f Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 23 Jun 2018 17:54:50 +0300 Subject: fsnotify: add helper to get mask from connector Use a helper to get the mask from the object (i.e. i_fsnotify_mask) to generalize code of add/remove inode/vfsmount mark. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 381cfb0e67fa..2b9b6f1ff5e0 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -401,6 +401,8 @@ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group /* functions used to manipulate the marks attached to inodes */ +/* Get mask of events for a list of marks */ +extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, -- cgit v1.2.3 From 22eceb8bf3e8f1f9b2f566062d06b25807725d7f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 19 Jun 2018 13:57:26 +0200 Subject: printk: Make CONSOLE_LOGLEVEL_QUIET configurable The goal of passing the "quiet" option to the kernel is for the kernel to be quiet unless something really is wrong. Sofar passing quiet has been (mostly) equivalent to passing loglevel=4 on the kernel commandline. Which means to show any messages with a level of KERN_ERR or higher severity on the console. In practice this often does not result in a quiet boot though, since there are many false-positive or otherwise harmless error messages printed, defeating the purpose of the quiet option. Esp. the ACPICA code is really bad wrt this, but there are plenty of others too. This commit makes CONSOLE_LOGLEVEL_QUIET configurable. This for example will allow distros which want quiet to really mean quiet to set CONSOLE_LOGLEVEL_QUIET so that only messages with a higher severity then KERN_ERR (CRIT, ALERT, EMERG) get printed, avoiding an endless game of whack-a-mole silencing harmless error messages. Link: http://lkml.kernel.org/r/20180619115726.3098-1-hdegoede@redhat.com To: Petr Mladek To: Sergey Senozhatsky Cc: Hans de Goede Cc: Steven Rostedt Cc: linux-kernel@vger.kernel.org Signed-off-by: Hans de Goede Acked-by: Steven Rostedt (VMware) Reviewed-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- include/linux/printk.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 6d7e800affd8..18602bb3eca8 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -50,15 +50,15 @@ static inline const char *printk_skip_headers(const char *buffer) /* We show everything that is MORE important than this.. */ #define CONSOLE_LOGLEVEL_SILENT 0 /* Mum's the word */ #define CONSOLE_LOGLEVEL_MIN 1 /* Minimum loglevel we let people use */ -#define CONSOLE_LOGLEVEL_QUIET 4 /* Shhh ..., when booted with "quiet" */ #define CONSOLE_LOGLEVEL_DEBUG 10 /* issue debug messages */ #define CONSOLE_LOGLEVEL_MOTORMOUTH 15 /* You can't shut this one up */ /* - * Default used to be hard-coded at 7, we're now allowing it to be set from - * kernel config. + * Default used to be hard-coded at 7, quiet used to be hardcoded at 4, + * we're now allowing both to be set from kernel config. */ #define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT +#define CONSOLE_LOGLEVEL_QUIET CONFIG_CONSOLE_LOGLEVEL_QUIET extern int console_printk[]; -- cgit v1.2.3 From e7d4a95da86e0b048702765bbdcdc968aaf312e7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 20 Jun 2018 08:58:28 +0200 Subject: bitfield: fix *_encode_bits() There's a bug in *_encode_bits() in using ~field_multiplier() for the check whether or not the constant value fits into the field, this is wrong and clearly ~field_mask() was intended. This was triggering for me for both constant and non-constant values. Additionally, make this case actually into an compile error. Declaring the extern function that will never exist with just a warning is pointless as then later we'll just get a link error. While at it, also fix the indentation in those lines I'm touching. Finally, as suggested by Andy Shevchenko, add some tests and for that introduce also u8 helpers. The tests don't compile without the fix, showing that it's necessary. Fixes: 00b0c9b82663 ("Add primitives for manipulating bitfields both in host- and fixed-endian.") Reviewed-by: Andy Shevchenko Signed-off-by: Johannes Berg Signed-off-by: Kalle Valo --- include/linux/bitfield.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index cf2588d81148..147a7bb341dd 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -104,7 +104,7 @@ (typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \ }) -extern void __compiletime_warning("value doesn't fit into mask") +extern void __compiletime_error("value doesn't fit into mask") __field_overflow(void); extern void __compiletime_error("bad bitfield mask") __bad_mask(void); @@ -121,8 +121,8 @@ static __always_inline u64 field_mask(u64 field) #define ____MAKE_OP(type,base,to,from) \ static __always_inline __##type type##_encode_bits(base v, base field) \ { \ - if (__builtin_constant_p(v) && (v & ~field_multiplier(field))) \ - __field_overflow(); \ + if (__builtin_constant_p(v) && (v & ~field_mask(field))) \ + __field_overflow(); \ return to((v & field_mask(field)) * field_multiplier(field)); \ } \ static __always_inline __##type type##_replace_bits(__##type old, \ -- cgit v1.2.3 From 37a3862e1238262e9866d5d66e5f5f9069cee3a1 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 20 Jun 2018 08:58:29 +0200 Subject: bitfield: add u8 helpers There's no reason why we shouldn't pack/unpack bits into/from u8 values/registers/etc., so add u8 helpers. Use the ____MAKE_OP() macro directly to avoid having nonsense le8_encode_bits() and similar functions. Reviewed-by: Andy Shevchenko Signed-off-by: Johannes Berg Signed-off-by: Kalle Valo --- include/linux/bitfield.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 147a7bb341dd..65a6981eef7b 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -143,6 +143,7 @@ static __always_inline base type##_get_bits(__##type v, base field) \ ____MAKE_OP(le##size,u##size,cpu_to_le##size,le##size##_to_cpu) \ ____MAKE_OP(be##size,u##size,cpu_to_be##size,be##size##_to_cpu) \ ____MAKE_OP(u##size,u##size,,) +____MAKE_OP(u8,u8,,) __MAKE_OP(16) __MAKE_OP(32) __MAKE_OP(64) -- cgit v1.2.3 From 4d97f7d53da7dc830dbf416a3d2a6778d267ae68 Mon Sep 17 00:00:00 2001 From: Henry Wilson Date: Thu, 31 May 2018 09:43:03 +0000 Subject: inotify: Add flag IN_MASK_CREATE for inotify_add_watch() The flag IN_MASK_CREATE is introduced as a flag for inotiy_add_watch() which prevents inotify from modifying any existing watches when invoked. If the pathname specified in the call has a watched inode associated with it and IN_MASK_CREATE is specified, fail with an errno of EEXIST. Use of IN_MASK_CREATE with IN_MASK_ADD is reserved for future use and will return EINVAL. RATIONALE In the current implementation, there is no way to prevent inotify_add_watch() from modifying existing watch descriptors. Even if the caller keeps a record of all watch descriptors collected, this is only sufficient to detect that an existing watch descriptor may have been modified. The assumption that a particular path will map to the same inode over multiple calls to inotify_add_watch() cannot be made as files can be renamed or deleted. It is also not possible to assume that two distinct paths do no map to the same inode, due to hard-links or a dereferenced symbolic link. Further uses of inotify_add_watch() to revert the change may cause other watch descriptors to be modified or created, merely compunding the problem. There is currently no system call such as inotify_modify_watch() to explicity modify a watch descriptor, which would be able to revert unwanted changes. Thus the caller cannot guarantee to be able to revert any changes to existing watch decriptors. Additionally the caller cannot assume that the events that are associated with a watch descriptor are within the set requested, as any future calls to inotify_add_watch() may unintentionally modify a watch descriptor's mask. Thus it cannot currently be guaranteed that a watch descriptor will only generate events which have been requested. The program must filter events which come through its watch descriptor to within its expected range. Reviewed-by: Amir Goldstein Signed-off-by: Henry Wilson Signed-off-by: Jan Kara --- include/linux/inotify.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 44f9ffe72c87..6a24905f6e1e 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -18,6 +18,6 @@ extern struct ctl_table inotify_table[]; /* for sysctl */ IN_DELETE_SELF | IN_MOVE_SELF | IN_UNMOUNT | \ IN_Q_OVERFLOW | IN_IGNORED | IN_ONLYDIR | \ IN_DONT_FOLLOW | IN_EXCL_UNLINK | IN_MASK_ADD | \ - IN_ISDIR | IN_ONESHOT) + IN_MASK_CREATE | IN_ISDIR | IN_ONESHOT) #endif /* _LINUX_INOTIFY_H */ -- cgit v1.2.3 From 5e85a04c8c0d271d7561a770b85741f186398868 Mon Sep 17 00:00:00 2001 From: Li Jun Date: Wed, 27 Jun 2018 07:45:22 +0800 Subject: usb: typec: add fwnode to tcpc Add fwnode handle to get the fwnode so we can get typec configs it contains. Suggested-by: Heikki Krogerus Reviewed-by: Heikki Krogerus Signed-off-by: Li Jun Reviewed-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tcpm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index b231b9314240..193920a2e05f 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -110,6 +110,7 @@ enum tcpc_mux_mode { /** * struct tcpc_dev - Port configuration and callback functions * @config: Pointer to port configuration + * @fwnode: Pointer to port fwnode * @get_vbus: Called to read current VBUS state * @get_current_limit: * Optional; called by the tcpm core when configured as a snk @@ -138,6 +139,7 @@ enum tcpc_mux_mode { */ struct tcpc_dev { const struct tcpc_config *config; + struct fwnode_handle *fwnode; int (*init)(struct tcpc_dev *dev); int (*get_vbus)(struct tcpc_dev *dev); -- cgit v1.2.3 From 9c90e02434b66f9bcfc5c9a91a808eee5b7aa21b Mon Sep 17 00:00:00 2001 From: Li Jun Date: Wed, 27 Jun 2018 07:45:23 +0800 Subject: usb: typec: add API to get typec basic port power and data config This patch adds 3 APIs to get the typec port power and data type, and preferred power role by its name string. Reviewed-by: Heikki Krogerus Signed-off-by: Li Jun Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 672b39bb0adc..15f8d9a50b31 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -267,4 +267,7 @@ int typec_set_orientation(struct typec_port *port, enum typec_orientation orientation); int typec_set_mode(struct typec_port *port, int mode); +int typec_find_port_power_role(const char *name); +int typec_find_power_role(const char *name); +int typec_find_port_data_role(const char *name); #endif /* __LINUX_USB_TYPEC_H */ -- cgit v1.2.3 From 82f5d7749fa4f3851f705c75b33babf68edb90b8 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Wed, 27 Jun 2018 18:19:46 +0300 Subject: usb: pd: include kernel.h This makes life a bit easier for the drivers that include pd.h. All pd_header_*_le() inline functions defined in pd.h call le16_to_cpu(), and all *_LE() macros in pd.h call cpu_to_le16(). Signed-off-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index 09b570feb297..f2162e0fe531 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -15,6 +15,7 @@ #ifndef __LINUX_USB_PD_H #define __LINUX_USB_PD_H +#include #include #include -- cgit v1.2.3 From aaf3f4e925dc2bdc4715142103660285632a245c Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Wed, 27 Jun 2018 18:19:47 +0300 Subject: usb: typec: function for checking cable plug orientation This adds function typec_get_orientation() that can be used for checking the current cable plug orientation. Signed-off-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 15f8d9a50b31..6c33b53d1162 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -265,6 +265,7 @@ void typec_set_pwr_opmode(struct typec_port *port, enum typec_pwr_opmode mode); int typec_set_orientation(struct typec_port *port, enum typec_orientation orientation); +enum typec_orientation typec_get_orientation(struct typec_port *port); int typec_set_mode(struct typec_port *port, int mode); int typec_find_port_power_role(const char *name); -- cgit v1.2.3 From 2b6a440351436d792b1960822da4b7d6e673f568 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 1 Jun 2018 10:22:52 +0200 Subject: gnss: add GNSS receiver subsystem Add a new subsystem for GNSS (e.g. GPS) receivers. While GNSS receivers are typically accessed using a UART interface they often also support other I/O interfaces such as I2C, SPI and USB, while yet other devices use iomem or even some form of remote-processor messaging (rpmsg). The new GNSS subsystem abstracts the underlying interface and provides a new "gnss" class type, which exposes a character-device interface (e.g. /dev/gnss0) to user space. This allows GNSS receivers to have a representation in the Linux device model, something which is important not least for power management purposes. Note that the character-device interface provides raw access to whatever protocol the receiver is (currently) using, such as NMEA 0183, UBX or SiRF Binary. These protocols are expected to be continued to be handled by user space for the time being, even if some hybrid solutions are also conceivable (e.g. to have kernel drivers issue management commands). This will still allow for better platform integration by allowing GNSS devices and their resources (e.g. regulators and enable-gpios) to be described by firmware and managed by kernel drivers rather than platform-specific scripts and services. While the current interface is kept minimal, it could be extended using IOCTLs, sysfs or uevents as needs and proper abstraction levels are identified and determined (e.g. for device and feature identification). Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/gnss.h | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) create mode 100644 include/linux/gnss.h (limited to 'include/linux') diff --git a/include/linux/gnss.h b/include/linux/gnss.h new file mode 100644 index 000000000000..e26aeac1e0e2 --- /dev/null +++ b/include/linux/gnss.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * GNSS receiver support + * + * Copyright (C) 2018 Johan Hovold + */ + +#ifndef _LINUX_GNSS_H +#define _LINUX_GNSS_H + +#include +#include +#include +#include +#include +#include +#include + +struct gnss_device; + +struct gnss_operations { + int (*open)(struct gnss_device *gdev); + void (*close)(struct gnss_device *gdev); + int (*write_raw)(struct gnss_device *gdev, const unsigned char *buf, + size_t count); +}; + +struct gnss_device { + struct device dev; + struct cdev cdev; + int id; + + unsigned long flags; + + struct rw_semaphore rwsem; + const struct gnss_operations *ops; + unsigned int count; + unsigned int disconnected:1; + + struct mutex read_mutex; + struct kfifo read_fifo; + wait_queue_head_t read_queue; + + struct mutex write_mutex; + char *write_buf; +}; + +struct gnss_device *gnss_allocate_device(struct device *parent); +void gnss_put_device(struct gnss_device *gdev); +int gnss_register_device(struct gnss_device *gdev); +void gnss_deregister_device(struct gnss_device *gdev); + +int gnss_insert_raw(struct gnss_device *gdev, const unsigned char *buf, + size_t count); + +static inline void gnss_set_drvdata(struct gnss_device *gdev, void *data) +{ + dev_set_drvdata(&gdev->dev, data); +} + +static inline void *gnss_get_drvdata(struct gnss_device *gdev) +{ + return dev_get_drvdata(&gdev->dev); +} + +#endif /* _LINUX_GNSS_H */ -- cgit v1.2.3 From 10f146639fee5ffaf7cf0081c1af518f7d0c533c Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 1 Jun 2018 10:22:59 +0200 Subject: gnss: add receiver type support Add a "type" device attribute and a "GNSS_TYPE" uevent variable which can be used to determine the type of a GNSS receiver. The currently identified types reflect the protocol(s) supported by a receiver: "NMEA" NMEA 0183 "SiRF" SiRF Binary "UBX" UBX Note that both SiRF and UBX type receivers typically support a subset of NMEA 0183 with vendor extensions (e.g. to allow switching to the vendor protocol). Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/gnss.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gnss.h b/include/linux/gnss.h index e26aeac1e0e2..43546977098c 100644 --- a/include/linux/gnss.h +++ b/include/linux/gnss.h @@ -18,6 +18,14 @@ struct gnss_device; +enum gnss_type { + GNSS_TYPE_NMEA = 0, + GNSS_TYPE_SIRF, + GNSS_TYPE_UBX, + + GNSS_TYPE_COUNT +}; + struct gnss_operations { int (*open)(struct gnss_device *gdev); void (*close)(struct gnss_device *gdev); @@ -30,6 +38,7 @@ struct gnss_device { struct cdev cdev; int id; + enum gnss_type type; unsigned long flags; struct rw_semaphore rwsem; -- cgit v1.2.3 From 5fd691afdf929061c391d897fa627822c3b2fd5a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Jun 2018 16:53:34 +0200 Subject: atomic/tty: Fix up atomic abuse in ldsem Mark found ldsem_cmpxchg() needed an (atomic_long_t *) cast to keep working after making the atomic_long interface type safe. Needing casts is bad form, which made me look at the code. There are no ld_semaphore::count users outside of these functions so there is no reason why it can not be an atomic_long_t in the first place, obviating the need for this cast. That also ensures the loads use atomic_long_read(), which implies (at least) READ_ONCE() in order to guarantee single-copy-atomic loads. When using atomic_long_try_cmpxchg() the ldsem_cmpxchg() wrapper gets very thin (the only difference is not changing *old on success, which most callers don't seem to care about). So rework the whole thing to use atomic_long_t and its accessors directly. While there, fixup all the horrible comment styles. Cc: Peter Hurley Reported-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_ldisc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 1ef64d4ad887..840894ca3fc0 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -119,13 +119,13 @@ #include #include - +#include /* * the semaphore definition */ struct ld_semaphore { - long count; + atomic_long_t count; raw_spinlock_t wait_lock; unsigned int wait_readers; struct list_head read_wait; -- cgit v1.2.3 From d8ae7242718738ee1bf9bfdd632d2a4b150fdd26 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 26 Jun 2018 23:56:40 -0400 Subject: vt: preserve unicode values corresponding to screen characters The vt code translates UTF-8 strings into glyph index values and stores those glyph values directly in the screen buffer. Because there can only be at most 512 glyphs, it is impossible to represent most unicode characters, in which case a default glyph (often '?') is displayed instead. The original unicode value is then lost. This patch implements the basic screen buffer handling to preserve unicode values alongside corresponding display glyphs. It is not activated by default, meaning that people not relying on that functionality won't get the implied overhead. Signed-off-by: Nicolas Pitre Tested-by: Dave Mielke Acked-by: Adam Borowski Signed-off-by: Greg Kroah-Hartman --- include/linux/console_struct.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index c0ec478ea5bf..2c8d3239899b 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -19,6 +19,7 @@ struct vt_struct; struct uni_pagedir; +struct uni_screen; #define NPAR 16 @@ -140,6 +141,7 @@ struct vc_data { struct vc_data **vc_display_fg; /* [!] Ptr to var holding fg console for this display */ struct uni_pagedir *vc_uni_pagedir; struct uni_pagedir **vc_uni_pagedir_loc; /* [!] Location of uni_pagedir variable for this console */ + struct uni_screen *vc_uni_screen; /* unicode screen content */ bool vc_panic_force_write; /* when oops/panic this VC can accept forced output/blanking */ /* additional information is in vt_kern.h */ }; -- cgit v1.2.3 From d21b0be246bf3bbf569e6e239f56abb529c7154e Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 26 Jun 2018 23:56:41 -0400 Subject: vt: introduce unicode mode for /dev/vcs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that the core vt code knows how to preserve unicode values for each displayed character, it is then possible to let user space access it via /dev/vcs*. Unicode characters are presented as 32 bit values in native endianity via the /dev/vcsu* devices, mimicking the simple /dev/vcs* devices. Unicode with attributes (similarly to /dev/vcsa*) is not supported at the moment. Data is available only as long as the console is in UTF-8 mode. ENODATA is returned otherwise. This was tested with the latest development version (to become version 5.7) of BRLTTY. Amongst other things, this allows ⠋⠕⠗ ⠞⠓⠊⠎ ⠃⠗⠁⠊⠇⠇⠑⠀⠞⠑⠭⠞⠀to appear directly on braille displays regardless of the console font being used. Signed-off-by: Nicolas Pitre Tested-by: Dave Mielke Acked-by: Adam Borowski Signed-off-by: Greg Kroah-Hartman --- include/linux/selection.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/selection.h b/include/linux/selection.h index 5b278ce99d8d..2b34df9f1e26 100644 --- a/include/linux/selection.h +++ b/include/linux/selection.h @@ -42,4 +42,9 @@ extern u16 vcs_scr_readw(struct vc_data *vc, const u16 *org); extern void vcs_scr_writew(struct vc_data *vc, u16 val, u16 *org); extern void vcs_scr_updated(struct vc_data *vc); +extern int vc_uniscr_check(struct vc_data *vc); +extern void vc_uniscr_copy_line(struct vc_data *vc, void *dest, + unsigned int row, unsigned int col, + unsigned int nr); + #endif -- cgit v1.2.3 From 708d0bff9121506db08adb73845a3c70312fadf3 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 26 Jun 2018 23:56:42 -0400 Subject: vt: unicode fallback for scrollback There is currently no provision for scrollback content in the core code, leaving that to backend video drivers where this can be highly optimized. There is currently no common method for those drivers to tell the core what part of the scrollback is actually displayed and what size the scrollback buffer is either. Because of that, the unicode screen buffer has no provision for any scrollback. At least we can provide backtranslated glyph values when the scrollback is active which should be plenty good enough for now. Signed-off-by: Nicolas Pitre Tested-by: Dave Mielke Acked-by: Adam Borowski Signed-off-by: Greg Kroah-Hartman --- include/linux/selection.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/selection.h b/include/linux/selection.h index 2b34df9f1e26..067d2e99c79f 100644 --- a/include/linux/selection.h +++ b/include/linux/selection.h @@ -43,7 +43,7 @@ extern void vcs_scr_writew(struct vc_data *vc, u16 val, u16 *org); extern void vcs_scr_updated(struct vc_data *vc); extern int vc_uniscr_check(struct vc_data *vc); -extern void vc_uniscr_copy_line(struct vc_data *vc, void *dest, +extern void vc_uniscr_copy_line(struct vc_data *vc, void *dest, int viewed, unsigned int row, unsigned int col, unsigned int nr); -- cgit v1.2.3 From 83d83bebf40132e2d55ec58af666713cc76f9764 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 28 Jun 2018 15:20:30 +0200 Subject: console/fbcon: Add support for deferred console takeover Currently fbcon claims fbdevs as soon as they are registered and takes over the console as soon as the first fbdev gets registered. This behavior is undesirable in cases where a smooth graphical bootup is desired, in such cases we typically want the contents of the framebuffer (typically a vendor logo) to stay in place as is. The current solution for this problem (on embedded systems) is to not enable fbcon. This commit adds a new FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER config option, which when enabled defers fbcon taking over the console from the dummy console until the first text is displayed on the console. Together with the "quiet" kernel commandline option, this allows fbcon to still be used together with a smooth graphical bootup, having it take over the console as soon as e.g. an error message is logged. Note the choice to detect the first console output in the dummycon driver, rather then handling this entirely inside the fbcon code, was made after 2 failed attempts to handle this entirely inside the fbcon code. The fbcon code is woven quite tightly into the console code, making this to only feasible option. Reviewed-by: Daniel Vetter Signed-off-by: Hans de Goede Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/console.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index dfd6b0e97855..f59f3dbca65c 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -21,6 +21,7 @@ struct console_font_op; struct console_font; struct module; struct tty_struct; +struct notifier_block; /* * this is what the terminal answers to a ESC-Z or csi0c query. @@ -220,4 +221,8 @@ static inline bool vgacon_text_force(void) { return false; } extern void console_init(void); +/* For deferred console takeover */ +void dummycon_register_output_notifier(struct notifier_block *nb); +void dummycon_unregister_output_notifier(struct notifier_block *nb); + #endif /* _LINUX_CONSOLE_H */ -- cgit v1.2.3 From 4b09791ba059cc5a5ec7d69049f5d05da65b6418 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ondrej=20Mosn=C3=A1=C4=8Dek?= Date: Tue, 26 Jun 2018 13:04:42 +0200 Subject: cred: conditionally declare groups-related functions The groups-related functions declared in include/linux/cred.h are defined in kernel/groups.c, which is compiled only when CONFIG_MULTIUSER=y. Move all these function declarations under #ifdef CONFIG_MULTIUSER to help avoid accidental usage in contexts where CONFIG_MULTIUSER might be disabled. This patch also adds a fallback for groups_search(). Currently this function is only called from kernel/groups.c itself and security/keys/permissions.c, where the call is (by coincidence) optimized away in case CONFIG_MULTIUSER=n. However, the audit subsystem (which does not depend on CONFIG_MULTIUSER) calls this function in -next, so the fallback will be needed to avoid compilation errors or ugly workarounds. See also: https://lkml.org/lkml/2018/6/20/670 https://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git/commit/?h=next&id=af85d1772e31fed34165a1b3decef340cf4080c0 Reported-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Ondrej Mosnacek Signed-off-by: Paul Moore --- include/linux/cred.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cred.h b/include/linux/cred.h index 631286535d0f..7eed6101c791 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -65,6 +65,12 @@ extern void groups_free(struct group_info *); extern int in_group_p(kgid_t); extern int in_egroup_p(kgid_t); +extern int groups_search(const struct group_info *, kgid_t); + +extern int set_current_groups(struct group_info *); +extern void set_groups(struct cred *, struct group_info *); +extern bool may_setgroups(void); +extern void groups_sort(struct group_info *); #else static inline void groups_free(struct group_info *group_info) { @@ -78,12 +84,11 @@ static inline int in_egroup_p(kgid_t grp) { return 1; } +static inline int groups_search(const struct group_info *group_info, kgid_t grp) +{ + return 1; +} #endif -extern int set_current_groups(struct group_info *); -extern void set_groups(struct cred *, struct group_info *); -extern int groups_search(const struct group_info *, kgid_t); -extern bool may_setgroups(void); -extern void groups_sort(struct group_info *); /* * The security context of a task -- cgit v1.2.3 From a11e1d432b51f63ba698d044441284a661f01144 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 28 Jun 2018 09:43:44 -0700 Subject: Revert changes to convert to ->poll_mask() and aio IOCB_CMD_POLL The poll() changes were not well thought out, and completely unexplained. They also caused a huge performance regression, because "->poll()" was no longer a trivial file operation that just called down to the underlying file operations, but instead did at least two indirect calls. Indirect calls are sadly slow now with the Spectre mitigation, but the performance problem could at least be largely mitigated by changing the "->get_poll_head()" operation to just have a per-file-descriptor pointer to the poll head instead. That gets rid of one of the new indirections. But that doesn't fix the new complexity that is completely unwarranted for the regular case. The (undocumented) reason for the poll() changes was some alleged AIO poll race fixing, but we don't make the common case slower and more complex for some uncommon special case, so this all really needs way more explanations and most likely a fundamental redesign. [ This revert is a revert of about 30 different commits, not reverted individually because that would just be unnecessarily messy - Linus ] Cc: Al Viro Cc: Christoph Hellwig Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 -- include/linux/net.h | 1 - include/linux/poll.h | 12 ++++++------ include/linux/skbuff.h | 3 ++- 4 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5c91108846db..d78d146a98da 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1720,8 +1720,6 @@ struct file_operations { int (*iterate) (struct file *, struct dir_context *); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); - struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t); - __poll_t (*poll_mask) (struct file *, __poll_t); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); diff --git a/include/linux/net.h b/include/linux/net.h index 08b6eb964dd6..6554d3ba4396 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -147,7 +147,6 @@ struct proto_ops { int (*getname) (struct socket *sock, struct sockaddr *addr, int peer); - __poll_t (*poll_mask) (struct socket *sock, __poll_t events); __poll_t (*poll) (struct file *file, struct socket *sock, struct poll_table_struct *wait); int (*ioctl) (struct socket *sock, unsigned int cmd, diff --git a/include/linux/poll.h b/include/linux/poll.h index fdf86b4cbc71..7e0fdcf905d2 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -74,18 +74,18 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) pt->_key = ~(__poll_t)0; /* all events enabled */ } -static inline bool file_has_poll_mask(struct file *file) +static inline bool file_can_poll(struct file *file) { - return file->f_op->get_poll_head && file->f_op->poll_mask; + return file->f_op->poll; } -static inline bool file_can_poll(struct file *file) +static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt) { - return file->f_op->poll || file_has_poll_mask(file); + if (unlikely(!file->f_op->poll)) + return DEFAULT_POLLMASK; + return file->f_op->poll(file, pt); } -__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt); - struct poll_table_entry { struct file *filp; __poll_t key; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c86885954994..164cdedf6012 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3252,7 +3252,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, int *peeked, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); -__poll_t datagram_poll_mask(struct socket *sock, __poll_t events); +__poll_t datagram_poll(struct file *file, struct socket *sock, + struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, struct iov_iter *to, int size); static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, -- cgit v1.2.3 From d50d82faa0c964e31f7a946ba8aba7c715ca7ab0 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 27 Jun 2018 23:26:09 -0700 Subject: slub: fix failure when we delete and create a slab cache In kernel 4.17 I removed some code from dm-bufio that did slab cache merging (commit 21bb13276768: "dm bufio: remove code that merges slab caches") - both slab and slub support merging caches with identical attributes, so dm-bufio now just calls kmem_cache_create and relies on implicit merging. This uncovered a bug in the slub subsystem - if we delete a cache and immediatelly create another cache with the same attributes, it fails because of duplicate filename in /sys/kernel/slab/. The slub subsystem offloads freeing the cache to a workqueue - and if we create the new cache before the workqueue runs, it complains because of duplicate filename in sysfs. This patch fixes the bug by moving the call of kobject_del from sysfs_slab_remove_workfn to shutdown_cache. kobject_del must be called while we hold slab_mutex - so that the sysfs entry is deleted before a cache with the same attributes could be created. Running device-mapper-test-suite with: dmtest run --suite thin-provisioning -n /commit_failure_causes_fallback/ triggered: Buffer I/O error on dev dm-0, logical block 1572848, async page read device-mapper: thin: 253:1: metadata operation 'dm_pool_alloc_data_block' failed: error = -5 device-mapper: thin: 253:1: aborting current metadata transaction sysfs: cannot create duplicate filename '/kernel/slab/:a-0000144' CPU: 2 PID: 1037 Comm: kworker/u48:1 Not tainted 4.17.0.snitm+ #25 Hardware name: Supermicro SYS-1029P-WTR/X11DDW-L, BIOS 2.0a 12/06/2017 Workqueue: dm-thin do_worker [dm_thin_pool] Call Trace: dump_stack+0x5a/0x73 sysfs_warn_dup+0x58/0x70 sysfs_create_dir_ns+0x77/0x80 kobject_add_internal+0xba/0x2e0 kobject_init_and_add+0x70/0xb0 sysfs_slab_add+0xb1/0x250 __kmem_cache_create+0x116/0x150 create_cache+0xd9/0x1f0 kmem_cache_create_usercopy+0x1c1/0x250 kmem_cache_create+0x18/0x20 dm_bufio_client_create+0x1ae/0x410 [dm_bufio] dm_block_manager_create+0x5e/0x90 [dm_persistent_data] __create_persistent_data_objects+0x38/0x940 [dm_thin_pool] dm_pool_abort_metadata+0x64/0x90 [dm_thin_pool] metadata_operation_failed+0x59/0x100 [dm_thin_pool] alloc_data_block.isra.53+0x86/0x180 [dm_thin_pool] process_cell+0x2a3/0x550 [dm_thin_pool] do_worker+0x28d/0x8f0 [dm_thin_pool] process_one_work+0x171/0x370 worker_thread+0x49/0x3f0 kthread+0xf8/0x130 ret_from_fork+0x35/0x40 kobject_add_internal failed for :a-0000144 with -EEXIST, don't try to register things with the same name in the same directory. kmem_cache_create(dm_bufio_buffer-16) failed with error -17 Link: http://lkml.kernel.org/r/alpine.LRH.2.02.1806151817130.6333@file01.intranet.prod.int.rdu2.redhat.com Signed-off-by: Mikulas Patocka Reported-by: Mike Snitzer Tested-by: Mike Snitzer Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 09fa2c6f0e68..3a1a1dbc6f49 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -155,8 +155,12 @@ struct kmem_cache { #ifdef CONFIG_SYSFS #define SLAB_SUPPORTS_SYSFS +void sysfs_slab_unlink(struct kmem_cache *); void sysfs_slab_release(struct kmem_cache *); #else +static inline void sysfs_slab_unlink(struct kmem_cache *s) +{ +} static inline void sysfs_slab_release(struct kmem_cache *s) { } -- cgit v1.2.3 From f77bc3a82ce58fe7977a11f28e0b6cac8a9e087c Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Wed, 27 Jun 2018 23:26:17 -0700 Subject: include/linux/dax.h: dax_iomap_fault() returns vm_fault_t Commit 1c8f422059ae ("mm: change return type to vm_fault_t") missed a conversion. It's not a big problem at present because mainline is still using typedef int vm_fault_t; Fixes: 1c8f422059ae ("mm: change return type to vm_fault_t") Link: http://lkml.kernel.org/r/20180620172046.GA27894@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Andrew Morton Cc: Matthew Wilcox Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dax.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 3855e3800f48..deb0f663252f 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -135,7 +135,7 @@ void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); -int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, +vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, pfn_t *pfnp, int *errp, const struct iomap_ops *ops); vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, enum page_entry_size pe_size, pfn_t pfn); -- cgit v1.2.3 From 0894aa28aece680a81e28906e2f328084a3d55c3 Mon Sep 17 00:00:00 2001 From: Radhey Shyam Pandey Date: Wed, 13 Jun 2018 13:04:48 +0530 Subject: dmaengine: xilinx_dma: Enable VDMA S2MM vertical flip support Vertical flip state is exported in xilinx_vdma_config and depending on IP configuration(c_enable_vert_flip) vertical flip state is programmed in hardware. Signed-off-by: Radhey Shyam Pandey Signed-off-by: Michal Simek Acked-by: Kedareswara rao Appana Signed-off-by: Vinod Koul --- include/linux/dma/xilinx_dma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma/xilinx_dma.h b/include/linux/dma/xilinx_dma.h index 34b98f276ed0..5b6e61e4b3aa 100644 --- a/include/linux/dma/xilinx_dma.h +++ b/include/linux/dma/xilinx_dma.h @@ -27,6 +27,7 @@ * @delay: Delay counter * @reset: Reset Channel * @ext_fsync: External Frame Sync source + * @vflip_en: Vertical Flip enable */ struct xilinx_vdma_config { int frm_dly; @@ -39,6 +40,7 @@ struct xilinx_vdma_config { int delay; int reset; int ext_fsync; + bool vflip_en; }; int xilinx_vdma_channel_set_config(struct dma_chan *dchan, -- cgit v1.2.3 From 9544bc5347207a68eb308cc8aaaed6c3a687cabd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 29 Jun 2018 08:48:06 -0600 Subject: sg: remove ->sg_magic member This was introduced more than a decade ago when sg chaining was added, but we never really caught anything with it. The scatterlist entry size can be critical, since drivers allocate it, so remove the magic member. Recently it's been triggering allocation stalls and failures in NVMe. Tested-by: Jordan Glover Acked-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/scatterlist.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 51f52020ad5f..093aa57120b0 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -9,9 +9,6 @@ #include struct scatterlist { -#ifdef CONFIG_DEBUG_SG - unsigned long sg_magic; -#endif unsigned long page_link; unsigned int offset; unsigned int length; @@ -64,7 +61,6 @@ struct sg_table { * */ -#define SG_MAGIC 0x87654321 #define SG_CHAIN 0x01UL #define SG_END 0x02UL @@ -98,7 +94,6 @@ static inline void sg_assign_page(struct scatterlist *sg, struct page *page) */ BUG_ON((unsigned long) page & (SG_CHAIN | SG_END)); #ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); BUG_ON(sg_is_chain(sg)); #endif sg->page_link = page_link | (unsigned long) page; @@ -129,7 +124,6 @@ static inline void sg_set_page(struct scatterlist *sg, struct page *page, static inline struct page *sg_page(struct scatterlist *sg) { #ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); BUG_ON(sg_is_chain(sg)); #endif return (struct page *)((sg)->page_link & ~(SG_CHAIN | SG_END)); @@ -195,9 +189,6 @@ static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents, **/ static inline void sg_mark_end(struct scatterlist *sg) { -#ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); -#endif /* * Set termination bit, clear potential chain bit */ @@ -215,9 +206,6 @@ static inline void sg_mark_end(struct scatterlist *sg) **/ static inline void sg_unmark_end(struct scatterlist *sg) { -#ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); -#endif sg->page_link &= ~SG_END; } @@ -260,12 +248,6 @@ static inline void *sg_virt(struct scatterlist *sg) static inline void sg_init_marker(struct scatterlist *sgl, unsigned int nents) { -#ifdef CONFIG_DEBUG_SG - unsigned int i; - - for (i = 0; i < nents; i++) - sgl[i].sg_magic = SG_MAGIC; -#endif sg_mark_end(&sgl[nents - 1]); } -- cgit v1.2.3 From 85782e037f8aba8922dadb24a1523ca0b82ab8bc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 28 Jun 2018 23:34:59 +0200 Subject: bpf: undo prog rejection on read-only lock failure Partially undo commit 9facc336876f ("bpf: reject any prog that failed read-only lock") since it caused a regression, that is, syzkaller was able to manage to cause a panic via fault injection deep in set_memory_ro() path by letting an allocation fail: In x86's __change_page_attr_set_clr() it was able to change the attributes of the primary mapping but not in the alias mapping via cpa_process_alias(), so the second, inner call to the __change_page_attr() via __change_page_attr_set_clr() had to split a larger page and failed in the alloc_pages() with the artifically triggered allocation error which is then propagated down to the call site. Thus, for set_memory_ro() this means that it returned with an error, but from debugging a probe_kernel_write() revealed EFAULT on that memory since the primary mapping succeeded to get changed. Therefore the subsequent hdr->locked = 0 reset triggered the panic as it was performed on read-only memory, so call-site assumptions were infact wrong to assume that it would either succeed /or/ not succeed at all since there's no such rollback in set_memory_*() calls from partial change of mappings, in other words, we're left in a state that is "half done". A later undo via set_memory_rw() is succeeding though due to matching permissions on that part (aka due to the try_preserve_large_page() succeeding). While reproducing locally with explicitly triggering this error, the initial splitting only happens on rare occasions and in real world it would additionally need oom conditions, but that said, it could partially fail. Therefore, it is definitely wrong to bail out on set_memory_ro() error and reject the program with the set_memory_*() semantics we have today. Shouldn't have gone the extra mile since no other user in tree today infact checks for any set_memory_*() errors, e.g. neither module_enable_ro() / module_disable_ro() for module RO/NX handling which is mostly default these days nor kprobes core with alloc_insn_page() / free_insn_page() as examples that could be invoked long after bootup and original 314beb9bcabf ("x86: bpf_jit_comp: secure bpf jit against spraying attacks") did neither when it got first introduced to BPF so "improving" with bailing out was clearly not right when set_memory_*() cannot handle it today. Kees suggested that if set_memory_*() can fail, we should annotate it with __must_check, and all callers need to deal with it gracefully given those set_memory_*() markings aren't "advisory", but they're expected to actually do what they say. This might be an option worth to move forward in future but would at the same time require that set_memory_*() calls from supporting archs are guaranteed to be "atomic" in that they provide rollback if part of the range fails, once that happened, the transition from RW -> RO could be made more robust that way, while subsequent RO -> RW transition /must/ continue guaranteeing to always succeed the undo part. Reported-by: syzbot+a4eb8c7766952a1ca872@syzkaller.appspotmail.com Reported-by: syzbot+d866d1925855328eac3b@syzkaller.appspotmail.com Fixes: 9facc336876f ("bpf: reject any prog that failed read-only lock") Cc: Laura Abbott Cc: Kees Cook Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 56 ++++++++------------------------------------------ 1 file changed, 8 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 20f2659dd829..300baad62c88 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -470,9 +470,7 @@ struct sock_fprog_kern { }; struct bpf_binary_header { - u16 pages; - u16 locked:1; - + u32 pages; /* Some arches need word alignment for their instructions */ u8 image[] __aligned(4); }; @@ -481,7 +479,7 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ - locked:1, /* Program image locked? */ + undo_set_mem:1, /* Passed set_memory_ro() checkpoint */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ @@ -677,46 +675,24 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - fp->locked = 1; - if (set_memory_ro((unsigned long)fp, fp->pages)) - fp->locked = 0; -#endif + fp->undo_set_mem = 1; + set_memory_ro((unsigned long)fp, fp->pages); } static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - if (fp->locked) { - WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages)); - /* In case set_memory_rw() fails, we want to be the first - * to crash here instead of some random place later on. - */ - fp->locked = 0; - } -#endif + if (fp->undo_set_mem) + set_memory_rw((unsigned long)fp, fp->pages); } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - hdr->locked = 1; - if (set_memory_ro((unsigned long)hdr, hdr->pages)) - hdr->locked = 0; -#endif + set_memory_ro((unsigned long)hdr, hdr->pages); } static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - if (hdr->locked) { - WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages)); - /* In case set_memory_rw() fails, we want to be the first - * to crash here instead of some random place later on. - */ - hdr->locked = 0; - } -#endif + set_memory_rw((unsigned long)hdr, hdr->pages); } static inline struct bpf_binary_header * @@ -728,22 +704,6 @@ bpf_jit_binary_hdr(const struct bpf_prog *fp) return (void *)addr; } -#ifdef CONFIG_ARCH_HAS_SET_MEMORY -static inline int bpf_prog_check_pages_ro_single(const struct bpf_prog *fp) -{ - if (!fp->locked) - return -ENOLCK; - if (fp->jited) { - const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); - - if (!hdr->locked) - return -ENOLCK; - } - - return 0; -} -#endif - int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { -- cgit v1.2.3 From cfdfc14e7fb8ae77290e9d5afaeecc0a234a3846 Mon Sep 17 00:00:00 2001 From: Doug Meyer Date: Wed, 23 May 2018 13:18:05 -0700 Subject: switchtec: Use generic PCI Vendor ID and Class Code Move the Microsemi Switchtec PCI Vendor ID (same as PCI_VENDOR_ID_PMC_Sierra) to pci_ids.h. Also, replace Microsemi class constants with the standard PCI definitions. Signed-off-by: Doug Meyer [bhelgaas: restore SPDX (I assume it was removed by mistake), remove device ID definitions] Signed-off-by: Bjorn Helgaas Reviewed-by: Logan Gunthorpe --- include/linux/pci_ids.h | 1 + include/linux/switchtec.h | 4 ---- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 29502238e510..80aec5b9a6c1 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1668,6 +1668,7 @@ #define PCI_DEVICE_ID_COMPEX_ENET100VG4 0x0112 #define PCI_VENDOR_ID_PMC_Sierra 0x11f8 +#define PCI_VENDOR_ID_MICROSEMI 0x11f8 #define PCI_VENDOR_ID_RP 0x11fe #define PCI_DEVICE_ID_RP32INTF 0x0001 diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index ec93e93371fa..ab400af6f0ce 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -19,10 +19,6 @@ #include #include -#define MICROSEMI_VENDOR_ID 0x11f8 -#define MICROSEMI_NTB_CLASSCODE 0x068000 -#define MICROSEMI_MGMT_CLASSCODE 0x058000 - #define SWITCHTEC_MRPC_PAYLOAD_SIZE 1024 #define SWITCHTEC_MAX_PFF_CSR 48 -- cgit v1.2.3 From 783e84961b1d7a75045383586b8c49e02b7704cd Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 29 Jun 2018 21:17:26 -0500 Subject: PCI: Make pci_get_rom_size() static pci_get_rom_size() is called only from pci_map_rom(), so it can be static. Make it static and remove the declaration from include/linux/pci.h. Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..f40d3e05ccd1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1122,7 +1122,6 @@ int pci_enable_rom(struct pci_dev *pdev); void pci_disable_rom(struct pci_dev *pdev); void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size); void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom); -size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size); void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size); /* Power management related routines */ -- cgit v1.2.3 From 7ce3f912ae0a79e5d738a3ae1f158b281973e849 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Sat, 30 Jun 2018 11:24:24 -0400 Subject: PCI: Enable PASID only if entire path supports End-End TLP prefixes A PCIe endpoint carries the process address space identifier (PASID) in the TLP prefix as part of the memory read/write transaction. The address information in the TLP is relevant only for a given PASID context. An IOMMU takes PASID value and the address information from the TLP to look up the physical address in the system. PASID is an End-End TLP Prefix (PCIe r4.0, sec 6.20). Sec 2.2.10.2 says It is an error to receive a TLP with an End-End TLP Prefix by a Receiver that does not support End-End TLP Prefixes. A TLP in violation of this rule is handled as a Malformed TLP. This is a reported error associated with the Receiving Port (see Section 6.2). Prevent error condition by proactively requiring End-End TLP prefix to be supported on the entire data path between the endpoint and the root port before enabling PASID. Signed-off-by: Sinan Kaya Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..6ba818449095 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -350,6 +350,7 @@ struct pci_dev { unsigned int ltr_path:1; /* Latency Tolerance Reporting supported from root to here */ #endif + unsigned int eetlp_prefix_path:1; /* End-to-End TLP Prefix */ pci_channel_state_t error_state; /* Current connectivity state */ struct device dev; /* Generic device interface */ -- cgit v1.2.3 From 80d19669ecd34423e85ca04f2210b0e42a47cb16 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Fri, 29 Jun 2018 21:26:41 -0700 Subject: net: Refactor XPS for CPUs and Rx queues Refactor XPS code to support Tx queue selection based on CPU(s) map or Rx queue(s) map. Signed-off-by: Amritha Nambiar Signed-off-by: David S. Miller --- include/linux/cpumask.h | 11 ++++-- include/linux/netdevice.h | 98 +++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 103 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index bf53d893ad02..57f20a0a7794 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -115,12 +115,17 @@ extern struct cpumask __cpu_active_mask; #define cpu_active(cpu) ((cpu) == 0) #endif -/* verify cpu argument to cpumask_* operators */ -static inline unsigned int cpumask_check(unsigned int cpu) +static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS - WARN_ON_ONCE(cpu >= nr_cpumask_bits); + WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ +} + +/* verify cpu argument to cpumask_* operators */ +static inline unsigned int cpumask_check(unsigned int cpu) +{ + cpu_max_bits_warn(cpu, nr_cpumask_bits); return cpu; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c6b377a15869..8bf8d6149f79 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -731,10 +731,15 @@ struct xps_map { */ struct xps_dev_maps { struct rcu_head rcu; - struct xps_map __rcu *cpu_map[0]; + struct xps_map __rcu *attr_map[0]; /* Either CPUs map or RXQs map */ }; -#define XPS_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ + +#define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ (nr_cpu_ids * (_tcs) * sizeof(struct xps_map *))) + +#define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\ + (_rxqs * (_tcs) * sizeof(struct xps_map *))) + #endif /* CONFIG_XPS */ #define TC_MAX_QUEUE 16 @@ -1910,7 +1915,8 @@ struct net_device { int watchdog_timeo; #ifdef CONFIG_XPS - struct xps_dev_maps __rcu *xps_maps; + struct xps_dev_maps __rcu *xps_cpus_map; + struct xps_dev_maps __rcu *xps_rxqs_map; #endif #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc __rcu *miniq_egress; @@ -3259,6 +3265,92 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index); +int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, + u16 index, bool is_rxqs_map); + +/** + * netif_attr_test_mask - Test a CPU or Rx queue set in a mask + * @j: CPU/Rx queue index + * @mask: bitmask of all cpus/rx queues + * @nr_bits: number of bits in the bitmask + * + * Test if a CPU or Rx queue index is set in a mask of all CPU/Rx queues. + */ +static inline bool netif_attr_test_mask(unsigned long j, + const unsigned long *mask, + unsigned int nr_bits) +{ + cpu_max_bits_warn(j, nr_bits); + return test_bit(j, mask); +} + +/** + * netif_attr_test_online - Test for online CPU/Rx queue + * @j: CPU/Rx queue index + * @online_mask: bitmask for CPUs/Rx queues that are online + * @nr_bits: number of bits in the bitmask + * + * Returns true if a CPU/Rx queue is online. + */ +static inline bool netif_attr_test_online(unsigned long j, + const unsigned long *online_mask, + unsigned int nr_bits) +{ + cpu_max_bits_warn(j, nr_bits); + + if (online_mask) + return test_bit(j, online_mask); + + return (j < nr_bits); +} + +/** + * netif_attrmask_next - get the next CPU/Rx queue in a cpu/Rx queues mask + * @n: CPU/Rx queue index + * @srcp: the cpumask/Rx queue mask pointer + * @nr_bits: number of bits in the bitmask + * + * Returns >= nr_bits if no further CPUs/Rx queues set. + */ +static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, + unsigned int nr_bits) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); + + if (srcp) + return find_next_bit(srcp, nr_bits, n + 1); + + return n + 1; +} + +/** + * netif_attrmask_next_and - get the next CPU/Rx queue in *src1p & *src2p + * @n: CPU/Rx queue index + * @src1p: the first CPUs/Rx queues mask pointer + * @src2p: the second CPUs/Rx queues mask pointer + * @nr_bits: number of bits in the bitmask + * + * Returns >= nr_bits if no further CPUs/Rx queues set in both. + */ +static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, + const unsigned long *src2p, + unsigned int nr_bits) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); + + if (src1p && src2p) + return find_next_and_bit(src1p, src2p, nr_bits, n + 1); + else if (src1p) + return find_next_bit(src1p, nr_bits, n + 1); + else if (src2p) + return find_next_bit(src2p, nr_bits, n + 1); + + return n + 1; +} #else static inline int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, -- cgit v1.2.3 From f308d7353d1f5c3ddedc784a367edc72fc51bbaa Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Sun, 24 Jun 2018 23:27:22 +0200 Subject: mtd: rawnand: add Reed-Solomon error correction algorithm Add Reed-Solomon (RS) to the enumeration of ECC algorithms. Signed-off-by: Stefan Agner Reviewed-by: Boris Brezillon Acked-by: Rob Herring Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 3e8ec3b8a39c..2d9cb7acbc3d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -121,6 +121,7 @@ enum nand_ecc_algo { NAND_ECC_UNKNOWN, NAND_ECC_HAMMING, NAND_ECC_BCH, + NAND_ECC_RS, }; /* -- cgit v1.2.3 From f922bd798bb94e0adcce26ddd811245443173268 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Sun, 24 Jun 2018 23:27:23 +0200 Subject: mtd: rawnand: add an option to specify NAND chip as a boot device Allow to define a NAND chip as a boot device. This can be helpful for the selection of the ECC algorithm and strength in case the boot ROM supports only a subset of controller provided options. Signed-off-by: Stefan Agner Reviewed-by: Boris Brezillon Acked-by: Rob Herring Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 2d9cb7acbc3d..80aeeca03f36 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -219,6 +219,12 @@ enum nand_ecc_algo { */ #define NAND_WAIT_TCCS 0x00200000 +/* + * Whether the NAND chip is a boot medium. Drivers might use this information + * to select ECC algorithms supported by the boot ROM or similar restrictions. + */ +#define NAND_IS_BOOT_MEDIUM 0x00400000 + /* Options set by nand scan */ /* Nand scan has allocated controller struct */ #define NAND_CONTROLLER_ALLOC 0x80000000 -- cgit v1.2.3 From 00ce4e039ad5bded462931606c3063ff691964b7 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Mon, 25 Jun 2018 10:44:44 +1200 Subject: mtd: rawnand: add manufacturer fixup for ONFI parameter page This is called after the ONFI parameter page checksum is verified and allows us to override the contents of the parameter page. Suggested-by: Boris Brezillon Signed-off-by: Chris Packham Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 80aeeca03f36..dc4538b58b84 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -785,11 +785,15 @@ nand_get_sdr_timings(const struct nand_data_interface *conf) * implementation) if any. * @cleanup: the ->init() function may have allocated resources, ->cleanup() * is here to let vendor specific code release those resources. + * @fixup_onfi_param_page: apply vendor specific fixups to the ONFI parameter + * page. This is called after the checksum is verified. */ struct nand_manufacturer_ops { void (*detect)(struct nand_chip *chip); int (*init)(struct nand_chip *chip); void (*cleanup)(struct nand_chip *chip); + void (*fixup_onfi_param_page)(struct nand_chip *chip, + struct nand_onfi_params *p); }; /** -- cgit v1.2.3 From 872b71ff084ab125c68073d9e69acfd7095f2015 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Mon, 25 Jun 2018 10:44:45 +1200 Subject: mtd: rawnand: add defines for ONFI version bits Add defines for the ONFI version bits and use them in nand_flash_detect_onfi(). Signed-off-by: Chris Packham Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index dc4538b58b84..fbac4741da52 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -237,6 +237,17 @@ enum nand_ecc_algo { /* Keep gcc happy */ struct nand_chip; +/* ONFI version bits */ +#define ONFI_VERSION_1_0 BIT(1) +#define ONFI_VERSION_2_0 BIT(2) +#define ONFI_VERSION_2_1 BIT(3) +#define ONFI_VERSION_2_2 BIT(4) +#define ONFI_VERSION_2_3 BIT(5) +#define ONFI_VERSION_3_0 BIT(6) +#define ONFI_VERSION_3_1 BIT(7) +#define ONFI_VERSION_3_2 BIT(8) +#define ONFI_VERSION_4_0 BIT(9) + /* ONFI features */ #define ONFI_FEATURE_16_BIT_BUS (1 << 0) #define ONFI_FEATURE_EXT_PARAM_PAGE (1 << 7) -- cgit v1.2.3 From 1b48b7202c43e41c9f05d39901567dbcad5dc307 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 3 May 2018 16:25:49 +0200 Subject: dma-fence: remove fill_driver_data callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Noticed while I was typing docs. Entirely unused. v2: Remove reference in @timeline_value_str too. While at it clarify why timeline_value_str has a fence parameter - we don't have an explicit timeline structure unfortunately. Cc: Eric Anholt Reviewed-by: Eric Anholt Reviewed-by: Christian König (v1) Cc: Christian König (v1) Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-2-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index eb9b05aa5aea..111aefe1c956 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -217,17 +217,6 @@ struct dma_fence_ops { */ void (*release)(struct dma_fence *fence); - /** - * @fill_driver_data: - * - * Callback to fill in free-form debug info. - * - * Returns amount of bytes filled, or negative error on failure. - * - * This callback is optional. - */ - int (*fill_driver_data)(struct dma_fence *fence, void *data, int size); - /** * @fence_value_str: * @@ -242,8 +231,9 @@ struct dma_fence_ops { * @timeline_value_str: * * Fills in the current value of the timeline as a string, like the - * sequence number. This should match what @fill_driver_data prints for - * the most recently signalled fence (assuming no delayed signalling). + * sequence number. Note that the specific fence passed to this function + * should not matter, drivers should only use it to look up the + * corresponding timeline structures. */ void (*timeline_value_str)(struct dma_fence *fence, char *str, int size); -- cgit v1.2.3 From c701317a3eb8c012364a8d468f20eabf6df1ad77 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 4 May 2018 16:10:34 +0200 Subject: dma-fence: Make ->enable_signaling optional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Many drivers have a trivial implementation for ->enable_signaling. Let's make it optional by assuming that signalling is already available when the callback isn't present. v2: Don't do the trick to set the ENABLE_SIGNAL_BIT unconditionally, it results in an expensive spinlock take for everyone. Instead just check if the callback is present. Suggested by Maarten. Also move misplaced kerneldoc hunk to the right patch. Cc: Maarten Lankhorst Reviewed-by: Christian König (v1) Reviewed-by: Maarten Lankhorst Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: Gustavo Padovan Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20180504141034.27727-1-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 111aefe1c956..c053d19e1e24 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -166,7 +166,8 @@ struct dma_fence_ops { * released when the fence is signalled (through e.g. the interrupt * handler). * - * This callback is mandatory. + * This callback is optional. If this callback is not present, then the + * driver must always have signaling enabled. */ bool (*enable_signaling)(struct dma_fence *fence); -- cgit v1.2.3 From 78c9c4dfbf8c04883941445a195276bb4bb92c76 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 26 Jun 2018 15:21:32 +0200 Subject: posix-timers: Sanitize overrun handling The posix timer overrun handling is broken because the forwarding functions can return a huge number of overruns which does not fit in an int. As a consequence timer_getoverrun(2) and siginfo::si_overrun can turn into random number generators. The k_clock::timer_forward() callbacks return a 64 bit value now. Make k_itimer::ti_overrun[_last] 64bit as well, so the kernel internal accounting is correct. 3Remove the temporary (int) casts. Add a helper function which clamps the overrun value returned to user space via timer_getoverrun(2) or siginfo::si_overrun limited to a positive value between 0 and INT_MAX. INT_MAX is an indicator for user space that the overrun value has been clamped. Reported-by: Team OWL337 Signed-off-by: Thomas Gleixner Acked-by: John Stultz Cc: Peter Zijlstra Cc: Michael Kerrisk Link: https://lkml.kernel.org/r/20180626132705.018623573@linutronix.de --- include/linux/posix-timers.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index c85704fcdbd2..ee7e987ea1b4 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -95,8 +95,8 @@ struct k_itimer { clockid_t it_clock; timer_t it_id; int it_active; - int it_overrun; - int it_overrun_last; + s64 it_overrun; + s64 it_overrun_last; int it_requeue_pending; int it_sigev_notify; ktime_t it_interval; -- cgit v1.2.3 From 05739375f1c0a1048fea8b9c4cb54d9e4a891938 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Fri, 29 Jun 2018 14:59:40 +0200 Subject: ASoC: pxa-ssp: remove .set_pll() and .set_clkdiv() callbacks The .set_pll() and .set_clkdiv() callbacks are considered legacy and should not be used anymore. In order to support PXA boards on DT platforms, remove them and let the code figure out the correct dividers and PLL base frequencies itself. Signed-off-by: Daniel Mack Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 03a7ca46735b..13b4244d44c1 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -171,6 +171,14 @@ #define SSACD_SCDB (1 << 3) /* SSPSYSCLK Divider Bypass */ #define SSACD_ACPS(x) ((x) << 4) /* Audio clock PLL select */ #define SSACD_ACDS(x) ((x) << 0) /* Audio clock divider select */ +#define SSACD_ACDS_1 (0) +#define SSACD_ACDS_2 (1) +#define SSACD_ACDS_4 (2) +#define SSACD_ACDS_8 (3) +#define SSACD_ACDS_16 (4) +#define SSACD_ACDS_32 (5) +#define SSACD_SCDB_4X (0) +#define SSACD_SCDB_1X (1) #define SSACD_SCDX8 (1 << 7) /* SYSCLK division ratio select */ /* LPSS SSP */ -- cgit v1.2.3 From 88763a5cf80ca59a7c3bea32681ce8f697d9995f Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 26 Jun 2018 12:53:29 +0200 Subject: powercap / idle_inject: Add an idle injection framework Initially, the cpu_cooling device for ARM was changed by adding a new policy inserting idle cycles. The intel_powerclamp driver does a similar action. Instead of implementing idle injections privately in the cpu_cooling device, move the idle injection code in a dedicated framework and give the opportunity to other frameworks to make use of it. The framework relies on the smpboot kthreads which handles via its main loop the common code for hotplugging and [un]parking. This code was previously tested with the cpu cooling device and went through several iterations. It results now in split code and API exported in the header file. It was tested with the cpu cooling device with success. Signed-off-by: Daniel Lezcano Reviewed-by: Viresh Kumar [ rjw: Rewrite of all comments ] Signed-off-by: Rafael J. Wysocki --- include/linux/idle_inject.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/linux/idle_inject.h (limited to 'include/linux') diff --git a/include/linux/idle_inject.h b/include/linux/idle_inject.h new file mode 100644 index 000000000000..bdc0293fb6cb --- /dev/null +++ b/include/linux/idle_inject.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 Linaro Ltd + * + * Author: Daniel Lezcano + * + */ +#ifndef __IDLE_INJECT_H__ +#define __IDLE_INJECT_H__ + +/* private idle injection device structure */ +struct idle_inject_device; + +struct idle_inject_device *idle_inject_register(struct cpumask *cpumask); + +void idle_inject_unregister(struct idle_inject_device *ii_dev); + +int idle_inject_start(struct idle_inject_device *ii_dev); + +void idle_inject_stop(struct idle_inject_device *ii_dev); + +void idle_inject_set_duration(struct idle_inject_device *ii_dev, + unsigned int run_duration_ms, + unsigned int idle_duration_ms); + +void idle_inject_get_duration(struct idle_inject_device *ii_dev, + unsigned int *run_duration_ms, + unsigned int *idle_duration_ms); +#endif /* __IDLE_INJECT_H__ */ -- cgit v1.2.3 From 603d4cf8fe095b1ee78f423d514427be507fb513 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Sat, 30 Jun 2018 17:38:55 +0200 Subject: net: fix use-after-free in GRO with ESP Since the addition of GRO for ESP, gro_receive can consume the skb and return -EINPROGRESS. In that case, the lower layer GRO handler cannot touch the skb anymore. Commit 5f114163f2f5 ("net: Add a skb_gro_flush_final helper.") converted some of the gro_receive handlers that can lead to ESP's gro_receive so that they wouldn't access the skb when -EINPROGRESS is returned, but missed other spots, mainly in tunneling protocols. This patch finishes the conversion to using skb_gro_flush_final(), and adds a new helper, skb_gro_flush_final_remcsum(), used in VXLAN and GUE. Fixes: 5f114163f2f5 ("net: Add a skb_gro_flush_final helper.") Signed-off-by: Sabrina Dubroca Reviewed-by: Stefano Brivio Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ec9850c7936..3d0cc0b5cec2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2789,11 +2789,31 @@ static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, if (PTR_ERR(pp) != -EINPROGRESS) NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff **pp, + int flush, + struct gro_remcsum *grc) +{ + if (PTR_ERR(pp) != -EINPROGRESS) { + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; + } +} #else static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff **pp, + int flush, + struct gro_remcsum *grc) +{ + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; +} #endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, -- cgit v1.2.3 From a7ca13826e478f9b201eb2f9f20de0b978a82ad9 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 29 Jun 2018 14:11:19 +1000 Subject: gpio: aspeed: Add interfaces for co-processor to grab GPIOs On the Aspeed chip, the GPIOs can be under control of the ARM chip or of the ColdFire coprocessor. (There's a third command source, the LPC bus, which we don't use or support yet). The control of which master is allowed to modify a given GPIO is per-bank (8 GPIOs). Unfortunately, systems already exist for which we want to use GPIOs of both sources in the same bank. This provides an API exported by the gpio-aspeed driver that an aspeed coprocessor driver can use to "grab" some GPIOs for use by the coprocessor, and allow the coprocessor driver to provide callbacks for arbitrating access. Once at least one GPIO of a given bank has been "grabbed" by the coprocessor, the entire bank is marked as being under coprocessor control. It's command source is switched to the coprocessor. If the ARM then tries to write to a GPIO in such a marked bank, the provided callbacks are used to request access from the coprocessor driver, which is responsible to doing whatever is necessary to "pause" the coprocessor or prevent it from trying to use the GPIOs while the ARM is doing its accesses. During that time, the command source for the bank is temporarily switched back to the ARM. Signed-off-by: Benjamin Herrenschmidt Reviewed-by: Joel Stanley Reviewed-by: Andrew Jeffery Signed-off-by: Linus Walleij --- include/linux/gpio/aspeed.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/gpio/aspeed.h (limited to 'include/linux') diff --git a/include/linux/gpio/aspeed.h b/include/linux/gpio/aspeed.h new file mode 100644 index 000000000000..1bfb3cdc86d0 --- /dev/null +++ b/include/linux/gpio/aspeed.h @@ -0,0 +1,15 @@ +#ifndef __GPIO_ASPEED_H +#define __GPIO_ASPEED_H + +struct aspeed_gpio_copro_ops { + int (*request_access)(void *data); + int (*release_access)(void *data); +}; + +int aspeed_gpio_copro_grab_gpio(struct gpio_desc *desc, + u16 *vreg_offset, u16 *dreg_offset, u8 *bit); +int aspeed_gpio_copro_release_gpio(struct gpio_desc *desc); +int aspeed_gpio_copro_set_ops(const struct aspeed_gpio_copro_ops *ops, void *data); + + +#endif /* __GPIO_ASPEED_H */ -- cgit v1.2.3 From 240630e61870e62e39a97225048f9945848fa5f5 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 1 Jul 2018 12:15:46 +0200 Subject: ahci: Disable LPM on Lenovo 50 series laptops with a too old BIOS There have been several reports of LPM related hard freezes about once a day on multiple Lenovo 50 series models. Strange enough these reports where not disk model specific as LPM issues usually are and some users with the exact same disk + laptop where seeing them while other users where not seeing these issues. It turns out that enabling LPM triggers a firmware bug somewhere, which has been fixed in later BIOS versions. This commit adds a new ahci_broken_lpm() function and a new ATA_FLAG_NO_LPM for dealing with this. The ahci_broken_lpm() function contains DMI match info for the 4 models which are known to be affected by this and the DMI BIOS date field for known good BIOS versions. If the BIOS date is older then the one in the table LPM will be disabled and a warning will be printed. Note the BIOS dates are for known good versions, some older versions may work too, but we don't know for sure, the table is using dates from BIOS versions for which users have confirmed that upgrading to that version makes the problem go away. Unfortunately I've been unable to get hold of the reporter who reported that BIOS version 2.35 fixed the problems on the W541 for him. I've been able to verify the DMI_SYS_VENDOR and DMI_PRODUCT_VERSION from an older dmidecode, but I don't know the exact BIOS date as reported in the DMI. Lenovo keeps a changelog with dates in their release notes, but the dates there are the release dates not the build dates which are in DMI. So I've chosen to set the date to which we compare to one day past the release date of the 2.34 BIOS. I plan to fix this with a follow up commit once I've the necessary info. Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Signed-off-by: Tejun Heo --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index a2257e380789..32f247cb5e9e 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -210,6 +210,7 @@ enum { ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ /* (doesn't imply presence) */ ATA_FLAG_SATA = (1 << 1), + ATA_FLAG_NO_LPM = (1 << 2), /* host not happy with LPM */ ATA_FLAG_NO_LOG_PAGE = (1 << 5), /* do not issue log page read */ ATA_FLAG_NO_ATAPI = (1 << 6), /* No ATAPI support */ ATA_FLAG_PIO_DMA = (1 << 7), /* PIO cmds via DMA */ -- cgit v1.2.3 From 93dd2112c7b2fa5512cc4aff2c449420487fcb68 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Wed, 27 Jun 2018 18:19:48 +0300 Subject: usb: typec: mux: Get the mux identifier from function parameter In order for the muxes to be usable with alternate modes, the alternate mode devices will need also to be able to get a handle to the muxes on top of the port devices. To make that possible, the muxes need to be possible to request with an identifier. This will change the API so that the mux identifier is given as a function parameter to typec_mux_get(), and the hard-coded "typec-mux" is replaced with that value. Signed-off-by: Heikki Krogerus Tested-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec_mux.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/typec_mux.h b/include/linux/usb/typec_mux.h index 12c1b057834b..79293f630ee1 100644 --- a/include/linux/usb/typec_mux.h +++ b/include/linux/usb/typec_mux.h @@ -47,7 +47,7 @@ void typec_switch_put(struct typec_switch *sw); int typec_switch_register(struct typec_switch *sw); void typec_switch_unregister(struct typec_switch *sw); -struct typec_mux *typec_mux_get(struct device *dev); +struct typec_mux *typec_mux_get(struct device *dev, const char *name); void typec_mux_put(struct typec_mux *mux); int typec_mux_register(struct typec_mux *mux); void typec_mux_unregister(struct typec_mux *mux); -- cgit v1.2.3 From 4ab8c18d4d67321cc7b660559de17511d4fc0237 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Wed, 27 Jun 2018 18:19:49 +0300 Subject: usb: typec: Register a device for every mode Before a device was created for every discovered SVID, but this will create a device for every discovered mode of every SVID. The idea is to make it easier to create mode specific drivers once a bus for the alternate mode is added. Signed-off-by: Heikki Krogerus Tested-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 37 +++++++++---------------------------- 1 file changed, 9 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 6c33b53d1162..2dcb1683075f 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -93,41 +93,23 @@ int typec_partner_set_identity(struct typec_partner *partner); int typec_cable_set_identity(struct typec_cable *cable); /* - * struct typec_mode_desc - Individual Mode of an Alternate Mode - * @index: Index of the Mode within the SVID + * struct typec_altmode_desc - USB Type-C Alternate Mode Descriptor + * @svid: Standard or Vendor ID + * @mode: Index of the Mode * @vdo: VDO returned by Discover Modes USB PD command - * @desc: Optional human readable description of the mode * @roles: Only for ports. DRP if the mode is available in both roles * - * Description of a mode of an Alternate Mode which a connector, cable plug or - * partner supports. Every mode will have it's own sysfs group. The details are - * the VDO returned by discover modes command, description for the mode and - * active flag telling has the mode being entered or not. + * Description of an Alternate Mode which a connector, cable plug or partner + * supports. */ -struct typec_mode_desc { - int index; +struct typec_altmode_desc { + u16 svid; + u8 mode; u32 vdo; - char *desc; /* Only used with ports */ enum typec_port_type roles; }; -/* - * struct typec_altmode_desc - USB Type-C Alternate Mode Descriptor - * @svid: Standard or Vendor ID - * @n_modes: Number of modes - * @modes: Array of modes supported by the Alternate Mode - * - * Representation of an Alternate Mode that has SVID assigned by USB-IF. The - * array of modes will list the modes of a particular SVID that are supported by - * a connector, partner of a cable plug. - */ -struct typec_altmode_desc { - u16 svid; - int n_modes; - struct typec_mode_desc modes[ALTMODE_MAX_MODES]; -}; - struct typec_altmode *typec_partner_register_altmode(struct typec_partner *partner, const struct typec_altmode_desc *desc); @@ -141,8 +123,7 @@ void typec_unregister_altmode(struct typec_altmode *altmode); struct typec_port *typec_altmode2port(struct typec_altmode *alt); -void typec_altmode_update_active(struct typec_altmode *alt, int mode, - bool active); +void typec_altmode_update_active(struct typec_altmode *alt, bool active); enum typec_plug_index { TYPEC_PLUG_SOP_P, -- cgit v1.2.3 From 8a37d87d72f0c69f837229c04d2fcd7117ea57e7 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Wed, 27 Jun 2018 18:19:50 +0300 Subject: usb: typec: Bus type for alternate modes Introducing a simple bus for the alternate modes. Bus allows binding drivers to the discovered alternate modes the partners support. Signed-off-by: Heikki Krogerus Tested-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 15 ++++ include/linux/usb/typec.h | 14 +--- include/linux/usb/typec_altmode.h | 160 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 178 insertions(+), 11 deletions(-) create mode 100644 include/linux/usb/typec_altmode.h (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 96a71a648eed..1298a7daa57d 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -746,4 +746,19 @@ struct tb_service_id { #define TBSVC_MATCH_PROTOCOL_VERSION 0x0004 #define TBSVC_MATCH_PROTOCOL_REVISION 0x0008 +/* USB Type-C Alternate Modes */ + +#define TYPEC_ANY_MODE 0x7 + +/** + * struct typec_device_id - USB Type-C alternate mode identifiers + * @svid: Standard or Vendor ID + * @mode: Mode index + */ +struct typec_device_id { + __u16 svid; + __u8 mode; + kernel_ulong_t driver_data; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 2dcb1683075f..7df4ecabc78a 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -5,21 +5,18 @@ #include -/* XXX: Once we have a header for USB Power Delivery, this belongs there */ -#define ALTMODE_MAX_MODES 6 - /* USB Type-C Specification releases */ #define USB_TYPEC_REV_1_0 0x100 /* 1.0 */ #define USB_TYPEC_REV_1_1 0x110 /* 1.1 */ #define USB_TYPEC_REV_1_2 0x120 /* 1.2 */ -struct typec_altmode; struct typec_partner; struct typec_cable; struct typec_plug; struct typec_port; struct fwnode_handle; +struct device; enum typec_port_type { TYPEC_PORT_SRC, @@ -107,7 +104,7 @@ struct typec_altmode_desc { u8 mode; u32 vdo; /* Only used with ports */ - enum typec_port_type roles; + enum typec_port_data roles; }; struct typec_altmode @@ -186,7 +183,6 @@ struct typec_partner_desc { * @dr_set: Set Data Role * @pr_set: Set Power Role * @vconn_set: Set VCONN Role - * @activate_mode: Enter/exit given Alternate Mode * @port_type_set: Set port type * * Static capabilities of a single USB Type-C port. @@ -212,12 +208,8 @@ struct typec_capability { enum typec_role); int (*vconn_set)(const struct typec_capability *, enum typec_role); - - int (*activate_mode)(const struct typec_capability *, - int mode, int activate); int (*port_type_set)(const struct typec_capability *, - enum typec_port_type); - + enum typec_port_type); }; /* Specific to try_role(). Indicates the user want's to clear the preference. */ diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h new file mode 100644 index 000000000000..9a88c74a1d0d --- /dev/null +++ b/include/linux/usb/typec_altmode.h @@ -0,0 +1,160 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __USB_TYPEC_ALTMODE_H +#define __USB_TYPEC_ALTMODE_H + +#include +#include +#include + +#define MODE_DISCOVERY_MAX 6 + +struct typec_altmode_ops; + +/** + * struct typec_altmode - USB Type-C alternate mode device + * @dev: Driver model's view of this device + * @svid: Standard or Vendor ID (SVID) of the alternate mode + * @mode: Index of the Mode + * @vdo: VDO returned by Discover Modes USB PD command + * @active: Tells has the mode been entered or not + * @desc: Optional human readable description of the mode + * @ops: Operations vector from the driver + */ +struct typec_altmode { + struct device dev; + u16 svid; + int mode; + u32 vdo; + unsigned int active:1; + + char *desc; + const struct typec_altmode_ops *ops; +}; + +#define to_typec_altmode(d) container_of(d, struct typec_altmode, dev) + +static inline void typec_altmode_set_drvdata(struct typec_altmode *altmode, + void *data) +{ + dev_set_drvdata(&altmode->dev, data); +} + +static inline void *typec_altmode_get_drvdata(struct typec_altmode *altmode) +{ + return dev_get_drvdata(&altmode->dev); +} + +/** + * struct typec_altmode_ops - Alternate mode specific operations vector + * @enter: Operations to be executed with Enter Mode Command + * @exit: Operations to be executed with Exit Mode Command + * @attention: Callback for Attention Command + * @vdm: Callback for SVID specific commands + * @notify: Communication channel for platform and the alternate mode + * @activate: User callback for Enter/Exit Mode + */ +struct typec_altmode_ops { + int (*enter)(struct typec_altmode *altmode); + int (*exit)(struct typec_altmode *altmode); + void (*attention)(struct typec_altmode *altmode, u32 vdo); + int (*vdm)(struct typec_altmode *altmode, const u32 hdr, + const u32 *vdo, int cnt); + int (*notify)(struct typec_altmode *altmode, unsigned long conf, + void *data); + int (*activate)(struct typec_altmode *altmode, int activate); +}; + +int typec_altmode_enter(struct typec_altmode *altmode); +int typec_altmode_exit(struct typec_altmode *altmode); +void typec_altmode_attention(struct typec_altmode *altmode, u32 vdo); +int typec_altmode_vdm(struct typec_altmode *altmode, + const u32 header, const u32 *vdo, int count); +int typec_altmode_notify(struct typec_altmode *altmode, unsigned long conf, + void *data); +const struct typec_altmode * +typec_altmode_get_partner(struct typec_altmode *altmode); + +/* + * These are the connector states (USB, Safe and Alt Mode) defined in USB Type-C + * Specification. SVID specific connector states are expected to follow and + * start from the value TYPEC_STATE_MODAL. + */ +enum { + TYPEC_STATE_SAFE, /* USB Safe State */ + TYPEC_STATE_USB, /* USB Operation */ + TYPEC_STATE_MODAL, /* Alternate Modes */ +}; + +/* + * For the muxes there is no difference between Accessory Modes and Alternate + * Modes, so the Accessory Modes are supplied with specific modal state values + * here. Unlike with Alternate Modes, where the mux will be linked with the + * alternate mode device, the mux for Accessory Modes will be linked with the + * port device instead. + * + * Port drivers can use TYPEC_MODE_AUDIO and TYPEC_MODE_DEBUG as the mode + * value for typec_set_mode() when accessory modes are supported. + */ +enum { + TYPEC_MODE_AUDIO = TYPEC_STATE_MODAL, /* Audio Accessory */ + TYPEC_MODE_DEBUG, /* Debug Accessory */ +}; + +#define TYPEC_MODAL_STATE(_state_) ((_state_) + TYPEC_STATE_MODAL) + +struct typec_altmode *typec_altmode_get_plug(struct typec_altmode *altmode, + enum typec_plug_index index); +void typec_altmode_put_plug(struct typec_altmode *plug); + +struct typec_altmode *typec_match_altmode(struct typec_altmode **altmodes, + size_t n, u16 svid, u8 mode); + +struct typec_altmode * +typec_altmode_register_notifier(struct device *dev, u16 svid, u8 mode, + struct notifier_block *nb); + +void typec_altmode_unregister_notifier(struct typec_altmode *adev, + struct notifier_block *nb); + +/** + * typec_altmode_get_orientation - Get cable plug orientation + * altmode: Handle to the alternate mode + */ +static inline enum typec_orientation +typec_altmode_get_orientation(struct typec_altmode *altmode) +{ + return typec_get_orientation(typec_altmode2port(altmode)); +} + +/** + * struct typec_altmode_driver - USB Type-C alternate mode device driver + * @id_table: Null terminated array of SVIDs + * @probe: Callback for device binding + * @remove: Callback for device unbinding + * @driver: Device driver model driver + * + * These drivers will be bind to the partner alternate mode devices. They will + * handle all SVID specific communication. + */ +struct typec_altmode_driver { + const struct typec_device_id *id_table; + int (*probe)(struct typec_altmode *altmode); + void (*remove)(struct typec_altmode *altmode); + struct device_driver driver; +}; + +#define to_altmode_driver(d) container_of(d, struct typec_altmode_driver, \ + driver) + +#define typec_altmode_register_driver(drv) \ + __typec_altmode_register_driver(drv, THIS_MODULE) +int __typec_altmode_register_driver(struct typec_altmode_driver *drv, + struct module *module); +void typec_altmode_unregister_driver(struct typec_altmode_driver *drv); + +#define module_typec_altmode_driver(__typec_altmode_driver) \ + module_driver(__typec_altmode_driver, typec_altmode_register_driver, \ + typec_altmode_unregister_driver) + +#endif /* __USB_TYPEC_ALTMODE_H */ -- cgit v1.2.3 From 0e3bb7d6894d9b6e67d6382bb03a46a1dc989588 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Wed, 27 Jun 2018 18:19:51 +0300 Subject: usb: typec: Add driver for DisplayPort alternate mode DisplayPort USB Type-C Alt Mode allows DisplayPort displays and adapters to be attached to the USB Type-C ports on the system. Signed-off-by: Heikki Krogerus Tested-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec_dp.h | 95 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 95 insertions(+) create mode 100644 include/linux/usb/typec_dp.h (limited to 'include/linux') diff --git a/include/linux/usb/typec_dp.h b/include/linux/usb/typec_dp.h new file mode 100644 index 000000000000..55ae781d60a9 --- /dev/null +++ b/include/linux/usb/typec_dp.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __USB_TYPEC_DP_H +#define __USB_TYPEC_DP_H + +#include + +#define USB_TYPEC_DP_SID 0xff01 +#define USB_TYPEC_DP_MODE 1 + +/* + * Connector states matching the pin assignments in DisplayPort Alt Mode + * Specification. + * + * These values are meant primarily to be used by the mux drivers, but they are + * also used as the "value" part in the alternate mode notification chain, so + * receivers of those notifications will always see them. + * + * Note. DisplayPort USB Type-C Alt Mode Specification version 1.0b deprecated + * pin assignments A, B and F, but they are still defined here for legacy + * purposes. + */ +enum { + TYPEC_DP_STATE_A = TYPEC_STATE_MODAL, /* Not supported after v1.0b */ + TYPEC_DP_STATE_B, /* Not supported after v1.0b */ + TYPEC_DP_STATE_C, + TYPEC_DP_STATE_D, + TYPEC_DP_STATE_E, + TYPEC_DP_STATE_F, /* Not supported after v1.0b */ +}; + +/* + * struct typec_displayport_data - DisplayPort Alt Mode specific data + * @status: Status Update command VDO content + * @conf: Configure command VDO content + * + * This structure is delivered as the data part with the notifications. It + * contains the VDOs from the two DisplayPort Type-C alternate mode specific + * commands: Status Update and Configure. + * + * @status will show for example the status of the HPD signal. + */ +struct typec_displayport_data { + u32 status; + u32 conf; +}; + +enum { + DP_PIN_ASSIGN_A, /* Not supported after v1.0b */ + DP_PIN_ASSIGN_B, /* Not supported after v1.0b */ + DP_PIN_ASSIGN_C, + DP_PIN_ASSIGN_D, + DP_PIN_ASSIGN_E, + DP_PIN_ASSIGN_F, /* Not supported after v1.0b */ +}; + +/* DisplayPort alt mode specific commands */ +#define DP_CMD_STATUS_UPDATE VDO_CMD_VENDOR(0) +#define DP_CMD_CONFIGURE VDO_CMD_VENDOR(1) + +/* DisplayPort Capabilities VDO bits (returned with Discover Modes) */ +#define DP_CAP_CAPABILITY(_cap_) ((_cap_) & 3) +#define DP_CAP_UFP_D 1 +#define DP_CAP_DFP_D 2 +#define DP_CAP_DFP_D_AND_UFP_D 3 +#define DP_CAP_DP_SIGNALING BIT(2) /* Always set */ +#define DP_CAP_GEN2 BIT(3) /* Reserved after v1.0b */ +#define DP_CAP_RECEPTACLE BIT(6) +#define DP_CAP_USB BIT(7) +#define DP_CAP_DFP_D_PIN_ASSIGN(_cap_) (((_cap_) & GENMASK(15, 8)) >> 8) +#define DP_CAP_UFP_D_PIN_ASSIGN(_cap_) (((_cap_) & GENMASK(23, 16)) >> 16) + +/* DisplayPort Status Update VDO bits */ +#define DP_STATUS_CONNECTION(_status_) ((_status_) & 3) +#define DP_STATUS_CON_DISABLED 0 +#define DP_STATUS_CON_DFP_D 1 +#define DP_STATUS_CON_UFP_D 2 +#define DP_STATUS_CON_BOTH 3 +#define DP_STATUS_POWER_LOW BIT(2) +#define DP_STATUS_ENABLED BIT(3) +#define DP_STATUS_PREFER_MULTI_FUNC BIT(4) +#define DP_STATUS_SWITCH_TO_USB BIT(5) +#define DP_STATUS_EXIT_DP_MODE BIT(6) +#define DP_STATUS_HPD_STATE BIT(7) /* 0 = HPD_Low, 1 = HPD_High */ +#define DP_STATUS_IRQ_HPD BIT(8) + +/* DisplayPort Configurations VDO bits */ +#define DP_CONF_CURRENTLY(_conf_) ((_conf_) & 3) +#define DP_CONF_UFP_U_AS_DFP_D BIT(0) +#define DP_CONF_UFP_U_AS_UFP_D BIT(1) +#define DP_CONF_SIGNALING_DP BIT(2) +#define DP_CONF_SIGNALING_GEN_2 BIT(3) /* Reserved after v1.0b */ +#define DP_CONF_PIN_ASSIGNEMENT_SHIFT 8 +#define DP_CONF_PIN_ASSIGNEMENT_MASK GENMASK(15, 8) + +#endif /* __USB_TYPEC_DP_H */ -- cgit v1.2.3 From e9576fe8e605c4413beb91b290b8a473985710de Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Wed, 27 Jun 2018 18:19:53 +0300 Subject: usb: typec: tcpm: Support for Alternate Modes This adds more complete handling of VDMs and registration of partner alternate modes, and introduces callbacks for alternate mode operations. Only DFP role is supported for now. Signed-off-by: Heikki Krogerus Tested-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tcpm.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index 193920a2e05f..7e7fbfb84e8e 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -98,15 +98,6 @@ struct tcpc_config { #define TCPC_MUX_DP_ENABLED BIT(1) /* DP enabled */ #define TCPC_MUX_POLARITY_INVERTED BIT(2) /* Polarity inverted */ -/* Mux modes, decoded to attributes */ -enum tcpc_mux_mode { - TYPEC_MUX_NONE = 0, /* Open switch */ - TYPEC_MUX_USB = TCPC_MUX_USB_ENABLED, /* USB only */ - TYPEC_MUX_DP = TCPC_MUX_DP_ENABLED, /* DP only */ - TYPEC_MUX_DOCK = TCPC_MUX_USB_ENABLED | /* Both USB and DP */ - TCPC_MUX_DP_ENABLED, -}; - /** * struct tcpc_dev - Port configuration and callback functions * @config: Pointer to port configuration -- cgit v1.2.3 From 60a866685006bae0c3db20e4bae31887eb452ff1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 26 Jun 2018 06:49:08 -0300 Subject: gpio.h: fix location of gpio legacy documentation The location of this doc file was moved. Change its reference accordingly. Fixes: 7ee2c13080c9 ("Documentation: gpio: Move legacy documentation to driver-api") Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Jonathan Corbet --- include/linux/gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 91ed23468530..39745b8bdd65 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -14,7 +14,7 @@ #include -/* see Documentation/gpio/gpio-legacy.txt */ +/* see Documentation/driver-api/gpio/legacy.rst */ /* make these flag values available regardless of GPIO kconfig options */ #define GPIOF_DIR_OUT (0 << 0) -- cgit v1.2.3 From dc8fbeb0ffde1f2395449006019e2c89c177df50 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Fri, 22 Jun 2018 00:41:26 +0200 Subject: ARM: OMAP1: Get rid of Split the header file into two parts and move them to directories where they belong. Information on internal structure of FIQ buffer is moved to for ams-delta-serio driver use. Other information used by ams-delta board init file and FIQ code is made local to mach-omap1 root directory. Signed-off-by: Janusz Krzysztofik Acked-by: Dmitry Torokhov Signed-off-by: Tony Lindgren --- include/linux/platform_data/ams-delta-fiq.h | 62 +++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) create mode 100644 include/linux/platform_data/ams-delta-fiq.h (limited to 'include/linux') diff --git a/include/linux/platform_data/ams-delta-fiq.h b/include/linux/platform_data/ams-delta-fiq.h new file mode 100644 index 000000000000..dc0f835ea918 --- /dev/null +++ b/include/linux/platform_data/ams-delta-fiq.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * include/linux/platform_data/ams-delta-fiq.h + * + * Taken from the original Amstrad modifications to fiq.h + * + * Copyright (c) 2004 Amstrad Plc + * Copyright (c) 2006 Matt Callow + * Copyright (c) 2010 Janusz Krzysztofik + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __LINUX_PLATFORM_DATA_AMS_DELTA_FIQ_H +#define __LINUX_PLATFORM_DATA_AMS_DELTA_FIQ_H + +/* + * These are the offsets from the beginning of the fiq_buffer. They are put here + * since the buffer and header need to be accessed by drivers servicing devices + * which generate GPIO interrupts - e.g. keyboard, modem, hook switch. + */ +#define FIQ_MASK 0 +#define FIQ_STATE 1 +#define FIQ_KEYS_CNT 2 +#define FIQ_TAIL_OFFSET 3 +#define FIQ_HEAD_OFFSET 4 +#define FIQ_BUF_LEN 5 +#define FIQ_KEY 6 +#define FIQ_MISSED_KEYS 7 +#define FIQ_BUFFER_START 8 +#define FIQ_GPIO_INT_MASK 9 +#define FIQ_KEYS_HICNT 10 +#define FIQ_IRQ_PEND 11 +#define FIQ_SIR_CODE_L1 12 +#define IRQ_SIR_CODE_L2 13 + +#define FIQ_CNT_INT_00 14 +#define FIQ_CNT_INT_KEY 15 +#define FIQ_CNT_INT_MDM 16 +#define FIQ_CNT_INT_03 17 +#define FIQ_CNT_INT_HSW 18 +#define FIQ_CNT_INT_05 19 +#define FIQ_CNT_INT_06 20 +#define FIQ_CNT_INT_07 21 +#define FIQ_CNT_INT_08 22 +#define FIQ_CNT_INT_09 23 +#define FIQ_CNT_INT_10 24 +#define FIQ_CNT_INT_11 25 +#define FIQ_CNT_INT_12 26 +#define FIQ_CNT_INT_13 27 +#define FIQ_CNT_INT_14 28 +#define FIQ_CNT_INT_15 29 + +#define FIQ_CIRC_BUFF 30 /*Start of circular buffer */ + +#ifndef __ASSEMBLER__ +extern unsigned int fiq_buffer[]; +#endif + +#endif -- cgit v1.2.3 From 5f73861fae087df19f7337620da65c99e4260c72 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Fri, 22 Jun 2018 00:41:28 +0200 Subject: Input: ams_delta_serio: Get FIQ buffer from platform_data Instead of exporting the FIQ buffer symbol to be used in ams-delta-serio driver, pass it to the driver as platform_data. Signed-off-by: Janusz Krzysztofik Acked-by: Dmitry Torokhov Signed-off-by: Tony Lindgren --- include/linux/platform_data/ams-delta-fiq.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ams-delta-fiq.h b/include/linux/platform_data/ams-delta-fiq.h index dc0f835ea918..cf4589ccb720 100644 --- a/include/linux/platform_data/ams-delta-fiq.h +++ b/include/linux/platform_data/ams-delta-fiq.h @@ -55,8 +55,4 @@ #define FIQ_CIRC_BUFF 30 /*Start of circular buffer */ -#ifndef __ASSEMBLER__ -extern unsigned int fiq_buffer[]; -#endif - #endif -- cgit v1.2.3 From d082852f40de5cf55a7a689bf582fced39f5443e Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Fri, 22 Jun 2018 13:32:48 +0800 Subject: ARM: imx: enable bus auto clock gating function for i.mx6sll i.MX6SLL has HW bus auto clock gating function, enable it by default to save VDD_SOC_IN power, about 5% ~ 20% saved depends on different use cases. Signed-off-by: Anson Huang Acked-by: Lee Jones Signed-off-by: Shawn Guo --- include/linux/mfd/syscon/imx6q-iomuxc-gpr.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h index e06f5f79eaef..6c1ad160ed87 100644 --- a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h +++ b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h @@ -457,4 +457,7 @@ #define MCLK_DIR(x) (x == 1 ? IMX6UL_GPR1_SAI1_MCLK_DIR : x == 2 ? \ IMX6UL_GPR1_SAI2_MCLK_DIR : IMX6UL_GPR1_SAI3_MCLK_DIR) +/* For imx6sll iomux gpr register field define */ +#define IMX6SLL_GPR5_AFCG_X_BYPASS_MASK (0x1f << 11) + #endif /* __LINUX_IMX6Q_IOMUXC_GPR_H */ -- cgit v1.2.3 From 1cef1150ef40ec52f507436a14230cbc2623299c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Jun 2018 11:45:49 +0200 Subject: kthread, sched/core: Fix kthread_parkme() (again...) Gaurav reports that commit: 85f1abe0019f ("kthread, sched/wait: Fix kthread_parkme() completion issue") isn't working for him. Because of the following race: > controller Thread CPUHP Thread > takedown_cpu > kthread_park > kthread_parkme > Set KTHREAD_SHOULD_PARK > smpboot_thread_fn > set Task interruptible > > > wake_up_process > if (!(p->state & state)) > goto out; > > Kthread_parkme > SET TASK_PARKED > schedule > raw_spin_lock(&rq->lock) > ttwu_remote > waiting for __task_rq_lock > context_switch > > finish_lock_switch > > > > Case TASK_PARKED > kthread_park_complete > > > SET Running Furthermore, Oleg noticed that the whole scheduler TASK_PARKED handling is buggered because the TASK_DEAD thing is done with preemption disabled, the current code can still complete early on preemption :/ So basically revert that earlier fix and go with a variant of the alternative mentioned in the commit. Promote TASK_PARKED to special state to avoid the store-store issue on task->state leading to the WARN in kthread_unpark() -> __kthread_bind(). But in addition, add wait_task_inactive() to kthread_park() to ensure the task really is PARKED when we return from kthread_park(). This avoids the whole kthread still gets migrated nonsense -- although it would be really good to get this done differently. Reported-by: Gaurav Kohli Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 85f1abe0019f ("kthread, sched/wait: Fix kthread_parkme() completion issue") Signed-off-by: Ingo Molnar --- include/linux/kthread.h | 1 - include/linux/sched.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 2803264c512f..c1961761311d 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -62,7 +62,6 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); -void kthread_park_complete(struct task_struct *k); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/include/linux/sched.h b/include/linux/sched.h index 9256118bd40c..43731fe51c97 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -118,7 +118,7 @@ struct task_group; * the comment with set_special_state(). */ #define is_special_task_state(state) \ - ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD)) + ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) #define __set_current_state(state_value) \ do { \ -- cgit v1.2.3 From 9cf57731b63e37ed995b46690adc604891a9a28f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Jun 2018 10:52:03 +0200 Subject: watchdog/softlockup: Replace "watchdog/%u" threads with cpu_stop_work Oleg suggested to replace the "watchdog/%u" threads with cpu_stop_work. That removes one thread per CPU while at the same time fixes softlockup vs SCHED_DEADLINE. But more importantly, it does away with the single smpboot_update_cpumask_percpu_thread() user, which allows cleanups/shrinkage of the smpboot interface. Suggested-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + include/linux/nmi.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 8796ba387152..4cf06a64bc02 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -164,6 +164,7 @@ enum cpuhp_state { CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, + CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_ONLINE_DYN, diff --git a/include/linux/nmi.h b/include/linux/nmi.h index b8d868d23e79..80664bbeca43 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -33,10 +33,15 @@ extern int sysctl_hardlockup_all_cpu_backtrace; #define sysctl_hardlockup_all_cpu_backtrace 0 #endif /* !CONFIG_SMP */ +extern int lockup_detector_online_cpu(unsigned int cpu); +extern int lockup_detector_offline_cpu(unsigned int cpu); + #else /* CONFIG_LOCKUP_DETECTOR */ static inline void lockup_detector_init(void) { } static inline void lockup_detector_soft_poweroff(void) { } static inline void lockup_detector_cleanup(void) { } +#define lockup_detector_online_cpu NULL +#define lockup_detector_offline_cpu NULL #endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR -- cgit v1.2.3 From 167a88677b05d6a810f23b871cfb2b5db1808e60 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Jun 2018 10:53:01 +0200 Subject: smpboot: Remove cpumask from the API Now that the sole use of the whole smpboot_*cpumask() API is gone, remove it. Suggested-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/smpboot.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index c174844cf663..d0884b525001 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -25,8 +25,6 @@ struct smpboot_thread_data; * parked (cpu offline) * @unpark: Optional unpark function, called when the thread is * unparked (cpu online) - * @cpumask: Internal state. To update which threads are unparked, - * call smpboot_update_cpumask_percpu_thread(). * @selfparking: Thread is not parked by the park function. * @thread_comm: The base name of the thread */ @@ -40,23 +38,12 @@ struct smp_hotplug_thread { void (*cleanup)(unsigned int cpu, bool online); void (*park)(unsigned int cpu); void (*unpark)(unsigned int cpu); - cpumask_var_t cpumask; bool selfparking; const char *thread_comm; }; -int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread, - const struct cpumask *cpumask); - -static inline int -smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) -{ - return smpboot_register_percpu_thread_cpumask(plug_thread, - cpu_possible_mask); -} +int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread); void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread); -void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *); #endif -- cgit v1.2.3 From 55f036ca7e74b85e34958af3d22121c656796413 Mon Sep 17 00:00:00 2001 From: Peter Ziljstra Date: Fri, 15 Jun 2018 10:07:12 +0200 Subject: locking: WW mutex cleanup Make the WW mutex code more readable by adding comments, splitting up functions and pointing out that we're actually using the Wait-Die algorithm. Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Gustavo Padovan Cc: Maarten Lankhorst Cc: Sean Paul Cc: David Airlie Cc: Davidlohr Bueso Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Thomas Gleixner Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Greg Kroah-Hartman Cc: linux-doc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Co-authored-by: Thomas Hellstrom Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Hellstrom Acked-by: Ingo Molnar --- include/linux/ww_mutex.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 39fda195bf78..f82fce2229c8 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -6,7 +6,7 @@ * * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar * - * Wound/wait implementation: + * Wait/Die implementation: * Copyright (C) 2013 Canonical Ltd. * * This file contains the main data structure and API definitions. @@ -28,9 +28,9 @@ struct ww_class { struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp; - unsigned acquired; + unsigned int acquired; #ifdef CONFIG_DEBUG_MUTEXES - unsigned done_acquire; + unsigned int done_acquire; struct ww_class *ww_class; struct ww_mutex *contending_lock; #endif @@ -38,8 +38,8 @@ struct ww_acquire_ctx { struct lockdep_map dep_map; #endif #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH - unsigned deadlock_inject_interval; - unsigned deadlock_inject_countdown; + unsigned int deadlock_inject_interval; + unsigned int deadlock_inject_countdown; #endif }; @@ -102,7 +102,7 @@ static inline void ww_mutex_init(struct ww_mutex *lock, * * Context-based w/w mutex acquiring can be done in any order whatsoever within * a given lock class. Deadlocks will be detected and handled with the - * wait/wound logic. + * wait/die logic. * * Mixing of context-based w/w mutex acquiring and single w/w mutex locking can * result in undetected deadlocks and is so forbidden. Mixing different contexts @@ -195,13 +195,13 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) * Lock the w/w mutex exclusively for this task. * * Deadlocks within a given w/w class of locks are detected and handled with the - * wait/wound algorithm. If the lock isn't immediately avaiable this function + * wait/die algorithm. If the lock isn't immediately available this function * will either sleep until it is (wait case). Or it selects the current context - * for backing off by returning -EDEADLK (wound case). Trying to acquire the + * for backing off by returning -EDEADLK (die case). Trying to acquire the * same lock with the same context twice is also detected and signalled by * returning -EALREADY. Returns 0 if the mutex was successfully acquired. * - * In the wound case the caller must release all currently held w/w mutexes for + * In the die case the caller must release all currently held w/w mutexes for * the given context and then wait for this contending lock to be available by * calling ww_mutex_lock_slow. Alternatively callers can opt to not acquire this * lock and proceed with trying to acquire further w/w mutexes (e.g. when @@ -226,14 +226,14 @@ extern int /* __must_check */ ww_mutex_lock(struct ww_mutex *lock, struct ww_acq * Lock the w/w mutex exclusively for this task. * * Deadlocks within a given w/w class of locks are detected and handled with the - * wait/wound algorithm. If the lock isn't immediately avaiable this function + * wait/die algorithm. If the lock isn't immediately available this function * will either sleep until it is (wait case). Or it selects the current context - * for backing off by returning -EDEADLK (wound case). Trying to acquire the + * for backing off by returning -EDEADLK (die case). Trying to acquire the * same lock with the same context twice is also detected and signalled by * returning -EALREADY. Returns 0 if the mutex was successfully acquired. If a * signal arrives while waiting for the lock then this function returns -EINTR. * - * In the wound case the caller must release all currently held w/w mutexes for + * In the die case the caller must release all currently held w/w mutexes for * the given context and then wait for this contending lock to be available by * calling ww_mutex_lock_slow_interruptible. Alternatively callers can opt to * not acquire this lock and proceed with trying to acquire further w/w mutexes @@ -256,7 +256,7 @@ extern int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock, * @lock: the mutex to be acquired * @ctx: w/w acquire context * - * Acquires a w/w mutex with the given context after a wound case. This function + * Acquires a w/w mutex with the given context after a die case. This function * will sleep until the lock becomes available. * * The caller must have released all w/w mutexes already acquired with the @@ -290,7 +290,7 @@ ww_mutex_lock_slow(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) * @lock: the mutex to be acquired * @ctx: w/w acquire context * - * Acquires a w/w mutex with the given context after a wound case. This function + * Acquires a w/w mutex with the given context after a die case. This function * will sleep until the lock becomes available and returns 0 when the lock has * been acquired. If a signal arrives while waiting for the lock then this * function returns -EINTR. -- cgit v1.2.3 From 08295b3b5beec9aac0f7a9db86f0fc3792039da3 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Fri, 15 Jun 2018 10:17:38 +0200 Subject: locking: Implement an algorithm choice for Wound-Wait mutexes The current Wound-Wait mutex algorithm is actually not Wound-Wait but Wait-Die. Implement also Wound-Wait as a per-ww-class choice. Wound-Wait is, contrary to Wait-Die a preemptive algorithm and is known to generate fewer backoffs. Testing reveals that this is true if the number of simultaneous contending transactions is small. As the number of simultaneous contending threads increases, Wait-Wound becomes inferior to Wait-Die in terms of elapsed time. Possibly due to the larger number of held locks of sleeping transactions. Update documentation and callers. Timings using git://people.freedesktop.org/~thomash/ww_mutex_test tag patch-18-06-15 Each thread runs 100000 batches of lock / unlock 800 ww mutexes randomly chosen out of 100000. Four core Intel x86_64: Algorithm #threads Rollbacks time Wound-Wait 4 ~100 ~17s. Wait-Die 4 ~150000 ~19s. Wound-Wait 16 ~360000 ~109s. Wait-Die 16 ~450000 ~82s. Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Gustavo Padovan Cc: Maarten Lankhorst Cc: Sean Paul Cc: David Airlie Cc: Davidlohr Bueso Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Thomas Gleixner Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Greg Kroah-Hartman Cc: linux-doc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Co-authored-by: Peter Zijlstra Signed-off-by: Thomas Hellstrom Acked-by: Peter Zijlstra (Intel) Acked-by: Ingo Molnar --- include/linux/ww_mutex.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index f82fce2229c8..3af7c0e03be5 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -8,6 +8,8 @@ * * Wait/Die implementation: * Copyright (C) 2013 Canonical Ltd. + * Choice of algorithm: + * Copyright (C) 2018 WMWare Inc. * * This file contains the main data structure and API definitions. */ @@ -23,12 +25,15 @@ struct ww_class { struct lock_class_key mutex_key; const char *acquire_name; const char *mutex_name; + unsigned int is_wait_die; }; struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp; unsigned int acquired; + unsigned short wounded; + unsigned short is_wait_die; #ifdef CONFIG_DEBUG_MUTEXES unsigned int done_acquire; struct ww_class *ww_class; @@ -58,17 +63,21 @@ struct ww_mutex { # define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) #endif -#define __WW_CLASS_INITIALIZER(ww_class) \ +#define __WW_CLASS_INITIALIZER(ww_class, _is_wait_die) \ { .stamp = ATOMIC_LONG_INIT(0) \ , .acquire_name = #ww_class "_acquire" \ - , .mutex_name = #ww_class "_mutex" } + , .mutex_name = #ww_class "_mutex" \ + , .is_wait_die = _is_wait_die } #define __WW_MUTEX_INITIALIZER(lockname, class) \ { .base = __MUTEX_INITIALIZER(lockname.base) \ __WW_CLASS_MUTEX_INITIALIZER(lockname, class) } +#define DEFINE_WD_CLASS(classname) \ + struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 1) + #define DEFINE_WW_CLASS(classname) \ - struct ww_class classname = __WW_CLASS_INITIALIZER(classname) + struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 0) #define DEFINE_WW_MUTEX(mutexname, ww_class) \ struct ww_mutex mutexname = __WW_MUTEX_INITIALIZER(mutexname, ww_class) @@ -123,6 +132,8 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, ctx->task = current; ctx->stamp = atomic_long_inc_return_relaxed(&ww_class->stamp); ctx->acquired = 0; + ctx->wounded = false; + ctx->is_wait_die = ww_class->is_wait_die; #ifdef CONFIG_DEBUG_MUTEXES ctx->ww_class = ww_class; ctx->done_acquire = 0; -- cgit v1.2.3 From d03db2bc26f0e4a6849ad649a09c9c73fccdc656 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Thu, 21 Jun 2018 09:23:22 -0700 Subject: compiler-gcc.h: Add __attribute__((gnu_inline)) to all inline declarations Functions marked extern inline do not emit an externally visible function when the gnu89 C standard is used. Some KBUILD Makefiles overwrite KBUILD_CFLAGS. This is an issue for GCC 5.1+ users as without an explicit C standard specified, the default is gnu11. Since c99, the semantics of extern inline have changed such that an externally visible function is always emitted. This can lead to multiple definition errors of extern inline functions at link time of compilation units whose build files have removed an explicit C standard compiler flag for users of GCC 5.1+ or Clang. Suggested-by: Arnd Bergmann Suggested-by: H. Peter Anvin Suggested-by: Joe Perches Signed-off-by: Nick Desaulniers Acked-by: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@redhat.com Cc: akataria@vmware.com Cc: akpm@linux-foundation.org Cc: andrea.parri@amarulasolutions.com Cc: ard.biesheuvel@linaro.org Cc: aryabinin@virtuozzo.com Cc: astrachan@google.com Cc: boris.ostrovsky@oracle.com Cc: brijesh.singh@amd.com Cc: caoj.fnst@cn.fujitsu.com Cc: geert@linux-m68k.org Cc: ghackmann@google.com Cc: gregkh@linuxfoundation.org Cc: jan.kiszka@siemens.com Cc: jarkko.sakkinen@linux.intel.com Cc: jpoimboe@redhat.com Cc: keescook@google.com Cc: kirill.shutemov@linux.intel.com Cc: kstewart@linuxfoundation.org Cc: linux-efi@vger.kernel.org Cc: linux-kbuild@vger.kernel.org Cc: manojgupta@google.com Cc: mawilcox@microsoft.com Cc: michal.lkml@markovi.net Cc: mjg59@google.com Cc: mka@chromium.org Cc: pombredanne@nexb.com Cc: rientjes@google.com Cc: rostedt@goodmis.org Cc: sedat.dilek@gmail.com Cc: thomas.lendacky@amd.com Cc: tstellar@redhat.com Cc: tweek@google.com Cc: virtualization@lists.linux-foundation.org Cc: will.deacon@arm.com Cc: yamada.masahiro@socionext.com Link: http://lkml.kernel.org/r/20180621162324.36656-2-ndesaulniers@google.com Signed-off-by: Ingo Molnar --- include/linux/compiler-gcc.h | 29 ++++++++++++++++++++++------- 1 file changed, 22 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index fd282c7d3e5e..573f5a7d42d4 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -65,6 +65,18 @@ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) #endif +/* + * Feature detection for gnu_inline (gnu89 extern inline semantics). Either + * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics, + * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not + * defined so the gnu89 semantics are the default. + */ +#ifdef __GNUC_STDC_INLINE__ +# define __gnu_inline __attribute__((gnu_inline)) +#else +# define __gnu_inline +#endif + /* * Force always-inline if the user requests it so via the .config, * or if gcc is too old. @@ -72,19 +84,22 @@ * -Wunused-function. This turns out to avoid the need for complex #ifdef * directives. Suppress the warning in clang as well by using "unused" * function attribute, which is redundant but not harmful for gcc. + * Prefer gnu_inline, so that extern inline functions do not emit an + * externally visible function. This makes extern inline behave as per gnu89 + * semantics rather than c99. This prevents multiple symbol definition errors + * of extern inline functions at link time. + * A lot of inline functions can cause havoc with function tracing. */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) -#define inline inline __attribute__((always_inline,unused)) notrace -#define __inline__ __inline__ __attribute__((always_inline,unused)) notrace -#define __inline __inline __attribute__((always_inline,unused)) notrace +#define inline \ + inline __attribute__((always_inline, unused)) notrace __gnu_inline #else -/* A lot of inline functions can cause havoc with function tracing */ -#define inline inline __attribute__((unused)) notrace -#define __inline__ __inline__ __attribute__((unused)) notrace -#define __inline __inline __attribute__((unused)) notrace +#define inline inline __attribute__((unused)) notrace __gnu_inline #endif +#define __inline__ inline +#define __inline inline #define __always_inline inline __attribute__((always_inline)) #define noinline __attribute__((noinline)) -- cgit v1.2.3 From 71b38245acb05a38d2d861792bdd99cd9f6a0f78 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Tue, 5 Jun 2018 13:37:51 -0700 Subject: Drivers: hv: vmbus: Add comments on ring buffer signaling Add comments describing intricacies of Hyper-V ring buffer signaling code. This information is not in Hyper-V public documents, so include here to capture the knowledge for future coders. There are no code changes in this commit. Signed-off-by: Michael Kelley Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 3a3012f57be4..2330f08062c7 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -89,18 +89,33 @@ struct hv_ring_buffer { u32 interrupt_mask; /* - * Win8 uses some of the reserved bits to implement - * interrupt driven flow management. On the send side - * we can request that the receiver interrupt the sender - * when the ring transitions from being full to being able - * to handle a message of size "pending_send_sz". + * WS2012/Win8 and later versions of Hyper-V implement interrupt + * driven flow management. The feature bit feat_pending_send_sz + * is set by the host on the host->guest ring buffer, and by the + * guest on the guest->host ring buffer. * - * Add necessary state for this enhancement. + * The meaning of the feature bit is a bit complex in that it has + * semantics that apply to both ring buffers. If the guest sets + * the feature bit in the guest->host ring buffer, the guest is + * telling the host that: + * 1) It will set the pending_send_sz field in the guest->host ring + * buffer when it is waiting for space to become available, and + * 2) It will read the pending_send_sz field in the host->guest + * ring buffer and interrupt the host when it frees enough space + * + * Similarly, if the host sets the feature bit in the host->guest + * ring buffer, the host is telling the guest that: + * 1) It will set the pending_send_sz field in the host->guest ring + * buffer when it is waiting for space to become available, and + * 2) It will read the pending_send_sz field in the guest->host + * ring buffer and interrupt the guest when it frees enough space + * + * If either the guest or host does not set the feature bit that it + * owns, that guest or host must do polling if it encounters a full + * ring buffer, and not signal the other end with an interrupt. */ u32 pending_send_sz; - u32 reserved1[12]; - union { struct { u32 feat_pending_send_sz:1; -- cgit v1.2.3 From 418cc6ca06071e7b7d75c0d525d80a6f49a763d6 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 3 May 2018 16:25:52 +0200 Subject: dma-fence: Make ->wait callback optional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Almost everyone uses dma_fence_default_wait. v2: Also remove the BUG_ON(!ops->wait) (Chris). Reviewed-by: Christian König (v1) Signed-off-by: Daniel Vetter Cc: Chris Wilson Cc: Sumit Semwal Cc: Gustavo Padovan Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-5-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index c053d19e1e24..02dba8cd033d 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -191,11 +191,14 @@ struct dma_fence_ops { /** * @wait: * - * Custom wait implementation, or dma_fence_default_wait. + * Custom wait implementation, defaults to dma_fence_default_wait() if + * not set. * - * Must not be NULL, set to dma_fence_default_wait for default implementation. - * the dma_fence_default_wait implementation should work for any fence, as long - * as enable_signaling works correctly. + * The dma_fence_default_wait implementation should work for any fence, as long + * as @enable_signaling works correctly. This hook allows drivers to + * have an optimized version for the case where a process context is + * already available, e.g. if @enable_signaling for the general case + * needs to set up a worker thread. * * Must return -ERESTARTSYS if the wait is intr = true and the wait was * interrupted, and remaining jiffies if fence has signaled, or 0 if wait @@ -203,7 +206,7 @@ struct dma_fence_ops { * which should be treated as if the fence is signaled. For example a hardware * lockup could be reported like that. * - * This callback is mandatory. + * This callback is optional. */ signed long (*wait)(struct dma_fence *fence, bool intr, signed long timeout); -- cgit v1.2.3 From 63453b59e41173241c4efe9335815f6432fa8586 Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Wed, 20 Jun 2018 10:51:53 +0200 Subject: i2c: smbus: add unlocked __i2c_smbus_xfer variant Removes all locking from i2c_smbus_xfer and renames it to __i2c_smbus_xfer, then adds a new i2c_smbus_xfer function that simply grabs the lock while calling the unlocked variant. This is not perfectly equivalent, since i2c_smbus_xfer was callable from atomic/irq context if you happened to end up emulating SMBus with an I2C transfer, and that is no longer the case with this patch. It is unknown (to me) if anything depends on that quirk, but it seems fragile enough to simply break those cases and require them to call i2c_transfer directly instead. While at it, for consistency rename the 2nd to last argument (size) of the i2c_smbus_xfer declaration to protocol and remove the surplus extern marker. Signed-off-by: Peter Rosin Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 254cd34eeae2..465afb092fa7 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -140,9 +140,14 @@ extern int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, and probably just as fast. Note that we use i2c_adapter here, because you do not need a specific smbus adapter to call this function. */ -extern s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, - unsigned short flags, char read_write, u8 command, - int size, union i2c_smbus_data *data); +s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, + unsigned short flags, char read_write, u8 command, + int protocol, union i2c_smbus_data *data); + +/* Unlocked flavor */ +s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, + unsigned short flags, char read_write, u8 command, + int protocol, union i2c_smbus_data *data); /* Now follow the 'nice' access routines. These also document the calling conventions of i2c_smbus_xfer. */ -- cgit v1.2.3 From 5ccba64a560fa6ca06008d4001f5d46ebeb34b41 Mon Sep 17 00:00:00 2001 From: Yisheng Xie Date: Fri, 2 Feb 2018 10:14:49 +0800 Subject: ftrace: Nuke clear_ftrace_function clear_ftrace_function is not used outside of ftrace.c and is not help to use a function, so nuke it per Steve's suggestion. Link: http://lkml.kernel.org/r/1517537689-34947-1-git-send-email-xieyisheng1@huawei.com Suggested-by: Steven Rostedt Signed-off-by: Yisheng Xie Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 8154f4920fcb..ebb77674be90 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -223,7 +223,6 @@ extern enum ftrace_tracing_type_t ftrace_tracing_type; */ int register_ftrace_function(struct ftrace_ops *ops); int unregister_ftrace_function(struct ftrace_ops *ops); -void clear_ftrace_function(void); extern void ftrace_stub(unsigned long a0, unsigned long a1, struct ftrace_ops *op, struct pt_regs *regs); @@ -239,7 +238,6 @@ static inline int ftrace_nr_registered_ops(void) { return 0; } -static inline void clear_ftrace_function(void) { } static inline void ftrace_kill(void) { } static inline void ftrace_free_init_mem(void) { } static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } -- cgit v1.2.3 From 077772468ec141b22e1e7c0c58bc09e2f9dc8762 Mon Sep 17 00:00:00 2001 From: Wang Dongsheng Date: Sun, 1 Jul 2018 23:15:46 -0700 Subject: net: phy: marvell: change default m88e1510 LED configuration The m88e1121 LED default configuration does not apply m88e151x. So add a function to relpace m88e1121 LED configuration. Signed-off-by: Wang Dongsheng Signed-off-by: David S. Miller --- include/linux/marvell_phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 4f5f8c21e283..1eb6f244588d 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -27,6 +27,8 @@ */ #define MARVELL_PHY_ID_88E6390 0x01410f90 +#define MARVELL_PHY_FAMILY_ID(id) ((id) >> 4) + /* struct phy_device dev_flags definitions */ #define MARVELL_PHY_M1145_FLAGS_RESISTANCE 0x00000001 #define MARVELL_PHY_M1118_DNS323_LEDS 0x00000002 -- cgit v1.2.3 From 8a9c58d28d0f66569737a3295116710ed24573cd Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 2 Jul 2018 18:21:12 +0800 Subject: sctp: add support for dscp and flowlabel per transport Like some other per transport params, flowlabel and dscp are added in transport, asoc and sctp_sock. By default, transport sets its value from asoc's, and asoc does it from sctp_sock. flowlabel only works for ipv6 transport. Other than that they need to be passed down in sctp_xmit, flow4/6 also needs to set them before looking up route in get_dst. Note that it uses '& 0x100000' to check if flowlabel is set and '& 0x1' (tos 1st bit is unused) to check if dscp is set by users, so that they could be set to 0 by sockopt in next patch. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index b36c76635f18..83d94341e003 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -801,4 +801,11 @@ struct sctp_strreset_resptsn { __be32 receivers_next_tsn; }; +enum { + SCTP_DSCP_SET_MASK = 0x1, + SCTP_DSCP_VAL_MASK = 0xfc, + SCTP_FLOWLABEL_SET_MASK = 0x100000, + SCTP_FLOWLABEL_VAL_MASK = 0xfffff +}; + #endif /* __LINUX_SCTP_H__ */ -- cgit v1.2.3 From f6ad8c1bcdf014272d08c55b9469536952a0a771 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 2 Jul 2018 16:12:45 +0100 Subject: net: core: trivial netif_receive_skb_list() entry point Just calls netif_receive_skb() in a loop. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 64480a0f2c16..f67258f057ca 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3477,6 +3477,7 @@ int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); +void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); -- cgit v1.2.3 From 4ce0017a373afaaa9ef17614d8fa4f6fde261d18 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 2 Jul 2018 16:13:40 +0100 Subject: net: core: another layer of lists, around PF_MEMALLOC skb handling First example of a layer splitting the list (rather than merely taking individual packets off it). Involves new list.h function, list_cut_before(), like list_cut_position() but cuts on the other side of the given entry. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/list.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 4b129df4d46b..de04cc5ed536 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -285,6 +285,36 @@ static inline void list_cut_position(struct list_head *list, __list_cut_position(list, head, entry); } +/** + * list_cut_before - cut a list into two, before given entry + * @list: a new list to add all removed entries + * @head: a list with entries + * @entry: an entry within head, could be the head itself + * + * This helper moves the initial part of @head, up to but + * excluding @entry, from @head to @list. You should pass + * in @entry an element you know is on @head. @list should + * be an empty list or a list you do not care about losing + * its data. + * If @entry == @head, all entries on @head are moved to + * @list. + */ +static inline void list_cut_before(struct list_head *list, + struct list_head *head, + struct list_head *entry) +{ + if (head->next == entry) { + INIT_LIST_HEAD(list); + return; + } + list->next = head->next; + list->next->prev = list; + list->prev = entry->prev; + list->prev->next = list; + head->next = entry; + entry->prev = head; +} + static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) -- cgit v1.2.3 From 17266ee939849cb095ed7dd9edbec4162172226b Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 2 Jul 2018 16:14:12 +0100 Subject: net: ipv4: listified version of ip_rcv Also involved adding a way to run a netfilter hook over a list of packets. Rather than attempting to make netfilter know about lists (which would be a major project in itself) we just let it call the regular okfn (in this case ip_rcv_finish()) for any packets it steals, and have it give us back a list of packets it's synchronously accepted (which normally NF_HOOK would automatically call okfn() on, but we want to be able to potentially pass the list to a listified version of okfn().) The netfilter hooks themselves are indirect calls that still happen per- packet (see nf_hook_entry_hookfn()), but again, changing that can be left for future work. There is potential for out-of-order receives if the netfilter hook ends up synchronously stealing packets, as they will be processed before any accepts earlier in the list. However, it was already possible for an asynchronous accept to cause out-of-order receives, so presumably this is considered OK. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ include/linux/netfilter.h | 22 ++++++++++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f67258f057ca..c1ef749b6f9f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2297,6 +2297,9 @@ struct packet_type { struct net_device *, struct packet_type *, struct net_device *); + void (*list_func) (struct list_head *, + struct packet_type *, + struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); void *af_packet_priv; diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index dd2052f0efb7..5a5e0a2ab2a3 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -288,6 +288,20 @@ NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct return ret; } +static inline void +NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct list_head *head, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) +{ + struct sk_buff *skb, *next; + + list_for_each_entry_safe(skb, next, head, list) { + int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn); + if (ret != 1) + list_del(&skb->list); + } +} + /* Call setsockopt() */ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, unsigned int len); @@ -369,6 +383,14 @@ NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, return okfn(net, sk, skb); } +static inline void +NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct list_head *head, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) +{ + /* nothing to do */ +} + static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, -- cgit v1.2.3 From 06635894a371be69373fcb5484f559284c8d1ac3 Mon Sep 17 00:00:00 2001 From: Sameer Nanda Date: Wed, 2 May 2018 17:44:16 +0200 Subject: mfd: cros_ec: Add USBPD charger commands and struct definitions. The USBPD charger driver gets information from the ChromeOS EC, this patch adds the USBPD charger definitions needed by this driver. Signed-off-by: Sameer Nanda Signed-off-by: Enric Balletbo i Serra Signed-off-by: Lee Jones --- include/linux/mfd/cros_ec_commands.h | 132 +++++++++++++++++++++++++++++++++-- 1 file changed, 128 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index f2edd9969b40..0d926492ac3a 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -2593,14 +2593,18 @@ struct ec_params_current_limit { } __packed; /* - * Set maximum external power current. + * Set maximum external voltage / current. */ -#define EC_CMD_EXT_POWER_CURRENT_LIMIT 0xa2 +#define EC_CMD_EXTERNAL_POWER_LIMIT 0x00A2 -struct ec_params_ext_power_current_limit { - uint32_t limit; /* in mA */ +/* Command v0 is used only on Spring and is obsolete + unsupported */ +struct ec_params_external_power_limit_v1 { + uint16_t current_lim; /* in mA, or EC_POWER_LIMIT_NONE to clear limit */ + uint16_t voltage_lim; /* in mV, or EC_POWER_LIMIT_NONE to clear limit */ } __packed; +#define EC_POWER_LIMIT_NONE 0xffff + /* Inform the EC when entering a sleep state */ #define EC_CMD_HOST_SLEEP_EVENT 0xa9 @@ -2974,6 +2978,12 @@ enum usb_chg_type { USB_CHG_TYPE_VBUS, USB_CHG_TYPE_UNKNOWN, }; +enum usb_power_roles { + USB_PD_PORT_POWER_DISCONNECTED, + USB_PD_PORT_POWER_SOURCE, + USB_PD_PORT_POWER_SINK, + USB_PD_PORT_POWER_SINK_NOT_CHARGING, +}; struct usb_chg_measures { uint16_t voltage_max; @@ -2991,6 +3001,120 @@ struct ec_response_usb_pd_power_info { uint32_t max_power; } __packed; +struct ec_params_usb_pd_info_request { + uint8_t port; +} __packed; + +/* Read USB-PD Device discovery info */ +#define EC_CMD_USB_PD_DISCOVERY 0x0113 +struct ec_params_usb_pd_discovery_entry { + uint16_t vid; /* USB-IF VID */ + uint16_t pid; /* USB-IF PID */ + uint8_t ptype; /* product type (hub,periph,cable,ama) */ +} __packed; + +/* Override default charge behavior */ +#define EC_CMD_PD_CHARGE_PORT_OVERRIDE 0x0114 + +/* Negative port parameters have special meaning */ +enum usb_pd_override_ports { + OVERRIDE_DONT_CHARGE = -2, + OVERRIDE_OFF = -1, + /* [0, CONFIG_USB_PD_PORT_COUNT): Port# */ +}; + +struct ec_params_charge_port_override { + int16_t override_port; /* Override port# */ +} __packed; + +/* Read (and delete) one entry of PD event log */ +#define EC_CMD_PD_GET_LOG_ENTRY 0x0115 + +struct ec_response_pd_log { + uint32_t timestamp; /* relative timestamp in milliseconds */ + uint8_t type; /* event type : see PD_EVENT_xx below */ + uint8_t size_port; /* [7:5] port number [4:0] payload size in bytes */ + uint16_t data; /* type-defined data payload */ + uint8_t payload[0]; /* optional additional data payload: 0..16 bytes */ +} __packed; + +/* The timestamp is the microsecond counter shifted to get about a ms. */ +#define PD_LOG_TIMESTAMP_SHIFT 10 /* 1 LSB = 1024us */ + +#define PD_LOG_SIZE_MASK 0x1f +#define PD_LOG_PORT_MASK 0xe0 +#define PD_LOG_PORT_SHIFT 5 +#define PD_LOG_PORT_SIZE(port, size) (((port) << PD_LOG_PORT_SHIFT) | \ + ((size) & PD_LOG_SIZE_MASK)) +#define PD_LOG_PORT(size_port) ((size_port) >> PD_LOG_PORT_SHIFT) +#define PD_LOG_SIZE(size_port) ((size_port) & PD_LOG_SIZE_MASK) + +/* PD event log : entry types */ +/* PD MCU events */ +#define PD_EVENT_MCU_BASE 0x00 +#define PD_EVENT_MCU_CHARGE (PD_EVENT_MCU_BASE+0) +#define PD_EVENT_MCU_CONNECT (PD_EVENT_MCU_BASE+1) +/* Reserved for custom board event */ +#define PD_EVENT_MCU_BOARD_CUSTOM (PD_EVENT_MCU_BASE+2) +/* PD generic accessory events */ +#define PD_EVENT_ACC_BASE 0x20 +#define PD_EVENT_ACC_RW_FAIL (PD_EVENT_ACC_BASE+0) +#define PD_EVENT_ACC_RW_ERASE (PD_EVENT_ACC_BASE+1) +/* PD power supply events */ +#define PD_EVENT_PS_BASE 0x40 +#define PD_EVENT_PS_FAULT (PD_EVENT_PS_BASE+0) +/* PD video dongles events */ +#define PD_EVENT_VIDEO_BASE 0x60 +#define PD_EVENT_VIDEO_DP_MODE (PD_EVENT_VIDEO_BASE+0) +#define PD_EVENT_VIDEO_CODEC (PD_EVENT_VIDEO_BASE+1) +/* Returned in the "type" field, when there is no entry available */ +#define PD_EVENT_NO_ENTRY 0xff + +/* + * PD_EVENT_MCU_CHARGE event definition : + * the payload is "struct usb_chg_measures" + * the data field contains the port state flags as defined below : + */ +/* Port partner is a dual role device */ +#define CHARGE_FLAGS_DUAL_ROLE BIT(15) +/* Port is the pending override port */ +#define CHARGE_FLAGS_DELAYED_OVERRIDE BIT(14) +/* Port is the override port */ +#define CHARGE_FLAGS_OVERRIDE BIT(13) +/* Charger type */ +#define CHARGE_FLAGS_TYPE_SHIFT 3 +#define CHARGE_FLAGS_TYPE_MASK (0xf << CHARGE_FLAGS_TYPE_SHIFT) +/* Power delivery role */ +#define CHARGE_FLAGS_ROLE_MASK (7 << 0) + +/* + * PD_EVENT_PS_FAULT data field flags definition : + */ +#define PS_FAULT_OCP 1 +#define PS_FAULT_FAST_OCP 2 +#define PS_FAULT_OVP 3 +#define PS_FAULT_DISCH 4 + +/* + * PD_EVENT_VIDEO_CODEC payload is "struct mcdp_info". + */ +struct mcdp_version { + uint8_t major; + uint8_t minor; + uint16_t build; +} __packed; + +struct mcdp_info { + uint8_t family[2]; + uint8_t chipid[2]; + struct mcdp_version irom; + struct mcdp_version fw; +} __packed; + +/* struct mcdp_info field decoding */ +#define MCDP_CHIPID(chipid) ((chipid[0] << 8) | chipid[1]) +#define MCDP_FAMILY(family) ((family[0] << 8) | family[1]) + /* Get info about USB-C SS muxes */ #define EC_CMD_USB_PD_MUX_INFO 0x11a -- cgit v1.2.3 From 7494de0454af50215bc46c93c83b88a32ca39fab Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 11 Jun 2018 13:58:38 +0200 Subject: mfd: da9063: Replace regmap_add_irq_chip with devm counterpart Use devm_regmap_add_irq_chip() instead of plain regmap_add_irq_chip(), which removes the need for da9063_irq_exit() altogether and also fixes a bug in da9063_device_init() where the da9063_irq_exit() was not called in a failpath. Signed-off-by: Marek Vasut Signed-off-by: Lee Jones --- include/linux/mfd/da9063/core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index f3ae65db4c86..9ab7049977aa 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -95,6 +95,5 @@ int da9063_device_init(struct da9063 *da9063, unsigned int irq); int da9063_irq_init(struct da9063 *da9063); void da9063_device_exit(struct da9063 *da9063); -void da9063_irq_exit(struct da9063 *da9063); #endif /* __MFD_DA9063_CORE_H__ */ -- cgit v1.2.3 From af8df945876c027969fafefb9ec07b79cfadb16f Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 11 Jun 2018 13:58:39 +0200 Subject: mfd: da9063: Replace mfd_add_devices with devm counterpart Use devm_mfd_add_devices() instead of plain mfd_add_devices(), which removes the need for da9063_device_exit() altogether and also for the .remove callback in da9063-i2c.c . Signed-off-by: Marek Vasut Signed-off-by: Lee Jones --- include/linux/mfd/da9063/core.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index 9ab7049977aa..8e6684d884e0 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -94,6 +94,4 @@ struct da9063 { int da9063_device_init(struct da9063 *da9063, unsigned int irq); int da9063_irq_init(struct da9063 *da9063); -void da9063_device_exit(struct da9063 *da9063); - #endif /* __MFD_DA9063_CORE_H__ */ -- cgit v1.2.3 From c727eea92c9232169c0d375309718fb398aaec67 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 11 Jun 2018 13:58:43 +0200 Subject: mfd: da9063: Replace DA9063_NUM_IRQ with ARRAY_SIZE Replace DA9063_NUM_IRQ macro which is not used anywhere with plain ARRAY_SIZE(). Signed-off-by: Marek Vasut Reviewed-by: Geert Uytterhoeven Signed-off-by: Lee Jones --- include/linux/mfd/da9063/core.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index 8e6684d884e0..260cd5834861 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -72,9 +72,6 @@ enum da9063_irqs { DA9063_IRQ_GPI15, }; -#define DA9063_IRQ_BASE_OFFSET 0 -#define DA9063_NUM_IRQ (DA9063_IRQ_GPI15 + 1 - DA9063_IRQ_BASE_OFFSET) - struct da9063 { /* Device */ struct device *dev; -- cgit v1.2.3 From df7878f9dc77a9f630893811f0401bc021df4fbf Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 11 Jun 2018 13:58:44 +0200 Subject: mfd: da9063: Rename PMIC_DA9063 to PMIC_CHIP_ID_DA9063 The PMIC_DA9063 is a complete misnomer, it denotes the value of the DA9063 chip ID register, so rename it as such. It is also the value of chip ID register of DA9063L though, so drop the enum as all the DA9063 "models" share the same chip ID and thus the distinction will have to be made using DT or otherwise. Signed-off-by: Marek Vasut Acked-by: Mark Brown Reviewed-by: Geert Uytterhoeven Acked-by: Steve Twiss Signed-off-by: Lee Jones --- include/linux/mfd/da9063/core.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index 260cd5834861..e015b065db7e 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -29,9 +29,7 @@ #define DA9063_DRVNAME_RTC "da9063-rtc" #define DA9063_DRVNAME_VIBRATION "da9063-vibration" -enum da9063_models { - PMIC_DA9063 = 0x61, -}; +#define PMIC_CHIP_ID_DA9063 0x61 enum da9063_variant_codes { PMIC_DA9063_AD = 0x3, -- cgit v1.2.3 From 492510dd7d39794e809d8218a2839e857c101ce5 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 11 Jun 2018 13:58:45 +0200 Subject: mfd: da9063: Replace model with type The model number stored in the struct da9063 is the same for all variants of the da9063 since it is the chip ID, which is always the same. Replace that with a separate identifier instead, which allows us to discern the DA9063 variants by setting the type based on either DT match or otherwise. Signed-off-by: Marek Vasut Acked-by: Mark Brown Reviewed-by: Geert Uytterhoeven Signed-off-by: Lee Jones --- include/linux/mfd/da9063/core.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index e015b065db7e..9e36097adc42 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -31,6 +31,10 @@ #define PMIC_CHIP_ID_DA9063 0x61 +enum da9063_type { + PMIC_TYPE_DA9063 = 0, +}; + enum da9063_variant_codes { PMIC_DA9063_AD = 0x3, PMIC_DA9063_BB = 0x5, @@ -73,7 +77,7 @@ enum da9063_irqs { struct da9063 { /* Device */ struct device *dev; - unsigned short model; + enum da9063_type type; unsigned char variant_code; unsigned int flags; -- cgit v1.2.3 From 8ae81814cca96a4b7f66dcf1aeb904a0a077f7f4 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 11 Jun 2018 13:58:46 +0200 Subject: mfd: da9063: Add DA9063L type Add type for DA9063L, which is a reduced variant of the DA9063 without RTC block and with less regulators. Signed-off-by: Marek Vasut Reviewed-by: Geert Uytterhoeven Acked-by: Steve Twiss Signed-off-by: Lee Jones --- include/linux/mfd/da9063/core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index 9e36097adc42..71b09154e2db 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -33,6 +33,7 @@ enum da9063_type { PMIC_TYPE_DA9063 = 0, + PMIC_TYPE_DA9063L, }; enum da9063_variant_codes { -- cgit v1.2.3 From 30000d80b506819ae5dae926f636412a34594ed6 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 3 May 2018 16:15:17 +0200 Subject: backlight: Remove obsolete comment for ->state Jani spotted this when reviewing my earlier patch to remove the driver internal usage of this field in: Commit 3cf91adaa594 ("backlight: Nuke BL_CORE_DRIVER1") Signed-off-by: Daniel Vetter Acked-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/backlight.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 7fbf0539e14a..0b5897446dca 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -79,7 +79,6 @@ struct backlight_properties { /* Backlight type */ enum backlight_type type; /* Flags used to signal drivers of state changes */ - /* Upper 4 bits are reserved for driver internal use */ unsigned int state; #define BL_CORE_SUSPENDED (1 << 0) /* backlight is suspended */ -- cgit v1.2.3 From 25db26a91364db00f5a30da2fea8e9afe14a163c Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Tue, 3 Jul 2018 15:42:53 -0700 Subject: net/sched: Introduce the ETF Qdisc The ETF (Earliest TxTime First) qdisc uses the information added earlier in this series (the socket option SO_TXTIME and the new role of sk_buff->tstamp) to schedule packets transmission based on absolute time. For some workloads, just bandwidth enforcement is not enough, and precise control of the transmission of packets is necessary. Example: $ tc qdisc replace dev enp2s0 parent root handle 100 mqprio num_tc 3 \ map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 0 $ tc qdisc add dev enp2s0 parent 100:1 etf delta 100000 \ clockid CLOCK_TAI In this example, the Qdisc will provide SW best-effort for the control of the transmission time to the network adapter, the time stamp in the socket will be in reference to the clockid CLOCK_TAI and packets will leave the qdisc "delta" (100000) nanoseconds before its transmission time. The ETF qdisc will buffer packets sorted by their txtime. It will drop packets on enqueue() if their skbuff clockid does not match the clock reference of the Qdisc. Moreover, on dequeue(), a packet will be dropped if it expires while being enqueued. The qdisc also supports the SO_TXTIME deadline mode. For this mode, it will dequeue a packet as soon as possible and change the skb timestamp to 'now' during etf_dequeue(). Note that both the qdisc's and the SO_TXTIME ABIs allow for a clockid to be configured, but it's been decided that usage of CLOCK_TAI should be enforced until we decide to allow for other clockids to be used. The rationale here is that PTP times are usually in the TAI scale, thus no other clocks should be necessary. For now, the qdisc will return EINVAL if any clocks other than CLOCK_TAI are used. Signed-off-by: Jesus Sanchez-Palencia Signed-off-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c1ef749b6f9f..f06ee8f91e74 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -798,6 +798,7 @@ enum tc_setup_type { TC_SETUP_QDISC_RED, TC_SETUP_QDISC_PRIO, TC_SETUP_QDISC_MQ, + TC_SETUP_QDISC_ETF, }; /* These structures hold the attributes of bpf state that are being passed -- cgit v1.2.3 From b5cb15d9372abc9adc4e844c0c1bf594ca6a7695 Mon Sep 17 00:00:00 2001 From: Chris von Recklinghausen Date: Tue, 3 Jul 2018 15:43:08 -0400 Subject: usercopy: Allow boot cmdline disabling of hardening Enabling HARDENED_USERCOPY may cause measurable regressions in networking performance: up to 8% under UDP flood. I ran a small packet UDP flood using pktgen vs. a host b2b connected. On the receiver side the UDP packets are processed by a simple user space process that just reads and drops them: https://github.com/netoptimizer/network-testing/blob/master/src/udp_sink.c Not very useful from a functional PoV, but it helps to pin-point bottlenecks in the networking stack. When running a kernel with CONFIG_HARDENED_USERCOPY=y, I see a 5-8% regression in the receive tput, compared to the same kernel without this option enabled. With CONFIG_HARDENED_USERCOPY=y, perf shows ~6% of CPU time spent cumulatively in __check_object_size (~4%) and __virt_addr_valid (~2%). The call-chain is: __GI___libc_recvfrom entry_SYSCALL_64_after_hwframe do_syscall_64 __x64_sys_recvfrom __sys_recvfrom inet_recvmsg udp_recvmsg __check_object_size udp_recvmsg() actually calls copy_to_iter() (inlined) and the latters calls check_copy_size() (again, inlined). A generic distro may want to enable HARDENED_USERCOPY in their default kernel config, but at the same time, such distro may want to be able to avoid the performance penalties in with the default configuration and disable the stricter check on a per-boot basis. This change adds a boot parameter that conditionally disables HARDENED_USERCOPY via "hardened_usercopy=off". Signed-off-by: Chris von Recklinghausen Signed-off-by: Kees Cook --- include/linux/jump_label.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index b46b541c67c4..1a0b6f17a5d6 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -299,12 +299,18 @@ struct static_key_false { #define DEFINE_STATIC_KEY_TRUE(name) \ struct static_key_true name = STATIC_KEY_TRUE_INIT +#define DEFINE_STATIC_KEY_TRUE_RO(name) \ + struct static_key_true name __ro_after_init = STATIC_KEY_TRUE_INIT + #define DECLARE_STATIC_KEY_TRUE(name) \ extern struct static_key_true name #define DEFINE_STATIC_KEY_FALSE(name) \ struct static_key_false name = STATIC_KEY_FALSE_INIT +#define DEFINE_STATIC_KEY_FALSE_RO(name) \ + struct static_key_false name __ro_after_init = STATIC_KEY_FALSE_INIT + #define DECLARE_STATIC_KEY_FALSE(name) \ extern struct static_key_false name -- cgit v1.2.3 From 4d4fb5dc988a36307711be292bde6e39b8bdbceb Mon Sep 17 00:00:00 2001 From: Yonatan Cohen Date: Tue, 19 Jun 2018 08:47:22 +0300 Subject: net/mlx5: Limit scope of dump_fill_mkey function mlx5_core_dump_fill_mkey() is going to be used in next patch in IB and doesn't need to be visible to whole mlx5_core. Move that command to mlx5_ib. Signed-off-by: Yonatan Cohen Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 80cbb7fdce4a..1cb1c0317b77 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1067,8 +1067,6 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey); int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, u32 *out, int outlen); -int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *_mkey, - u32 *mkey); int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn); int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn); int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, -- cgit v1.2.3 From b183ee27f5fb07c8428e2fe45d5f35dac611c45d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 19 Jun 2018 08:47:23 +0300 Subject: net/mlx5: Add hardware definitions for dump_fill_mkey MLX5 IB HCA offers the memory key, dump_fill_mkey to boost performance by forcing local HCA operations to skip the PCI bus access, This patch adds needed hardware definitions. Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index deb3a459a22e..1853e7fd6924 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -885,7 +885,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_eq_sz[0x8]; u8 reserved_at_e8[0x2]; u8 log_max_mkey[0x6]; - u8 reserved_at_f0[0xc]; + u8 reserved_at_f0[0x8]; + u8 dump_fill_mkey[0x1]; + u8 reserved_at_f9[0x3]; u8 log_max_eq[0x4]; u8 max_indirection[0x8]; -- cgit v1.2.3 From 7a872b6fb7fdc4213e9bb4e1c83a65e6b8af7ebd Mon Sep 17 00:00:00 2001 From: Keerthy Date: Wed, 4 Jul 2018 20:19:06 -0700 Subject: soc: ti: wkup_m3_ipc: Add rtc_only with ddr in self refresh mode support Adds rtc_only support. This needs resume function to shutdown and reboot the m3. Signed-off-by: Keerthy Signed-off-by: Santosh Shilimkar --- include/linux/wkup_m3_ipc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index d6ba7d39a62f..d639df15e8ba 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -40,6 +40,7 @@ struct wkup_m3_ipc { struct mbox_chan *mbox; struct wkup_m3_ipc_ops *ops; + int is_rtc_only; }; struct wkup_m3_ipc_ops { @@ -48,8 +49,10 @@ struct wkup_m3_ipc_ops { int (*prepare_low_power)(struct wkup_m3_ipc *m3_ipc, int state); int (*finish_low_power)(struct wkup_m3_ipc *m3_ipc); int (*request_pm_status)(struct wkup_m3_ipc *m3_ipc); + void (*set_rtc_only)(struct wkup_m3_ipc *m3_ipc); }; struct wkup_m3_ipc *wkup_m3_ipc_get(void); void wkup_m3_ipc_put(struct wkup_m3_ipc *m3_ipc); +void wkup_m3_set_rtc_only_mode(void); #endif /* _LINUX_WKUP_M3_IPC_H */ -- cgit v1.2.3 From ec93b62fec9c7138d2b75334d192ecc12376f885 Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Wed, 4 Jul 2018 20:19:06 -0700 Subject: soc: ti: wkup_m3_ipc: Add wkup_m3_request_wake_src Add wkup_m3_request_wake_src to allow users to get the name of the wakeup source after a DeepSleep or Standby transition. Signed-off-by: Dave Gerlach Signed-off-by: Keerthy Signed-off-by: Santosh Shilimkar --- include/linux/wkup_m3_ipc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index d639df15e8ba..e497e621dbb7 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -43,12 +43,18 @@ struct wkup_m3_ipc { int is_rtc_only; }; +struct wkup_m3_wakeup_src { + int irq_nr; + char src[10]; +}; + struct wkup_m3_ipc_ops { void (*set_mem_type)(struct wkup_m3_ipc *m3_ipc, int mem_type); void (*set_resume_address)(struct wkup_m3_ipc *m3_ipc, void *addr); int (*prepare_low_power)(struct wkup_m3_ipc *m3_ipc, int state); int (*finish_low_power)(struct wkup_m3_ipc *m3_ipc); int (*request_pm_status)(struct wkup_m3_ipc *m3_ipc); + const char *(*request_wake_src)(struct wkup_m3_ipc *m3_ipc); void (*set_rtc_only)(struct wkup_m3_ipc *m3_ipc); }; -- cgit v1.2.3 From 6312fe77751f57d4fa2b28abeef84c6a95c28136 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Thu, 5 Jul 2018 14:34:32 +0800 Subject: net: limit each hash list length to MAX_GRO_SKBS After commit 07d78363dcff ("net: Convert NAPI gro list into a small hash table.")' there is 8 hash buckets, which allows more flows to be held for merging. but MAX_GRO_SKBS, the total held skb for merging, is 8 skb still, limit the hash table performance. keep MAX_GRO_SKBS as 8 skb, but limit each hash list length to 8 skb, not the total 8 skb Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f06ee8f91e74..b683971e500d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -302,6 +302,11 @@ struct netdev_boot_setup { int __init netdev_boot_setup(char *str); +struct gro_list { + struct list_head list; + int count; +}; + /* * Structure for NAPI scheduling similar to tasklet but with weighting */ @@ -323,7 +328,7 @@ struct napi_struct { int poll_owner; #endif struct net_device *dev; - struct list_head gro_hash[GRO_HASH_BUCKETS]; + struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; struct hrtimer timer; struct list_head dev_list; -- cgit v1.2.3 From 0380cf7dbaca75c524e34b30979f0806124fa8e6 Mon Sep 17 00:00:00 2001 From: pascal paillet Date: Thu, 5 Jul 2018 14:25:57 +0000 Subject: regulator: core: Change suspend_late to suspend Change suspend_late ops to suspend normal ops. The goal is to avoid requesting all the regulator drivers to be operational in suspend late phase. Signed-off-by: pascal paillet Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index dea96ee39fdc..0fd8fbb74763 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -220,7 +220,7 @@ struct regulator_ops { /* set regulator suspend operating mode (defined in consumer.h) */ int (*set_suspend_mode) (struct regulator_dev *, unsigned int mode); - int (*resume_early)(struct regulator_dev *rdev); + int (*resume)(struct regulator_dev *rdev); int (*set_pull_down) (struct regulator_dev *); }; -- cgit v1.2.3 From d8842211b6f63d3f069df973d137de0a85964965 Mon Sep 17 00:00:00 2001 From: pascal paillet Date: Thu, 5 Jul 2018 14:25:56 +0000 Subject: driver core: Add device_link_remove function Device_link_remove uses the same arguments than device_link_add. The Goal is to avoid storing the link pointer. Signed-off-by: pascal paillet Acked-by: Greg Kroah-Hartman Signed-off-by: Mark Brown --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 055a69dbcd18..9c1c3b1d5e11 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1316,6 +1316,7 @@ extern const char *dev_driver_string(const struct device *dev); struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags); void device_link_del(struct device_link *link); +void device_link_remove(void *consumer, struct device *supplier); #ifdef CONFIG_PRINTK -- cgit v1.2.3 From 2282e125a406e09331c5a785e3df29035c99a607 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 2 Jul 2018 22:05:21 +0200 Subject: leds: triggers: let struct led_trigger::activate() return an error code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Given that activating a trigger can fail, let the callback return an indication. This prevents to have a trigger active according to the "trigger" sysfs attribute but not functional. All users are changed accordingly to return 0 for now. There is no intended change in behaviour. Signed-off-by: Uwe Kleine-König Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index b7e82550e655..ba5baaaa43bf 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -253,7 +253,7 @@ static inline bool led_sysfs_is_disabled(struct led_classdev *led_cdev) struct led_trigger { /* Trigger Properties */ const char *name; - void (*activate)(struct led_classdev *led_cdev); + int (*activate)(struct led_classdev *led_cdev); void (*deactivate)(struct led_classdev *led_cdev); /* LEDs under control by this trigger (for simple triggers) */ @@ -288,8 +288,8 @@ extern void led_trigger_blink_oneshot(struct led_trigger *trigger, unsigned long *delay_off, int invert); extern void led_trigger_set_default(struct led_classdev *led_cdev); -extern void led_trigger_set(struct led_classdev *led_cdev, - struct led_trigger *trigger); +extern int led_trigger_set(struct led_classdev *led_cdev, + struct led_trigger *trigger); extern void led_trigger_remove(struct led_classdev *led_cdev); static inline void *led_get_trigger_data(struct led_classdev *led_cdev) @@ -334,8 +334,12 @@ static inline void led_trigger_blink_oneshot(struct led_trigger *trigger, unsigned long *delay_off, int invert) {} static inline void led_trigger_set_default(struct led_classdev *led_cdev) {} -static inline void led_trigger_set(struct led_classdev *led_cdev, - struct led_trigger *trigger) {} +static inline int led_trigger_set(struct led_classdev *led_cdev, + struct led_trigger *trigger) +{ + return 0; +} + static inline void led_trigger_remove(struct led_classdev *led_cdev) {} static inline void *led_get_trigger_data(struct led_classdev *led_cdev) { -- cgit v1.2.3 From a7e7a3156300a7e1982b03cc9cb8fb0c86434c49 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 2 Jul 2018 22:05:22 +0200 Subject: leds: triggers: add device attribute support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As many triggers use device attributes, add support for these in led_trigger_set which allows simplifying the drivers accordingly. Signed-off-by: Uwe Kleine-König Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index ba5baaaa43bf..33484a5c7478 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -262,8 +262,19 @@ struct led_trigger { /* Link to next registered trigger */ struct list_head next_trig; + + const struct attribute_group **groups; }; +/* + * Currently the attributes in struct led_trigger::groups are added directly to + * the LED device. As this might change in the future, the following + * macros abstract getting the LED device and its trigger_data from the dev + * parameter passed to the attribute accessor functions. + */ +#define led_trigger_get_led(dev) ((struct led_classdev *)dev_get_drvdata((dev))) +#define led_trigger_get_drvdata(dev) (led_get_trigger_data(led_trigger_get_led(dev))) + ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr, -- cgit v1.2.3 From a0b750768371e410d77b60bcf49c18bd45078d55 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 2 Jul 2018 22:05:24 +0200 Subject: leds: triggers: define module_led_trigger helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This helps to simplify modules that provide a simple led_trigger. It's inspired by module_platform_driver, module_i2c_driver et al. Signed-off-by: Uwe Kleine-König Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 33484a5c7478..a3ee10846a4b 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -326,6 +326,10 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) extern void led_trigger_rename_static(const char *name, struct led_trigger *trig); +#define module_led_trigger(__led_trigger) \ + module_driver(__led_trigger, led_trigger_register, \ + led_trigger_unregister) + #else /* Trigger has no members */ -- cgit v1.2.3 From 9acc560de2aac73ef99c54f0fdfb86b4684296b5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 2 Jul 2018 22:05:25 +0200 Subject: leds: triggers: new function led_set_trigger_data() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is the natural counter part to the already existing led_get_trigger_data(). Signed-off-by: Uwe Kleine-König Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index a3ee10846a4b..834683d603f9 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -303,6 +303,12 @@ extern int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trigger); extern void led_trigger_remove(struct led_classdev *led_cdev); +static inline void led_set_trigger_data(struct led_classdev *led_cdev, + void *trigger_data) +{ + led_cdev->trigger_data = trigger_data; +} + static inline void *led_get_trigger_data(struct led_classdev *led_cdev) { return led_cdev->trigger_data; @@ -356,6 +362,7 @@ static inline int led_trigger_set(struct led_classdev *led_cdev, } static inline void led_trigger_remove(struct led_classdev *led_cdev) {} +static inline void led_set_trigger_data(struct led_classdev *led_cdev) {} static inline void *led_get_trigger_data(struct led_classdev *led_cdev) { return NULL; -- cgit v1.2.3 From 576c7218a1546e0153480b208b125509cec71470 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 25 Jun 2018 13:17:41 -0500 Subject: PCI: Export pcie_get_speed_cap and pcie_get_width_cap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So drivers can use them. This can be used to replace duplicate code in the drm subsystem. Acked-by: Christian König Acked-by: Bjorn Helgaas Signed-off-by: Alex Deucher --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..6e0c0803b241 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -261,6 +261,9 @@ enum pci_bus_speed { PCI_SPEED_UNKNOWN = 0xff, }; +enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev); +enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev); + struct pci_cap_saved_data { u16 cap_nr; bool cap_extended; -- cgit v1.2.3 From 1b0707a781eeaeeaacb464e18bb3f049b99b496b Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 7 Jun 2018 19:50:38 +0000 Subject: Bluetooth: remove unused bt-nokia-h4p.h header Nothing in tree use this header which seems a remains of a staging driver. This patch remove it. Signed-off-by: Corentin Labbe Reviewed-by: Sebastian Reichel Signed-off-by: Marcel Holtmann --- include/linux/platform_data/bt-nokia-h4p.h | 38 ------------------------------ 1 file changed, 38 deletions(-) delete mode 100644 include/linux/platform_data/bt-nokia-h4p.h (limited to 'include/linux') diff --git a/include/linux/platform_data/bt-nokia-h4p.h b/include/linux/platform_data/bt-nokia-h4p.h deleted file mode 100644 index 30d169dfadf3..000000000000 --- a/include/linux/platform_data/bt-nokia-h4p.h +++ /dev/null @@ -1,38 +0,0 @@ -/* - * This file is part of Nokia H4P bluetooth driver - * - * Copyright (C) 2010 Nokia Corporation. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA - * - */ - - -/** - * struct hci_h4p_platform data - hci_h4p Platform data structure - */ -struct hci_h4p_platform_data { - int chip_type; - int bt_sysclk; - unsigned int bt_wakeup_gpio; - unsigned int host_wakeup_gpio; - unsigned int reset_gpio; - int reset_gpio_shared; - unsigned int uart_irq; - phys_addr_t uart_base; - const char *uart_iclk; - const char *uart_fclk; - void (*set_pm_limits)(struct device *dev, bool set); -}; -- cgit v1.2.3 From 0f725561e168485eff7277d683405c05b192f537 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Thu, 7 Jun 2018 09:56:59 -0700 Subject: iommu/vt-d: Add definitions for PFSID When SRIOV VF device IOTLB is invalidated, we need to provide the PF source ID such that IOMMU hardware can gauge the depth of invalidation queue which is shared among VFs. This is needed when device invalidation throttle (DIT) capability is supported. This patch adds bit definitions for checking and tracking PFSID. Signed-off-by: Jacob Pan Cc: stable@vger.kernel.org Cc: "Ashok Raj" Cc: "Lu Baolu" Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 1df940196ab2..3b1c37155572 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -114,6 +114,7 @@ * Extended Capability Register */ +#define ecap_dit(e) ((e >> 41) & 0x1) #define ecap_pasid(e) ((e >> 40) & 0x1) #define ecap_pss(e) ((e >> 35) & 0x1f) #define ecap_eafs(e) ((e >> 34) & 0x1) @@ -283,6 +284,7 @@ enum { #define QI_DEV_IOTLB_SID(sid) ((u64)((sid) & 0xffff) << 32) #define QI_DEV_IOTLB_QDEP(qdep) (((qdep) & 0x1f) << 16) #define QI_DEV_IOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) +#define QI_DEV_IOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xfff) << 52)) #define QI_DEV_IOTLB_SIZE 1 #define QI_DEV_IOTLB_MAX_INVS 32 @@ -307,6 +309,7 @@ enum { #define QI_DEV_EIOTLB_PASID(p) (((u64)p) << 32) #define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) #define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) +#define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xfff) << 52)) #define QI_DEV_EIOTLB_MAX_INVS 32 #define QI_PGRP_IDX(idx) (((u64)(idx)) << 55) -- cgit v1.2.3 From 1c48db44924298ad0cb5a6386b88017539be8822 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Thu, 7 Jun 2018 09:57:00 -0700 Subject: iommu/vt-d: Fix dev iotlb pfsid use PFSID should be used in the invalidation descriptor for flushing device IOTLBs on SRIOV VFs. Signed-off-by: Jacob Pan Cc: stable@vger.kernel.org Cc: "Ashok Raj" Cc: "Lu Baolu" Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 3b1c37155572..6692b40ca814 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -455,9 +455,8 @@ extern void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm, u64 type); extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, unsigned int size_order, u64 type); -extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep, - u64 addr, unsigned mask); - +extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, + u16 qdep, u64 addr, unsigned mask); extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu); extern int dmar_ir_support(void); -- cgit v1.2.3 From bad614b24293ae463e74d2465685f0e4e229baca Mon Sep 17 00:00:00 2001 From: Gary R Hook Date: Tue, 12 Jun 2018 16:41:21 -0500 Subject: iommu: Enable debugfs exposure of IOMMU driver internals Provide base enablement for using debugfs to expose internal data of an IOMMU driver. When called, create the /sys/kernel/debug/iommu directory. Emit a strong warning at boot time to indicate that this feature is enabled. This function is called from iommu_init, and creates the initial DebugFS directory. Drivers may then call iommu_debugfs_new_driver_dir() to instantiate a device-specific directory to expose internal data. It will return a pointer to the new dentry structure created in /sys/kernel/debug/iommu, or NULL in the event of a failure. Since the IOMMU driver can not be removed from the running system, there is no need for an "off" function. Signed-off-by: Gary R Hook Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 19938ee6eb31..7447b0b0579a 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -698,4 +698,11 @@ const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) #endif /* CONFIG_IOMMU_API */ +#ifdef CONFIG_IOMMU_DEBUGFS +extern struct dentry *iommu_debugfs_dir; +void iommu_debugfs_setup(void); +#else +static inline void iommu_debugfs_setup(void) {} +#endif + #endif /* __LINUX_IOMMU_H */ -- cgit v1.2.3 From 818b7587b4d34e989ea6c042eeb8d50ffa5be13e Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Wed, 27 Jun 2018 10:31:20 -0500 Subject: x86: irq_remapping: Move irq remapping mode enum The enum is currently defined in Intel-specific DMAR header file, but it is also used by APIC common code. Therefore, move it to a more appropriate interrupt-remapping common header file. This will also be used by subsequent patches. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Joerg Roedel Signed-off-by: Suravee Suthikulpanit Signed-off-by: Joerg Roedel --- include/linux/dmar.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index e2433bc50210..843a41ba7e28 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -265,11 +265,6 @@ static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src) #define PDA_LOW_BIT 26 #define PDA_HIGH_BIT 32 -enum { - IRQ_REMAP_XAPIC_MODE, - IRQ_REMAP_X2APIC_MODE, -}; - /* Can't use the common MSI interrupt functions * since DMAR is not a pci device */ -- cgit v1.2.3 From 3ffa6583e24e1ad1abab836d24bfc9d2308074e5 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Mon, 25 Jun 2018 09:51:48 +0200 Subject: power: remove possible deadlock when unregistering power_supply If a device gets removed right after having registered a power_supply node, we might enter in a deadlock between the remove call (that has a lock on the parent device) and the deferred register work. Allow the deferred register work to exit without taking the lock when we are in the remove state. Stack trace on a Ubuntu 16.04: [16072.109121] INFO: task kworker/u16:2:1180 blocked for more than 120 seconds. [16072.109127] Not tainted 4.13.0-41-generic #46~16.04.1-Ubuntu [16072.109129] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [16072.109132] kworker/u16:2 D 0 1180 2 0x80000000 [16072.109142] Workqueue: events_power_efficient power_supply_deferred_register_work [16072.109144] Call Trace: [16072.109152] __schedule+0x3d6/0x8b0 [16072.109155] schedule+0x36/0x80 [16072.109158] schedule_preempt_disabled+0xe/0x10 [16072.109161] __mutex_lock.isra.2+0x2ab/0x4e0 [16072.109166] __mutex_lock_slowpath+0x13/0x20 [16072.109168] ? __mutex_lock_slowpath+0x13/0x20 [16072.109171] mutex_lock+0x2f/0x40 [16072.109174] power_supply_deferred_register_work+0x2b/0x50 [16072.109179] process_one_work+0x15b/0x410 [16072.109182] worker_thread+0x4b/0x460 [16072.109186] kthread+0x10c/0x140 [16072.109189] ? process_one_work+0x410/0x410 [16072.109191] ? kthread_create_on_node+0x70/0x70 [16072.109194] ret_from_fork+0x35/0x40 [16072.109199] INFO: task test:2257 blocked for more than 120 seconds. [16072.109202] Not tainted 4.13.0-41-generic #46~16.04.1-Ubuntu [16072.109204] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [16072.109206] test D 0 2257 2256 0x00000004 [16072.109208] Call Trace: [16072.109211] __schedule+0x3d6/0x8b0 [16072.109215] schedule+0x36/0x80 [16072.109218] schedule_timeout+0x1f3/0x360 [16072.109221] ? check_preempt_curr+0x5a/0xa0 [16072.109224] ? ttwu_do_wakeup+0x1e/0x150 [16072.109227] wait_for_completion+0xb4/0x140 [16072.109230] ? wait_for_completion+0xb4/0x140 [16072.109233] ? wake_up_q+0x70/0x70 [16072.109236] flush_work+0x129/0x1e0 [16072.109240] ? worker_detach_from_pool+0xb0/0xb0 [16072.109243] __cancel_work_timer+0x10f/0x190 [16072.109247] ? device_del+0x264/0x310 [16072.109250] ? __wake_up+0x44/0x50 [16072.109253] cancel_delayed_work_sync+0x13/0x20 [16072.109257] power_supply_unregister+0x37/0xb0 [16072.109260] devm_power_supply_release+0x11/0x20 [16072.109263] release_nodes+0x110/0x200 [16072.109266] devres_release_group+0x7c/0xb0 [16072.109274] wacom_remove+0xc2/0x110 [wacom] [16072.109279] hid_device_remove+0x6e/0xd0 [hid] [16072.109284] device_release_driver_internal+0x158/0x210 [16072.109288] device_release_driver+0x12/0x20 [16072.109291] bus_remove_device+0xec/0x160 [16072.109293] device_del+0x1de/0x310 [16072.109298] hid_destroy_device+0x27/0x60 [hid] [16072.109303] usbhid_disconnect+0x51/0x70 [usbhid] [16072.109308] usb_unbind_interface+0x77/0x270 [16072.109311] device_release_driver_internal+0x158/0x210 [16072.109315] device_release_driver+0x12/0x20 [16072.109318] usb_driver_release_interface+0x77/0x80 [16072.109321] proc_ioctl+0x20f/0x250 [16072.109325] usbdev_do_ioctl+0x57f/0x1140 [16072.109327] ? __wake_up+0x44/0x50 [16072.109331] usbdev_ioctl+0xe/0x20 [16072.109336] do_vfs_ioctl+0xa4/0x600 [16072.109339] ? vfs_write+0x15a/0x1b0 [16072.109343] SyS_ioctl+0x79/0x90 [16072.109347] entry_SYSCALL_64_fastpath+0x24/0xab [16072.109349] RIP: 0033:0x7f20da807f47 [16072.109351] RSP: 002b:00007ffc422ae398 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [16072.109353] RAX: ffffffffffffffda RBX: 00000000010b8560 RCX: 00007f20da807f47 [16072.109355] RDX: 00007ffc422ae3a0 RSI: 00000000c0105512 RDI: 0000000000000009 [16072.109356] RBP: 0000000000000000 R08: 00007ffc422ae3e0 R09: 0000000000000010 [16072.109357] R10: 00000000000000a6 R11: 0000000000000246 R12: 0000000000000000 [16072.109359] R13: 00000000010b8560 R14: 00007ffc422ae2e0 R15: 0000000000000000 Reported-and-tested-by: Richard Hughes Tested-by: Aaron Skomra Signed-off-by: Benjamin Tissoires Fixes: 7f1a57fdd6cb ("power_supply: Fix possible NULL pointer dereference on early uevent") Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index b21c4bd96b84..f80769175c56 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -269,6 +269,7 @@ struct power_supply { spinlock_t changed_lock; bool changed; bool initialized; + bool removing; atomic_t use_cnt; #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd; -- cgit v1.2.3 From 7efe25a70c37395b41b034335345d6855926c2a6 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 7 Jun 2018 19:44:56 +0000 Subject: iommu/shmobile: Remove unused include/linux/platform_data/sh_ipmmu.h header include/linux/platform_data/sh_ipmmu.h is unused since commit ae50dc4874c5 ("iommu/shmobile: Remove unused Renesas IPMMU/IPMMUI") Let's remove it. Signed-off-by: Corentin Labbe Reviewed-by: Geert Uytterhoeven Reviewed-by: Simon Horman Signed-off-by: Joerg Roedel --- include/linux/platform_data/sh_ipmmu.h | 18 ------------------ 1 file changed, 18 deletions(-) delete mode 100644 include/linux/platform_data/sh_ipmmu.h (limited to 'include/linux') diff --git a/include/linux/platform_data/sh_ipmmu.h b/include/linux/platform_data/sh_ipmmu.h deleted file mode 100644 index 39f7405cdac5..000000000000 --- a/include/linux/platform_data/sh_ipmmu.h +++ /dev/null @@ -1,18 +0,0 @@ -/* sh_ipmmu.h - * - * Copyright (C) 2012 Hideki EIRAKU - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - */ - -#ifndef __SH_IPMMU_H__ -#define __SH_IPMMU_H__ - -struct shmobile_ipmmu_platform_data { - const char * const *dev_names; - unsigned int num_dev_names; -}; - -#endif /* __SH_IPMMU_H__ */ -- cgit v1.2.3 From 663336ee2628096df0ce2b546b148cb74b5249fe Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 9 May 2018 08:15:46 -0700 Subject: device: Add #define dev_fmt similar to #define pr_fmt Add a prefixing macro to dev_ uses similar to the pr_fmt prefixing macro used in pr_ calls. This can help avoid some string duplication in dev_ uses. The default, like pr_fmt, is an empty #define dev_fmt(fmt) fmt Rename the existing dev_ functions to _dev_ and introduce #define dev_ _dev_ macros that use the new #define dev_fmt Miscellanea: o Consistently use #defines with fmt, ... and ##__VA_ARGS__ o Remove unnecessary externs Signed-off-by: Joe Perches Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 103 ++++++++++++++++++++++++++++--------------------- 1 file changed, 58 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 055a69dbcd18..2eaa9ea13c09 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1317,30 +1317,34 @@ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags); void device_link_del(struct device_link *link); +#ifndef dev_fmt +#define dev_fmt(fmt) fmt +#endif + #ifdef CONFIG_PRINTK -extern __printf(3, 0) +__printf(3, 0) int dev_vprintk_emit(int level, const struct device *dev, const char *fmt, va_list args); -extern __printf(3, 4) +__printf(3, 4) int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...); -extern __printf(3, 4) +__printf(3, 4) void dev_printk(const char *level, const struct device *dev, const char *fmt, ...); -extern __printf(2, 3) -void dev_emerg(const struct device *dev, const char *fmt, ...); -extern __printf(2, 3) -void dev_alert(const struct device *dev, const char *fmt, ...); -extern __printf(2, 3) -void dev_crit(const struct device *dev, const char *fmt, ...); -extern __printf(2, 3) -void dev_err(const struct device *dev, const char *fmt, ...); -extern __printf(2, 3) -void dev_warn(const struct device *dev, const char *fmt, ...); -extern __printf(2, 3) -void dev_notice(const struct device *dev, const char *fmt, ...); -extern __printf(2, 3) +__printf(2, 3) +void _dev_emerg(const struct device *dev, const char *fmt, ...); +__printf(2, 3) +void _dev_alert(const struct device *dev, const char *fmt, ...); +__printf(2, 3) +void _dev_crit(const struct device *dev, const char *fmt, ...); +__printf(2, 3) +void _dev_err(const struct device *dev, const char *fmt, ...); +__printf(2, 3) +void _dev_warn(const struct device *dev, const char *fmt, ...); +__printf(2, 3) +void _dev_notice(const struct device *dev, const char *fmt, ...); +__printf(2, 3) void _dev_info(const struct device *dev, const char *fmt, ...); #else @@ -1358,26 +1362,26 @@ static inline void __dev_printk(const char *level, const struct device *dev, {} static inline __printf(3, 4) void dev_printk(const char *level, const struct device *dev, - const char *fmt, ...) + const char *fmt, ...) {} static inline __printf(2, 3) -void dev_emerg(const struct device *dev, const char *fmt, ...) +void _dev_emerg(const struct device *dev, const char *fmt, ...) {} static inline __printf(2, 3) -void dev_crit(const struct device *dev, const char *fmt, ...) +void _dev_crit(const struct device *dev, const char *fmt, ...) {} static inline __printf(2, 3) -void dev_alert(const struct device *dev, const char *fmt, ...) +void _dev_alert(const struct device *dev, const char *fmt, ...) {} static inline __printf(2, 3) -void dev_err(const struct device *dev, const char *fmt, ...) +void _dev_err(const struct device *dev, const char *fmt, ...) {} static inline __printf(2, 3) -void dev_warn(const struct device *dev, const char *fmt, ...) +void _dev_warn(const struct device *dev, const char *fmt, ...) {} static inline __printf(2, 3) -void dev_notice(const struct device *dev, const char *fmt, ...) +void _dev_notice(const struct device *dev, const char *fmt, ...) {} static inline __printf(2, 3) void _dev_info(const struct device *dev, const char *fmt, ...) @@ -1386,27 +1390,36 @@ void _dev_info(const struct device *dev, const char *fmt, ...) #endif /* - * Stupid hackaround for existing uses of non-printk uses dev_info - * - * Note that the definition of dev_info below is actually _dev_info - * and a macro is used to avoid redefining dev_info + * #defines for all the dev_ macros to prefix with whatever + * possible use of #define dev_fmt(fmt) ... */ -#define dev_info(dev, fmt, arg...) _dev_info(dev, fmt, ##arg) +#define dev_emerg(dev, fmt, ...) \ + _dev_emerg(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_crit(dev, fmt, ...) \ + _dev_crit(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_alert(dev, fmt, ...) \ + _dev_alert(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_err(dev, fmt, ...) \ + _dev_err(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_warn(dev, fmt, ...) \ + _dev_warn(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_notice(dev, fmt, ...) \ + _dev_notice(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_info(dev, fmt, ...) \ + _dev_info(dev, dev_fmt(fmt), ##__VA_ARGS__) #if defined(CONFIG_DYNAMIC_DEBUG) -#define dev_dbg(dev, format, ...) \ -do { \ - dynamic_dev_dbg(dev, format, ##__VA_ARGS__); \ -} while (0) +#define dev_dbg(dev, fmt, ...) \ + dynamic_dev_dbg(dev, dev_fmt(fmt), ##__VA_ARGS__) #elif defined(DEBUG) -#define dev_dbg(dev, format, arg...) \ - dev_printk(KERN_DEBUG, dev, format, ##arg) +#define dev_dbg(dev, fmt, ...) \ + dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #else -#define dev_dbg(dev, format, arg...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, format, ##arg); \ +#define dev_dbg(dev, fmt, ...) \ +({ \ + if (0) \ + dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ }) #endif @@ -1478,7 +1491,7 @@ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \ __ratelimit(&_rs)) \ - __dynamic_dev_dbg(&descriptor, dev, fmt, \ + __dynamic_dev_dbg(&descriptor, dev, dev_fmt(fmt), \ ##__VA_ARGS__); \ } while (0) #elif defined(DEBUG) @@ -1488,23 +1501,23 @@ do { \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ if (__ratelimit(&_rs)) \ - dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ + dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ } while (0) #else #define dev_dbg_ratelimited(dev, fmt, ...) \ do { \ if (0) \ - dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ + dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ } while (0) #endif #ifdef VERBOSE_DEBUG #define dev_vdbg dev_dbg #else -#define dev_vdbg(dev, format, arg...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, format, ##arg); \ +#define dev_vdbg(dev, fmt, ...) \ +({ \ + if (0) \ + dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ }) #endif -- cgit v1.2.3 From 5740c99e9d30b81fcc478797e7215c61e241f44e Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jul 2018 23:57:03 +0200 Subject: vfs: dedupe: return int Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5c91108846db..b81c4b7e339f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1749,7 +1749,7 @@ struct file_operations { loff_t, size_t, unsigned int); int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, u64); - ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *, + int (*dedupe_file_range)(struct file *, u64, u64, struct file *, u64); } __randomize_layout; -- cgit v1.2.3 From 87eb5eb2423213ac0e7315ce5d275f1ff80e0263 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Jul 2018 23:57:03 +0200 Subject: vfs: dedupe: rationalize args Clean up f_op->dedupe_file_range() interface. 1) Use loff_t for offsets and length instead of u64 2) Order the arguments the same way as {copy|clone}_file_range(). Signed-off-by: Miklos Szeredi Reviewed-by: Darrick J. Wong --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b81c4b7e339f..a8fee2f44981 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1749,7 +1749,7 @@ struct file_operations { loff_t, size_t, unsigned int); int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, u64); - int (*dedupe_file_range)(struct file *, u64, u64, struct file *, + int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); } __randomize_layout; -- cgit v1.2.3 From 06ae48269d1e0324d806fca30fe77112f4a4a14a Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Fri, 6 Jul 2018 15:13:18 -0700 Subject: lib: reciprocal_div: implement the improved algorithm on the paper mentioned The new added "reciprocal_value_adv" implements the advanced version of the algorithm described in Figure 4.2 of the paper except when "divisor > (1U << 31)" whose ceil(log2(d)) result will be 32 which then requires u128 divide on host. The exception case could be easily handled before calling "reciprocal_value_adv". The advanced version requires more complex calculation to get the reciprocal multiplier and other control variables, but then could reduce the required emulation operations. It makes no sense to use this advanced version for host divide emulation, those extra complexities for calculating multiplier etc could completely waive our saving on emulation operations. However, it makes sense to use it for JIT divide code generation (for example eBPF JIT backends) for which we are willing to trade performance of JITed code with that of host. As shown by the following pseudo code, the required emulation operations could go down from 6 (the basic version) to 3 or 4. To use the result of "reciprocal_value_adv", suppose we want to calculate n/d, the C-style pseudo code will be the following, it could be easily changed to real code generation for other JIT targets. struct reciprocal_value_adv rvalue; u8 pre_shift, exp; // handle exception case. if (d >= (1U << 31)) { result = n >= d; return; } rvalue = reciprocal_value_adv(d, 32) exp = rvalue.exp; if (rvalue.is_wide_m && !(d & 1)) { // floor(log2(d & (2^32 -d))) pre_shift = fls(d & -d) - 1; rvalue = reciprocal_value_adv(d >> pre_shift, 32 - pre_shift); } else { pre_shift = 0; } // code generation starts. if (imm == 1U << exp) { result = n >> exp; } else if (rvalue.is_wide_m) { // pre_shift must be zero when reached here. t = (n * rvalue.m) >> 32; result = n - t; result >>= 1; result += t; result >>= rvalue.sh - 1; } else { if (pre_shift) result = n >> pre_shift; result = ((u64)result * rvalue.m) >> 32; result >>= rvalue.sh; } Signed-off-by: Jiong Wang Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- include/linux/reciprocal_div.h | 68 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reciprocal_div.h b/include/linux/reciprocal_div.h index e031e9f2f9d8..585ce89c0f33 100644 --- a/include/linux/reciprocal_div.h +++ b/include/linux/reciprocal_div.h @@ -25,6 +25,9 @@ struct reciprocal_value { u8 sh1, sh2; }; +/* "reciprocal_value" and "reciprocal_divide" together implement the basic + * version of the algorithm described in Figure 4.1 of the paper. + */ struct reciprocal_value reciprocal_value(u32 d); static inline u32 reciprocal_divide(u32 a, struct reciprocal_value R) @@ -33,4 +36,69 @@ static inline u32 reciprocal_divide(u32 a, struct reciprocal_value R) return (t + ((a - t) >> R.sh1)) >> R.sh2; } +struct reciprocal_value_adv { + u32 m; + u8 sh, exp; + bool is_wide_m; +}; + +/* "reciprocal_value_adv" implements the advanced version of the algorithm + * described in Figure 4.2 of the paper except when "divisor > (1U << 31)" whose + * ceil(log2(d)) result will be 32 which then requires u128 divide on host. The + * exception case could be easily handled before calling "reciprocal_value_adv". + * + * The advanced version requires more complex calculation to get the reciprocal + * multiplier and other control variables, but then could reduce the required + * emulation operations. + * + * It makes no sense to use this advanced version for host divide emulation, + * those extra complexities for calculating multiplier etc could completely + * waive our saving on emulation operations. + * + * However, it makes sense to use it for JIT divide code generation for which + * we are willing to trade performance of JITed code with that of host. As shown + * by the following pseudo code, the required emulation operations could go down + * from 6 (the basic version) to 3 or 4. + * + * To use the result of "reciprocal_value_adv", suppose we want to calculate + * n/d, the pseudo C code will be: + * + * struct reciprocal_value_adv rvalue; + * u8 pre_shift, exp; + * + * // handle exception case. + * if (d >= (1U << 31)) { + * result = n >= d; + * return; + * } + * + * rvalue = reciprocal_value_adv(d, 32) + * exp = rvalue.exp; + * if (rvalue.is_wide_m && !(d & 1)) { + * // floor(log2(d & (2^32 -d))) + * pre_shift = fls(d & -d) - 1; + * rvalue = reciprocal_value_adv(d >> pre_shift, 32 - pre_shift); + * } else { + * pre_shift = 0; + * } + * + * // code generation starts. + * if (imm == 1U << exp) { + * result = n >> exp; + * } else if (rvalue.is_wide_m) { + * // pre_shift must be zero when reached here. + * t = (n * rvalue.m) >> 32; + * result = n - t; + * result >>= 1; + * result += t; + * result >>= rvalue.sh - 1; + * } else { + * if (pre_shift) + * result = n >> pre_shift; + * result = ((u64)result * rvalue.m) >> 32; + * result >>= rvalue.sh; + * } + */ +struct reciprocal_value_adv reciprocal_value_adv(u32 d, u8 prec); + #endif /* _LINUX_RECIPROCAL_DIV_H */ -- cgit v1.2.3 From 000244d3dc1f8114e38fe9ee2d9a0986404d9cbe Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 6 Jul 2018 14:44:02 +0200 Subject: net: bridge: fix br_vlan_get_{pvid,info} return values These two functions return the regular -EINVAL failure in the normal code path, but return a nonstandard '-1' error otherwise, which gets interpreted as -EPERM. Let's change it to -EINVAL for the dummy functions as well. Fixes: 4d4fd36126d6 ("net: bridge: Publish bridge accessor functions") Signed-off-by: Arnd Bergmann Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 7843b98e1c6e..c20c7e197d07 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -105,13 +105,13 @@ static inline bool br_vlan_enabled(const struct net_device *dev) static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { - return -1; + return -EINVAL; } static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { - return -1; + return -EINVAL; } #endif -- cgit v1.2.3 From 543af5861f41af0a5d2432f6fb5976af50f9cee5 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Fri, 6 Jul 2018 22:05:38 -0400 Subject: uio: change to use the mutex lock instead of the spin lock We are hitting a regression with the following commit: commit a93e7b331568227500186a465fee3c2cb5dffd1f Author: Hamish Martin Date: Mon May 14 13:32:23 2018 +1200 uio: Prevent device destruction while fds are open The problem is the addition of spin_lock_irqsave in uio_write. This leads to hitting uio_write -> copy_from_user -> _copy_from_user -> might_fault and the logs filling up with sleeping warnings. I also noticed some uio drivers allocate memory, sleep, grab mutexes from callouts like open() and release and uio is now doing spin_lock_irqsave while calling them. Reported-by: Mike Christie CC: Hamish Martin Reviewed-by: Hamish Martin Signed-off-by: Xiubo Li Signed-off-by: Greg Kroah-Hartman --- include/linux/uio_driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 6c5f2074e14f..6f8b68cd460f 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -75,7 +75,7 @@ struct uio_device { struct fasync_struct *async_queue; wait_queue_head_t wait; struct uio_info *info; - spinlock_t info_lock; + struct mutex info_lock; struct kobject *map_dir; struct kobject *portio_dir; }; -- cgit v1.2.3 From e0772de8a48b69d39624cdf99fac8f4a3fcc387b Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 19 Jun 2018 17:12:57 +0100 Subject: slimbus: core: add of_slim_device_get() helper On SLIMBus controllers like Qcom NGD(non ported device), controller can request logical address once the remote side is powered, having a helper function like this to explicitly enumerate the bus is helpful. Also codec drivers which are taking to interface device would need such a helper too. Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/slimbus.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slimbus.h b/include/linux/slimbus.h index c36cf121d2cd..efa36a852dc3 100644 --- a/include/linux/slimbus.h +++ b/include/linux/slimbus.h @@ -138,6 +138,8 @@ static inline void slim_set_devicedata(struct slim_device *dev, void *data) dev_set_drvdata(&dev->dev, data); } +struct slim_device *of_slim_get_device(struct slim_controller *ctrl, + struct device_node *np); struct slim_device *slim_get_device(struct slim_controller *ctrl, struct slim_eaddr *e_addr); int slim_get_logical_addr(struct slim_device *sbdev); -- cgit v1.2.3 From db455d66b9900a8a81fe474f11c78c8c8a95eefa Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 19 Jun 2018 17:12:58 +0100 Subject: slimbus: core: rearrange slim_eaddr structure Rearrange struct slim_eaddr so that the structure is packed correctly to be able to send in SLIMBus messages. Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/slimbus.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slimbus.h b/include/linux/slimbus.h index efa36a852dc3..63801bcc5e60 100644 --- a/include/linux/slimbus.h +++ b/include/linux/slimbus.h @@ -14,16 +14,16 @@ extern struct bus_type slimbus_bus; /** * struct slim_eaddr - Enumeration address for a SLIMbus device - * @manf_id: Manufacturer Id for the device - * @prod_code: Product code - * @dev_index: Device index * @instance: Instance value + * @dev_index: Device index + * @prod_code: Product code + * @manf_id: Manufacturer Id for the device */ struct slim_eaddr { - u16 manf_id; - u16 prod_code; - u8 dev_index; u8 instance; + u8 dev_index; + u16 prod_code; + u16 manf_id; } __packed; /** -- cgit v1.2.3 From abb9c9b8b51ba53b47ad7685ad2a0a64dbbf7bf5 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 5 Jul 2018 14:54:25 +0100 Subject: slimbus: stream: add stream support This patch adds support to SLIMbus stream apis for slimbus device. SLIMbus streaming involves adding support to Data Channel Management and channel Reconfiguration Messages to slim core plus few stream apis. >From slim device side the apis are very simple mostly inline with other stream apis. Currently it only supports Isochronous and Push/Pull transport protocols, which are sufficient for audio use cases. Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/slimbus.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slimbus.h b/include/linux/slimbus.h index 63801bcc5e60..12c9719b2a55 100644 --- a/include/linux/slimbus.h +++ b/include/linux/slimbus.h @@ -48,6 +48,8 @@ struct slim_controller; * @ctrl: slim controller instance. * @laddr: 1-byte Logical address of this device. * @is_laddr_valid: indicates if the laddr is valid or not + * @stream_list: List of streams on this device + * @stream_list_lock: lock to protect the stream list * * This is the client/device handle returned when a SLIMbus * device is registered with a controller. @@ -60,6 +62,8 @@ struct slim_device { enum slim_device_status status; u8 laddr; bool is_laddr_valid; + struct list_head stream_list; + spinlock_t stream_list_lock; }; #define to_slim_device(d) container_of(d, struct slim_device, dev) @@ -108,6 +112,36 @@ struct slim_val_inf { struct completion *comp; }; +#define SLIM_DEVICE_MAX_CHANNELS 256 +/* A SLIMBus Device may have frmo 0 to 31 Ports (inclusive) */ +#define SLIM_DEVICE_MAX_PORTS 32 + +/** + * struct slim_stream_config - SLIMbus stream configuration + * Configuring a stream is done at hw_params or prepare call + * from audio drivers where they have all the required information + * regarding rate, number of channels and so on. + * There is a 1:1 mapping of channel and ports. + * + * @rate: data rate + * @bps: bits per data sample + * @ch_count: number of channels + * @chs: pointer to list of channel numbers + * @port_mask: port mask of ports to use for this stream + * @direction: direction of the stream, SNDRV_PCM_STREAM_PLAYBACK + * or SNDRV_PCM_STREAM_CAPTURE. + */ +struct slim_stream_config { + unsigned int rate; + unsigned int bps; + /* MAX 256 channels */ + unsigned int ch_count; + unsigned int *chs; + /* Max 32 ports per device */ + unsigned long port_mask; + int direction; +}; + /* * use a macro to avoid include chaining to get THIS_MODULE */ @@ -163,4 +197,16 @@ int slim_readb(struct slim_device *sdev, u32 addr); int slim_writeb(struct slim_device *sdev, u32 addr, u8 value); int slim_read(struct slim_device *sdev, u32 addr, size_t count, u8 *val); int slim_write(struct slim_device *sdev, u32 addr, size_t count, u8 *val); + +/* SLIMbus Stream apis */ +struct slim_stream_runtime; +struct slim_stream_runtime *slim_stream_allocate(struct slim_device *dev, + const char *sname); +int slim_stream_prepare(struct slim_stream_runtime *stream, + struct slim_stream_config *c); +int slim_stream_enable(struct slim_stream_runtime *stream); +int slim_stream_disable(struct slim_stream_runtime *stream); +int slim_stream_unprepare(struct slim_stream_runtime *stream); +int slim_stream_free(struct slim_stream_runtime *stream); + #endif /* _LINUX_SLIMBUS_H */ -- cgit v1.2.3 From ea614629c69c2c0258ef6414b017c998e3cc61a7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 16 Jun 2018 18:53:57 -0700 Subject: linux/device.h: fix kernel-doc notation warning Fix kernel-doc build warning (missing " *" at beginning of line): ../include/linux/device.h:93: warning: bad line: this bus. Fixes: 07397df29e57c ("dma-mapping: move dma configuration to bus infrastructure") Signed-off-by: Randy Dunlap Cc: Nipun Gupta Cc: Christoph Hellwig Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 2eaa9ea13c09..575c5a35ece5 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -90,7 +90,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @num_vf: Called to find out how many virtual functions a device on this * bus supports. * @dma_configure: Called to setup DMA configuration on a device on - this bus. + * this bus. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU -- cgit v1.2.3 From ac3167257b9fe16c9426c2087ead1c9f1b0992b1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 19 Jun 2018 22:47:28 -0700 Subject: headers: separate linux/mod_devicetable.h from linux/platform_device.h At over 4000 #includes, is the 9th most #included header file in the Linux kernel. It does not need , so drop that header and explicitly add to source files that need it. 4146 #include After this patch, there are 225 files that use , for a reduction of around 3900 times that does not have to be read & parsed. 225 #include This patch was build-tested on 20 different arch-es. It also makes these drivers SubmitChecklist#1 compliant. Signed-off-by: Randy Dunlap Reported-by: kbuild test robot # drivers/media/platform/vimc/ Reported-by: kbuild test robot # drivers/pinctrl/pinctrl-u300.c Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 3097c943fab9..1a9f38f27f65 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -12,13 +12,13 @@ #define _PLATFORM_DEVICE_H_ #include -#include #define PLATFORM_DEVID_NONE (-1) #define PLATFORM_DEVID_AUTO (-2) struct mfd_cell; struct property_entry; +struct platform_device_id; struct platform_device { const char *name; -- cgit v1.2.3 From d8d7218ad842e18fc6976b87c08ed749e8d56313 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 6 Jul 2018 11:49:00 +0900 Subject: xdp: XDP_REDIRECT should check IFF_UP and MTU Otherwise we end up with attempting to send packets from down devices or to send oversized packets, which may cause unexpected driver/device behaviour. Generic XDP has already done this check, so reuse the logic in native XDP. Fixes: 814abfabef3c ("xdp: add bpf_redirect helper function") Signed-off-by: Toshiaki Makita Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 300baad62c88..c73dd7396886 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -765,8 +765,8 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); -static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, - struct net_device *fwd) +static inline int xdp_ok_fwd_dev(const struct net_device *fwd, + unsigned int pktlen) { unsigned int len; @@ -774,7 +774,7 @@ static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, return -ENETDOWN; len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; - if (skb->len > len) + if (pktlen > len) return -EMSGSIZE; return 0; -- cgit v1.2.3 From b233504033dbd65740e59681820ccfd0a2a8ec53 Mon Sep 17 00:00:00 2001 From: Yifeng Sun Date: Mon, 2 Jul 2018 08:18:03 -0700 Subject: openvswitch: kernel datapath clone action Add 'clone' action to kernel datapath by using existing functions. When actions within clone don't modify the current flow, the flow key is not cloned before executing clone actions. This is a follow up patch for this incomplete work: https://patchwork.ozlabs.org/patch/722096/ v1 -> v2: Refactor as advised by reviewer. Signed-off-by: Yifeng Sun Signed-off-by: Andy Zhou Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/openvswitch.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h index e6b240b6196c..379affc63e24 100644 --- a/include/linux/openvswitch.h +++ b/include/linux/openvswitch.h @@ -21,4 +21,9 @@ #include +#define OVS_CLONE_ATTR_EXEC 0 /* Specify an u32 value. When nonzero, + * actions in clone will not change flow + * keys. False otherwise. + */ + #endif /* _LINUX_OPENVSWITCH_H */ -- cgit v1.2.3 From 69448867abcb231afaa7891ff9d9fd04b2b94a0d Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 5 Jul 2018 09:25:43 +0300 Subject: fs: shave 8 bytes off of struct inode Here is a link to Linus' reply to Jan's concern about making i_blkbibts byte addressable: https://marc.info/?l=linux-fsdevel&m=152882624707975&w=2 Here is a link to an lkp.org report about potential performance improvement in some workload, which could(?) be related to packing i_blkbits closer to i_bytes/i_lock: https://marc.info/?l=linux-fsdevel&m=153077048108198&w=2 Changes since v1: - Add links to relevant discussions Signed-off-by: Amir Goldstein Signed-off-by: Al Viro --- include/linux/fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f140c11d35dd..9b00676f5d9d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -275,6 +275,7 @@ struct writeback_control; /* * Write life time hint values. + * Stored in struct inode as u8. */ enum rw_hint { WRITE_LIFE_NOT_SET = 0, @@ -609,8 +610,8 @@ struct inode { struct timespec64 i_ctime; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; - unsigned int i_blkbits; - enum rw_hint i_write_hint; + u8 i_blkbits; + u8 i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED -- cgit v1.2.3 From f292b87d3ac020418644d8a4bbf29814890505cb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 6 Jul 2018 14:34:29 -0700 Subject: bpf: include errno.h from bpf-cgroup.h Commit fdb5c4531c1e ("bpf: fix attach type BPF_LIRC_MODE2 dependency wrt CONFIG_CGROUP_BPF") caused some build issues, detected by 0-DAY kernel test infrastructure. The problem is that cgroup_bpf_prog_attach/detach/query() functions can return -EINVAL error code, which is not defined. Fix this adding errno.h to includes. Fixes: fdb5c4531c1e ("bpf: fix attach type BPF_LIRC_MODE2 dependency wrt CONFIG_CGROUP_BPF") Signed-off-by: Roman Gushchin Cc: Sean Young Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 79795c5fa7c3..d50c2f0a655a 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -2,6 +2,7 @@ #ifndef _BPF_CGROUP_H #define _BPF_CGROUP_H +#include #include #include -- cgit v1.2.3 From 5d6be70add65e3f236642ab0029e356261617cd0 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 29 Jun 2018 13:04:31 +0200 Subject: PM / Domains: Introduce option to attach a device by name to genpd For the multiple PM domain case, let's introduce a new function called genpd_dev_pm_attach_by_name(). This allows a device to be associated with its PM domain through genpd, by using a name based lookup. Note that, genpd_dev_pm_attach_by_name() shall only be called by the driver core / PM core, similar to how the existing dev_pm_domain_attach_by_id() makes use of genpd_dev_pm_attach_by_id(). However, this is implemented by following changes on top. Signed-off-by: Ulf Hansson Tested-by: Rajendra Nayak Reviewed-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index cb8d84090cfb..03e14a38462d 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -239,6 +239,8 @@ unsigned int of_genpd_opp_to_performance_state(struct device *dev, int genpd_dev_pm_attach(struct device *dev); struct device *genpd_dev_pm_attach_by_id(struct device *dev, unsigned int index); +struct device *genpd_dev_pm_attach_by_name(struct device *dev, + char *name); #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */ static inline int of_genpd_add_provider_simple(struct device_node *np, struct generic_pm_domain *genpd) @@ -290,6 +292,12 @@ static inline struct device *genpd_dev_pm_attach_by_id(struct device *dev, return NULL; } +static inline struct device *genpd_dev_pm_attach_by_name(struct device *dev, + char *name) +{ + return NULL; +} + static inline struct generic_pm_domain *of_genpd_remove_last(struct device_node *np) { -- cgit v1.2.3 From 27dceb81f445c58b1d10d27d26eaf4ac2e9e0b00 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 29 Jun 2018 13:04:32 +0200 Subject: PM / Domains: Introduce dev_pm_domain_attach_by_name() For the multiple PM domain case, let's introduce a new API called dev_pm_domain_attach_by_name(). This allows a consumer driver to associate its device with one of its PM domains, by using a name based lookup. Do note that, currently it's only genpd that supports multiple PM domains per device, but dev_pm_domain_attach_by_name() can easily by extended to cover other PM domain types, if/when needed. Signed-off-by: Ulf Hansson Tested-by: Rajendra Nayak Reviewed-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 03e14a38462d..776c546d581a 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -309,6 +309,8 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np) int dev_pm_domain_attach(struct device *dev, bool power_on); struct device *dev_pm_domain_attach_by_id(struct device *dev, unsigned int index); +struct device *dev_pm_domain_attach_by_name(struct device *dev, + char *name); void dev_pm_domain_detach(struct device *dev, bool power_off); void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd); #else @@ -321,6 +323,11 @@ static inline struct device *dev_pm_domain_attach_by_id(struct device *dev, { return NULL; } +static inline struct device *dev_pm_domain_attach_by_name(struct device *dev, + char *name) +{ + return NULL; +} static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {} static inline void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd) {} -- cgit v1.2.3 From e88728f46cfbb59cc7e7acf1d230c05ec093764e Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Wed, 27 Jun 2018 18:20:55 +0530 Subject: driver core: Rename flag AUTOREMOVE to AUTOREMOVE_CONSUMER Now that we want to add another flag to autoremove the device link on supplier unbind, it's fair to rename the existing flag from DL_FLAG_AUTOREMOVE to DL_FLAG_AUTOREMOVE_CONSUMER so that we can add similar flag for supplier later. And, while we are touching device.h, fix a doc build warning. Signed-off-by: Vivek Gautam Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/device.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 055a69dbcd18..3929805cdd59 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -90,7 +90,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @num_vf: Called to find out how many virtual functions a device on this * bus supports. * @dma_configure: Called to setup DMA configuration on a device on - this bus. + * this bus. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU @@ -784,14 +784,14 @@ enum device_link_state { * Device link flags. * * STATELESS: The core won't track the presence of supplier/consumer drivers. - * AUTOREMOVE: Remove this link automatically on consumer driver unbind. + * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind. * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. */ -#define DL_FLAG_STATELESS BIT(0) -#define DL_FLAG_AUTOREMOVE BIT(1) -#define DL_FLAG_PM_RUNTIME BIT(2) -#define DL_FLAG_RPM_ACTIVE BIT(3) +#define DL_FLAG_STATELESS BIT(0) +#define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) +#define DL_FLAG_PM_RUNTIME BIT(2) +#define DL_FLAG_RPM_ACTIVE BIT(3) /** * struct device_link - Device link representation. -- cgit v1.2.3 From 1689cac5b32a6db6f812e8063ea418a7cf023d03 Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Wed, 27 Jun 2018 18:20:56 +0530 Subject: driver core: Add flag to autoremove device link on supplier unbind Add a flag to autoremove the device links on supplier driver unbind. This obviates the need to explicitly delete the link in the remove path. We remove these links only when the supplier's link to its consumers has gone to DL_STATE_SUPPLIER_UNBIND state. Signed-off-by: Vivek Gautam Suggested-by: Lukas Wunner Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 3929805cdd59..e80920452b49 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -787,11 +787,13 @@ enum device_link_state { * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind. * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. + * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) #define DL_FLAG_PM_RUNTIME BIT(2) #define DL_FLAG_RPM_ACTIVE BIT(3) +#define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) /** * struct device_link - Device link representation. -- cgit v1.2.3 From 63f3fb8d7ccb813e0a1f2ceedb9a3ebe2685b620 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 2 Jul 2018 15:59:37 -0700 Subject: pinctrl: Document pin_config_group_get() return codes like pin_config_get() The pinconf_generic_dump_one() function makes the assumption that pin_config_group_get() should return -EINVAL and -ENOTSUPP just like pin_config_get() does. Document that so it's more obvious. Signed-off-by: Douglas Anderson Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h index 09eb80f2574a..8dd85d302b90 100644 --- a/include/linux/pinctrl/pinconf.h +++ b/include/linux/pinctrl/pinconf.h @@ -28,7 +28,8 @@ struct seq_file; * is not available on this controller this should return -ENOTSUPP * and if it is available but disabled it should return -EINVAL * @pin_config_set: configure an individual pin - * @pin_config_group_get: get configurations for an entire pin group + * @pin_config_group_get: get configurations for an entire pin group; should + * return -ENOTSUPP and -EINVAL using the same rules as pin_config_get. * @pin_config_group_set: configure all pins in a group * @pin_config_dbg_parse_modify: optional debugfs to modify a pin configuration * @pin_config_dbg_show: optional debugfs display hook that will provide -- cgit v1.2.3 From 03fc7f9c99c1e7ae2925d459e8487f1a6f199f79 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 27 Jun 2018 16:20:28 +0200 Subject: printk/nmi: Prevent deadlock when accessing the main log buffer in NMI The commit 719f6a7040f1bdaf96 ("printk: Use the main logbuf in NMI when logbuf_lock is available") brought back the possible deadlocks in printk() and NMI. The check of logbuf_lock is done only in printk_nmi_enter() to prevent mixed output. But another CPU might take the lock later, enter NMI, and: + Both NMIs might be serialized by yet another lock, for example, the one in nmi_cpu_backtrace(). + The other CPU might get stopped in NMI, see smp_send_stop() in panic(). The only safe solution is to use trylock when storing the message into the main log-buffer. It might cause reordering when some lines go to the main lock buffer directly and others are delayed via the per-CPU buffer. It means that it is not useful in general. This patch replaces the problematic NMI deferred context with NMI direct context. It can be used to mark a code that might produce many messages in NMI and the risk of losing them is more critical than problems with eventual reordering. The context is then used when dumping trace buffers on oops. It was the primary motivation for the original fix. Also the reordering is even smaller issue there because some traces have their own time stamps. Finally, nmi_cpu_backtrace() need not longer be serialized because it will always us the per-CPU buffers again. Fixes: 719f6a7040f1bdaf96 ("printk: Use the main logbuf in NMI when logbuf_lock is available") Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20180627142028.11259-1-pmladek@suse.com To: Steven Rostedt Cc: Peter Zijlstra Cc: Tetsuo Handa Cc: Sergey Senozhatsky Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org Acked-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- include/linux/printk.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 6d7e800affd8..3ede9f46a494 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -148,9 +148,13 @@ void early_printk(const char *s, ...) { } #ifdef CONFIG_PRINTK_NMI extern void printk_nmi_enter(void); extern void printk_nmi_exit(void); +extern void printk_nmi_direct_enter(void); +extern void printk_nmi_direct_exit(void); #else static inline void printk_nmi_enter(void) { } static inline void printk_nmi_exit(void) { } +static inline void printk_nmi_direct_enter(void) { } +static inline void printk_nmi_direct_exit(void) { } #endif /* PRINTK_NMI */ #ifdef CONFIG_PRINTK -- cgit v1.2.3 From 6b1d83d274486615cc341e410467a98fd9c27c0a Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 15 Jun 2018 14:55:19 -0700 Subject: block: Remove bdev_nr_zones() Remove this function since it has no callers. This function was introduced in commit 6cc77e9cb080 ("block: introduce zoned block devices zone write locking"). Signed-off-by: Bart Van Assche Reviewed-by: Damien Le Moal Cc: Christoph Hellwig Cc: Matias Bjorling Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 79226ca8f80f..49a400afb146 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1639,15 +1639,6 @@ static inline unsigned int bdev_zone_sectors(struct block_device *bdev) return 0; } -static inline unsigned int bdev_nr_zones(struct block_device *bdev) -{ - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return blk_queue_nr_zones(q); - return 0; -} - static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; -- cgit v1.2.3 From 7c8542b7982264226cf94102950343185869b584 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 15 Jun 2018 14:55:20 -0700 Subject: block: Inline blk_queue_nr_zones() Since the implementation of blk_queue_nr_zones() is trivial and since it only has a single caller, inline this function. Signed-off-by: Bart Van Assche Reviewed-by: Damien Le Moal Cc: Matias Bjorling Cc: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49a400afb146..905daa7c647e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -800,11 +800,6 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } -static inline unsigned int blk_queue_nr_zones(struct request_queue *q) -{ - return q->nr_zones; -} - static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { -- cgit v1.2.3 From 6a5ac9846508ad7d1d23881d9d5add35f2e6ae71 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 15 Jun 2018 14:55:21 -0700 Subject: block: Make struct request_queue smaller for CONFIG_BLK_DEV_ZONED=n Exclude zoned block device members from struct request_queue for CONFIG_BLK_DEV_ZONED == n. Avoid breaking the build by only building the code that uses these struct request_queue members if CONFIG_BLK_DEV_ZONED != n. Signed-off-by: Bart Van Assche Reviewed-by: Damien Le Moal Cc: Matias Bjorling Cc: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 905daa7c647e..ca5a8b046894 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -592,6 +592,7 @@ struct request_queue { struct queue_limits limits; +#ifdef CONFIG_BLK_DEV_ZONED /* * Zoned block device information for request dispatch control. * nr_zones is the total number of zones of the device. This is always @@ -612,6 +613,7 @@ struct request_queue { unsigned int nr_zones; unsigned long *seq_zones_bitmap; unsigned long *seq_zones_wlock; +#endif /* CONFIG_BLK_DEV_ZONED */ /* * sg stuff @@ -800,6 +802,7 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } +#ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { @@ -815,6 +818,7 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q, return false; return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap); } +#endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) { @@ -1065,6 +1069,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; } +#ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_rq_zone_no(struct request *rq) { return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); @@ -1074,6 +1079,7 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq) { return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq)); } +#endif /* CONFIG_BLK_DEV_ZONED */ /* * Some commands like WRITE SAME have a payload or data transfer size which -- cgit v1.2.3 From 5815839b3ca16bb1d45939270871169f6803a121 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 25 Jun 2018 19:31:47 +0800 Subject: blk-mq: introduce new lock for protecting hctx->dispatch_wait Now hctx->lock is only acquired when adding hctx->dispatch_wait to one wait queue, but not held when removing it from the wait queue. IO hang can be observed easily if SCHED RESTART is disabled, that means now RESTART exits just for fixing the issue in blk_mq_mark_tag_wait(). This patch fixes the issue by introducing hctx->dispatch_wait_lock and holding it for removing hctx->dispatch_wait in blk_mq_dispatch_wake(), since we need to avoid acquiring hctx->lock in irq context. Fixes: eb619fdb2d4cb8b3d3419 ("blk-mq: fix issue with shared tag queue re-running") Cc: Christoph Hellwig Cc: Omar Sandoval Cc: Bart Van Assche Tested-by: Andrew Jones Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index e3147eb74222..ea690254dab7 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -39,6 +39,7 @@ struct blk_mq_hw_ctx { struct blk_mq_ctx **ctxs; unsigned int nr_ctx; + spinlock_t dispatch_wait_lock; wait_queue_entry_t dispatch_wait; atomic_t wait_index; -- cgit v1.2.3 From 97889f9ac24f8d2fc8e703ea7f80c162bab10d4d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 25 Jun 2018 19:31:48 +0800 Subject: blk-mq: remove synchronize_rcu() from blk_mq_del_queue_tag_set() We have to remove synchronize_rcu() from blk_queue_cleanup(), otherwise long delay can be caused during lun probe. For removing it, we have to avoid to iterate the set->tag_list in IO path, eg, blk_mq_sched_restart(). This patch reverts 5b79413946d (Revert "blk-mq: don't handle TAG_SHARED in restart"). Given we have fixed enough IO hang issue, and there isn't any reason to restart all queues in one tags any more, see the following reasons: 1) blk-mq core can deal with shared-tags case well via blk_mq_get_driver_tag(), which can wake up queues waiting for driver tag. 2) SCSI is a bit special because it may return BLK_STS_RESOURCE if queue, target or host is ready, but SCSI built-in restart can cover all these well, see scsi_end_request(), queue will be rerun after any request initiated from this host/target is completed. In my test on scsi_debug(8 luns), this patch may improve IOPS by 20% ~ 30% when running I/O on these 8 luns concurrently. Fixes: 705cda97ee3a ("blk-mq: Make it safe to use RCU to iterate over blk_mq_tag_set.tag_list") Cc: Omar Sandoval Cc: Bart Van Assche Cc: Christoph Hellwig Cc: Martin K. Petersen Cc: linux-scsi@vger.kernel.org Reported-by: Andrew Jones Tested-by: Andrew Jones Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ca5a8b046894..9d05646d5059 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -442,8 +442,6 @@ struct request_queue { int nr_rqs[2]; /* # allocated [a]sync rqs */ int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ - atomic_t shared_hctx_restart; - struct blk_queue_stats *stats; struct rq_wb *rq_wb; -- cgit v1.2.3 From 6e768717304bdbe8d2897ca8298f6b58863fdc41 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 3 Jul 2018 09:03:16 -0600 Subject: blk-mq: dequeue request one by one from sw queue if hctx is busy It won't be efficient to dequeue request one by one from sw queue, but we have to do that when queue is busy for better merge performance. This patch takes the Exponential Weighted Moving Average(EWMA) to figure out if queue is busy, then only dequeue request one by one from sw queue when queue is busy. Fixes: b347689ffbca ("blk-mq-sched: improve dispatching from sw queue") Cc: Kashyap Desai Cc: Laurence Oberman Cc: Omar Sandoval Cc: Christoph Hellwig Cc: Bart Van Assche Cc: Hannes Reinecke Reported-by: Kashyap Desai Tested-by: Kashyap Desai Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ea690254dab7..d710e92874cc 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -35,9 +35,10 @@ struct blk_mq_hw_ctx { struct sbitmap ctx_map; struct blk_mq_ctx *dispatch_from; + unsigned int dispatch_busy; - struct blk_mq_ctx **ctxs; unsigned int nr_ctx; + struct blk_mq_ctx **ctxs; spinlock_t dispatch_wait_lock; wait_queue_entry_t dispatch_wait; -- cgit v1.2.3 From 08e18eab0c579ad84399c1899c11899734854eb2 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:14:50 -0400 Subject: block: add bi_blkg to the bio for cgroups Currently io.low uses a bi_cg_private to stash its private data for the blkg, however other blkcg policies may want to use this as well. Since we can get the private data out of the blkg, move this to bi_blkg in the bio and make it generic, then we can use bio_associate_blkg() to attach the blkg to the bio. Theoretically we could simply replace the bi_css with this since we can get to all the same information from the blkg, however you have to lookup the blkg, so for example wbc_init_bio() would have to lookup and possibly allocate the blkg for the css it was trying to attach to the bio. This could be problematic and result in us either not attaching the css at all to the bio, or falling back to the root blkcg if we are unable to allocate the corresponding blkg. So for now do this, and in the future if possible we could just replace the bi_css with bi_blkg and update the helpers to do the correct translation. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 + include/linux/blk_types.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index f08f5fe7bd08..a279ba384da9 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -555,6 +555,7 @@ do { \ #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); +int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); void bio_disassociate_task(struct bio *bio); void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 3c4f390aea4b..3364d42ebe08 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -179,8 +179,8 @@ struct bio { */ struct io_context *bi_ioc; struct cgroup_subsys_state *bi_css; + struct blkcg_gq *bi_blkg; #ifdef CONFIG_BLK_DEV_THROTTLING_LOW - void *bi_cg_private; struct bio_issue bi_issue; #endif #endif -- cgit v1.2.3 From c7c98fd37653955d3a17dd4f1fa67aba070096a9 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:14:51 -0400 Subject: block: introduce bio_issue_as_root_blkg Instead of forcing all file systems to get the right context on their bio's, simply check for REQ_META to see if we need to issue as the root blkg. We don't want to force all bio's to have the root blkg associated with them if REQ_META is set, as some controllers (blk-iolatency) need to know who the originating cgroup is so it can backcharge them for the work they are doing. This helper will make sure that the controllers do the proper thing wrt the IO priority and backcharging. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 6c666fd7de3c..69aa71dc0c04 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -238,6 +238,22 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) return css_to_blkcg(task_css(current, io_cgrp_id)); } +/** + * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg + * @return: true if this bio needs to be submitted with the root blkg context. + * + * In order to avoid priority inversions we sometimes need to issue a bio as if + * it were attached to the root blkg, and then backcharge to the actual owning + * blkg. The idea is we do bio_blkcg() to look up the actual context for the + * bio and attach the appropriate blkg to the bio. Then we call this helper and + * if it is true run with the root blkg for that queue and then do any + * backcharging to the originating cgroup once the io is complete. + */ +static inline bool bio_issue_as_root_blkg(struct bio *bio) +{ + return (bio->bi_opf & REQ_META); +} + /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest -- cgit v1.2.3 From 903d23f0a354f226fa78f1c1c34b60aaf992e812 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:14:52 -0400 Subject: blk-cgroup: allow controllers to output their own stats blk-iolatency has a few stats that it would like to print out, and instead of adding a bunch of crap to the generic code just provide a helper so that controllers can add stuff to the stat line if they want to. Hide it behind a boot option since it changes the output of io.stat from normal, and these stats are only interesting to developers. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 69aa71dc0c04..b41292726c0f 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -148,6 +148,8 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); +typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf, + size_t size); struct blkcg_policy { int plid; @@ -167,6 +169,7 @@ struct blkcg_policy { blkcg_pol_offline_pd_fn *pd_offline_fn; blkcg_pol_free_pd_fn *pd_free_fn; blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; + blkcg_pol_stat_pd_fn *pd_stat_fn; }; extern struct blkcg blkcg_root; -- cgit v1.2.3 From 0d1e0c7cd5909d6c6aa0957179318e13fcca971a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:14:53 -0400 Subject: blk: introduce REQ_SWAP Just like REQ_META, it's important to know the IO coming down is swap in order to guard against potential IO priority inversion issues with cgroups. Add REQ_SWAP and use it for all swap IO, and add it to our bio_issue_as_root_blkg helper. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 2 +- include/linux/blk_types.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index b41292726c0f..a8f9ba8f33a4 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -254,7 +254,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) */ static inline bool bio_issue_as_root_blkg(struct bio *bio) { - return (bio->bi_opf & REQ_META); + return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0; } /** diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 3364d42ebe08..0ffc34c5cc83 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -329,7 +329,7 @@ enum req_flag_bits { /* for driver use */ __REQ_DRV, - + __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; @@ -351,6 +351,7 @@ enum req_flag_bits { #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_DRV (1ULL << __REQ_DRV) +#define REQ_SWAP (1ULL << __REQ_SWAP) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) -- cgit v1.2.3 From 0d3bd88d54f513723602b361dccfc71639f50779 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 3 Jul 2018 11:14:54 -0400 Subject: swap,blkcg: issue swap io with the appropriate context For backcharging we need to know who the page belongs to when swapping it out. We don't worry about things that do ->rw_page (zram etc) at the moment, we're only worried about pages that actually go to a block device. Signed-off-by: Tejun Heo Signed-off-by: Josef Bacik Acked-by: Johannes Weiner Acked-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/bio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index a279ba384da9..a00dfff51aa5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -553,6 +553,13 @@ do { \ #define bio_dev(bio) \ disk_devt((bio)->bi_disk) +#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) +int bio_associate_blkcg_from_page(struct bio *bio, struct page *page); +#else +static inline int bio_associate_blkcg_from_page(struct bio *bio, + struct page *page) { return 0; } +#endif + #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); -- cgit v1.2.3 From d09d8df3a29403693d9d20cc34ed101f2c558e2b Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:14:55 -0400 Subject: blkcg: add generic throttling mechanism Since IO can be issued from literally anywhere it's almost impossible to do throttling without having some sort of adverse effect somewhere else in the system because of locking or other dependencies. The best way to solve this is to do the throttling when we know we aren't holding any other kernel resources. Do this by tracking throttling in a per-blkg basis, and if we require throttling flag the task that it needs to check before it returns to user space and possibly sleep there. This is to address the case where a process is doing work that is generating IO that can't be throttled, whether that is directly with a lot of REQ_META IO, or indirectly by allocating so much memory that it is swamping the disk with REQ_SWAP. We can't use task_add_work as we don't want to induce a memory allocation in the IO path, so simply saving the request queue in the task and flagging it to do the notify_resume thing achieves the same result without the overhead of a memory allocation. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 99 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/cgroup-defs.h | 3 ++ include/linux/sched.h | 8 ++++ include/linux/tracehook.h | 2 + 4 files changed, 112 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index a8f9ba8f33a4..de57de4831d5 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -136,6 +136,12 @@ struct blkcg_gq { struct blkg_policy_data *pd[BLKCG_MAX_POLS]; struct rcu_head rcu_head; + + atomic_t use_delay; + atomic64_t delay_nsec; + atomic64_t delay_start; + u64 last_delay; + int last_use; }; typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); @@ -241,6 +247,26 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) return css_to_blkcg(task_css(current, io_cgrp_id)); } +static inline bool blk_cgroup_congested(void) +{ + struct cgroup_subsys_state *css; + bool ret = false; + + rcu_read_lock(); + css = kthread_blkcg(); + if (!css) + css = task_css(current, io_cgrp_id); + while (css) { + if (atomic_read(&css->cgroup->congestion_count)) { + ret = true; + break; + } + css = css->parent; + } + rcu_read_unlock(); + return ret; +} + /** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg * @return: true if this bio needs to be submitted with the root blkg context. @@ -374,6 +400,21 @@ static inline void blkg_get(struct blkcg_gq *blkg) atomic_inc(&blkg->refcnt); } +/** + * blkg_try_get - try and get a blkg reference + * @blkg: blkg to get + * + * This is for use when doing an RCU lookup of the blkg. We may be in the midst + * of freeing this blkg, so we can only use it if the refcnt is not zero. + */ +static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) +{ + if (atomic_inc_not_zero(&blkg->refcnt)) + return blkg; + return NULL; +} + + void __blkg_release_rcu(struct rcu_head *rcu); /** @@ -734,6 +775,59 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, return !throtl; } +static inline void blkcg_use_delay(struct blkcg_gq *blkg) +{ + if (atomic_add_return(1, &blkg->use_delay) == 1) + atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); +} + +static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) +{ + int old = atomic_read(&blkg->use_delay); + + if (old == 0) + return 0; + + /* + * We do this song and dance because we can race with somebody else + * adding or removing delay. If we just did an atomic_dec we'd end up + * negative and we'd already be in trouble. We need to subtract 1 and + * then check to see if we were the last delay so we can drop the + * congestion count on the cgroup. + */ + while (old) { + int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1); + if (cur == old) + break; + old = cur; + } + + if (old == 0) + return 0; + if (old == 1) + atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); + return 1; +} + +static inline void blkcg_clear_delay(struct blkcg_gq *blkg) +{ + int old = atomic_read(&blkg->use_delay); + if (!old) + return; + /* We only want 1 person clearing the congestion count for this blkg. */ + while (old) { + int cur = atomic_cmpxchg(&blkg->use_delay, old, 0); + if (cur == old) { + atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); + break; + } + old = cur; + } +} + +void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); +void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); +void blkcg_maybe_throttle_current(void); #else /* CONFIG_BLK_CGROUP */ struct blkcg { @@ -753,8 +847,13 @@ struct blkcg_policy { #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) +static inline void blkcg_maybe_throttle_current(void) { } +static inline bool blk_cgroup_congested(void) { return false; } + #ifdef CONFIG_BLOCK +static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } + static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } static inline int blkcg_init_queue(struct request_queue *q) { return 0; } static inline void blkcg_drain_queue(struct request_queue *q) { } diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index c0e68f903011..ff20b677fb9f 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -438,6 +438,9 @@ struct cgroup { /* used to store eBPF programs */ struct cgroup_bpf bpf; + /* If there is block congestion on this cgroup. */ + atomic_t congestion_count; + /* ids of the ancestors at each level including self */ int ancestor_ids[]; }; diff --git a/include/linux/sched.h b/include/linux/sched.h index 43731fe51c97..c2e993de67ec 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -734,6 +734,10 @@ struct task_struct { /* disallow userland-initiated cgroup migration */ unsigned no_cgroup_migration:1; #endif +#ifdef CONFIG_BLK_CGROUP + /* to be used once the psi infrastructure lands upstream. */ + unsigned use_memdelay:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -1151,6 +1155,10 @@ struct task_struct { unsigned int memcg_nr_pages_over_high; #endif +#ifdef CONFIG_BLK_CGROUP + struct request_queue *throttle_queue; +#endif + #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 4a8841963c2e..05589a3e37f4 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -51,6 +51,7 @@ #include #include #include +#include struct linux_binprm; /* @@ -192,6 +193,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) task_work_run(); mem_cgroup_handle_over_high(); + blkcg_maybe_throttle_current(); } #endif /* */ -- cgit v1.2.3 From 2cf855837b89d92996cf264713f3bed2bf9b0b4f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 3 Jul 2018 11:14:56 -0400 Subject: memcontrol: schedule throttling if we are congested Memory allocations can induce swapping via kswapd or direct reclaim. If we are having IO done for us by kswapd and don't actually go into direct reclaim we may never get scheduled for throttling. So instead check to see if our cgroup is congested, and if so schedule the throttling. Before we return to user space the throttling stuff will only throttle if we actually required it. Signed-off-by: Tejun Heo Signed-off-by: Josef Bacik Acked-by: Johannes Weiner Acked-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/memcontrol.h | 13 +++++++++++++ include/linux/swap.h | 11 ++++++++++- 2 files changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6c6fb116e925..680d3395fc83 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -317,6 +317,9 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp, bool compound); +int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask, struct mem_cgroup **memcgp, + bool compound); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare, bool compound); void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, @@ -789,6 +792,16 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, return 0; } +static inline int mem_cgroup_try_charge_delay(struct page *page, + struct mm_struct *mm, + gfp_t gfp_mask, + struct mem_cgroup **memcgp, + bool compound) +{ + *memcgp = NULL; + return 0; +} + static inline void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare, bool compound) diff --git a/include/linux/swap.h b/include/linux/swap.h index c063443d8638..1a8bd05a335e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -629,7 +629,6 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) return memcg->swappiness; } - #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { @@ -637,6 +636,16 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) } #endif +#if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) +extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node, + gfp_t gfp_mask); +#else +static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, + int node, gfp_t gfp_mask) +{ +} +#endif + #ifdef CONFIG_MEMCG_SWAP extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); -- cgit v1.2.3 From a79050434b45959f397042080fd1d70ffa9bd9df Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 09:32:35 -0600 Subject: blk-rq-qos: refactor out common elements of blk-wbt blkcg-qos is going to do essentially what wbt does, only on a cgroup basis. Break out the common code that will be shared between blkcg-qos and wbt into blk-rq-qos.* so they can both utilize the same infrastructure. Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9d05646d5059..137759862f07 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -42,7 +42,7 @@ struct bsg_job; struct blkcg_gq; struct blk_flush_queue; struct pr_ops; -struct rq_wb; +struct rq_qos; struct blk_queue_stats; struct blk_stat_callback; @@ -443,7 +443,7 @@ struct request_queue { int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ struct blk_queue_stats *stats; - struct rq_wb *rq_wb; + struct rq_qos *rq_qos; /* * If blkcg is not used, @q->root_rl serves all requests. If blkcg -- cgit v1.2.3 From d70675121546c35feaceebf7ed9caed8716640f3 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:15:01 -0400 Subject: block: introduce blk-iolatency io controller Current IO controllers for the block layer are less than ideal for our use case. The io.max controller is great at hard limiting, but it is not work conserving. This patch introduces io.latency. You provide a latency target for your group and we monitor the io in short windows to make sure we are not exceeding those latency targets. This makes use of the rq-qos infrastructure and works much like the wbt stuff. There are a few differences from wbt - It's bio based, so the latency covers the whole block layer in addition to the actual io. - We will throttle all IO types that comes in here if we need to. - We use the mean latency over the 100ms window. This is because writes can be particularly fast, which could give us a false sense of the impact of other workloads on our protected workload. - By default there's no throttling, we set the queue_depth to INT_MAX so that we can have as many outstanding bio's as we're allowed to. Only at throttle time do we pay attention to the actual queue depth. - We backcharge cgroups for root cg issued IO and induce artificial delays in order to deal with cases like metadata only or swap heavy workloads. In testing this has worked out relatively well. Protected workloads will throttle noisy workloads down to 1 io at time if they are doing normal IO on their own, or induce up to a 1 second delay per syscall if they are doing a lot of root issued IO (metadata/swap IO). Our testing has revolved mostly around our production web servers where we have hhvm (the web server application) in a protected group and everything else in another group. We see slightly higher requests per second (RPS) on the test tier vs the control tier, and much more stable RPS across all machines in the test tier vs the control tier. Another test we run is a slow memory allocator in the unprotected group. Before this would eventually push us into swap and cause the whole box to die and not recover at all. With these patches we see slight RPS drops (usually 10-15%) before the memory consumer is properly killed and things recover within seconds. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 0ffc34c5cc83..e13449a379a1 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -180,9 +180,7 @@ struct bio { struct io_context *bi_ioc; struct cgroup_subsys_state *bi_css; struct blkcg_gq *bi_blkg; -#ifdef CONFIG_BLK_DEV_THROTTLING_LOW struct bio_issue bi_issue; -#endif #endif union { #if defined(CONFIG_BLK_DEV_INTEGRITY) -- cgit v1.2.3 From d8095f94e19581057bcad35b8a725aa739e77595 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 2 Jul 2018 15:08:10 +0200 Subject: dmaengine: add support for reporting pause and resume separately 'cmd_pause' DMA channel capability means that respective DMA engine supports both pausing and resuming given DMA channel. However, in some cases it is important to know if DMA channel can be paused without the need to resume it. This is a typical requirement for proper residue reading on transfer timeout in UART drivers. There are also some DMA engines with limited hardware, which doesn't really support resuming. Reporting pause and resume capabilities separately allows UART drivers to properly check for the really required capabilities and operate in DMA mode also in systems with limited DMA hardware. On the other hand drivers, which rely on full channel suspend/resume support, should now check for both 'pause' and 'resume' features. Existing clients of dma_get_slave_caps() have been checked and the only driver which rely on proper channel resuming is soc-generic-dmaengine-pcm driver, which has been updated to check the newly added capability. Existing 'cmd_pause' now only indicates that DMA engine support pausing given DMA channel. Signed-off-by: Marek Szyprowski Acked-by: Mark Brown Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 861be5cab1df..c8c3a7a93802 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -415,7 +415,9 @@ enum dma_residue_granularity { * each type, the dma controller should set BIT() and same * should be checked by controller as well * @max_burst: max burst capability per-transfer - * @cmd_pause: true, if pause and thereby resume is supported + * @cmd_pause: true, if pause is supported (i.e. for reading residue or + * for resume later) + * @cmd_resume: true, if resume is supported * @cmd_terminate: true, if terminate cmd is supported * @residue_granularity: granularity of the reported transfer residue * @descriptor_reuse: if a descriptor can be reused by client and @@ -427,6 +429,7 @@ struct dma_slave_caps { u32 directions; u32 max_burst; bool cmd_pause; + bool cmd_resume; bool cmd_terminate; enum dma_residue_granularity residue_granularity; bool descriptor_reuse; -- cgit v1.2.3 From ffcfe25bb50f27395e15fa999f1a7eb769f55360 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 9 Jul 2018 12:19:38 -0400 Subject: net: Add support for subordinate device traffic classes This patch is meant to provide the basic tools needed to allow us to create subordinate device traffic classes. The general idea here is to allow subdividing the queues of a device into queue groups accessible through an upper device such as a macvlan. The idea here is to enforce the idea that an upper device has to be a single queue device, ideally with IFF_NO_QUQUE set. With that being the case we can pretty much guarantee that the tc_to_txq mappings and XPS maps for the upper device are unused. As such we could reuse those in order to support subdividing the lower device and distributing those queues between the subordinate devices. In order to distinguish between a regular set of traffic classes and if a device is carrying subordinate traffic classes I changed num_tc from a u8 to a s16 value and use the negative values to represent the subordinate pool values. So starting at -1 and running to -32768 we can encode those as pool values, and the existing values of 0 to 15 can be maintained. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/netdevice.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b683971e500d..b1ff77276bc4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -575,6 +575,9 @@ struct netdev_queue { * (/sys/class/net/DEV/Q/trans_timeout) */ unsigned long trans_timeout; + + /* Subordinate device that the queue has been assigned to */ + struct net_device *sb_dev; /* * write-mostly part */ @@ -1991,7 +1994,7 @@ struct net_device { #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; #endif - u8 num_tc; + s16 num_tc; struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; u8 prio_tc_map[TC_BITMASK + 1]; @@ -2045,6 +2048,17 @@ int netdev_get_num_tc(struct net_device *dev) return dev->num_tc; } +void netdev_unbind_sb_channel(struct net_device *dev, + struct net_device *sb_dev); +int netdev_bind_sb_channel_queue(struct net_device *dev, + struct net_device *sb_dev, + u8 tc, u16 count, u16 offset); +int netdev_set_sb_channel(struct net_device *dev, u16 channel); +static inline int netdev_get_sb_channel(struct net_device *dev) +{ + return max_t(int, -dev->num_tc, 0); +} + static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) -- cgit v1.2.3 From eadec877ce9ca46a94e9036b5a44e7941d4fc501 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 9 Jul 2018 12:19:48 -0400 Subject: net: Add support for subordinate traffic classes to netdev_pick_tx This change makes it so that we can support the concept of subordinate device traffic classes to the core networking code. In doing this we can start pulling out the driver specific bits needed to support selecting a queue based on an upper device. The solution at is currently stands is only partially implemented. I have the start of some XPS bits in here, but I would still need to allow for configuration of the XPS maps on the queues reserved for the subordinate devices. For now I am using the reference to the sb_dev XPS map as just a way to skip the lookup of the lower device XPS map for now as that would result in the wrong queue being picked. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b1ff77276bc4..fda0bcda7a42 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2103,7 +2103,7 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + struct net_device *sb_dev); /* returns the headroom that the master device needs to take in account * when forwarding to this dev @@ -2568,7 +2568,7 @@ void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); -int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); +int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); -- cgit v1.2.3 From a4ea8a3dacc312c3402c78f6e4843afdda9b43a0 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 9 Jul 2018 12:19:54 -0400 Subject: net: Add generic ndo_select_queue functions This patch adds a generic version of the ndo_select_queue functions for either returning 0 or selecting a queue based on the processor ID. This is generally meant to just reduce the number of functions we have to change in the future when we have to deal with ndo_select_queue changes. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fda0bcda7a42..46f4c44ce3e4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2567,6 +2567,10 @@ void dev_close(struct net_device *dev); void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); +u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback); +u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); -- cgit v1.2.3 From 4f49dec9075aa0277b8c9c657ec31e6361f88724 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 9 Jul 2018 12:19:59 -0400 Subject: net: allow ndo_select_queue to pass netdev This patch makes it so that instead of passing a void pointer as the accel_priv we instead pass a net_device pointer as sb_dev. Making this change allows us to pass the subordinate device through to the fallback function eventually so that we can keep the actual code in the ndo_select_queue call as focused on possible on the exception cases. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/netdevice.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 46f4c44ce3e4..bbf062c1ca8a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -957,7 +957,8 @@ struct dev_ifalias { * those the driver believes to be appropriate. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - * void *accel_priv, select_queue_fallback_t fallback); + * struct net_device *sb_dev, + * select_queue_fallback_t fallback); * Called to decide which queue to use when device supports multiple * transmit queues. * @@ -1229,7 +1230,7 @@ struct net_device_ops { netdev_features_t features); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, + struct net_device *sb_dev, select_queue_fallback_t fallback); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); @@ -2568,9 +2569,11 @@ void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback); + struct net_device *sb_dev, + select_queue_fallback_t fallback); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback); + struct net_device *sb_dev, + select_queue_fallback_t fallback); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); -- cgit v1.2.3 From 8ec56fc3c5ee6f9700adac190e9ce5b8859a58b6 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 9 Jul 2018 12:20:04 -0400 Subject: net: allow fallback function to pass netdev For most of these calls we can just pass NULL through to the fallback function as the sb_dev. The only cases where we cannot are the cases where we might be dealing with either an upper device or a driver that would have configured things to support an sb_dev itself. The only driver that has any significant change in this patch set should be ixgbe as we can drop the redundant functionality that existed in both the ndo_select_queue function and the fallback function that was passed through to us. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bbf062c1ca8a..2daf2fa6554f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -793,7 +793,8 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, } typedef u16 (*select_queue_fallback_t)(struct net_device *dev, - struct sk_buff *skb); + struct sk_buff *skb, + struct net_device *sb_dev); enum tc_setup_type { TC_SETUP_QDISC_MQPRIO, -- cgit v1.2.3 From 9f17dbf04ddf55ae48f5bbafea4c4920ea943215 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 9 Jul 2018 18:10:02 +0100 Subject: netfilter: fix use-after-free in NF_HOOK_LIST nf_hook() can free the skb, so we need to remove it from the list before calling, and add passed skbs to a sublist afterwards. Fixes: 17266ee93984 ("net: ipv4: listified version of ip_rcv") Reported-by: Dan Carpenter Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/netfilter.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 5a5e0a2ab2a3..23b48de8c2e2 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -294,12 +294,16 @@ NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { struct sk_buff *skb, *next; + struct list_head sublist; + INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { - int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn); - if (ret != 1) - list_del(&skb->list); + list_del(&skb->list); + if (nf_hook(pf, hook, net, sk, skb, in, out, okfn) == 1) + list_add_tail(&skb->list, &sublist); } + /* Put passed packets back on main list */ + list_splice(&sublist, head); } /* Call setsockopt() */ -- cgit v1.2.3 From 7f35e63dbfcb627bd30bac45702ffdf1ddde1516 Mon Sep 17 00:00:00 2001 From: Faiz Abbas Date: Mon, 9 Jul 2018 22:18:38 +0530 Subject: bus: ti-sysc: Add support for using ti-sysc for MCAN on dra76x The dra76x MCAN generic interconnect module has a its own format for the bits in the control registers. Therefore add a new module type, new regbits and new capabilities specific to the MCAN module. Acked-by: Rob Herring CC: Tony Lindgren Signed-off-by: Faiz Abbas Signed-off-by: Tony Lindgren --- include/linux/platform_data/ti-sysc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 990aad477458..2efa3470a451 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -14,6 +14,7 @@ enum ti_sysc_module_type { TI_SYSC_OMAP4_SR, TI_SYSC_OMAP4_MCASP, TI_SYSC_OMAP4_USB_HOST_FS, + TI_SYSC_DRA7_MCAN, }; struct ti_sysc_cookie { -- cgit v1.2.3 From 74655749a58405e259eaaba66bfc391fdbe1e34e Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Mon, 9 Jul 2018 13:03:16 +0530 Subject: ARM: OMAP2+: sleep33/43xx: Make sleep actions configurable Add an argument to the sleep33xx and sleep43xx code to allow us to set flags to determine which portions of the code get called in order to use the same code for multiple power saving modes. This patch allows us to decide whether or not we flush and disable caches, save EMIF context, put the memory into self refresh and disable the EMIF, and/or invoke the wkup_m3 when entering into WFI. Signed-off-by: Dave Gerlach Signed-off-by: Tero Kristo Signed-off-by: Keerthy Signed-off-by: Tony Lindgren --- include/linux/platform_data/pm33xx.h | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/pm33xx.h b/include/linux/platform_data/pm33xx.h index f9bed2a0af9d..d231265c135c 100644 --- a/include/linux/platform_data/pm33xx.h +++ b/include/linux/platform_data/pm33xx.h @@ -12,6 +12,29 @@ #include #include +/* + * WFI Flags for sleep code control + * + * These flags allow PM code to exclude certain operations from happening + * in the low level ASM code found in sleep33xx.S and sleep43xx.S + * + * WFI_FLAG_FLUSH_CACHE: Flush the ARM caches and disable caching. Only + * needed when MPU will lose context. + * WFI_FLAG_SELF_REFRESH: Let EMIF place DDR memory into self-refresh and + * disable EMIF. + * WFI_FLAG_SAVE_EMIF: Save context of all EMIF registers and restore in + * resume path. Only needed if PER domain loses context + * and must also have WFI_FLAG_SELF_REFRESH set. + * WFI_FLAG_WAKE_M3: Disable MPU clock or clockdomain to cause wkup_m3 to + * execute when WFI instruction executes. + * WFI_FLAG_RTC_ONLY: Configure the RTC to enter RTC+DDR mode. + */ +#define WFI_FLAG_FLUSH_CACHE BIT(0) +#define WFI_FLAG_SELF_REFRESH BIT(1) +#define WFI_FLAG_SAVE_EMIF BIT(2) +#define WFI_FLAG_WAKE_M3 BIT(3) +#define WFI_FLAG_RTC_ONLY BIT(4) + #ifndef __ASSEMBLER__ struct am33xx_pm_sram_addr { void (*do_wfi)(void); @@ -23,7 +46,8 @@ struct am33xx_pm_sram_addr { struct am33xx_pm_platform_data { int (*init)(void); - int (*soc_suspend)(unsigned int state, int (*fn)(unsigned long)); + int (*soc_suspend)(unsigned int state, int (*fn)(unsigned long), + unsigned long args); struct am33xx_pm_sram_addr *(*get_sram_addrs)(void); }; -- cgit v1.2.3 From 8c5a916f4c8815196cc8a86b9582ca89422aac25 Mon Sep 17 00:00:00 2001 From: Keerthy Date: Mon, 9 Jul 2018 13:03:17 +0530 Subject: ARM: OMAP2+: sleep33/43xx: Add RTC-Mode support Add support for RTC mode to low level suspend code. This includes providing the rtc base address for the assembly code to configuring the PMIC_PWR_EN line late in suspend to enter RTC+DDR mode. Note: This patch also fold in left out space parameter for am33xx_emif_sram_table and am43xx_emif_sram_table Signed-off-by: Dave Gerlach Signed-off-by: Keerthy Signed-off-by: Tony Lindgren --- include/linux/platform_data/pm33xx.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/pm33xx.h b/include/linux/platform_data/pm33xx.h index d231265c135c..fbf5ed73c7cc 100644 --- a/include/linux/platform_data/pm33xx.h +++ b/include/linux/platform_data/pm33xx.h @@ -42,6 +42,7 @@ struct am33xx_pm_sram_addr { unsigned long *resume_offset; unsigned long *emif_sram_table; unsigned long *ro_sram_data; + unsigned long resume_address; }; struct am33xx_pm_platform_data { @@ -49,6 +50,7 @@ struct am33xx_pm_platform_data { int (*soc_suspend)(unsigned int state, int (*fn)(unsigned long), unsigned long args); struct am33xx_pm_sram_addr *(*get_sram_addrs)(void); + void __iomem *(*get_rtc_base_addr)(void); }; struct am33xx_pm_sram_data { @@ -60,6 +62,7 @@ struct am33xx_pm_sram_data { struct am33xx_pm_ro_sram_data { u32 amx3_pm_sram_data_virt; u32 amx3_pm_sram_data_phys; + void __iomem *rtc_base_virt; } __packed __aligned(8); #endif /* __ASSEMBLER__ */ -- cgit v1.2.3 From 7f69ae7fadd9dbebe563bfc28b993a2bc9c8acf9 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 28 Jun 2018 11:57:48 +0200 Subject: ARM: davinci: unduplicate aemif support All users now register platform devices using the ti-aemif driver. Remove the handcrafted aemif API. Signed-off-by: Bartosz Golaszewski Signed-off-by: Sekhar Nori --- include/linux/platform_data/mtd-davinci-aemif.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mtd-davinci-aemif.h b/include/linux/platform_data/mtd-davinci-aemif.h index 97948ac2bb9b..a403dd51dacc 100644 --- a/include/linux/platform_data/mtd-davinci-aemif.h +++ b/include/linux/platform_data/mtd-davinci-aemif.h @@ -33,5 +33,4 @@ struct davinci_aemif_timing { u8 ta; }; -int davinci_aemif_setup(struct platform_device *pdev); #endif -- cgit v1.2.3 From 25b4e70dcce92168eab4d8113817bb4dd130ebd2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 9 Jul 2018 09:41:48 -0600 Subject: driver core: allow stopping deferred probe after init Deferred probe will currently wait forever on dependent devices to probe, but sometimes a driver will never exist. It's also not always critical for a driver to exist. Platforms can rely on default configuration from the bootloader or reset defaults for things such as pinctrl and power domains. This is often the case with initial platform support until various drivers get enabled. There's at least 2 scenarios where deferred probe can render a platform broken. Both involve using a DT which has more devices and dependencies than the kernel supports. The 1st case is a driver may be disabled in the kernel config. The 2nd case is the kernel version may simply not have the dependent driver. This can happen if using a newer DT (provided by firmware perhaps) with a stable kernel version. Deferred probe issues can be difficult to debug especially if the console has dependencies or userspace fails to boot to a shell. There are also cases like IOMMUs where only built-in drivers are supported, so deferring probe after initcalls is not needed. The IOMMU subsystem implemented its own mechanism to handle this using OF_DECLARE linker sections. This commit adds makes ending deferred probe conditional on initcalls being completed or a debug timeout. Subsystems or drivers may opt-in by calling driver_deferred_probe_check_init_done() instead of unconditionally returning -EPROBE_DEFER. They may use additional information from DT or kernel's config to decide whether to continue to defer probe or not. The timeout mechanism is intended for debug purposes and WARNs loudly. The remaining deferred probe pending list will also be dumped after the timeout. Not that this timeout won't work for the console which needs to be enabled before userspace starts. However, if the console's dependencies are resolved, then the kernel log will be printed (as opposed to no output). Cc: Alexander Graf Signed-off-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 575c5a35ece5..d2acc78d279b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -339,6 +339,8 @@ struct device *driver_find_device(struct device_driver *drv, struct device *start, void *data, int (*match)(struct device *dev, void *data)); +int driver_deferred_probe_check_state(struct device *dev); + /** * struct subsys_interface - interfaces to device functions * @name: name of the device function -- cgit v1.2.3 From ac6bbf0cdf4206c517ac9789814c23e372ebce4d Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 9 Jul 2018 09:41:52 -0600 Subject: iommu: Remove IOMMU_OF_DECLARE Now that we use the driver core to stop deferred probe for missing drivers, IOMMU_OF_DECLARE can be removed. This is slightly less optimal than having a list of built-in drivers in that we'll now defer probe twice before giving up. This shouldn't have a significant impact on boot times as past discussions about deferred probe have given no evidence of deferred probe having a substantial impact. Cc: Robin Murphy Cc: Kukjin Kim Cc: Krzysztof Kozlowski Cc: Rob Clark Cc: Heiko Stuebner Cc: Frank Rowand Cc: linux-arm-kernel@lists.infradead.org Cc: iommu@lists.linux-foundation.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-arm-msm@vger.kernel.org Cc: linux-rockchip@lists.infradead.org Cc: devicetree@vger.kernel.org Acked-by: Will Deacon Acked-by: Marek Szyprowski Acked-by: Joerg Roedel Signed-off-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- include/linux/of_iommu.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h index 4fa654e4b5a9..f3d40dd7bb66 100644 --- a/include/linux/of_iommu.h +++ b/include/linux/of_iommu.h @@ -32,8 +32,4 @@ static inline const struct iommu_ops *of_iommu_configure(struct device *dev, #endif /* CONFIG_OF_IOMMU */ -extern struct of_device_id __iommu_of_table; - -#define IOMMU_OF_DECLARE(name, compat) OF_DECLARE_1(iommu, name, compat, NULL) - #endif /* __OF_IOMMU_H */ -- cgit v1.2.3 From aef92a8bed25d03b8f03ce499a56e8e8e5e2c05e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 10 Jul 2018 13:42:10 +0200 Subject: watchdog/softlockup: Fix the SOFTLOCKUP_DETECTOR=n build I got confused by all the various CONFIG options here about and conflated CONFIG_LOCKUP_DETECTOR and CONFIG_SOFTLOCKUP_DETECTOR. This results in a build failure for: CONFIG_LOCKUP_DETECTOR=y && CONFIG_SOFTLOCKUP_DETECTOR=n As reported by Abdul. Reported-and-tested-by: Abdul Haleem Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-next Cc: linuxppc-dev Cc: mpe Cc: sachinp Cc: stephen Rothwell Fixes: 9cf57731b63e ("watchdog/softlockup: Replace "watchdog/%u" threads with cpu_stop_work") Link: http://lkml.kernel.org/r/20180710114210.GI2476@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 80664bbeca43..08f9247e9827 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -33,15 +33,10 @@ extern int sysctl_hardlockup_all_cpu_backtrace; #define sysctl_hardlockup_all_cpu_backtrace 0 #endif /* !CONFIG_SMP */ -extern int lockup_detector_online_cpu(unsigned int cpu); -extern int lockup_detector_offline_cpu(unsigned int cpu); - #else /* CONFIG_LOCKUP_DETECTOR */ static inline void lockup_detector_init(void) { } static inline void lockup_detector_soft_poweroff(void) { } static inline void lockup_detector_cleanup(void) { } -#define lockup_detector_online_cpu NULL -#define lockup_detector_offline_cpu NULL #endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR @@ -50,12 +45,18 @@ extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; -#else + +extern int lockup_detector_online_cpu(unsigned int cpu); +extern int lockup_detector_offline_cpu(unsigned int cpu); +#else /* CONFIG_SOFTLOCKUP_DETECTOR */ static inline void touch_softlockup_watchdog_sched(void) { } static inline void touch_softlockup_watchdog(void) { } static inline void touch_softlockup_watchdog_sync(void) { } static inline void touch_all_softlockup_watchdogs(void) { } -#endif + +#define lockup_detector_online_cpu NULL +#define lockup_detector_offline_cpu NULL +#endif /* CONFIG_SOFTLOCKUP_DETECTOR */ #ifdef CONFIG_DETECT_HUNG_TASK void reset_hung_task_detector(void); -- cgit v1.2.3 From 8d3e994241e6bcc7ead2b918c4f15b7683afa90a Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 10 Jul 2018 09:57:58 +0100 Subject: arm_pmu: Clean up maximum period handling Each PMU defines their max_period of the counter as the maximum value that can be counted. Since all the PMU backends support 32bit counters by default, let us remove the redundant field. No functional changes. Cc: Will Deacon Acked-by: Mark Rutland Reviewed-by: Julien Thierry Signed-off-by: Suzuki K Poulose Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index ad5444491975..12c30a22fc8d 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -94,7 +94,6 @@ struct arm_pmu { void (*reset)(void *); int (*map_event)(struct perf_event *event); int num_events; - u64 max_period; bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); -- cgit v1.2.3 From 3a95200d3f89afd8b67f39d88d36cc7ec96ce385 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 10 Jul 2018 09:57:59 +0100 Subject: arm_pmu: Change API to support 64bit counter values Convert the {read/write}_counter APIs to handle 64bit values to enable supporting chained event counters. The backends still use 32bit values and we pass them 32bit values only. So in effect there are no functional changes. Cc: Will Deacon Acked-by: Mark Rutland Reviewed-by: Julien Thierry Signed-off-by: Suzuki K Poulose Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 12c30a22fc8d..f7126a21df30 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -87,8 +87,8 @@ struct arm_pmu { struct perf_event *event); int (*set_event_filter)(struct hw_perf_event *evt, struct perf_event_attr *attr); - u32 (*read_counter)(struct perf_event *event); - void (*write_counter)(struct perf_event *event, u32 val); + u64 (*read_counter)(struct perf_event *event); + void (*write_counter)(struct perf_event *event, u64 val); void (*start)(struct arm_pmu *); void (*stop)(struct arm_pmu *); void (*reset)(void *); -- cgit v1.2.3 From e2da97d328d4951d25f6634eda7213f7257417b6 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 10 Jul 2018 09:58:00 +0100 Subject: arm_pmu: Add support for 64bit event counters Each PMU has a set of 32bit event counters. But in some special cases, the events could be counted using counters which are effectively 64bit wide. e.g, Arm V8 PMUv3 has a 64 bit cycle counter which can count only the CPU cycles. Also, the PMU can chain the event counters to effectively count as a 64bit counter. Add support for tracking the events that uses 64bit counters. This only affects the periods set for each counter in the core driver. Cc: Will Deacon Reviewed-by: Julien Thierry Acked-by: Mark Rutland Signed-off-by: Suzuki K Poulose Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index f7126a21df30..10f92e1d8e7b 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -25,6 +25,12 @@ */ #define ARMPMU_MAX_HWEVENTS 32 +/* + * ARM PMU hw_event flags + */ +/* Event uses a 64bit counter */ +#define ARMPMU_EVT_64BIT 1 + #define HW_OP_UNSUPPORTED 0xFFFF #define C(_x) PERF_COUNT_HW_CACHE_##_x #define CACHE_OP_UNSUPPORTED 0xFFFF -- cgit v1.2.3 From 14b470b56840dbb093abd71f214e9d63770c87b8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 6 Jul 2018 22:19:07 +0200 Subject: scsi: target: sbitmap: add seq_file forward declaration The target core runs into a warning in the linux/sbitmap.h file in some configurations: In file included from include/target/target_core_base.h:7, from drivers/target/target_core_fabric_lib.c:41: include/linux/sbitmap.h:331:46: error: 'struct seq_file' declared inside parameter list will not be visible outside of this definition or declaration [-Werror] void sbitmap_show(struct sbitmap *sb, struct seq_file *m); ^~~~~~~~ In general, headers should not depend on others being included first, so this fixes it with a forward declaration for that struct name, but we probably want to merge the patch through the scsi tree to help bisection. Fixes: 10e9cbb6b531 ("scsi: target: Convert target drivers to use sbitmap") Signed-off-by: Arnd Bergmann Reviewed-by: Bart Van Assche Reviewed-by: Omar Sandoval Reviewed-by: Jens Axboe Signed-off-by: Martin K. Petersen --- include/linux/sbitmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index e6539536dea9..804a50983ec5 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -23,6 +23,8 @@ #include #include +struct seq_file; + /** * struct sbitmap_word - Word in a &struct sbitmap. */ -- cgit v1.2.3 From b60a60405fb95a688eb2ef4ef20f5fcaa7b64f68 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Fri, 6 Jul 2018 17:37:19 +0200 Subject: netfilter: Add nf_ct_get_tuple_skb global lookup function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds a global netfilter function to extract a conntrack tuple from an skb. The function uses a new function added to nf_ct_hook, which will try to get the tuple from skb->_nfct, and do a full lookup if that fails. This makes it possible to use the lookup function before the skb has passed through the conntrack init hooks (e.g., in an ingress qdisc). The tuple is copied to the caller to avoid issues with reference counting. The function returns false if conntrack is not loaded, allowing it to be used without incurring a module dependency on conntrack. This is used by the NAT mode in sch_cake. Cc: netfilter-devel@vger.kernel.org Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/linux/netfilter.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 23b48de8c2e2..07efffd0c759 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -414,8 +414,17 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; void nf_ct_attach(struct sk_buff *, const struct sk_buff *); +struct nf_conntrack_tuple; +bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, + const struct sk_buff *skb); #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} +struct nf_conntrack_tuple; +static inline bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, + const struct sk_buff *skb) +{ + return false; +} #endif struct nf_conn; @@ -424,6 +433,8 @@ enum ip_conntrack_info; struct nf_ct_hook { int (*update)(struct net *net, struct sk_buff *skb); void (*destroy)(struct nf_conntrack *); + bool (*get_tuple_skb)(struct nf_conntrack_tuple *, + const struct sk_buff *); }; extern struct nf_ct_hook __rcu *nf_ct_hook; -- cgit v1.2.3 From 19f391eb05b8b005f2907ddc8f284487b446abf3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 11:19:32 -0400 Subject: turn filp_clone_open() into inline wrapper for dentry_open() it's exactly the same thing as dentry_open(&file->f_path, file->f_flags, file->f_cred) ... and rename it to file_clone_open(), while we are at it. 'filp' naming convention is bogus; sure, it's "file pointer", but we generally don't do that kind of Hungarian notation. Some of the instances have too many callers to touch, but this one has only two, so let's sanitize it while we can... Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/fs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index aa9b4c169ed2..c4ca4c9c1130 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2422,7 +2422,10 @@ extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); -extern struct file *filp_clone_open(struct file *); +static inline struct file *file_clone_open(struct file *file) +{ + return dentry_open(&file->f_path, file->f_flags, file->f_cred); +} extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); -- cgit v1.2.3 From b4e7a7a88b5d060650094b8d3454bc521d669f6a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 11:17:54 -0400 Subject: drm_mode_create_lease_ioctl(): fix open-coded filp_clone_open() Failure of ->open() should *not* be followed by fput(). Fixed by using filp_clone_open(), which gets the cleanups right. Cc: stable@vger.kernel.org Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5c91108846db..aa9b4c169ed2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2422,6 +2422,7 @@ extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); +extern struct file *filp_clone_open(struct file *); extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); -- cgit v1.2.3 From fae68031f7fbc8b6db58d87830ba7ed1d696fbb1 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Fri, 6 Jul 2018 07:35:50 +0200 Subject: w1: core: match sub-nodes of bus masters in devicetree Once a new slave device is detected, match it against all sub-nodes of the master bus controller. If a match is found, set the slave device's of_node pointer. Signed-off-by: Daniel Mack Signed-off-by: Sebastian Reichel --- include/linux/w1.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/w1.h b/include/linux/w1.h index 694101f744c7..3111585c371f 100644 --- a/include/linux/w1.h +++ b/include/linux/w1.h @@ -274,6 +274,8 @@ struct w1_family { struct w1_family_ops *fops; + const struct of_device_id *of_match_table; + atomic_t refcnt; }; -- cgit v1.2.3 From 23ebda2fc715534d383d59ae6740d4e3ebd43798 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 11 Jul 2018 17:21:05 +0200 Subject: libata: remove ata_sff_data_xfer_noirq() ata_sff_data_xfer_noirq() is invoked via the ->sff_data_xfer hook. The latter is invoked by ata_pio_sector(), atapi_send_cdb() and __atapi_pio_bytes() which in turn is invoked by ata_sff_hsm_move(). The latter function requires that the "ap->lock" lock is held which needs to be taken with disabled interrupts. There is no need have to have ata_sff_data_xfer_noirq() which invokes ata_sff_data_xfer32() with disabled interrupts because at this point the interrupts are already disabled. Remove the function and its references to it and replace all callers with ata_sff_data_xfer32(). Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Tejun Heo --- include/linux/libata.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 8b8946dd63b9..aa8583655a18 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1832,8 +1832,6 @@ extern unsigned int ata_sff_data_xfer(struct ata_queued_cmd *qc, unsigned char *buf, unsigned int buflen, int rw); extern unsigned int ata_sff_data_xfer32(struct ata_queued_cmd *qc, unsigned char *buf, unsigned int buflen, int rw); -extern unsigned int ata_sff_data_xfer_noirq(struct ata_queued_cmd *qc, - unsigned char *buf, unsigned int buflen, int rw); extern void ata_sff_irq_on(struct ata_port *ap); extern void ata_sff_irq_clear(struct ata_port *ap); extern int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, -- cgit v1.2.3 From 9dc55f1389f9569acf9659e58dd836a9c70df217 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Jul 2018 22:26:05 -0700 Subject: iomap: add support for sub-pagesize buffered I/O without buffer heads After already supporting a simple implementation of buffered writes for the blocksize == PAGE_SIZE case in the last commit this adds full support even for smaller block sizes. There are three bits of per-block information in the buffer_head structure that really matter for the iomap read and write path: - uptodate status (BH_uptodate) - marked as currently under read I/O (BH_Async_Read) - marked as currently under write I/O (BH_Async_Write) Instead of having new per-block structures this now adds a per-page structure called struct iomap_page to track this information in a slightly different form: - a bitmap for the per-block uptodate status. For worst case of a 64k page size system this bitmap needs to contain 128 bits. For the typical 4k page size case it only needs 8 bits, although we still need a full unsigned long due to the way the atomic bitmap API works. - two atomic_t counters are used to track the outstanding read and write counts There is quite a bit of boilerplate code as the buffered I/O path uses various helper methods, but the actual code is very straight forward. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 5eb9ca8d7ce5..3555d54bf79a 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -2,6 +2,9 @@ #ifndef LINUX_IOMAP_H #define LINUX_IOMAP_H 1 +#include +#include +#include #include struct address_space; @@ -98,12 +101,40 @@ struct iomap_ops { ssize_t written, unsigned flags, struct iomap *iomap); }; +/* + * Structure allocate for each page when block size < PAGE_SIZE to track + * sub-page uptodate status and I/O completions. + */ +struct iomap_page { + atomic_t read_count; + atomic_t write_count; + DECLARE_BITMAP(uptodate, PAGE_SIZE / 512); +}; + +static inline struct iomap_page *to_iomap_page(struct page *page) +{ + if (page_has_private(page)) + return (struct iomap_page *)page_private(page); + return NULL; +} + ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); int iomap_readpages(struct address_space *mapping, struct list_head *pages, unsigned nr_pages, const struct iomap_ops *ops); int iomap_set_page_dirty(struct page *page); +int iomap_is_partially_uptodate(struct page *page, unsigned long from, + unsigned long count); +int iomap_releasepage(struct page *page, gfp_t gfp_mask); +void iomap_invalidatepage(struct page *page, unsigned int offset, + unsigned int len); +#ifdef CONFIG_MIGRATION +int iomap_migrate_page(struct address_space *mapping, struct page *newpage, + struct page *page, enum migrate_mode mode); +#else +#define iomap_migrate_page NULL +#endif int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, -- cgit v1.2.3 From 3443b00e07eed5798605ba6524de37e1d3f1a4bf Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Tue, 10 Jul 2018 10:02:57 +0300 Subject: team: Publish team_port_get_rcu() A follow-up patch adds a new entry point, team_port_dev_txable(). Making it an ordinary exported function would mean that any module that may need the service in one of the supported configurations also unconditionally needs to pull in the team module, whether or not the user actually intends to create team interfaces. To prevent that, team_port_dev_txable() is defined in if_team.h, and therefore all dependencies of that function also need to be publicly-visible. Therefore move team_port_get_rcu() from team.c to if_team.h. Signed-off-by: Petr Machata Reviewed-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/if_team.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index d95cae09dea0..0d07c6655cce 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -74,6 +74,11 @@ struct team_port { long mode_priv[0]; }; +static inline struct team_port *team_port_get_rcu(const struct net_device *dev) +{ + return rcu_dereference(dev->rx_handler_data); +} + static inline bool team_port_enabled(struct team_port *port) { return port->index != -1; -- cgit v1.2.3 From eeed992b776c54af6108187c87ac60d028e69d37 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Tue, 10 Jul 2018 10:02:58 +0300 Subject: net: Add lag.h, net_lag_port_dev_txable() LAG devices (team or bond) recognize for each one of their slave devices whether LAG traffic is going to be sent through that device. Bond calls such devices "active", team calls them "txable". When this state changes, a NETDEV_CHANGELOWERSTATE notification is distributed, together with a netdev_notifier_changelowerstate_info structure that for LAG devices includes a tx_enabled flag that refers to the new state. The notification thus makes it possible to react to the changes in txability in drivers. However there's no way to query txability from the outside on demand. That is problematic namely for mlxsw, which when resolving ERSPAN packet path, may encounter a LAG device, and needs to determine which of the slaves it should choose. To that end, introduce a new function, net_lag_port_dev_txable(), which determines whether a given slave device is "active" or "txable" (depending on the flavor of the LAG device). That function then dispatches to per-LAG-flavor helpers, bond_is_active_slave_dev() resp. team_port_dev_txable(). Because there currently is no good place where net_lag_port_dev_txable() should be added, introduce a new header file, lag.h, which should from now on hold any logic common to both team and bond. (But keep netif_is_lag_master() together with the rest of netif_is_*_master() functions). Signed-off-by: Petr Machata Reviewed-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/if_team.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 0d07c6655cce..ac42da56f7a2 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -89,6 +89,19 @@ static inline bool team_port_txable(struct team_port *port) return port->linkup && team_port_enabled(port); } +static inline bool team_port_dev_txable(const struct net_device *port_dev) +{ + struct team_port *port; + bool txable; + + rcu_read_lock(); + port = team_port_get_rcu(port_dev); + txable = port ? team_port_txable(port) : false; + rcu_read_unlock(); + + return txable; +} + #ifdef CONFIG_NET_POLL_CONTROLLER static inline void team_netpoll_send_skb(struct team_port *port, struct sk_buff *skb) -- cgit v1.2.3 From bf1c77b4644f46d2986b7ca5e43e012f0fc8984b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 11 Jul 2018 14:56:50 +0100 Subject: kernel: add ksys_personality() Using this helper allows us to avoid the in-kernel call to the sys_personality() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_personality(). Since ksys_personality is trivial, it is implemented directly in , as we do for ksys_close() and friends. This helper is necessary to enable conversion of arm64's syscall handling to use pt_regs wrappers. Signed-off-by: Mark Rutland Reviewed-by: Dominik Brodowski Cc: Al Viro Cc: Christoph Hellwig Cc: Dave Martin Signed-off-by: Will Deacon --- include/linux/syscalls.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a368a68cb667..abfe12d8a9c5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -80,6 +80,7 @@ union bpf_attr; #include #include #include +#include #include #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER @@ -1281,4 +1282,14 @@ static inline long ksys_truncate(const char __user *pathname, loff_t length) return do_sys_truncate(pathname, length); } +static inline unsigned int ksys_personality(unsigned int personality) +{ + unsigned int old = current->personality; + + if (personality != 0xffffffff) + set_personality(personality); + + return old; +} + #endif -- cgit v1.2.3 From 9b54bf9d6a5b30e2cc22b18793e9a4158c5b4882 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 11 Jul 2018 14:56:51 +0100 Subject: kernel: add kcompat_sys_{f,}statfs64() Using this helper allows us to avoid the in-kernel calls to the compat_sys_{f,}statfs64() sycalls, as are necessary for parameter mangling in arm64's compat handling. Following the example of ksys_* functions, kcompat_sys_* functions are intended to be a drop-in replacement for their compat_sys_* counterparts, with the same calling convention. This is necessary to enable conversion of arm64's syscall handling to use pt_regs wrappers. Signed-off-by: Mark Rutland Reviewed-by: Dominik Brodowski Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Will Deacon --- include/linux/compat.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index c68acc47da57..43f4ed44c5d5 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -1028,6 +1028,17 @@ static inline struct compat_timeval ns_to_compat_timeval(s64 nsec) return ctv; } +/* + * Kernel code should not call compat syscalls (i.e., compat_sys_xyzyyz()) + * directly. Instead, use one of the functions which work equivalently, such + * as the kcompat_sys_xyzyyz() functions prototyped below. + */ + +int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz, + struct compat_statfs64 __user * buf); +int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, + struct compat_statfs64 __user * buf); + #else /* !CONFIG_COMPAT */ #define is_compat_task() (0) -- cgit v1.2.3 From c9c554f21490bbc96cc554f80024d27d09670480 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 11 Jul 2018 14:19:04 -0400 Subject: alloc_file(): switch to passing O_... flags instead of FMODE_... mode ... so that it could set both ->f_flags and ->f_mode, without callers having to set ->f_flags manually. Signed-off-by: Al Viro --- include/linux/file.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 279720db984a..6d34a1262b31 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -18,7 +18,7 @@ struct file_operations; struct vfsmount; struct dentry; struct path; -extern struct file *alloc_file(const struct path *, fmode_t mode, +extern struct file *alloc_file(const struct path *, int flags, const struct file_operations *fop); static inline void fput_light(struct file *file, int fput_needed) -- cgit v1.2.3 From e3f20ae21079ecac282df65d83865c5771f4bca0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Jul 2018 13:25:29 -0400 Subject: security_file_open(): lose cred argument Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/security.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 63030c85ee19..88d30fc975e7 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -309,7 +309,7 @@ void security_file_set_fowner(struct file *file); int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig); int security_file_receive(struct file *file); -int security_file_open(struct file *file, const struct cred *cred); +int security_file_open(struct file *file); int security_task_alloc(struct task_struct *task, unsigned long clone_flags); void security_task_free(struct task_struct *task); int security_cred_alloc_blank(struct cred *cred, gfp_t gfp); @@ -858,8 +858,7 @@ static inline int security_file_receive(struct file *file) return 0; } -static inline int security_file_open(struct file *file, - const struct cred *cred) +static inline int security_file_open(struct file *file) { return 0; } -- cgit v1.2.3 From 9481769208b5e39b871ae4e89f5328c776ec38dc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Jul 2018 14:13:18 -0400 Subject: ->file_open(): lose cred argument Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/lsm_hooks.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 8f1131c8dd54..a8ee106b865d 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1569,7 +1569,7 @@ union security_list_options { int (*file_send_sigiotask)(struct task_struct *tsk, struct fown_struct *fown, int sig); int (*file_receive)(struct file *file); - int (*file_open)(struct file *file, const struct cred *cred); + int (*file_open)(struct file *file); int (*task_alloc)(struct task_struct *task, unsigned long clone_flags); void (*task_free)(struct task_struct *task); -- cgit v1.2.3 From f5d11409e61dadf1f9af91b22bbedc28a60a2e2c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 9 Jul 2018 02:35:08 -0400 Subject: introduce FMODE_OPENED basically, "is that instance set up enough for regular fput(), or do we want put_filp() for that one". NOTE: the only alloc_file() caller that could be followed by put_filp() is in arch/ia64/kernel/perfmon.c, which is (Kconfig-level) broken. Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c4ca4c9c1130..05f34726e29c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -148,6 +148,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)0x40000) +#define FMODE_OPENED ((__force fmode_t)0x80000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) -- cgit v1.2.3 From 4d27f3266f14e4d1d13125ce32cb49a40f3122c3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 9 Jul 2018 11:14:39 -0400 Subject: fold put_filp() into fput() Just check FMODE_OPENED in __fput() and be done with that... Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/file.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 6d34a1262b31..aed45d69811e 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -78,7 +78,6 @@ extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); -extern void put_filp(struct file *); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); -- cgit v1.2.3 From 73a09dd94377e4b186b300bd5461920710c7c3d5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 13:22:02 -0400 Subject: introduce FMODE_CREATED and switch to it Parallel to FILE_CREATED, goes into ->f_mode instead of *opened. NFS is a bit of a wart here - it doesn't have file at the point where FILE_CREATED used to be set, so we need to propagate it there (for now). IMA is another one (here and everywhere)... Note that this needs do_dentry_open() to leave old bits in ->f_mode alone - we want it to preserve FMODE_CREATED if it had been already set (no other bit can be there). Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 05f34726e29c..ca668c7e48a7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -149,6 +149,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_CAN_WRITE ((__force fmode_t)0x40000) #define FMODE_OPENED ((__force fmode_t)0x80000) +#define FMODE_CREATED ((__force fmode_t)0x100000) /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) -- cgit v1.2.3 From 6035a27b25ab9dadc8c3d5c5df5eae3fca62fc95 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 13:40:10 -0400 Subject: IMA: don't propagate opened through the entire thing just check ->f_mode in ima_appraise_measurement() Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/ima.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 0e4647e0eb60..d9ba3fc363b7 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -16,7 +16,7 @@ struct linux_binprm; #ifdef CONFIG_IMA extern int ima_bprm_check(struct linux_binprm *bprm); -extern int ima_file_check(struct file *file, int mask, int opened); +extern int ima_file_check(struct file *file, int mask); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern int ima_read_file(struct file *file, enum kernel_read_file_id id); @@ -34,7 +34,7 @@ static inline int ima_bprm_check(struct linux_binprm *bprm) return 0; } -static inline int ima_file_check(struct file *file, int mask, int opened) +static inline int ima_file_check(struct file *file, int mask) { return 0; } -- cgit v1.2.3 From be12af3ef5e61ebc44d065e121424ac605d7bb8e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 11:44:56 -0400 Subject: getting rid of 'opened' argument of ->atomic_open() - part 1 'opened' argument of finish_open() is unused. Kill it. Signed-off-by Al Viro --- include/linux/fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ca668c7e48a7..70be3e4c26ac 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2441,8 +2441,7 @@ enum { FILE_OPENED = 2 }; extern int finish_open(struct file *file, struct dentry *dentry, - int (*open)(struct inode *, struct file *), - int *opened); + int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); /* fs/ioctl.c */ -- cgit v1.2.3 From 44907d79002466049fdbb8ef15730d185e0808b4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 13:32:02 -0400 Subject: get rid of 'opened' argument of ->atomic_open() - part 3 now it can be done... Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 70be3e4c26ac..c25896b30e9f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1781,7 +1781,7 @@ struct inode_operations { int (*update_time)(struct inode *, struct timespec64 *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, - umode_t create_mode, int *opened); + umode_t create_mode); int (*tmpfile) (struct inode *, struct dentry *, umode_t); int (*set_acl)(struct inode *, struct posix_acl *, int); } ____cacheline_aligned; -- cgit v1.2.3 From dbae8f2ca2f0586f4b80201c78ff0aed2a012ab5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 17:51:47 -0400 Subject: kill FILE_{CREATED,OPENED} no users left Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/fs.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c25896b30e9f..bd904c496878 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2436,10 +2436,6 @@ extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); extern void putname(struct filename *name); -enum { - FILE_CREATED = 1, - FILE_OPENED = 2 -}; extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); -- cgit v1.2.3 From d93aa9d82aea80b80f225dbf9c7986df444d8106 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 9 Jun 2018 09:40:05 -0400 Subject: new wrapper: alloc_file_pseudo() takes inode, vfsmount, name, O_... flags and file_operations and either returns a new struct file (in which case inode reference we held is consumed) or returns ERR_PTR(), in which case no refcounts are altered. converted aio_private_file() and sock_alloc_file() to it Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/file.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index aed45d69811e..5b25388f2f79 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -17,9 +17,12 @@ extern void fput(struct file *); struct file_operations; struct vfsmount; struct dentry; +struct inode; struct path; extern struct file *alloc_file(const struct path *, int flags, const struct file_operations *fop); +extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, + const char *, int flags, const struct file_operations *); static inline void fput_light(struct file *file, int fput_needed) { -- cgit v1.2.3 From 183266f26f45a47958afb5c9aa1b3d4651e2eb8c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 17 Jun 2018 14:15:10 -0400 Subject: new helper: alloc_file_clone() alloc_file_clone(old_file, mode, ops): create a new struct file with ->f_path equal to that of old_file. pipe converted. Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/file.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 5b25388f2f79..60914843c737 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -23,6 +23,8 @@ extern struct file *alloc_file(const struct path *, int flags, const struct file_operations *fop); extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); +extern struct file *alloc_file_clone(struct file *, int flags, + const struct file_operations *); static inline void fput_light(struct file *file, int fput_needed) { -- cgit v1.2.3 From ee1904ba44bd4a242b453e8fe179b374906da173 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 17 Jun 2018 14:21:27 -0400 Subject: make alloc_file() static Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/file.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 60914843c737..6b2fb032416c 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -19,8 +19,6 @@ struct vfsmount; struct dentry; struct inode; struct path; -extern struct file *alloc_file(const struct path *, int flags, - const struct file_operations *fop); extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_clone(struct file *, int flags, -- cgit v1.2.3 From 0238d2b4a4c7bb1b2268e1ef789629878e16ab02 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Thu, 12 Jul 2018 09:57:00 +0800 Subject: serial: 8250: introduce get_divisor() and set_divisor() hook Add these two hooks so that they can be overridden with driver specific implementations. Signed-off-by: Jisheng Zhang Reviewed-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 06ea4eeb09ab..406edae44ca3 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -127,6 +127,13 @@ struct uart_port { struct ktermios *); unsigned int (*get_mctrl)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int); + unsigned int (*get_divisor)(struct uart_port *, + unsigned int baud, + unsigned int *frac); + void (*set_divisor)(struct uart_port *, + unsigned int baud, + unsigned int quot, + unsigned int quot_frac); int (*startup)(struct uart_port *port); void (*shutdown)(struct uart_port *port); void (*throttle)(struct uart_port *port); -- cgit v1.2.3 From 6226e5f31a786b58f33781852c897ac32a325ce6 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Thu, 12 Jul 2018 09:58:14 +0800 Subject: serial: 8250: export serial8250_do_set_divisor() Some drivers could call serial8250_do_set_divisor() to complete its own set_divisor routine. Export this symbol for code reusing. Signed-off-by: Jisheng Zhang Reviewed-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 76b9db71e489..18e21427bce4 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -160,6 +160,9 @@ extern void serial8250_do_shutdown(struct uart_port *port); extern void serial8250_do_pm(struct uart_port *port, unsigned int state, unsigned int oldstate); extern void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); +extern void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, + unsigned int quot, + unsigned int quot_frac); extern int fsl8250_handle_irq(struct uart_port *port); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); unsigned char serial8250_rx_chars(struct uart_8250_port *up, unsigned char lsr); -- cgit v1.2.3 From 2abc77af89e17582db9039293c8ac881c8c96d79 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 12 Jul 2018 11:18:42 -0400 Subject: new helper: open_with_fake_path() open a file by given inode, faking ->f_path. Use with shitloads of caution - at the very least you'd damn better make sure that some dentry alias of that inode is pinned down by the path in question. Again, this is no general-purpose interface and I hope it will eventually go away. Right now overlayfs wants something like that, but nothing else should. Any out-of-tree code with bright idea of using this one *will* eventually get hurt, with zero notice and great delight on my part. I refuse to use EXPORT_SYMBOL_GPL(), especially in situations when it's really EXPORT_SYMBOL_DONT_USE_IT(), but don't take that export as "you are welcome to use it". Signed-off-by: Al Viro --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 05f34726e29c..4ff7b7012186 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2424,6 +2424,8 @@ extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); +extern struct file * open_with_fake_path(const struct path *, int, + struct inode*, const struct cred *); static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); -- cgit v1.2.3 From a8802d97e73346bc81609df9dfba7d3306f40d87 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Jul 2018 11:16:41 -0700 Subject: ktime: Provide typesafe ktime_to_ns() Using ktime_to_ns() is nice to help backports to stable kernels. Having a typesafe function instead of a macro avoid stupid typos and waste of time tracking these typos. Reported-by: Willem de Bruijn Signed-off-by: Eric Dumazet Signed-off-by: Thomas Gleixner Cc: Eric Dumazet Cc: John Stultz Cc: Peter Zijlstra Cc: Linus Torvalds Link: https://lkml.kernel.org/r/20180711181641.10369-1-edumazet@google.com --- include/linux/ktime.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 5b9fddbaac41..b2bb44f87f5a 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -93,8 +93,11 @@ static inline ktime_t timeval_to_ktime(struct timeval tv) /* Map the ktime_t to timeval conversion to ns_to_timeval function */ #define ktime_to_timeval(kt) ns_to_timeval((kt)) -/* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */ -#define ktime_to_ns(kt) (kt) +/* Convert ktime_t to nanoseconds */ +static inline s64 ktime_to_ns(const ktime_t kt) +{ + return kt; +} /** * ktime_compare - Compares two ktime_t variables for less, greater or equal -- cgit v1.2.3 From cca9bab1b72cd2296097c75f59ef11ef80461279 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 11 Jul 2018 12:16:12 +0200 Subject: tcp: use monotonic timestamps for PAWS Using get_seconds() for timestamps is deprecated since it can lead to overflows on 32-bit systems. While the interface generally doesn't overflow until year 2106, the specific implementation of the TCP PAWS algorithm breaks in 2038 when the intermediate signed 32-bit timestamps overflow. A related problem is that the local timestamps in CLOCK_REALTIME form lead to unexpected behavior when settimeofday is called to set the system clock backwards or forwards by more than 24 days. While the first problem could be solved by using an overflow-safe method of comparing the timestamps, a nicer solution is to use a monotonic clocksource with ktime_get_seconds() that simply doesn't overflow (at least not until 136 years after boot) and that doesn't change during settimeofday(). To make 32-bit and 64-bit architectures behave the same way here, and also save a few bytes in the tcp_options_received structure, I'm changing the type to a 32-bit integer, which is now safe on all architectures. Finally, the ts_recent_stamp field also (confusingly) gets used to store a jiffies value in tcp_synq_overflow()/tcp_synq_no_recent_overflow(). This is currently safe, but changing the type to 32-bit requires some small changes there to keep it working. Signed-off-by: Arnd Bergmann Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3dbea6610304..58a8d7d71354 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -89,7 +89,7 @@ struct tcp_sack_block { struct tcp_options_received { /* PAWS/RTTM data */ - long ts_recent_stamp;/* Time we stored ts_recent (for aging) */ + int ts_recent_stamp;/* Time we stored ts_recent (for aging) */ u32 ts_recent; /* Time stamp to echo next */ u32 rcv_tsval; /* Time stamp value */ u32 rcv_tsecr; /* Time stamp echo reply */ @@ -426,7 +426,7 @@ struct tcp_timewait_sock { /* The time we sent the last out-of-window ACK: */ u32 tw_last_oow_ack_time; - long tw_ts_recent_stamp; + int tw_ts_recent_stamp; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tw_md5_key; #endif -- cgit v1.2.3 From 3f3a89e1d7c31558c070692241e3d6146d2cf1bf Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Wed, 20 Jun 2018 07:18:03 +0200 Subject: i2c: remove i2c_lock_adapter and use i2c_lock_bus directly The i2c_lock_adapter name is ambiguous since it is unclear if it refers to the root adapter or the adapter you name in the argument. The natural interpretation is the adapter you name in the argument, but there are historical reasons for that not being the case; it in fact locks the root adapter. Just remove the function and force users to spell out the I2C_LOCK_ROOT_ADAPTER name to indicate what is really going on. Also remove i2c_unlock_adapter, of course. This patch was generated with git grep -l 'i2c_\(un\)\?lock_adapter' \ | xargs sed -i 's/i2c_\(un\)\?lock_adapter(\([^)]*\))/'\ 'i2c_\1lock_bus(\2, I2C_LOCK_ROOT_ADAPTER)/g' followed by white-space touch-up. Signed-off-by: Peter Rosin Acked-by: Jonathan Cameron Tested-by: Sekhar Nori Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 254cd34eeae2..795e3a860afe 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -754,18 +754,6 @@ i2c_unlock_bus(struct i2c_adapter *adapter, unsigned int flags) adapter->lock_ops->unlock_bus(adapter, flags); } -static inline void -i2c_lock_adapter(struct i2c_adapter *adapter) -{ - i2c_lock_bus(adapter, I2C_LOCK_ROOT_ADAPTER); -} - -static inline void -i2c_unlock_adapter(struct i2c_adapter *adapter) -{ - i2c_unlock_bus(adapter, I2C_LOCK_ROOT_ADAPTER); -} - /*flags for the client struct: */ #define I2C_CLIENT_PEC 0x04 /* Use Packet Error Checking */ #define I2C_CLIENT_TEN 0x10 /* we have a ten bit chip address */ -- cgit v1.2.3 From 8b7008620b8452728cadead460a36f64ed78c460 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Wed, 11 Jul 2018 14:39:42 +0200 Subject: net: Don't copy pfmemalloc flag in __copy_skb_header() The pfmemalloc flag indicates that the skb was allocated from the PFMEMALLOC reserves, and the flag is currently copied on skb copy and clone. However, an skb copied from an skb flagged with pfmemalloc wasn't necessarily allocated from PFMEMALLOC reserves, and on the other hand an skb allocated that way might be copied from an skb that wasn't. So we should not copy the flag on skb copy, and rather decide whether to allow an skb to be associated with sockets unrelated to page reclaim depending only on how it was allocated. Move the pfmemalloc flag before headers_start[0] using an existing 1-bit hole, so that __copy_skb_header() doesn't copy it. When cloning, we'll now take care of this flag explicitly, contravening to the warning comment of __skb_clone(). While at it, restore the newline usage introduced by commit b19372273164 ("net: reorganize sk_buff for faster __copy_skb_header()") to visually separate bytes used in bitfields after headers_start[0], that was gone after commit a9e419dc7be6 ("netfilter: merge ctinfo into nfct pointer storage area"), and describe the pfmemalloc flag in the kernel-doc structure comment. This doesn't change the size of sk_buff or cacheline boundaries, but consolidates the 15 bits hole before tc_index into a 2 bytes hole before csum, that could now be filled more easily. Reported-by: Patrick Talbert Fixes: c93bdd0e03e8 ("netvm: allow skb allocation to use PFMEMALLOC reserves") Signed-off-by: Stefano Brivio Signed-off-by: David S. Miller --- include/linux/skbuff.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 164cdedf6012..610a201126ee 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -630,6 +630,7 @@ typedef unsigned char *sk_buff_data_t; * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @xmit_more: More SKBs are pending for this queue + * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport @@ -735,7 +736,7 @@ struct sk_buff { peeked:1, head_frag:1, xmit_more:1, - __unused:1; /* one bit hole */ + pfmemalloc:1; /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() @@ -754,31 +755,30 @@ struct sk_buff { __u8 __pkt_type_offset[0]; __u8 pkt_type:3; - __u8 pfmemalloc:1; __u8 ignore_df:1; - __u8 nf_trace:1; __u8 ip_summed:2; __u8 ooo_okay:1; + __u8 l4_hash:1; __u8 sw_hash:1; __u8 wifi_acked_valid:1; __u8 wifi_acked:1; - __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; + __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 csum_not_inet:1; - __u8 dst_pending_confirm:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif __u8 ipvs_property:1; + __u8 inner_protocol_type:1; __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV -- cgit v1.2.3 From 3949fa9bac090ad217534c30bc3b6572289abf21 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 8 May 2018 15:29:10 -0700 Subject: rcu: Make rcu_read_unlock_special() static Because rcu_read_unlock_special() is no longer used outside of kernel/rcu/tree_plugin.h, this commit makes it static. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 65163aa0bb04..67ec077c7ee5 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -64,7 +64,6 @@ void rcu_barrier_tasks(void); void __rcu_read_lock(void); void __rcu_read_unlock(void); -void rcu_read_unlock_special(struct task_struct *t); void synchronize_rcu(void); /* -- cgit v1.2.3 From 07f27570dcd148a5f4de7dc3513c1d1cd069b362 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Fri, 11 May 2018 17:30:34 +0900 Subject: rcu: Improve rcu_note_voluntary_context_switch() reporting We expect a quiescent state of TASKS_RCU when cond_resched_tasks_rcu_qs() is called, no matter whether it actually be scheduled or not. However, it currently doesn't report the quiescent state when the task enters into __schedule() as it's called with preempt = true. So make it report the quiescent state unconditionally when cond_resched_tasks_rcu_qs() is called. And in TINY_RCU, even though the quiescent state of rcu_bh also should be reported when the tick interrupt comes from user, it doesn't. So make it reported. Lastly in TREE_RCU, rcu_note_voluntary_context_switch() should be reported when the tick interrupt comes from not only user but also idle, as an extended quiescent state. Signed-off-by: Byungchul Park Signed-off-by: Paul E. McKenney [ paulmck: Simplify rcutiny portion given no RCU-tasks for !PREEMPT. ] --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 67ec077c7ee5..5cab15e7ec83 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -194,8 +194,8 @@ static inline void exit_tasks_rcu_finish(void) { } */ #define cond_resched_tasks_rcu_qs() \ do { \ - if (!cond_resched()) \ - rcu_note_voluntary_context_switch_lite(current); \ + rcu_note_voluntary_context_switch_lite(current); \ + cond_resched(); \ } while (0) /* -- cgit v1.2.3 From 1445e9175bead409bb9930f3c745246a09f22cf6 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 7 May 2018 06:35:46 -0300 Subject: rcu: rcupdate.h: Get rid of Sphinx warnings at rcu_pointer_handoff() The code example at rcupdate.h currently produce lots of warnings: ./include/linux/rcupdate.h:572: WARNING: Unexpected indentation. ./include/linux/rcupdate.h:576: WARNING: Unexpected indentation. ./include/linux/rcupdate.h:580: WARNING: Block quote ends without a blank line; unexpected unindent. ./include/linux/rcupdate.h:582: WARNING: Block quote ends without a blank line; unexpected unindent. ./include/linux/rcupdate.h:582: WARNING: Inline literal start-string without end-string. This commit therefore changes it to a code-block. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 5cab15e7ec83..dacc90358b33 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -566,8 +566,8 @@ static inline void rcu_preempt_sleep_check(void) { } * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to - * kill_dependency(). It could be used as follows: - * `` + * kill_dependency(). It could be used as follows:: + * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); @@ -578,7 +578,6 @@ static inline void rcu_preempt_sleep_check(void) { } * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); - *`` */ #define rcu_pointer_handoff(p) (p) -- cgit v1.2.3 From 6f56f714db067056c80f5d71510118f82872e34c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 14 May 2018 13:52:27 -0700 Subject: rcu: Improve RCU-tasks naming and comments The naming and comments associated with some RCU-tasks code make the faulty assumption that context switches due to cond_resched() are voluntary. As several people pointed out, this is not the case. This commit therefore updates function names and comments to better reflect current reality. Reported-by: Byungchul Park Reported-by: Joel Fernandes Reported-by: Steven Rostedt Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 12 ++++++------ include/linux/rcutiny.h | 2 +- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index dacc90358b33..75e5b393cf44 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -158,11 +158,11 @@ static inline void rcu_init_nohz(void) { } } while (0) /* - * Note a voluntary context switch for RCU-tasks benefit. This is a - * macro rather than an inline function to avoid #include hell. + * Note a quasi-voluntary context switch for RCU-tasks's benefit. + * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU -#define rcu_note_voluntary_context_switch_lite(t) \ +#define rcu_tasks_qs(t) \ do { \ if (READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ @@ -170,14 +170,14 @@ static inline void rcu_init_nohz(void) { } #define rcu_note_voluntary_context_switch(t) \ do { \ rcu_all_qs(); \ - rcu_note_voluntary_context_switch_lite(t); \ + rcu_tasks_qs(t); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ -#define rcu_note_voluntary_context_switch_lite(t) do { } while (0) +#define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) rcu_all_qs() #define call_rcu_tasks call_rcu_sched #define synchronize_rcu_tasks synchronize_sched @@ -194,7 +194,7 @@ static inline void exit_tasks_rcu_finish(void) { } */ #define cond_resched_tasks_rcu_qs() \ do { \ - rcu_note_voluntary_context_switch_lite(current); \ + rcu_tasks_qs(current); \ cond_resched(); \ } while (0) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 7b3c82e8a625..8d9a0ea8f0b5 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -93,7 +93,7 @@ static inline void kfree_call_rcu(struct rcu_head *head, #define rcu_note_context_switch(preempt) \ do { \ rcu_sched_qs(); \ - rcu_note_voluntary_context_switch_lite(current); \ + rcu_tasks_qs(current); \ } while (0) static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) -- cgit v1.2.3 From b7b6f94cf6e6d961f78064315b6f5de5d9c6414b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 18 Jun 2018 14:22:40 +1000 Subject: rculist: Improve documentation for list_for_each_entry_from_rcu() Unfortunately the patch for adding list_for_each_entry_from_rcu() wasn't the final patch after all review. It is functionally correct but the documentation was incomplete. This patch adds this missing documentation which includes an update to the documentation for list_for_each_entry_continue_rcu() to match the documentation for the new list_for_each_entry_from_rcu(), and adds list_for_each_entry_from_rcu() and the already existing hlist_for_each_entry_from_rcu() to section 7 of whatisRCU.txt. Reviewed-by: Paul E. McKenney Signed-off-by: NeilBrown Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 36df6ccbc874..4786c2235b98 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -396,7 +396,16 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after - * the current position. + * the current position which must have been in the list when the RCU read + * lock was taken. + * This would typically require either that you obtained the node from a + * previous walk of the list in the same RCU read-side critical section, or + * that you held some sort of non-RCU reference (such as a reference count) + * to keep the node alive *and* in the list. + * + * This iterator is similar to list_for_each_entry_from_rcu() except + * this starts after the given position and that one starts at the given + * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ @@ -411,6 +420,14 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. + * This would typically require either that you obtained the node from a + * previous walk of the list in the same RCU read-side critical section, or + * that you held some sort of non-RCU reference (such as a reference count) + * to keep the node alive *and* in the list. + * + * This iterator is similar to list_for_each_entry_continue_rcu() except + * this starts from the given position and that one starts from the position + * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ -- cgit v1.2.3 From 3025520ec424df8b0fd5cdc319ad6b83406d9954 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 22 May 2018 11:38:47 -0700 Subject: rcutorture: Use per-CPU random state for rcu_torture_timer() Currently, the rcu_torture_timer() function uses a single global torture_random_state structure protected by a single global lock. This conflicts to some extent with performance and scalability, but even more with the goal of consolidating read-side testing with rcu_torture_reader(). This commit therefore creates a per-CPU torture_random_state structure for use by rcu_torture_timer() and eliminates the lock. Signed-off-by: Paul E. McKenney [ paulmck: Make rcu_torture_timer_rand static, per 0day Test Robot report. ] --- include/linux/torture.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/torture.h b/include/linux/torture.h index a55e80817dae..61dfd93b6ee4 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -64,6 +64,8 @@ struct torture_random_state { long trs_count; }; #define DEFINE_TORTURE_RANDOM(name) struct torture_random_state name = { 0, 0 } +#define DEFINE_TORTURE_RANDOM_PERCPU(name) \ + DEFINE_PER_CPU(struct torture_random_state, name) unsigned long torture_random(struct torture_random_state *trsp); /* Task shuffler, which causes CPUs to occasionally go idle. */ -- cgit v1.2.3 From 523f9eb1ef25aab4aaf9aeb5356160e8039411ef Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:15 +0300 Subject: net/mlx4_core: Add health buffer address capability Health buffer address is a 32 bit PCI address offset provided by the FW. This offset is used for reading FW health debug data located on the shared CR space. Cr space is accessible in both driver and FW and allows for different queries and configurations. Health buffer size is always 64B of readable data followed by a lock which is used to block volatile CR space access. Signed-off-by: Alex Vesker Signed-off-by: Tariq Toukan Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 122e7e9d3091..e3bfe76aea98 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -630,6 +630,7 @@ struct mlx4_caps { u32 vf_caps; bool wol_port[MLX4_MAX_PORTS + 1]; struct mlx4_rate_limit_caps rl_caps; + u32 health_buffer_addrs; }; struct mlx4_buf_list { -- cgit v1.2.3 From bedc989b0c98285b277ff8a08ff9514e580913f4 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:16 +0300 Subject: net/mlx4_core: Add Crdump FW snapshot support Crdump allows the driver to create a snapshot of the FW PCI crspace and health buffer during a critical FW issue. In case of a FW command timeout, FW getting stuck or a non zero value on the catastrophic buffer, a snapshot will be taken. The snapshot is exposed using devlink, cr-space, fw-health address regions are registered on init and snapshots are attached once a new snapshot is collected by the driver. Signed-off-by: Alex Vesker Signed-off-by: Tariq Toukan Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index e3bfe76aea98..300b944e6e1e 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -852,6 +852,11 @@ struct mlx4_vf_dev { u8 n_ports; }; +struct mlx4_fw_crdump { + struct devlink_region *region_crspace; + struct devlink_region *region_fw_health; +}; + enum mlx4_pci_status { MLX4_PCI_STATUS_DISABLED, MLX4_PCI_STATUS_ENABLED, @@ -872,6 +877,7 @@ struct mlx4_dev_persistent { u8 interface_state; struct mutex pci_status_mutex; /* sync pci state */ enum mlx4_pci_status pci_status; + struct mlx4_fw_crdump crdump; }; struct mlx4_dev { -- cgit v1.2.3 From 3c641ba4a852cf4e90e3d7f29c5df08e24213c5d Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:18 +0300 Subject: net/mlx4_core: Use devlink region_snapshot parameter This parameter enables capturing region snapshot of the crspace during critical errors. The default value of this parameter is disabled, it can be enabled using devlink param commands. It is possible to configure during runtime and also driver init. Signed-off-by: Alex Vesker Signed-off-by: Jiri Pirko Reviewed-by: Moshe Shemesh Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 300b944e6e1e..dca6ab4eaa99 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -853,6 +853,7 @@ struct mlx4_vf_dev { }; struct mlx4_fw_crdump { + bool snapshot_enable; struct devlink_region *region_crspace; struct devlink_region *region_fw_health; }; -- cgit v1.2.3 From 57e94c8b974db2d83c60e1139c89a70806abbea0 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Wed, 4 Jul 2018 17:08:18 +0200 Subject: mfd: cros-ec: Increase maximum mkbp event size Having a 16 byte mkbp event size makes it possible to send CEC messages from the EC to the AP directly inside the mkbp event instead of first doing a notification and then a read. Signed-off-by: Stefan Adolfsson Signed-off-by: Neil Armstrong Tested-by: Enric Balletbo i Serra Acked-by: Hans Verkuil Signed-off-by: Lee Jones --- include/linux/mfd/cros_ec.h | 2 +- include/linux/mfd/cros_ec_commands.h | 16 ++++++++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 32421dfeb996..20949dde35cd 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -147,7 +147,7 @@ struct cros_ec_device { bool mkbp_event_supported; struct blocking_notifier_head event_notifier; - struct ec_response_get_next_event event_data; + struct ec_response_get_next_event_v1 event_data; int event_size; u32 host_event_wake_mask; }; diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index f2edd9969b40..c4f0caa642be 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -2093,12 +2093,28 @@ union ec_response_get_next_data { uint32_t sysrq; } __packed; +union ec_response_get_next_data_v1 { + uint8_t key_matrix[16]; + uint32_t host_event; + uint32_t buttons; + uint32_t switches; + uint32_t sysrq; + uint32_t cec_events; + uint8_t cec_message[16]; +} __packed; + struct ec_response_get_next_event { uint8_t event_type; /* Followed by event data if any */ union ec_response_get_next_data data; } __packed; +struct ec_response_get_next_event_v1 { + uint8_t event_type; + /* Followed by event data if any */ + union ec_response_get_next_data_v1 data; +} __packed; + /* Bit indices for buttons and switches.*/ /* Buttons */ #define EC_MKBP_POWER_BUTTON 0 -- cgit v1.2.3 From f47674e5263dfe0f89a640fc8b7dc54f9b79d5db Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Wed, 4 Jul 2018 17:08:19 +0200 Subject: mfd: cros-ec: Introduce CEC commands and events definitions. The EC can expose a CEC bus, this patch adds the CEC related definitions needed by the cros-ec-cec driver. Signed-off-by: Neil Armstrong Tested-by: Enric Balletbo i Serra Reviewed-by: Hans Verkuil Signed-off-by: Lee Jones --- include/linux/mfd/cros_ec_commands.h | 81 ++++++++++++++++++++++++++++++++++++ 1 file changed, 81 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index c4f0caa642be..5079bc2d4378 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -804,6 +804,8 @@ enum ec_feature_code { EC_FEATURE_MOTION_SENSE_FIFO = 24, /* EC has RTC feature that can be controlled by host commands */ EC_FEATURE_RTC = 27, + /* EC supports CEC commands */ + EC_FEATURE_CEC = 35, }; #define EC_FEATURE_MASK_0(event_code) (1UL << (event_code % 32)) @@ -2078,6 +2080,12 @@ enum ec_mkbp_event { /* EC sent a sysrq command */ EC_MKBP_EVENT_SYSRQ = 6, + /* Notify the AP that something happened on CEC */ + EC_MKBP_EVENT_CEC_EVENT = 8, + + /* Send an incoming CEC message to the AP */ + EC_MKBP_EVENT_CEC_MESSAGE = 9, + /* Number of MKBP events */ EC_MKBP_EVENT_COUNT, }; @@ -2845,6 +2853,79 @@ struct ec_params_reboot_ec { #define EC_ACPI_MEM_VERSION_CURRENT 1 +/*****************************************************************************/ +/* + * HDMI CEC commands + * + * These commands are for sending and receiving message via HDMI CEC + */ +#define EC_MAX_CEC_MSG_LEN 16 + +/* CEC message from the AP to be written on the CEC bus */ +#define EC_CMD_CEC_WRITE_MSG 0x00B8 + +/** + * struct ec_params_cec_write - Message to write to the CEC bus + * @msg: message content to write to the CEC bus + */ +struct ec_params_cec_write { + uint8_t msg[EC_MAX_CEC_MSG_LEN]; +} __packed; + +/* Set various CEC parameters */ +#define EC_CMD_CEC_SET 0x00BA + +/** + * struct ec_params_cec_set - CEC parameters set + * @cmd: parameter type, can be CEC_CMD_ENABLE or CEC_CMD_LOGICAL_ADDRESS + * @val: in case cmd is CEC_CMD_ENABLE, this field can be 0 to disable CEC + * or 1 to enable CEC functionality, in case cmd is CEC_CMD_LOGICAL_ADDRESS, + * this field encodes the requested logical address between 0 and 15 + * or 0xff to unregister + */ +struct ec_params_cec_set { + uint8_t cmd; /* enum cec_command */ + uint8_t val; +} __packed; + +/* Read various CEC parameters */ +#define EC_CMD_CEC_GET 0x00BB + +/** + * struct ec_params_cec_get - CEC parameters get + * @cmd: parameter type, can be CEC_CMD_ENABLE or CEC_CMD_LOGICAL_ADDRESS + */ +struct ec_params_cec_get { + uint8_t cmd; /* enum cec_command */ +} __packed; + +/** + * struct ec_response_cec_get - CEC parameters get response + * @val: in case cmd was CEC_CMD_ENABLE, this field will 0 if CEC is + * disabled or 1 if CEC functionality is enabled, + * in case cmd was CEC_CMD_LOGICAL_ADDRESS, this will encode the + * configured logical address between 0 and 15 or 0xff if unregistered + */ +struct ec_response_cec_get { + uint8_t val; +} __packed; + +/* CEC parameters command */ +enum ec_cec_command { + /* CEC reading, writing and events enable */ + CEC_CMD_ENABLE, + /* CEC logical address */ + CEC_CMD_LOGICAL_ADDRESS, +}; + +/* Events from CEC to AP */ +enum mkbp_cec_event { + /* Outgoing message was acknowledged by a follower */ + EC_MKBP_CEC_SEND_OK = BIT(0), + /* Outgoing message was not acknowledged */ + EC_MKBP_CEC_SEND_FAILED = BIT(1), +}; + /*****************************************************************************/ /* * Special commands -- cgit v1.2.3 From 03133347b4452ef9b1f1456b92f5fafa467c0655 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 30 Apr 2018 18:33:24 +0200 Subject: KVM: s390: a utility function for migration Introduce a utility function that will be used later on for storage attributes migration, and use it in kvm_main.c to replace existing code that does the same thing. Signed-off-by: Claudio Imbrenda Message-Id: <1525106005-13931-2-git-send-email-imbrenda@linux.vnet.ibm.com> Signed-off-by: Christian Borntraeger --- include/linux/kvm_host.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4ee7bc548a83..5f138b40e433 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -309,6 +309,13 @@ static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memsl return ALIGN(memslot->npages, BITS_PER_LONG) / 8; } +static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *memslot) +{ + unsigned long len = kvm_dirty_bitmap_bytes(memslot); + + return memslot->dirty_bitmap + len / sizeof(*memslot->dirty_bitmap); +} + struct kvm_s390_adapter_int { u64 ind_addr; u64 summary_addr; -- cgit v1.2.3 From afed7bcf9487bb28e2e2b016a195085c07416c0b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 11 Jul 2018 10:36:07 +0100 Subject: locking/refcount: Always allow checked forms In many cases, it would be useful to be able to use the full sanity-checked refcount helpers regardless of CONFIG_REFCOUNT_FULL, as this would help to avoid duplicate warnings where callers try to sanity-check refcount manipulation. This patch refactors things such that the full refcount helpers were always built, as refcount_${op}_checked(), such that they can be used regardless of CONFIG_REFCOUNT_FULL. This will allow code which *always* wants a checked refcount to opt-in, avoiding the need to duplicate the logic for warnings. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: David Sterba Acked-by: Kees Cook Acked-by: Will Deacon Cc: Boqun Feng Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180711093607.1644-1-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/refcount.h | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index c36addd27dd5..53c5eca24d83 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -43,17 +43,30 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } +extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r); +extern void refcount_add_checked(unsigned int i, refcount_t *r); + +extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r); +extern void refcount_inc_checked(refcount_t *r); + +extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r); + +extern __must_check bool refcount_dec_and_test_checked(refcount_t *r); +extern void refcount_dec_checked(refcount_t *r); + #ifdef CONFIG_REFCOUNT_FULL -extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r); -extern void refcount_add(unsigned int i, refcount_t *r); -extern __must_check bool refcount_inc_not_zero(refcount_t *r); -extern void refcount_inc(refcount_t *r); +#define refcount_add_not_zero refcount_add_not_zero_checked +#define refcount_add refcount_add_checked + +#define refcount_inc_not_zero refcount_inc_not_zero_checked +#define refcount_inc refcount_inc_checked + +#define refcount_sub_and_test refcount_sub_and_test_checked -extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r); +#define refcount_dec_and_test refcount_dec_and_test_checked +#define refcount_dec refcount_dec_checked -extern __must_check bool refcount_dec_and_test(refcount_t *r); -extern void refcount_dec(refcount_t *r); #else # ifdef CONFIG_ARCH_HAS_REFCOUNT # include -- cgit v1.2.3 From 05814a10370b3252fe2b0898b6adac3cdd531096 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Fri, 13 Jul 2018 17:07:26 +0300 Subject: block: remove blkdev_entry_to_request() macro Remove blkdev_entry_to_request() macro, which remained unused through the observable history, also note that it repeats list_entry_rq() macro verbatim. Signed-off-by: Vladimir Zapolskiy Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 137759862f07..1939ed95f936 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1436,8 +1436,6 @@ enum blk_default_limits { BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; -#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) - static inline unsigned long queue_segment_boundary(struct request_queue *q) { return q->limits.seg_boundary_mask; -- cgit v1.2.3 From 8e1b706b6e819bed215c0db16345568864660393 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 13 Jul 2018 16:23:23 +0200 Subject: cpu/hotplug: Expose SMT control init function The L1TF mitigation will gain a commend line parameter which allows to set a combination of hypervisor mitigation and SMT control. Expose cpu_smt_disable() so the command line parser can tweak SMT settings. [ tglx: Split out of larger patch and made it preserve an already existing force off state ] Signed-off-by: Jiri Kosina Signed-off-by: Thomas Gleixner Tested-by: Jiri Kosina Reviewed-by: Greg Kroah-Hartman Reviewed-by: Josh Poimboeuf Link: https://lkml.kernel.org/r/20180713142323.039715135@linutronix.de --- include/linux/cpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 7532cbf27b1d..c9b23ad27b38 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -177,8 +177,10 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; +extern void cpu_smt_disable(bool force); #else # define cpu_smt_control (CPU_SMT_ENABLED) +static inline void cpu_smt_disable(bool force) { } #endif #endif /* _LINUX_CPU_H_ */ -- cgit v1.2.3 From fee0aede6f4739c87179eca76136f83210953b86 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 13 Jul 2018 16:23:24 +0200 Subject: cpu/hotplug: Set CPU_SMT_NOT_SUPPORTED early The CPU_SMT_NOT_SUPPORTED state is set (if the processor does not support SMT) when the sysfs SMT control file is initialized. That was fine so far as this was only required to make the output of the control file correct and to prevent writes in that case. With the upcoming l1tf command line parameter, this needs to be set up before the L1TF mitigation selection and command line parsing happens. Signed-off-by: Thomas Gleixner Tested-by: Jiri Kosina Reviewed-by: Greg Kroah-Hartman Reviewed-by: Josh Poimboeuf Link: https://lkml.kernel.org/r/20180713142323.121795971@linutronix.de --- include/linux/cpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index c9b23ad27b38..ccdf3a67ce56 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -178,9 +178,11 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); +extern void cpu_smt_check_topology(void); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } +static inline void cpu_smt_check_topology(void) { } #endif #endif /* _LINUX_CPU_H_ */ -- cgit v1.2.3 From 6b8675897338f874c41612655a85d8e10cdb23d8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 Jul 2018 20:36:39 -0700 Subject: xdp: don't make drivers report attachment mode prog_attached of struct netdev_bpf should have been superseded by simply setting prog_id long time ago, but we kept it around to allow offloading drivers to communicate attachment mode (drv vs hw). Subsequently drivers were also allowed to report back attachment flags (prog_flags), and since nowadays only programs attached will XDP_FLAGS_HW_MODE can get offloaded, we can tell the attachment mode from the flags driver reports. Remove prog_attached member. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/linux/netdevice.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b683971e500d..69a664789b33 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -819,10 +819,6 @@ enum bpf_netdev_command { */ XDP_SETUP_PROG, XDP_SETUP_PROG_HW, - /* Check if a bpf program is set on the device. The callee should - * set @prog_attached to one of XDP_ATTACHED_* values, note that "true" - * is equivalent to XDP_ATTACHED_DRV. - */ XDP_QUERY_PROG, /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_VERIFIER_PREP, @@ -849,7 +845,6 @@ struct netdev_bpf { }; /* XDP_QUERY_PROG */ struct { - u8 prog_attached; u32 prog_id; /* flags with which program was installed */ u32 prog_flags; -- cgit v1.2.3 From a25717d2b604347d9af8da81deea7b08e8c94220 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 Jul 2018 20:36:41 -0700 Subject: xdp: support simultaneous driver and hw XDP attachment Split the query of HW-attached program from the software one. Introduce new .ndo_bpf command to query HW-attached program. This will allow drivers to install different programs in HW and SW at the same time. Netlink can now also carry multiple programs on dump (in which case mode will be set to XDP_ATTACHED_MULTI and user has to check per-attachment point attributes, IFLA_XDP_PROG_ID will not be present). We reuse IFLA_XDP_PROG_ID skb space for second mode, so rtnl_xdp_size() doesn't need to be updated. Note that the installation side is still not there, since all drivers currently reject installing more than one program at the time. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/linux/netdevice.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 69a664789b33..2422c0e88f5c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -820,6 +820,7 @@ enum bpf_netdev_command { XDP_SETUP_PROG, XDP_SETUP_PROG_HW, XDP_QUERY_PROG, + XDP_QUERY_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_VERIFIER_PREP, BPF_OFFLOAD_TRANSLATE, @@ -843,7 +844,7 @@ struct netdev_bpf { struct bpf_prog *prog; struct netlink_ext_ack *extack; }; - /* XDP_QUERY_PROG */ + /* XDP_QUERY_PROG, XDP_QUERY_PROG_HW */ struct { u32 prog_id; /* flags with which program was installed */ @@ -3533,8 +3534,8 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags); -void __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, - struct netdev_bpf *xdp); +u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, + enum bpf_netdev_command cmd); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); -- cgit v1.2.3 From c921c2077b32081617789a645120148bc8b60c98 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 13 Jul 2018 12:16:43 +0300 Subject: net: ipmr: add support for passing full packet on wrong vif This patch adds support for IGMPMSG_WRVIFWHOLE which is used to pass full packet and real vif id when the incoming interface is wrong. While the RP and FHR are setting up state we need to be sending the registers encapsulated with all the data inside otherwise we lose it. The RP then decapsulates it and forwards it to the interested parties. Currently with WRONGVIF we can only be sending empty register packets and will lose that data. This behaviour can be enabled by using MRT_PIM with val == IGMPMSG_WRVIFWHOLE. This doesn't prevent IGMPMSG_WRONGVIF from happening, it happens in addition to it, also it is controlled by the same throttling parameters as WRONGVIF (i.e. 1 packet per 3 seconds currently). Both messages are generated to keep backwards compatibily and avoid breaking someone who was enabling MRT_PIM with val == 4, since any positive val is accepted and treated the same. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/mroute_base.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index fd436cdd4725..6675b9f81979 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -254,6 +254,7 @@ struct mr_table { atomic_t cache_resolve_queue_len; bool mroute_do_assert; bool mroute_do_pim; + bool mroute_do_wrvifwhole; int mroute_reg_vif_num; }; -- cgit v1.2.3 From 25b4a2b909dc9fdd141ee4239cf78d1617a9d91d Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Wed, 11 Jul 2018 13:40:13 -0600 Subject: coresight: Remove function coresight_vpid_to_pid() Now that we prevent users from using contextID tracing when PID namespaces are involved there is no client for function coresight_vpid_to_pid(). As such simply remove it. Signed-off-by: Mathieu Poirier Reviewed-by: Kim Phillips Acked-by: "Eric W. Biederman" Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index c265e0468414..e5421b83e4e6 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -267,24 +267,4 @@ static inline struct coresight_platform_data *of_get_coresight_platform_data( struct device *dev, const struct device_node *node) { return NULL; } #endif -#ifdef CONFIG_PID_NS -static inline unsigned long -coresight_vpid_to_pid(unsigned long vpid) -{ - struct task_struct *task = NULL; - unsigned long pid = 0; - - rcu_read_lock(); - task = find_task_by_vpid(vpid); - if (task) - pid = task_pid_nr(task); - rcu_read_unlock(); - - return pid; -} -#else -static inline unsigned long -coresight_vpid_to_pid(unsigned long vpid) { return vpid; } -#endif - #endif -- cgit v1.2.3 From 575694978247b7cc1588ec233bde3fbf66db9e50 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Wed, 11 Jul 2018 13:40:27 -0600 Subject: coresight: Cleanup platform description data Nobody uses the "clk" field in struct coresight_platform_data. Remove it. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index e5421b83e4e6..69a5c9f82469 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -87,7 +87,6 @@ struct coresight_dev_subtype { * @child_ports:child component port number the current component is connected to. * @nr_outport: number of output ports for this component. - * @clk: The clock this component is associated to. */ struct coresight_platform_data { int cpu; @@ -97,7 +96,6 @@ struct coresight_platform_data { const char **child_names; int *child_ports; int nr_outport; - struct clk *clk; }; /** -- cgit v1.2.3 From 00b78e8b7b003c686a8570df7d231787f514226c Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Wed, 11 Jul 2018 13:40:29 -0600 Subject: coresight: Cleanup device subtype struct Clean up our struct a little bit by using a union instead of a struct for tracking the subtype of a device. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 69a5c9f82469..7c188c2a5b3c 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -63,17 +63,20 @@ enum coresight_dev_subtype_source { }; /** - * struct coresight_dev_subtype - further characterisation of a type + * union coresight_dev_subtype - further characterisation of a type * @sink_subtype: type of sink this component is, as defined - by @coresight_dev_subtype_sink. + * by @coresight_dev_subtype_sink. * @link_subtype: type of link this component is, as defined - by @coresight_dev_subtype_link. + * by @coresight_dev_subtype_link. * @source_subtype: type of source this component is, as defined - by @coresight_dev_subtype_source. + * by @coresight_dev_subtype_source. */ -struct coresight_dev_subtype { - enum coresight_dev_subtype_sink sink_subtype; - enum coresight_dev_subtype_link link_subtype; +union coresight_dev_subtype { + /* We have some devices which acts as LINK and SINK */ + struct { + enum coresight_dev_subtype_sink sink_subtype; + enum coresight_dev_subtype_link link_subtype; + }; enum coresight_dev_subtype_source source_subtype; }; @@ -111,7 +114,7 @@ struct coresight_platform_data { */ struct coresight_desc { enum coresight_dev_type type; - struct coresight_dev_subtype subtype; + union coresight_dev_subtype subtype; const struct coresight_ops *ops; struct coresight_platform_data *pdata; struct device *dev; @@ -155,7 +158,7 @@ struct coresight_device { int nr_inport; int nr_outport; enum coresight_dev_type type; - struct coresight_dev_subtype subtype; + union coresight_dev_subtype subtype; const struct coresight_ops *ops; struct device dev; atomic_t *refcnt; -- cgit v1.2.3 From 8a091d847cecd1a3656172cb79b53a19e90b8c4f Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Wed, 11 Jul 2018 13:40:30 -0600 Subject: coresight: Add helper device type Add a new coresight device type, which do not belong to any of the existing types, i.e, source, sink, link etc. A helper device could be connected to a coresight device, which could augment the functionality of the coresight device. This is intended to cover Coresight Address Translation Unit (CATU) devices, which provide improved Scatter Gather mechanism for TMC ETR. The idea is that the helper device could be controlled by the driver of the device it is attached to (in this case ETR), transparent to the generic coresight driver (and paths). The operations include enable(), disable(), both of which could accept a device specific "data" which the driving device and the helper device could share. Since they don't appear in the coresight "path" tracked by software, we have to ensure that they are powered up/down whenever the master device is turned on. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 7c188c2a5b3c..3d40a2b135f1 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -40,6 +40,7 @@ enum coresight_dev_type { CORESIGHT_DEV_TYPE_LINK, CORESIGHT_DEV_TYPE_LINKSINK, CORESIGHT_DEV_TYPE_SOURCE, + CORESIGHT_DEV_TYPE_HELPER, }; enum coresight_dev_subtype_sink { @@ -62,6 +63,10 @@ enum coresight_dev_subtype_source { CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE, }; +enum coresight_dev_subtype_helper { + CORESIGHT_DEV_SUBTYPE_HELPER_NONE, +}; + /** * union coresight_dev_subtype - further characterisation of a type * @sink_subtype: type of sink this component is, as defined @@ -70,6 +75,8 @@ enum coresight_dev_subtype_source { * by @coresight_dev_subtype_link. * @source_subtype: type of source this component is, as defined * by @coresight_dev_subtype_source. + * @helper_subtype: type of helper this component is, as defined + * by @coresight_dev_subtype_helper. */ union coresight_dev_subtype { /* We have some devices which acts as LINK and SINK */ @@ -78,6 +85,7 @@ union coresight_dev_subtype { enum coresight_dev_subtype_link link_subtype; }; enum coresight_dev_subtype_source source_subtype; + enum coresight_dev_subtype_helper helper_subtype; }; /** @@ -172,6 +180,7 @@ struct coresight_device { #define source_ops(csdev) csdev->ops->source_ops #define sink_ops(csdev) csdev->ops->sink_ops #define link_ops(csdev) csdev->ops->link_ops +#define helper_ops(csdev) csdev->ops->helper_ops /** * struct coresight_ops_sink - basic operations for a sink @@ -231,10 +240,25 @@ struct coresight_ops_source { struct perf_event *event); }; +/** + * struct coresight_ops_helper - Operations for a helper device. + * + * All operations could pass in a device specific data, which could + * help the helper device to determine what to do. + * + * @enable : Enable the device + * @disable : Disable the device + */ +struct coresight_ops_helper { + int (*enable)(struct coresight_device *csdev, void *data); + int (*disable)(struct coresight_device *csdev, void *data); +}; + struct coresight_ops { const struct coresight_ops_sink *sink_ops; const struct coresight_ops_link *link_ops; const struct coresight_ops_source *source_ops; + const struct coresight_ops_helper *helper_ops; }; #ifdef CONFIG_CORESIGHT -- cgit v1.2.3 From fcacb5c154baaeaee3d89b2a2b7cf6e4ce43f5f5 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Wed, 11 Jul 2018 13:40:31 -0600 Subject: coresight: Introduce support for Coresight Address Translation Unit Add the initial support for Coresight Address Translation Unit, which augments the TMC in Coresight SoC-600 by providing an improved Scatter Gather mechanism. CATU is always connected to a single TMC-ETR and converts the AXI address with a translated address (from a given SG table with specific format). The CATU should be programmed in pass through mode and enabled even if the ETR doesn't use the translation by CATU. This patch provides mechanism to enable/disable the CATU always in the pass through mode. We reuse the existing ports mechanism to link the TMC-ETR to the connected CATU. i.e, TMC-ETR:output_port0 -> CATU:input_port0 Reference manual for CATU component is avilable in version r2p0 of : "Arm Coresight System-on-Chip SoC-600 Technical Reference Manual". Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 3d40a2b135f1..d828a6efe0b1 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -65,6 +65,7 @@ enum coresight_dev_subtype_source { enum coresight_dev_subtype_helper { CORESIGHT_DEV_SUBTYPE_HELPER_NONE, + CORESIGHT_DEV_SUBTYPE_HELPER_CATU, }; /** -- cgit v1.2.3 From 571d78bd458a831cf51dff2afa1dda3309bd82b2 Mon Sep 17 00:00:00 2001 From: Wu Hao Date: Sat, 30 Jun 2018 08:53:09 +0800 Subject: fpga: mgr: add region_id to fpga_image_info This patch adds region_id to fpga_image_info data structure, it allows driver to pass region id information to fpga-mgr via fpga_image_info for fpga reconfiguration function. Signed-off-by: Wu Hao Acked-by: Moritz Fischer Acked-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index eec7c2478b0d..3eb6b9d60d65 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -77,6 +77,7 @@ enum fpga_mgr_states { * @sgt: scatter/gather table containing FPGA image * @buf: contiguous buffer containing FPGA image * @count: size of buf + * @region_id: id of target region * @dev: device that owns this * @overlay: Device Tree overlay */ @@ -89,6 +90,7 @@ struct fpga_image_info { struct sg_table *sgt; const char *buf; size_t count; + int region_id; struct device *dev; #ifdef CONFIG_OF struct device_node *overlay; -- cgit v1.2.3 From ecb5fbe299dfaad778033259f35bc696fa1fb743 Mon Sep 17 00:00:00 2001 From: Wu Hao Date: Sat, 30 Jun 2018 08:53:10 +0800 Subject: fpga: mgr: add status for fpga-manager This patch adds status sysfs interface for fpga manager, it's a read only interface which allows user to get fpga manager status, including full/partial reconfiguration error and other status information. It adds a status callback to fpga_manager_ops too, allows each fpga_manager driver to define its own method to collect latest status from hardware. The following sysfs file is created: * /sys/class/fpga_manager//status Return status of fpga manager, including reconfiguration errors. Signed-off-by: Wu Hao Acked-by: Alan Tull Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 3eb6b9d60d65..e249b7250345 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -101,6 +101,7 @@ struct fpga_image_info { * struct fpga_manager_ops - ops for low level fpga manager drivers * @initial_header_size: Maximum number of bytes that should be passed into write_init * @state: returns an enum value of the FPGA's state + * @status: returns status of the FPGA, including reconfiguration error code * @write_init: prepare the FPGA to receive confuration data * @write: write count bytes of configuration data to the FPGA * @write_sg: write the scatter list of configuration data to the FPGA @@ -115,6 +116,7 @@ struct fpga_image_info { struct fpga_manager_ops { size_t initial_header_size; enum fpga_mgr_states (*state)(struct fpga_manager *mgr); + u64 (*status)(struct fpga_manager *mgr); int (*write_init)(struct fpga_manager *mgr, struct fpga_image_info *info, const char *buf, size_t count); @@ -126,6 +128,13 @@ struct fpga_manager_ops { const struct attribute_group **groups; }; +/* FPGA manager status: Partial/Full Reconfiguration errors */ +#define FPGA_MGR_STATUS_OPERATION_ERR BIT(0) +#define FPGA_MGR_STATUS_CRC_ERR BIT(1) +#define FPGA_MGR_STATUS_INCOMPATIBLE_IMAGE_ERR BIT(2) +#define FPGA_MGR_STATUS_IP_PROTOCOL_ERR BIT(3) +#define FPGA_MGR_STATUS_FIFO_OVERFLOW_ERR BIT(4) + /** * struct fpga_manager - fpga manager structure * @name: name of low level fpga manager -- cgit v1.2.3 From 99a560bde313892f87ca81db568a829d3d205882 Mon Sep 17 00:00:00 2001 From: Wu Hao Date: Sat, 30 Jun 2018 08:53:11 +0800 Subject: fpga: mgr: add compat_id support This patch introduces compat_id support to fpga manager, it adds a fpga_compat_id pointer to fpga manager data structure to allow fpga manager drivers to save the compatibility id. This compat_id could be used for compatibility checking before doing partial reconfiguration to associated fpga regions. Signed-off-by: Wu Hao Acked-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index e249b7250345..8942e61f0028 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -135,12 +135,24 @@ struct fpga_manager_ops { #define FPGA_MGR_STATUS_IP_PROTOCOL_ERR BIT(3) #define FPGA_MGR_STATUS_FIFO_OVERFLOW_ERR BIT(4) +/** + * struct fpga_compat_id - id for compatibility check + * + * @id_h: high 64bit of the compat_id + * @id_l: low 64bit of the compat_id + */ +struct fpga_compat_id { + u64 id_h; + u64 id_l; +}; + /** * struct fpga_manager - fpga manager structure * @name: name of low level fpga manager * @dev: fpga manager device * @ref_mutex: only allows one reference to fpga manager * @state: state of fpga manager + * @compat_id: FPGA manager id for compatibility check. * @mops: pointer to struct of fpga manager ops * @priv: low level driver private date */ @@ -149,6 +161,7 @@ struct fpga_manager { struct device dev; struct mutex ref_mutex; enum fpga_mgr_states state; + struct fpga_compat_id *compat_id; const struct fpga_manager_ops *mops; void *priv; }; -- cgit v1.2.3 From 41a8b2c56470b7e4e3e2db93324d50bbbf60cdc4 Mon Sep 17 00:00:00 2001 From: Wu Hao Date: Sat, 30 Jun 2018 08:53:12 +0800 Subject: fpga: region: add compat_id support This patch introduces a compat_id pointer member and sysfs interface for each fpga region, similar as compat_id for fpga manager, it allows applications to read the per region compat_id for compatibility checking before other actions on this fpga-region (e.g. PR). Signed-off-by: Wu Hao Acked-by: Alan Tull Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-region.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index d7071cddd727..0521b7f577a4 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -14,6 +14,7 @@ * @bridge_list: list of FPGA bridges specified in region * @mgr: FPGA manager * @info: FPGA image info + * @compat_id: FPGA region id for compatibility check. * @priv: private data * @get_bridges: optional function to get bridges to a list */ @@ -23,6 +24,7 @@ struct fpga_region { struct list_head bridge_list; struct fpga_manager *mgr; struct fpga_image_info *info; + struct fpga_compat_id *compat_id; void *priv; int (*get_bridges)(struct fpga_region *region); }; -- cgit v1.2.3 From 5fd778915ad29184a5ff8eb82d1118f6916b79e4 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Thu, 28 Jun 2018 17:45:14 +0200 Subject: sched/sysctl: Remove unused sched_time_avg_ms sysctl /proc/sys/kernel/sched_time_avg_ms entry is not used anywhere, remove it. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Luis R. Rodriguez Cc: Kees Cook Cc: Linus Torvalds Cc: Morten.Rasmussen@arm.com Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: claudio@evidence.eu.com Cc: daniel.lezcano@linaro.org Cc: dietmar.eggemann@arm.com Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: luca.abeni@santannapisa.it Cc: patrick.bellasi@arm.com Cc: quentin.perret@arm.com Cc: rjw@rjwysocki.net Cc: valentin.schneider@arm.com Cc: viresh.kumar@linaro.org Link: http://lkml.kernel.org/r/1530200714-4504-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- include/linux/sched/sysctl.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 1c1a1512ec55..913488d828cb 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -40,7 +40,6 @@ extern unsigned int sysctl_numa_balancing_scan_size; #ifdef CONFIG_SCHED_DEBUG extern __read_mostly unsigned int sysctl_sched_migration_cost; extern __read_mostly unsigned int sysctl_sched_nr_migrate; -extern __read_mostly unsigned int sysctl_sched_time_avg; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, -- cgit v1.2.3 From 788faab70d5a882693286b8d5022779559c79904 Mon Sep 17 00:00:00 2001 From: Tobias Tefke Date: Mon, 9 Jul 2018 12:57:15 +0200 Subject: perf, tools: Use correct articles in comments Some of the comments in the perf events code use articles incorrectly, using 'a' for words beginning with a vowel sound, where 'an' should be used. Signed-off-by: Tobias Tefke Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@kernel.org Cc: alexander.shishkin@linux.intel.com Cc: jolsa@redhat.com Cc: namhyung@kernel.org Link: http://lkml.kernel.org/r/20180709105715.22938-1-tobias.tefke@tutanota.com [ Fix a few more perf related 'a event' typo fixes from all around the kernel and tooling tree. ] Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1fa12887ec02..e6dd3a2f8ec4 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -490,7 +490,7 @@ struct perf_addr_filters_head { }; /** - * enum perf_event_state - the states of a event + * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, -- cgit v1.2.3 From 3eb420e70d879ce0e6bf752accf5cdedb0a59de8 Mon Sep 17 00:00:00 2001 From: Sai Praneeth Date: Wed, 11 Jul 2018 11:40:35 +0200 Subject: efi: Use a work queue to invoke EFI Runtime Services Presently, when a user process requests the kernel to execute any UEFI runtime service, the kernel temporarily switches to a separate set of page tables that describe the virtual mapping of the UEFI runtime services regions in memory. Since UEFI runtime services are typically invoked with interrupts enabled, any code that may be called during this time, will have an incorrect view of the process's address space. Although it is unusual for code running in interrupt context to make assumptions about the process context it runs in, there are cases (such as the perf subsystem taking samples) where this causes problems. So let's set up a work queue for calling UEFI runtime services, so that the actual calls are made when the work queue items are dispatched by a work queue worker running in a separate kernel thread. Such threads are not expected to have userland mappings in the first place, and so the additional mappings created for the UEFI runtime services can never clash with any. The ResetSystem() runtime service is not covered by the work queue handling, since it is not expected to return, and may be called at a time when the kernel is torn down to the point where we cannot expect work queues to still be operational. The non-blocking variants of SetVariable() and QueryVariableInfo() are also excluded: these are intended to be used from atomic context, which obviously rules out waiting for a completion to be signalled by another thread. Note that these variants are currently only used for UEFI runtime services calls that occur very early in the boot, and for ones that occur in critical conditions, e.g., to flush kernel logs to UEFI variables via efi-pstore. Suggested-by: Andy Lutomirski Signed-off-by: Sai Praneeth Prakhya [ardb: exclude ResetSystem() from the workqueue treatment merge from 2 separate patches and rewrite commit log] Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20180711094040.12506-4-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 56add823f190..8ba0cdd244b2 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1651,4 +1651,7 @@ struct linux_efi_tpm_eventlog { extern int efi_tpm_eventlog_init(void); +/* Workqueue to queue EFI Runtime Services */ +extern struct workqueue_struct *efi_rts_wq; + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From f5dcc214aae29a68b37b2b4183f7171724e7b02d Mon Sep 17 00:00:00 2001 From: Sai Praneeth Date: Wed, 11 Jul 2018 11:40:37 +0200 Subject: efi: Remove the declaration of efi_late_init() as the function is unused The following commit: 7b0a911478c74 ("efi/x86: Move the EFI BGRT init code to early init code") ... removed the implementation and all the references to efi_late_init() but the function is still declared at include/linux/efi.h. Hence, remove the unnecessary declaration. Signed-off-by: Sai Praneeth Prakhya Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20180711094040.12506-6-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 8ba0cdd244b2..e190652f5ef9 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -988,14 +988,12 @@ extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg); extern void efi_gettimeofday (struct timespec64 *ts); extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */ #ifdef CONFIG_X86 -extern void efi_late_init(void); extern void efi_free_boot_services(void); extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size, bool nonblocking); extern void efi_find_mirror(void); #else -static inline void efi_late_init(void) {} static inline void efi_free_boot_services(void) {} static inline efi_status_t efi_query_variable_store(u32 attributes, -- cgit v1.2.3 From 784abe24c903b093af04cf1a043140faa556cad7 Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Fri, 13 Jul 2018 14:33:35 +0300 Subject: net: Add decrypted field to skb The decrypted bit is propogated to cloned/copied skbs. This will be used later by the inline crypto receive side offload of tls. Signed-off-by: Boris Pismenny Signed-off-by: Ilya Lesokhin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7601838c2513..3ceb8dcc54da 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -630,6 +630,7 @@ typedef unsigned char *sk_buff_data_t; * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @xmit_more: More SKBs are pending for this queue + * @decrypted: Decrypted SKB * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport @@ -736,7 +737,11 @@ struct sk_buff { peeked:1, head_frag:1, xmit_more:1, - __unused:1; /* one bit hole */ +#ifdef CONFIG_TLS_DEVICE + decrypted:1; +#else + __unused:1; +#endif /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() -- cgit v1.2.3 From 14136564c8ee94566945e85014019cbdb1716dca Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Fri, 13 Jul 2018 14:33:36 +0300 Subject: net: Add TLS RX offload feature This patch adds a netdev feature to configure TLS RX inline crypto offload. Signed-off-by: Ilya Lesokhin Signed-off-by: Boris Pismenny Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 623bb8ced060..2b2a6dce1630 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -79,6 +79,7 @@ enum { NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */ NETIF_F_HW_TLS_TX_BIT, /* Hardware TLS TX offload */ + NETIF_F_HW_TLS_RX_BIT, /* Hardware TLS RX offload */ NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */ NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */ @@ -151,6 +152,7 @@ enum { #define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD) #define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4) #define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX) +#define NETIF_F_HW_TLS_RX __NETIF_F(HW_TLS_RX) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) -- cgit v1.2.3 From 16e4edc297ffc9b643b8dd3da6b0d579753ea2b3 Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Fri, 13 Jul 2018 14:33:37 +0300 Subject: net: Add TLS rx resync NDO Add new netdev tls op for resynchronizing HW tls context Signed-off-by: Boris Pismenny Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4fa7f7a3f8b3..3514d67112b3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -903,6 +903,8 @@ struct tlsdev_ops { void (*tls_dev_del)(struct net_device *netdev, struct tls_context *ctx, enum tls_offload_ctx_dir direction); + void (*tls_dev_resync_rx)(struct net_device *netdev, + struct sock *sk, u32 seq, u64 rcd_sn); }; #endif -- cgit v1.2.3 From ab412e1dd7db132c2abeb9385b4bf0dc8e6c5a65 Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Fri, 13 Jul 2018 14:33:46 +0300 Subject: net/mlx5: Accel, add TLS rx offload routines In Innova TLS, TLS contexts are added or deleted via a command message over the SBU connection. The HW then sends a response message over the same connection. Complete the implementation for Innova TLS (FPGA-based) hardware by adding support for rx inline crypto offload. Signed-off-by: Boris Pismenny Signed-off-by: Ilya Lesokhin Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc_fpga.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index 64d0f40d4cc3..37e065a80a43 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -576,6 +576,7 @@ struct mlx5_ifc_fpga_ipsec_sa { enum fpga_tls_cmds { CMD_SETUP_STREAM = 0x1001, CMD_TEARDOWN_STREAM = 0x1002, + CMD_RESYNC_RX = 0x1003, }; #define MLX5_TLS_1_2 (0) -- cgit v1.2.3 From a94a7483a91cb6a0d15a4413e8fc853f33a4e1b9 Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Wed, 30 May 2018 10:11:43 +0800 Subject: mmc: core: Adjust and reuse the macro of R1_STATUS(x) R1_STATUS(x) now is only used by ioctl_rpmb_card_status_poll(), which checks all bits as possible. But according to the spec, bit 17 and bit 18 should be ignored, as well bit 14 which is reserved(must be set to 0) quoting from the spec and these rule apply to all places checking the device status. So change its checking from 0xFFFFE000 to 0xFFF9A000. As a bonus, we reuse it for mmc_do_erase() as well as mmc_switch_status_error(). (1) Currently mmc_switch_status_error() doesn't check bit 25, but it means device is locked but not unlocked by CMD42 prior to any operations which need check busy, which is also not allowed. (2) mmc_do_erase() also forgot to to check bit 15, WP_ERASE_SKIP. The spec says "Only partial address space was erased due to existing write protected blocks.", which obviously means we should fail this I/O. Otherwise, the partial erased data stored in nonvalatile flash violates the data integrity from the view of I/O owner, which probably confuse it when further used. So reusing R1_STATUS for them not only improve the readability but also slove real problems. Signed-off-by: Shawn Lin Signed-off-by: Ulf Hansson --- include/linux/mmc/mmc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 3ffc27aaeeaf..897a87c4c827 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -144,7 +144,7 @@ static inline bool mmc_op_multi(u32 opcode) #define R1_WP_ERASE_SKIP (1 << 15) /* sx, c */ #define R1_CARD_ECC_DISABLED (1 << 14) /* sx, a */ #define R1_ERASE_RESET (1 << 13) /* sr, c */ -#define R1_STATUS(x) (x & 0xFFFFE000) +#define R1_STATUS(x) (x & 0xFFF9A000) #define R1_CURRENT_STATE(x) ((x & 0x00001E00) >> 9) /* sx, b (4 bits) */ #define R1_READY_FOR_DATA (1 << 8) /* sx, a */ #define R1_SWITCH_ERROR (1 << 7) /* sx, c */ -- cgit v1.2.3 From ba6c7ac3a2f421635ae4446269526359d8bff721 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 18 Jun 2018 14:57:49 +0200 Subject: mmc: core: more fine-grained hooks for HS400 tuning This adds two new HS400 tuning operations: * hs400_downgrade * hs400_complete These supplement the existing HS400 operation: * prepare_hs400_tuning This is motivated by a requirement of Renesas SDHI for the following: 1. Disabling SCC before selecting to HS if selection of HS400 has occurred. This can be done in an implementation of prepare_hs400_tuning_downgrade 2. Updating registers after switching to HS400 This can be done in an implementation of complete_hs400_tuning If hs400_downgrade or hs400_complete are not implemented then they are not called. Thus means there should be no affect for existing drivers as none implemt these ops. Signed-off-by: Simon Horman Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 64300a48dcce..a39e2925c84c 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -146,6 +146,13 @@ struct mmc_host_ops { /* Prepare HS400 target operating frequency depending host driver */ int (*prepare_hs400_tuning)(struct mmc_host *host, struct mmc_ios *ios); + + /* Prepare for switching from HS400 to HS200 */ + void (*hs400_downgrade)(struct mmc_host *host); + + /* Complete selection of HS400 */ + void (*hs400_complete)(struct mmc_host *host); + /* Prepare enhanced strobe depending host driver */ void (*hs400_enhanced_strobe)(struct mmc_host *host, struct mmc_ios *ios); -- cgit v1.2.3 From db924bba47c8031188545c84bf943f4058b659d0 Mon Sep 17 00:00:00 2001 From: Masaharu Hayakawa Date: Mon, 18 Jun 2018 14:57:50 +0200 Subject: mmc: tmio: add eMMC HS400 mode support This patch adds processing for selecting HS400 mode. Signed-off-by: Masaharu Hayakawa Signed-off-by: Simon Horman Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 91f92215ca74..77866214ab51 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -90,6 +90,9 @@ /* Some controllers have a CBSY bit */ #define TMIO_MMC_HAVE_CBSY BIT(11) +/* Some controllers that support HS400 use use 4 taps while others use 8. */ +#define TMIO_MMC_HAVE_4TAP_HS400 BIT(13) + int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base); int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base); void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state); -- cgit v1.2.3 From 29772f8a73d88a5de648177d9d822055ab7d1ba6 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 26 Jun 2018 16:51:31 +0200 Subject: mmc: core: Drop the unused mmc_power_save|restore_host() The last user of mmc_power_save|restore_host() APIs is gone, hence let's drop them. Drop also the corresponding bus_ops callback, ->power_save|restore() as those becomes redundant. Cc: Tony Lindgren Cc: Eyal Reizer Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index a39e2925c84c..beed7121c781 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -481,9 +481,6 @@ static inline void *mmc_priv(struct mmc_host *host) #define mmc_classdev(x) (&(x)->class_dev) #define mmc_hostname(x) (dev_name(&(x)->class_dev)) -int mmc_power_save_host(struct mmc_host *host); -int mmc_power_restore_host(struct mmc_host *host); - void mmc_detect_change(struct mmc_host *, unsigned long delay); void mmc_request_done(struct mmc_host *, struct mmc_request *); void mmc_command_done(struct mmc_host *host, struct mmc_request *mrq); -- cgit v1.2.3 From 86f495c57f7146bc5d363d27483957928bb9d1d8 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Thu, 28 Jun 2018 10:13:29 +0200 Subject: mmc: sdhci-esdhc-imx: get rid of support_vsel The field support_vsel is currently only used in the device tree case. Get rid of it. No change in behavior. Signed-off-by: Stefan Agner Signed-off-by: Ulf Hansson --- include/linux/platform_data/mmc-esdhc-imx.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h index 7daa78a2f342..640dec8b5b0c 100644 --- a/include/linux/platform_data/mmc-esdhc-imx.h +++ b/include/linux/platform_data/mmc-esdhc-imx.h @@ -34,7 +34,6 @@ enum cd_types { * @cd_gpio: gpio for card_detect interrupt * @wp_type: type of write_protect method (see wp_types enum above) * @cd_type: type of card_detect method (see cd_types enum above) - * @support_vsel: indicate it supports 1.8v switching */ struct esdhc_platform_data { @@ -43,7 +42,6 @@ struct esdhc_platform_data { enum wp_types wp_type; enum cd_types cd_type; int max_bus_width; - bool support_vsel; unsigned int delay_line; unsigned int tuning_step; /* The delay cell steps in tuning procedure */ unsigned int tuning_start_tap; /* The start delay cell point in tuning procedure */ -- cgit v1.2.3 From 8b0bbd956228ae87139673e5611c4c880ddb9529 Mon Sep 17 00:00:00 2001 From: Chris Brandt Date: Wed, 11 Jul 2018 09:41:30 -0500 Subject: serial: sh-sci: Add support for R7S9210 Add support for a "RZ_SCIFA" which is different than a traditional SCIFA. It looks like a normal SCIF with FIFO data, but with a compressed address space. Also, the break out of interrupts are different then traditinal SCIF: ERI/BRI, RXI, TXI, TEI, DRI. The R7S9210 (RZ/A2) contains this type of SCIF. Signed-off-by: Chris Brandt Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_sci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index c0e795d95477..1c89611e0e06 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -36,6 +36,7 @@ enum { SCIx_SH4_SCIF_FIFODATA_REGTYPE, SCIx_SH7705_SCIF_REGTYPE, SCIx_HSCIF_REGTYPE, + SCIx_RZ_SCIFA_REGTYPE, SCIx_NR_REGTYPES, }; -- cgit v1.2.3 From 3ec78790ec9a1e23fd9b6c8681a7cd3b64d3ad23 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 15 Jul 2018 10:31:28 -0700 Subject: sysfs.h: fix non-kernel-doc comment Don't use "/**" to begin this comment block since it is not a kernel-doc comment block. Also adjust comment line to fit in 80 characters. Signed-off-by: Randy Dunlap Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index b8bfdc173ec0..8e08a90b1d15 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -91,9 +91,9 @@ struct attribute_group { struct bin_attribute **bin_attrs; }; -/** - * Use these macros to make defining attributes easier. See include/linux/device.h - * for examples.. +/* + * Use these macros to make defining attributes easier. + * See include/linux/device.h for examples.. */ #define SYSFS_PREALLOC 010000 -- cgit v1.2.3 From 726e41097920a73e4c7c33385dcc0debb1281e18 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 10 Jul 2018 10:29:10 +1000 Subject: drivers: core: Remove glue dirs from sysfs earlier For devices with a class, we create a "glue" directory between the parent device and the new device with the class name. This directory is never "explicitely" removed when empty however, this is left to the implicit sysfs removal done by kobject_release() when the object loses its last reference via kobject_put(). This is problematic because as long as it's not been removed from sysfs, it is still present in the class kset and in sysfs directory structure. The presence in the class kset exposes a use after free bug fixed by the previous patch, but the presence in sysfs means that until the kobject is released, which can take a while (especially with kobject debugging), any attempt at re-creating such as binding a new device for that class/parent pair, will result in a sysfs duplicate file name error. This fixes it by instead doing an explicit kobject_del() when the glue dir is empty, by keeping track of the number of child devices of the gluedir. This is made easy by the fact that all glue dir operations are done with a global mutex, and there's already a function (cleanup_glue_dir) called in all the right places taking that mutex that can be enhanced for this. It appears that this was in fact the intent of the function, but the implementation was wrong. Signed-off-by: Benjamin Herrenschmidt Acked-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 7f6f93c3df9c..270b40515e79 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -116,6 +116,23 @@ extern void kobject_put(struct kobject *kobj); extern const void *kobject_namespace(struct kobject *kobj); extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); +/** + * kobject_has_children - Returns whether a kobject has children. + * @kobj: the object to test + * + * This will return whether a kobject has other kobjects as children. + * + * It does NOT account for the presence of attribute files, only sub + * directories. It also assumes there is no concurrent addition or + * removal of such children, and thus relies on external locking. + */ +static inline bool kobject_has_children(struct kobject *kobj) +{ + WARN_ON_ONCE(kref_read(&kobj->kref) == 0); + + return kobj->sd && kobj->sd->dir.subdirs; +} + struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; -- cgit v1.2.3 From a4f9edb29d9c19f9f8dcd2df7ddfe4eb7ad58996 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 30 May 2018 17:29:52 +0100 Subject: irqchip/gic-v3: Expose GICD_TYPER in the rdist structure Instead of exposing the GIC distributor IntID field in the rdist structure that is passed to the ITS, let's replace it with a copy of the whole GICD_TYPER register. We are going to need some of this information at a later time. No functionnal change. Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index cbb872c1b607..396cd99af02f 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -576,8 +576,8 @@ struct rdists { phys_addr_t phys_base; } __percpu *rdist; struct page *prop_page; - int id_bits; u64 flags; + u32 gicd_typer; bool has_vlpis; bool has_direct_lpi; }; -- cgit v1.2.3 From 12b2905af183c931bedcab4292c81d3a415e080f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 31 May 2018 09:01:59 +0100 Subject: irqchip/gic-v3-its: Honor hypervisor enforced LPI range A recent extension to the GIC architecture allows a hypervisor to arbitrarily reduce the number of LPIs available to a guest, no matter what the GIC says about the valid range of IntIDs. Let's factor in this information when computing the number of available LPIs Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 396cd99af02f..9d2ea3e907d0 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -73,6 +73,7 @@ #define GICD_TYPER_MBIS (1U << 16) #define GICD_TYPER_ID_BITS(typer) ((((typer) >> 19) & 0x1f) + 1) +#define GICD_TYPER_NUM_LPIS(typer) ((((typer) >> 11) & 0x1f) + 1) #define GICD_TYPER_IRQS(typer) ((((typer) & 0x1f) + 1) * 32) #define GICD_IROUTER_SPI_MODE_ONE (0U << 31) -- cgit v1.2.3 From 0f292f023ffcc67ec49d63dcb7fe388711cbb83a Mon Sep 17 00:00:00 2001 From: Jorge Sanjuan Date: Wed, 11 Jul 2018 13:37:53 +0100 Subject: ALSA: usb-audio: Add support for Processing Units in UAC3 This patch adds support for the Processig Units defined in the UAC3 spec. The main difference with the previous specs is the lack of on/off switches in the controls for these units and the addiction of the new Multi Function Processing Unit. The current version of the UAC3 spec doesn't define any useful controls for the new Multi Function Processing Unit so no control will get created once this unit is parsed. Signed-off-by: Jorge Sanjuan Signed-off-by: Takashi Iwai --- include/linux/usb/audio-v3.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h index a710e28b5215..334bfa6dfb47 100644 --- a/include/linux/usb/audio-v3.h +++ b/include/linux/usb/audio-v3.h @@ -387,6 +387,12 @@ struct uac3_interrupt_data_msg { #define UAC3_CONNECTORS 0x0f #define UAC3_POWER_DOMAIN 0x10 +/* A.20 PROCESSING UNIT PROCESS TYPES */ +#define UAC3_PROCESS_UNDEFINED 0x00 +#define UAC3_PROCESS_UP_DOWNMIX 0x01 +#define UAC3_PROCESS_STEREO_EXTENDER 0x02 +#define UAC3_PROCESS_MULTI_FUNCTION 0x03 + /* A.22 AUDIO CLASS-SPECIFIC REQUEST CODES */ /* see audio-v2.h for the rest, which is identical to v2 */ #define UAC3_CS_REQ_INTEN 0x04 @@ -406,6 +412,15 @@ struct uac3_interrupt_data_msg { #define UAC3_TE_OVERFLOW 0x04 #define UAC3_TE_LATENCY 0x05 +/* A.23.10 PROCESSING UNITS CONTROL SELECTROS */ + +/* Up/Down Mixer */ +#define UAC3_UD_MODE_SELECT 0x01 + +/* Stereo Extender */ +#define UAC3_EXT_WIDTH_CONTROL 0x01 + + /* BADD predefined Unit/Terminal values */ #define UAC3_BADD_IT_ID1 1 /* Input Terminal ID1: bTerminalID = 1 */ #define UAC3_BADD_FU_ID2 2 /* Feature Unit ID2: bUnitID = 2 */ -- cgit v1.2.3 From d7e5a9a50245b91f016c814b0f076f7e55cbb980 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Jun 2018 17:49:43 +0200 Subject: netfilter: utils: move nf_ip_checksum* from ipv4 to utils allows to make nf_ip_checksum_partial static, it no longer has an external caller. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv4.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index b31dabfdb453..95ab5cc64422 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -23,9 +23,6 @@ struct nf_queue_entry; #ifdef CONFIG_INET __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); -__sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, unsigned int len, - u_int8_t protocol); int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict); int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry); @@ -35,14 +32,6 @@ static inline __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, { return 0; } -static inline __sum16 nf_ip_checksum_partial(struct sk_buff *skb, - unsigned int hook, - unsigned int dataoff, - unsigned int len, - u_int8_t protocol) -{ - return 0; -} static inline int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict) { -- cgit v1.2.3 From ebee5a50d0b7cdc576aa8081f05b86971880054d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Jun 2018 17:49:59 +0200 Subject: netfilter: utils: move nf_ip6_checksum* from ipv6 to utils similar to previous change, this also allows to remove it from nf_ipv6_ops and avoid the indirection. It also removes the bogus dependency of nf_conntrack_ipv6 on ipv6 module: ipv6 checksum functions are built into kernel even if CONFIG_IPV6=m, but ipv6/netfilter.o isn't. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 288c597e75b3..c0dc4dd78887 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -30,11 +30,6 @@ struct nf_ipv6_ops { void (*route_input)(struct sk_buff *skb); int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); - __sum16 (*checksum)(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, u_int8_t protocol); - __sum16 (*checksum_partial)(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, unsigned int len, - u_int8_t protocol); int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict); int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); -- cgit v1.2.3 From d1b47a7c9efcf3c3384b70f6e3c8f1423b44d8c7 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Mon, 16 Jul 2018 11:16:30 -0400 Subject: mm: don't do zero_resv_unavail if memmap is not allocated Moving zero_resv_unavail before memmap_init_zone(), caused a regression on x86-32. The cause is that we access struct pages before they are allocated when CONFIG_FLAT_NODE_MEM_MAP is used. free_area_init_nodes() zero_resv_unavail() mm_zero_struct_page(pfn_to_page(pfn)); <- struct page is not alloced free_area_init_node() if CONFIG_FLAT_NODE_MEM_MAP alloc_node_mem_map() memblock_virt_alloc_node_nopanic() <- struct page alloced here On the other hand memblock_virt_alloc_node_nopanic() zeroes all the memory that it returns, so we do not need to do zero_resv_unavail() here. Fixes: e181ae0c5db9 ("mm: zero unavailable pages before memmap init") Signed-off-by: Pavel Tatashin Tested-by: Matt Hart Acked-by: Michal Hocko Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a0fbb9ffe380..3982c83fdcbf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2132,7 +2132,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif -#ifdef CONFIG_HAVE_MEMBLOCK +#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) void zero_resv_unavail(void); #else static inline void zero_resv_unavail(void) {} -- cgit v1.2.3 From 6e2059b53f9885f202b086d7b4ca10a98926e974 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 10 Jul 2018 22:41:26 +0800 Subject: ipv4/igmp: init group mode as INCLUDE when join source group Based on RFC3376 5.1 If no interface state existed for that multicast address before the change (i.e., the change consisted of creating a new per-interface record), or if no state exists after the change (i.e., the change consisted of deleting a per-interface record), then the "non-existent" state is considered to have a filter mode of INCLUDE and an empty source list. Which means a new multicast group should start with state IN(). Function ip_mc_join_group() works correctly for IGMP ASM(Any-Source Multicast) mode. It adds a group with state EX() and inits crcount to mc_qrv, so the kernel will send a TO_EX() report message after adding group. But for IGMPv3 SSM(Source-specific multicast) JOIN_SOURCE_GROUP mode, we split the group joining into two steps. First we join the group like ASM, i.e. via ip_mc_join_group(). So the state changes from IN() to EX(). Then we add the source-specific address with INCLUDE mode. So the state changes from EX() to IN(A). Before the first step sends a group change record, we finished the second step. So we will only send the second change record. i.e. TO_IN(A). Regarding the RFC stands, we should actually send an ALLOW(A) message for SSM JOIN_SOURCE_GROUP as the state should mimic the 'IN() to IN(A)' transition. The issue was exposed by commit a052517a8ff65 ("net/multicast: should not send source list records when have filter mode change"). Before this change, we used to send both ALLOW(A) and TO_IN(A). After this change we only send TO_IN(A). Fix it by adding a new parameter to init group mode. Also add new wrapper functions so we don't need to change too much code. v1 -> v2: In my first version I only cleared the group change record. But this is not enough. Because when a new group join, it will init as EXCLUDE and trigger an filter mode change in ip/ip6_mc_add_src(), which will clear all source addresses' sf_crcount. This will prevent early joined address sending state change records if multi source addressed joined at the same time. In v2 patch, I fixed it by directly initializing the mode to INCLUDE for SSM JOIN_SOURCE_GROUP. I also split the original patch into two separated patches for IPv4 and IPv6. Fixes: a052517a8ff65 ("net/multicast: should not send source list records when have filter mode change") Reviewed-by: Stefano Brivio Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index f8231854b5d6..119f53941c12 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -109,6 +109,8 @@ struct ip_mc_list { extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); +extern int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, + unsigned int mode); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern void ip_mc_drop_socket(struct sock *sk); extern int ip_mc_source(int add, int omode, struct sock *sk, -- cgit v1.2.3 From 377179cd28cd417dcfb4396edb824533431e607e Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Fri, 13 Jul 2018 14:05:56 -0400 Subject: security: define new LSM hook named security_kernel_load_data Differentiate between the kernel reading a file specified by userspace from the kernel loading a buffer containing data provided by userspace. This patch defines a new LSM hook named security_kernel_load_data(). Signed-off-by: Mimi Zohar Cc: Eric Biederman Cc: Luis R. Rodriguez Cc: Kees Cook Cc: Casey Schaufler Acked-by: Serge Hallyn Acked-by: Kees Cook Signed-off-by: James Morris --- include/linux/lsm_hooks.h | 6 ++++++ include/linux/security.h | 27 +++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 8f1131c8dd54..a08bc2587b96 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -576,6 +576,10 @@ * userspace to load a kernel module with the given name. * @kmod_name name of the module requested by the kernel * Return 0 if successful. + * @kernel_load_data: + * Load data provided by userspace. + * @id kernel load data identifier + * Return 0 if permission is granted. * @kernel_read_file: * Read a file specified by userspace. * @file contains the file structure pointing to the file being read @@ -1582,6 +1586,7 @@ union security_list_options { int (*kernel_act_as)(struct cred *new, u32 secid); int (*kernel_create_files_as)(struct cred *new, struct inode *inode); int (*kernel_module_request)(char *kmod_name); + int (*kernel_load_data)(enum kernel_load_data_id id); int (*kernel_read_file)(struct file *file, enum kernel_read_file_id id); int (*kernel_post_read_file)(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id); @@ -1872,6 +1877,7 @@ struct security_hook_heads { struct hlist_head cred_getsecid; struct hlist_head kernel_act_as; struct hlist_head kernel_create_files_as; + struct hlist_head kernel_load_data; struct hlist_head kernel_read_file; struct hlist_head kernel_post_read_file; struct hlist_head kernel_module_request; diff --git a/include/linux/security.h b/include/linux/security.h index 63030c85ee19..3410acfe139c 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -159,6 +159,27 @@ extern int mmap_min_addr_handler(struct ctl_table *table, int write, typedef int (*initxattrs) (struct inode *inode, const struct xattr *xattr_array, void *fs_data); + +/* Keep the kernel_load_data_id enum in sync with kernel_read_file_id */ +#define __data_id_enumify(ENUM, dummy) LOADING_ ## ENUM, +#define __data_id_stringify(dummy, str) #str, + +enum kernel_load_data_id { + __kernel_read_file_id(__data_id_enumify) +}; + +static const char * const kernel_load_data_str[] = { + __kernel_read_file_id(__data_id_stringify) +}; + +static inline const char *kernel_load_data_id_str(enum kernel_load_data_id id) +{ + if ((unsigned)id >= LOADING_MAX_ID) + return kernel_load_data_str[LOADING_UNKNOWN]; + + return kernel_load_data_str[id]; +} + #ifdef CONFIG_SECURITY struct security_mnt_opts { @@ -320,6 +341,7 @@ void security_cred_getsecid(const struct cred *c, u32 *secid); int security_kernel_act_as(struct cred *new, u32 secid); int security_kernel_create_files_as(struct cred *new, struct inode *inode); int security_kernel_module_request(char *kmod_name); +int security_kernel_load_data(enum kernel_load_data_id id); int security_kernel_read_file(struct file *file, enum kernel_read_file_id id); int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id); @@ -909,6 +931,11 @@ static inline int security_kernel_module_request(char *kmod_name) return 0; } +static inline int security_kernel_load_data(enum kernel_load_data_id id) +{ + return 0; +} + static inline int security_kernel_read_file(struct file *file, enum kernel_read_file_id id) { -- cgit v1.2.3 From 16c267aac86b463b1fcccd43c89f4c8e5c5c86fa Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Fri, 13 Jul 2018 14:05:58 -0400 Subject: ima: based on policy require signed kexec kernel images The original kexec_load syscall can not verify file signatures, nor can the kexec image be measured. Based on policy, deny the kexec_load syscall. Signed-off-by: Mimi Zohar Cc: Eric Biederman Cc: Kees Cook Reviewed-by: Kees Cook Signed-off-by: James Morris --- include/linux/ima.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 0e4647e0eb60..84806b54b50a 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -11,6 +11,7 @@ #define _LINUX_IMA_H #include +#include #include struct linux_binprm; @@ -19,6 +20,7 @@ extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask, int opened); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); +extern int ima_load_data(enum kernel_load_data_id id); extern int ima_read_file(struct file *file, enum kernel_read_file_id id); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); @@ -49,6 +51,11 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot) return 0; } +static inline int ima_load_data(enum kernel_load_data_id id) +{ + return 0; +} + static inline int ima_read_file(struct file *file, enum kernel_read_file_id id) { return 0; -- cgit v1.2.3 From 2b9672ddb6f347467d7b33b86c5dfc4d5c0501a8 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 12 Jul 2018 21:32:53 +0200 Subject: net: phy: add phy_speed_down and phy_speed_up Some network drivers include functionality to speed down the PHY when suspending and just waiting for a WoL packet because this saves energy. This functionality is quite generic, therefore let's factor it out to phylib. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 6cd09098427c..075c2f770d3e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -942,6 +942,8 @@ void phy_start(struct phy_device *phydev); void phy_stop(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); +int phy_speed_down(struct phy_device *phydev, bool sync); +int phy_speed_up(struct phy_device *phydev); int phy_stop_interrupts(struct phy_device *phydev); int phy_restart_aneg(struct phy_device *phydev); -- cgit v1.2.3 From d9f37d01e294e5338aa3e9d3b2eda61b59b619df Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Fri, 13 Jul 2018 14:41:36 +0800 Subject: net: convert gro_count to bitmask gro_hash size is 192 bytes, and uses 3 cache lines, if there is few flows, gro_hash may be not fully used, so it is unnecessary to iterate all gro_hash in napi_gro_flush(), to occupy unnecessary cacheline. convert gro_count to a bitmask, and rename it as gro_bitmask, each bit represents a element of gro_hash, only flush a gro_hash element if the related bit is set, to speed up napi_gro_flush(). and update gro_bitmask only if it will be changed, to reduce cache update Suggested-by: Eric Dumazet Signed-off-by: Li RongQing Cc: Stefano Brivio Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3514d67112b3..c1295c7a452e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -308,9 +308,14 @@ struct gro_list { }; /* - * Structure for NAPI scheduling similar to tasklet but with weighting + * size of gro hash buckets, must less than bit number of + * napi_struct::gro_bitmask */ #define GRO_HASH_BUCKETS 8 + +/* + * Structure for NAPI scheduling similar to tasklet but with weighting + */ struct napi_struct { /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means @@ -322,7 +327,7 @@ struct napi_struct { unsigned long state; int weight; - unsigned int gro_count; + unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL int poll_owner; -- cgit v1.2.3 From c133459765fae249ba482f62e12f987aec4376f0 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 13 Jul 2018 21:25:19 -0700 Subject: net/ethernet/freescale/fman: fix cross-build error CC [M] drivers/net/ethernet/freescale/fman/fman.o In file included from ../drivers/net/ethernet/freescale/fman/fman.c:35: ../include/linux/fsl/guts.h: In function 'guts_set_dmacr': ../include/linux/fsl/guts.h:165:2: error: implicit declaration of function 'clrsetbits_be32' [-Werror=implicit-function-declaration] clrsetbits_be32(&guts->dmacr, 3 << shift, device << shift); ^~~~~~~~~~~~~~~ Signed-off-by: Randy Dunlap Cc: Madalin Bucur Cc: netdev@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: David S. Miller --- include/linux/fsl/guts.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsl/guts.h b/include/linux/fsl/guts.h index 3efa3b861d44..941b11811f85 100644 --- a/include/linux/fsl/guts.h +++ b/include/linux/fsl/guts.h @@ -16,6 +16,7 @@ #define __FSL_GUTS_H__ #include +#include /** * Global Utility Registers. -- cgit v1.2.3 From 3d85b2703783636366560c94842affd8608ec9d1 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Mon, 16 Jul 2018 11:06:02 -0700 Subject: locking/spinlock, sched/core: Clarify requirements for smp_mb__after_spinlock() There are 11 interpretations of the requirements described in the header comment for smp_mb__after_spinlock(): one for each LKMM maintainer, and one currently encoded in the Cat file. Stick to the latter (until a more satisfactory solution is available). This also reworks some snippets related to the barrier to illustrate the requirements and to link them to the idioms which are relied upon at its call sites. Suggested-by: Boqun Feng Signed-off-by: Andrea Parri Signed-off-by: Paul E. McKenney Acked-by: Peter Zijlstra Cc: Linus Torvalds Cc: Thomas Gleixner Cc: Will Deacon Cc: akiyks@gmail.com Cc: dhowells@redhat.com Cc: j.alglave@ucl.ac.uk Cc: linux-arch@vger.kernel.org Cc: luc.maranget@inria.fr Cc: npiggin@gmail.com Cc: parri.andrea@gmail.com Cc: stern@rowland.harvard.edu Link: http://lkml.kernel.org/r/20180716180605.16115-11-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/spinlock.h | 53 ++++++++++++++++++++++++++++++++---------------- 1 file changed, 36 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index fd57888d4942..3190997df9ca 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -114,29 +114,48 @@ do { \ #endif /*arch_spin_is_contended*/ /* - * This barrier must provide two things: + * smp_mb__after_spinlock() provides the equivalent of a full memory barrier + * between program-order earlier lock acquisitions and program-order later + * memory accesses. * - * - it must guarantee a STORE before the spin_lock() is ordered against a - * LOAD after it, see the comments at its two usage sites. + * This guarantees that the following two properties hold: * - * - it must ensure the critical section is RCsc. + * 1) Given the snippet: * - * The latter is important for cases where we observe values written by other - * CPUs in spin-loops, without barriers, while being subject to scheduling. + * { X = 0; Y = 0; } * - * CPU0 CPU1 CPU2 + * CPU0 CPU1 * - * for (;;) { - * if (READ_ONCE(X)) - * break; - * } - * X=1 - * - * - * r = X; + * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1); + * spin_lock(S); smp_mb(); + * smp_mb__after_spinlock(); r1 = READ_ONCE(X); + * r0 = READ_ONCE(Y); + * spin_unlock(S); * - * without transitivity it could be that CPU1 observes X!=0 breaks the loop, - * we get migrated and CPU2 sees X==0. + * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0) + * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments + * preceding the call to smp_mb__after_spinlock() in __schedule() and in + * try_to_wake_up(). + * + * 2) Given the snippet: + * + * { X = 0; Y = 0; } + * + * CPU0 CPU1 CPU2 + * + * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y); + * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb(); + * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X); + * WRITE_ONCE(Y, 1); + * spin_unlock(S); + * + * it is forbidden that CPU0's critical section executes before CPU1's + * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1) + * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments + * preceding the calls to smp_rmb() in try_to_wake_up() for similar + * snippets but "projected" onto two CPUs. + * + * Property (2) upgrades the lock to an RCsc lock. * * Since most load-store architectures implement ACQUIRE with an smp_mb() after * the LL/SC loop, they need no further barriers. Similarly all our TSO -- cgit v1.2.3 From 7696f9910a9a40b8a952f57d3428515fabd2d889 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Mon, 16 Jul 2018 11:06:03 -0700 Subject: sched/Documentation: Update wake_up() & co. memory-barrier guarantees Both the implementation and the users' expectation [1] for the various wakeup primitives have evolved over time, but the documentation has not kept up with these changes: brings it into 2018. [1] http://lkml.kernel.org/r/20180424091510.GB4064@hirez.programming.kicks-ass.net Also applied feedback from Alan Stern. Suggested-by: Peter Zijlstra Signed-off-by: Andrea Parri Signed-off-by: Paul E. McKenney Acked-by: Peter Zijlstra (Intel) Cc: Akira Yokosawa Cc: Alan Stern Cc: Boqun Feng Cc: Daniel Lustig Cc: David Howells Cc: Jade Alglave Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Luc Maranget Cc: Nicholas Piggin Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arch@vger.kernel.org Cc: parri.andrea@gmail.com Link: http://lkml.kernel.org/r/20180716180605.16115-12-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 43731fe51c97..05cd419f962d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -167,8 +167,8 @@ struct task_group; * need_sleep = false; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * - * Where wake_up_state() (and all other wakeup primitives) imply enough - * barriers to order the store of the variable against wakeup. + * where wake_up_state() executes a full memory barrier before accessing the + * task state. * * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a -- cgit v1.2.3 From c1a2f7f0c06454387c2cd7b93ff1491c715a8c69 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 16 Jul 2018 15:03:31 -0400 Subject: mm: Allocate the mm_cpumask (mm->cpu_bitmap[]) dynamically based on nr_cpu_ids The mm_struct always contains a cpumask bitmap, regardless of CONFIG_CPUMASK_OFFSTACK. That means the first step can be to simplify things, and simply have one bitmask at the end of the mm_struct for the mm_cpumask. This does necessitate moving everything else in mm_struct into an anonymous sub-structure, which can be randomized when struct randomization is enabled. The second step is to determine the correct size for the mm_struct slab object from the size of the mm_struct (excluding the CPU bitmap) and the size the cpumask. For init_mm we can simply allocate the maximum size this kernel is compiled for, since we only have one init_mm in the system, anyway. Pointer magic by Mike Galbraith, to evade -Wstringop-overflow getting confused by the dynamically sized array. Tested-by: Song Liu Signed-off-by: Rik van Riel Signed-off-by: Mike Galbraith Signed-off-by: Rik van Riel Acked-by: Dave Hansen Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kernel-team@fb.com Cc: luto@kernel.org Link: http://lkml.kernel.org/r/20180716190337.26133-2-riel@surriel.com Signed-off-by: Ingo Molnar --- include/linux/mm_types.h | 241 ++++++++++++++++++++++++----------------------- 1 file changed, 124 insertions(+), 117 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 99ce070e7dcb..efdc24dd9e97 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -335,176 +335,183 @@ struct core_state { struct kioctx_table; struct mm_struct { - struct vm_area_struct *mmap; /* list of VMAs */ - struct rb_root mm_rb; - u32 vmacache_seqnum; /* per-thread vmacache */ + struct { + struct vm_area_struct *mmap; /* list of VMAs */ + struct rb_root mm_rb; + u32 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU - unsigned long (*get_unmapped_area) (struct file *filp, + unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #endif - unsigned long mmap_base; /* base of mmap area */ - unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ + unsigned long mmap_base; /* base of mmap area */ + unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES - /* Base adresses for compatible mmap() */ - unsigned long mmap_compat_base; - unsigned long mmap_compat_legacy_base; + /* Base adresses for compatible mmap() */ + unsigned long mmap_compat_base; + unsigned long mmap_compat_legacy_base; #endif - unsigned long task_size; /* size of task vm space */ - unsigned long highest_vm_end; /* highest vma end address */ - pgd_t * pgd; - - /** - * @mm_users: The number of users including userspace. - * - * Use mmget()/mmget_not_zero()/mmput() to modify. When this drops - * to 0 (i.e. when the task exits and there are no other temporary - * reference holders), we also release a reference on @mm_count - * (which may then free the &struct mm_struct if @mm_count also - * drops to 0). - */ - atomic_t mm_users; - - /** - * @mm_count: The number of references to &struct mm_struct - * (@mm_users count as 1). - * - * Use mmgrab()/mmdrop() to modify. When this drops to 0, the - * &struct mm_struct is freed. - */ - atomic_t mm_count; + unsigned long task_size; /* size of task vm space */ + unsigned long highest_vm_end; /* highest vma end address */ + pgd_t * pgd; + + /** + * @mm_users: The number of users including userspace. + * + * Use mmget()/mmget_not_zero()/mmput() to modify. When this + * drops to 0 (i.e. when the task exits and there are no other + * temporary reference holders), we also release a reference on + * @mm_count (which may then free the &struct mm_struct if + * @mm_count also drops to 0). + */ + atomic_t mm_users; + + /** + * @mm_count: The number of references to &struct mm_struct + * (@mm_users count as 1). + * + * Use mmgrab()/mmdrop() to modify. When this drops to 0, the + * &struct mm_struct is freed. + */ + atomic_t mm_count; #ifdef CONFIG_MMU - atomic_long_t pgtables_bytes; /* PTE page table pages */ + atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif - int map_count; /* number of VMAs */ + int map_count; /* number of VMAs */ - spinlock_t page_table_lock; /* Protects page tables and some counters */ - struct rw_semaphore mmap_sem; + spinlock_t page_table_lock; /* Protects page tables and some + * counters + */ + struct rw_semaphore mmap_sem; - struct list_head mmlist; /* List of maybe swapped mm's. These are globally strung - * together off init_mm.mmlist, and are protected - * by mmlist_lock - */ + struct list_head mmlist; /* List of maybe swapped mm's. These + * are globally strung together off + * init_mm.mmlist, and are protected + * by mmlist_lock + */ - unsigned long hiwater_rss; /* High-watermark of RSS usage */ - unsigned long hiwater_vm; /* High-water virtual memory usage */ + unsigned long hiwater_rss; /* High-watermark of RSS usage */ + unsigned long hiwater_vm; /* High-water virtual memory usage */ - unsigned long total_vm; /* Total pages mapped */ - unsigned long locked_vm; /* Pages that have PG_mlocked set */ - unsigned long pinned_vm; /* Refcount permanently increased */ - unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ - unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ - unsigned long stack_vm; /* VM_STACK */ - unsigned long def_flags; + unsigned long total_vm; /* Total pages mapped */ + unsigned long locked_vm; /* Pages that have PG_mlocked set */ + unsigned long pinned_vm; /* Refcount permanently increased */ + unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ + unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ + unsigned long stack_vm; /* VM_STACK */ + unsigned long def_flags; - spinlock_t arg_lock; /* protect the below fields */ - unsigned long start_code, end_code, start_data, end_data; - unsigned long start_brk, brk, start_stack; - unsigned long arg_start, arg_end, env_start, env_end; + spinlock_t arg_lock; /* protect the below fields */ + unsigned long start_code, end_code, start_data, end_data; + unsigned long start_brk, brk, start_stack; + unsigned long arg_start, arg_end, env_start, env_end; - unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ + unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ - /* - * Special counters, in some configurations protected by the - * page_table_lock, in other configurations by being atomic. - */ - struct mm_rss_stat rss_stat; - - struct linux_binfmt *binfmt; + /* + * Special counters, in some configurations protected by the + * page_table_lock, in other configurations by being atomic. + */ + struct mm_rss_stat rss_stat; - cpumask_var_t cpu_vm_mask_var; + struct linux_binfmt *binfmt; - /* Architecture-specific MM context */ - mm_context_t context; + /* Architecture-specific MM context */ + mm_context_t context; - unsigned long flags; /* Must use atomic bitops to access the bits */ + unsigned long flags; /* Must use atomic bitops to access */ - struct core_state *core_state; /* coredumping support */ + struct core_state *core_state; /* coredumping support */ #ifdef CONFIG_MEMBARRIER - atomic_t membarrier_state; + atomic_t membarrier_state; #endif #ifdef CONFIG_AIO - spinlock_t ioctx_lock; - struct kioctx_table __rcu *ioctx_table; + spinlock_t ioctx_lock; + struct kioctx_table __rcu *ioctx_table; #endif #ifdef CONFIG_MEMCG - /* - * "owner" points to a task that is regarded as the canonical - * user/owner of this mm. All of the following must be true in - * order for it to be changed: - * - * current == mm->owner - * current->mm != mm - * new_owner->mm == mm - * new_owner->alloc_lock is held - */ - struct task_struct __rcu *owner; + /* + * "owner" points to a task that is regarded as the canonical + * user/owner of this mm. All of the following must be true in + * order for it to be changed: + * + * current == mm->owner + * current->mm != mm + * new_owner->mm == mm + * new_owner->alloc_lock is held + */ + struct task_struct __rcu *owner; #endif - struct user_namespace *user_ns; + struct user_namespace *user_ns; - /* store ref to file /proc//exe symlink points to */ - struct file __rcu *exe_file; + /* store ref to file /proc//exe symlink points to */ + struct file __rcu *exe_file; #ifdef CONFIG_MMU_NOTIFIER - struct mmu_notifier_mm *mmu_notifier_mm; + struct mmu_notifier_mm *mmu_notifier_mm; #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS - pgtable_t pmd_huge_pte; /* protected by page_table_lock */ -#endif -#ifdef CONFIG_CPUMASK_OFFSTACK - struct cpumask cpumask_allocation; + pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING - /* - * numa_next_scan is the next time that the PTEs will be marked - * pte_numa. NUMA hinting faults will gather statistics and migrate - * pages to new nodes if necessary. - */ - unsigned long numa_next_scan; + /* + * numa_next_scan is the next time that the PTEs will be marked + * pte_numa. NUMA hinting faults will gather statistics and + * migrate pages to new nodes if necessary. + */ + unsigned long numa_next_scan; - /* Restart point for scanning and setting pte_numa */ - unsigned long numa_scan_offset; + /* Restart point for scanning and setting pte_numa */ + unsigned long numa_scan_offset; - /* numa_scan_seq prevents two threads setting pte_numa */ - int numa_scan_seq; + /* numa_scan_seq prevents two threads setting pte_numa */ + int numa_scan_seq; #endif - /* - * An operation with batched TLB flushing is going on. Anything that - * can move process memory needs to flush the TLB when moving a - * PROT_NONE or PROT_NUMA mapped page. - */ - atomic_t tlb_flush_pending; + /* + * An operation with batched TLB flushing is going on. Anything + * that can move process memory needs to flush the TLB when + * moving a PROT_NONE or PROT_NUMA mapped page. + */ + atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH - /* See flush_tlb_batched_pending() */ - bool tlb_flush_batched; + /* See flush_tlb_batched_pending() */ + bool tlb_flush_batched; #endif - struct uprobes_state uprobes_state; + struct uprobes_state uprobes_state; #ifdef CONFIG_HUGETLB_PAGE - atomic_long_t hugetlb_usage; + atomic_long_t hugetlb_usage; #endif - struct work_struct async_put_work; + struct work_struct async_put_work; #if IS_ENABLED(CONFIG_HMM) - /* HMM needs to track a few things per mm */ - struct hmm *hmm; + /* HMM needs to track a few things per mm */ + struct hmm *hmm; #endif -} __randomize_layout; + } __randomize_layout; + + /* + * The mm_cpumask needs to be at the end of mm_struct, because it + * is dynamically sized based on nr_cpu_ids. + */ + unsigned long cpu_bitmap[]; +}; extern struct mm_struct init_mm; +/* Pointer magic because the dynamic array size confuses some compilers. */ static inline void mm_init_cpumask(struct mm_struct *mm) { -#ifdef CONFIG_CPUMASK_OFFSTACK - mm->cpu_vm_mask_var = &mm->cpumask_allocation; -#endif - cpumask_clear(mm->cpu_vm_mask_var); + unsigned long cpu_bitmap = (unsigned long)mm; + + cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap); + cpumask_clear((struct cpumask *)cpu_bitmap); } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { - return mm->cpu_vm_mask_var; + return (struct cpumask *)&mm->cpu_bitmap; } struct mmu_gather; -- cgit v1.2.3 From ffc59c496bf8498657321c59433f55bbcf2d9c38 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 10 Jul 2018 23:42:16 +0200 Subject: i2c: recovery: require either get_sda or set_sda For bus recovery, we either need to bail out early if we can read SDA or we need to send STOP after every pulse. Otherwise recovery might be misinterpreted as an unwanted write. So, require one of those SDA handling functions to avoid this problem. Signed-off-by: Wolfram Sang Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 24acd69c8874..4c4360f94786 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -581,12 +581,12 @@ struct i2c_timings { * recovery. Populated internally for generic GPIO recovery. * @set_scl: This sets/clears the SCL line. Mandatory for generic SCL recovery. * Populated internally for generic GPIO recovery. - * @get_sda: This gets current value of SDA line. Optional for generic SCL - * recovery. Populated internally, if sda_gpio is a valid GPIO, for generic - * GPIO recovery. - * @set_sda: This sets/clears the SDA line. Optional for generic SCL recovery. - * Populated internally, if sda_gpio is a valid GPIO, for generic GPIO - * recovery. + * @get_sda: This gets current value of SDA line. This or set_sda() is mandatory + * for generic SCL recovery. Populated internally, if sda_gpio is a valid + * GPIO, for generic GPIO recovery. + * @set_sda: This sets/clears the SDA line. This or get_sda() is mandatory for + * generic SCL recovery. Populated internally, if sda_gpio is a valid GPIO, + * for generic GPIO recovery. * @prepare_recovery: This will be called before starting recovery. Platform may * configure padmux here for SDA/SCL line or something else they want. * @unprepare_recovery: This will be called after completing recovery. Platform -- cgit v1.2.3 From 7ca5f6be7900ca753ed01c0202dc5f998a41f4ee Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 11 Jul 2018 00:24:22 +0200 Subject: i2c: recovery: add get_bus_free callback Some IP cores have an internal 'bus free' logic which may be more advanced than just checking if SDA is high. Add a separate callback to get this status. Filling it is optional. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 4c4360f94786..bc8d42f8544f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -587,6 +587,8 @@ struct i2c_timings { * @set_sda: This sets/clears the SDA line. This or get_sda() is mandatory for * generic SCL recovery. Populated internally, if sda_gpio is a valid GPIO, * for generic GPIO recovery. + * @get_bus_free: Returns the bus free state as seen from the IP core in case it + * has a more complex internal logic than just reading SDA. Optional. * @prepare_recovery: This will be called before starting recovery. Platform may * configure padmux here for SDA/SCL line or something else they want. * @unprepare_recovery: This will be called after completing recovery. Platform @@ -601,6 +603,7 @@ struct i2c_bus_recovery_info { void (*set_scl)(struct i2c_adapter *adap, int val); int (*get_sda)(struct i2c_adapter *adap); void (*set_sda)(struct i2c_adapter *adap, int val); + int (*get_bus_free)(struct i2c_adapter *adap); void (*prepare_recovery)(struct i2c_adapter *adap); void (*unprepare_recovery)(struct i2c_adapter *adap); -- cgit v1.2.3 From 4aaf448fa9754e2d5ee188d32327b24ffc15ca4d Mon Sep 17 00:00:00 2001 From: Jim Qu Date: Tue, 17 Jul 2018 16:20:50 +0800 Subject: vga_switcheroo: set audio client id according to bound GPU id On modern laptop, there are more and more platforms have two GPUs, and each of them maybe have audio codec for HDMP/DP output. For some dGPU which is no output, audio codec usually is disabled. In currect HDA audio driver, it will set all codec as VGA_SWITCHEROO_DIS, the audio which is binded to UMA will be suspended if user use debugfs to contorl power In HDA driver side, it is difficult to know which GPU the audio has binded to. So set the bound gpu pci dev to vga_switcheroo. if the audio client is not the third registration, audio id will set in vga_switcheroo enable function. if the audio client is the last registration when vga_switcheroo _ready() get true, we should get audio client id from bound GPU directly. Signed-off-by: Jim Qu Reviewed-by: Lukas Wunner Signed-off-by: Takashi Iwai --- include/linux/vga_switcheroo.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index 77f0f0af3a71..a34539b7f750 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -84,8 +84,8 @@ enum vga_switcheroo_state { * Client identifier. Audio clients use the same identifier & 0x100. */ enum vga_switcheroo_client_id { - VGA_SWITCHEROO_UNKNOWN_ID = -1, - VGA_SWITCHEROO_IGD, + VGA_SWITCHEROO_UNKNOWN_ID = 0x1000, + VGA_SWITCHEROO_IGD = 0, VGA_SWITCHEROO_DIS, VGA_SWITCHEROO_MAX_CLIENTS, }; @@ -151,7 +151,7 @@ int vga_switcheroo_register_client(struct pci_dev *dev, bool driver_power_control); int vga_switcheroo_register_audio_client(struct pci_dev *pdev, const struct vga_switcheroo_client_ops *ops, - enum vga_switcheroo_client_id id); + struct pci_dev *vga_dev); void vga_switcheroo_client_fb_set(struct pci_dev *dev, struct fb_info *info); @@ -180,7 +180,7 @@ static inline int vga_switcheroo_register_handler(const struct vga_switcheroo_ha enum vga_switcheroo_handler_flags_t handler_flags) { return 0; } static inline int vga_switcheroo_register_audio_client(struct pci_dev *pdev, const struct vga_switcheroo_client_ops *ops, - enum vga_switcheroo_client_id id) { return 0; } + struct pci_dev *vga_dev) { return 0; } static inline void vga_switcheroo_unregister_handler(void) {} static inline enum vga_switcheroo_handler_flags_t vga_switcheroo_handler_flags(void) { return 0; } static inline int vga_switcheroo_lock_ddc(struct pci_dev *pdev) { return -ENODEV; } -- cgit v1.2.3 From 5b56c182edb1224bc1a97a1c74003eaa0eb59daf Mon Sep 17 00:00:00 2001 From: Wenyou Yang Date: Tue, 17 Jul 2018 11:26:55 +0300 Subject: ARM: at91: pm: Add ULP1 mode support In the ULP1 mode, in order to achieve the lowest power consumption with the system in retention mode and be able to resume on the wake up events, all the clocks are shut off, inclusive the embedded 12MHz RC oscillator, and the number of wake up sources is limited as well. When the wake up event is asserted, the embedded 12MHz RC oscillator restarts automatically. The ULP1 (Ultra Low-power mode 1) is introduced by SAMA5D2. The previous size of pm_suspend.o was 2148 bytes. With the addition of ULP1 mode the new size of pm_suspend.o raised at 2456 bytes. Signed-off-by: Wenyou Yang Signed-off-by: Ludovic Desroches [claudiu.beznea@microchip.com: aligned with 4.18-rc1] Signed-off-by: Claudiu Beznea Signed-off-by: Alexandre Belloni --- include/linux/clk/at91_pmc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 6aca5ce8a99a..4ea2cbf9b50d 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -47,8 +47,10 @@ #define AT91_CKGR_MOR 0x20 /* Main Oscillator Register [not on SAM9RL] */ #define AT91_PMC_MOSCEN (1 << 0) /* Main Oscillator Enable */ #define AT91_PMC_OSCBYPASS (1 << 1) /* Oscillator Bypass */ +#define AT91_PMC_WAITMODE (1 << 2) /* Wait Mode Command */ #define AT91_PMC_MOSCRCEN (1 << 3) /* Main On-Chip RC Oscillator Enable [some SAM9] */ #define AT91_PMC_OSCOUNT (0xff << 8) /* Main Oscillator Start-up Time */ +#define AT91_PMC_KEY_MASK (0xff << 16) #define AT91_PMC_KEY (0x37 << 16) /* MOR Writing Key */ #define AT91_PMC_MOSCSEL (1 << 24) /* Main Oscillator Selection [some SAM9] */ #define AT91_PMC_CFDEN (1 << 25) /* Clock Failure Detector Enable [some SAM9] */ -- cgit v1.2.3 From 3abd729aa468d7346f12d7dfc8f81aba653f6c88 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 17 Jul 2018 11:26:56 +0300 Subject: ARM: at91: pm: add PMC fast startup registers defines Add PMC fast startup registers defines. Signed-off-by: Claudiu Beznea Signed-off-by: Alexandre Belloni --- include/linux/clk/at91_pmc.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 4ea2cbf9b50d..931ab05f771d 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -157,6 +157,19 @@ #define AT91_PMC_GCKRDY (1 << 24) /* Generated Clocks */ #define AT91_PMC_IMR 0x6c /* Interrupt Mask Register */ +#define AT91_PMC_FSMR 0x70 /* Fast Startup Mode Register */ +#define AT91_PMC_FSTT(n) BIT(n) +#define AT91_PMC_RTCAL BIT(17) /* RTC Alarm Enable */ +#define AT91_PMC_USBAL BIT(18) /* USB Resume Enable */ +#define AT91_PMC_SDMMC_CD BIT(19) /* SDMMC Card Detect Enable */ +#define AT91_PMC_LPM BIT(20) /* Low-power Mode */ +#define AT91_PMC_RXLP_MCE BIT(24) /* Backup UART Receive Enable */ +#define AT91_PMC_ACC_CE BIT(25) /* ACC Enable */ + +#define AT91_PMC_FSPR 0x74 /* Fast Startup Polarity Reg */ + +#define AT91_PMC_FS_INPUT_MASK 0x7ff + #define AT91_PMC_PLLICPR 0x80 /* PLL Charge Pump Current Register */ #define AT91_PMC_PROT 0xe4 /* Write Protect Mode Register [some SAM9] */ -- cgit v1.2.3 From ba6b055e0f3b4ff4942e4ab273260affcfad9bff Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 13 Jul 2018 16:13:49 +0200 Subject: HID: input: enable Totem on the Dell Canvas 27 The Dell Canvas 27 has a tool that can be put on the surface and acts as a dial. The firmware processes the detection of the tool and forward regular HID reports with X, Y, Azimuth, rotation, width/height. The firmware also exports Contact ID, Countact Count which may hint that several totems can be used at the same time (the FW only supports one). We can tell that MT_TOOL_DIAL will be reported by setting the min/max of ABS_MT_TOOL_TYPE to MT_TOOL_DIAL. This tool is aimed at being used by the system and not the applications, so the user space processing should not go through the regular touch inputs. We set INPUT_PROP_DIRECT which applies ID_INPUT_TOUCHSCREEN to this new type of devices, but we will counter this for the time being with the special udev hwdb entry mentioned above. Link: https://bugzilla.redhat.com/show_bug.cgi?id=1511846 Acked-by: Peter Hutterer Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 773bcb1d4044..2e4498d52a2f 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -190,6 +190,12 @@ struct hid_item { * http://www.usb.org/developers/hidpage/HUTRR40RadioHIDUsagesFinal.pdf */ #define HID_GD_WIRELESS_RADIO_CTLS 0x0001000c +/* + * System Multi-Axis, see: + * http://www.usb.org/developers/hidpage/HUTRR62_-_Generic_Desktop_CA_for_System_Multi-Axis_Controllers.txt + */ +#define HID_GD_SYSTEM_MULTIAXIS 0x0001000e + #define HID_GD_X 0x00010030 #define HID_GD_Y 0x00010031 #define HID_GD_Z 0x00010032 -- cgit v1.2.3 From 08a8a7cf14595f95d5cbb28ef5c15c56a6255fb4 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 13 Jul 2018 16:13:50 +0200 Subject: HID: core: do not upper bound the collection stack Looks like 4 was sufficient until now. However, the Surface Dial needs a stack of 5 and simply fails at probing. Dynamically add HID_COLLECTION_STACK_SIZE to the size of the stack if we hit the upper bound. Checkpatch complains about bare unsigned, so converting those to 'unsigned int' in struct hid_parser Acked-by: Peter Hutterer Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 2e4498d52a2f..aee281522c6d 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -644,12 +644,13 @@ static inline void hid_set_drvdata(struct hid_device *hdev, void *data) struct hid_parser { struct hid_global global; struct hid_global global_stack[HID_GLOBAL_STACK_SIZE]; - unsigned global_stack_ptr; + unsigned int global_stack_ptr; struct hid_local local; - unsigned collection_stack[HID_COLLECTION_STACK_SIZE]; - unsigned collection_stack_ptr; + unsigned int *collection_stack; + unsigned int collection_stack_ptr; + unsigned int collection_stack_size; struct hid_device *device; - unsigned scan_flags; + unsigned int scan_flags; }; struct hid_class_descriptor { -- cgit v1.2.3 From 9afb719e7046c4f2462278862ab3db2961cc141c Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Thu, 5 Jul 2018 17:49:37 -0700 Subject: kbuild: Add build salt to the kernel and modules In Fedora, the debug information is packaged separately (foo-debuginfo) and can be installed separately. There's been a long standing issue where only one version of a debuginfo info package can be installed at a time. There's been an effort for Fedora for parallel debuginfo to rectify this problem. Part of the requirement to allow parallel debuginfo to work is that build ids are unique between builds. The existing upstream rpm implementation ensures this by re-calculating the build-id using the version and release as a seed. This doesn't work 100% for the kernel because of the vDSO which is its own binary and doesn't get updated when embedded. Fix this by adding some data in an ELF note for both the kernel and modules. The data is controlled via a Kconfig option so distributions can set it to an appropriate value to ensure uniqueness between builds. Suggested-by: Masahiro Yamada Signed-off-by: Laura Abbott Signed-off-by: Masahiro Yamada --- include/linux/build-salt.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/linux/build-salt.h (limited to 'include/linux') diff --git a/include/linux/build-salt.h b/include/linux/build-salt.h new file mode 100644 index 000000000000..bb007bd05e7a --- /dev/null +++ b/include/linux/build-salt.h @@ -0,0 +1,20 @@ +#ifndef __BUILD_SALT_H +#define __BUILD_SALT_H + +#include + +#define LINUX_ELFNOTE_BUILD_SALT 0x100 + +#ifdef __ASSEMBLER__ + +#define BUILD_SALT \ + ELFNOTE(Linux, LINUX_ELFNOTE_BUILD_SALT, .asciz CONFIG_BUILD_SALT) + +#else + +#define BUILD_SALT \ + ELFNOTE32("Linux", LINUX_ELFNOTE_BUILD_SALT, CONFIG_BUILD_SALT) + +#endif + +#endif /* __BUILD_SALT_H */ -- cgit v1.2.3 From 2fe31e43124040a67495fa81f7ac67bc4c09ebc8 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 17 Jul 2018 21:48:10 +0200 Subject: hwmon: Add missing HWMON_T_LCRIT_ALARM define The enum hwmon_temp_lcrit_alarm exists, but the BIT definition is missing. Signed-off-by: Andrew Lunn Acked-by: Guenter Roeck Signed-off-by: David S. Miller --- include/linux/hwmon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index e5fd2707b6df..1b74ad11a5a4 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -93,6 +93,7 @@ enum hwmon_temp_attributes { #define HWMON_T_MIN_ALARM BIT(hwmon_temp_min_alarm) #define HWMON_T_MAX_ALARM BIT(hwmon_temp_max_alarm) #define HWMON_T_CRIT_ALARM BIT(hwmon_temp_crit_alarm) +#define HWMON_T_LCRIT_ALARM BIT(hwmon_temp_lcrit_alarm) #define HWMON_T_EMERGENCY_ALARM BIT(hwmon_temp_emergency_alarm) #define HWMON_T_FAULT BIT(hwmon_temp_fault) #define HWMON_T_OFFSET BIT(hwmon_temp_offset) -- cgit v1.2.3 From aa7f29b07c8702127124d0522e3cd46850cdbc41 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 17 Jul 2018 21:48:11 +0200 Subject: hwmon: Add support for power min, lcrit, min_alarm and lcrit_alarm Some sensors support reporting minimal and lower critical power, as well as alarms when these thresholds are reached. Add support for these attributes to the hwmon core. Signed-off-by: Andrew Lunn Acked-by: Guenter Roeck Signed-off-by: David S. Miller --- include/linux/hwmon.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 1b74ad11a5a4..b217101ca76e 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -188,12 +188,16 @@ enum hwmon_power_attributes { hwmon_power_cap_hyst, hwmon_power_cap_max, hwmon_power_cap_min, + hwmon_power_min, hwmon_power_max, hwmon_power_crit, + hwmon_power_lcrit, hwmon_power_label, hwmon_power_alarm, hwmon_power_cap_alarm, + hwmon_power_min_alarm, hwmon_power_max_alarm, + hwmon_power_lcrit_alarm, hwmon_power_crit_alarm, }; @@ -214,12 +218,16 @@ enum hwmon_power_attributes { #define HWMON_P_CAP_HYST BIT(hwmon_power_cap_hyst) #define HWMON_P_CAP_MAX BIT(hwmon_power_cap_max) #define HWMON_P_CAP_MIN BIT(hwmon_power_cap_min) +#define HWMON_P_MIN BIT(hwmon_power_min) #define HWMON_P_MAX BIT(hwmon_power_max) +#define HWMON_P_LCRIT BIT(hwmon_power_lcrit) #define HWMON_P_CRIT BIT(hwmon_power_crit) #define HWMON_P_LABEL BIT(hwmon_power_label) #define HWMON_P_ALARM BIT(hwmon_power_alarm) #define HWMON_P_CAP_ALARM BIT(hwmon_power_cap_alarm) +#define HWMON_P_MIN_ALARM BIT(hwmon_power_max_alarm) #define HWMON_P_MAX_ALARM BIT(hwmon_power_max_alarm) +#define HWMON_P_LCRIT_ALARM BIT(hwmon_power_lcrit_alarm) #define HWMON_P_CRIT_ALARM BIT(hwmon_power_crit_alarm) enum hwmon_energy_attributes { -- cgit v1.2.3 From dcb5d0fcaa1ddd0af9c18ef51e6b05e38a6cec71 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 17 Jul 2018 21:48:12 +0200 Subject: hwmon: Add helper to tell if a char is invalid in a name HWMON device names are not allowed to contain "-* \t\n". Add a helper which will return true if passed an invalid character. It can be used to massage a string into a hwmon compatible name by replacing invalid characters with '_'. Signed-off-by: Andrew Lunn Acked-by: Guenter Roeck Signed-off-by: David S. Miller --- include/linux/hwmon.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index b217101ca76e..9493d4a388db 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -398,4 +398,27 @@ devm_hwmon_device_register_with_info(struct device *dev, void hwmon_device_unregister(struct device *dev); void devm_hwmon_device_unregister(struct device *dev); +/** + * hwmon_is_bad_char - Is the char invalid in a hwmon name + * @ch: the char to be considered + * + * hwmon_is_bad_char() can be used to determine if the given character + * may not be used in a hwmon name. + * + * Returns true if the char is invalid, false otherwise. + */ +static inline bool hwmon_is_bad_char(const char ch) +{ + switch (ch) { + case '-': + case '*': + case ' ': + case '\t': + case '\n': + return true; + default: + return false; + } +} + #endif -- cgit v1.2.3 From 1323061a018a7514287894a552c4ec2a5f0cb0cd Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 17 Jul 2018 21:48:13 +0200 Subject: net: phy: sfp: Add HWMON support for module sensors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SFP modules can contain a number of sensors. The EEPROM also contains recommended alarm and critical values for each sensor, and indications of if these have been exceeded. Export this information via HWMON. Currently temperature, VCC, bias current, transmit power, and possibly receiver power is supported. The sensors in the modules can either return calibrate or uncalibrated values. Uncalibrated values need to be manipulated, using coefficients provided in the SFP EEPROM. Uncalibrated receive power values require floating point maths in order to calibrate them. Performing this in the kernel is hard. So if the SFP module indicates it uses uncalibrated values, RX power is not made available. With this hwmon device, it is possible to view the sensor values using lm-sensors programs: in0: +3.29 V (crit min = +2.90 V, min = +3.00 V) (max = +3.60 V, crit max = +3.70 V) temp1: +33.0°C (low = -5.0°C, high = +80.0°C) (crit low = -10.0°C, crit = +85.0°C) power1: 1000.00 nW (max = 794.00 uW, min = 50.00 uW) ALARM (LCRIT) (lcrit = 40.00 uW, crit = 1000.00 uW) curr1: +0.00 A (crit min = +0.00 A, min = +0.00 A) ALARM (LCRIT, MIN) (max = +0.01 A, crit max = +0.01 A) The scaling sensors performs on the bias current is not particularly good. The raw values are more useful: curr1: curr1_input: 0.000 curr1_min: 0.002 curr1_max: 0.010 curr1_lcrit: 0.000 curr1_crit: 0.011 curr1_min_alarm: 1.000 curr1_max_alarm: 0.000 curr1_lcrit_alarm: 1.000 curr1_crit_alarm: 0.000 In order to keep the I2C overhead to a minimum, the constant values, such as limits and calibration coefficients are read once at module insertion time. Thus only reading *_input and *_alarm properties requires i2c read operations. Signed-off-by: Andrew Lunn Acked-by: Guenter Roeck Signed-off-by: David S. Miller --- include/linux/sfp.h | 72 ++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 71 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index ebce9e24906a..d37518e89db2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -231,6 +231,50 @@ struct sfp_eeprom_id { struct sfp_eeprom_ext ext; } __packed; +struct sfp_diag { + __be16 temp_high_alarm; + __be16 temp_low_alarm; + __be16 temp_high_warn; + __be16 temp_low_warn; + __be16 volt_high_alarm; + __be16 volt_low_alarm; + __be16 volt_high_warn; + __be16 volt_low_warn; + __be16 bias_high_alarm; + __be16 bias_low_alarm; + __be16 bias_high_warn; + __be16 bias_low_warn; + __be16 txpwr_high_alarm; + __be16 txpwr_low_alarm; + __be16 txpwr_high_warn; + __be16 txpwr_low_warn; + __be16 rxpwr_high_alarm; + __be16 rxpwr_low_alarm; + __be16 rxpwr_high_warn; + __be16 rxpwr_low_warn; + __be16 laser_temp_high_alarm; + __be16 laser_temp_low_alarm; + __be16 laser_temp_high_warn; + __be16 laser_temp_low_warn; + __be16 tec_cur_high_alarm; + __be16 tec_cur_low_alarm; + __be16 tec_cur_high_warn; + __be16 tec_cur_low_warn; + __be32 cal_rxpwr4; + __be32 cal_rxpwr3; + __be32 cal_rxpwr2; + __be32 cal_rxpwr1; + __be32 cal_rxpwr0; + __be16 cal_txi_slope; + __be16 cal_txi_offset; + __be16 cal_txpwr_slope; + __be16 cal_txpwr_offset; + __be16 cal_t_slope; + __be16 cal_t_offset; + __be16 cal_v_slope; + __be16 cal_v_offset; +} __packed; + /* SFP EEPROM registers */ enum { SFP_PHYS_ID = 0x00, @@ -384,7 +428,33 @@ enum { SFP_TEC_CUR = 0x6c, SFP_STATUS = 0x6e, - SFP_ALARM = 0x70, + SFP_ALARM0 = 0x70, + SFP_ALARM0_TEMP_HIGH = BIT(7), + SFP_ALARM0_TEMP_LOW = BIT(6), + SFP_ALARM0_VCC_HIGH = BIT(5), + SFP_ALARM0_VCC_LOW = BIT(4), + SFP_ALARM0_TX_BIAS_HIGH = BIT(3), + SFP_ALARM0_TX_BIAS_LOW = BIT(2), + SFP_ALARM0_TXPWR_HIGH = BIT(1), + SFP_ALARM0_TXPWR_LOW = BIT(0), + + SFP_ALARM1 = 0x71, + SFP_ALARM1_RXPWR_HIGH = BIT(7), + SFP_ALARM1_RXPWR_LOW = BIT(6), + + SFP_WARN0 = 0x74, + SFP_WARN0_TEMP_HIGH = BIT(7), + SFP_WARN0_TEMP_LOW = BIT(6), + SFP_WARN0_VCC_HIGH = BIT(5), + SFP_WARN0_VCC_LOW = BIT(4), + SFP_WARN0_TX_BIAS_HIGH = BIT(3), + SFP_WARN0_TX_BIAS_LOW = BIT(2), + SFP_WARN0_TXPWR_HIGH = BIT(1), + SFP_WARN0_TXPWR_LOW = BIT(0), + + SFP_WARN1 = 0x75, + SFP_WARN1_RXPWR_HIGH = BIT(7), + SFP_WARN1_RXPWR_LOW = BIT(6), SFP_EXT_STATUS = 0x76, SFP_VSL = 0x78, -- cgit v1.2.3 From 753d433b586d1d43c487e3d660f5778c7c8d58ea Mon Sep 17 00:00:00 2001 From: "Tobin C. Harding" Date: Fri, 22 Jun 2018 09:15:32 +1000 Subject: random: Return nbytes filled from hw RNG Currently the function get_random_bytes_arch() has return value 'void'. If the hw RNG fails we currently fall back to using get_random_bytes(). This defeats the purpose of requesting random material from the hw RNG in the first place. There are currently no intree users of get_random_bytes_arch(). Only get random bytes from the hw RNG, make function return the number of bytes retrieved from the hw RNG. Acked-by: Theodore Ts'o Reviewed-by: Steven Rostedt (VMware) Signed-off-by: Tobin C. Harding Signed-off-by: Theodore Ts'o --- include/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index 2ddf13b4281e..f1c9bc5cd231 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -38,7 +38,7 @@ extern void get_random_bytes(void *buf, int nbytes); extern int wait_for_random_bytes(void); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); -extern void get_random_bytes_arch(void *buf, int nbytes); +extern int __must_check get_random_bytes_arch(void *buf, int nbytes); #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; -- cgit v1.2.3 From 9ba546c01976a426292af99e682a557075d6c010 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Jul 2018 15:48:46 +0200 Subject: aio: don't expose __aio_sigset in uapi glibc uses a different defintion of sigset_t than the kernel does, and the current version would pull in both. To fix this just do not expose the type at all - this somewhat mirrors pselect() where we do not even have a type for the magic sigmask argument, but just use pointer arithmetics. Fixes: 7a074e96 ("aio: implement io_pgetevents") Signed-off-by: Christoph Hellwig Reported-by: Adrian Reber Signed-off-by: Al Viro --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 73810808cdf2..b06b5eeda8e8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -11,6 +11,7 @@ #ifndef _LINUX_SYSCALLS_H #define _LINUX_SYSCALLS_H +struct __aio_sigset; struct epoll_event; struct iattr; struct inode; -- cgit v1.2.3 From 181ace9e1b2e1c5c2be590bc9603baa65f3a16d8 Mon Sep 17 00:00:00 2001 From: Abhishek Sahu Date: Wed, 20 Jun 2018 12:57:28 +0530 Subject: mtd: rawnand: helper function for setting up ECC configuration commit 2c8f8afa7f92 ("mtd: nand: add generic helpers to check, match, maximize ECC settings") provides generic helpers which drivers can use for setting up ECC parameters. Since same board can have different ECC strength nand chips so following is the logic for setting up ECC strength and ECC step size, which can be used by most of the drivers. 1. If both ECC step size and ECC strength are already set (usually by DT) then just check whether this setting is supported by NAND controller. 2. If NAND_ECC_MAXIMIZE is set, then select maximum ECC strength supported by NAND controller. 3. Otherwise, try to match the ECC step size and ECC strength closest to the chip's requirement. If available OOB size can't fit the chip requirement then select maximum ECC strength which can be fit with available OOB size. This patch introduces nand_ecc_choose_conf function which calls the required helper functions for the above logic. The drivers can use this single function instead of calling the 3 helper functions individually. Signed-off-by: Abhishek Sahu Reviewed-by: Masahiro Yamada Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index fbac4741da52..2ce305388471 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1672,6 +1672,9 @@ int nand_match_ecc_req(struct nand_chip *chip, int nand_maximize_ecc(struct nand_chip *chip, const struct nand_ecc_caps *caps, int oobavail); +int nand_ecc_choose_conf(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + /* Default write_oob implementation */ int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); -- cgit v1.2.3 From 0cf5c7dbaa392d11cfae532cedeaad0ac48b2165 Mon Sep 17 00:00:00 2001 From: Abhishek Sahu Date: Wed, 20 Jun 2018 12:57:42 +0530 Subject: mtd: rawnand: provide only single helper function for ECC conf Function nand_ecc_choose_conf() will be help for all the cases, so other helper functions can be made static. nand_check_ecc_caps(): Invoke nand_ecc_choose_conf() with both chip->ecc.size and chip->ecc.strength value set. nand_maximize_ecc(): Invoke nand_ecc_choose_conf() with NAND_ECC_MAXIMIZE flag. nand_match_ecc_req(): Invoke nand_ecc_choose_conf() with either chip->ecc.size or chip->ecc.strength value set and without NAND_ECC_MAXIMIZE flag. CC: Masahiro Yamada Signed-off-by: Abhishek Sahu Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 2ce305388471..0c6fb316b409 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1663,15 +1663,6 @@ int nand_check_erased_ecc_chunk(void *data, int datalen, void *extraoob, int extraooblen, int threshold); -int nand_check_ecc_caps(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail); - -int nand_match_ecc_req(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail); - -int nand_maximize_ecc(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail); - int nand_ecc_choose_conf(struct nand_chip *chip, const struct nand_ecc_caps *caps, int oobavail); -- cgit v1.2.3 From 7529df4652482c33ae1a99ee8189401146f13cb7 Mon Sep 17 00:00:00 2001 From: Peter Pan Date: Fri, 22 Jun 2018 14:28:23 +0200 Subject: mtd: nand: Add core infrastructure to support SPI NANDs Add a SPI NAND framework based on the generic NAND framework and the spi-mem infrastructure. In its current state, this framework supports the following features: - single/dual/quad IO modes - on-die ECC Signed-off-by: Peter Pan Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/spinand.h | 416 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/spi/spi-mem.h | 4 +- 2 files changed, 419 insertions(+), 1 deletion(-) create mode 100644 include/linux/mtd/spinand.h (limited to 'include/linux') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h new file mode 100644 index 000000000000..d3efe62dc9de --- /dev/null +++ b/include/linux/mtd/spinand.h @@ -0,0 +1,416 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2016-2017 Micron Technology, Inc. + * + * Authors: + * Peter Pan + */ +#ifndef __LINUX_MTD_SPINAND_H +#define __LINUX_MTD_SPINAND_H + +#include +#include +#include +#include +#include +#include +#include + +/** + * Standard SPI NAND flash operations + */ + +#define SPINAND_RESET_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xff, 1), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPINAND_WR_EN_DIS_OP(enable) \ + SPI_MEM_OP(SPI_MEM_OP_CMD((enable) ? 0x06 : 0x04, 1), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPINAND_READID_OP(ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x9f, 1), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 1)) + +#define SPINAND_SET_FEATURE_OP(reg, valptr) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x1f, 1), \ + SPI_MEM_OP_ADDR(1, reg, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(1, valptr, 1)) + +#define SPINAND_GET_FEATURE_OP(reg, valptr) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x0f, 1), \ + SPI_MEM_OP_ADDR(1, reg, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_IN(1, valptr, 1)) + +#define SPINAND_BLK_ERASE_OP(addr) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xd8, 1), \ + SPI_MEM_OP_ADDR(3, addr, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPINAND_PAGE_READ_OP(addr) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x13, 1), \ + SPI_MEM_OP_ADDR(3, addr, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPINAND_PAGE_READ_FROM_CACHE_OP(fast, addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 1)) + +#define SPINAND_PAGE_READ_FROM_CACHE_X2_OP(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 2)) + +#define SPINAND_PAGE_READ_FROM_CACHE_X4_OP(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 4)) + +#define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1), \ + SPI_MEM_OP_ADDR(2, addr, 2), \ + SPI_MEM_OP_DUMMY(ndummy, 2), \ + SPI_MEM_OP_DATA_IN(len, buf, 2)) + +#define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1), \ + SPI_MEM_OP_ADDR(2, addr, 4), \ + SPI_MEM_OP_DUMMY(ndummy, 4), \ + SPI_MEM_OP_DATA_IN(len, buf, 4)) + +#define SPINAND_PROG_EXEC_OP(addr) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x10, 1), \ + SPI_MEM_OP_ADDR(3, addr, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPINAND_PROG_LOAD(reset, addr, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x02 : 0x84, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(len, buf, 1)) + +#define SPINAND_PROG_LOAD_X4(reset, addr, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x32 : 0x34, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(len, buf, 4)) + +/** + * Standard SPI NAND flash commands + */ +#define SPINAND_CMD_PROG_LOAD_X4 0x32 +#define SPINAND_CMD_PROG_LOAD_RDM_DATA_X4 0x34 + +/* feature register */ +#define REG_BLOCK_LOCK 0xa0 +#define BL_ALL_UNLOCKED 0x00 + +/* configuration register */ +#define REG_CFG 0xb0 +#define CFG_OTP_ENABLE BIT(6) +#define CFG_ECC_ENABLE BIT(4) +#define CFG_QUAD_ENABLE BIT(0) + +/* status register */ +#define REG_STATUS 0xc0 +#define STATUS_BUSY BIT(0) +#define STATUS_ERASE_FAILED BIT(2) +#define STATUS_PROG_FAILED BIT(3) +#define STATUS_ECC_MASK GENMASK(5, 4) +#define STATUS_ECC_NO_BITFLIPS (0 << 4) +#define STATUS_ECC_HAS_BITFLIPS (1 << 4) +#define STATUS_ECC_UNCOR_ERROR (2 << 4) + +struct spinand_op; +struct spinand_device; + +#define SPINAND_MAX_ID_LEN 4 + +/** + * struct spinand_id - SPI NAND id structure + * @data: buffer containing the id bytes. Currently 4 bytes large, but can + * be extended if required + * @len: ID length + * + * struct_spinand_id->data contains all bytes returned after a READ_ID command, + * including dummy bytes if the chip does not emit ID bytes right after the + * READ_ID command. The responsibility to extract real ID bytes is left to + * struct_manufacurer_ops->detect(). + */ +struct spinand_id { + u8 data[SPINAND_MAX_ID_LEN]; + int len; +}; + +/** + * struct manufacurer_ops - SPI NAND manufacturer specific operations + * @detect: detect a SPI NAND device. Every time a SPI NAND device is probed + * the core calls the struct_manufacurer_ops->detect() hook of each + * registered manufacturer until one of them return 1. Note that + * the first thing to check in this hook is that the manufacturer ID + * in struct_spinand_device->id matches the manufacturer whose + * ->detect() hook has been called. Should return 1 if there's a + * match, 0 if the manufacturer ID does not match and a negative + * error code otherwise. When true is returned, the core assumes + * that properties of the NAND chip (spinand->base.memorg and + * spinand->base.eccreq) have been filled + * @init: initialize a SPI NAND device + * @cleanup: cleanup a SPI NAND device + * + * Each SPI NAND manufacturer driver should implement this interface so that + * NAND chips coming from this vendor can be detected and initialized properly. + */ +struct spinand_manufacturer_ops { + int (*detect)(struct spinand_device *spinand); + int (*init)(struct spinand_device *spinand); + void (*cleanup)(struct spinand_device *spinand); +}; + +/** + * struct spinand_manufacturer - SPI NAND manufacturer instance + * @id: manufacturer ID + * @name: manufacturer name + * @ops: manufacturer operations + */ +struct spinand_manufacturer { + u8 id; + char *name; + const struct spinand_manufacturer_ops *ops; +}; + +/** + * struct spinand_op_variants - SPI NAND operation variants + * @ops: the list of variants for a given operation + * @nops: the number of variants + * + * Some operations like read-from-cache/write-to-cache have several variants + * depending on the number of IO lines you use to transfer data or address + * cycles. This structure is a way to describe the different variants supported + * by a chip and let the core pick the best one based on the SPI mem controller + * capabilities. + */ +struct spinand_op_variants { + const struct spi_mem_op *ops; + unsigned int nops; +}; + +#define SPINAND_OP_VARIANTS(name, ...) \ + const struct spinand_op_variants name = { \ + .ops = (struct spi_mem_op[]) { __VA_ARGS__ }, \ + .nops = sizeof((struct spi_mem_op[]){ __VA_ARGS__ }) / \ + sizeof(struct spi_mem_op), \ + } + +/** + * spinand_ecc_info - description of the on-die ECC implemented by a SPI NAND + * chip + * @get_status: get the ECC status. Should return a positive number encoding + * the number of corrected bitflips if correction was possible or + * -EBADMSG if there are uncorrectable errors. I can also return + * other negative error codes if the error is not caused by + * uncorrectable bitflips + * @ooblayout: the OOB layout used by the on-die ECC implementation + */ +struct spinand_ecc_info { + int (*get_status)(struct spinand_device *spinand, u8 status); + const struct mtd_ooblayout_ops *ooblayout; +}; + +#define SPINAND_HAS_QE_BIT BIT(0) + +/** + * struct spinand_info - Structure used to describe SPI NAND chips + * @model: model name + * @devid: device ID + * @flags: OR-ing of the SPINAND_XXX flags + * @memorg: memory organization + * @eccreq: ECC requirements + * @eccinfo: on-die ECC info + * @op_variants: operations variants + * @op_variants.read_cache: variants of the read-cache operation + * @op_variants.write_cache: variants of the write-cache operation + * @op_variants.update_cache: variants of the update-cache operation + * @select_target: function used to select a target/die. Required only for + * multi-die chips + * + * Each SPI NAND manufacturer driver should have a spinand_info table + * describing all the chips supported by the driver. + */ +struct spinand_info { + const char *model; + u8 devid; + u32 flags; + struct nand_memory_organization memorg; + struct nand_ecc_req eccreq; + struct spinand_ecc_info eccinfo; + struct { + const struct spinand_op_variants *read_cache; + const struct spinand_op_variants *write_cache; + const struct spinand_op_variants *update_cache; + } op_variants; + int (*select_target)(struct spinand_device *spinand, + unsigned int target); +}; + +#define SPINAND_INFO_OP_VARIANTS(__read, __write, __update) \ + { \ + .read_cache = __read, \ + .write_cache = __write, \ + .update_cache = __update, \ + } + +#define SPINAND_ECCINFO(__ooblayout, __get_status) \ + .eccinfo = { \ + .ooblayout = __ooblayout, \ + .get_status = __get_status, \ + } + +#define SPINAND_SELECT_TARGET(__func) \ + .select_target = __func, + +#define SPINAND_INFO(__model, __id, __memorg, __eccreq, __op_variants, \ + __flags, ...) \ + { \ + .model = __model, \ + .devid = __id, \ + .memorg = __memorg, \ + .eccreq = __eccreq, \ + .op_variants = __op_variants, \ + .flags = __flags, \ + __VA_ARGS__ \ + } + +/** + * struct spinand_device - SPI NAND device instance + * @base: NAND device instance + * @spimem: pointer to the SPI mem object + * @lock: lock used to serialize accesses to the NAND + * @id: NAND ID as returned by READ_ID + * @flags: NAND flags + * @op_templates: various SPI mem op templates + * @op_templates.read_cache: read cache op template + * @op_templates.write_cache: write cache op template + * @op_templates.update_cache: update cache op template + * @select_target: select a specific target/die. Usually called before sending + * a command addressing a page or an eraseblock embedded in + * this die. Only required if your chip exposes several dies + * @cur_target: currently selected target/die + * @eccinfo: on-die ECC information + * @cfg_cache: config register cache. One entry per die + * @databuf: bounce buffer for data + * @oobbuf: bounce buffer for OOB data + * @scratchbuf: buffer used for everything but page accesses. This is needed + * because the spi-mem interface explicitly requests that buffers + * passed in spi_mem_op be DMA-able, so we can't based the bufs on + * the stack + * @manufacturer: SPI NAND manufacturer information + * @priv: manufacturer private data + */ +struct spinand_device { + struct nand_device base; + struct spi_mem *spimem; + struct mutex lock; + struct spinand_id id; + u32 flags; + + struct { + const struct spi_mem_op *read_cache; + const struct spi_mem_op *write_cache; + const struct spi_mem_op *update_cache; + } op_templates; + + int (*select_target)(struct spinand_device *spinand, + unsigned int target); + unsigned int cur_target; + + struct spinand_ecc_info eccinfo; + + u8 *cfg_cache; + u8 *databuf; + u8 *oobbuf; + u8 *scratchbuf; + const struct spinand_manufacturer *manufacturer; + void *priv; +}; + +/** + * mtd_to_spinand() - Get the SPI NAND device attached to an MTD instance + * @mtd: MTD instance + * + * Return: the SPI NAND device attached to @mtd. + */ +static inline struct spinand_device *mtd_to_spinand(struct mtd_info *mtd) +{ + return container_of(mtd_to_nanddev(mtd), struct spinand_device, base); +} + +/** + * spinand_to_mtd() - Get the MTD device embedded in a SPI NAND device + * @spinand: SPI NAND device + * + * Return: the MTD device embedded in @spinand. + */ +static inline struct mtd_info *spinand_to_mtd(struct spinand_device *spinand) +{ + return nanddev_to_mtd(&spinand->base); +} + +/** + * nand_to_spinand() - Get the SPI NAND device embedding an NAND object + * @nand: NAND object + * + * Return: the SPI NAND device embedding @nand. + */ +static inline struct spinand_device *nand_to_spinand(struct nand_device *nand) +{ + return container_of(nand, struct spinand_device, base); +} + +/** + * spinand_to_nand() - Get the NAND device embedded in a SPI NAND object + * @spinand: SPI NAND device + * + * Return: the NAND device embedded in @spinand. + */ +static inline struct nand_device * +spinand_to_nand(struct spinand_device *spinand) +{ + return &spinand->base; +} + +/** + * spinand_set_of_node - Attach a DT node to a SPI NAND device + * @spinand: SPI NAND device + * @np: DT node + * + * Attach a DT node to a SPI NAND device. + */ +static inline void spinand_set_of_node(struct spinand_device *spinand, + struct device_node *np) +{ + nanddev_set_of_node(&spinand->base, np); +} + +int spinand_match_and_init(struct spinand_device *dev, + const struct spinand_info *table, + unsigned int table_size, u8 devid); + +int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val); +int spinand_select_target(struct spinand_device *spinand, unsigned int target); + +#endif /* __LINUX_MTD_SPINAND_H */ diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index bb4bd15ae1f6..4fa34a227a0f 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -3,7 +3,9 @@ * Copyright (C) 2018 Exceet Electronics GmbH * Copyright (C) 2018 Bootlin * - * Author: Boris Brezillon + * Author: + * Peter Pan + * Boris Brezillon */ #ifndef __LINUX_SPI_MEM_H -- cgit v1.2.3 From a508e8875e135d7a1df26d8131b5443cb07005ff Mon Sep 17 00:00:00 2001 From: Peter Pan Date: Fri, 22 Jun 2018 14:28:25 +0200 Subject: mtd: spinand: Add initial support for Micron MT29F2G01ABAGD Add a basic driver for Micron SPI NANDs. Only one device is supported right now, but the driver will be extended to support more devices afterwards. Signed-off-by: Peter Pan Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/spinand.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index d3efe62dc9de..717b272940f1 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -193,6 +193,9 @@ struct spinand_manufacturer { const struct spinand_manufacturer_ops *ops; }; +/* SPI NAND manufacturers */ +extern const struct spinand_manufacturer micron_spinand_manufacturer; + /** * struct spinand_op_variants - SPI NAND operation variants * @ops: the list of variants for a given operation -- cgit v1.2.3 From 1075492bb9e26312bc8ddeec1a93e2de5f9c76b4 Mon Sep 17 00:00:00 2001 From: Frieder Schrempf Date: Fri, 22 Jun 2018 14:28:26 +0200 Subject: mtd: spinand: Add initial support for Winbond W25M02GV Add support for the W25M02GV chip. Signed-off-by: Frieder Schrempf Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/spinand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 717b272940f1..f0f16b9029e7 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -195,6 +195,7 @@ struct spinand_manufacturer { /* SPI NAND manufacturers */ extern const struct spinand_manufacturer micron_spinand_manufacturer; +extern const struct spinand_manufacturer winbond_spinand_manufacturer; /** * struct spinand_op_variants - SPI NAND operation variants -- cgit v1.2.3 From b02308af05e62c7d995f4fc75b0bc2ae3c3026f7 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 22 Jun 2018 14:28:27 +0200 Subject: mtd: spinand: Add initial support for the MX35LF1GE4AB chip Add minimal support for the MX35LF1GE4AB SPI NAND chip. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/spinand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index f0f16b9029e7..088ff96c3eb6 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -194,6 +194,7 @@ struct spinand_manufacturer { }; /* SPI NAND manufacturers */ +extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; extern const struct spinand_manufacturer winbond_spinand_manufacturer; -- cgit v1.2.3 From a4c025372d9d4756e7be98a98f5dde302c6df562 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:27 +0200 Subject: mtd: rawnand: Remove nand_do_read() prototype from rawnand.h nand_do_read() is a static function implemented in nand_base.c. There's no good reason to expose its prototype in rawnand.h. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 0c6fb316b409..4d7a46c42900 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1545,8 +1545,6 @@ int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs); int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt); int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr, int allowbbt); -int nand_do_read(struct mtd_info *mtd, loff_t from, size_t len, - size_t *retlen, uint8_t *buf); /** * struct platform_nand_chip - chip level device structure -- cgit v1.2.3 From 707329aca6e0cf5781ca7f62c39bdcb5f87e9c23 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:28 +0200 Subject: mtd: rawnand: Remove forward declaration of mtd_info struct mtd_info is defined in linux/mtd/mtd.h which is included at the beginning of nand_base.c, there's thus no need for the forward declaration of mtd_info. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 4d7a46c42900..32145b302585 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -23,7 +23,6 @@ #include #include -struct mtd_info; struct nand_flash_dev; struct device_node; -- cgit v1.2.3 From 1c3ab61ebcf8cfb5308d2e68e03fd4b4df484e62 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:29 +0200 Subject: mtd: rawnand: Remove forward declaration of device_node struct device_node is defined in linux/of.h. Let's include this file instead of having a forward declaration of this struct. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 32145b302585..83ab6779144e 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -21,10 +21,10 @@ #include #include #include +#include #include struct nand_flash_dev; -struct device_node; /* Scan and identify a NAND device */ int nand_scan_with_ids(struct mtd_info *mtd, int max_chips, -- cgit v1.2.3 From 44b07b921dea5ec997fb929ceaa82582a7415816 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:30 +0200 Subject: mtd: rawnand: Rename nand_default_bbt() into nand_create_bbt() Rename nand_default_bbt() into nand_create_bbt() and pass it a nand_chip object to prepare removal of the chip->scan_bbt() hook. We add a temporary nand_default_bbt() wrapper which will be dropped after the removal of ->scan_bbt(). Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 83ab6779144e..186f9fb1e7eb 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1538,7 +1538,7 @@ extern const struct nand_manufacturer_ops micron_nand_manuf_ops; extern const struct nand_manufacturer_ops amd_nand_manuf_ops; extern const struct nand_manufacturer_ops macronix_nand_manuf_ops; -int nand_default_bbt(struct mtd_info *mtd); +int nand_create_bbt(struct nand_chip *chip); int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs); int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs); int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt); -- cgit v1.2.3 From e80eba7581512625083ba540f120479b935425de Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:31 +0200 Subject: mtd: rawnand: Kill the chip->scan_bbt() hook None of the existing drivers are overloading the ->scan_bbt() method, let's get rid of it and replace calls to ->scan_bbt() by nand_create_bbt() ones. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 186f9fb1e7eb..ac0007ddadf2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1199,7 +1199,6 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @buf_align: minimum buffer alignment required by a platform * @hwcontrol: platform-specific hardware control structure * @erase: [REPLACEABLE] erase function - * @scan_bbt: [REPLACEABLE] function to scan bad block table * @chip_delay: [BOARDSPECIFIC] chip dependent delay for transferring * data from array to read regs (tR). * @state: [INTERN] the current state of the NAND device @@ -1292,7 +1291,6 @@ struct nand_chip { const struct nand_operation *op, bool check_only); int (*erase)(struct mtd_info *mtd, int page); - int (*scan_bbt)(struct mtd_info *mtd); int (*set_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*get_features)(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From f0f01838f76420988b50b23f315704c9a5cd2fa9 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:32 +0200 Subject: mtd: rawnand: orion_nand: Kill orion_nand_data.dev_ready() None of the boards seem to overload the ->dev_ready() hook, just drop this field from orion_nand_data. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/platform_data/mtd-orion_nand.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mtd-orion_nand.h b/include/linux/platform_data/mtd-orion_nand.h index a7ce77c7c1a8..34828eb85982 100644 --- a/include/linux/platform_data/mtd-orion_nand.h +++ b/include/linux/platform_data/mtd-orion_nand.h @@ -12,7 +12,6 @@ */ struct orion_nand_data { struct mtd_partition *parts; - int (*dev_ready)(struct mtd_info *mtd); u32 nr_parts; u8 ale; /* address line number connected to ALE */ u8 cle; /* address line number connected to CLE */ -- cgit v1.2.3 From dc2d8856a758627d4f126d17bc113eedd72b2d60 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:33 +0200 Subject: mtd: rawnand: plat_nand: Kill pdata->ctrl.{hwcontrol, read_byte}() None of the board files are overloading those hooks, so let's drop them from struct platform_nand_ctrl. Signed-off-by: Boris Brezillon Acked-by: Robert Jarzmik Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index ac0007ddadf2..11c2426fc363 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1572,14 +1572,12 @@ struct platform_device; * struct platform_nand_ctrl - controller level device structure * @probe: platform specific function to probe/setup hardware * @remove: platform specific function to remove/teardown hardware - * @hwcontrol: platform specific hardware control structure * @dev_ready: platform specific function to read ready/busy pin * @select_chip: platform specific chip select function * @cmd_ctrl: platform specific function for controlling * ALE/CLE/nCE. Also used to write command and address * @write_buf: platform specific function for write buffer * @read_buf: platform specific function for read buffer - * @read_byte: platform specific function to read one byte from chip * @priv: private data to transport driver specific settings * * All fields are optional and depend on the hardware driver requirements @@ -1587,13 +1585,11 @@ struct platform_device; struct platform_nand_ctrl { int (*probe)(struct platform_device *pdev); void (*remove)(struct platform_device *pdev); - void (*hwcontrol)(struct mtd_info *mtd, int cmd); int (*dev_ready)(struct mtd_info *mtd); void (*select_chip)(struct mtd_info *mtd, int chip); void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); - unsigned char (*read_byte)(struct mtd_info *mtd); void *priv; }; -- cgit v1.2.3 From dc2865ac3527d76fe04ee1f1a3ffc101a60faba0 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 9 Jul 2018 22:09:40 +0200 Subject: MIPS: txx9: Move the ndfc.h header to include/linux/platform_data/txx9 This way we will be able to compile the ndfmc driver when COMPILE_TEST=y. Signed-off-by: Boris Brezillon Acked-by: Paul Burton Signed-off-by: Miquel Raynal --- include/linux/platform_data/txx9/ndfmc.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) create mode 100644 include/linux/platform_data/txx9/ndfmc.h (limited to 'include/linux') diff --git a/include/linux/platform_data/txx9/ndfmc.h b/include/linux/platform_data/txx9/ndfmc.h new file mode 100644 index 000000000000..fc172627d54e --- /dev/null +++ b/include/linux/platform_data/txx9/ndfmc.h @@ -0,0 +1,30 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * (C) Copyright TOSHIBA CORPORATION 2007 + */ +#ifndef __TXX9_NDFMC_H +#define __TXX9_NDFMC_H + +#define NDFMC_PLAT_FLAG_USE_BSPRT 0x01 +#define NDFMC_PLAT_FLAG_NO_RSTR 0x02 +#define NDFMC_PLAT_FLAG_HOLDADD 0x04 +#define NDFMC_PLAT_FLAG_DUMMYWRITE 0x08 + +struct txx9ndfmc_platform_data { + unsigned int shift; + unsigned int gbus_clock; + unsigned int hold; /* hold time in nanosecond */ + unsigned int spw; /* strobe pulse width in nanosecond */ + unsigned int flags; + unsigned char ch_mask; /* available channel bitmask */ + unsigned char wp_mask; /* write-protect bitmask */ + unsigned char wide_mask; /* 16bit-nand bitmask */ +}; + +void txx9_ndfmc_init(unsigned long baseaddr, + const struct txx9ndfmc_platform_data *plat_data); + +#endif /* __TXX9_NDFMC_H */ -- cgit v1.2.3 From e65e3a50702f4e7a01c0b36ff08d6ed8dde7ee7b Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 9 Jul 2018 22:09:42 +0200 Subject: MIPS: jz4740: Move jz4740_nand.h header to include/linux/platform_data/jz4740 This way we will be able to compile the jz4740_nand driver when COMPILE_TEST=y. Signed-off-by: Boris Brezillon Acked-by: Paul Burton Signed-off-by: Miquel Raynal --- include/linux/platform_data/jz4740/jz4740_nand.h | 34 ++++++++++++++++++++++++ 1 file changed, 34 insertions(+) create mode 100644 include/linux/platform_data/jz4740/jz4740_nand.h (limited to 'include/linux') diff --git a/include/linux/platform_data/jz4740/jz4740_nand.h b/include/linux/platform_data/jz4740/jz4740_nand.h new file mode 100644 index 000000000000..bc571f6d5ced --- /dev/null +++ b/include/linux/platform_data/jz4740/jz4740_nand.h @@ -0,0 +1,34 @@ +/* + * Copyright (C) 2009-2010, Lars-Peter Clausen + * JZ4740 SoC NAND controller driver + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 675 Mass Ave, Cambridge, MA 02139, USA. + * + */ + +#ifndef __JZ4740_NAND_H__ +#define __JZ4740_NAND_H__ + +#include +#include + +#define JZ_NAND_NUM_BANKS 4 + +struct jz_nand_platform_data { + int num_partitions; + struct mtd_partition *partitions; + + unsigned char banks[JZ_NAND_NUM_BANKS]; + + void (*ident_callback)(struct platform_device *, struct mtd_info *, + struct mtd_partition **, int *num_partitions); +}; + +#endif -- cgit v1.2.3 From be2ab5b4d5c0bf041a34ec2e1397d50afbfb095e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 11 Jul 2018 13:45:12 +0200 Subject: netfilter: nf_tables: take module reference when starting a batch Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 3ecc3050be0e..4a520d3304a2 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -29,6 +29,7 @@ struct nfnetlink_subsystem { __u8 subsys_id; /* nfnetlink subsystem ID */ __u8 cb_count; /* number of callbacks */ const struct nfnl_callback *cb; /* callback for individual types */ + struct module *owner; int (*commit)(struct net *net, struct sk_buff *skb); int (*abort)(struct net *net, struct sk_buff *skb); void (*cleanup)(struct net *net); -- cgit v1.2.3 From e2861fa71641c6414831d628a1f4f793b6562580 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Fri, 8 Jun 2018 14:57:42 -0700 Subject: evm: Don't deadlock if a crypto algorithm is unavailable When EVM attempts to appraise a file signed with a crypto algorithm the kernel doesn't have support for, it will cause the kernel to trigger a module load. If the EVM policy includes appraisal of kernel modules this will in turn call back into EVM - since EVM is holding a lock until the crypto initialisation is complete, this triggers a deadlock. Add a CRYPTO_NOLOAD flag and skip module loading if it's set, and add that flag in the EVM case in order to fail gracefully with an error message instead of deadlocking. Signed-off-by: Matthew Garrett Acked-by: Herbert Xu Signed-off-by: Mimi Zohar --- include/linux/crypto.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 6eb06101089f..e8839d3a7559 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -112,6 +112,11 @@ */ #define CRYPTO_ALG_OPTIONAL_KEY 0x00004000 +/* + * Don't trigger module loading + */ +#define CRYPTO_NOLOAD 0x00008000 + /* * Transform masks and values (for crt_flags). */ -- cgit v1.2.3 From 6eb864c1d9dd1ef32b88e03c3f49d8be0dab7dcf Mon Sep 17 00:00:00 2001 From: Mikhail Kurinnoi Date: Wed, 27 Jun 2018 16:33:42 +0300 Subject: integrity: prevent deadlock during digsig verification. This patch aimed to prevent deadlock during digsig verification.The point of issue - user space utility modprobe and/or it's dependencies (ld-*.so, libz.so.*, libc-*.so and /lib/modules/ files) that could be used for kernel modules load during digsig verification and could be signed by digsig in the same time. First at all, look at crypto_alloc_tfm() work algorithm: crypto_alloc_tfm() will first attempt to locate an already loaded algorithm. If that fails and the kernel supports dynamically loadable modules, it will then attempt to load a module of the same name or alias. If that fails it will send a query to any loaded crypto manager to construct an algorithm on the fly. We have situation, when public_key_verify_signature() in case of RSA algorithm use alg_name to store internal information in order to construct an algorithm on the fly, but crypto_larval_lookup() will try to use alg_name in order to load kernel module with same name. 1) we can't do anything with crypto module work, since it designed to work exactly in this way; 2) we can't globally filter module requests for modprobe, since it designed to work with any requests. In this patch, I propose add an exception for "crypto-pkcs1pad(rsa,*)" module requests only in case of enabled integrity asymmetric keys support. Since we don't have any real "crypto-pkcs1pad(rsa,*)" kernel modules for sure, we are safe to fail such module request from crypto_larval_lookup(). In this way we prevent modprobe execution during digsig verification and avoid possible deadlock if modprobe and/or it's dependencies also signed with digsig. Requested "crypto-pkcs1pad(rsa,*)" kernel module name formed by: 1) "pkcs1pad(rsa,%s)" in public_key_verify_signature(); 2) "crypto-%s" / "crypto-%s-all" in crypto_larval_lookup(). "crypto-pkcs1pad(rsa," part of request is a constant and unique and could be used as filter. Signed-off-by: Mikhail Kurinnoi Signed-off-by: Mimi Zohar include/linux/integrity.h | 13 +++++++++++++ security/integrity/digsig_asymmetric.c | 23 +++++++++++++++++++++++ security/security.c | 7 ++++++- 3 files changed, 42 insertions(+), 1 deletion(-) --- include/linux/integrity.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/integrity.h b/include/linux/integrity.h index 858d3f4a2241..54c853ec2fd1 100644 --- a/include/linux/integrity.h +++ b/include/linux/integrity.h @@ -44,4 +44,17 @@ static inline void integrity_load_keys(void) } #endif /* CONFIG_INTEGRITY */ +#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS + +extern int integrity_kernel_module_request(char *kmod_name); + +#else + +static inline int integrity_kernel_module_request(char *kmod_name) +{ + return 0; +} + +#endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */ + #endif /* _LINUX_INTEGRITY_H */ -- cgit v1.2.3 From d29ab6e1fa21ebc2a8a771015dd9e0e5d4e28dc1 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 13 Jul 2018 12:41:10 -0700 Subject: bpf: bpf_prog_array_alloc() should return a generic non-rcu pointer Currently the return type of the bpf_prog_array_alloc() is struct bpf_prog_array __rcu *, which is not quite correct. Obviously, the returned pointer is a generic pointer, which is valid for an indefinite amount of time and it's not shared with anyone else, so there is no sense in marking it as __rcu. This change eliminate the following sparse warnings: kernel/bpf/core.c:1544:31: warning: incorrect type in return expression (different address spaces) kernel/bpf/core.c:1544:31: expected struct bpf_prog_array [noderef] * kernel/bpf/core.c:1544:31: got void * kernel/bpf/core.c:1548:17: warning: incorrect type in return expression (different address spaces) kernel/bpf/core.c:1548:17: expected struct bpf_prog_array [noderef] * kernel/bpf/core.c:1548:17: got struct bpf_prog_array * kernel/bpf/core.c:1681:15: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1681:15: expected struct bpf_prog_array *array kernel/bpf/core.c:1681:15: got struct bpf_prog_array [noderef] * Fixes: 324bda9e6c5a ("bpf: multi program support for cgroup+bpf") Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8827e797ff97..943fb08d8287 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -352,7 +352,7 @@ struct bpf_prog_array { struct bpf_prog *progs[0]; }; -struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); +struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); int bpf_prog_array_length(struct bpf_prog_array __rcu *progs); int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, -- cgit v1.2.3 From 09728266b6f99ab57cd4f84f3eead65b7b65dbf7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 17 Jul 2018 10:53:23 -0700 Subject: bpf: offload: rename bpf_offload_dev_match() to bpf_offload_prog_map_match() A set of new API functions exported for the drivers will soon use 'bpf_offload_dev_' as a prefix. Rename the bpf_offload_dev_match() which is internal to the core (used by the verifier) to avoid any confusion. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 943fb08d8287..9b010d9129f3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -648,7 +648,7 @@ int bpf_map_offload_delete_elem(struct bpf_map *map, void *key); int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key); -bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map); +bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); -- cgit v1.2.3 From 9fd7c5559165f4c679b40c5e6ad442955832dfad Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 17 Jul 2018 10:53:24 -0700 Subject: bpf: offload: aggregate offloads per-device Currently we have two lists of offloaded objects - programs and maps. Netdevice unregister notifier scans those lists to orphan objects associated with device being unregistered. This puts unnecessary (even if negligible) burden on all netdev unregister calls in BPF- -enabled kernel. The lists of objects may potentially get long making the linear scan even more problematic. There haven't been complaints about this mechanisms so far, but it is suboptimal. Instead of relying on notifiers, make the few BPF-capable drivers register explicitly for BPF offloads. The programs and maps will now be collected per-device not on a global list, and only scanned for removal when driver unregisters from BPF offloads. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9b010d9129f3..aa2e834a122b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -650,6 +650,9 @@ int bpf_map_offload_get_next_key(struct bpf_map *map, bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); +int bpf_offload_dev_netdev_register(struct net_device *netdev); +void bpf_offload_dev_netdev_unregister(struct net_device *netdev); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); -- cgit v1.2.3 From 602144c224604f1cbff02ee2d1cf46825269ecbd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 17 Jul 2018 10:53:25 -0700 Subject: bpf: offload: keep the offload state per-ASIC Create a higher-level entity to represent a device/ASIC to allow programs and maps to be shared between device ports. The extra work is required to make sure we don't destroy BPF objects as soon as the netdev for which they were loaded gets destroyed, as other ports may still be using them. When netdev goes away all of its BPF objects will be moved to other netdevs of the device, and only destroyed when last netdev is unregistered. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aa2e834a122b..913465e45062 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -85,6 +85,7 @@ struct bpf_map { char name[BPF_OBJ_NAME_LEN]; }; +struct bpf_offload_dev; struct bpf_offloaded_map; struct bpf_map_dev_ops { @@ -650,8 +651,12 @@ int bpf_map_offload_get_next_key(struct bpf_map *map, bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); -int bpf_offload_dev_netdev_register(struct net_device *netdev); -void bpf_offload_dev_netdev_unregister(struct net_device *netdev); +struct bpf_offload_dev *bpf_offload_dev_create(void); +void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); +int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, + struct net_device *netdev); +void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, + struct net_device *netdev); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); -- cgit v1.2.3 From fd4f227dea0f24d89f52f7c4eb3207f84ddcbcbd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 17 Jul 2018 10:53:26 -0700 Subject: bpf: offload: allow program and map sharing per-ASIC Allow programs and maps to be re-used across different netdevs, as long as they belong to the same struct bpf_offload_dev. Update the bpf_offload_prog_map_match() helper for the verifier and export a new helper for the drivers to use when checking programs at attachment time. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 913465e45062..5b5ad95cf339 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -657,6 +657,7 @@ int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); +bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); -- cgit v1.2.3 From d3b1084dfd629ef89bc1c4bab95e5cb87e7d08c2 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Jul 2018 15:44:40 +0200 Subject: vfs: make open_with_fake_path() not contribute to nr_files Stacking file operations in overlay will store an extra open file for each overlay file opened. The overhead is just that of "struct file" which is about 256bytes, because overlay already pins an extra dentry and inode when the file is open, which add up to a much larger overhead. For fear of breaking working setups, don't start accounting the extra file. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5ce2b413abc6..e1884840d556 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -156,6 +156,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)0x8000000) +/* File does not contribute to nr_files count */ +#define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) + /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector * that indicates that they should check the contents of the iovec are -- cgit v1.2.3 From 9df6702ad0e85901450fe48a7b5f0f8975353eeb Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Jul 2018 15:44:40 +0200 Subject: vfs: export vfs_ioctl() to modules This is needed by the stacked ioctl implementation in overlayfs. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e1884840d556..019817a083a0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1634,6 +1634,8 @@ int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); +extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); + /* * VFS file helper functions. */ -- cgit v1.2.3 From f182536684d876afaf4627c36a16c4e15ea8a2b8 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Jul 2018 15:44:40 +0200 Subject: vfs: export vfs_dedupe_file_range_one() to modules This is needed by the stacked dedupe implementation in overlayfs. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 019817a083a0..b67209948f1b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1829,6 +1829,10 @@ extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); +extern int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, + struct file *dst_file, loff_t dst_pos, + u64 len); + struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); -- cgit v1.2.3 From 88059de155d4db817a3a78ba899cb3b7f4de0fb0 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Jul 2018 15:44:43 +0200 Subject: Revert "ovl: fix relatime for directories" This reverts commit cd91304e7190b4c4802f8e413ab2214b233e0260. Overlayfs no longer relies on the vfs correct atime handling. Signed-off-by: Miklos Szeredi --- include/linux/dcache.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 66c6e17e61e5..ddae4103d324 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -564,9 +564,6 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) return upper; } -/* d_real() flags */ -#define D_REAL_UPPER 0x2 /* return upper dentry or NULL if non-upper */ - /** * d_real - Return the real dentry * @dentry: the dentry to query -- cgit v1.2.3 From c6718543463dbb78486ad259f884cb800df802b5 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Jul 2018 15:44:43 +0200 Subject: Revert "vfs: update ovl inode before relatime check" This reverts commit 598e3c8f72f5b77c84d2cb26cfd936ffb3cfdbaa. Overlayfs no longer relies on the vfs correct atime handling. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b67209948f1b..8f8c9ac1c9d5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2088,6 +2088,7 @@ enum file_time_flags { S_VERSION = 8, }; +extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); static inline void file_accessed(struct file *file) { -- cgit v1.2.3 From 4ab30319fd7c691a1b3165325c647a5cd6d282ac Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Jul 2018 15:44:43 +0200 Subject: Revert "vfs: add flags to d_real()" This reverts commit 495e642939114478a5237a7d91661ba93b76f15a. No user of "flags" argument of d_real() remain. Signed-off-by: Miklos Szeredi --- include/linux/dcache.h | 11 +++++------ include/linux/fs.h | 2 +- 2 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ddae4103d324..8fe4efa94af6 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -146,7 +146,7 @@ struct dentry_operations { struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, const struct inode *, - unsigned int, unsigned int); + unsigned int); } ____cacheline_aligned; /* @@ -568,8 +568,7 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) * d_real - Return the real dentry * @dentry: the dentry to query * @inode: inode to select the dentry from multiple layers (can be NULL) - * @open_flags: open flags to control copy-up behavior - * @flags: flags to control what is returned by this function + * @flags: open flags to control copy-up behavior * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. @@ -578,10 +577,10 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) */ static inline struct dentry *d_real(struct dentry *dentry, const struct inode *inode, - unsigned int open_flags, unsigned int flags) + unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) - return dentry->d_op->d_real(dentry, inode, open_flags, flags); + return dentry->d_op->d_real(dentry, inode, flags); else return dentry; } @@ -596,7 +595,7 @@ static inline struct dentry *d_real(struct dentry *dentry, static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ - return d_backing_inode(d_real((struct dentry *) dentry, NULL, 0, 0)); + return d_backing_inode(d_real((struct dentry *) dentry, NULL, 0)); } struct name_snapshot { diff --git a/include/linux/fs.h b/include/linux/fs.h index 8f8c9ac1c9d5..16e2741cec3c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1249,7 +1249,7 @@ static inline struct inode *file_inode(const struct file *f) static inline struct dentry *file_dentry(const struct file *file) { - return d_real(file->f_path.dentry, file_inode(file), 0, 0); + return d_real(file->f_path.dentry, file_inode(file), 0); } static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) -- cgit v1.2.3 From de2a4a501e716bbf5ff691ba16faf59a35320228 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Jul 2018 15:44:43 +0200 Subject: Partially revert "locks: fix file locking on overlayfs" This partially reverts commit c568d68341be7030f5647def68851e469b21ca11. Overlayfs files will now automatically get the correct locks, no need to hack overlay support in VFS. It is a partial revert, because it leaves the locks_inode() calls in place and defines locks_inode() to file_inode(). We could revert those as well, but it would be unnecessary code churn and it makes sense to document that we are getting the inode for locking purposes. Don't revert MS_NOREMOTELOCK yet since that has been part of the userspace API for some time (though not in a useful way). Will try to remove internal flags later when the dust around the new mount API settles. Signed-off-by: Miklos Szeredi Acked-by: Jeff Layton --- include/linux/fs.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 16e2741cec3c..1cbcf37c45e1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1054,17 +1054,7 @@ struct file_lock_context { extern void send_sigio(struct fown_struct *fown, int fd, int band); -/* - * Return the inode to use for locking - * - * For overlayfs this should be the overlay inode, not the real inode returned - * by file_inode(). For any other fs file_inode(filp) and locks_inode(filp) are - * equal. - */ -static inline struct inode *locks_inode(const struct file *f) -{ - return f->f_path.dentry->d_inode; -} +#define locks_inode(f) file_inode(f) #ifdef CONFIG_FILE_LOCKING extern int fcntl_getlk(struct file *, unsigned int, struct flock *); @@ -1305,7 +1295,6 @@ extern int send_sigurg(struct fown_struct *fown); /* These sb flags are internal to the kernel */ #define SB_SUBMOUNT (1<<26) -#define SB_NOREMOTELOCK (1<<27) #define SB_NOSEC (1<<28) #define SB_BORN (1<<29) #define SB_ACTIVE (1<<30) -- cgit v1.2.3 From 573e1784817ca1f13d76a0df636929e983e5de3c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Jul 2018 15:44:44 +0200 Subject: Revert "fsnotify: support overlayfs" This reverts commit f3fbbb079263bd29ae592478de6808db7e708267. Overlayfs now works correctly without adding hacks to fsnotify. Signed-off-by: Miklos Szeredi --- include/linux/fsnotify.h | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index bdaf22582f6e..fd1ce10553bf 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -30,11 +30,7 @@ static inline int fsnotify_parent(const struct path *path, struct dentry *dentry static inline int fsnotify_perm(struct file *file, int mask) { const struct path *path = &file->f_path; - /* - * Do not use file_inode() here or anywhere in this file to get the - * inode. That would break *notity on overlayfs. - */ - struct inode *inode = path->dentry->d_inode; + struct inode *inode = file_inode(file); __u32 fsnotify_mask = 0; int ret; @@ -178,7 +174,7 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) static inline void fsnotify_access(struct file *file) { const struct path *path = &file->f_path; - struct inode *inode = path->dentry->d_inode; + struct inode *inode = file_inode(file); __u32 mask = FS_ACCESS; if (S_ISDIR(inode->i_mode)) @@ -196,7 +192,7 @@ static inline void fsnotify_access(struct file *file) static inline void fsnotify_modify(struct file *file) { const struct path *path = &file->f_path; - struct inode *inode = path->dentry->d_inode; + struct inode *inode = file_inode(file); __u32 mask = FS_MODIFY; if (S_ISDIR(inode->i_mode)) @@ -214,7 +210,7 @@ static inline void fsnotify_modify(struct file *file) static inline void fsnotify_open(struct file *file) { const struct path *path = &file->f_path; - struct inode *inode = path->dentry->d_inode; + struct inode *inode = file_inode(file); __u32 mask = FS_OPEN; if (S_ISDIR(inode->i_mode)) @@ -230,7 +226,7 @@ static inline void fsnotify_open(struct file *file) static inline void fsnotify_close(struct file *file) { const struct path *path = &file->f_path; - struct inode *inode = path->dentry->d_inode; + struct inode *inode = file_inode(file); fmode_t mode = file->f_mode; __u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; -- cgit v1.2.3 From fb16043b46831a75c9b076a7262ae035290b0409 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Jul 2018 15:44:44 +0200 Subject: vfs: remove open_flags from d_real() Opening regular files on overlayfs is now handled via ovl_open(). Remove the now unused "open_flags" argument from d_op->d_real() and the d_real() helper. Signed-off-by: Miklos Szeredi --- include/linux/dcache.h | 11 ++++------- include/linux/fs.h | 2 +- 2 files changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 8fe4efa94af6..78cea80423a3 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -145,8 +145,7 @@ struct dentry_operations { char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); - struct dentry *(*d_real)(struct dentry *, const struct inode *, - unsigned int); + struct dentry *(*d_real)(struct dentry *, const struct inode *); } ____cacheline_aligned; /* @@ -568,7 +567,6 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) * d_real - Return the real dentry * @dentry: the dentry to query * @inode: inode to select the dentry from multiple layers (can be NULL) - * @flags: open flags to control copy-up behavior * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. @@ -576,11 +574,10 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) * See also: Documentation/filesystems/vfs.txt */ static inline struct dentry *d_real(struct dentry *dentry, - const struct inode *inode, - unsigned int flags) + const struct inode *inode) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) - return dentry->d_op->d_real(dentry, inode, flags); + return dentry->d_op->d_real(dentry, inode); else return dentry; } @@ -595,7 +592,7 @@ static inline struct dentry *d_real(struct dentry *dentry, static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ - return d_backing_inode(d_real((struct dentry *) dentry, NULL, 0)); + return d_backing_inode(d_real((struct dentry *) dentry, NULL)); } struct name_snapshot { diff --git a/include/linux/fs.h b/include/linux/fs.h index 1cbcf37c45e1..1fa63d184d1f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1239,7 +1239,7 @@ static inline struct inode *file_inode(const struct file *f) static inline struct dentry *file_dentry(const struct file *file) { - return d_real(file->f_path.dentry, file_inode(file), 0); + return d_real(file->f_path.dentry, file_inode(file)); } static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) -- cgit v1.2.3 From 3f289dcb4b265416a57ca79cf4a324060bb09060 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 18 Jul 2018 04:47:36 -0700 Subject: block: make bdev_ops->rw_page() take a REQ_OP instead of bool c11f0c0b5bb9 ("block/mm: make bdev_ops->rw_page() take a bool for read/write") replaced @op with boolean @is_write, which limited the amount of information going into ->rw_page() and more importantly page_endio(), which removed the need to expose block internals to mm. Unfortunately, we want to track discards separately and @is_write isn't enough information. This patch updates bdev_ops->rw_page() to take REQ_OP instead but leaves page_endio() to take bool @is_write. This allows the block part of operations to have enough information while not leaking it to mm. Signed-off-by: Tejun Heo Cc: Mike Christie Cc: Minchan Kim Cc: Dan Williams Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1939ed95f936..331a6cb8805f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1943,7 +1943,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req, struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); - int (*rw_page)(struct block_device *, sector_t, struct page *, bool); + int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, -- cgit v1.2.3 From 59767fbd49d794b4499d30b314df6c0d4aca584b Mon Sep 17 00:00:00 2001 From: Michael Callahan Date: Wed, 18 Jul 2018 04:47:37 -0700 Subject: block: Add part_stat_read_accum to read across field entries. Add a part_stat_read_accum macro to genhd.h to read and sum across field entries. For example to sum up the number read and write sectors completed. In addition to being ar reasonable cleanup by itself this will make it easier to add new stat fields in the future. tj: Refreshed on top of v4.17. Signed-off-by: Michael Callahan Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6cb8a5789668..19f36fa10995 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -353,6 +353,10 @@ static inline void free_part_stats(struct hd_struct *part) #endif /* CONFIG_SMP */ +#define part_stat_read_accum(part, field) \ + (part_stat_read(part, field[0]) + \ + part_stat_read(part, field[1])) + #define part_stat_add(cpu, part, field, addnd) do { \ __part_stat_add((cpu), (part), field, addnd); \ if ((part)->partno) \ -- cgit v1.2.3 From dbae2c551377b6533a00c11fc7ede370100ab404 Mon Sep 17 00:00:00 2001 From: Michael Callahan Date: Wed, 18 Jul 2018 04:47:38 -0700 Subject: block: Define and use STAT_READ and STAT_WRITE Add defines for STAT_READ and STAT_WRITE for indexing the partition stat entries. This clarifies some fs/ code which has hardcoded 1 for STAT_WRITE and will make it easier to extend the stats with additional fields. tj: Refreshed on top of v4.17. Signed-off-by: Michael Callahan Signed-off-by: Tejun Heo Cc: "Theodore Ts'o" Cc: Jaegeuk Kim Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 7 +++++++ include/linux/genhd.h | 13 +++++++------ 2 files changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index e13449a379a1..d2b44de56bc1 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -357,6 +357,13 @@ enum req_flag_bits { #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA) +enum stat_group { + STAT_READ, + STAT_WRITE, + + NR_STAT_GROUPS +}; + #define bio_op(bio) \ ((bio)->bi_opf & REQ_OP_MASK) #define req_op(req) \ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 19f36fa10995..a75445446974 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -16,6 +16,7 @@ #include #include #include +#include #ifdef CONFIG_BLOCK @@ -82,10 +83,10 @@ struct partition { } __attribute__((packed)); struct disk_stats { - unsigned long sectors[2]; /* READs and WRITEs */ - unsigned long ios[2]; - unsigned long merges[2]; - unsigned long ticks[2]; + unsigned long sectors[NR_STAT_GROUPS]; + unsigned long ios[NR_STAT_GROUPS]; + unsigned long merges[NR_STAT_GROUPS]; + unsigned long ticks[NR_STAT_GROUPS]; unsigned long io_ticks; unsigned long time_in_queue; }; @@ -354,8 +355,8 @@ static inline void free_part_stats(struct hd_struct *part) #endif /* CONFIG_SMP */ #define part_stat_read_accum(part, field) \ - (part_stat_read(part, field[0]) + \ - part_stat_read(part, field[1])) + (part_stat_read(part, field[STAT_READ]) + \ + part_stat_read(part, field[STAT_WRITE])) #define part_stat_add(cpu, part, field, addnd) do { \ __part_stat_add((cpu), (part), field, addnd); \ -- cgit v1.2.3 From ddcf35d397976421a4ec1d0d00fbcc027a8cb034 Mon Sep 17 00:00:00 2001 From: Michael Callahan Date: Wed, 18 Jul 2018 04:47:39 -0700 Subject: block: Add and use op_stat_group() for indexing disk_stat fields. Add and use a new op_stat_group() function for indexing partition stat fields rather than indexing them by rq_data_dir() or bio_data_dir(). This function works similarly to op_is_sync() in that it takes the request::cmd_flags or bio::bi_opf flags and determines which stats should et updated. In addition, the second parameter to generic_start_io_acct() and generic_end_io_acct() is now a REQ_OP rather than simply a read or write bit and it uses op_stat_group() on the parameter to determine the stat group. Note that the partition in_flight counts are not part of the per-cpu statistics and as such are not indexed via this function. It's now indexed by op_is_write(). tj: Refreshed on top of v4.17. Updated to pass around REQ_OP. Signed-off-by: Michael Callahan Signed-off-by: Tejun Heo Cc: Minchan Kim Cc: Dan Williams Cc: Joshua Morris Cc: Philipp Reisner Cc: Matias Bjorling Cc: Kent Overstreet Cc: Alasdair Kergon Signed-off-by: Jens Axboe --- include/linux/bio.h | 4 ++-- include/linux/blk_types.h | 5 +++++ 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index a00dfff51aa5..ab221c517f4e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -496,9 +496,9 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int, extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); -void generic_start_io_acct(struct request_queue *q, int rw, +void generic_start_io_acct(struct request_queue *q, int op, unsigned long sectors, struct hd_struct *part); -void generic_end_io_acct(struct request_queue *q, int rw, +void generic_end_io_acct(struct request_queue *q, int op, struct hd_struct *part, unsigned long start_time); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d2b44de56bc1..2960a96d833c 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -401,6 +401,11 @@ static inline bool op_is_sync(unsigned int op) (op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH)); } +static inline int op_stat_group(unsigned int op) +{ + return op_is_write(op); +} + typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U #define BLK_QC_T_SHIFT 16 -- cgit v1.2.3 From bdca3c87fb7ad1cc61d231d37eb0d8f90d001e0c Mon Sep 17 00:00:00 2001 From: Michael Callahan Date: Wed, 18 Jul 2018 04:47:40 -0700 Subject: block: Track DISCARD statistics and output them in stat and diskstat Add tracking of REQ_OP_DISCARD ios to the partition statistics and append them to the various stat files in /sys as well as /proc/diskstats. These are tracked with the same four stats as reads and writes: Number of discard ios completed. Number of discard ios merged Number of discard sectors completed Milliseconds spent on discard requests This is done via adding a new STAT_DISCARD define to genhd.h and then using it to index that stat field for discard requests. tj: Refreshed on top of v4.17 and other previous updates. Signed-off-by: Michael Callahan Signed-off-by: Tejun Heo Cc: Andy Newell Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 8 ++++++++ include/linux/genhd.h | 3 ++- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 2960a96d833c..f6dfb30737d8 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -360,6 +360,7 @@ enum req_flag_bits { enum stat_group { STAT_READ, STAT_WRITE, + STAT_DISCARD, NR_STAT_GROUPS }; @@ -401,8 +402,15 @@ static inline bool op_is_sync(unsigned int op) (op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH)); } +static inline bool op_is_discard(unsigned int op) +{ + return (op & REQ_OP_MASK) == REQ_OP_DISCARD; +} + static inline int op_stat_group(unsigned int op) { + if (op_is_discard(op)) + return STAT_DISCARD; return op_is_write(op); } diff --git a/include/linux/genhd.h b/include/linux/genhd.h index a75445446974..57864422a2c8 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -356,7 +356,8 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_read_accum(part, field) \ (part_stat_read(part, field[STAT_READ]) + \ - part_stat_read(part, field[STAT_WRITE])) + part_stat_read(part, field[STAT_WRITE]) + \ + part_stat_read(part, field[STAT_DISCARD])) #define part_stat_add(cpu, part, field, addnd) do { \ __part_stat_add((cpu), (part), field, addnd); \ -- cgit v1.2.3 From 636620b66d5d4012c4a9c86206013964d3986c4f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 18 Jul 2018 04:47:41 -0700 Subject: blkcg: Track DISCARD statistics and output them in cgroup io.stat Add tracking of REQ_OP_DISCARD ios to the per-cgroup io.stat. Two fields, dbytes and dios, to respectively count the total bytes and number of discards are added. Signed-off-by: Tejun Heo Cc: Andy Newell Cc: Michael Callahan Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index de57de4831d5..3bed5e02a873 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -35,6 +35,7 @@ enum blkg_rwstat_type { BLKG_RWSTAT_WRITE, BLKG_RWSTAT_SYNC, BLKG_RWSTAT_ASYNC, + BLKG_RWSTAT_DISCARD, BLKG_RWSTAT_NR, BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, @@ -649,7 +650,9 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, { struct percpu_counter *cnt; - if (op_is_write(op)) + if (op_is_discard(op)) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD]; + else if (op_is_write(op)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; -- cgit v1.2.3 From bcf7eac3d97f49d8400ba52c71bee5934bf20093 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 17 Jul 2018 00:47:48 +0900 Subject: regmap: add SCCB support This adds Serial Camera Control Bus (SCCB) support for regmap API that is intended to be used by some of Omnivision sensor drivers. The ov772x and ov9650 drivers are going to use this SCCB regmap API. The ov772x driver was previously only worked with the i2c controller drivers that support I2C_FUNC_PROTOCOL_MANGLING, because the ov772x device doesn't support repeated starts. After commit 0b964d183cbf ("media: ov772x: allow i2c controllers without I2C_FUNC_PROTOCOL_MANGLING"), reading ov772x register is replaced with issuing two separated i2c messages in order to avoid repeated start. Using this SCCB regmap hides the implementation detail. The ov9650 driver also issues two separated i2c messages to read the registers as the device doesn't support repeated start. So it can make use of this SCCB regmap. Cc: Mark Brown Cc: Peter Rosin Cc: Sebastian Reichel Cc: Wolfram Sang Cc: Sylwester Nawrocki Cc: Jacopo Mondi Cc: Laurent Pinchart Cc: Hans Verkuil Cc: Sakari Ailus Cc: Mauro Carvalho Chehab Signed-off-by: Akinobu Mita Signed-off-by: Mark Brown --- include/linux/regmap.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4f38068ffb71..52bf358e2c73 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -514,6 +514,10 @@ struct regmap *__regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__regmap_init_sccb(struct i2c_client *i2c, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); struct regmap *__regmap_init_slimbus(struct slim_device *slimbus, const struct regmap_config *config, struct lock_class_key *lock_key, @@ -558,6 +562,10 @@ struct regmap *__devm_regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__devm_regmap_init_sccb(struct i2c_client *i2c, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); struct regmap *__devm_regmap_init_spi(struct spi_device *dev, const struct regmap_config *config, struct lock_class_key *lock_key, @@ -645,6 +653,19 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, __regmap_lockdep_wrapper(__regmap_init_i2c, #config, \ i2c, config) +/** + * regmap_init_sccb() - Initialise register map + * + * @i2c: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_sccb(i2c, config) \ + __regmap_lockdep_wrapper(__regmap_init_sccb, #config, \ + i2c, config) + /** * regmap_init_slimbus() - Initialise register map * @@ -797,6 +818,20 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); __regmap_lockdep_wrapper(__devm_regmap_init_i2c, #config, \ i2c, config) +/** + * devm_regmap_init_sccb() - Initialise managed register map + * + * @i2c: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_sccb(i2c, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_sccb, #config, \ + i2c, config) + /** * devm_regmap_init_spi() - Initialise register map * -- cgit v1.2.3 From 7c201ead1bfd19935f689fca69100c335028c047 Mon Sep 17 00:00:00 2001 From: David Lechner Date: Mon, 16 Jul 2018 22:20:49 -0500 Subject: spi: spi-bitbang: change flags from u8 to u16 This changes the data type of the flags field in struct spi_bitbang from u8 to u16. This matches the size of the mode field of struct spi_device where these flags are also used. This is done in preparation of adding a new SPI mode flag that will be used with this field that would otherwise not fit in 8 bits. Signed-off-by: David Lechner Signed-off-by: Mark Brown --- include/linux/spi/spi_bitbang.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index 51d8c060e513..c1e61641a7f1 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -8,7 +8,7 @@ struct spi_bitbang { struct mutex lock; u8 busy; u8 use_dma; - u8 flags; /* extra spi->mode support */ + u16 flags; /* extra spi->mode support */ struct spi_master *master; -- cgit v1.2.3 From a5fb9fb023a1435f2b42bccd7f547560f3a21dc3 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Wed, 18 Jul 2018 15:40:26 -0500 Subject: PCI: OF: Fix I/O space page leak When testing the R-Car PCIe driver on the Condor board, if the PCIe PHY driver was left disabled, the kernel crashed with this BUG: kernel BUG at lib/ioremap.c:72! Internal error: Oops - BUG: 0 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 39 Comm: kworker/0:1 Not tainted 4.17.0-dirty #1092 Hardware name: Renesas Condor board based on r8a77980 (DT) Workqueue: events deferred_probe_work_func pstate: 80000005 (Nzcv daif -PAN -UAO) pc : ioremap_page_range+0x370/0x3c8 lr : ioremap_page_range+0x40/0x3c8 sp : ffff000008da39e0 x29: ffff000008da39e0 x28: 00e8000000000f07 x27: ffff7dfffee00000 x26: 0140000000000000 x25: ffff7dfffef00000 x24: 00000000000fe100 x23: ffff80007b906000 x22: ffff000008ab8000 x21: ffff000008bb1d58 x20: ffff7dfffef00000 x19: ffff800009c30fb8 x18: 0000000000000001 x17: 00000000000152d0 x16: 00000000014012d0 x15: 0000000000000000 x14: 0720072007200720 x13: 0720072007200720 x12: 0720072007200720 x11: 0720072007300730 x10: 00000000000000ae x9 : 0000000000000000 x8 : ffff7dffff000000 x7 : 0000000000000000 x6 : 0000000000000100 x5 : 0000000000000000 x4 : 000000007b906000 x3 : ffff80007c61a880 x2 : ffff7dfffeefffff x1 : 0000000040000000 x0 : 00e80000fe100f07 Process kworker/0:1 (pid: 39, stack limit = 0x (ptrval)) Call trace: ioremap_page_range+0x370/0x3c8 pci_remap_iospace+0x7c/0xac pci_parse_request_of_pci_ranges+0x13c/0x190 rcar_pcie_probe+0x4c/0xb04 platform_drv_probe+0x50/0xbc driver_probe_device+0x21c/0x308 __device_attach_driver+0x98/0xc8 bus_for_each_drv+0x54/0x94 __device_attach+0xc4/0x12c device_initial_probe+0x10/0x18 bus_probe_device+0x90/0x98 deferred_probe_work_func+0xb0/0x150 process_one_work+0x12c/0x29c worker_thread+0x200/0x3fc kthread+0x108/0x134 ret_from_fork+0x10/0x18 Code: f9004ba2 54000080 aa0003fb 17ffff48 (d4210000) It turned out that pci_remap_iospace() wasn't undone when the driver's probe failed, and since devm_phy_optional_get() returned -EPROBE_DEFER, the probe was retried, finally causing the BUG due to trying to remap already remapped pages. Introduce the devm_pci_remap_iospace() managed API and replace the pci_remap_iospace() call with it to fix the bug. Fixes: dbf9826d5797 ("PCI: generic: Convert to DT resource parsing API") Signed-off-by: Sergei Shtylyov [lorenzo.pieralisi@arm.com: split commit/updated the commit log] Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Linus Walleij --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..abd5d5e17aee 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1240,6 +1240,8 @@ int pci_register_io_range(struct fwnode_handle *fwnode, phys_addr_t addr, unsigned long pci_address_to_pio(phys_addr_t addr); phys_addr_t pci_pio_to_address(unsigned long pio); int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr); +int devm_pci_remap_iospace(struct device *dev, const struct resource *res, + phys_addr_t phys_addr); void pci_unmap_iospace(struct resource *res); void __iomem *devm_pci_remap_cfgspace(struct device *dev, resource_size_t offset, -- cgit v1.2.3 From a48d189ef53146a8df132a327a637c4182f50a16 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Tue, 17 Jul 2018 11:52:57 +0200 Subject: net: Move skb decrypted field, avoid explicity copy Commit 784abe24c903 ("net: Add decrypted field to skb") introduced a 'decrypted' field that is explicitly copied on skb copy and clone. Move it between headers_start[0] and headers_end[0], so that we don't need to copy it explicitly as it's copied by the memcpy() in __copy_skb_header(). While at it, drop the assignment in __skb_clone(), it was already redundant. This doesn't change the size of sk_buff or cacheline boundaries. The 15-bits hole before tc_index becomes a 14-bits hole, and will be again a 15-bits hole when this change is merged with commit 8b7008620b84 ("net: Don't copy pfmemalloc flag in __copy_skb_header()"). v2: as reported by kbuild test robot (oops, I forgot to build with CONFIG_TLS_DEVICE it seems), we can't use CHECK_SKB_FIELD() on a bit-field member. Just drop the check for the moment being, perhaps we could think of some magic to also check bit-field members one day. Fixes: 784abe24c903 ("net: Add decrypted field to skb") Signed-off-by: Stefano Brivio Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3ceb8dcc54da..14bc9ebe30f2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -630,7 +630,6 @@ typedef unsigned char *sk_buff_data_t; * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @xmit_more: More SKBs are pending for this queue - * @decrypted: Decrypted SKB * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport @@ -641,6 +640,7 @@ typedef unsigned char *sk_buff_data_t; * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @dst_pending_confirm: need to confirm neighbour + * @decrypted: Decrypted SKB * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking * @mark: Generic packet mark @@ -737,11 +737,7 @@ struct sk_buff { peeked:1, head_frag:1, xmit_more:1, -#ifdef CONFIG_TLS_DEVICE - decrypted:1; -#else __unused:1; -#endif /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() @@ -797,6 +793,9 @@ struct sk_buff { __u8 tc_redirected:1; __u8 tc_from_ingress:1; #endif +#ifdef CONFIG_TLS_DEVICE + __u8 decrypted:1; +#endif #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ -- cgit v1.2.3 From eff8ea8f24eac76bc21c25e4ca4ac4ee2dade846 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Mon, 16 Jul 2018 18:35:30 -0700 Subject: net/mlx5: FW tracer, add hardware structures This change adds the infrastructure to mlx5 core fw tracer. It introduces the following 4 new registers: MLX5_REG_MTRC_CAP - Used to read tracer capabilities MLX5_REG_MTRC_CONF - Used to set tracer configurations MLX5_REG_MTRC_STDB - Used to query tracer strings database MLX5_REG_MTRC_CTRL - Used to control the tracer The capability of the tracing can be checked using mcam access register, therefore, the mcam access register interface will expose the tracer register. Signed-off-by: Feras Daoud Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 4 +++ include/linux/mlx5/mlx5_ifc.h | 61 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 64 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1cb1c0317b77..4a4125b4279d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -138,6 +138,10 @@ enum { MLX5_REG_HOST_ENDIANNESS = 0x7004, MLX5_REG_MCIA = 0x9014, MLX5_REG_MLCR = 0x902b, + MLX5_REG_MTRC_CAP = 0x9040, + MLX5_REG_MTRC_CONF = 0x9041, + MLX5_REG_MTRC_STDB = 0x9042, + MLX5_REG_MTRC_CTRL = 0x9043, MLX5_REG_MPCNT = 0x9051, MLX5_REG_MTPPS = 0x9053, MLX5_REG_MTPPSE = 0x9054, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1853e7fd6924..bd7b71f54d59 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8112,7 +8112,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mcqi[0x1]; u8 reserved_at_1f[0x1]; - u8 regs_95_to_64[0x20]; + u8 regs_95_to_68[0x1c]; + u8 tracer_registers[0x4]; + u8 regs_63_to_32[0x20]; u8 regs_31_to_0[0x20]; }; @@ -9187,4 +9189,61 @@ struct mlx5_ifc_create_uctx_in_bits { struct mlx5_ifc_uctx_bits uctx; }; +struct mlx5_ifc_mtrc_string_db_param_bits { + u8 string_db_base_address[0x20]; + + u8 reserved_at_20[0x8]; + u8 string_db_size[0x18]; +}; + +struct mlx5_ifc_mtrc_cap_bits { + u8 trace_owner[0x1]; + u8 trace_to_memory[0x1]; + u8 reserved_at_2[0x4]; + u8 trc_ver[0x2]; + u8 reserved_at_8[0x14]; + u8 num_string_db[0x4]; + + u8 first_string_trace[0x8]; + u8 num_string_trace[0x8]; + u8 reserved_at_30[0x28]; + + u8 log_max_trace_buffer_size[0x8]; + + u8 reserved_at_60[0x20]; + + struct mlx5_ifc_mtrc_string_db_param_bits string_db_param[8]; + + u8 reserved_at_280[0x180]; +}; + +struct mlx5_ifc_mtrc_conf_bits { + u8 reserved_at_0[0x1c]; + u8 trace_mode[0x4]; + u8 reserved_at_20[0x18]; + u8 log_trace_buffer_size[0x8]; + u8 trace_mkey[0x20]; + u8 reserved_at_60[0x3a0]; +}; + +struct mlx5_ifc_mtrc_stdb_bits { + u8 string_db_index[0x4]; + u8 reserved_at_4[0x4]; + u8 read_size[0x18]; + u8 start_offset[0x20]; + u8 string_db_data[0]; +}; + +struct mlx5_ifc_mtrc_ctrl_bits { + u8 trace_status[0x2]; + u8 reserved_at_2[0x2]; + u8 arm_event[0x1]; + u8 reserved_at_5[0xb]; + u8 modify_field_select[0x10]; + u8 reserved_at_20[0x2b]; + u8 current_timestamp52_32[0x15]; + u8 current_timestamp31_0[0x20]; + u8 reserved_at_80[0x180]; +}; + #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From 5e022dd353b74132bf216a77b169c43e39f5be9e Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 16 Jul 2018 18:35:31 -0700 Subject: net/mlx5: Expose MPEGC (Management PCIe General Configuration) structures This patch exposes PRM layout for handling MPEGC (Management PCIe General Configuration). This will be used in the downstream patch for configuring MPEGC via the driver. Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 23 +++++++++++++++++++++-- 2 files changed, 22 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 4a4125b4279d..957199c20a0f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -145,6 +145,7 @@ enum { MLX5_REG_MPCNT = 0x9051, MLX5_REG_MTPPS = 0x9053, MLX5_REG_MTPPSE = 0x9054, + MLX5_REG_MPEGC = 0x9056, MLX5_REG_MCQI = 0x9061, MLX5_REG_MCC = 0x9062, MLX5_REG_MCDA = 0x9063, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index bd7b71f54d59..2de5feaeb74a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8049,6 +8049,19 @@ struct mlx5_ifc_peir_reg_bits { u8 error_type[0x8]; }; +struct mlx5_ifc_mpegc_reg_bits { + u8 reserved_at_0[0x30]; + u8 field_select[0x10]; + + u8 tx_overflow_sense[0x1]; + u8 mark_cqe[0x1]; + u8 mark_cnp[0x1]; + u8 reserved_at_43[0x1b]; + u8 tx_lossy_overflow_oper[0x2]; + + u8 reserved_at_60[0x100]; +}; + struct mlx5_ifc_pcam_enhanced_features_bits { u8 reserved_at_0[0x6d]; u8 rx_icrc_encapsulated_counter[0x1]; @@ -8097,7 +8110,11 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x7b]; + u8 reserved_at_0[0x74]; + u8 mark_tx_action_cnp[0x1]; + u8 mark_tx_action_cqe[0x1]; + u8 dynamic_tx_overflow[0x1]; + u8 reserved_at_77[0x4]; u8 pcie_outbound_stalled[0x1]; u8 tx_overflow_buffer_pkt[0x1]; u8 mtpps_enh_out_per_adj[0x1]; @@ -8112,7 +8129,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mcqi[0x1]; u8 reserved_at_1f[0x1]; - u8 regs_95_to_68[0x1c]; + u8 regs_95_to_87[0x9]; + u8 mpegc[0x1]; + u8 regs_85_to_68[0x12]; u8 tracer_registers[0x4]; u8 regs_63_to_32[0x20]; -- cgit v1.2.3 From 8da6fe2a18505b9bd977e573d62d33f836c6903c Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Mon, 16 Jul 2018 18:35:32 -0700 Subject: net/mlx5: Add core support for double vlan push/pop steering action As newer firmware supports double push/pop in a single FTE, we add core bits and extend vlan action logic for it. Signed-off-by: Jianbo Liu Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 4 +++- include/linux/mlx5/mlx5_ifc.h | 11 +++++++++-- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 757b4a30281e..c40f2fc68655 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -152,6 +152,8 @@ struct mlx5_fs_vlan { u8 prio; }; +#define MLX5_FS_VLAN_DEPTH 2 + struct mlx5_flow_act { u32 action; bool has_flow_tag; @@ -159,7 +161,7 @@ struct mlx5_flow_act { u32 encap_id; u32 modify_id; uintptr_t esp_id; - struct mlx5_fs_vlan vlan; + struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 2de5feaeb74a..ae12120ef021 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -337,7 +337,10 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_9[0x1]; u8 pop_vlan[0x1]; u8 push_vlan[0x1]; - u8 reserved_at_c[0x14]; + u8 reserved_at_c[0x1]; + u8 pop_vlan_2[0x1]; + u8 push_vlan_2[0x1]; + u8 reserved_at_f[0x11]; u8 reserved_at_20[0x2]; u8 log_max_ft_size[0x6]; @@ -2386,6 +2389,8 @@ enum { MLX5_FLOW_CONTEXT_ACTION_MOD_HDR = 0x40, MLX5_FLOW_CONTEXT_ACTION_VLAN_POP = 0x80, MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH = 0x100, + MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2 = 0x400, + MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800, }; struct mlx5_ifc_vlan_bits { @@ -2416,7 +2421,9 @@ struct mlx5_ifc_flow_context_bits { u8 modify_header_id[0x20]; - u8 reserved_at_100[0x100]; + struct mlx5_ifc_vlan_bits push_vlan_2; + + u8 reserved_at_120[0xe0]; struct mlx5_ifc_fte_match_param_bits match_value; -- cgit v1.2.3 From e2abdcf1d2dd59d7164cf975c50e1587b96b9d04 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 16 Jul 2018 18:35:36 -0700 Subject: net/mlx5: Better return types for CQE API Reduce sizes of return types. Use bool for binary indication. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f8671c0a43aa..0566c6a94805 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -750,7 +750,7 @@ enum { #define MLX5_MINI_CQE_ARRAY_SIZE 8 -static inline int mlx5_get_cqe_format(struct mlx5_cqe64 *cqe) +static inline u8 mlx5_get_cqe_format(struct mlx5_cqe64 *cqe) { return (cqe->op_own >> 2) & 0x3; } @@ -770,14 +770,14 @@ static inline u8 get_cqe_l3_hdr_type(struct mlx5_cqe64 *cqe) return (cqe->l4_l3_hdr_type >> 2) & 0x3; } -static inline u8 cqe_is_tunneled(struct mlx5_cqe64 *cqe) +static inline bool cqe_is_tunneled(struct mlx5_cqe64 *cqe) { return cqe->outer_l3_tunneled & 0x1; } -static inline int cqe_has_vlan(struct mlx5_cqe64 *cqe) +static inline bool cqe_has_vlan(struct mlx5_cqe64 *cqe) { - return !!(cqe->l4_l3_hdr_type & 0x1); + return cqe->l4_l3_hdr_type & 0x1; } static inline u64 get_cqe_ts(struct mlx5_cqe64 *cqe) -- cgit v1.2.3 From d7037ad73daa9598b8caa7d5fdf41e8ceee6ef73 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Sun, 8 Jul 2018 12:14:59 +0300 Subject: net/mlx5: Fix QP fragmented buffer allocation Fix bad alignment of SQ buffer in fragmented QP allocation. It should start directly after RQ buffer ends. Take special care of the end case where the RQ buffer does not occupy a whole page. RQ size is a power of two, so would be the case only for small RQ sizes (RQ size < PAGE_SIZE). Fix wrong assignments for sqb->size (mistakenly assigned RQ size), and for npages value of RQ and SQ. Fixes: 3a2f70331226 ("net/mlx5: Use order-0 allocations for all WQ types") Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 80cbb7fdce4a..83957920653a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -358,6 +358,7 @@ struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; u32 frag_sz_m1; + u32 strides_offset; u8 log_sz; u8 log_stride; u8 log_frag_strides; @@ -983,14 +984,22 @@ static inline u32 mlx5_base_mkey(const u32 key) return key & 0xffffff00u; } -static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, - struct mlx5_frag_buf_ctrl *fbc) +static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, + u32 strides_offset, + struct mlx5_frag_buf_ctrl *fbc) { fbc->log_stride = log_stride; fbc->log_sz = log_sz; fbc->sz_m1 = (1 << fbc->log_sz) - 1; fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride; fbc->frag_sz_m1 = (1 << fbc->log_frag_strides) - 1; + fbc->strides_offset = strides_offset; +} + +static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, + struct mlx5_frag_buf_ctrl *fbc) +{ + mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc); } static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, @@ -1004,7 +1013,10 @@ static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, u32 ix) { - unsigned int frag = (ix >> fbc->log_frag_strides); + unsigned int frag; + + ix += fbc->strides_offset; + frag = ix >> fbc->log_frag_strides; return fbc->frag_buf.frags[frag].buf + ((fbc->frag_sz_m1 & ix) << fbc->log_stride); -- cgit v1.2.3 From 8963106eabdc56911e9b65258eb5e9a6b7b3dfda Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Thu, 19 Jul 2018 10:32:12 +0200 Subject: PCI: endpoint: Add MSI-X interfaces Add PCI_EPC_IRQ_MSIX type. Add MSI-X callbacks signatures to the ops structure. Add sysfs interface for set/get MSI-X capability maximum number. Update documentation accordingly. Signed-off-by: Gustavo Pimentel Signed-off-by: Lorenzo Pieralisi Acked-by: Kishon Vijay Abraham I --- include/linux/pci-epc.h | 9 +++++++++ include/linux/pci-epf.h | 1 + 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 243eaa5a66ff..89f079f582df 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -17,6 +17,7 @@ enum pci_epc_irq_type { PCI_EPC_IRQ_UNKNOWN, PCI_EPC_IRQ_LEGACY, PCI_EPC_IRQ_MSI, + PCI_EPC_IRQ_MSIX, }; /** @@ -30,6 +31,10 @@ enum pci_epc_irq_type { * capability register * @get_msi: ops to get the number of MSI interrupts allocated by the RC from * the MSI capability register + * @set_msix: ops to set the requested number of MSI-X interrupts in the + * MSI-X capability register + * @get_msix: ops to get the number of MSI-X interrupts allocated by the RC + * from the MSI-X capability register * @raise_irq: ops to raise a legacy or MSI interrupt * @start: ops to start the PCI link * @stop: ops to stop the PCI link @@ -48,6 +53,8 @@ struct pci_epc_ops { phys_addr_t addr); int (*set_msi)(struct pci_epc *epc, u8 func_no, u8 interrupts); int (*get_msi)(struct pci_epc *epc, u8 func_no); + int (*set_msix)(struct pci_epc *epc, u8 func_no, u16 interrupts); + int (*get_msix)(struct pci_epc *epc, u8 func_no); int (*raise_irq)(struct pci_epc *epc, u8 func_no, enum pci_epc_irq_type type, u8 interrupt_num); int (*start)(struct pci_epc *epc); @@ -144,6 +151,8 @@ void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no, phys_addr_t phys_addr); int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts); int pci_epc_get_msi(struct pci_epc *epc, u8 func_no); +int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts); +int pci_epc_get_msix(struct pci_epc *epc, u8 func_no); int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, enum pci_epc_irq_type type, u8 interrupt_num); int pci_epc_start(struct pci_epc *epc); diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 4e7764935fa8..ec02f58758c8 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -119,6 +119,7 @@ struct pci_epf { struct pci_epf_header *header; struct pci_epf_bar bar[6]; u8 msi_interrupts; + u16 msix_interrupts; u8 func_no; struct pci_epc *epc; -- cgit v1.2.3 From d3c70a98d7d63cae02d50ebfafea04264a767401 Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Thu, 19 Jul 2018 10:32:13 +0200 Subject: PCI: Update xxx_pcie_ep_raise_irq() and pci_epc_raise_irq() signatures Change {cdns, dra7xx, artpec6, dw, rockchip}_pcie_ep_raise_irq() and pci_epc_raise_irq() signature, namely the interrupt_num variable type from u8 to u16 to accommodate 2048 maximum MSI-X interrupts. Signed-off-by: Gustavo Pimentel Signed-off-by: Lorenzo Pieralisi Acked-by: Alan Douglas Acked-by: Shawn Lin Acked-by: Jesper Nilsson Acked-by: Joao Pinto Acked-by: Kishon Vijay Abraham I --- include/linux/pci-epc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 89f079f582df..bb2395b56f13 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -35,7 +35,7 @@ enum pci_epc_irq_type { * MSI-X capability register * @get_msix: ops to get the number of MSI-X interrupts allocated by the RC * from the MSI-X capability register - * @raise_irq: ops to raise a legacy or MSI interrupt + * @raise_irq: ops to raise a legacy, MSI or MSI-X interrupt * @start: ops to start the PCI link * @stop: ops to stop the PCI link * @owner: the module owner containing the ops @@ -56,7 +56,7 @@ struct pci_epc_ops { int (*set_msix)(struct pci_epc *epc, u8 func_no, u16 interrupts); int (*get_msix)(struct pci_epc *epc, u8 func_no); int (*raise_irq)(struct pci_epc *epc, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num); + enum pci_epc_irq_type type, u16 interrupt_num); int (*start)(struct pci_epc *epc); void (*stop)(struct pci_epc *epc); struct module *owner; @@ -154,7 +154,7 @@ int pci_epc_get_msi(struct pci_epc *epc, u8 func_no); int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts); int pci_epc_get_msix(struct pci_epc *epc, u8 func_no); int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num); + enum pci_epc_irq_type type, u16 interrupt_num); int pci_epc_start(struct pci_epc *epc); void pci_epc_stop(struct pci_epc *epc); struct pci_epc *pci_epc_get(const char *epc_name); -- cgit v1.2.3 From c2e00e31087e58f6c49b90b4702fc3df4fad6a83 Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Thu, 19 Jul 2018 10:32:19 +0200 Subject: pci-epf-test/pci_endpoint_test: Add MSI-X support Add MSI-X support and update driver documentation accordingly. Signed-off-by: Gustavo Pimentel Signed-off-by: Lorenzo Pieralisi Acked-by: Kishon Vijay Abraham I --- include/linux/pci-epc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index bb2395b56f13..37dab8116901 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -102,6 +102,7 @@ struct pci_epc { #define EPC_FEATURE_NO_LINKUP_NOTIFIER BIT(0) #define EPC_FEATURE_BAR_MASK (BIT(1) | BIT(2) | BIT(3)) +#define EPC_FEATURE_MSIX_AVAILABLE BIT(4) #define EPC_FEATURE_SET_BAR(features, bar) \ (features |= (EPC_FEATURE_BAR_MASK & (bar << 1))) #define EPC_FEATURE_GET_BAR(features) \ -- cgit v1.2.3 From d70420bcd447e5400a0116b20b9b6088bb32448e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 18 Jul 2018 22:33:02 +0200 Subject: mtd: adapt misleading comment in mtd_oob_ops structure A comment in the kernel doc of the mtd_oob_ops structure tells that it is not possible to write more than one page with OOB. This is actually true for only a few MTD devices like 'onenand' but it is definitely not a general limitation. While this would benefit to be handled elsewhere either by the MTD layer or by the limited drivers, let's update this comment to reflect the reality. Signed-off-by: Miquel Raynal Signed-off-by: Boris Brezillon --- include/linux/mtd/mtd.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index a86c4fa93115..cd0be91bdefa 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -67,9 +67,11 @@ struct mtd_erase_region_info { * @datbuf: data buffer - if NULL only oob data are read/written * @oobbuf: oob data buffer * - * Note, it is allowed to read more than one OOB area at one go, but not write. - * The interface assumes that the OOB write requests program only one page's - * OOB area. + * Note, some MTD drivers do not allow you to write more than one OOB area at + * one go. If you try to do that on such an MTD device, -EINVAL will be + * returned. If you want to make your implementation portable on all kind of MTD + * devices you should split the write request into several sub-requests when the + * request crosses a page boundary. */ struct mtd_oob_ops { unsigned int mode; -- cgit v1.2.3 From 0d6030ac041f6835974deb88a1a9c299b4adc3ad Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Wed, 18 Jul 2018 10:42:17 +0200 Subject: mtd: rawnand: Expose _notsupp() helpers for raw page accessors Some implementations simply can't disable their ECC engine. Expose helpers returning -ENOTSUPP so that the caller knows that raw accesses are not supported instead of silently falling back to non-raw accessors. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 11c2426fc363..f60fad29eae6 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1681,10 +1681,14 @@ int nand_get_set_features_notsupp(struct mtd_info *mtd, struct nand_chip *chip, /* Default read_page_raw implementation */ int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, int oob_required, int page); +int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip, + u8 *buf, int oob_required, int page); /* Default write_page_raw implementation */ int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, const uint8_t *buf, int oob_required, int page); +int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip, + const u8 *buf, int oob_required, int page); /* Reset and initialize a NAND device */ int nand_reset(struct nand_chip *chip, int chipnr); -- cgit v1.2.3 From 60ed982a4e78ff938824a750dbac8a10e5b472ef Mon Sep 17 00:00:00 2001 From: Rajat Jain Date: Thu, 21 Jun 2018 16:48:26 -0700 Subject: PCI/AER: Move internal declarations to drivers/pci/pci.h Since pci_aer_init() and pci_no_aer() are used only internally, move their declarations to the PCI internal header file. Also, no one cares about return value of pci_aer_init(), so make it void. Signed-off-by: Rajat Jain Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..b4ffea05c999 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1468,13 +1468,9 @@ static inline bool pcie_aspm_support_enabled(void) { return false; } #endif #ifdef CONFIG_PCIEAER -void pci_no_aer(void); bool pci_aer_available(void); -int pci_aer_init(struct pci_dev *dev); #else -static inline void pci_no_aer(void) { } static inline bool pci_aer_available(void) { return false; } -static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; } #endif #ifdef CONFIG_PCIE_ECRC -- cgit v1.2.3 From db89ccbe52c7885644ba578c7771e57620f879b1 Mon Sep 17 00:00:00 2001 From: Rajat Jain Date: Sat, 30 Jun 2018 15:07:17 -0500 Subject: PCI/AER: Define aer_stats structure for AER capable devices Define a structure to hold the AER statistics. There are 2 groups of statistics: dev_* counters that are to be collected for all AER capable devices and rootport_* counters that are collected for all (AER capable) rootports only. Allocate and free this structure when device is added or released (thus counters survive the lifetime of the device). Signed-off-by: Rajat Jain Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b4ffea05c999..6bc0aa0fc33f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -299,6 +299,7 @@ struct pci_dev { u8 hdr_type; /* PCI header type (`multi' flag masked out) */ #ifdef CONFIG_PCIEAER u16 aer_cap; /* AER capability offset */ + struct aer_stats *aer_stats; /* AER stats for this device */ #endif u8 pcie_cap; /* PCIe capability offset */ u8 msi_cap; /* MSI capability offset */ -- cgit v1.2.3 From 3eca993740b8eb40f514b90b1877a4dbcf0a6710 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Thu, 19 Jul 2018 16:55:34 -0400 Subject: timekeeping: Replace read_boot_clock64() with read_persistent_wall_and_boot_offset() If architecture does not support exact boot time, it is challenging to estimate boot time without having a reference to the current persistent clock value. Yet, it cannot read the persistent clock time again, because this may lead to math discrepancies with the caller of read_boot_clock64() who have read the persistent clock at a different time. This is why it is better to provide two values simultaneously: the persistent clock value, and the boot time. Replace read_boot_clock64() with: read_persistent_wall_and_boot_offset(wall_time, boot_offset) Where wall_time is returned by read_persistent_clock() And boot_offset is wall_time - boot time, which defaults to 0. Signed-off-by: Pavel Tatashin Signed-off-by: Thomas Gleixner Cc: steven.sistare@oracle.com Cc: daniel.m.jordan@oracle.com Cc: linux@armlinux.org.uk Cc: schwidefsky@de.ibm.com Cc: heiko.carstens@de.ibm.com Cc: john.stultz@linaro.org Cc: sboyd@codeaurora.org Cc: hpa@zytor.com Cc: douly.fnst@cn.fujitsu.com Cc: peterz@infradead.org Cc: prarit@redhat.com Cc: feng.tang@intel.com Cc: pmladek@suse.com Cc: gnomes@lxorguk.ukuu.org.uk Cc: linux-s390@vger.kernel.org Cc: boris.ostrovsky@oracle.com Cc: jgross@suse.com Cc: pbonzini@redhat.com Link: https://lkml.kernel.org/r/20180719205545.16512-16-pasha.tatashin@oracle.com --- include/linux/timekeeping.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 86bc2026efce..686bc27acef0 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -243,7 +243,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); -extern void read_boot_clock64(struct timespec64 *ts); +void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock, + struct timespec64 *boot_offset); extern int update_persistent_clock64(struct timespec64 now); /* -- cgit v1.2.3 From 5d2a4e91a541cb04d20d11602f0f9340291322ac Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Thu, 19 Jul 2018 16:55:41 -0400 Subject: sched/clock: Move sched clock initialization and merge with generic clock sched_clock_postinit() initializes a generic clock on systems where no other clock is provided. This function may be called only after timekeeping_init(). Rename sched_clock_postinit to generic_clock_inti() and call it from sched_clock_init(). Move the call for sched_clock_init() until after time_init(). Suggested-by: Peter Zijlstra Signed-off-by: Pavel Tatashin Signed-off-by: Thomas Gleixner Cc: steven.sistare@oracle.com Cc: daniel.m.jordan@oracle.com Cc: linux@armlinux.org.uk Cc: schwidefsky@de.ibm.com Cc: heiko.carstens@de.ibm.com Cc: john.stultz@linaro.org Cc: sboyd@codeaurora.org Cc: hpa@zytor.com Cc: douly.fnst@cn.fujitsu.com Cc: prarit@redhat.com Cc: feng.tang@intel.com Cc: pmladek@suse.com Cc: gnomes@lxorguk.ukuu.org.uk Cc: linux-s390@vger.kernel.org Cc: boris.ostrovsky@oracle.com Cc: jgross@suse.com Cc: pbonzini@redhat.com Link: https://lkml.kernel.org/r/20180719205545.16512-23-pasha.tatashin@oracle.com --- include/linux/sched_clock.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index 411b52e424e1..abe28d5cb3f4 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -9,17 +9,16 @@ #define LINUX_SCHED_CLOCK #ifdef CONFIG_GENERIC_SCHED_CLOCK -extern void sched_clock_postinit(void); +extern void generic_sched_clock_init(void); extern void sched_clock_register(u64 (*read)(void), int bits, unsigned long rate); #else -static inline void sched_clock_postinit(void) { } +static inline void generic_sched_clock_init(void) { } static inline void sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) { - ; } #endif -- cgit v1.2.3 From 381634cad15b711e033a2638d558232b60f753f6 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Thu, 19 Jul 2018 18:04:11 -0500 Subject: PCI: Hide pci_reset_bridge_secondary_bus() from drivers Rename pci_reset_bridge_secondary_bus() to pci_bridge_secondary_bus_reset() and move the declaration from linux/pci.h to drivers/pci.h to be used internally in PCI directory only. Signed-off-by: Sinan Kaya Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 6ba818449095..03520ff23d73 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1103,7 +1103,6 @@ int pci_reset_bus(struct pci_bus *bus); int pci_try_reset_bus(struct pci_bus *bus); void pci_reset_secondary_bus(struct pci_dev *dev); void pcibios_reset_secondary_bus(struct pci_dev *dev); -int pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); -- cgit v1.2.3 From 811c5cb37df46b0cd714dbd053d19cdb97d08cff Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Thu, 19 Jul 2018 18:04:12 -0500 Subject: PCI: Unify try slot and bus reset API Drivers are expected to call pci_try_reset_slot() or pci_try_reset_bus() by querying if a system supports hotplug or not. A survey showed that most drivers don't do this and we are leaking hotplug capability to the user. Hide pci_try_slot_reset() from drivers and embed into pci_try_bus_reset(). Change pci_try_reset_bus() parameter from struct pci_bus to struct pci_dev. Signed-off-by: Sinan Kaya Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 03520ff23d73..19fb82559145 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1097,10 +1097,9 @@ int pci_reset_function_locked(struct pci_dev *dev); int pci_try_reset_function(struct pci_dev *dev); int pci_probe_reset_slot(struct pci_slot *slot); int pci_reset_slot(struct pci_slot *slot); -int pci_try_reset_slot(struct pci_slot *slot); int pci_probe_reset_bus(struct pci_bus *bus); int pci_reset_bus(struct pci_bus *bus); -int pci_try_reset_bus(struct pci_bus *bus); +int pci_try_reset_bus(struct pci_dev *dev); void pci_reset_secondary_bus(struct pci_dev *dev); void pcibios_reset_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); -- cgit v1.2.3 From fe32e2fa656c29d5d25f959f8e6168ac405d9ab4 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Thu, 19 Jul 2018 18:04:14 -0500 Subject: PCI: Deprecate pci_reset_bus() and pci_reset_slot() functions pci_reset_bus() and pci_reset_slot() functions are not being used by any code. Remove them from the kernel in favor of pci_try_reset_bus() and pci_try_reset_slot() functions. Signed-off-by: Sinan Kaya Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 19fb82559145..cf53ecb50789 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1096,9 +1096,7 @@ int pci_reset_function(struct pci_dev *dev); int pci_reset_function_locked(struct pci_dev *dev); int pci_try_reset_function(struct pci_dev *dev); int pci_probe_reset_slot(struct pci_slot *slot); -int pci_reset_slot(struct pci_slot *slot); int pci_probe_reset_bus(struct pci_bus *bus); -int pci_reset_bus(struct pci_bus *bus); int pci_try_reset_bus(struct pci_dev *dev); void pci_reset_secondary_bus(struct pci_dev *dev); void pcibios_reset_secondary_bus(struct pci_dev *dev); -- cgit v1.2.3 From c6a44ba950d147e15fe6dab6455a52f91d8fe625 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Thu, 19 Jul 2018 18:04:15 -0500 Subject: PCI: Rename pci_try_reset_bus() to pci_reset_bus() Now that the old implementation of pci_reset_bus() is gone, replace pci_try_reset_bus() with pci_reset_bus(). Compared to the old implementation, new code will fail immmediately with -EAGAIN if object lock cannot be obtained. Signed-off-by: Sinan Kaya Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index cf53ecb50789..307b336496f6 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1097,7 +1097,7 @@ int pci_reset_function_locked(struct pci_dev *dev); int pci_try_reset_function(struct pci_dev *dev); int pci_probe_reset_slot(struct pci_slot *slot); int pci_probe_reset_bus(struct pci_bus *bus); -int pci_try_reset_bus(struct pci_dev *dev); +int pci_reset_bus(struct pci_dev *dev); void pci_reset_secondary_bus(struct pci_dev *dev); void pcibios_reset_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); -- cgit v1.2.3 From b976690f5db26fbc7c2be413bfa0fbd270547a94 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 18 Jul 2018 11:41:06 +0200 Subject: x86/mm/pti: Introduce pti_finalize() Introduce a new function to finalize the kernel mappings for the userspace page-table after all ro/nx protections have been applied to the kernel mappings. Also move the call to pti_clone_kernel_text() to that function so that it will run on 32 bit kernels too. Signed-off-by: Joerg Roedel Signed-off-by: Thomas Gleixner Tested-by: Pavel Machek Cc: "H . Peter Anvin" Cc: linux-mm@kvack.org Cc: Linus Torvalds Cc: Andy Lutomirski Cc: Dave Hansen Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Jiri Kosina Cc: Boris Ostrovsky Cc: Brian Gerst Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Cc: Andrea Arcangeli Cc: Waiman Long Cc: "David H . Gutteridge" Cc: joro@8bytes.org Link: https://lkml.kernel.org/r/1531906876-13451-30-git-send-email-joro@8bytes.org --- include/linux/pti.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pti.h b/include/linux/pti.h index 0174883a935a..1a941efcaa62 100644 --- a/include/linux/pti.h +++ b/include/linux/pti.h @@ -6,6 +6,7 @@ #include #else static inline void pti_init(void) { } +static inline void pti_finalize(void) { } #endif #endif -- cgit v1.2.3 From 985e695074d35768cb04d65f58bca45f7bf1a99d Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Fri, 13 Jul 2018 14:06:42 +0200 Subject: timekeeping/ntp: Constify some function arguments Add 'const' to some function arguments and variables to make it easier to read the code. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Cc: Stephen Boyd Signed-off-by: Ondrej Mosnacek [jstultz: Also fixup pre-existing checkpatch warnings for prototype arguments with no variable name] Signed-off-by: John Stultz --- include/linux/timekeeping.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 86bc2026efce..edace6b656e9 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -177,7 +177,7 @@ static inline time64_t ktime_get_clocktai_seconds(void) extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); -extern void timekeeping_inject_sleeptime64(struct timespec64 *delta); +extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /* * struct system_time_snapshot - simultaneous raw/real time capture with -- cgit v1.2.3 From 39232ed5a1793f67b11430c43ed8a9ed6e96c6eb Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Tue, 17 Jul 2018 15:55:16 +0800 Subject: time: Introduce one suspend clocksource to compensate the suspend time On some hardware with multiple clocksources, we have coarse grained clocksources that support the CLOCK_SOURCE_SUSPEND_NONSTOP flag, but which are less than ideal for timekeeping whereas other clocksources can be better candidates but halt on suspend. Currently, the timekeeping core only supports timing suspend using CLOCK_SOURCE_SUSPEND_NONSTOP clocksources if that clocksource is the current clocksource for timekeeping. As a result, some architectures try to implement read_persistent_clock64() using those non-stop clocksources, but isn't really ideal, which will introduce more duplicate code. To fix this, provide logic to allow a registered SUSPEND_NONSTOP clocksource, which isn't the current clocksource, to be used to calculate the suspend time. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Cc: Stephen Boyd Cc: Daniel Lezcano Reviewed-by: Thomas Gleixner Reviewed-by: Daniel Lezcano Suggested-by: Thomas Gleixner Signed-off-by: Baolin Wang [jstultz: minor tweaks to merge with previous resume changes] Signed-off-by: John Stultz --- include/linux/clocksource.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 7dff1963c185..308918928767 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -194,6 +194,9 @@ extern void clocksource_suspend(void); extern void clocksource_resume(void); extern struct clocksource * __init clocksource_default_clock(void); extern void clocksource_mark_unstable(struct clocksource *cs); +extern void +clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles); +extern u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 now); extern u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cycles); -- cgit v1.2.3 From b51dab46c6adfbb7e80cd0f59ae17b8a30d94b1a Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 18 Jul 2018 06:27:22 -0700 Subject: qed: Add qed APIs for PHY module query. This patch adds qed APIs for reading the PHY module. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index b4040023cbfb..8cd34645e892 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -759,6 +759,9 @@ struct qed_generic_tlvs { u8 mac[QED_TLV_MAC_COUNT][ETH_ALEN]; }; +#define QED_I2C_DEV_ADDR_A0 0xA0 +#define QED_I2C_DEV_ADDR_A2 0xA2 + #define QED_NVM_SIGNATURE 0x12435687 enum qed_nvm_flash_cmd { @@ -1026,6 +1029,18 @@ struct qed_common_ops { * @param enabled - true iff WoL should be enabled. */ int (*update_wol) (struct qed_dev *cdev, bool enabled); + +/** + * @brief read_module_eeprom + * + * @param cdev + * @param buf - buffer + * @param dev_addr - PHY device memory region + * @param offset - offset into eeprom contents to be read + * @param len - buffer length, i.e., max bytes to be read + */ + int (*read_module_eeprom)(struct qed_dev *cdev, + char *buf, u8 dev_addr, u32 offset, u32 len); }; #define MASK_FIELD(_name, _value) \ -- cgit v1.2.3 From 2db1581e1f432ac6b4efe152c57fdfb4de85c154 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sun, 8 Jul 2018 14:23:21 +0800 Subject: Revert "iommu/vt-d: Clean up pasid quirk for pre-production devices" This reverts commit ab96746aaa344fb720a198245a837e266fad3b62. The commit ab96746aaa34 ("iommu/vt-d: Clean up pasid quirk for pre-production devices") triggers ECS mode on some platforms which have broken ECS support. As the result, graphic device will be inoperable on boot. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107017 Cc: Ashok Raj Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 1df940196ab2..ef169d67df92 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -121,6 +121,7 @@ #define ecap_srs(e) ((e >> 31) & 0x1) #define ecap_ers(e) ((e >> 30) & 0x1) #define ecap_prs(e) ((e >> 29) & 0x1) +#define ecap_broken_pasid(e) ((e >> 28) & 0x1) #define ecap_dis(e) ((e >> 27) & 0x1) #define ecap_nest(e) ((e >> 26) & 0x1) #define ecap_mts(e) ((e >> 25) & 0x1) -- cgit v1.2.3 From 51261aac51a05c791ef880a100ac2ceed201ef72 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 14 Jul 2018 15:46:55 +0800 Subject: iommu/vt-d: Avoid using idr_for_each_entry() idr_for_each_entry() is used to iteratte over idr elements of a given type. It isn't suitable for the globle pasid idr since the pasid idr consumer could specify different types of pointers to bind with a pasid. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Reviewed-by: Liu Yi L Reviewed-by: Peter Xu Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 6692b40ca814..e1e193855581 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -487,6 +487,7 @@ struct intel_svm { int flags; int pasid; struct list_head devs; + struct list_head list; }; extern int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev); -- cgit v1.2.3 From af39507305fb83a5d3c475c2851f4d59545d8a18 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 14 Jul 2018 15:46:56 +0800 Subject: iommu/vt-d: Apply global PASID in SVA This patch applies the global pasid name space in the shared virtual address (SVA) implementation. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Reviewed-by: Liu Yi L Reviewed-by: Peter Xu Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index e1e193855581..2ff15195f73d 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -420,7 +420,6 @@ struct intel_iommu { struct pasid_state_entry *pasid_state_table; struct page_req_dsc *prq; unsigned char prq_name[16]; /* Name for PRQ interrupt */ - struct idr pasid_idr; u32 pasid_max; #endif struct q_inval *qi; /* Queued invalidation info */ -- cgit v1.2.3 From 9ddbfb42138d84bb326023616c40a3dc30ea2837 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 14 Jul 2018 15:46:57 +0800 Subject: iommu/vt-d: Move device_domain_info to header This allows the per device iommu data and some helpers to be used in other files. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Liu Yi L Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 61 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 61 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 2ff15195f73d..2e1fbde020ca 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -387,6 +388,42 @@ struct pasid_entry; struct pasid_state_entry; struct page_req_dsc; +struct dmar_domain { + int nid; /* node id */ + + unsigned iommu_refcnt[DMAR_UNITS_SUPPORTED]; + /* Refcount of devices per iommu */ + + + u16 iommu_did[DMAR_UNITS_SUPPORTED]; + /* Domain ids per IOMMU. Use u16 since + * domain ids are 16 bit wide according + * to VT-d spec, section 9.3 */ + + bool has_iotlb_device; + struct list_head devices; /* all devices' list */ + struct iova_domain iovad; /* iova's that belong to this domain */ + + struct dma_pte *pgd; /* virtual address */ + int gaw; /* max guest address width */ + + /* adjusted guest address width, 0 is level 2 30-bit */ + int agaw; + + int flags; /* flags to find out type of domain */ + + int iommu_coherency;/* indicate coherency of iommu access */ + int iommu_snooping; /* indicate snooping control feature*/ + int iommu_count; /* reference count of iommu */ + int iommu_superpage;/* Level of superpages supported: + 0 == 4KiB (no superpages), 1 == 2MiB, + 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ + u64 max_addr; /* maximum mapped address */ + + struct iommu_domain domain; /* generic domain data structure for + iommu core */ +}; + struct intel_iommu { void __iomem *reg; /* Pointer to hardware regs, virtual addr */ u64 reg_phys; /* physical address of hw register set */ @@ -435,6 +472,25 @@ struct intel_iommu { u32 flags; /* Software defined flags */ }; +/* PCI domain-device relationship */ +struct device_domain_info { + struct list_head link; /* link to domain siblings */ + struct list_head global; /* link to global list */ + u8 bus; /* PCI bus number */ + u8 devfn; /* PCI devfn number */ + u16 pfsid; /* SRIOV physical function source ID */ + u8 pasid_supported:3; + u8 pasid_enabled:1; + u8 pri_supported:1; + u8 pri_enabled:1; + u8 ats_supported:1; + u8 ats_enabled:1; + u8 ats_qdep; + struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ + struct intel_iommu *iommu; /* IOMMU used by this device */ + struct dmar_domain *domain; /* pointer to domain */ +}; + static inline void __iommu_flush_cache( struct intel_iommu *iommu, void *addr, int size) { @@ -460,6 +516,11 @@ extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu); extern int dmar_ir_support(void); +struct dmar_domain *get_valid_domain_for_dev(struct device *dev); +void *alloc_pgtable_page(int node); +void free_pgtable_page(void *vaddr); +struct intel_iommu *domain_get_iommu(struct dmar_domain *domain); + #ifdef CONFIG_INTEL_IOMMU_SVM extern int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu); extern int intel_svm_free_pasid_tables(struct intel_iommu *iommu); -- cgit v1.2.3 From 85319dcc8955f8f31828dc8bafff29f6aa011d93 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 14 Jul 2018 15:46:58 +0800 Subject: iommu/vt-d: Add for_each_device_domain() helper This adds a helper named for_each_device_domain() to iterate over the elements in device_domain_list and invoke a callback against each element. This allows to search the device_domain list in other source files. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Liu Yi L Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 2e1fbde020ca..4fd4c6fee93e 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -520,6 +520,8 @@ struct dmar_domain *get_valid_domain_for_dev(struct device *dev); void *alloc_pgtable_page(int node); void free_pgtable_page(void *vaddr); struct intel_iommu *domain_get_iommu(struct dmar_domain *domain); +int for_each_device_domain(int (*fn)(struct device_domain_info *info, + void *data), void *data); #ifdef CONFIG_INTEL_IOMMU_SVM extern int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu); -- cgit v1.2.3 From cc580e41260dbf1a46269235f1f2b572137d9d03 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 14 Jul 2018 15:46:59 +0800 Subject: iommu/vt-d: Per PCI device pasid table interfaces This patch adds the interfaces for per PCI device pasid table management. Currently we allocate one pasid table for all PCI devices under the scope of an IOMMU. It's insecure in some cases where multiple devices under one single IOMMU unit support PASID features. With per PCI device pasid table, we can achieve finer protection and isolation granularity. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Liu Yi L Suggested-by: Ashok Raj Signed-off-by: Lu Baolu Reviewed-by: Liu Yi L Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4fd4c6fee93e..e7901d402337 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -476,6 +476,7 @@ struct intel_iommu { struct device_domain_info { struct list_head link; /* link to domain siblings */ struct list_head global; /* link to global list */ + struct list_head table; /* link to pasid table */ u8 bus; /* PCI bus number */ u8 devfn; /* PCI devfn number */ u16 pfsid; /* SRIOV physical function source ID */ @@ -489,6 +490,7 @@ struct device_domain_info { struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ struct intel_iommu *iommu; /* IOMMU used by this device */ struct dmar_domain *domain; /* pointer to domain */ + struct pasid_table *pasid_table; /* pasid table */ }; static inline void __iommu_flush_cache( -- cgit v1.2.3 From d9737953d85131436b09668b5e8d3389c37c1f28 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 14 Jul 2018 15:47:02 +0800 Subject: iommu/vt-d: Remove the obsolete per iommu pasid tables The obsolete per iommu pasid tables are no longer used. Hence, clean up them. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Liu Yi L Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index e7901d402337..3c43882d3b77 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -453,7 +453,6 @@ struct intel_iommu { * devices away to userspace processes (e.g. for DPDK) and don't * want to trust that userspace will use *only* the PASID it was * told to. But while it's all driver-arbitrated, we're fine. */ - struct pasid_entry *pasid_table; struct pasid_state_entry *pasid_state_table; struct page_req_dsc *prq; unsigned char prq_name[16]; /* Name for PRQ interrupt */ @@ -526,8 +525,8 @@ int for_each_device_domain(int (*fn)(struct device_domain_info *info, void *data), void *data); #ifdef CONFIG_INTEL_IOMMU_SVM -extern int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu); -extern int intel_svm_free_pasid_tables(struct intel_iommu *iommu); +int intel_svm_init(struct intel_iommu *iommu); +int intel_svm_exit(struct intel_iommu *iommu); extern int intel_svm_enable_prq(struct intel_iommu *iommu); extern int intel_svm_finish_prq(struct intel_iommu *iommu); -- cgit v1.2.3 From 226ab561075f6f8f3cd5f7b3b7544f3997aab51f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 13 Jul 2018 21:49:34 -0700 Subject: device-dax: Convert to vmf_insert_mixed and vm_fault_t Use new return type vm_fault_t for fault and huge_fault handler. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. Commit 1c8f422059ae ("mm: change return type to vm_fault_t") Previously vm_insert_mixed() returned an error code which driver mapped into VM_FAULT_* type. The new function vmf_insert_mixed() will replace this inefficiency by returning VM_FAULT_* type. Signed-off-by: Souptick Joarder Reviewed-by: Matthew Wilcox Reviewed-by: Ross Zwisler Signed-off-by: Dan Williams Signed-off-by: Dave Jiang --- include/linux/huge_mm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index a8a126259bc4..d3bbf6bea9e9 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -3,6 +3,7 @@ #define _LINUX_HUGE_MM_H #include +#include #include /* only for vma_is_dax() */ @@ -46,9 +47,9 @@ extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); -int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, pfn_t pfn, bool write); -int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, pfn_t pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, -- cgit v1.2.3 From eef5ba1aa148ca5e6deb1e0aa1de797fa4e12cb7 Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Wed, 20 Jun 2018 10:51:53 +0200 Subject: i2c: smbus: add unlocked __i2c_smbus_xfer variant Removes all locking from i2c_smbus_xfer and renames it to __i2c_smbus_xfer, then adds a new i2c_smbus_xfer function that simply grabs the lock while calling the unlocked variant. This is not perfectly equivalent, since i2c_smbus_xfer was callable from atomic/irq context if you happened to end up emulating SMBus with an I2C transfer, and that is no longer the case with this patch. It is unknown (to me) if anything depends on that quirk, but it seems fragile enough to simply break those cases and require them to call i2c_transfer directly instead. While at it, for consistency rename the 2nd to last argument (size) of the i2c_smbus_xfer declaration to protocol and remove the surplus extern marker. Signed-off-by: Peter Rosin Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 254cd34eeae2..465afb092fa7 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -140,9 +140,14 @@ extern int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, and probably just as fast. Note that we use i2c_adapter here, because you do not need a specific smbus adapter to call this function. */ -extern s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, - unsigned short flags, char read_write, u8 command, - int size, union i2c_smbus_data *data); +s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, + unsigned short flags, char read_write, u8 command, + int protocol, union i2c_smbus_data *data); + +/* Unlocked flavor */ +s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, + unsigned short flags, char read_write, u8 command, + int protocol, union i2c_smbus_data *data); /* Now follow the 'nice' access routines. These also document the calling conventions of i2c_smbus_xfer. */ -- cgit v1.2.3 From 488dee96bb62f0b3d9e678cf42574034d5b033a5 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 20 Jul 2018 21:56:47 +0000 Subject: kernfs: allow creating kernfs objects with arbitrary uid/gid This change allows creating kernfs files and directories with arbitrary uid/gid instead of always using GLOBAL_ROOT_UID/GID by extending kernfs_create_dir_ns() and kernfs_create_file_ns() with uid/gid arguments. The "simple" kernfs_create_file() and kernfs_create_dir() are left alone and always create objects belonging to the global root. When creating symlinks ownership (uid/gid) is taken from the target kernfs object. Co-Developed-by: Tyler Hicks Signed-off-by: Dmitry Torokhov Signed-off-by: Tyler Hicks Signed-off-by: David S. Miller --- include/linux/kernfs.h | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index ab25c8b6d9e3..814643f7ee52 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -15,6 +15,7 @@ #include #include #include +#include #include struct file; @@ -325,12 +326,14 @@ void kernfs_destroy_root(struct kernfs_root *root); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, + kuid_t uid, kgid_t gid, void *priv, const void *ns); struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, const char *name); struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, - const char *name, - umode_t mode, loff_t size, + const char *name, umode_t mode, + kuid_t uid, kgid_t gid, + loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key); @@ -415,12 +418,14 @@ static inline void kernfs_destroy_root(struct kernfs_root *root) { } static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, - umode_t mode, void *priv, const void *ns) + umode_t mode, kuid_t uid, kgid_t gid, + void *priv, const void *ns) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * __kernfs_create_file(struct kernfs_node *parent, const char *name, - umode_t mode, loff_t size, const struct kernfs_ops *ops, + umode_t mode, kuid_t uid, kgid_t gid, + loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key) { return ERR_PTR(-ENOSYS); } @@ -498,12 +503,15 @@ static inline struct kernfs_node * kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode, void *priv) { - return kernfs_create_dir_ns(parent, name, mode, priv, NULL); + return kernfs_create_dir_ns(parent, name, mode, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + priv, NULL); } static inline struct kernfs_node * kernfs_create_file_ns(struct kernfs_node *parent, const char *name, - umode_t mode, loff_t size, const struct kernfs_ops *ops, + umode_t mode, kuid_t uid, kgid_t gid, + loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns) { struct lock_class_key *key = NULL; @@ -511,15 +519,17 @@ kernfs_create_file_ns(struct kernfs_node *parent, const char *name, #ifdef CONFIG_DEBUG_LOCK_ALLOC key = (struct lock_class_key *)&ops->lockdep_key; #endif - return __kernfs_create_file(parent, name, mode, size, ops, priv, ns, - key); + return __kernfs_create_file(parent, name, mode, uid, gid, + size, ops, priv, ns, key); } static inline struct kernfs_node * kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, loff_t size, const struct kernfs_ops *ops, void *priv) { - return kernfs_create_file_ns(parent, name, mode, size, ops, priv, NULL); + return kernfs_create_file_ns(parent, name, mode, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + size, ops, priv, NULL); } static inline int kernfs_remove_by_name(struct kernfs_node *parent, -- cgit v1.2.3 From 5f81880d5204ee2388fd9a75bb850ccd526885b7 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 20 Jul 2018 21:56:48 +0000 Subject: sysfs, kobject: allow creating kobject belonging to arbitrary users Normally kobjects and their sysfs representation belong to global root, however it is not necessarily the case for objects in separate namespaces. For example, objects in separate network namespace logically belong to the container's root and not global root. This change lays groundwork for allowing network namespace objects ownership to be transferred to container's root user by defining get_ownership() callback in ktype structure and using it in sysfs code to retrieve desired uid/gid when creating sysfs objects for given kobject. Co-Developed-by: Tyler Hicks Signed-off-by: Dmitry Torokhov Signed-off-by: Tyler Hicks Signed-off-by: David S. Miller --- include/linux/kobject.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 7f6f93c3df9c..b49ff230beba 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -26,6 +26,7 @@ #include #include #include +#include #define UEVENT_HELPER_PATH_LEN 256 #define UEVENT_NUM_ENVP 32 /* number of env pointers */ @@ -114,6 +115,8 @@ extern struct kobject * __must_check kobject_get_unless_zero( extern void kobject_put(struct kobject *kobj); extern const void *kobject_namespace(struct kobject *kobj); +extern void kobject_get_ownership(struct kobject *kobj, + kuid_t *uid, kgid_t *gid); extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); struct kobj_type { @@ -122,6 +125,7 @@ struct kobj_type { struct attribute **default_attrs; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); + void (*get_ownership)(struct kobject *kobj, kuid_t *uid, kgid_t *gid); }; struct kobj_uevent_env { -- cgit v1.2.3 From 9944e894c1266dc8515c82d1ff752d681215526b Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 20 Jul 2018 21:56:50 +0000 Subject: driver core: set up ownership of class devices in sysfs Plumb in get_ownership() callback for devices belonging to a class so that they can be created with uid/gid different from global root. This will allow network devices in a container to belong to container's root and not global root. Signed-off-by: Dmitry Torokhov Reviewed-by: Tyler Hicks Signed-off-by: David S. Miller --- include/linux/device.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 055a69dbcd18..fe6ccb6dc119 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -384,6 +384,9 @@ int subsys_virtual_register(struct bus_type *subsys, * @shutdown_pre: Called at shut-down time before driver shutdown. * @ns_type: Callbacks so sysfs can detemine namespaces. * @namespace: Namespace of the device belongs to this class. + * @get_ownership: Allows class to specify uid/gid of the sysfs directories + * for the devices belonging to the class. Usually tied to + * device's namespace. * @pm: The default device power management operations of this class. * @p: The private data of the driver core, no one other than the * driver core can touch this. @@ -413,6 +416,8 @@ struct class { const struct kobj_ns_type_operations *ns_type; const void *(*namespace)(struct device *dev); + void (*get_ownership)(struct device *dev, kuid_t *uid, kgid_t *gid); + const struct dev_pm_ops *pm; struct subsys_private *p; -- cgit v1.2.3 From 9bfdc2611d417be453c3deb7a7ef2ffc718febfa Mon Sep 17 00:00:00 2001 From: Adam Borowski Date: Wed, 18 Jul 2018 04:10:44 +0200 Subject: vt: selection: take screen contents from uniscr if available This preserves whatever was written even if we can't currently display the given glyph. Mouse paste won't corrupt any character of wcwidth() == 1 anymore. Note that for now uniscr doesn't get allocated until something reads /dev/vcsuN for that console, making this code dormant for most users. Signed-off-by: Adam Borowski Acked-by: Nicolas Pitre Signed-off-by: Greg Kroah-Hartman --- include/linux/selection.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/selection.h b/include/linux/selection.h index 067d2e99c79f..a8f5b97b216f 100644 --- a/include/linux/selection.h +++ b/include/linux/selection.h @@ -32,6 +32,7 @@ extern unsigned char default_blu[]; extern unsigned short *screen_pos(struct vc_data *vc, int w_offset, int viewed); extern u16 screen_glyph(struct vc_data *vc, int offset); +extern u32 screen_glyph_unicode(struct vc_data *vc, int offset); extern void complement_pos(struct vc_data *vc, int offset); extern void invert_screen(struct vc_data *vc, int offset, int count, int shift); -- cgit v1.2.3 From f4c6fbc96eb187d6432fbba1f9c0c2db598cdf29 Mon Sep 17 00:00:00 2001 From: Adam Borowski Date: Wed, 18 Jul 2018 05:03:22 +0200 Subject: vt: drop unused struct vt_struct Hasn't been ever used within historic (ie, git) times. Signed-off-by: Adam Borowski Signed-off-by: Greg Kroah-Hartman --- include/linux/console_struct.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 2c8d3239899b..fea64f2692a0 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -17,7 +17,6 @@ #include #include -struct vt_struct; struct uni_pagedir; struct uni_screen; @@ -150,7 +149,7 @@ struct vc { struct vc_data *d; struct work_struct SAK_work; - /* might add scrmem, vt_struct, kbd at some time, + /* might add scrmem, kbd at some time, to have everything in one place - the disadvantage would be that vc_cons etc can no longer be static */ }; -- cgit v1.2.3 From a2dca217dae29c4ff6420e8c78d56b3f61ae0797 Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Mon, 16 Jul 2018 15:06:18 +0200 Subject: KVM: arm/arm64: vgic: Define GICD_IIDR fields for GICv2 and GIv3 Instead of hardcoding the shifts and masks in the GICD_IIDR register emulation, let's add the definition of these fields to the GIC header files and use them. This will make things more obvious when we're going to bump the revision in the IIDR when we'll make guest-visible changes to the implementation. Reviewed-by: Andrew Jones Signed-off-by: Christoffer Dall Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 10 ++++++++++ include/linux/irqchip/arm-gic.h | 10 ++++++++++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index cbb872c1b607..b22f9dfa61af 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -61,6 +61,16 @@ #define GICD_CTLR_ENABLE_G1A (1U << 1) #define GICD_CTLR_ENABLE_G1 (1U << 0) +#define GICD_IIDR_IMPLEMENTER_SHIFT 0 +#define GICD_IIDR_IMPLEMENTER_MASK (0xfff << GICD_IIDR_IMPLEMENTER_SHIFT) +#define GICD_IIDR_REVISION_SHIFT 12 +#define GICD_IIDR_REVISION_MASK (0xf << GICD_IIDR_REVISION_SHIFT) +#define GICD_IIDR_VARIANT_SHIFT 16 +#define GICD_IIDR_VARIANT_MASK (0xf << GICD_IIDR_VARIANT_SHIFT) +#define GICD_IIDR_PRODUCT_ID_SHIFT 24 +#define GICD_IIDR_PRODUCT_ID_MASK (0xff << GICD_IIDR_PRODUCT_ID_SHIFT) + + /* * In systems with a single security state (what we emulate in KVM) * the meaning of the interrupt group enable bits is slightly different diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 68d8b1f73682..484f5bfa9f3d 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -71,6 +71,16 @@ (GICD_INT_DEF_PRI << 8) |\ GICD_INT_DEF_PRI) +#define GICD_IIDR_IMPLEMENTER_SHIFT 0 +#define GICD_IIDR_IMPLEMENTER_MASK (0xfff << GICD_IIDR_IMPLEMENTER_SHIFT) +#define GICD_IIDR_REVISION_SHIFT 12 +#define GICD_IIDR_REVISION_MASK (0xf << GICD_IIDR_REVISION_SHIFT) +#define GICD_IIDR_VARIANT_SHIFT 16 +#define GICD_IIDR_VARIANT_MASK (0xf << GICD_IIDR_VARIANT_SHIFT) +#define GICD_IIDR_PRODUCT_ID_SHIFT 24 +#define GICD_IIDR_PRODUCT_ID_MASK (0xff << GICD_IIDR_PRODUCT_ID_SHIFT) + + #define GICH_HCR 0x0 #define GICH_VTR 0x4 #define GICH_VMCR 0x8 -- cgit v1.2.3 From 87322099052b6a534cecd3d303fc097d4560b7d0 Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Mon, 16 Jul 2018 15:06:22 +0200 Subject: KVM: arm/arm64: vgic: Signal IRQs using their configured group Now when we have a group configuration on the struct IRQ, use this state when populating the LR and signaling interrupts as either group 0 or group 1 to the VM. Depending on the model of the emulated GIC, and the guest's configuration of the VMCR, interrupts may be signaled as IRQs or FIQs to the VM. Reviewed-by: Andrew Jones Signed-off-by: Christoffer Dall Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 484f5bfa9f3d..6c4aaf04046c 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -104,6 +104,7 @@ #define GICH_LR_PENDING_BIT (1 << 28) #define GICH_LR_ACTIVE_BIT (1 << 29) #define GICH_LR_EOI (1 << 19) +#define GICH_LR_GROUP1 (1 << 30) #define GICH_LR_HW (1 << 31) #define GICH_VMCR_ENABLE_GRP0_SHIFT 0 -- cgit v1.2.3 From 1fb53567a3633740aac8761eb7023dc5671f0edb Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 5 May 2017 13:45:14 -0500 Subject: pids: Move task_pid_type into sched/signal.h The function is general and inline so there is no need to hide it inside of exit.c Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 113d1ad1ced7..d8ef0a3d2e7e 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -556,6 +556,14 @@ extern bool current_is_single_threaded(void); typedef int (*proc_visitor)(struct task_struct *p, void *data); void walk_process_tree(struct task_struct *top, proc_visitor, void *); +static inline +struct pid *task_pid_type(struct task_struct *task, enum pid_type type) +{ + if (type != PIDTYPE_PID) + task = task->group_leader; + return task->pids[type].pid; +} + static inline int get_nr_threads(struct task_struct *tsk) { return tsk->signal->nr_threads; -- cgit v1.2.3 From 7a36094d61bfe9843de5484ff0140227983ac5d5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Sep 2017 12:45:33 -0500 Subject: pids: Compute task_tgid using signal->leader_pid The cost is the the same and this removes the need to worry about complications that come from de_thread and group_leader changing. __task_pid_nr_ns has been updated to take advantage of this change. Signed-off-by: "Eric W. Biederman" --- include/linux/sched.h | 5 ----- include/linux/sched/signal.h | 5 +++++ 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 87bf02d93a27..a461ff89a3af 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1202,11 +1202,6 @@ static inline struct pid *task_pid(struct task_struct *task) return task->pids[PIDTYPE_PID].pid; } -static inline struct pid *task_tgid(struct task_struct *task) -{ - return task->group_leader->pids[PIDTYPE_PID].pid; -} - /* * Without tasklist or RCU lock it is not safe to dereference * the result of task_pgrp/task_session even if task == current, diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index d8ef0a3d2e7e..b95a272c1ab5 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -564,6 +564,11 @@ struct pid *task_pid_type(struct task_struct *task, enum pid_type type) return task->pids[type].pid; } +static inline struct pid *task_tgid(struct task_struct *task) +{ + return task->signal->leader_pid; +} + static inline int get_nr_threads(struct task_struct *tsk) { return tsk->signal->nr_threads; -- cgit v1.2.3 From 2c4704756cab7cfa031ada4dab361562f0e357c0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Sep 2017 13:06:43 -0500 Subject: pids: Move the pgrp and session pid pointers from task_struct to signal_struct To access these fields the code always has to go to group leader so going to signal struct is no loss and is actually a fundamental simplification. This saves a little bit of memory by only allocating the pid pointer array once instead of once for every thread, and even better this removes a few potential races caused by the fact that group_leader can be changed by de_thread, while signal_struct can not. Signed-off-by: "Eric W. Biederman" --- include/linux/init_task.h | 9 --------- include/linux/pid.h | 8 +------- include/linux/sched.h | 22 ++++------------------ include/linux/sched/signal.h | 26 +++++++++++++++++++++++--- 4 files changed, 28 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index a454b8aeb938..a7083a45a26c 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -46,15 +46,6 @@ extern struct cred init_cred; #define INIT_CPU_TIMERS(s) #endif -#define INIT_PID_LINK(type) \ -{ \ - .node = { \ - .next = NULL, \ - .pprev = NULL, \ - }, \ - .pid = &init_struct_pid, \ -} - #define INIT_TASK_COMM "swapper" /* Attach to the init_task data structure for proper alignment */ diff --git a/include/linux/pid.h b/include/linux/pid.h index 7633d55d9a24..3d4c504dcc8c 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -67,12 +67,6 @@ struct pid extern struct pid init_struct_pid; -struct pid_link -{ - struct hlist_node node; - struct pid *pid; -}; - static inline struct pid *get_pid(struct pid *pid) { if (pid) @@ -177,7 +171,7 @@ pid_t pid_vnr(struct pid *pid); do { \ if ((pid) != NULL) \ hlist_for_each_entry_rcu((task), \ - &(pid)->tasks[type], pids[type].node) { + &(pid)->tasks[type], pid_links[type]) { /* * Both old and new leaders may be attached to diff --git a/include/linux/sched.h b/include/linux/sched.h index a461ff89a3af..445bdf5b1f64 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -775,7 +775,8 @@ struct task_struct { struct list_head ptrace_entry; /* PID/PID hash table linkage. */ - struct pid_link pids[PIDTYPE_MAX]; + struct pid *thread_pid; + struct hlist_node pid_links[PIDTYPE_MAX]; struct list_head thread_group; struct list_head thread_node; @@ -1199,22 +1200,7 @@ struct task_struct { static inline struct pid *task_pid(struct task_struct *task) { - return task->pids[PIDTYPE_PID].pid; -} - -/* - * Without tasklist or RCU lock it is not safe to dereference - * the result of task_pgrp/task_session even if task == current, - * we can race with another thread doing sys_setsid/sys_setpgid. - */ -static inline struct pid *task_pgrp(struct task_struct *task) -{ - return task->group_leader->pids[PIDTYPE_PGID].pid; -} - -static inline struct pid *task_session(struct task_struct *task) -{ - return task->group_leader->pids[PIDTYPE_SID].pid; + return task->thread_pid; } /* @@ -1263,7 +1249,7 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk) */ static inline int pid_alive(const struct task_struct *p) { - return p->pids[PIDTYPE_PID].pid != NULL; + return p->thread_pid != NULL; } static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index b95a272c1ab5..2dcded16eb1e 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -146,7 +146,9 @@ struct signal_struct { #endif + /* PID/PID hash table linkage. */ struct pid *leader_pid; + struct pid *pids[PIDTYPE_MAX]; #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; @@ -559,9 +561,12 @@ void walk_process_tree(struct task_struct *top, proc_visitor, void *); static inline struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { - if (type != PIDTYPE_PID) - task = task->group_leader; - return task->pids[type].pid; + struct pid *pid; + if (type == PIDTYPE_PID) + pid = task_pid(task); + else + pid = task->signal->pids[type]; + return pid; } static inline struct pid *task_tgid(struct task_struct *task) @@ -569,6 +574,21 @@ static inline struct pid *task_tgid(struct task_struct *task) return task->signal->leader_pid; } +/* + * Without tasklist or RCU lock it is not safe to dereference + * the result of task_pgrp/task_session even if task == current, + * we can race with another thread doing sys_setsid/sys_setpgid. + */ +static inline struct pid *task_pgrp(struct task_struct *task) +{ + return task->signal->pids[PIDTYPE_PGID]; +} + +static inline struct pid *task_session(struct task_struct *task) +{ + return task->signal->pids[PIDTYPE_SID]; +} + static inline int get_nr_threads(struct task_struct *tsk) { return tsk->signal->nr_threads; -- cgit v1.2.3 From 6883f81aac6f44e7df70a6af189b3689ff52cbfb Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 4 Jun 2017 04:32:13 -0500 Subject: pid: Implement PIDTYPE_TGID Everywhere except in the pid array we distinguish between a tasks pid and a tasks tgid (thread group id). Even in the enumeration we want that distinction sometimes so we have added __PIDTYPE_TGID. With leader_pid we almost have an implementation of PIDTYPE_TGID in struct signal_struct. Add PIDTYPE_TGID as a first class member of the pid_type enumeration and into the pids array. Then remove the __PIDTYPE_TGID special case and the leader_pid in signal_struct. The net size increase is just an extra pointer added to struct pid and an extra pair of pointers of an hlist_node added to task_struct. The effect on code maintenance is the removal of a number of special cases today and the potential to remove many more special cases as PIDTYPE_TGID gets used to it's fullest. The long term potential is allowing zombie thread group leaders to exit, which will remove a lot more special cases in the code. Signed-off-by: "Eric W. Biederman" --- include/linux/pid.h | 3 +-- include/linux/sched.h | 4 ++-- include/linux/sched/signal.h | 5 ++--- 3 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 3d4c504dcc8c..14a9a39da9c7 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -7,11 +7,10 @@ enum pid_type { PIDTYPE_PID, + PIDTYPE_TGID, PIDTYPE_PGID, PIDTYPE_SID, PIDTYPE_MAX, - /* only valid to __task_pid_nr_ns() */ - __PIDTYPE_TGID }; /* diff --git a/include/linux/sched.h b/include/linux/sched.h index 445bdf5b1f64..06b4e3bda93a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1275,12 +1275,12 @@ static inline pid_t task_session_vnr(struct task_struct *tsk) static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { - return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, ns); + return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns); } static inline pid_t task_tgid_vnr(struct task_struct *tsk) { - return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, NULL); + return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL); } static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 2dcded16eb1e..ee30a5ba475f 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -147,7 +147,6 @@ struct signal_struct { #endif /* PID/PID hash table linkage. */ - struct pid *leader_pid; struct pid *pids[PIDTYPE_MAX]; #ifdef CONFIG_NO_HZ_FULL @@ -571,7 +570,7 @@ struct pid *task_pid_type(struct task_struct *task, enum pid_type type) static inline struct pid *task_tgid(struct task_struct *task) { - return task->signal->leader_pid; + return task->signal->pids[PIDTYPE_TGID]; } /* @@ -607,7 +606,7 @@ static inline bool thread_group_leader(struct task_struct *p) */ static inline bool has_group_leader_pid(struct task_struct *p) { - return task_pid(p) == p->signal->leader_pid; + return task_pid(p) == task_tgid(p); } static inline -- cgit v1.2.3 From 24122c7f4969adeeaeca3fb1656a31569e9aa59b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 20 Jul 2018 14:30:23 -0500 Subject: signal: Pass pid and pid type into send_sigqueue Make the code more maintainable by performing more of the signal related work in send_sigqueue. A quick inspection of do_timer_create will show that this code path does not lookup a thread group by a thread's pid. Making it safe to find the task pointed to by it_pid with "pid_task(it_pid, type)"; This supports the changes needed in fork to tell if a signal was sent to a single process or a group of processes. Having the pid to task transition in signal.c will also make it easier to sort out races with de_thread and and the thread group leader exiting when it comes time to address that. Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index ee30a5ba475f..94558ffa82ab 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -330,7 +330,7 @@ extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); -extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group); +extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline int restart_syscall(void) -- cgit v1.2.3 From 0102498083d58d8b17759642c602b525215e1a54 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 13 Jul 2018 18:40:57 -0500 Subject: signal: Pass pid type into group_send_sig_info This passes the information we already have at the call sight into group_send_sig_info. Ultimatelly allowing for to better handle signals sent to a group of processes. Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 3c5200137b24..d8f2bf3d41e6 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -254,11 +254,13 @@ static inline int valid_signal(unsigned long sig) struct timespec; struct pt_regs; +enum pid_type; extern int next_signal(struct sigpending *pending, sigset_t *mask); extern int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, bool group); -extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p); +extern int group_send_sig_info(int sig, struct siginfo *info, + struct task_struct *p, enum pid_type type); extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); -- cgit v1.2.3 From 40b3b02535621027f56d248139e0e467573c3098 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 21 Jul 2018 10:45:15 -0500 Subject: signal: Pass pid type into do_send_sig_info This passes the information we already have at the call sight into do_send_sig_info. Ultimately allowing for better handling of signals sent to a group of processes during fork. Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index d8f2bf3d41e6..fe125b0335f7 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -258,7 +258,7 @@ enum pid_type; extern int next_signal(struct sigpending *pending, sigset_t *mask); extern int do_send_sig_info(int sig, struct siginfo *info, - struct task_struct *p, bool group); + struct task_struct *p, enum pid_type type); extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, enum pid_type type); extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); -- cgit v1.2.3 From a3134fb09e0bc5bee76e13bf863173b86f21cf87 Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Wed, 23 May 2018 17:35:21 -0700 Subject: drivers: soc: Add LLCC driver LLCC (Last Level Cache Controller) provides additional cache memory in the system. LLCC is partitioned into multiple slices and each slice gets its own priority, size, ID and other config parameters. LLCC driver programs these parameters for each slice. Clients that are assigned to use LLCC need to get information such size & ID of the slice they get and activate or deactivate the slice as needed. LLCC driver provides API for the clients to perform these operations. Signed-off-by: Channagoud Kadabi Signed-off-by: Rishabh Bhatnagar Reviewed-by: Evan Green Reviewed-by: Rob Herring Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/soc/qcom/llcc-qcom.h | 180 +++++++++++++++++++++++++++++++++++++ 1 file changed, 180 insertions(+) create mode 100644 include/linux/soc/qcom/llcc-qcom.h (limited to 'include/linux') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h new file mode 100644 index 000000000000..7e3b9c605ab2 --- /dev/null +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -0,0 +1,180 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. + * + */ + +#include +#ifndef __LLCC_QCOM__ +#define __LLCC_QCOM__ + +#define LLCC_CPUSS 1 +#define LLCC_VIDSC0 2 +#define LLCC_VIDSC1 3 +#define LLCC_ROTATOR 4 +#define LLCC_VOICE 5 +#define LLCC_AUDIO 6 +#define LLCC_MDMHPGRW 7 +#define LLCC_MDM 8 +#define LLCC_CMPT 10 +#define LLCC_GPUHTW 11 +#define LLCC_GPU 12 +#define LLCC_MMUHWT 13 +#define LLCC_CMPTDMA 15 +#define LLCC_DISP 16 +#define LLCC_VIDFW 17 +#define LLCC_MDMHPFX 20 +#define LLCC_MDMPNG 21 +#define LLCC_AUDHW 22 + +/** + * llcc_slice_desc - Cache slice descriptor + * @slice_id: llcc slice id + * @slice_size: Size allocated for the llcc slice + */ +struct llcc_slice_desc { + u32 slice_id; + size_t slice_size; +}; + +/** + * llcc_slice_config - Data associated with the llcc slice + * @usecase_id: usecase id for which the llcc slice is used + * @slice_id: llcc slice id assigned to each slice + * @max_cap: maximum capacity of the llcc slice + * @priority: priority of the llcc slice + * @fixed_size: whether the llcc slice can grow beyond its size + * @bonus_ways: bonus ways associated with llcc slice + * @res_ways: reserved ways associated with llcc slice + * @cache_mode: mode of the llcc slice + * @probe_target_ways: Probe only reserved and bonus ways on a cache miss + * @dis_cap_alloc: Disable capacity based allocation + * @retain_on_pc: Retain through power collapse + * @activate_on_init: activate the slice on init + */ +struct llcc_slice_config { + u32 usecase_id; + u32 slice_id; + u32 max_cap; + u32 priority; + bool fixed_size; + u32 bonus_ways; + u32 res_ways; + u32 cache_mode; + u32 probe_target_ways; + bool dis_cap_alloc; + bool retain_on_pc; + bool activate_on_init; +}; + +/** + * llcc_drv_data - Data associated with the llcc driver + * @regmap: regmap associated with the llcc device + * @cfg: pointer to the data structure for slice configuration + * @lock: mutex associated with each slice + * @cfg_size: size of the config data table + * @max_slices: max slices as read from device tree + * @bcast_off: Offset of the broadcast bank + * @num_banks: Number of llcc banks + * @bitmap: Bit map to track the active slice ids + * @offsets: Pointer to the bank offsets array + */ +struct llcc_drv_data { + struct regmap *regmap; + const struct llcc_slice_config *cfg; + struct mutex lock; + u32 cfg_size; + u32 max_slices; + u32 bcast_off; + u32 num_banks; + unsigned long *bitmap; + u32 *offsets; +}; + +#if IS_ENABLED(CONFIG_QCOM_LLCC) +/** + * llcc_slice_getd - get llcc slice descriptor + * @uid: usecase_id of the client + */ +struct llcc_slice_desc *llcc_slice_getd(u32 uid); + +/** + * llcc_slice_putd - llcc slice descritpor + * @desc: Pointer to llcc slice descriptor + */ +void llcc_slice_putd(struct llcc_slice_desc *desc); + +/** + * llcc_get_slice_id - get slice id + * @desc: Pointer to llcc slice descriptor + */ +int llcc_get_slice_id(struct llcc_slice_desc *desc); + +/** + * llcc_get_slice_size - llcc slice size + * @desc: Pointer to llcc slice descriptor + */ +size_t llcc_get_slice_size(struct llcc_slice_desc *desc); + +/** + * llcc_slice_activate - Activate the llcc slice + * @desc: Pointer to llcc slice descriptor + */ +int llcc_slice_activate(struct llcc_slice_desc *desc); + +/** + * llcc_slice_deactivate - Deactivate the llcc slice + * @desc: Pointer to llcc slice descriptor + */ +int llcc_slice_deactivate(struct llcc_slice_desc *desc); + +/** + * qcom_llcc_probe - program the sct table + * @pdev: platform device pointer + * @table: soc sct table + * @sz: Size of the config table + */ +int qcom_llcc_probe(struct platform_device *pdev, + const struct llcc_slice_config *table, u32 sz); +#else +static inline struct llcc_slice_desc *llcc_slice_getd(u32 uid) +{ + return NULL; +} + +static inline void llcc_slice_putd(struct llcc_slice_desc *desc) +{ + +}; + +static inline int llcc_get_slice_id(struct llcc_slice_desc *desc) +{ + return -EINVAL; +} + +static inline size_t llcc_get_slice_size(struct llcc_slice_desc *desc) +{ + return 0; +} +static inline int llcc_slice_activate(struct llcc_slice_desc *desc) +{ + return -EINVAL; +} + +static inline int llcc_slice_deactivate(struct llcc_slice_desc *desc) +{ + return -EINVAL; +} +static inline int qcom_llcc_probe(struct platform_device *pdev, + const struct llcc_slice_config *table, u32 sz) +{ + return -ENODEV; +} + +static inline int qcom_llcc_remove(struct platform_device *pdev) +{ + return -ENODEV; +} +#endif + +#endif -- cgit v1.2.3 From a0b1561f846191a1967e8f5a26d8ef59c1b9162a Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Tue, 12 Jun 2018 15:23:13 +0200 Subject: firmware: qcom: scm: add a dummy qcom_scm_assign_mem() Add a dummy qcom_scm_assign_mem() to enable building drivers when CONFIG_COMPILE_TEST=y && CONFIG_QCOM_SCM=n. All other qcom_scm_* functions already have a dummy version. Signed-off-by: Niklas Cassel Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/qcom_scm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index b401b962afff..5d65521260b3 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -87,6 +87,10 @@ static inline int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, static inline int qcom_scm_pas_auth_and_reset(u32 peripheral) { return -ENODEV; } static inline int qcom_scm_pas_shutdown(u32 peripheral) { return -ENODEV; } +static inline int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, + unsigned int *src, + struct qcom_scm_vmperm *newvm, + int dest_cnt) { return -ENODEV; } static inline void qcom_scm_cpu_power_down(u32 flags) {} static inline u32 qcom_scm_get_version(void) { return 0; } static inline u32 -- cgit v1.2.3 From 3928d4f5ee37cdc523894f6e549e6aae521d8980 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 21 Jul 2018 13:48:51 -0700 Subject: mm: use helper functions for allocating and freeing vm_area structs The vm_area_struct is one of the most fundamental memory management objects, but the management of it is entirely open-coded evertwhere, ranging from allocation and freeing (using kmem_cache_[z]alloc and kmem_cache_free) to initializing all the fields. We want to unify this in order to end up having some unified initialization of the vmas, and the first step to this is to at least have basic allocation functions. Right now those functions are literally just wrappers around the kmem_cache_*() calls. This is a purely mechanical conversion: # new vma: kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL) -> vm_area_alloc() # copy old vma kmem_cache_alloc(vm_area_cachep, GFP_KERNEL) -> vm_area_dup(old) # free vma kmem_cache_free(vm_area_cachep, vma) -> vm_area_free(vma) to the point where the old vma passed in to the vm_area_dup() function isn't even used yet (because I've left all the old manual initialization alone). Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3982c83fdcbf..de2fd86c6154 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -155,7 +155,9 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, * mmap() functions). */ -extern struct kmem_cache *vm_area_cachep; +struct vm_area_struct *vm_area_alloc(void); +struct vm_area_struct *vm_area_dup(struct vm_area_struct *); +void vm_area_free(struct vm_area_struct *); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; -- cgit v1.2.3 From 490fc053865c9cc40f1085ef8a5504f5341f79d2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 21 Jul 2018 15:24:03 -0700 Subject: mm: make vm_area_alloc() initialize core fields Like vm_area_dup(), it initializes the anon_vma_chain head, and the basic mm pointer. The rest of the fields end up being different for different users, although the plan is to also initialize the 'vm_ops' field to a dummy entry. Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index de2fd86c6154..d3a3842316b8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -155,7 +155,7 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, * mmap() functions). */ -struct vm_area_struct *vm_area_alloc(void); +struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); -- cgit v1.2.3 From f95de8aa9f824d96421cb7ca81552b4ad8768a31 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 19 Jul 2018 15:56:59 +0800 Subject: bpfilter: Fix mismatch in function argument types Fix following warning: net/ipv4/bpfilter/sockopt.c:28:5: error: symbol 'bpfilter_ip_set_sockopt' redeclared with different type net/ipv4/bpfilter/sockopt.c:34:5: error: symbol 'bpfilter_ip_get_sockopt' redeclared with different type Signed-off-by: YueHaibing Acked-by: Martin KaFai Lau Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpfilter.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index 687b1760bb9f..f02cee0225d4 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -5,10 +5,10 @@ #include struct sock; -int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char *optval, +int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen); -int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char *optval, - int *optlen); +int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, + int __user *optlen); extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname, char __user *optval, unsigned int optlen, bool is_set); -- cgit v1.2.3 From c4db9c1e8c70bc60e392da8a485bcfb035d559c2 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Fri, 20 Jul 2018 10:47:23 +0900 Subject: efi: Deduplicate efi_open_volume() There's one ARM, one x86_32 and one x86_64 version of efi_open_volume() which can be folded into a single shared version by masking their differences with the efi_call_proto() macro introduced by commit: 3552fdf29f01 ("efi: Allow bitness-agnostic protocol calls"). To be able to dereference the device_handle attribute from the efi_loaded_image_t table in an arch- and bitness-agnostic manner, introduce the efi_table_attr() macro (which already exists for x86) to arm and arm64. No functional change intended. Signed-off-by: Lukas Wunner Signed-off-by: Ard Biesheuvel Cc: Andy Shevchenko Cc: Hans de Goede Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20180720014726.24031-7-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index e190652f5ef9..401e4b254e30 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -894,6 +894,16 @@ typedef struct _efi_file_handle { void *flush; } efi_file_handle_t; +typedef struct { + u64 revision; + u32 open_volume; +} efi_file_io_interface_32_t; + +typedef struct { + u64 revision; + u64 open_volume; +} efi_file_io_interface_64_t; + typedef struct _efi_file_io_interface { u64 revision; int (*open_volume)(struct _efi_file_io_interface *, -- cgit v1.2.3 From f88a333b44318643282b8acc92af90deda441f5e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 22 Jul 2018 15:07:11 +0100 Subject: alpha: fix osf_wait4() breakage kernel_wait4() expects a userland address for status - it's only rusage that goes as a kernel one (and needs a copyout afterwards) [ Also, fix the prototype of kernel_wait4() to have that __user annotation - Linus ] Fixes: 92ebce5ac55d ("osf_wait4: switch to kernel_wait4()") Cc: stable@kernel.org # v4.13+ Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/sched/task.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 5be31eb7b266..108ede99e533 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -75,7 +75,7 @@ extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -extern long kernel_wait4(pid_t, int *, int, struct rusage *); +extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); extern void free_task(struct task_struct *tsk); -- cgit v1.2.3 From d5e838275c80aeb96d4c0b81442a851dfef2e948 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 5 Jun 2018 13:21:26 +1000 Subject: devres: Add devm_of_iomap() There are still quite a few cases where a device might want to get to a different node of the device-tree, obtain the resources and map them. We have of_iomap() and of_io_request_and_map() but they both have shortcomings, such as not returning the size of the resource found (which can be useful) and not being "managed". This adds a devm_of_iomap() that provides all of these and should probably replace uses of the above in most drivers. Signed-off-by: Benjamin Herrenschmidt Reviewed-by: Linus Walleij Reviewed-by: Joel Stanley --- include/linux/device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 055a69dbcd18..6aa8d51eabe9 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -696,6 +696,10 @@ extern void devm_free_pages(struct device *dev, unsigned long addr); void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res); +void __iomem *devm_of_iomap(struct device *dev, + struct device_node *node, int index, + resource_size_t *size); + /* allows to add/remove a custom action to devres stack */ int devm_add_action(struct device *dev, void (*action)(void *), void *data); void devm_remove_action(struct device *dev, void (*action)(void *), void *data); -- cgit v1.2.3 From 40c6f9c28ef03f2f2c3ee58c2447a6e6b9a713f2 Mon Sep 17 00:00:00 2001 From: Revanth Rajashekar Date: Fri, 15 Jun 2018 12:39:27 -0600 Subject: nvme.h: resync with nvme-cli Added some feature ids present in nvme-cli but not kernel. Signed-off-by: Revanth Rajashekar Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 2950ce957656..80dfedcf0bf7 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -749,6 +749,11 @@ enum { NVME_FEAT_HOST_MEM_BUF = 0x0d, NVME_FEAT_TIMESTAMP = 0x0e, NVME_FEAT_KATO = 0x0f, + NVME_FEAT_HCTM = 0x10, + NVME_FEAT_NOPSC = 0x11, + NVME_FEAT_RRL = 0x12, + NVME_FEAT_PLM_CONFIG = 0x13, + NVME_FEAT_PLM_WINDOW = 0x14, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, -- cgit v1.2.3 From 1a8861f117608e269647fb09658ce77bd5899d42 Mon Sep 17 00:00:00 2001 From: "Daniel M. Lambea" Date: Tue, 17 Jul 2018 22:35:36 +0100 Subject: HID: cougar: make compare_device_paths reusable The function compare_device_paths from wacom_sys.c is generic and useful for other drivers. Move the function to hid-core and rename it as hid_compare_device_paths. Signed-off-by: Daniel M. Lambea Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 773bcb1d4044..938d9ba6d7cd 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -894,6 +894,8 @@ const struct hid_device_id *hid_match_id(const struct hid_device *hdev, const struct hid_device_id *id); const struct hid_device_id *hid_match_device(struct hid_device *hdev, struct hid_driver *hdrv); +bool hid_compare_device_paths(struct hid_device *hdev_a, + struct hid_device *hdev_b, char separator); s32 hid_snto32(__u32 value, unsigned n); __u32 hid_field_extract(const struct hid_device *hid, __u8 *report, unsigned offset, unsigned n); -- cgit v1.2.3 From 977d5ad39f3ea12ac0bd51d75020cea5ecdca235 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 17 Jul 2018 17:19:11 +0300 Subject: ACPI: Convert ACPI reference args to generic fwnode reference args Convert all users of struct acpi_reference_args to more generic fwnode_reference_args. This will 1) avoid an ACPI specific references to device nodes with integer arguments as well as 2) allow making references to nodes other than device nodes in ACPI. As a by-product, convert the fwnode interger arguments to u64. The arguments were 64-bit integers on ACPI but the fwnode arguments were just 32-bit. Signed-off-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 17 +++++------------ include/linux/fwnode.h | 2 +- 2 files changed, 6 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index e54f40974eb0..11cf39719fd8 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1058,27 +1058,20 @@ static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) /* Device properties */ -#define MAX_ACPI_REFERENCE_ARGS 8 -struct acpi_reference_args { - struct acpi_device *adev; - size_t nargs; - u64 args[MAX_ACPI_REFERENCE_ARGS]; -}; - #ifdef CONFIG_ACPI int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj); int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, - struct acpi_reference_args *args); + struct fwnode_reference_args *args); static inline int acpi_node_get_property_reference( const struct fwnode_handle *fwnode, const char *name, size_t index, - struct acpi_reference_args *args) + struct fwnode_reference_args *args) { return __acpi_node_get_property_reference(fwnode, name, index, - MAX_ACPI_REFERENCE_ARGS, args); + NR_FWNODE_REFERENCE_ARGS, args); } int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, @@ -1169,7 +1162,7 @@ static inline int acpi_dev_get_property(struct acpi_device *adev, static inline int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, - struct acpi_reference_args *args) + struct fwnode_reference_args *args) { return -ENXIO; } @@ -1177,7 +1170,7 @@ __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, static inline int acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, - struct acpi_reference_args *args) + struct fwnode_reference_args *args) { return -ENXIO; } diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 4fe8f289b3f6..faebf0ca0686 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -45,7 +45,7 @@ struct fwnode_endpoint { struct fwnode_reference_args { struct fwnode_handle *fwnode; unsigned int nargs; - unsigned int args[NR_FWNODE_REFERENCE_ARGS]; + u64 args[NR_FWNODE_REFERENCE_ARGS]; }; /** -- cgit v1.2.3 From 0ef7478639c5165a672f01b4024aacfffa951813 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 17 Jul 2018 17:19:14 +0300 Subject: ACPI: property: Make the ACPI graph API private The fwnode graph API is preferred over the ACPI graph API. Therefore make the ACPI graph API private, and use it as a back-end for the fwnode graph API only. Unused functionality is removed while the functionality actually used remains the same. Signed-off-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 11cf39719fd8..de8d3d3fa651 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1089,14 +1089,6 @@ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode); -struct fwnode_handle * -acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, - struct fwnode_handle *prev); -int acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode, - struct fwnode_handle **remote, - struct fwnode_handle **port, - struct fwnode_handle **endpoint); - struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, struct acpi_probe_entry *); -- cgit v1.2.3 From 0e3fd810c4f41dbd63fb7caddc11684959176727 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 10 Jul 2018 16:46:41 +0200 Subject: Documentation: document ktime_get_*() APIs As Dave Chinner points out, we don't have a proper documentation for the ktime_get() family of interfaces, making it rather unclear which of the over 30 (!) interfaces one should actually use in a driver or elsewhere in the kernel. I wrote up an explanation from how I personally see the interfaces, documenting what each of the functions do and hopefully making it a bit clearer which should be used where. This is the first time I tried writing .rst format documentation, so in addition to any mistakes in the content, I probably also introduce nonstandard formatting ;-) I first tried to add an extra section to Documentation/timers/timekeeping.txt, but this is currently not included in the generated API, and it seems useful to have the API docs as part of what gets generated in https://www.kernel.org/doc/html/latest/core-api/index.html#core-utilities instead, so I started a new file there. I also considered adding the documentation inline in the include/linux/timekeeping.h header, but couldn't figure out how to do that in a way that would result both in helpful inline comments as well as readable html output, so I settled for the latter, with a small note pointing to it from the header. Cc: Dave Chinner Cc: John Stultz Cc: Thomas Gleixner Cc: Stephen Boyd Tested-by: Randy Dunlap Reviewed-by: Randy Dunlap Reviewed-by: Linus Walleij Signed-off-by: Arnd Bergmann Signed-off-by: Jonathan Corbet --- include/linux/timekeeping.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 86bc2026efce..947b1b8d2d01 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -20,6 +20,21 @@ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); +/* + * ktime_get() family: read the current time in a multitude of ways, + * + * The default time reference is CLOCK_MONOTONIC, starting at + * boot time but not counting the time spent in suspend. + * For other references, use the functions with "real", "clocktai", + * "boottime" and "raw" suffixes. + * + * To get the time in a different format, use the ones wit + * "ns", "ts64" and "seconds" suffix. + * + * See Documentation/core-api/timekeeping.rst for more details. + */ + + /* * timespec64 based interfaces */ -- cgit v1.2.3 From c2a7d2a115525d3501d38e23d24875a79a07e15e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 13 Jul 2018 21:50:16 -0700 Subject: filesystem-dax: Introduce dax_lock_mapping_entry() In preparation for implementing support for memory poison (media error) handling via dax mappings, implement a lock_page() equivalent. Poison error handling requires rmap and needs guarantees that the page->mapping association is maintained / valid (inode not freed) for the duration of the lookup. In the device-dax case it is sufficient to simply hold a dev_pagemap reference. In the filesystem-dax case we need to use the entry lock. Export the entry lock via dax_lock_mapping_entry() that uses rcu_read_lock() to protect against the inode being freed, and revalidates the page->mapping association under xa_lock(). Cc: Christoph Hellwig Cc: Matthew Wilcox Cc: Ross Zwisler Cc: Jan Kara Signed-off-by: Dan Williams Signed-off-by: Dave Jiang --- include/linux/dax.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index deb0f663252f..450b28db9533 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -88,6 +88,8 @@ int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); +bool dax_lock_mapping_entry(struct page *page); +void dax_unlock_mapping_entry(struct page *page); #else static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) @@ -119,6 +121,17 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping, { return -EOPNOTSUPP; } + +static inline bool dax_lock_mapping_entry(struct page *page) +{ + if (IS_DAX(page->mapping->host)) + return true; + return false; +} + +static inline void dax_unlock_mapping_entry(struct page *page) +{ +} #endif int dax_read_lock(void); -- cgit v1.2.3 From 6100e34b2526e1dc3dbcc47fea2677974d6aaea5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 13 Jul 2018 21:50:21 -0700 Subject: mm, memory_failure: Teach memory_failure() about dev_pagemap pages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit mce: Uncorrected hardware memory error in user-access at af34214200 {1}[Hardware Error]: It has been corrected by h/w and requires no further action mce: [Hardware Error]: Machine check events logged {1}[Hardware Error]: event severity: corrected Memory failure: 0xaf34214: reserved kernel page still referenced by 1 users [..] Memory failure: 0xaf34214: recovery action for reserved kernel page: Failed mce: Memory error not recovered In contrast to typical memory, dev_pagemap pages may be dax mapped. With dax there is no possibility to map in another page dynamically since dax establishes 1:1 physical address to file offset associations. Also dev_pagemap pages associated with NVDIMM / persistent memory devices can internal remap/repair addresses with poison. While memory_failure() assumes that it can discard typical poisoned pages and keep them unmapped indefinitely, dev_pagemap pages may be returned to service after the error is cleared. Teach memory_failure() to detect and handle MEMORY_DEVICE_HOST dev_pagemap pages that have poison consumed by userspace. Mark the memory as UC instead of unmapping it completely to allow ongoing access via the device driver (nd_pmem). Later, nd_pmem will grow support for marking the page back to WB when the error is cleared. Cc: Jan Kara Cc: Christoph Hellwig Cc: Jérôme Glisse Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: Ross Zwisler Signed-off-by: Dan Williams Signed-off-by: Dave Jiang --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a0fbb9ffe380..374e5e9284f7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2725,6 +2725,7 @@ enum mf_action_page_type { MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, MF_MSG_BUDDY_2ND, + MF_MSG_DAX, MF_MSG_UNKNOWN, }; -- cgit v1.2.3 From f53aaa31cce7b543e407da7e97690a700206f7b9 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Mon, 16 Jul 2018 15:22:01 -0700 Subject: net/mlx5: FW tracer, implement tracer logic Implement FW tracer logic and registers access, initialization and cleanup flows. Initializing the tracer will be part of load one flow, as multiple PFs will try to acquire ownership but only one will succeed and will be the tracer owner. Signed-off-by: Feras Daoud Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 957199c20a0f..86cb0ebf92fa 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -816,6 +816,8 @@ struct mlx5_clock { struct mlx5_pps pps_info; }; +struct mlx5_fw_tracer; + struct mlx5_core_dev { struct pci_dev *pdev; /* sync pci state */ @@ -860,6 +862,7 @@ struct mlx5_core_dev { struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; struct page *clock_info_page; + struct mlx5_fw_tracer *tracer; }; struct mlx5_db { -- cgit v1.2.3 From c71ad41ccb0c29fce95149b74786574b354c9dda Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Wed, 7 Feb 2018 11:08:56 +0200 Subject: net/mlx5: FW tracer, events handling The tracer has one event, event 0x26, with two subtypes: - Subtype 0: Ownership change - Subtype 1: Traces available An ownership change occurs in the following cases: 1- Owner releases his ownership, in this case, an event will be sent to inform others to reattempt acquire ownership. 2- Ownership was taken by a higher priority tool, in this case the owner should understand that it lost ownership, and go through tear down flow. The second subtype indicates that there are traces in the trace buffer, in this case, the driver polls the tracer buffer for new traces, parse them and prepares the messages for printing. The HW starts tracing from the first address in the tracer buffer. Driver receives an event notifying that new trace block exists. HW posts a timestamp event at the last 8B of every 256B block. Comparing the timestamp to the last handled timestamp would indicate that this is a new trace block. Once the new timestamp is detected, the entire block is considered valid. Block validation and parsing, should be done after copying the current block to a different location, in order to avoid block overwritten during processing. Signed-off-by: Feras Daoud Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0566c6a94805..d489494b0a84 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -332,6 +332,13 @@ enum mlx5_event { MLX5_EVENT_TYPE_FPGA_ERROR = 0x20, MLX5_EVENT_TYPE_FPGA_QP_ERROR = 0x21, + + MLX5_EVENT_TYPE_DEVICE_TRACER = 0x26, +}; + +enum { + MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE = 0x0, + MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE = 0x1, }; enum { -- cgit v1.2.3 From 51bbf9bee34ff5d4006d266f24a54dc9c1669eb5 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Thu, 19 Jul 2018 17:27:43 -0500 Subject: PCI: hotplug: Demidlayer registration with the core When a hotplug driver calls pci_hp_register(), all steps necessary for registration are carried out in one go, including creation of a kobject and addition to sysfs. That's a problem for pciehp once it's converted to enable/disable the slot exclusively from the IRQ thread: The thread needs to be spawned after creation of the kobject (because it uses the kobject's name), but before addition to sysfs (because it will handle enable/disable requests submitted via sysfs). pci_hp_deregister() does offer a ->release callback that's invoked after deletion from sysfs and before destruction of the kobject. But because pci_hp_register() doesn't offer a counterpart, hotplug drivers' ->probe and ->remove code becomes asymmetric, which is error prone as recently discovered use-after-free bugs in pciehp's ->remove hook have shown. In a sense, this appears to be a case of the midlayer antipattern: "The core thesis of the "midlayer mistake" is that midlayers are bad and should not exist. That common functionality which it is so tempting to put in a midlayer should instead be provided as library routines which can [be] used, augmented, or ignored by each bottom level driver independently. Thus every subsystem that supports multiple implementations (or drivers) should provide a very thin top layer which calls directly into the bottom layer drivers, and a rich library of support code that eases the implementation of those drivers. This library is available to, but not forced upon, those drivers." -- Neil Brown (2009), https://lwn.net/Articles/336262/ The presence of midlayer traits in the PCI hotplug core might be ascribed to its age: When it was introduced in February 2002, the blessings of a library approach might not have been well known: https://git.kernel.org/tglx/history/c/a8a2069f432c For comparison, the driver core does offer split functions for creating a kobject (device_initialize()) and addition to sysfs (device_add()) as an alternative to carrying out everything at once (device_register()). This was introduced in October 2002: https://git.kernel.org/tglx/history/c/8b290eb19962 The odd ->release callback in the PCI hotplug core was added in 2003: https://git.kernel.org/tglx/history/c/69f8d663b595 Clearly, a library approach would not force every hotplug driver to implement a ->release callback, but rather allow the driver to remove the sysfs files, release its data structures and finally destroy the kobject. Alternatively, a driver may choose to remove everything with pci_hp_deregister(), then release its data structures. To this end, offer drivers pci_hp_initialize() and pci_hp_add() as a split-up version of pci_hp_register(). Likewise, offer pci_hp_del() and pci_hp_destroy() as a split-up version of pci_hp_deregister(). Eliminate the ->release callback and move its code into each driver's teardown routine. Declare pci_hp_deregister() void, in keeping with the usual kernel pattern that enablement can fail, but disablement cannot. It only returned an error if the caller passed in a NULL pointer or a slot which has never or is no longer registered or is sharing its name with another slot. Those would be bugs, so WARN about them. Few hotplug drivers actually checked the return value and those that did only printed a useless error message to dmesg. Remove that. For most drivers the conversion was straightforward since it doesn't matter whether the code in the ->release callback is executed before or after destruction of the kobject. But in the case of ibmphp, it was unclear to me whether setting slot_cur->ctrl and slot_cur->bus_on to NULL needs to happen before the kobject is destroyed, so I erred on the side of caution and ensured that the order stays the same. Another nontrivial case is pnv_php, I've found the list and kref logic difficult to understand, however my impression was that it is safe to delete the list element and drop the references until after the kobject is destroyed. Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Acked-by: Andy Shevchenko # drivers/platform/x86 Cc: Rafael J. Wysocki Cc: Len Brown Cc: Scott Murray Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Gavin Shan Cc: Sebastian Ott Cc: Gerald Schaefer Cc: Corentin Chary Cc: Darren Hart Cc: Andy Shevchenko --- include/linux/pci_hotplug.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index cf5e22103f68..a6d6650a0490 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -80,15 +80,12 @@ struct hotplug_slot_info { * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot * @info: pointer to the &struct hotplug_slot_info for the initial values for * this slot. - * @release: called during pci_hp_deregister to free memory allocated in a - * hotplug_slot structure. * @private: used by the hotplug pci controller driver to store whatever it * needs. */ struct hotplug_slot { struct hotplug_slot_ops *ops; struct hotplug_slot_info *info; - void (*release) (struct hotplug_slot *slot); void *private; /* Variables below this are for use only by the hotplug pci core. */ @@ -104,13 +101,23 @@ static inline const char *hotplug_slot_name(const struct hotplug_slot *slot) int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *pbus, int nr, const char *name, struct module *owner, const char *mod_name); -int pci_hp_deregister(struct hotplug_slot *slot); +int __pci_hp_initialize(struct hotplug_slot *slot, struct pci_bus *bus, int nr, + const char *name, struct module *owner, + const char *mod_name); +int pci_hp_add(struct hotplug_slot *slot); + +void pci_hp_del(struct hotplug_slot *slot); +void pci_hp_destroy(struct hotplug_slot *slot); +void pci_hp_deregister(struct hotplug_slot *slot); + int __must_check pci_hp_change_slot_info(struct hotplug_slot *slot, struct hotplug_slot_info *info); /* use a define to avoid include chaining to get THIS_MODULE & friends */ #define pci_hp_register(slot, pbus, devnr, name) \ __pci_hp_register(slot, pbus, devnr, name, THIS_MODULE, KBUILD_MODNAME) +#define pci_hp_initialize(slot, bus, nr, name) \ + __pci_hp_initialize(slot, bus, nr, name, THIS_MODULE, KBUILD_MODNAME) /* PCI Setting Record (Type 0) */ struct hpp_type0 { -- cgit v1.2.3 From 664000b6bb4352295dc774108a1fc87c4a1ad0e3 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 19 Jun 2018 15:23:36 +0300 Subject: net/mlx5: Add support for flow table destination number Add support to set a destination from a flow table number. This functionality will be used in downstream patches from this series by the DEVX stuff. Signed-off-by: Yishai Hadas Acked-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 1 + include/linux/mlx5/mlx5_ifc.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index c40f2fc68655..af0592400499 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -89,6 +89,7 @@ struct mlx5_flow_destination { enum mlx5_flow_destination_type type; union { u32 tir_num; + u32 ft_num; struct mlx5_flow_table *ft; struct mlx5_fc *counter; struct { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ae12120ef021..c14b81559505 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1180,6 +1180,7 @@ enum mlx5_flow_destination_type { MLX5_FLOW_DESTINATION_TYPE_PORT = 0x99, MLX5_FLOW_DESTINATION_TYPE_COUNTER = 0x100, + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM = 0x101, }; struct mlx5_ifc_dest_format_struct_bits { -- cgit v1.2.3 From 3730cf4dd70b6a36e48d58a862120311411b77f5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 24 Jul 2018 12:47:56 +0200 Subject: netlink: do not store start function in netlink_cb ->start() is called once when dump is being initialized, there is no need to store it in netlink_cb. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index f3075d6c7e82..71f121b66ca8 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -170,7 +170,6 @@ netlink_skb_clone(struct sk_buff *skb, gfp_t gfp_mask) struct netlink_callback { struct sk_buff *skb; const struct nlmsghdr *nlh; - int (*start)(struct netlink_callback *); int (*dump)(struct sk_buff * skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); -- cgit v1.2.3 From 10ac86884b4d7642a235f9da61367c3f8d2ab2ff Mon Sep 17 00:00:00 2001 From: Yisheng Xie Date: Tue, 24 Jul 2018 19:11:26 +0200 Subject: fbcon: introduce for_each_registered_fb() helper Following pattern is often used: for (i = 0; i < FB_MAX; i++) { if (registered_fb[i]) { ... } } Therefore, as Andy's suggestion, for_each_registered_fb() helper can be introduced to make the code easier to read and write by reducing indentation level. It also saves few lines of code in each occurrence. This patch convert all part here at the same time. Suggested-by: Andy Shevchenko Signed-off-by: Yisheng Xie Acked-by: Hans de Goede Reviewed-by: Andy Shevchenko Cc: Kees Cook Cc: David Lechner Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/fb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index aa74a228bb92..fd31e6f24b8d 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -650,6 +650,10 @@ extern struct fb_info *registered_fb[FB_MAX]; extern int num_registered_fb; extern struct class *fb_class; +#define for_each_registered_fb(i) \ + for (i = 0; i < FB_MAX; i++) \ + if (!registered_fb[i]) {} else + extern int lock_fb_info(struct fb_info *info); static inline void unlock_fb_info(struct fb_info *info) -- cgit v1.2.3 From 3d910ef71732d15f251ca9b679da634adca72f5a Mon Sep 17 00:00:00 2001 From: Yisheng Xie Date: Tue, 24 Jul 2018 19:11:26 +0200 Subject: fbdev: fix typo in comment Change beeng to being and occured to occurred. Signed-off-by: Yisheng Xie Acked-by: Hans de Goede Cc: Kees Cook Cc: David Lechner Cc: Andy Shevchenko Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/fb.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index fd31e6f24b8d..3e7e75383d32 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -126,7 +126,7 @@ struct fb_cursor_user { /* The resolution of the passed in fb_info about to change */ #define FB_EVENT_MODE_CHANGE 0x01 -/* The display on this fb_info is beeing suspended, no access to the +/* The display on this fb_info is being suspended, no access to the * framebuffer is allowed any more after that call returns */ #define FB_EVENT_SUSPEND 0x02 @@ -159,9 +159,9 @@ struct fb_cursor_user { #define FB_EVENT_FB_UNBIND 0x0E /* CONSOLE-SPECIFIC: remap all consoles to new fb - for vga_switcheroo */ #define FB_EVENT_REMAP_ALL_CONSOLE 0x0F -/* A hardware display blank early change occured */ +/* A hardware display blank early change occurred */ #define FB_EARLY_EVENT_BLANK 0x10 -/* A hardware display blank revert early change occured */ +/* A hardware display blank revert early change occurred */ #define FB_R_EARLY_EVENT_BLANK 0x11 struct fb_event { -- cgit v1.2.3 From e5cda42c16d89720c29678f51d95a119490ef7d8 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 23 Jul 2018 19:52:57 +0200 Subject: ARM: exynos: Define EINT_WAKEUP_MASK registers for S5Pv210 and Exynos5433 S5Pv210 and Exynos5433/Exynos7 have different address of EINT_WAKEUP_MASK register. Rename existing S5P_EINT_WAKEUP_MASK to avoid confusion and add new ones. Signed-off-by: Krzysztof Kozlowski Cc: Tomasz Figa Cc: Sylwester Nawrocki Acked-by: Tomasz Figa Tested-by: Marek Szyprowski --- include/linux/soc/samsung/exynos-regs-pmu.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index 66dcb9ec273a..eb0d240df7a7 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -42,7 +42,7 @@ #define EXYNOS_SWRESET 0x0400 #define S5P_WAKEUP_STAT 0x0600 -#define S5P_EINT_WAKEUP_MASK 0x0604 +#define EXYNOS_EINT_WAKEUP_MASK 0x0604 #define S5P_WAKEUP_MASK 0x0608 #define S5P_WAKEUP_MASK2 0x0614 @@ -180,6 +180,9 @@ #define S5P_CORE_WAKEUP_FROM_LOCAL_CFG (0x3 << 8) #define S5P_CORE_AUTOWAKEUP_EN (1 << 31) +/* Only for S5Pv210 */ +#define S5PV210_EINT_WAKEUP_MASK 0xC004 + /* Only for EXYNOS4210 */ #define S5P_CMU_CLKSTOP_LCD1_LOWPWR 0x1154 #define S5P_CMU_RESET_LCD1_LOWPWR 0x1174 @@ -641,6 +644,7 @@ | EXYNOS5420_KFC_USE_STANDBY_WFI3) /* For EXYNOS5433 */ +#define EXYNOS5433_EINT_WAKEUP_MASK (0x060C) #define EXYNOS5433_USBHOST30_PHY_CONTROL (0x0728) #define EXYNOS5433_PAD_RETENTION_AUD_OPTION (0x3028) #define EXYNOS5433_PAD_RETENTION_MMC2_OPTION (0x30C8) -- cgit v1.2.3 From a8be2af0218cf037704dc2e733bf56d6560fa324 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 23 Jul 2018 19:52:58 +0200 Subject: pinctrl: samsung: Write external wakeup interrupt mask The pinctrl driver defines an IRQ chip which handles external wakeup interrupts, therefore from logical point of view, it is the owner of external interrupt mask. The register controlling the mask belongs to Power Management Unit address space so it has to be accessed with PMU syscon regmap handle. This mask should be written to hardware during system suspend. Till now ARMv7 machine code was responsible for this which created a dependency between pin controller driver and arch/arm/mach code. Try to rework this dependency so the pinctrl driver will write external wakeup interrupt mask during late suspend. Impact on ARMv7 designs (S5Pv210 and Exynos) ============================================ This duplicates setting mask with existing machine code arch/arm/mach-exynos/suspend.c and arch/arm/mach-s5pv210/pm.c but it is not a problem - the wakeup mask register will be written twice. The machine code will be cleaned up later. The difference between implementation here and ARMv7 machine code (arch/arm/mach-*) is the time of writing the mask: 1. The machine code is writing the mask quite late during system suspend path, after offlining secondary CPUs and just before doing actual suspend. 2. The implementation in pinctrl driver uses late suspend ops, therefore it will write the mask much earlier. Hopefully late enough, after all drivers will enable or disable their interrupt wakeups (enable_irq_wake() etc). Impact on ARMv8 designs (Exynos5433 and Exynos7) ================================================ The Suspend to RAM was not supported and external wakeup interrupt mask was not written to HW. This change brings us one step closer to supporting Suspend to RAM. Signed-off-by: Krzysztof Kozlowski Cc: Tomasz Figa Cc: Sylwester Nawrocki Acked-by: Tomasz Figa Tested-by: Marek Szyprowski --- include/linux/soc/samsung/exynos-regs-pmu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index eb0d240df7a7..5addaf5ccbce 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -42,6 +42,8 @@ #define EXYNOS_SWRESET 0x0400 #define S5P_WAKEUP_STAT 0x0600 +/* Value for EXYNOS_EINT_WAKEUP_MASK disabling all external wakeup interrupts */ +#define EXYNOS_EINT_WAKEUP_MASK_DISABLED 0xffffffff #define EXYNOS_EINT_WAKEUP_MASK 0x0604 #define S5P_WAKEUP_MASK 0x0608 #define S5P_WAKEUP_MASK2 0x0614 -- cgit v1.2.3 From 0fc09f920983f61be625658c62cc40ac25a7b3a5 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 23 Jul 2018 08:37:50 -0600 Subject: blk-mq: export setting request completion state This is preparing for drivers that want to directly alter the state of their requests. No functional change here. Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index e3147eb74222..ca3f2c2edd85 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -287,6 +287,20 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); +/** + * blk_mq_mark_complete() - Set request state to complete + * @rq: request to set to complete state + * + * Returns true if request state was successfully set to complete. If + * successful, the caller is responsibile for seeing this request is ended, as + * blk_mq_complete_request will not work again. + */ +static inline bool blk_mq_mark_complete(struct request *rq) +{ + return cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) == + MQ_RQ_IN_FLIGHT; +} + /* * Driver command data is immediately after the request. So subtract request * size to get back to the original request, add request size to get the PDU. -- cgit v1.2.3 From 071f52fbce6161706d070ceada5accb81630bf02 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Jul 2018 09:52:32 +0200 Subject: block: remove bio_clone_kmalloc Unused now. Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index ab221c517f4e..b861baa59454 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -443,12 +443,6 @@ static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs) return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL); } -static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask) -{ - return bio_clone_bioset(bio, gfp_mask, NULL); - -} - extern blk_qc_t submit_bio(struct bio *); extern void bio_endio(struct bio *); -- cgit v1.2.3 From c55183c9aaa00d2bbb578169a480e31aff3d397c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Jul 2018 09:52:34 +0200 Subject: block: unexport bio_clone_bioset Now only used by the bounce code, so move it there and mark the function static. Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index b861baa59454..51371740d2a8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -429,7 +429,6 @@ extern void bio_put(struct bio *); extern void __bio_clone_fast(struct bio *, struct bio *); extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); -extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs); extern struct bio_set fs_bio_set; -- cgit v1.2.3 From 62cedf3e60af03e47849fe2bd6a03ec179422a8a Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Fri, 20 Jul 2018 10:39:13 +0200 Subject: locking/rtmutex: Allow specifying a subclass for nested locking Needed for annotating rt_mutex locks. Tested-by: John Sperbeck Signed-off-by: Peter Rosin Signed-off-by: Peter Zijlstra (Intel) Cc: Davidlohr Bueso Cc: Deepa Dinamani Cc: Greg Kroah-Hartman Cc: Linus Torvalds Cc: Peter Chang Cc: Peter Zijlstra Cc: Philippe Ombredanne Cc: Thomas Gleixner Cc: Will Deacon Cc: Wolfram Sang Link: http://lkml.kernel.org/r/20180720083914.1950-2-peda@axentia.se Signed-off-by: Ingo Molnar --- include/linux/rtmutex.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 1b92a28dd672..6fd615a0eea9 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -106,7 +106,14 @@ static inline int rt_mutex_is_locked(struct rt_mutex *lock) extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key); extern void rt_mutex_destroy(struct rt_mutex *lock); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass); +#define rt_mutex_lock(lock) rt_mutex_lock_nested(lock, 0) +#else extern void rt_mutex_lock(struct rt_mutex *lock); +#define rt_mutex_lock_nested(lock, subclass) rt_mutex_lock(lock) +#endif + extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); extern int rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout); -- cgit v1.2.3 From 6e30396767508101eacec8b93b068e8905e660dc Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Wed, 20 Jun 2018 22:32:42 +0530 Subject: sched/numa: Remove redundant field 'numa_entry' is a struct list_head defined in task_struct, but never used. No functional change. Signed-off-by: Srikar Dronamraju Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Rik van Riel Acked-by: Mel Gorman Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1529514181-9842-2-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 43731fe51c97..e0f4f56c9310 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1017,7 +1017,6 @@ struct task_struct { u64 last_sum_exec_runtime; struct callback_head numa_work; - struct list_head numa_entry; struct numa_group *numa_group; /* -- cgit v1.2.3 From 6cbc304f2f360f25cc8607817239d6f4a2fd3dc5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 10 May 2018 15:48:41 +0200 Subject: perf/x86/intel: Fix unwind errors from PEBS entries (mk-II) Vince reported the perf_fuzzer giving various unwinder warnings and Josh reported: > Deja vu. Most of these are related to perf PEBS, similar to the > following issue: > > b8000586c90b ("perf/x86/intel: Cure bogus unwind from PEBS entries") > > This is basically the ORC version of that. setup_pebs_sample_data() is > assembling a franken-pt_regs which ORC isn't happy about. RIP is > inconsistent with some of the other registers (like RSP and RBP). And where the previous unwinder only needed BP,SP ORC also requires IP. But we cannot spoof IP because then the sample will get displaced, entirely negating the point of PEBS. So cure the whole thing differently by doing the unwind early; this does however require a means to communicate we did the unwind early. We (ab)use an unused sample_type bit for this, which we set on events that fill out the data->callchain before the normal perf_prepare_sample(). Debugged-by: Josh Poimboeuf Reported-by: Vince Weaver Tested-by: Josh Poimboeuf Tested-by: Prashant Bhole Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1fa12887ec02..87f6db437e4a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1130,6 +1130,7 @@ extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); +extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); -- cgit v1.2.3 From fd2efaa4eb5317c3a86357a83a7d456a1b86a0ac Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 16 Jul 2018 12:30:11 +0100 Subject: locking/atomics: Rework ordering barriers Currently architectures can override __atomic_op_*() to define the barriers used before/after a relaxed atomic when used to build acquire/release/fence variants. This has the unfortunate property of requiring the architecture to define the full wrapper for the atomics, rather than just the barriers they care about, and gets in the way of generating atomics which can be easily read. Instead, this patch has architectures define an optional set of barriers: * __atomic_acquire_fence() * __atomic_release_fence() * __atomic_pre_full_fence() * __atomic_post_full_fence() ... which uses to build the wrappers. It would be nice if we could undef these, along with the __atomic_op_*() wrappers, but that would break the cmpxchg() wrappers, which are written in preprocessor. Undefs would have been nice, but alas. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Acked-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrea Parri Cc: Boqun Feng Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: andy.shevchenko@gmail.com Cc: arnd@arndb.de Cc: aryabinin@virtuozzo.com Cc: catalin.marinas@arm.com Cc: dvyukov@google.com Cc: glider@google.com Cc: linux-arm-kernel@lists.infradead.org Cc: peter@hurleysoftware.com Link: http://lkml.kernel.org/r/20180716113017.3909-7-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 38 ++++++++++++++++++++++---------------- 1 file changed, 22 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 8e04f1f69bd9..1e8e88bdaf09 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -38,40 +38,46 @@ * barriers on top of the relaxed variant. In the case where the relaxed * variant is already fully ordered, no additional barriers are needed. * - * Besides, if an arch has a special barrier for acquire/release, it could - * implement its own __atomic_op_* and use the same framework for building - * variants - * - * If an architecture overrides __atomic_op_acquire() it will probably want - * to define smp_mb__after_spinlock(). + * If an architecture overrides __atomic_acquire_fence() it will probably + * want to define smp_mb__after_spinlock(). */ -#ifndef __atomic_op_acquire +#ifndef __atomic_acquire_fence +#define __atomic_acquire_fence smp_mb__after_atomic +#endif + +#ifndef __atomic_release_fence +#define __atomic_release_fence smp_mb__before_atomic +#endif + +#ifndef __atomic_pre_full_fence +#define __atomic_pre_full_fence smp_mb__before_atomic +#endif + +#ifndef __atomic_post_full_fence +#define __atomic_post_full_fence smp_mb__after_atomic +#endif + #define __atomic_op_acquire(op, args...) \ ({ \ typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - smp_mb__after_atomic(); \ + __atomic_acquire_fence(); \ __ret; \ }) -#endif -#ifndef __atomic_op_release #define __atomic_op_release(op, args...) \ ({ \ - smp_mb__before_atomic(); \ + __atomic_release_fence(); \ op##_relaxed(args); \ }) -#endif -#ifndef __atomic_op_fence #define __atomic_op_fence(op, args...) \ ({ \ typeof(op##_relaxed(args)) __ret; \ - smp_mb__before_atomic(); \ + __atomic_pre_full_fence(); \ __ret = op##_relaxed(args); \ - smp_mb__after_atomic(); \ + __atomic_post_full_fence(); \ __ret; \ }) -#endif /* atomic_add_return_relaxed */ #ifndef atomic_add_return_relaxed -- cgit v1.2.3 From d27fb99f62af7b79c542d161aa5155ed57271ddc Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 23 Jul 2018 22:42:48 +0100 Subject: dma-mapping: relax warning for per-device areas The reasons why dma_free_attrs() should not be called from IRQ context are not necessarily obvious and somewhat buried in the development history, so let's start by documenting the warning itself to help anyone who does happen to hit it and wonder what the deal is. However, this check turns out to be slightly over-restrictive for the way that per-device memory has been spliced into the general API, since for that case we know that dma_declare_coherent_memory() has created an appropriate CPU mapping for the entire area and nothing dynamic should be happening. Given that the usage model for per-device memory is often more akin to streaming DMA than 'real' coherent DMA (e.g. allocating and freeing space to copy short-lived packets in and out), it is also somewhat more reasonable for those operations to happen in IRQ handlers for such devices. Therefore, let's move the irqs_disabled() check down past the per-device area hook, so that that gets a chance to resolve the request before we reach definite "you're doing it wrong" territory. Reported-by: Fredrik Noring Tested-by: Fredrik Noring Signed-off-by: Robin Murphy Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index f9cc309507d9..1db6a6b46d0d 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -538,10 +538,17 @@ static inline void dma_free_attrs(struct device *dev, size_t size, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!ops); - WARN_ON(irqs_disabled()); if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr)) return; + /* + * On non-coherent platforms which implement DMA-coherent buffers via + * non-cacheable remaps, ops->free() may call vunmap(). Thus getting + * this far in IRQ context is a) at risk of a BUG_ON() or trying to + * sleep on some machines, and b) an indication that the driver is + * probably misusing the coherent API anyway. + */ + WARN_ON(irqs_disabled()); if (!ops->free || !cpu_addr) return; -- cgit v1.2.3 From 73c8d8945505acdcbae137c2e00a1232e0be709f Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 14 Jul 2018 01:28:15 +0900 Subject: ring_buffer: tracing: Inherit the tracing setting to next ring buffer Maintain the tracing on/off setting of the ring_buffer when switching to the trace buffer snapshot. Taking a snapshot is done by swapping the backup ring buffer (max_tr_buffer). But since the tracing on/off setting is defined by the ring buffer, when swapping it, the tracing on/off setting can also be changed. This causes a strange result like below: /sys/kernel/debug/tracing # cat tracing_on 1 /sys/kernel/debug/tracing # echo 0 > tracing_on /sys/kernel/debug/tracing # cat tracing_on 0 /sys/kernel/debug/tracing # echo 1 > snapshot /sys/kernel/debug/tracing # cat tracing_on 1 /sys/kernel/debug/tracing # echo 1 > snapshot /sys/kernel/debug/tracing # cat tracing_on 0 We don't touch tracing_on, but snapshot changes tracing_on setting each time. This is an anomaly, because user doesn't know that each "ring_buffer" stores its own tracing-enable state and the snapshot is done by swapping ring buffers. Link: http://lkml.kernel.org/r/153149929558.11274.11730609978254724394.stgit@devbox Cc: Ingo Molnar Cc: Shuah Khan Cc: Tom Zanussi Cc: Hiraku Toyooka Cc: stable@vger.kernel.org Fixes: debdd57f5145 ("tracing: Make a snapshot feature available from userspace") Signed-off-by: Masami Hiramatsu [ Updated commit log and comment in the code ] Signed-off-by: Steven Rostedt (VMware) --- include/linux/ring_buffer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index b72ebdff0b77..003d09ab308d 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -165,6 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer); void ring_buffer_record_off(struct ring_buffer *buffer); void ring_buffer_record_on(struct ring_buffer *buffer); int ring_buffer_record_is_on(struct ring_buffer *buffer); +int ring_buffer_record_is_set_on(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); -- cgit v1.2.3 From 3c507b8af638c67d4a80d70091d2057ecb01e8a6 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 23 Jul 2018 21:40:07 +0200 Subject: net: phy: add helper phy_polling_mode Add a helper for checking whether polling is used to detect PHY status changes. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 075c2f770d3e..cd6f637cbbfb 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -824,6 +824,16 @@ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) return phydev->irq != PHY_POLL && phydev->irq != PHY_IGNORE_INTERRUPT; } +/** + * phy_polling_mode - Convenience function for testing whether polling is + * used to detect PHY status changes + * @phydev: the phy_device struct + */ +static inline bool phy_polling_mode(struct phy_device *phydev) +{ + return phydev->irq == PHY_POLL; +} + /** * phy_is_internal - Convenience function for testing if a PHY is internal * @phydev: the phy_device struct -- cgit v1.2.3 From 6f4ceee9305dc3fe74099159b460f4b56b506f1d Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 24 Jul 2018 14:26:04 -0400 Subject: cpu/hotplug: Add a cpus_read_trylock() function There are use cases where it can be useful to have a cpus_read_trylock() function to work around circular lock dependency problem involving the cpu_hotplug_lock. Signed-off-by: Waiman Long Signed-off-by: Rafael J. Wysocki --- include/linux/cpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a97a63eef59f..e850bfea3e84 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -103,6 +103,7 @@ extern void cpus_write_lock(void); extern void cpus_write_unlock(void); extern void cpus_read_lock(void); extern void cpus_read_unlock(void); +extern int cpus_read_trylock(void); extern void lockdep_assert_cpus_held(void); extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); @@ -115,6 +116,7 @@ static inline void cpus_write_lock(void) { } static inline void cpus_write_unlock(void) { } static inline void cpus_read_lock(void) { } static inline void cpus_read_unlock(void) { } +static inline int cpus_read_trylock(void) { return true; } static inline void lockdep_assert_cpus_held(void) { } static inline void cpu_hotplug_disable(void) { } static inline void cpu_hotplug_enable(void) { } -- cgit v1.2.3 From 1560d0848a1a84db6c1d9b17c14273c0dae41828 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 25 Jul 2018 14:34:29 +0200 Subject: rtc: remove rtc_irq_register/rtc_irq_unregister The rtc_irq_* interface is not used from outside the RTC subsytem since 2016. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 6268208760e9..f868d6b619ab 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -204,10 +204,6 @@ extern void rtc_update_irq(struct rtc_device *rtc, extern struct rtc_device *rtc_class_open(const char *name); extern void rtc_class_close(struct rtc_device *rtc); -extern int rtc_irq_register(struct rtc_device *rtc, - struct rtc_task *task); -extern void rtc_irq_unregister(struct rtc_device *rtc, - struct rtc_task *task); extern int rtc_irq_set_state(struct rtc_device *rtc, struct rtc_task *task, int enabled); extern int rtc_irq_set_freq(struct rtc_device *rtc, -- cgit v1.2.3 From acecb3ad8b21a519ce4ad728106d45d4e978bb56 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 25 Jul 2018 14:58:10 +0200 Subject: rtc: remove irq_task and irq_task_lock There is no way to set a periodic task anymore, remove task pointer and lock. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index f868d6b619ab..8cc23fdfd4ee 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -121,8 +121,6 @@ struct rtc_device { wait_queue_head_t irq_queue; struct fasync_struct *async_queue; - struct rtc_task *irq_task; - spinlock_t irq_task_lock; int irq_freq; int max_user_freq; -- cgit v1.2.3 From 8719d3c9188b38db462a77ecd8c7a8e25e7e8c4c Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 25 Jul 2018 15:07:09 +0200 Subject: rtc: simplify rtc_irq_set_state/rtc_irq_set_freq The PIE doesn't handle tasks anymore, remove the pointer from the interface. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 8cc23fdfd4ee..bf4d375025d1 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -202,10 +202,8 @@ extern void rtc_update_irq(struct rtc_device *rtc, extern struct rtc_device *rtc_class_open(const char *name); extern void rtc_class_close(struct rtc_device *rtc); -extern int rtc_irq_set_state(struct rtc_device *rtc, - struct rtc_task *task, int enabled); -extern int rtc_irq_set_freq(struct rtc_device *rtc, - struct rtc_task *task, int freq); +extern int rtc_irq_set_state(struct rtc_device *rtc, int enabled); +extern int rtc_irq_set_freq(struct rtc_device *rtc, int freq); extern int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled); extern int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled); extern int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc, -- cgit v1.2.3 From 1f45a4db3657c5ecafb7d3331536c987e6d18311 Mon Sep 17 00:00:00 2001 From: Paul McKenney Date: Thu, 28 Jun 2018 11:21:43 -0700 Subject: srcu: Add notrace variants of srcu_read_{lock,unlock} This is needed for a future tracepoint patch that uses srcu, and to make sure it doesn't call into lockdep. tracepoint code already calls notrace variants for rcu_read_lock_sched so this patch does the same for srcu which will be used in a later patch. Keeps it consistent with rcu-sched. [Joel: Added commit message] Link: http://lkml.kernel.org/r/20180628182149.226164-2-joel@joelfernandes.org Reviewed-by: Steven Rostedt (VMware) Signed-off-by: Paul McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Steven Rostedt (VMware) --- include/linux/srcu.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 91494d7e8e41..3e72a291c401 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -195,6 +195,16 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) return retval; } +/* Used by tracing, cannot be traced and cannot invoke lockdep. */ +static inline notrace int +srcu_read_lock_notrace(struct srcu_struct *sp) __acquires(sp) +{ + int retval; + + retval = __srcu_read_lock(sp); + return retval; +} + /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @sp: srcu_struct in which to unregister the old reader. @@ -209,6 +219,13 @@ static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) __srcu_read_unlock(sp, idx); } +/* Used by tracing, cannot be traced and cannot call lockdep. */ +static inline notrace void +srcu_read_unlock_notrace(struct srcu_struct *sp, int idx) __releases(sp) +{ + __srcu_read_unlock(sp, idx); +} + /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * -- cgit v1.2.3 From 0b764a6e4e19dc254caca636002eaa47b1d0b0af Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Thu, 28 Jun 2018 11:21:44 -0700 Subject: srcu: Add notrace variant of srcu_dereference In the last patch in this series, we are making lockdep register hooks onto the irq_{disable,enable} tracepoints. These tracepoints use the _rcuidle tracepoint variant. In this series we switch the _rcuidle tracepoint callers to use SRCU instead of sched-RCU. Inorder to dereference the pointer to the probe functions, we could call srcu_dereference, however this API will call back into lockdep to check if the lock is held *before* the lockdep probe hooks have a chance to run and annotate the IRQ enabled/disabled state. For this reason we need a notrace variant of srcu_dereference since otherwise we get lockdep splats. This patch adds the needed srcu_dereference_notrace variant. Link: http://lkml.kernel.org/r/20180628182149.226164-3-joel@joelfernandes.org Reviewed-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Steven Rostedt (VMware) --- include/linux/srcu.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 3e72a291c401..67135d4a8a30 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -169,6 +169,11 @@ static inline int srcu_read_lock_held(const struct srcu_struct *sp) */ #define srcu_dereference(p, sp) srcu_dereference_check((p), (sp), 0) +/** + * srcu_dereference_notrace - no tracing and no lockdep calls from here + */ +#define srcu_dereference_notrace(p, sp) srcu_dereference_check((p), (sp), 1) + /** * srcu_read_lock - register a new reader for an SRCU-protected structure. * @sp: srcu_struct in which to register the new reader. -- cgit v1.2.3 From 72809cbf6748830ae4a59a45bcb2367a6c24d74d Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 26 Jul 2018 21:44:32 +0900 Subject: tracing: Remove orphaned function ftrace_nr_registered_ops() Remove ftrace_nr_registered_ops() because it is no longer used. ftrace_nr_registered_ops() has been introduced by commit ea701f11da44 ("ftrace: Add selftest to test function trace recursion protection"), but its caller has been removed by commit 05cbbf643b8e ("tracing: Fix selftest function recursion accounting"). So it is not called anymore. Link: http://lkml.kernel.org/r/153260907227.12474.5234899025934963683.stgit@devbox Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ebb77674be90..63af5eb0ff46 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -234,10 +234,6 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1, */ #define register_ftrace_function(ops) ({ 0; }) #define unregister_ftrace_function(ops) ({ 0; }) -static inline int ftrace_nr_registered_ops(void) -{ - return 0; -} static inline void ftrace_kill(void) { } static inline void ftrace_free_init_mem(void) { } static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } @@ -328,8 +324,6 @@ struct seq_file; extern int ftrace_text_reserved(const void *start, const void *end); -extern int ftrace_nr_registered_ops(void); - struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr); bool is_ftrace_trampoline(unsigned long addr); -- cgit v1.2.3 From af9b6d7570ca9afbbc6076ab7920d8f00f7e55c1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 29 Jun 2018 12:45:53 -0400 Subject: pNFS: Parse the results of layoutget on open even if permissions checks fail Even if the results of the permissions checks failed, we should parse the results of the layout on open call so that we can return the layout if required. Note that we also want to ignore the sequence counter for whether or not a layout recall occurred. If the recall pertained to our OPEN, then the callback will know, and will attempt to wait for us to finih processing anyway. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 - include/linux/nfs_xdr.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 74ae3e1d19a0..2c18d618604e 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -28,7 +28,6 @@ struct nfs41_impl_id; struct nfs_client { refcount_t cl_count; atomic_t cl_mds_count; - seqcount_t cl_callback_count; int cl_cons_state; /* current construction state (-ve: init error) */ #define NFS_CS_READY 0 /* ready to be used */ #define NFS_CS_INITING 1 /* busy initialising */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 712eed156d09..3b7325cfb291 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -271,7 +271,6 @@ struct nfs4_layoutget { struct nfs4_layoutget_args args; struct nfs4_layoutget_res res; struct rpc_cred *cred; - unsigned callback_count; gfp_t gfp_flags; }; -- cgit v1.2.3 From 359f642700f2ff05d9c94cd9216c97af7b8e9553 Mon Sep 17 00:00:00 2001 From: Greg Edwards Date: Wed, 25 Jul 2018 10:22:58 -0400 Subject: block: move bio_integrity_{intervals,bytes} into blkdev.h This allows bio_integrity_bytes() to be called from drivers instead of open coding it. Acked-by: Martin K. Petersen Signed-off-by: Greg Edwards Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 331a6cb8805f..050d599f5ea9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1865,6 +1865,28 @@ static inline bool integrity_req_gap_front_merge(struct request *req, bip_next->bip_vec[0].bv_offset); } +/** + * bio_integrity_intervals - Return number of integrity intervals for a bio + * @bi: blk_integrity profile for device + * @sectors: Size of the bio in 512-byte sectors + * + * Description: The block layer calculates everything in 512 byte + * sectors but integrity metadata is done in terms of the data integrity + * interval size of the storage device. Convert the block layer sectors + * to the appropriate number of integrity intervals. + */ +static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, + unsigned int sectors) +{ + return sectors >> (bi->interval_exp - 9); +} + +static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, + unsigned int sectors) +{ + return bio_integrity_intervals(bi, sectors) * bi->tuple_size; +} + #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; @@ -1938,6 +1960,18 @@ static inline bool integrity_req_gap_front_merge(struct request *req, return false; } +static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, + unsigned int sectors) +{ + return 0; +} + +static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, + unsigned int sectors) +{ + return 0; +} + #endif /* CONFIG_BLK_DEV_INTEGRITY */ struct block_device_operations { -- cgit v1.2.3 From 0ab5fe5374743d5a279b1ff6297ef2c54d06cd5f Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 20 Jun 2018 15:22:52 +1000 Subject: fsi: Add new central chardev support The various FSI devices (sbefifo, occ, scom, more to come) currently use misc devices. This is problematic as the minor device space for misc is limited and there can be a lot of them. Also it limits our ability to move them to a dedicated /dev/fsi directory or to be smart about device naming and numbering. It also means we have IDAs on every single of these drivers This creates a common fsi "device_type" for the optional /dev/fsi grouping and a dev_t allocator for all FSI devices. "Legacy" devices get to use a backward compatible numbering scheme (as long as chip id <16 and there's only one copy of a given unit type per chip). A single major number and a single IDA are shared for all FSI devices. This doesn't convert the FSI device drivers to use the new scheme yet, they will be converted individually. Signed-off-by: Benjamin Herrenschmidt --- include/linux/fsi.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsi.h b/include/linux/fsi.h index 141fd38d061f..ec3be0d5b786 100644 --- a/include/linux/fsi.h +++ b/include/linux/fsi.h @@ -76,8 +76,18 @@ extern int fsi_slave_read(struct fsi_slave *slave, uint32_t addr, extern int fsi_slave_write(struct fsi_slave *slave, uint32_t addr, const void *val, size_t size); +extern struct bus_type fsi_bus_type; +extern const struct device_type fsi_cdev_type; +enum fsi_dev_type { + fsi_dev_cfam, + fsi_dev_sbefifo, + fsi_dev_scom, + fsi_dev_occ +}; -extern struct bus_type fsi_bus_type; +extern int fsi_get_new_minor(struct fsi_device *fdev, enum fsi_dev_type type, + dev_t *out_dev, int *out_index); +extern void fsi_free_minor(dev_t dev); #endif /* LINUX_FSI_H */ -- cgit v1.2.3 From b512719f771a82180211c9a315b8a7f628832b3d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 26 Jul 2018 16:37:08 -0700 Subject: delayacct: fix crash in delayacct_blkio_end() after delayacct init failure While forking, if delayacct init fails due to memory shortage, it continues expecting all delayacct users to check task->delays pointer against NULL before dereferencing it, which all of them used to do. Commit c96f5471ce7d ("delayacct: Account blkio completion on the correct task"), while updating delayacct_blkio_end() to take the target task instead of always using %current, made the function test NULL on %current->delays and then continue to operated on @p->delays. If %current succeeded init while @p didn't, it leads to the following crash. BUG: unable to handle kernel NULL pointer dereference at 0000000000000004 IP: __delayacct_blkio_end+0xc/0x40 PGD 8000001fd07e1067 P4D 8000001fd07e1067 PUD 1fcffbb067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 4 PID: 25774 Comm: QIOThread0 Not tainted 4.16.0-9_fbk1_rc2_1180_g6b593215b4d7 #9 RIP: 0010:__delayacct_blkio_end+0xc/0x40 Call Trace: try_to_wake_up+0x2c0/0x600 autoremove_wake_function+0xe/0x30 __wake_up_common+0x74/0x120 wake_up_page_bit+0x9c/0xe0 mpage_end_io+0x27/0x70 blk_update_request+0x78/0x2c0 scsi_end_request+0x2c/0x1e0 scsi_io_completion+0x20b/0x5f0 blk_mq_complete_request+0xa2/0x100 ata_scsi_qc_complete+0x79/0x400 ata_qc_complete_multiple+0x86/0xd0 ahci_handle_port_interrupt+0xc9/0x5c0 ahci_handle_port_intr+0x54/0xb0 ahci_single_level_irq_intr+0x3b/0x60 __handle_irq_event_percpu+0x43/0x190 handle_irq_event_percpu+0x20/0x50 handle_irq_event+0x2a/0x50 handle_edge_irq+0x80/0x1c0 handle_irq+0xaf/0x120 do_IRQ+0x41/0xc0 common_interrupt+0xf/0xf Fix it by updating delayacct_blkio_end() check @p->delays instead. Link: http://lkml.kernel.org/r/20180724175542.GP1934745@devbig577.frc2.facebook.com Fixes: c96f5471ce7d ("delayacct: Account blkio completion on the correct task") Signed-off-by: Tejun Heo Reported-by: Dave Jones Debugged-by: Dave Jones Reviewed-by: Andrew Morton Cc: Josh Snyder Cc: [4.15+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index e6c0448ebcc7..31c865d1842e 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -124,7 +124,7 @@ static inline void delayacct_blkio_start(void) static inline void delayacct_blkio_end(struct task_struct *p) { - if (current->delays) + if (p->delays) __delayacct_blkio_end(p); delayacct_clear_flag(DELAYACCT_PF_BLKIO); } -- cgit v1.2.3 From 027232da7c7c1c7f04383f93bd798e475dde5285 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 26 Jul 2018 16:37:25 -0700 Subject: mm: introduce vma_init() Not all VMAs allocated with vm_area_alloc(). Some of them allocated on stack or in data segment. The new helper can be use to initialize VMA properly regardless where it was allocated. Link: http://lkml.kernel.org/r/20180724121139.62570-2-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Acked-by: Linus Torvalds Reviewed-by: Andrew Morton Cc: Dmitry Vyukov Cc: Oleg Nesterov Cc: Andrea Arcangeli Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d3a3842316b8..31540f166987 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -452,6 +452,12 @@ struct vm_operations_struct { unsigned long addr); }; +static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) +{ + vma->vm_mm = mm; + INIT_LIST_HEAD(&vma->anon_vma_chain); +} + struct mmu_gather; struct inode; -- cgit v1.2.3 From bfd40eaff5abb9f62c8ef94ca13ed0d94a560f10 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 26 Jul 2018 16:37:35 -0700 Subject: mm: fix vma_is_anonymous() false-positives vma_is_anonymous() relies on ->vm_ops being NULL to detect anonymous VMA. This is unreliable as ->mmap may not set ->vm_ops. False-positive vma_is_anonymous() may lead to crashes: next ffff8801ce5e7040 prev ffff8801d20eca50 mm ffff88019c1e13c0 prot 27 anon_vma ffff88019680cdd8 vm_ops 0000000000000000 pgoff 0 file ffff8801b2ec2d00 private_data 0000000000000000 flags: 0xff(read|write|exec|shared|mayread|maywrite|mayexec|mayshare) ------------[ cut here ]------------ kernel BUG at mm/memory.c:1422! invalid opcode: 0000 [#1] SMP KASAN CPU: 0 PID: 18486 Comm: syz-executor3 Not tainted 4.18.0-rc3+ #136 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:zap_pmd_range mm/memory.c:1421 [inline] RIP: 0010:zap_pud_range mm/memory.c:1466 [inline] RIP: 0010:zap_p4d_range mm/memory.c:1487 [inline] RIP: 0010:unmap_page_range+0x1c18/0x2220 mm/memory.c:1508 Call Trace: unmap_single_vma+0x1a0/0x310 mm/memory.c:1553 zap_page_range_single+0x3cc/0x580 mm/memory.c:1644 unmap_mapping_range_vma mm/memory.c:2792 [inline] unmap_mapping_range_tree mm/memory.c:2813 [inline] unmap_mapping_pages+0x3a7/0x5b0 mm/memory.c:2845 unmap_mapping_range+0x48/0x60 mm/memory.c:2880 truncate_pagecache+0x54/0x90 mm/truncate.c:800 truncate_setsize+0x70/0xb0 mm/truncate.c:826 simple_setattr+0xe9/0x110 fs/libfs.c:409 notify_change+0xf13/0x10f0 fs/attr.c:335 do_truncate+0x1ac/0x2b0 fs/open.c:63 do_sys_ftruncate+0x492/0x560 fs/open.c:205 __do_sys_ftruncate fs/open.c:215 [inline] __se_sys_ftruncate fs/open.c:213 [inline] __x64_sys_ftruncate+0x59/0x80 fs/open.c:213 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Reproducer: #include #include #include #include #include #include #include #include #include #include #include #define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) #define KCOV_ENABLE _IO('c', 100) #define KCOV_DISABLE _IO('c', 101) #define COVER_SIZE (1024<<10) #define KCOV_TRACE_PC 0 #define KCOV_TRACE_CMP 1 int main(int argc, char **argv) { int fd; unsigned long *cover; system("mount -t debugfs none /sys/kernel/debug"); fd = open("/sys/kernel/debug/kcov", O_RDWR); ioctl(fd, KCOV_INIT_TRACE, COVER_SIZE); cover = mmap(NULL, COVER_SIZE * sizeof(unsigned long), PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); munmap(cover, COVER_SIZE * sizeof(unsigned long)); cover = mmap(NULL, COVER_SIZE * sizeof(unsigned long), PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); memset(cover, 0, COVER_SIZE * sizeof(unsigned long)); ftruncate(fd, 3UL << 20); return 0; } This can be fixed by assigning anonymous VMAs own vm_ops and not relying on it being NULL. If ->mmap() failed to set ->vm_ops, mmap_region() will set it to dummy_vm_ops. This way we will have non-NULL ->vm_ops for all VMAs. Link: http://lkml.kernel.org/r/20180724121139.62570-4-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Reported-by: syzbot+3f84280d52be9b7083cc@syzkaller.appspotmail.com Acked-by: Linus Torvalds Reviewed-by: Andrew Morton Cc: Dmitry Vyukov Cc: Oleg Nesterov Cc: Andrea Arcangeli Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 31540f166987..7ba6d356d18f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -454,10 +454,18 @@ struct vm_operations_struct { static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { + static const struct vm_operations_struct dummy_vm_ops = {}; + vma->vm_mm = mm; + vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); } +static inline void vma_set_anonymous(struct vm_area_struct *vma) +{ + vma->vm_ops = NULL; +} + struct mmu_gather; struct inode; -- cgit v1.2.3 From fa3fc2ad99b4f025446d1cff589a8d2dd7db92f2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Jul 2018 16:37:38 -0700 Subject: include/linux/eventfd.h: include linux/errno.h The new gasket staging driver ran into a randconfig build failure when CONFIG_EVENTFD is disabled: In file included from drivers/staging/gasket/gasket_interrupt.h:11, from drivers/staging/gasket/gasket_interrupt.c:4: include/linux/eventfd.h: In function 'eventfd_ctx_fdget': include/linux/eventfd.h:51:9: error: implicit declaration of function 'ERR_PTR' [-Werror=implicit-function-declaration] I can't see anything wrong with including eventfd.h before err.h, so the easiest fix is to make it possible to do this by including the file where it is needed. Link: http://lkml.kernel.org/r/20180724110737.3985088-1-arnd@arndb.de Fixes: 9a69f5087ccc ("drivers/staging: Gasket driver framework + Apex driver") Signed-off-by: Arnd Bergmann Cc: Eric Biggers Cc: Al Viro Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/eventfd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 7094718b653b..ffcc7724ca21 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -11,6 +11,7 @@ #include #include +#include /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining -- cgit v1.2.3 From 2b8de8a832add91a4e522536078b505283d3979f Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Fri, 6 Jul 2018 19:41:06 -0700 Subject: mfd: rave-sp: Add legacy EEPROM access command translation This is needed to make rave-sp-eeprom driver work on "legacy" firmware. Signed-off-by: Andrey Smirnov Signed-off-by: Lee Jones --- include/linux/mfd/rave-sp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rave-sp.h b/include/linux/mfd/rave-sp.h index fe0ce7bc59cf..11eef77ef976 100644 --- a/include/linux/mfd/rave-sp.h +++ b/include/linux/mfd/rave-sp.h @@ -21,6 +21,7 @@ enum rave_sp_command { RAVE_SP_CMD_STATUS = 0xA0, RAVE_SP_CMD_SW_WDT = 0xA1, RAVE_SP_CMD_PET_WDT = 0xA2, + RAVE_SP_CMD_RMB_EEPROM = 0xA4, RAVE_SP_CMD_SET_BACKLIGHT = 0xA6, RAVE_SP_CMD_RESET = 0xA7, RAVE_SP_CMD_RESET_REASON = 0xA8, -- cgit v1.2.3 From 4d3e55bc7690b289eeae0c7e994db965cb2a993d Mon Sep 17 00:00:00 2001 From: Alberto Panizzo Date: Mon, 9 Jul 2018 19:46:46 +0200 Subject: mfd: wm8994: Allow to configure CS/ADDR Pulldown from dts For designs where CS/ADDR pin is floating, it is useful to allow dts to define whether to keep internal pull down or not. Signed-off-by: Alberto Panizzo Signed-off-by: Anthony Brandon Acked-by: Charles Keepax Signed-off-by: Lee Jones --- include/linux/mfd/wm8994/pdata.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8994/pdata.h b/include/linux/mfd/wm8994/pdata.h index 90c60524a496..b19c370fe81a 100644 --- a/include/linux/mfd/wm8994/pdata.h +++ b/include/linux/mfd/wm8994/pdata.h @@ -222,6 +222,12 @@ struct wm8994_pdata { */ bool spkmode_pu; + /* + * CS/ADDR must be pulled internally by the device on this + * system. + */ + bool csnaddr_pd; + /** * Maximum number of channels clocks will be generated for, * useful for systems where and I2S bus with multiple data -- cgit v1.2.3 From c8fda5bfa9972dc1175b898dfdaa3a375dca6022 Mon Sep 17 00:00:00 2001 From: Marcel Ziswiler Date: Tue, 3 Jul 2018 17:04:11 +0200 Subject: mfd: as3722: Disable auto-power-on when AC OK On ams AS3722, power on when AC OK is enabled by default. Making this option as disable by default and enable only when platform need this explicitly. Signed-off-by: Laxman Dewangan Reviewed-by: Bibek Basu Tested-by: Bibek Basu Signed-off-by: Marcel Ziswiler Acked-by: Rob Herring Signed-off-by: Lee Jones --- include/linux/mfd/as3722.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/as3722.h b/include/linux/mfd/as3722.h index 51e6f9414575..b404a5af9bba 100644 --- a/include/linux/mfd/as3722.h +++ b/include/linux/mfd/as3722.h @@ -296,6 +296,8 @@ #define AS3722_ADC1_CONV_NOTREADY BIT(7) #define AS3722_ADC1_SOURCE_SELECT_MASK 0x1F +#define AS3722_CTRL_SEQU1_AC_OK_PWR_ON BIT(0) + /* GPIO modes */ #define AS3722_GPIO_MODE_MASK 0x07 #define AS3722_GPIO_MODE_INPUT 0x00 @@ -391,6 +393,7 @@ struct as3722 { unsigned long irq_flags; bool en_intern_int_pullup; bool en_intern_i2c_pullup; + bool en_ac_ok_pwr_on; struct regmap_irq_chip_data *irq_data; }; -- cgit v1.2.3 From 038709071328ff68a936c6b8c33a24a805eea3c5 Mon Sep 17 00:00:00 2001 From: Zhu Yi Date: Wed, 13 Jun 2018 16:37:17 +0200 Subject: can: dev: enable multi-queue for SocketCAN devices The existing SocketCAN implementation provides alloc_candev() to allocate a CAN device using a single Tx and Rx queue. This can lead to priority inversion in case the single Tx queue is already full with low priority messages and a high priority message needs to be sent while the bus is fully loaded with medium priority messages. This problem can be solved by using the existing multi-queue support of the network subsytem. The commit makes it possible to use multi-queue in the CAN subsystem in the same way it is used in the Ethernet subsystem by adding an alloc_candev_mqs() call and accompanying macros. With this support a CAN device can use multi-queue qdisc (e.g. mqprio) to avoid the aforementioned priority inversion. The exisiting functionality of alloc_candev() is the same as before. CAN devices need to have prioritized multiple hardware queues or are able to abort waiting for arbitration to make sensible use of multi-queues. Signed-off-by: Zhu Yi Signed-off-by: Mark Jonas Reviewed-by: Heiko Schocher Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 055aaf5ed9af..a83e1f632eb7 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -143,7 +143,12 @@ u8 can_dlc2len(u8 can_dlc); /* map the sanitized data length to an appropriate data length code */ u8 can_len2dlc(u8 len); -struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max); +struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, + unsigned int txqs, unsigned int rxqs); +#define alloc_candev(sizeof_priv, echo_skb_max) \ + alloc_candev_mqs(sizeof_priv, echo_skb_max, 1, 1) +#define alloc_candev_mq(sizeof_priv, echo_skb_max, count) \ + alloc_candev_mqs(sizeof_priv, echo_skb_max, count, count) void free_candev(struct net_device *dev); /* a candev safe wrapper around netdev_priv */ -- cgit v1.2.3 From 1fb2e3f276ddafee81073d884f599cd2574c31e2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 17 Jul 2018 18:05:36 +0200 Subject: lib/crc: Move polynomial definition to separate header Allow other drivers and parts of kernel to use the same define for CRC32 polynomial, instead of duplicating it in many places. This code does not bring any functional changes, except moving existing code. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Herbert Xu --- include/linux/crc32poly.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/linux/crc32poly.h (limited to 'include/linux') diff --git a/include/linux/crc32poly.h b/include/linux/crc32poly.h new file mode 100644 index 000000000000..7ad5aa92d3c7 --- /dev/null +++ b/include/linux/crc32poly.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CRC32_POLY_H +#define _LINUX_CRC32_POLY_H + +/* + * There are multiple 16-bit CRC polynomials in common use, but this is + * *the* standard CRC-32 polynomial, first popularized by Ethernet. + * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0 + */ +#define CRCPOLY_LE 0xedb88320 +#define CRCPOLY_BE 0x04c11db7 + +/* + * This is the CRC32c polynomial, as outlined by Castagnoli. + * x^32+x^28+x^27+x^26+x^25+x^23+x^22+x^20+x^19+x^18+x^14+x^13+x^11+x^10+x^9+ + * x^8+x^6+x^0 + */ +#define CRC32C_POLY_LE 0x82F63B78 + +#endif /* _LINUX_CRC32_POLY_H */ -- cgit v1.2.3 From e37f2f93afe594682702439ca34eb8130598cdf2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 17 Jul 2018 18:05:37 +0200 Subject: lib/crc: Use consistent naming for CRC-32 polynomials Header was defining CRCPOLY_LE/BE and CRC32C_POLY_LE but in fact all of them are CRC-32 polynomials so use consistent naming. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Herbert Xu --- include/linux/crc32poly.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crc32poly.h b/include/linux/crc32poly.h index 7ad5aa92d3c7..62c4b7790a28 100644 --- a/include/linux/crc32poly.h +++ b/include/linux/crc32poly.h @@ -7,8 +7,8 @@ * *the* standard CRC-32 polynomial, first popularized by Ethernet. * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0 */ -#define CRCPOLY_LE 0xedb88320 -#define CRCPOLY_BE 0x04c11db7 +#define CRC32_POLY_LE 0xedb88320 +#define CRC32_POLY_BE 0x04c11db7 /* * This is the CRC32c polynomial, as outlined by Castagnoli. -- cgit v1.2.3 From f07d141fe9430cdf9f8a65a87c4136bd83b8ab2e Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 23 Jul 2018 23:16:07 +0100 Subject: dma-mapping: Generalise dma_32bit_limit flag Whilst the notion of an upstream DMA restriction is most commonly seen in PCI host bridges saddled with a 32-bit native interface, a more general version of the same issue can exist on complex SoCs where a bus or point-to-point interconnect link from a device's DMA master interface to another component along the path to memory (often an IOMMU) may carry fewer address bits than the interfaces at both ends nominally support. In order to properly deal with this, the first step is to expand the dma_32bit_limit flag into an arbitrary mask. To minimise the impact on existing code, we'll make sure to only consider this new mask valid if set. That makes sense anyway, since a mask of zero would represent DMA not being wired up at all, and that would be better handled by not providing valid ops in the first place. Signed-off-by: Robin Murphy Acked-by: Ard Biesheuvel Signed-off-by: Christoph Hellwig --- include/linux/device.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 055a69dbcd18..6d3b000be57e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -886,6 +886,8 @@ struct dev_links_info { * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all * hardware supports 64-bit addresses for consistent allocations * such descriptors. + * @bus_dma_mask: Mask of an upstream bridge or bus which imposes a smaller DMA + * limit than the device itself supports. * @dma_pfn_offset: offset of DMA memory range relatively of RAM * @dma_parms: A low level driver may set these to teach IOMMU code about * segment limitations. @@ -912,8 +914,6 @@ struct dev_links_info { * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. - * @dma_32bit_limit: bridge limited to 32bit DMA even if the device itself - * indicates support for a higher limit in the dma_mask field. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -967,6 +967,7 @@ struct device { not all hardware supports 64 bit addresses for consistent allocations such descriptors. */ + u64 bus_dma_mask; /* upstream dma_mask constraint */ unsigned long dma_pfn_offset; struct device_dma_parameters *dma_parms; @@ -1002,7 +1003,6 @@ struct device { bool offline_disabled:1; bool offline:1; bool of_node_reused:1; - bool dma_32bit_limit:1; }; static inline struct device *kobj_to_dev(struct kobject *kobj) -- cgit v1.2.3 From 9b89bc3857a6c0dfda18ddae2a42c114ecc32753 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 12 May 2018 18:18:12 +0200 Subject: nvme.h: add support for the log specific field NVMe 1.3 added a new log specific field to the get log page CQ defintion, add it to our get_log_page SQ structure. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn --- include/linux/nvme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 80dfedcf0bf7..39f05b0b8c7f 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -885,7 +885,7 @@ struct nvme_get_log_page_command { __u64 rsvd2[2]; union nvme_data_ptr dptr; __u8 lid; - __u8 rsvd10; + __u8 lsp; /* upper 4 bits reserved */ __le16 numdl; __le16 numdu; __u16 rsvd11; -- cgit v1.2.3 From 1a37621658fe06b10cf8bac02c32304d2a1c888c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 13 May 2018 18:53:57 +0200 Subject: nvme.h: add ANA definitions Add various defintions from NVMe 1.3 TP 4004. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn --- include/linux/nvme.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 47 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 39f05b0b8c7f..64c9175723de 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -242,7 +242,12 @@ struct nvme_id_ctrl { __le32 sanicap; __le32 hmminds; __le16 hmmaxd; - __u8 rsvd338[174]; + __u8 rsvd338[4]; + __u8 anatt; + __u8 anacap; + __le32 anagrpmax; + __le32 nanagrpid; + __u8 rsvd352[160]; __u8 sqes; __u8 cqes; __le16 maxcmd; @@ -258,7 +263,8 @@ struct nvme_id_ctrl { __le16 acwu; __u8 rsvd534[2]; __le32 sgls; - __u8 rsvd540[228]; + __le32 mnan; + __u8 rsvd544[224]; char subnqn[256]; __u8 rsvd1024[768]; __le32 ioccsz; @@ -312,7 +318,9 @@ struct nvme_id_ns { __le16 nabspf; __le16 noiob; __u8 nvmcap[16]; - __u8 rsvd64[40]; + __u8 rsvd64[28]; + __le32 anagrpid; + __u8 rsvd96[8]; __u8 nguid[16]; __u8 eui64[8]; struct nvme_lbaf lbaf[16]; @@ -425,6 +433,32 @@ struct nvme_effects_log { __u8 resv[2048]; }; +enum nvme_ana_state { + NVME_ANA_OPTIMIZED = 0x01, + NVME_ANA_NONOPTIMIZED = 0x02, + NVME_ANA_INACCESSIBLE = 0x03, + NVME_ANA_PERSISTENT_LOSS = 0x04, + NVME_ANA_CHANGE = 0x0f, +}; + +struct nvme_ana_group_desc { + __le32 grpid; + __le32 nnsids; + __le64 chgcnt; + __u8 state; + __u8 rsvd17[7]; + __le32 nsids[]; +}; + +/* flag for the log specific field of the ANA log */ +#define NVME_ANA_LOG_RGO (1 << 0) + +struct nvme_ana_rsp_hdr { + __le64 chgcnt; + __le16 ngrps; + __le16 rsvd10[3]; +}; + enum { NVME_SMART_CRIT_SPARE = 1 << 0, NVME_SMART_CRIT_TEMPERATURE = 1 << 1, @@ -444,11 +478,13 @@ enum { enum { NVME_AER_NOTICE_NS_CHANGED = 0x00, NVME_AER_NOTICE_FW_ACT_STARTING = 0x01, + NVME_AER_NOTICE_ANA = 0x03, }; enum { NVME_AEN_CFG_NS_ATTR = 1 << 8, NVME_AEN_CFG_FW_ACT = 1 << 9, + NVME_AEN_CFG_ANA_CHANGE = 1 << 11, }; struct nvme_lba_range_type { @@ -763,6 +799,7 @@ enum { NVME_LOG_FW_SLOT = 0x03, NVME_LOG_CHANGED_NS = 0x04, NVME_LOG_CMD_EFFECTS = 0x05, + NVME_LOG_ANA = 0x0c, NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, NVME_FWACT_REPL = (0 << 3), @@ -1185,6 +1222,13 @@ enum { NVME_SC_ACCESS_DENIED = 0x286, NVME_SC_UNWRITTEN_BLOCK = 0x287, + /* + * Path-related Errors: + */ + NVME_SC_ANA_PERSISTENT_LOSS = 0x301, + NVME_SC_ANA_INACCESSIBLE = 0x302, + NVME_SC_ANA_TRANSITION = 0x303, + NVME_SC_DNR = 0x4000, }; -- cgit v1.2.3 From 22a65aa8b1a84ca429c0fc8415dee5681ab36eb3 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 25 Dec 2017 18:40:52 +0200 Subject: net/mlx5e: Vxlan, check maximum number of UDP ports The NIC has a limited number of offloaded VXLAN UDP ports (usually 4). Instead of letting the firmware fail when trying to add more ports than it can handle, let the driver check it on its own. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 22f54bedfaae..60c2308fe062 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -668,7 +668,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 swp[0x1]; u8 swp_csum[0x1]; u8 swp_lso[0x1]; - u8 reserved_at_23[0x1b]; + u8 reserved_at_23[0xd]; + u8 max_vxlan_udp_ports[0x8]; + u8 reserved_at_38[0x6]; u8 max_geneve_opt_len[0x1]; u8 tunnel_stateless_geneve_rx[0x1]; -- cgit v1.2.3 From 358aa5ce288aa1085f0f3ef9f315119563fa6541 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Wed, 9 May 2018 13:28:00 -0700 Subject: net/mlx5e: Vxlan, move vxlan logic to core driver Move vxlan logic and objects to mlx5 core dirver. Since it going to be used from different mlx5 interfaces. e.g. mlx5e PF NIC netdev and mlx5e E-Switch representors. Signed-off-by: Saeed Mahameed Reviewed-by: Or Gerlitz --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fd0aaa5568fe..54f385cc8811 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -818,6 +818,7 @@ struct mlx5_clock { }; struct mlx5_fw_tracer; +struct mlx5_vxlan; struct mlx5_core_dev { struct pci_dev *pdev; @@ -850,6 +851,7 @@ struct mlx5_core_dev { atomic_t num_qps; u32 issi; struct mlx5e_resources mlx5e_res; + struct mlx5_vxlan *vxlan; struct { struct mlx5_rsvd_gids reserved_gids; u32 roce_en; -- cgit v1.2.3 From 627448e85c766587f6fdde1ea3886d6615081c77 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Thu, 28 Jun 2018 18:13:33 +0300 Subject: tpm: separate cmd_ready/go_idle from runtime_pm Fix tpm ptt initialization error: tpm tpm0: A TPM error (378) occurred get tpm pcr allocation. We cannot use go_idle cmd_ready commands via runtime_pm handles as with the introduction of localities this is no longer an optional feature, while runtime pm can be not enabled. Though cmd_ready/go_idle provides a power saving, it's also a part of TPM2 protocol and should be called explicitly. This patch exposes cmd_read/go_idle via tpm class ops and removes runtime pm support as it is not used by any driver. When calling from nested context always use both flags: TPM_TRANSMIT_UNLOCKED and TPM_TRANSMIT_RAW. Both are needed to resolve tpm spaces and locality request recursive calls to tpm_transmit(). TPM_TRANSMIT_RAW should never be used standalone as it will fail on double locking. While TPM_TRANSMIT_UNLOCKED standalone should be called from non-recursive locked contexts. New wrappers are added tpm_cmd_ready() and tpm_go_idle() to streamline tpm_try_transmit code. tpm_crb no longer needs own power saving functions and can drop using tpm_pm_suspend/resume. This patch cannot be really separated from the locality fix. Fixes: 888d867df441 (tpm: cmd_ready command can be issued only after granting locality) Cc: stable@vger.kernel.org Fixes: 888d867df441 (tpm: cmd_ready command can be issued only after granting locality) Signed-off-by: Tomas Winkler Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/linux/tpm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 06639fb6ab85..8eb5e5ebe136 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -43,6 +43,8 @@ struct tpm_class_ops { u8 (*status) (struct tpm_chip *chip); bool (*update_timeouts)(struct tpm_chip *chip, unsigned long *timeout_cap); + int (*go_idle)(struct tpm_chip *chip); + int (*cmd_ready)(struct tpm_chip *chip); int (*request_locality)(struct tpm_chip *chip, int loc); int (*relinquish_locality)(struct tpm_chip *chip, int loc); void (*clk_enable)(struct tpm_chip *chip, bool value); -- cgit v1.2.3 From aaae81536351f831fe6719e5b4e6afbadc5e5f85 Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Tue, 26 Jun 2018 15:09:30 -0400 Subject: tpm: Implement tpm_default_chip() to find a TPM chip Implement tpm_default_chip() to find the first TPM chip and return it to the caller while increasing the reference count on its device. This function can be used by other subsystems, such as IMA, to find the system's default TPM chip and use it for all subsequent TPM operations. Signed-off-by: Stefan Berger Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/linux/tpm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 8eb5e5ebe136..4609b94142d4 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -63,6 +63,7 @@ extern int tpm_seal_trusted(struct tpm_chip *chip, extern int tpm_unseal_trusted(struct tpm_chip *chip, struct trusted_key_payload *payload, struct trusted_key_options *options); +extern struct tpm_chip *tpm_default_chip(void); #else static inline int tpm_is_tpm2(struct tpm_chip *chip) { @@ -98,5 +99,9 @@ static inline int tpm_unseal_trusted(struct tpm_chip *chip, { return -ENODEV; } +static inline struct tpm_chip *tpm_default_chip(void) +{ + return NULL; +} #endif #endif -- cgit v1.2.3 From e15d54d5009688ccb2a5312f3b70d631615329c9 Mon Sep 17 00:00:00 2001 From: Yunlei He Date: Wed, 27 Jun 2018 14:46:21 +0800 Subject: f2fs: Allocate and stat mem used by free nid bitmap more accurately This patch used f2fs_bitmap_size macro to calculate mem used by free nid bitmap, and stat used mem including aligned part. Signed-off-by: Yunlei He Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index aa5db8b5521a..f70f8ac9c4f4 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -304,11 +304,6 @@ struct f2fs_node { * For NAT entries */ #define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry)) -#define NAT_ENTRY_BITMAP_SIZE ((NAT_ENTRY_PER_BLOCK + 7) / 8) -#define NAT_ENTRY_BITMAP_SIZE_ALIGNED \ - ((NAT_ENTRY_BITMAP_SIZE + BITS_PER_LONG - 1) / \ - BITS_PER_LONG * BITS_PER_LONG) - struct f2fs_nat_entry { __u8 version; /* latest version of cached nat entry */ -- cgit v1.2.3 From 5cbf777cfdf6e5a7b7149006e4881a255da78fdd Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 27 Jul 2018 16:37:28 +0800 Subject: route: add support for directed broadcast forwarding This patch implements the feature described in rfc1812#section-5.3.5.2 and rfc2644. It allows the router to forward directed broadcast when sysctl bc_forwarding is enabled. Note that this feature could be done by iptables -j TEE, but it would cause some problems: - target TEE's gateway param has to be set with a specific address, and it's not flexible especially when the route wants forward all directed broadcasts. - this duplicates the directed broadcasts so this may cause side effects to applications. Besides, to keep consistent with other os router like BSD, it's also necessary to implement it in the route rx path. Note that route cache needs to be flushed when bc_forwarding is changed. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 27650f1bff3d..c759d1cbcedd 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -93,6 +93,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) +#define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ -- cgit v1.2.3 From 7a4c53bee3324ac00bf964aa2f82d15d279e86e4 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 27 Jul 2018 13:43:23 -0700 Subject: net: report invalid mtu value via netlink extack If an invalid MTU value is set through rtnetlink return extra error information instead of putting message in kernel log. For other cases where there is no visible API, keep the error report in the log. Example: # ip li set dev enp12s0 mtu 10000 Error: mtu greater than device maximum. # ifconfig enp12s0 mtu 10000 SIOCSIFMTU: Invalid argument # dmesg | tail -1 [ 2047.795467] enp12s0: mtu greater than device maximum Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c1295c7a452e..9c917467a2c7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3546,6 +3546,8 @@ int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); +int dev_set_mtu_ext(struct net_device *dev, int mtu, + struct netlink_ext_ack *extack); int dev_set_mtu(struct net_device *, int); int dev_change_tx_queue_len(struct net_device *, unsigned long); void dev_set_group(struct net_device *, int); -- cgit v1.2.3 From 0969a204bfdaf7470d2666736b90a8595ae671e9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 27 Jul 2018 17:47:01 +0300 Subject: gpiolib: Use GPIOD_OUT_{LOW,HIGH} macros in open drain ones There should not be anything more than stated by the name of newly introduced constants, i.e. GPIOD_OUT_LOW_OPEN_DRAIN == GPIOD_OUT_LOW + open drain and nothing more. Make it better to read and slightly more robust by using GPIOD_OUT_LOW and GPIOD_OUT_HIGH constants with open drain flag. No functional change intended. Signed-off-by: Andy Shevchenko Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index e8aaf34dd65d..21ddbe440030 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -41,11 +41,8 @@ enum gpiod_flags { GPIOD_OUT_LOW = GPIOD_FLAGS_BIT_DIR_SET | GPIOD_FLAGS_BIT_DIR_OUT, GPIOD_OUT_HIGH = GPIOD_FLAGS_BIT_DIR_SET | GPIOD_FLAGS_BIT_DIR_OUT | GPIOD_FLAGS_BIT_DIR_VAL, - GPIOD_OUT_LOW_OPEN_DRAIN = GPIOD_FLAGS_BIT_DIR_SET | - GPIOD_FLAGS_BIT_DIR_OUT | GPIOD_FLAGS_BIT_OPEN_DRAIN, - GPIOD_OUT_HIGH_OPEN_DRAIN = GPIOD_FLAGS_BIT_DIR_SET | - GPIOD_FLAGS_BIT_DIR_OUT | GPIOD_FLAGS_BIT_DIR_VAL | - GPIOD_FLAGS_BIT_OPEN_DRAIN, + GPIOD_OUT_LOW_OPEN_DRAIN = GPIOD_OUT_LOW | GPIOD_FLAGS_BIT_OPEN_DRAIN, + GPIOD_OUT_HIGH_OPEN_DRAIN = GPIOD_OUT_HIGH | GPIOD_FLAGS_BIT_OPEN_DRAIN, }; #ifdef CONFIG_GPIOLIB -- cgit v1.2.3 From f39b948dbeaf9da0dfd17e68704f38fe4237788f Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Thu, 26 Jul 2018 14:45:53 +0800 Subject: dmaengine: add a new helper dmaenginem_async_device_register This patch adds the dmaenginem_async_device_register for DMA code. Use the Devres to call the release for the DMA engine driver. Signed-off-by: Huang Shijie Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c8c3a7a93802..d49ec5c31944 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1406,6 +1406,7 @@ static inline int dmaengine_desc_free(struct dma_async_tx_descriptor *desc) /* --- DMA device --- */ int dma_async_device_register(struct dma_device *device); +int dmaenginem_async_device_register(struct dma_device *device); void dma_async_device_unregister(struct dma_device *device); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); struct dma_chan *dma_get_slave_channel(struct dma_chan *chan); -- cgit v1.2.3 From 51c23b47e6b8590ea7a6a6776ffb21810ece73bf Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 13 Jul 2018 14:54:45 +0200 Subject: netfilter: nf_osf: add nf_osf_find() This new function returns the OS genre as a string. Plan is to use to from the new nft_osf extension. Note that this doesn't yet support ttl options, but it could be easily extended to do so. Tested-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_osf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h index 0e114c492fb8..aee460fcbd31 100644 --- a/include/linux/netfilter/nf_osf.h +++ b/include/linux/netfilter/nf_osf.h @@ -1,3 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NFOSF_H +#define _NFOSF_H + #include /* Initial window size option state machine: multiple of mss, mtu or @@ -31,3 +35,8 @@ bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, int hooknum, struct net_device *in, struct net_device *out, const struct nf_osf_info *info, struct net *net, const struct list_head *nf_osf_fingers); + +const char *nf_osf_find(const struct sk_buff *skb, + const struct list_head *nf_osf_fingers); + +#endif /* _NFOSF_H */ -- cgit v1.2.3 From f609e7a0f3956e3b03af735b83600a4eef2a04ec Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 7 Jun 2018 15:55:25 -0400 Subject: media: sii9234: remove unused header The include/linux/platform_data/media/sii9234.h header file is unused, let's remove it. Signed-off-by: Corentin Labbe Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/media/sii9234.h | 24 ------------------------ 1 file changed, 24 deletions(-) delete mode 100644 include/linux/platform_data/media/sii9234.h (limited to 'include/linux') diff --git a/include/linux/platform_data/media/sii9234.h b/include/linux/platform_data/media/sii9234.h deleted file mode 100644 index 6a4a809fe9a3..000000000000 --- a/include/linux/platform_data/media/sii9234.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * Driver header for SII9234 MHL converter chip. - * - * Copyright (c) 2011 Samsung Electronics, Co. Ltd - * Contact: Tomasz Stanislawski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#ifndef SII9234_H -#define SII9234_H - -/** - * @gpio_n_reset: GPIO driving nRESET pin - */ - -struct sii9234_platform_data { - int gpio_n_reset; -}; - -#endif /* SII9234_H */ -- cgit v1.2.3 From 489cae632fc04927e8ef36ac8d8847193a41df3b Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Tue, 24 Jul 2018 10:33:19 -0600 Subject: include: Move ascii85 functions from i915 to linux/ascii85.h The i915 DRM driver very cleverly used ascii85 encoding for their GPU state file. Move the encode functions to a general header file to support other drivers that might be interested in the same functionality. v4: Make the return value const char * as suggested by Chris Wilson v3: Fix error_puts -> err_puts pointed out by the 01.org bot v2: Update API to be cleaner for the caller as suggested by Chris Wilson Reviewed-by: Chris Wilson Signed-off-by: Jordan Crouse Signed-off-by: Rob Clark --- include/linux/ascii85.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/linux/ascii85.h (limited to 'include/linux') diff --git a/include/linux/ascii85.h b/include/linux/ascii85.h new file mode 100644 index 000000000000..4cc40201273e --- /dev/null +++ b/include/linux/ascii85.h @@ -0,0 +1,38 @@ +/* + * SPDX-License-Identifier: GPL-2.0 + * + * Copyright (c) 2008 Intel Corporation + * Copyright (c) 2018 The Linux Foundation. All rights reserved. + */ + +#ifndef _ASCII85_H_ +#define _ASCII85_H_ + +#include + +#define ASCII85_BUFSZ 6 + +static inline long +ascii85_encode_len(long len) +{ + return DIV_ROUND_UP(len, 4); +} + +static inline const char * +ascii85_encode(u32 in, char *out) +{ + int i; + + if (in == 0) + return "z"; + + out[5] = '\0'; + for (i = 5; i--; ) { + out[i] = '!' + in % 85; + in /= 85; + } + + return out; +} + +#endif -- cgit v1.2.3 From a5ec5a7bfd1f28d1905499641c9f589be36808c1 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Fri, 27 Jul 2018 13:47:02 -0700 Subject: ata: ahci: Support state with min power but Partial low power state MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently when min_power policy is selected, the partial low power state is not entered and link will try aggressively enter to only slumber state. Add a new policy which still enable DEVSLP but also try to enter partial low power state. This policy is presented as "min_power_with_partial". For information the difference between partial and slumber Partial – PHY logic is powered up, and in a reduced power state. The link PM exit latency to active state maximum is 10 ns. Slumber – PHY logic is powered up, and in a reduced power state. The link PM exit latency to active state maximum is 10 ms. Devslp – PHY logic is powered down. The link PM exit latency from this state to active state maximum is 20 ms, unless otherwise specified by DETO. Suggested-and-reviewed-by: Hans de Goede Signed-off-by: Srinivas Pandruvada Signed-off-by: Tejun Heo --- include/linux/libata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index aa8583655a18..80c2bd202367 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -522,7 +522,8 @@ enum ata_lpm_policy { ATA_LPM_MAX_POWER, ATA_LPM_MED_POWER, ATA_LPM_MED_POWER_WITH_DIPM, /* Med power + DIPM as win IRST does */ - ATA_LPM_MIN_POWER, + ATA_LPM_MIN_POWER_WITH_PARTIAL, /* Min Power + partial and slumber */ + ATA_LPM_MIN_POWER, /* Min power + no partial (slumber only) */ }; enum ata_lpm_hints { -- cgit v1.2.3 From c454edc21b12dd7d416de6c81555e87aaec9685c Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 30 Jul 2018 10:10:01 -0400 Subject: block: don't account for split bio's size in cgroup stats We need to check in blkcg_bio_issue_check if the bio is flagged as QUEUE_ENTERED, because if it is then we've already accounted for the size of the IO in the cgroup stats. We can still however account for the extra IO since it'll be another request. Reported-by: Tejun Heo Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 3bed5e02a873..f7b910768306 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -769,8 +769,14 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, if (!throtl) { blkg = blkg ?: q->root_blkg; - blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf, - bio->bi_iter.bi_size); + /* + * If the bio is flagged with BIO_QUEUE_ENTERED it means this + * is a split bio and we would have already accounted for the + * size of the bio. + */ + if (!bio_flagged(bio, BIO_QUEUE_ENTERED)) + blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf, + bio->bi_iter.bi_size); blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } -- cgit v1.2.3 From ddd0bc756983dc4d19000a4fe021b4c7f9d59aab Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Mon, 30 Jul 2018 00:15:31 +0300 Subject: block: move ref_tag calculation func to the block layer Currently this function is implemented in the scsi layer, but it's actual place should be the block layer since T10-PI is a general data integrity feature that is used in the nvme protocol as well. Suggested-by: Christoph Hellwig Cc: Martin K. Petersen Signed-off-by: Max Gurtovoy Signed-off-by: Jens Axboe --- include/linux/t10-pi.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index c6aa8a3c42ed..c40511f4e63d 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -37,6 +37,16 @@ struct t10_pi_tuple { #define T10_PI_APP_ESCAPE cpu_to_be16(0xffff) #define T10_PI_REF_ESCAPE cpu_to_be32(0xffffffff) +static inline u32 t10_pi_ref_tag(struct request *rq) +{ +#ifdef CONFIG_BLK_DEV_INTEGRITY + return blk_rq_pos(rq) >> + (rq->q->integrity.interval_exp - 9) & 0xffffffff; +#else + return -1U; +#endif +} + extern const struct blk_integrity_profile t10_pi_type1_crc; extern const struct blk_integrity_profile t10_pi_type1_ip; extern const struct blk_integrity_profile t10_pi_type3_crc; -- cgit v1.2.3 From 10c41ddd61323b27b447bc8e18296ac6c06107ad Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Mon, 30 Jul 2018 00:15:32 +0300 Subject: block: move dif_prepare/dif_complete functions to block layer Currently these functions are implemented in the scsi layer, but their actual place should be the block layer since T10-PI is a general data integrity feature that is used in the nvme protocol as well. Also, use the tuple size from the integrity profile since it may vary between integrity types. Suggested-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Max Gurtovoy Signed-off-by: Jens Axboe --- include/linux/t10-pi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index c40511f4e63d..5a427c289f58 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -51,5 +51,8 @@ extern const struct blk_integrity_profile t10_pi_type1_crc; extern const struct blk_integrity_profile t10_pi_type1_ip; extern const struct blk_integrity_profile t10_pi_type3_crc; extern const struct blk_integrity_profile t10_pi_type3_ip; +extern void t10_pi_prepare(struct request *rq, u8 protection_type); +extern void t10_pi_complete(struct request *rq, u8 protection_type, + unsigned int intervals); #endif -- cgit v1.2.3 From 82b98ca566ca2af170eb0ab50cef09dd7335fa55 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Thu, 5 Jul 2018 16:48:50 +0000 Subject: net/sunrpc: Make rpc_auth_create_args a const This turns rpc_auth_create_args into a const as it gets passed through the auth stack. Signed-off-by: Sargun Dhillon Signed-off-by: Anna Schumaker --- include/linux/sunrpc/auth.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index d9af474a857d..58a6765c1c5e 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -125,7 +125,8 @@ struct rpc_authops { struct module *owner; rpc_authflavor_t au_flavor; /* flavor (RPC_AUTH_*) */ char * au_name; - struct rpc_auth * (*create)(struct rpc_auth_create_args *, struct rpc_clnt *); + struct rpc_auth * (*create)(const struct rpc_auth_create_args *, + struct rpc_clnt *); void (*destroy)(struct rpc_auth *); int (*hash_cred)(struct auth_cred *, unsigned int); @@ -174,7 +175,7 @@ struct rpc_cred * rpc_lookup_generic_cred(struct auth_cred *, int, gfp_t); struct rpc_cred * rpc_lookup_machine_cred(const char *service_name); int rpcauth_register(const struct rpc_authops *); int rpcauth_unregister(const struct rpc_authops *); -struct rpc_auth * rpcauth_create(struct rpc_auth_create_args *, +struct rpc_auth * rpcauth_create(const struct rpc_auth_create_args *, struct rpc_clnt *); void rpcauth_release(struct rpc_auth *); rpc_authflavor_t rpcauth_get_pseudoflavor(rpc_authflavor_t, -- cgit v1.2.3 From e6753f23d961d601dbae50a2fc2a3975c9715b14 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Mon, 30 Jul 2018 15:24:22 -0700 Subject: tracepoint: Make rcuidle tracepoint callers use SRCU In recent tests with IRQ on/off tracepoints, a large performance overhead ~10% is noticed when running hackbench. This is root caused to calls to rcu_irq_enter_irqson and rcu_irq_exit_irqson from the tracepoint code. Following a long discussion on the list [1] about this, we concluded that srcu is a better alternative for use during rcu idle. Although it does involve extra barriers, its lighter than the sched-rcu version which has to do additional RCU calls to notify RCU idle about entry into RCU sections. In this patch, we change the underlying implementation of the trace_*_rcuidle API to use SRCU. This has shown to improve performance alot for the high frequency irq enable/disable tracepoints. Test: Tested idle and preempt/irq tracepoints. Here are some performance numbers: With a run of the following 30 times on a single core x86 Qemu instance with 1GB memory: hackbench -g 4 -f 2 -l 3000 Completion times in seconds. CONFIG_PROVE_LOCKING=y. No patches (without this series) Mean: 3.048 Median: 3.025 Std Dev: 0.064 With Lockdep using irq tracepoints with RCU implementation: Mean: 3.451 (-11.66 %) Median: 3.447 (-12.22%) Std Dev: 0.049 With Lockdep using irq tracepoints with SRCU implementation (this series): Mean: 3.020 (I would consider the improvement against the "without this series" case as just noise). Median: 3.013 Std Dev: 0.033 [1] https://patchwork.kernel.org/patch/10344297/ [remove rcu_read_lock_sched_notrace as its the equivalent of preempt_disable_notrace and is unnecessary to call in tracepoint code] Link: http://lkml.kernel.org/r/20180730222423.196630-3-joel@joelfernandes.org Cleaned-up-by: Peter Zijlstra Acked-by: Peter Zijlstra Reviewed-by: Mathieu Desnoyers Signed-off-by: Joel Fernandes (Google) [ Simplified WARN_ON_ONCE() ] Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 40 ++++++++++++++++++++++++++++++++-------- 1 file changed, 32 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 19a690b559ca..d9a084c72541 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -15,6 +15,7 @@ */ #include +#include #include #include #include @@ -33,6 +34,8 @@ struct trace_eval_map { #define TRACEPOINT_DEFAULT_PRIO 10 +extern struct srcu_struct tracepoint_srcu; + extern int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data); extern int @@ -75,10 +78,16 @@ int unregister_tracepoint_module_notifier(struct notifier_block *nb) * probe unregistration and the end of module exit to make sure there is no * caller executing a probe when it is freed. */ +#ifdef CONFIG_TRACEPOINTS static inline void tracepoint_synchronize_unregister(void) { + synchronize_srcu(&tracepoint_srcu); synchronize_sched(); } +#else +static inline void tracepoint_synchronize_unregister(void) +{ } +#endif #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS extern int syscall_regfunc(void); @@ -129,18 +138,31 @@ extern void syscall_unregfunc(void); * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto". */ -#define __DO_TRACE(tp, proto, args, cond, rcucheck) \ +#define __DO_TRACE(tp, proto, args, cond, rcuidle) \ do { \ struct tracepoint_func *it_func_ptr; \ void *it_func; \ void *__data; \ + int __maybe_unused idx = 0; \ \ if (!(cond)) \ return; \ - if (rcucheck) \ - rcu_irq_enter_irqson(); \ - rcu_read_lock_sched_notrace(); \ - it_func_ptr = rcu_dereference_sched((tp)->funcs); \ + \ + /* srcu can't be used from NMI */ \ + WARN_ON_ONCE(rcuidle && in_nmi()); \ + \ + /* keep srcu and sched-rcu usage consistent */ \ + preempt_disable_notrace(); \ + \ + /* \ + * For rcuidle callers, use srcu since sched-rcu \ + * doesn't work from the idle path. \ + */ \ + if (rcuidle) \ + idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + \ + it_func_ptr = rcu_dereference_raw((tp)->funcs); \ + \ if (it_func_ptr) { \ do { \ it_func = (it_func_ptr)->func; \ @@ -148,9 +170,11 @@ extern void syscall_unregfunc(void); ((void(*)(proto))(it_func))(args); \ } while ((++it_func_ptr)->func); \ } \ - rcu_read_unlock_sched_notrace(); \ - if (rcucheck) \ - rcu_irq_exit_irqson(); \ + \ + if (rcuidle) \ + srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + \ + preempt_enable_notrace(); \ } while (0) #ifndef MODULE -- cgit v1.2.3 From 760c435e0f85ed19e48a90d746ce1de2cd02def7 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 19 Jul 2018 00:09:12 +0200 Subject: mtd: rawnand: make subop helpers return unsigned values A report from Colin Ian King pointed a CoverityScan issue where error values on these helpers where not checked in the drivers. These helpers can error out only in case of a software bug in driver code, not because of a runtime/hardware error. Hence, let's WARN_ON() in this case and return 0 which is harmless anyway. Fixes: 8878b126df76 ("mtd: nand: add ->exec_op() implementation") Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index f60fad29eae6..598d356de83f 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1007,14 +1007,14 @@ struct nand_subop { unsigned int last_instr_end_off; }; -int nand_subop_get_addr_start_off(const struct nand_subop *subop, - unsigned int op_id); -int nand_subop_get_num_addr_cyc(const struct nand_subop *subop, - unsigned int op_id); -int nand_subop_get_data_start_off(const struct nand_subop *subop, - unsigned int op_id); -int nand_subop_get_data_len(const struct nand_subop *subop, - unsigned int op_id); +unsigned int nand_subop_get_addr_start_off(const struct nand_subop *subop, + unsigned int op_id); +unsigned int nand_subop_get_num_addr_cyc(const struct nand_subop *subop, + unsigned int op_id); +unsigned int nand_subop_get_data_start_off(const struct nand_subop *subop, + unsigned int op_id); +unsigned int nand_subop_get_data_len(const struct nand_subop *subop, + unsigned int op_id); /** * struct nand_op_parser_addr_constraints - Constraints for address instructions -- cgit v1.2.3 From 7da45139d264f3b7ead04e00ebb29b189cf9826e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 17 Jul 2018 09:08:02 +0200 Subject: mtd: rawnand: better name for the controller structure In the raw NAND core, a NAND chip is described by a nand_chip structure, while a NAND controller is described with a nand_hw_control structure which is not very meaningful. Rename this structure nand_controller. As the structure gets renamed, it is logical to also rename the core function initializing it from nand_hw_control_init() to nand_controller_init(). Lastly, the 'hwcontrol' entry of the nand_chip structure is not meaningful neither while it has the role of fallback when no controller structure is provided by the driver (the controller driver is dumb and can only control a single chip). Thus, it is renamed dummy_controller. Signed-off-by: Miquel Raynal Acked-by: Boris Brezillon --- include/linux/mtd/rawnand.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 598d356de83f..93a2678e0f0d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -510,20 +510,21 @@ struct nand_id { }; /** - * struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices + * struct nand_controller - Structure used to describe a NAND controller + * * @lock: protection lock * @active: the mtd device which holds the controller currently * @wq: wait queue to sleep on if a NAND operation is in * progress used instead of the per chip wait queue * when a hw controller is available. */ -struct nand_hw_control { +struct nand_controller { spinlock_t lock; struct nand_chip *active; wait_queue_head_t wq; }; -static inline void nand_hw_control_init(struct nand_hw_control *nfc) +static inline void nand_controller_init(struct nand_controller *nfc) { nfc->active = NULL; spin_lock_init(&nfc->lock); @@ -1197,7 +1198,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure * @buf_align: minimum buffer alignment required by a platform - * @hwcontrol: platform-specific hardware control structure + * @dummy_controller: dummy controller implementation for drivers that can + * only control a single chip * @erase: [REPLACEABLE] erase function * @chip_delay: [BOARDSPECIFIC] chip dependent delay for transferring * data from array to read regs (tR). @@ -1333,11 +1335,11 @@ struct nand_chip { flstate_t state; uint8_t *oob_poi; - struct nand_hw_control *controller; + struct nand_controller *controller; struct nand_ecc_ctrl ecc; unsigned long buf_align; - struct nand_hw_control hwcontrol; + struct nand_controller dummy_controller; uint8_t *bbt; struct nand_bbt_descr *bbt_td; -- cgit v1.2.3 From 05b54c7bac906c443fd0b23ab8954e0560b33e5c Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 19 Jul 2018 01:05:46 +0200 Subject: mtd: rawnand: add hooks that may be called during nand_scan() In order to remove the limitation that forbids dynamic allocation in nand_scan_ident(), we must create a path that will be the same for all controller drivers. The idea is to use nand_scan() instead of the widely used nand_scan_ident()/nand_scan_tail() couple. In order to achieve this, controller drivers will need to adjust some parameters between these two functions depending on the NAND chip wired on them. This takes the form of two new hooks (->{attach,detach}_chip()) that are placed in a new nand_controller_ops structure, which is then attached to the nand_controller object at driver initialization time. ->attach_chip() is called between nand_scan_ident() and nand_scan_tail(), and ->detach_chip() is called in the error path of nand_scan() and in nand_cleanup(). Note that some NAND controller drivers don't have a dedicated nand_controller object and instead rely on the default/dummy one embedded in nand_chip. If you're in this case and still want to initialize the controller ops, you'll have to manipulate chip->dummy_controller directly. Last but not least, it's worth mentioning that we plan to move some of the controller related hooks placed in nand_chip into nand_controller_ops to make the separation between NAND chip and NAND controller methods clearer. Signed-off-by: Miquel Raynal Acked-by: Boris Brezillon --- include/linux/mtd/rawnand.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 93a2678e0f0d..fbd6b29cf22c 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -509,6 +509,25 @@ struct nand_id { int len; }; +/** + * struct nand_controller_ops - Controller operations + * + * @attach_chip: this method is called after the NAND detection phase after + * flash ID and MTD fields such as erase size, page size and OOB + * size have been set up. ECC requirements are available if + * provided by the NAND chip or device tree. Typically used to + * choose the appropriate ECC configuration and allocate + * associated resources. + * This hook is optional. + * @detach_chip: free all resources allocated/claimed in + * nand_controller_ops->attach_chip(). + * This hook is optional. + */ +struct nand_controller_ops { + int (*attach_chip)(struct nand_chip *chip); + void (*detach_chip)(struct nand_chip *chip); +}; + /** * struct nand_controller - Structure used to describe a NAND controller * @@ -517,11 +536,13 @@ struct nand_id { * @wq: wait queue to sleep on if a NAND operation is in * progress used instead of the per chip wait queue * when a hw controller is available. + * @ops: NAND controller operations. */ struct nand_controller { spinlock_t lock; struct nand_chip *active; wait_queue_head_t wq; + const struct nand_controller_ops *ops; }; static inline void nand_controller_init(struct nand_controller *nfc) -- cgit v1.2.3 From 98732da1a08ebb666983d469981a8b994e77d556 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 25 Jul 2018 15:31:50 +0200 Subject: mtd: rawnand: do not export nand_scan_[ident|tail]() anymore Both nand_scan_ident() and nand_scan_tail() helpers used to be called directly from controller drivers that needed to tweak some ECC-related parameters before nand_scan_tail(). This separation prevented dynamic allocations during the phase of NAND identification, which was inconvenient. All controller drivers have been moved to use nand_scan(), in conjunction with the chip->ecc.[attach|detach]_chip() hooks that actually do the required tweaking sequence between both ident/tail calls, allowing programmers to use dynamic allocation as they need all across the scanning sequence. Declare nand_scan_[ident|tail]() statically now. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon --- include/linux/mtd/rawnand.h | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index fbd6b29cf22c..71571ed23a20 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -35,17 +35,6 @@ static inline int nand_scan(struct mtd_info *mtd, int max_chips) return nand_scan_with_ids(mtd, max_chips, NULL); } -/* - * Separate phases of nand_scan(), allowing board driver to intervene - * and override command or ECC setup according to flash type. - */ -int nand_scan_ident(struct mtd_info *mtd, int max_chips, - struct nand_flash_dev *table); -int nand_scan_tail(struct mtd_info *mtd); - -/* Unregister the MTD device and free resources held by the NAND device */ -void nand_release(struct mtd_info *mtd); - /* Internal helper for board drivers which need to override command function */ void nand_wait_ready(struct mtd_info *mtd); @@ -1745,8 +1734,13 @@ int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len, int nand_write_data_op(struct nand_chip *chip, const void *buf, unsigned int len, bool force_8bit); -/* Free resources held by the NAND device */ +/* + * Free resources held by the NAND device, must be called on error after a + * sucessful nand_scan(). + */ void nand_cleanup(struct nand_chip *chip); +/* Unregister the MTD device and calls nand_cleanup() */ +void nand_release(struct mtd_info *mtd); /* Default extended ID decoding function */ void nand_decode_ext_id(struct nand_chip *chip); -- cgit v1.2.3 From 2023f1fa216f30b1877d65be2057fbaf0bbd49b3 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 25 Jul 2018 15:31:51 +0200 Subject: mtd: rawnand: allocate model parameter dynamically Thanks to the migration of all drivers to use nand_scan() and the related nand_controller_ops, we can now allocate data during the detection phase. Let's do it first for the NAND model parameter which is allocated in nand_detect(). Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 71571ed23a20..099fa166569a 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -476,7 +476,7 @@ struct onfi_params { */ struct nand_parameters { /* Generic parameters */ - char model[100]; + const char *model; bool supports_set_get_features; DECLARE_BITMAP(set_feature_list, ONFI_FEATURE_NUMBER); DECLARE_BITMAP(get_feature_list, ONFI_FEATURE_NUMBER); -- cgit v1.2.3 From 56e6c104e4f151e19eb410004405ec52b4f8605a Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 31 Jul 2018 13:06:57 +0200 Subject: console: Replace #if 0 with atomic var 'ignore_console_lock_warning' The macro WARN_CONSOLE_UNLOCKED prints a warning when a thread enters the console's critical section without having acquired the console lock. The console lock can be ignored when debugging the console using printk, but this makes WARN_CONSOLE_UNLOCKED generate unnecessary warnings. The variable ignore_console_lock_warning temporarily disables WARN_CONSOLE_UNLOCKED. Developers interested in debugging the console's critical sections should increment it before entering the CS and decrement it after leaving the CS. Setting ignore_console_lock_warning is only for debugging. Regular operation should not manipulate it. Acknoledgements: This patch is based on an earlier version by Steven Rostedt. The use of atomic increment/decrement was suggested by Petr Mladek. Link: http://lkml.kernel.org/r/717e6337-e7a6-7a92-1c1b-8929a25696b5@suse.de Signed-off-by: Thomas Zimmermann Acked-by: Hans de Goede Acked-by: Petr Mladek Reviewed-by: Sergey Senozhatsky Cc: Steven Rostedt (VMware) Cc: Andrew Morton [b.zolnierkie: use ] Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/console.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index f59f3dbca65c..ec9bdb3d7bab 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -14,6 +14,7 @@ #ifndef _LINUX_CONSOLE_H_ #define _LINUX_CONSOLE_H_ 1 +#include #include struct vc_data; @@ -201,11 +202,14 @@ void vcs_make_sysfs(int index); void vcs_remove_sysfs(int index); /* Some debug stub to catch some of the obvious races in the VT code */ -#if 1 -#define WARN_CONSOLE_UNLOCKED() WARN_ON(!is_console_locked() && !oops_in_progress) -#else -#define WARN_CONSOLE_UNLOCKED() -#endif +#define WARN_CONSOLE_UNLOCKED() \ + WARN_ON(!atomic_read(&ignore_console_lock_warning) && \ + !is_console_locked() && !oops_in_progress) +/* + * Increment ignore_console_lock_warning if you need to quiet + * WARN_CONSOLE_UNLOCKED() for debugging purposes. + */ +extern atomic_t ignore_console_lock_warning; /* VESA Blanking Levels */ #define VESA_NO_BLANKING 0 -- cgit v1.2.3 From 11785ef53228d23ec386f5fe4a34601536f0c891 Mon Sep 17 00:00:00 2001 From: Jorge Sanjuan Date: Tue, 31 Jul 2018 13:28:42 +0100 Subject: ALSA: usb-audio: Initial Power Domain support Thee USB Audio Class 3 (UAC3) introduces Power Domains as a new feature to let a host turn individual parts of an audio function to different power states via USB requests. This lets the device get to know a bit amore about what the host is up to in order to optimize power consumption efficiently. The Power Domains are optional for UAC3 configuration but all UAC3 devices shall include at least one BADD configuration where the support for Power Domains is compulsory. This patch adds a set of features/helpers to parse these power domains and change their status. Signed-off-by: Jorge Sanjuan Signed-off-by: Takashi Iwai --- include/linux/usb/audio-v3.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h index 334bfa6dfb47..6b708434b7f9 100644 --- a/include/linux/usb/audio-v3.h +++ b/include/linux/usb/audio-v3.h @@ -447,4 +447,8 @@ struct uac3_interrupt_data_msg { /* BADD sample rate is always fixed to 48kHz */ #define UAC3_BADD_SAMPLING_RATE 48000 +/* BADD power domains recovery times in 50us increments */ +#define UAC3_BADD_PD_RECOVER_D1D0 0x0258 /* 30ms */ +#define UAC3_BADD_PD_RECOVER_D2D0 0x1770 /* 300ms */ + #endif /* __LINUX_USB_AUDIO_V3_H */ -- cgit v1.2.3 From 08fcf813281ebcf72c69487c1501ad91b7121cdb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 31 Jul 2018 09:10:26 -0600 Subject: t10-pi: provide empty t10_pi_complete() for !CONFIG_BLK_DEV_INTEGRITY Fixes a link failure whtn BLK_DEV_INTEGRITY isn't defined. Fixes: 10c41ddd6132 ("block: move dif_prepare/dif_complete functions to block layer") Signed-off-by: Jens Axboe --- include/linux/t10-pi.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index 5a427c289f58..b9626aa7e90c 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -51,8 +51,19 @@ extern const struct blk_integrity_profile t10_pi_type1_crc; extern const struct blk_integrity_profile t10_pi_type1_ip; extern const struct blk_integrity_profile t10_pi_type3_crc; extern const struct blk_integrity_profile t10_pi_type3_ip; + +#ifdef CONFIG_BLK_DEV_INTEGRITY extern void t10_pi_prepare(struct request *rq, u8 protection_type); extern void t10_pi_complete(struct request *rq, u8 protection_type, unsigned int intervals); +#else +static inline void t10_pi_complete(struct request *rq, u8 protection_type, + unsigned int intervals) +{ +} +static inline void t10_pi_prepare(struct request *rq, u8 protection_type) +{ +} +#endif #endif -- cgit v1.2.3 From c3bc8fd637a9623f5c507bd18f9677effbddf584 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Mon, 30 Jul 2018 15:24:23 -0700 Subject: tracing: Centralize preemptirq tracepoints and unify their usage This patch detaches the preemptirq tracepoints from the tracers and keeps it separate. Advantages: * Lockdep and irqsoff event can now run in parallel since they no longer have their own calls. * This unifies the usecase of adding hooks to an irqsoff and irqson event, and a preemptoff and preempton event. 3 users of the events exist: - Lockdep - irqsoff and preemptoff tracers - irqs and preempt trace events The unification cleans up several ifdefs and makes the code in preempt tracer and irqsoff tracers simpler. It gets rid of all the horrific ifdeferry around PROVE_LOCKING and makes configuration of the different users of the tracepoints more easy and understandable. It also gets rid of the time_* function calls from the lockdep hooks used to call into the preemptirq tracer which is not needed anymore. The negative delta in lines of code in this patch is quite large too. In the patch we introduce a new CONFIG option PREEMPTIRQ_TRACEPOINTS as a single point for registering probes onto the tracepoints. With this, the web of config options for preempt/irq toggle tracepoints and its users becomes: PREEMPT_TRACER PREEMPTIRQ_EVENTS IRQSOFF_TRACER PROVE_LOCKING | | \ | | \ (selects) / \ \ (selects) / TRACE_PREEMPT_TOGGLE ----> TRACE_IRQFLAGS \ / \ (depends on) / PREEMPTIRQ_TRACEPOINTS Other than the performance tests mentioned in the previous patch, I also ran the locking API test suite. I verified that all tests cases are passing. I also injected issues by not registering lockdep probes onto the tracepoints and I see failures to confirm that the probes are indeed working. This series + lockdep probes not registered (just to inject errors): [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12:FAILED|FAILED| ok | [ 0.000000] sirq-safe-A => hirqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | With this series + lockdep probes registered, all locking tests pass: [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | Link: http://lkml.kernel.org/r/20180730222423.196630-4-joel@joelfernandes.org Acked-by: Peter Zijlstra (Intel) Reviewed-by: Namhyung Kim Signed-off-by: Joel Fernandes (Google) Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 11 +---------- include/linux/irqflags.h | 11 ++++++++--- include/linux/lockdep.h | 8 +++++--- include/linux/preempt.h | 2 +- 4 files changed, 15 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 63af5eb0ff46..a397907e8d72 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -701,16 +701,7 @@ static inline unsigned long get_lock_parent_ip(void) return CALLER_ADDR2; } -#ifdef CONFIG_IRQSOFF_TRACER - extern void time_hardirqs_on(unsigned long a0, unsigned long a1); - extern void time_hardirqs_off(unsigned long a0, unsigned long a1); -#else - static inline void time_hardirqs_on(unsigned long a0, unsigned long a1) { } - static inline void time_hardirqs_off(unsigned long a0, unsigned long a1) { } -#endif - -#if defined(CONFIG_PREEMPT_TRACER) || \ - (defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS)) +#ifdef CONFIG_TRACE_PREEMPT_TOGGLE extern void trace_preempt_on(unsigned long a0, unsigned long a1); extern void trace_preempt_off(unsigned long a0, unsigned long a1); #else diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 9700f00bbc04..50edb9cbbd26 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -15,9 +15,16 @@ #include #include -#ifdef CONFIG_TRACE_IRQFLAGS +/* Currently trace_softirqs_on/off is used only by lockdep */ +#ifdef CONFIG_PROVE_LOCKING extern void trace_softirqs_on(unsigned long ip); extern void trace_softirqs_off(unsigned long ip); +#else +# define trace_softirqs_on(ip) do { } while (0) +# define trace_softirqs_off(ip) do { } while (0) +#endif + +#ifdef CONFIG_TRACE_IRQFLAGS extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); # define trace_hardirq_context(p) ((p)->hardirq_context) @@ -43,8 +50,6 @@ do { \ #else # define trace_hardirqs_on() do { } while (0) # define trace_hardirqs_off() do { } while (0) -# define trace_softirqs_on(ip) do { } while (0) -# define trace_softirqs_off(ip) do { } while (0) # define trace_hardirq_context(p) 0 # define trace_softirq_context(p) 0 # define trace_hardirqs_enabled(p) 0 diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 6fc77d4dbdcd..a8113357ceeb 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -266,7 +266,8 @@ struct held_lock { /* * Initialization, self-test and debugging-output methods: */ -extern void lockdep_info(void); +extern void lockdep_init(void); +extern void lockdep_init_early(void); extern void lockdep_reset(void); extern void lockdep_reset_lock(struct lockdep_map *lock); extern void lockdep_free_key_range(void *start, unsigned long size); @@ -406,7 +407,8 @@ static inline void lockdep_on(void) # define lock_downgrade(l, i) do { } while (0) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) -# define lockdep_info() do { } while (0) +# define lockdep_init() do { } while (0) +# define lockdep_init_early() do { } while (0) # define lockdep_init_map(lock, name, key, sub) \ do { (void)(name); (void)(key); } while (0) # define lockdep_set_class(lock, key) do { (void)(key); } while (0) @@ -532,7 +534,7 @@ do { \ #endif /* CONFIG_LOCKDEP */ -#ifdef CONFIG_TRACE_IRQFLAGS +#ifdef CONFIG_PROVE_LOCKING extern void print_irqtrace_events(struct task_struct *curr); #else static inline void print_irqtrace_events(struct task_struct *curr) diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 5bd3f151da78..c01813c3fbe9 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -150,7 +150,7 @@ */ #define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET) -#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER) +#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE) extern void preempt_count_add(int val); extern void preempt_count_sub(int val); #define preempt_count_dec_and_test() \ -- cgit v1.2.3 From 44bda4b7d26e9fffed6d7152d98a2e9edaeb2a76 Mon Sep 17 00:00:00 2001 From: Hari Vyas Date: Tue, 3 Jul 2018 14:35:41 +0530 Subject: PCI: Fix is_added/is_busmaster race condition When a PCI device is detected, pdev->is_added is set to 1 and proc and sysfs entries are created. When the device is removed, pdev->is_added is checked for one and then device is detached with clearing of proc and sys entries and at end, pdev->is_added is set to 0. is_added and is_busmaster are bit fields in pci_dev structure sharing same memory location. A strange issue was observed with multiple removal and rescan of a PCIe NVMe device using sysfs commands where is_added flag was observed as zero instead of one while removing device and proc,sys entries are not cleared. This causes issue in later device addition with warning message "proc_dir_entry" already registered. Debugging revealed a race condition between the PCI core setting the is_added bit in pci_bus_add_device() and the NVMe driver reset work-queue setting the is_busmaster bit in pci_set_master(). As these fields are not handled atomically, that clears the is_added bit. Move the is_added bit to a separate private flag variable and use atomic functions to set and retrieve the device addition state. This avoids the race because is_added no longer shares a memory location with is_busmaster. Link: https://bugzilla.kernel.org/show_bug.cgi?id=200283 Signed-off-by: Hari Vyas Signed-off-by: Bjorn Helgaas Reviewed-by: Lukas Wunner Acked-by: Michael Ellerman --- include/linux/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index abd5d5e17aee..c133ccfa002e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -368,7 +368,6 @@ struct pci_dev { unsigned int transparent:1; /* Subtractive decode bridge */ unsigned int multifunction:1; /* Multi-function device */ - unsigned int is_added:1; unsigned int is_busmaster:1; /* Is busmaster */ unsigned int no_msi:1; /* May not use MSI */ unsigned int no_64bit_msi:1; /* May only use 32-bit MSIs */ -- cgit v1.2.3 From c29c2ebd2ae0066c026045a21aa33ccbfcd8bb3c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 30 Jul 2018 20:43:51 -0700 Subject: net: update real_num_rx_queues even when !CONFIG_SYSFS We used to depend on real_num_rx_queues as a upper bound for sanity checks. For AF_XDP socket validation it's useful if the check behaves the same regardless of CONFIG_SYSFS setting. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9c917467a2c7..3bf7e93c9e96 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3431,8 +3431,9 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq); int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq); #else static inline int netif_set_real_num_rx_queues(struct net_device *dev, - unsigned int rxq) + unsigned int rxqs) { + dev->real_num_rx_queues = rxqs; return 0; } #endif -- cgit v1.2.3 From 84c6b86875e01a08a0daa6fdd4a01b36bf0bf0b2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 30 Jul 2018 20:43:53 -0700 Subject: xsk: don't allow umem replace at stack level MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently drivers have to check if they already have a umem installed for a given queue and return an error if so. Make better use of XDP_QUERY_XSK_UMEM and move this functionality to the core. We need to keep rtnl across the calls now. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Björn Töpel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3bf7e93c9e96..282e2e95ad5b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -872,10 +872,10 @@ struct netdev_bpf { struct { struct bpf_offloaded_map *offmap; }; - /* XDP_SETUP_XSK_UMEM */ + /* XDP_QUERY_XSK_UMEM, XDP_SETUP_XSK_UMEM */ struct { - struct xdp_umem *umem; - u16 queue_id; + struct xdp_umem *umem; /* out for query*/ + u16 queue_id; /* in for query */ } xsk; }; }; @@ -3568,6 +3568,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags); u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, enum bpf_netdev_command cmd); +int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); -- cgit v1.2.3 From 016583d7030cec9b69e0d55269a5967f4ee871d2 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Tue, 31 Jul 2018 10:10:51 -0400 Subject: sunrpc: Change rpc_print_iostats to rpc_clnt_show_stats and handle rpc_clnt clones The existing rpc_print_iostats has a few shortcomings. First, the naming is not consistent with other functions in the kernel that display stats. Second, it is really displaying stats for an rpc_clnt structure as it displays both xprt stats and per-op stats. Third, it does not handle rpc_clnt clones, which is important for the one in-kernel tree caller of this function, the NFS client's nfs_show_stats function. Fix all of the above by renaming the rpc_print_iostats to rpc_clnt_show_stats and looping through any rpc_clnt clones via cl_parent. Once this interface is fixed, this addresses a problem with NFSv4. Before this patch, the /proc/self/mountstats always showed incorrect counts for NFSv4 lease and session related opcodes such as SEQUENCE, RENEW, SETCLIENTID, CREATE_SESSION, etc. These counts were always 0 even though many ops would go over the wire. The reason for this is there are multiple rpc_clnt structures allocated for any given NFSv4 mount, and inside nfs_show_stats() we callled into rpc_print_iostats() which only handled one of them, nfs_server->client. Fix these counts by calling sunrpc's new rpc_clnt_show_stats() function, which handles cloned rpc_clnt structs and prints the stats together. Note that one side-effect of the above is that multiple mounts from the same NFS server will show identical counts in the above ops due to the fact the one rpc_clnt (representing the NFSv4 client state) is shared across mounts. Signed-off-by: Dave Wysochanski Signed-off-by: Anna Schumaker --- include/linux/sunrpc/metrics.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h index 9baed7b355b2..1b3751327575 100644 --- a/include/linux/sunrpc/metrics.h +++ b/include/linux/sunrpc/metrics.h @@ -82,7 +82,7 @@ void rpc_count_iostats(const struct rpc_task *, struct rpc_iostats *); void rpc_count_iostats_metrics(const struct rpc_task *, struct rpc_iostats *); -void rpc_print_iostats(struct seq_file *, struct rpc_clnt *); +void rpc_clnt_show_stats(struct seq_file *, struct rpc_clnt *); void rpc_free_iostats(struct rpc_iostats *); #else /* CONFIG_PROC_FS */ @@ -95,7 +95,7 @@ static inline void rpc_count_iostats_metrics(const struct rpc_task *task, { } -static inline void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) {} +static inline void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt) {} static inline void rpc_free_iostats(struct rpc_iostats *stats) {} #endif /* CONFIG_PROC_FS */ -- cgit v1.2.3 From 0f90be132cbf1537d87a6a8b9e80867adac892f6 Mon Sep 17 00:00:00 2001 From: Bill Baker Date: Tue, 19 Jun 2018 16:24:58 -0500 Subject: NFSv4 client live hangs after live data migration recovery After a live data migration event at the NFS server, the client may send I/O requests to the wrong server, causing a live hang due to repeated recovery events. On the wire, this will appear as an I/O request failing with NFS4ERR_BADSESSION, followed by successful CREATE_SESSION, repeatedly. NFS4ERR_BADSSESSION is returned because the session ID being used was issued by the other server and is not valid at the old server. The failure is caused by async worker threads having cached the transport (xprt) in the rpc_task structure. After the migration recovery completes, the task is redispatched and the task resends the request to the wrong server based on the old value still present in tk_xprt. The solution is to recompute the tk_xprt field of the rpc_task structure so that the request goes to the correct server. Signed-off-by: Bill Baker Reviewed-by: Chuck Lever Tested-by: Helen Chao Fixes: fb43d17210ba ("SUNRPC: Use the multipath iterator to assign a ...") Cc: stable@vger.kernel.org # v4.9+ Signed-off-by: Anna Schumaker --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 9b11b6a0978c..73d5c4a870fa 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -156,6 +156,7 @@ int rpc_switch_client_transport(struct rpc_clnt *, void rpc_shutdown_client(struct rpc_clnt *); void rpc_release_client(struct rpc_clnt *); +void rpc_task_release_transport(struct rpc_task *); void rpc_task_release_client(struct rpc_task *); int rpcb_create_local(struct net *); -- cgit v1.2.3 From e6476c21447c4b17c47e476aade6facf050f31e8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 30 Jul 2018 09:45:07 +0200 Subject: net: remove bogus RCU annotations on socket.wq We never use RCU protection for it, just a lot of cargo-cult rcu_deference_protects calls. Note that we do keep the kfree_rcu call for it, as the references through struct sock are RCU protected and thus might require a grace period before freeing. Signed-off-by: Christoph Hellwig Reviewed-by: Eric Dumazet Acked-by: Paul E. McKenney Signed-off-by: David S. Miller --- include/linux/net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 6554d3ba4396..e0930678c8bf 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -114,7 +114,7 @@ struct socket { unsigned long flags; - struct socket_wq __rcu *wq; + struct socket_wq *wq; struct file *file; struct sock *sk; -- cgit v1.2.3 From 7209049d40dc37791ce0f3738965296f30e26044 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 31 Jul 2018 17:27:02 -0400 Subject: dm kcopyd: return void from dm_kcopyd_copy() dm_kcopyd_copy() only ever returns 0 so there is no need for callers to account for possible failure. Same goes for dm_kcopyd_zero(). Signed-off-by: Mike Snitzer --- include/linux/dm-kcopyd.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index cfac8588ed56..e42de7750c88 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -62,9 +62,9 @@ void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc); typedef void (*dm_kcopyd_notify_fn)(int read_err, unsigned long write_err, void *context); -int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, - unsigned num_dests, struct dm_io_region *dests, - unsigned flags, dm_kcopyd_notify_fn fn, void *context); +void dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, + unsigned num_dests, struct dm_io_region *dests, + unsigned flags, dm_kcopyd_notify_fn fn, void *context); /* * Prepare a callback and submit it via the kcopyd thread. @@ -81,9 +81,9 @@ void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc, dm_kcopyd_notify_fn fn, void *context); void dm_kcopyd_do_callback(void *job, int read_err, unsigned long write_err); -int dm_kcopyd_zero(struct dm_kcopyd_client *kc, - unsigned num_dests, struct dm_io_region *dests, - unsigned flags, dm_kcopyd_notify_fn fn, void *context); +void dm_kcopyd_zero(struct dm_kcopyd_client *kc, + unsigned num_dests, struct dm_io_region *dests, + unsigned flags, dm_kcopyd_notify_fn fn, void *context); #endif /* __KERNEL__ */ #endif /* _LINUX_DM_KCOPYD_H */ -- cgit v1.2.3 From 546c596cf5491fda1516536e049c6a36836eb884 Mon Sep 17 00:00:00 2001 From: Shunyong Yang Date: Wed, 18 Jul 2018 09:40:35 +0800 Subject: PCI: Unify PCI and normal DMA direction definitions Current DMA direction definitions in pci-dma-compat.h and dma-direction.h are mirrored in value. Unify them to enhance readability and avoid possible inconsistency. Signed-off-by: Shunyong Yang Signed-off-by: Bjorn Helgaas Cc: Joey Zheng --- include/linux/dma-direction.h | 6 ++---- include/linux/pci-dma-compat.h | 8 ++++---- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direction.h b/include/linux/dma-direction.h index 3649a031893a..9c96e30e6a0b 100644 --- a/include/linux/dma-direction.h +++ b/include/linux/dma-direction.h @@ -1,14 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_DMA_DIRECTION_H #define _LINUX_DMA_DIRECTION_H -/* - * These definitions mirror those in pci.h, so they can be used - * interchangeably with their PCI_ counterparts. - */ + enum dma_data_direction { DMA_BIDIRECTIONAL = 0, DMA_TO_DEVICE = 1, DMA_FROM_DEVICE = 2, DMA_NONE = 3, }; + #endif diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h index 0dd1a3f7b309..c3f1b44ade29 100644 --- a/include/linux/pci-dma-compat.h +++ b/include/linux/pci-dma-compat.h @@ -8,10 +8,10 @@ #include /* This defines the direction arg to the DMA mapping routines. */ -#define PCI_DMA_BIDIRECTIONAL 0 -#define PCI_DMA_TODEVICE 1 -#define PCI_DMA_FROMDEVICE 2 -#define PCI_DMA_NONE 3 +#define PCI_DMA_BIDIRECTIONAL DMA_BIDIRECTIONAL +#define PCI_DMA_TODEVICE DMA_TO_DEVICE +#define PCI_DMA_FROMDEVICE DMA_FROM_DEVICE +#define PCI_DMA_NONE DMA_NONE static inline void * pci_alloc_consistent(struct pci_dev *hwdev, size_t size, -- cgit v1.2.3 From bb276262e88dae52cc717bb636b7468f66bb234e Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 27 Jul 2018 11:33:13 -0700 Subject: mtd: spi-nor: only apply reset hacks to broken hardware Commit 59b356ffd0b0 ("mtd: m25p80: restore the status of SPI flash when exiting") is the latest from a long history of attempts to add reboot handling to handle stateful addressing modes on SPI flash. Some prior mostly-related discussions: http://lists.infradead.org/pipermail/linux-mtd/2013-March/046343.html [PATCH 1/3] mtd: m25p80: utilize dedicated 4-byte addressing commands http://lists.infradead.org/pipermail/barebox/2014-September/020682.html [RFC] MTD m25p80 3-byte addressing and boot problem http://lists.infradead.org/pipermail/linux-mtd/2015-February/057683.html [PATCH 2/2] m25p80: if supported put chip to deep power down if not used Previously, attempts to add reboot-time software reset handling were rejected, but the latest attempt was not. Quick summary of the problem: Some systems (e.g., boot ROM or bootloader) assume that they can read initial boot code from their SPI flash using 3-byte addressing. If the flash is left in 4-byte mode after reset, these systems won't boot. The above patch provided a shutdown/remove hook to attempt to reset the addressing mode before we reboot. Notably, this patch misses out on huge classes of unexpected reboots (e.g., crashes, watchdog resets). Unfortunately, it is essentially impossible to solve this problem 100%: if your system doesn't know how to reset the SPI flash to power-on defaults at initialization time, no amount of software can really rescue you -- there will always be a chance of some unexpected reset that leaves your flash in an addressing mode that your boot sequence didn't expect. While it is not directly harmful to perform hacks like the aforementioned commit on all 4-byte addressing flash, a properly-designed system should not need the hack -- and in fact, providing this hack may mask the fact that a given system is indeed broken. So this patch attempts to apply this unsound hack more narrowly, providing a strong suggestion to developers and system designers that this is truly a hack. With luck, system designers can catch their errors early on in their development cycle, rather than applying this hack long term. But apparently enough systems are out in the wild that we still have to provide this hack. Document a new device tree property to denote systems that do not have a proper hardware (or software) reset mechanism, and apply the hack (with a loud warning) only in this case. Signed-off-by: Brian Norris Reviewed-by: Guenter Roeck Signed-off-by: Boris Brezillon --- include/linux/mtd/spi-nor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index e60da0d34cc1..c922e97f205a 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -235,6 +235,7 @@ enum spi_nor_option_flags { SNOR_F_S3AN_ADDR_DEFAULT = BIT(3), SNOR_F_READY_XSR_RDY = BIT(4), SNOR_F_USE_CLSR = BIT(5), + SNOR_F_BROKEN_RESET = BIT(6), }; /** -- cgit v1.2.3 From 3d3fe3c05d5a17ebdf55b936c51017c127c0ed44 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 25 Jul 2018 15:31:52 +0200 Subject: mtd: rawnand: allocate dynamically ONFI parameters during detection Now that it is possible to do dynamic allocations during the identification phase, convert the onfi_params structure (which is only needed with ONFI compliant chips) into a pointer that will be allocated only if needed. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon --- include/linux/mtd/rawnand.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 099fa166569a..efb2345359bb 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -482,7 +482,7 @@ struct nand_parameters { DECLARE_BITMAP(get_feature_list, ONFI_FEATURE_NUMBER); /* ONFI parameters */ - struct onfi_params onfi; + struct onfi_params *onfi; }; /* The maximum expected count of bytes in the NAND ID sequence */ @@ -1618,10 +1618,10 @@ struct platform_nand_data { /* return the supported asynchronous timing mode. */ static inline int onfi_get_async_timing_mode(struct nand_chip *chip) { - if (!chip->parameters.onfi.version) + if (!chip->parameters.onfi) return ONFI_TIMING_MODE_UNKNOWN; - return chip->parameters.onfi.async_timing_mode; + return chip->parameters.onfi->async_timing_mode; } int onfi_fill_data_interface(struct nand_chip *chip, -- cgit v1.2.3 From 304d34360b099020a12af2abb7e1ac506f4ba16d Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sat, 28 Jul 2018 10:19:13 +0200 Subject: spi: add flags parameter to txrx_word function pointers Add the capability to specify the flag parameter used in bitbang_txrx_be_cpha{0,1} through the txrx_word function pointers of spi_bitbang data structure. That feature will be used to add spi-3wire support to the spi-gpio controller Signed-off-by: Lorenzo Bianconi Signed-off-by: Mark Brown --- include/linux/spi/spi_bitbang.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index c1e61641a7f1..5847f00ef9cf 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -30,7 +30,7 @@ struct spi_bitbang { /* txrx_word[SPI_MODE_*]() just looks like a shift register */ u32 (*txrx_word[4])(struct spi_device *spi, unsigned nsecs, - u32 word, u8 bits); + u32 word, u8 bits, unsigned flags); }; /* you can call these default bitbang->master methods from your custom -- cgit v1.2.3 From 4b859db2c60692560afbfef1b030d0ddef57b7ee Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sat, 28 Jul 2018 10:19:14 +0200 Subject: spi: spi-gpio: add SPI_3WIRE support Add SPI_3WIRE support to spi-gpio controller introducing set_line_direction function pointer in spi_bitbang data structure. Spi-gpio controller has been tested using hts221 temp/rh iio sensor running in 3wire mode and lsm6dsm running in 4wire mode Signed-off-by: Lorenzo Bianconi Signed-off-by: Mark Brown --- include/linux/spi/spi_bitbang.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index 5847f00ef9cf..b7e021b274dc 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -31,6 +31,7 @@ struct spi_bitbang { u32 (*txrx_word[4])(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits, unsigned flags); + int (*set_line_direction)(struct spi_device *spi, bool output); }; /* you can call these default bitbang->master methods from your custom -- cgit v1.2.3 From ba113c3aa79a7f941ac162d05a3620bdc985c58d Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 31 Jul 2018 17:46:21 -0700 Subject: tcp: add data bytes sent stats Introduce a new TCP stat to record the number of bytes sent (RFC4898 tcpEStatsPerfHCDataOctetsOut) and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 58a8d7d71354..d0798dcd2cab 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -181,6 +181,9 @@ struct tcp_sock { u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut * total number of data segments sent. */ + u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut + * total number of data bytes sent. + */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked * sum(delta(snd_una)), or how many bytes * were acked. -- cgit v1.2.3 From fb31c9b9f6c85b1bad569ecedbde78d9e37cd87b Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 31 Jul 2018 17:46:22 -0700 Subject: tcp: add data bytes retransmitted stats Introduce a new TCP stat to record the number of bytes retransmitted (RFC4898 tcpEStatsPerfOctetsRetrans) and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index d0798dcd2cab..fb67f9a51b95 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -333,6 +333,9 @@ struct tcp_sock { * the first SYN. */ u32 undo_marker; /* snd_una upon a new recovery episode. */ int undo_retrans; /* number of undoable retransmissions. */ + u64 bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans + * Total data bytes retransmitted + */ u32 total_retrans; /* Total retransmits for entire connection */ u32 urg_seq; /* Seq of received urgent pointer */ -- cgit v1.2.3 From 7e10b6554ff2ce7f86d5d3eec3af5db8db482caa Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 31 Jul 2018 17:46:23 -0700 Subject: tcp: add dsack blocks received stats Introduce a new TCP stat to record the number of DSACK blocks received (RFC4989 tcpEStatsStackDSACKDups) and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index fb67f9a51b95..da6281c549a5 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -188,6 +188,9 @@ struct tcp_sock { * sum(delta(snd_una)), or how many bytes * were acked. */ + u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups + * total number of DSACK blocks received + */ u32 snd_una; /* First byte we want an ack for */ u32 snd_sml; /* Last byte of the most recently transmitted small packet */ u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ -- cgit v1.2.3 From 7ec65372ca534217b53fd208500cf7aac223a383 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 31 Jul 2018 17:46:24 -0700 Subject: tcp: add stat of data packet reordering events Introduce a new TCP stats to record the number of reordering events seen and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Application can use this stats to track the frequency of the reordering events in addition to the existing reordering stats which tracks the magnitude of the latest reordering event. Note: this new stats tracks reordering events triggered by ACKs, which could often be fewer than the actual number of packets being delivered out-of-order. Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index da6281c549a5..263e37271afd 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -220,8 +220,7 @@ struct tcp_sock { #define TCP_RACK_RECOVERY_THRESH 16 u8 reo_wnd_persist:5, /* No. of recovery since last adj */ dsack_seen:1, /* Whether DSACK seen after last adj */ - advanced:1, /* mstamp advanced since last lost marking */ - reord:1; /* reordering detected */ + advanced:1; /* mstamp advanced since last lost marking */ } rack; u16 advmss; /* Advertised MSS */ u8 compressed_ack; @@ -267,6 +266,7 @@ struct tcp_sock { u8 ecn_flags; /* ECN status bits. */ u8 keepalive_probes; /* num of allowed keep alive probes */ u32 reordering; /* Packet reordering metric. */ + u32 reord_seen; /* number of data packet reordering events */ u32 snd_up; /* Urgent pointer */ /* -- cgit v1.2.3 From 8b11ec1b5ffb54f71cb5a5e5c8c4d36e5d113085 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 1 Aug 2018 13:43:38 -0700 Subject: mm: do not initialize TLB stack vma's with vma_init() Commit 2c4541e24c55 ("mm: use vma_init() to initialize VMAs on stack and data segments") tried to initialize various left-over ad-hoc vma's "properly", but actually made things worse for the temporary vma's used for TLB flushing. vma_init() doesn't actually initialize all of the vma, just a few fields, so doing something like - struct vm_area_struct vma = { .vm_mm = tlb->mm, }; + struct vm_area_struct vma; + + vma_init(&vma, tlb->mm); was actually very bad: instead of having a nicely initialized vma with every field but "vm_mm" zeroed, you'd have an entirely uninitialized vma with only a couple of fields initialized. And they weren't even fields that the code in question mostly cared about. The flush_tlb_range() function takes a "struct vma" rather than a "struct mm_struct", because a few architectures actually care about what kind of range it is - being able to only do an ITLB flush if it's a range that doesn't have data accesses enabled, for example. And all the normal users already have the vma for doing the range invalidation. But a few people want to call flush_tlb_range() with a range they just made up, so they also end up using a made-up vma. x86 just has a special "flush_tlb_mm_range()" function for this, but other architectures (arm and ia64) do the "use fake vma" thing instead, and thus got caught up in the vma_init() changes. At the same time, the TLB flushing code really doesn't care about most other fields in the vma, so vma_init() is just unnecessary and pointless. This fixes things by having an explicit "this is just an initializer for the TLB flush" initializer macro, which is used by the arm/arm64/ia64 people who mis-use this interface with just a dummy vma. Fixes: 2c4541e24c55 ("mm: use vma_init() to initialize VMAs on stack and data segments") Cc: Dmitry Vyukov Cc: Oleg Nesterov Cc: Andrea Arcangeli Cc: Kirill Shutemov Cc: Andrew Morton Cc: John Stultz Cc: Hugh Dickins Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7ba6d356d18f..68a5121694ef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -466,6 +466,9 @@ static inline void vma_set_anonymous(struct vm_area_struct *vma) vma->vm_ops = NULL; } +/* flush_tlb_range() takes a vma, not a mm, and can care about flags */ +#define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } + struct mmu_gather; struct inode; -- cgit v1.2.3 From 3ebea280d7e9b610fa3d31c9cfd556b1705eeedf Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 1 Aug 2018 21:08:30 -0400 Subject: ring-buffer: Make ring_buffer_record_is_on() return bool The value of ring_buffer_record_is_on() is either true or false, so have its return value be bool. Signed-off-by: Steven Rostedt (VMware) --- include/linux/ring_buffer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 003d09ab308d..5176124fc4ba 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -164,7 +164,7 @@ void ring_buffer_record_disable(struct ring_buffer *buffer); void ring_buffer_record_enable(struct ring_buffer *buffer); void ring_buffer_record_off(struct ring_buffer *buffer); void ring_buffer_record_on(struct ring_buffer *buffer); -int ring_buffer_record_is_on(struct ring_buffer *buffer); +bool ring_buffer_record_is_on(struct ring_buffer *buffer); int ring_buffer_record_is_set_on(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); -- cgit v1.2.3 From d7224c0e128c7337c0b0f66ac20921fbbf4efc14 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 1 Aug 2018 21:09:50 -0400 Subject: ring-buffer: Make ring_buffer_record_is_set_on() return bool The value of ring_buffer_record_is_set_on() is either true or false, so have its return value be bool. Signed-off-by: Steven Rostedt (VMware) --- include/linux/ring_buffer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 5176124fc4ba..0940fda59872 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -165,7 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer); void ring_buffer_record_off(struct ring_buffer *buffer); void ring_buffer_record_on(struct ring_buffer *buffer); bool ring_buffer_record_is_on(struct ring_buffer *buffer); -int ring_buffer_record_is_set_on(struct ring_buffer *buffer); +bool ring_buffer_record_is_set_on(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); -- cgit v1.2.3 From c971e6a006175bd0f195c6346c4e8bc4089bec00 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 28 May 2018 18:27:19 -0400 Subject: kill d_instantiate_no_diralias() The only user is fuse_create_new_entry(), and there it's used to mitigate the same mkdir/open-by-handle race as in nfs_mkdir(). The same solution applies - unhash the mkdir argument, then call d_splice_alias() and if that returns a reference to preexisting alias, dput() and report success. ->mkdir() argument left unhashed negative with the preexisting alias moved in the right place is just fine from the ->mkdir() callers point of view. Cc: Miklos Szeredi Signed-off-by: Al Viro --- include/linux/dcache.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 66c6e17e61e5..0b83629a3d8f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -227,7 +227,6 @@ extern void d_instantiate(struct dentry *, struct inode *); extern void d_instantiate_new(struct dentry *, struct inode *); extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *); extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *); -extern int d_instantiate_no_diralias(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); -- cgit v1.2.3 From 7acece71a517cad83a0842a94d94c13f271b680c Mon Sep 17 00:00:00 2001 From: Chris Brandt Date: Tue, 31 Jul 2018 05:41:38 -0500 Subject: serial: sh-sci: Remove SCIx_RZ_SCIFA_REGTYPE There is no more need for SCIx_RZ_SCIFA_REGTYPE now that SCIx_SH4_SCIF_REGTYPE can provide the same register/address definitions. Also, R7S9210 no longer needs a special compatible since the standard "renesas,scif" will work just fine. Signed-off-by: Chris Brandt Reviewed-by: Geert Uytterhoeven Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_sci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 1c89611e0e06..c0e795d95477 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -36,7 +36,6 @@ enum { SCIx_SH4_SCIF_FIFODATA_REGTYPE, SCIx_SH7705_SCIF_REGTYPE, SCIx_HSCIF_REGTYPE, - SCIx_RZ_SCIFA_REGTYPE, SCIx_NR_REGTYPES, }; -- cgit v1.2.3 From d3b26dd7cb0e3433bfd3c1d4dcf74c6039bb49fb Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Thu, 2 Aug 2018 03:08:23 +0000 Subject: Drivers: hv: vmbus: Reset the channel callback in vmbus_onoffer_rescind() Before setting channel->rescind in vmbus_rescind_cleanup(), we should make sure the channel callback won't run any more, otherwise a high-level driver like pci_hyperv, which may be infinitely waiting for the host VSP's response and notices the channel has been rescinded, can't safely give up: e.g., in hv_pci_protocol_negotiation() -> wait_for_response(), it's unsafe to exit from wait_for_response() and proceed with the on-stack variable "comp_pkt" popped. The issue was originally spotted by Michael Kelley . In vmbus_close_internal(), the patch also minimizes the range protected by disabling/enabling channel->callback_event: we don't really need that for the whole function. Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Cc: stable@vger.kernel.org Cc: K. Y. Srinivasan Cc: Stephen Hemminger Cc: Michael Kelley Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2330f08062c7..efda23cf32c7 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1061,6 +1061,8 @@ extern int vmbus_establish_gpadl(struct vmbus_channel *channel, extern int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle); +void vmbus_reset_channel_cb(struct vmbus_channel *channel); + extern int vmbus_recvpacket(struct vmbus_channel *channel, void *buffer, u32 bufferlen, -- cgit v1.2.3 From 72755eed6c1c5312425ad3d78bf0b916769e6125 Mon Sep 17 00:00:00 2001 From: Roman Kiryanov Date: Mon, 23 Jul 2018 15:47:26 -0700 Subject: goldfish: Add missing includes to goldfish.h goldfish.h refers to external symbols such as dma_addr_t and writel. This causes compilation errors if this file is included before other header files. The mentioned symbols are defined in types.h (dma_addr_t) and io.h (writel). Signed-off-by: Roman Kiryanov Signed-off-by: Greg Kroah-Hartman --- include/linux/goldfish.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/goldfish.h b/include/linux/goldfish.h index 2835c150c3ff..159b4191f15d 100644 --- a/include/linux/goldfish.h +++ b/include/linux/goldfish.h @@ -2,6 +2,9 @@ #ifndef __LINUX_GOLDFISH_H #define __LINUX_GOLDFISH_H +#include +#include + /* Helpers for Goldfish virtual platform */ static inline void gf_write_ptr(const void *ptr, void __iomem *portl, -- cgit v1.2.3 From 68275680ea12e9f378e51ff525dacbb76f006764 Mon Sep 17 00:00:00 2001 From: Roman Kiryanov Date: Mon, 23 Jul 2018 15:47:27 -0700 Subject: goldfish: Use dedicated macros instead of manual bit shifting There are dedicated macros (lower_32_bits and upper_32_bits) available to extract the lower and upper 32 bits. They provide better readability and could prevent some compilation warnings. Signed-off-by: Roman Kiryanov Signed-off-by: Greg Kroah-Hartman --- include/linux/goldfish.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/goldfish.h b/include/linux/goldfish.h index 159b4191f15d..265a099cd3b8 100644 --- a/include/linux/goldfish.h +++ b/include/linux/goldfish.h @@ -2,6 +2,7 @@ #ifndef __LINUX_GOLDFISH_H #define __LINUX_GOLDFISH_H +#include #include #include @@ -10,9 +11,11 @@ static inline void gf_write_ptr(const void *ptr, void __iomem *portl, void __iomem *porth) { - writel((u32)(unsigned long)ptr, portl); + const unsigned long addr = (unsigned long)ptr; + + writel(lower_32_bits(addr), portl); #ifdef CONFIG_64BIT - writel((unsigned long)ptr >> 32, porth); + writel(upper_32_bits(addr), porth); #endif } @@ -20,9 +23,9 @@ static inline void gf_write_dma_addr(const dma_addr_t addr, void __iomem *portl, void __iomem *porth) { - writel((u32)addr, portl); + writel(lower_32_bits(addr), portl); #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT - writel(addr >> 32, porth); + writel(upper_32_bits(addr), porth); #endif } -- cgit v1.2.3 From 06bcb5168d7d49aa3ed449ff13a6d13c30afc3f0 Mon Sep 17 00:00:00 2001 From: Frieder Schrempf Date: Thu, 2 Aug 2018 14:53:52 +0200 Subject: spi: spi-mem: Fix a typo in the documentation of struct spi_mem Fix a typo in the @drvpriv description. Signed-off-by: Frieder Schrempf Acked-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index bb4bd15ae1f6..951a2e949d5f 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -122,7 +122,7 @@ struct spi_mem_op { /** * struct spi_mem - describes a SPI memory device * @spi: the underlying SPI device - * @drvpriv: spi_mem_drviver private data + * @drvpriv: spi_mem_driver private data * * Extra information that describe the SPI memory device and may be needed by * the controller to properly handle this device should be placed here. -- cgit v1.2.3 From 5d27a9c8ea9e967d00b92a76d4bb242bf7692f2b Mon Sep 17 00:00:00 2001 From: Frieder Schrempf Date: Thu, 2 Aug 2018 14:53:53 +0200 Subject: spi: spi-mem: Extend the SPI mem interface to set a custom memory name When porting (Q)SPI controller drivers from the MTD layer to the SPI layer, the naming scheme for the memory devices changes. To be able to keep compatibility with the old drivers naming scheme, a name field is added to struct spi_mem and a hook is added to let controller drivers set a custom name for the memory device. Example for the FSL QSPI driver: Name with the old driver: 21e0000.qspi, or with multiple devices: 21e0000.qspi-0, 21e0000.qspi-1, ... Name with the new driver without spi_mem_get_name: spi4.0 Suggested-by: Boris Brezillon Signed-off-by: Frieder Schrempf Reviewed-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 951a2e949d5f..0d64ccc4e584 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -123,6 +123,7 @@ struct spi_mem_op { * struct spi_mem - describes a SPI memory device * @spi: the underlying SPI device * @drvpriv: spi_mem_driver private data + * @name: name of the SPI memory device * * Extra information that describe the SPI memory device and may be needed by * the controller to properly handle this device should be placed here. @@ -133,6 +134,7 @@ struct spi_mem_op { struct spi_mem { struct spi_device *spi; void *drvpriv; + char *name; }; /** @@ -165,6 +167,13 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem) * limitations) * @supports_op: check if an operation is supported by the controller * @exec_op: execute a SPI memory operation + * @get_name: get a custom name for the SPI mem device from the controller. + * This might be needed if the controller driver has been ported + * to use the SPI mem layer and a custom name is used to keep + * mtdparts compatible. + * Note that if the implementation of this function allocates memory + * dynamically, then it should do so with devm_xxx(), as we don't + * have a ->free_name() function. * * This interface should be implemented by SPI controllers providing an * high-level interface to execute SPI memory operation, which is usually the @@ -176,6 +185,7 @@ struct spi_controller_mem_ops { const struct spi_mem_op *op); int (*exec_op)(struct spi_mem *mem, const struct spi_mem_op *op); + const char *(*get_name)(struct spi_mem *mem); }; /** @@ -234,6 +244,8 @@ bool spi_mem_supports_op(struct spi_mem *mem, int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op); +const char *spi_mem_get_name(struct spi_mem *mem); + int spi_mem_driver_register_with_owner(struct spi_mem_driver *drv, struct module *owner); -- cgit v1.2.3 From 5a5ba10f44fa1cd081cec38389e1b47f438fe25b Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 26 Jul 2018 15:40:56 +0200 Subject: rtc: remove struct rtc_task Include rtc_task members directly in rtc_timer member. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index bf4d375025d1..6aedc30003e7 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -87,16 +87,11 @@ struct rtc_class_ops { int (*set_offset)(struct device *, long offset); }; -typedef struct rtc_task { - void (*func)(void *private_data); - void *private_data; -} rtc_task_t; - - struct rtc_timer { - struct rtc_task task; struct timerqueue_node node; ktime_t period; + void (*func)(void *private_data); + void *private_data; int enabled; }; -- cgit v1.2.3 From a83c0ea79d8b5705d09a39c73224332f9170a903 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sat, 30 Jun 2018 17:54:59 +0300 Subject: docs/mm: bootmem: add kernel-doc description of 'struct bootmem_data' Signed-off-by: Mike Rapoport Signed-off-by: Jonathan Corbet --- include/linux/bootmem.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 7942a96b1a9d..42515195d7d8 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -27,9 +27,20 @@ extern unsigned long max_pfn; extern unsigned long long max_possible_pfn; #ifndef CONFIG_NO_BOOTMEM -/* - * node_bootmem_map is a map pointer - the bits represent all physical - * memory pages (including holes) on the node. +/** + * struct bootmem_data - per-node information used by the bootmem allocator + * @node_min_pfn: the starting physical address of the node's memory + * @node_low_pfn: the end physical address of the directly addressable memory + * @node_bootmem_map: is a bitmap pointer - the bits represent all physical + * memory pages (including holes) on the node. + * @last_end_off: the offset within the page of the end of the last allocation; + * if 0, the page used is full + * @hint_idx: the PFN of the page used with the last allocation; + * together with using this with the @last_end_offset field, + * a test can be made to see if allocations can be merged + * with the page used for the last allocation rather than + * using up a full new page. + * @list: list entry in the linked list ordered by the memory addresses */ typedef struct bootmem_data { unsigned long node_min_pfn; -- cgit v1.2.3 From e1720fee27246dfb84f7c433e35367170a2d4436 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sat, 30 Jun 2018 17:55:01 +0300 Subject: mm/memblock: add a name for memblock flags enumeration Since kernel-doc does not like anonymous enums the name is required for adding documentation. While on it, I've also updated all the function declarations to use 'enum memblock_flags' instead of unsigned long. Signed-off-by: Mike Rapoport Signed-off-by: Jonathan Corbet --- include/linux/memblock.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index ca59883c8364..8b8fbceffd4d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -21,7 +21,7 @@ #define INIT_PHYSMEM_REGIONS 4 /* Definition of memblock flags. */ -enum { +enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ MEMBLOCK_MIRROR = 0x2, /* mirrored region */ @@ -31,7 +31,7 @@ enum { struct memblock_region { phys_addr_t base; phys_addr_t size; - unsigned long flags; + enum memblock_flags flags; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif @@ -72,7 +72,7 @@ void memblock_discard(void); phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, - int nid, ulong flags); + int nid, enum memblock_flags flags); phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align); void memblock_allow_resize(void); @@ -89,19 +89,19 @@ int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); -ulong choose_memblock_flags(void); +enum memblock_flags choose_memblock_flags(void); /* Low level functions */ int memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, - int nid, unsigned long flags); + int nid, enum memblock_flags flags); -void __next_mem_range(u64 *idx, int nid, ulong flags, +void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); -void __next_mem_range_rev(u64 *idx, int nid, ulong flags, +void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); @@ -253,13 +253,13 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL) static inline void memblock_set_region_flags(struct memblock_region *r, - unsigned long flags) + enum memblock_flags flags) { r->flags |= flags; } static inline void memblock_clear_region_flags(struct memblock_region *r, - unsigned long flags) + enum memblock_flags flags) { r->flags &= ~flags; } @@ -317,10 +317,10 @@ static inline bool memblock_bottom_up(void) phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, - ulong flags); + enum memblock_flags flags); phys_addr_t memblock_alloc_base_nid(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr, - int nid, ulong flags); + int nid, enum memblock_flags flags); phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr); phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align, -- cgit v1.2.3 From 47cec4432ab06c4ba90c241b142a016f878ac6da Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sat, 30 Jun 2018 17:55:02 +0300 Subject: docs/mm: memblock: update kernel-doc comments * make memblock_discard description kernel-doc compatible * add brief description for memblock_setclr_flag and describe its parameters * fixup return value descriptions Signed-off-by: Mike Rapoport Signed-off-by: Jonathan Corbet --- include/linux/memblock.h | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8b8fbceffd4d..63704c64583a 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -239,7 +239,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, /** * for_each_resv_unavail_range - iterate through reserved and unavailable memory * @i: u64 used as loop variable - * @flags: pick from blocks based on memory attributes * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @@ -367,8 +366,10 @@ phys_addr_t memblock_get_current_limit(void); */ /** - * memblock_region_memory_base_pfn - Return the lowest pfn intersecting with the memory region + * memblock_region_memory_base_pfn - get the lowest pfn of the memory region * @reg: memblock_region structure + * + * Return: the lowest pfn intersecting with the memory region */ static inline unsigned long memblock_region_memory_base_pfn(const struct memblock_region *reg) { @@ -376,8 +377,10 @@ static inline unsigned long memblock_region_memory_base_pfn(const struct membloc } /** - * memblock_region_memory_end_pfn - Return the end_pfn this region + * memblock_region_memory_end_pfn - get the end pfn of the memory region * @reg: memblock_region structure + * + * Return: the end_pfn of the reserved region */ static inline unsigned long memblock_region_memory_end_pfn(const struct memblock_region *reg) { @@ -385,8 +388,10 @@ static inline unsigned long memblock_region_memory_end_pfn(const struct memblock } /** - * memblock_region_reserved_base_pfn - Return the lowest pfn intersecting with the reserved region + * memblock_region_reserved_base_pfn - get the lowest pfn of the reserved region * @reg: memblock_region structure + * + * Return: the lowest pfn intersecting with the reserved region */ static inline unsigned long memblock_region_reserved_base_pfn(const struct memblock_region *reg) { @@ -394,8 +399,10 @@ static inline unsigned long memblock_region_reserved_base_pfn(const struct membl } /** - * memblock_region_reserved_end_pfn - Return the end_pfn this region + * memblock_region_reserved_end_pfn - get the end pfn of the reserved region * @reg: memblock_region structure + * + * Return: the end_pfn of the reserved region */ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblock_region *reg) { -- cgit v1.2.3 From 9a0de1bfe191220cb0437865261ab2f95cbb13ef Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sat, 30 Jun 2018 17:55:04 +0300 Subject: docs/mm: memblock: add kernel-doc description for memblock types Signed-off-by: Mike Rapoport Signed-off-by: Jonathan Corbet --- include/linux/memblock.h | 37 +++++++++++++++++++++++++++++++++---- 1 file changed, 33 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 63704c64583a..516920549378 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -20,7 +20,13 @@ #define INIT_MEMBLOCK_REGIONS 128 #define INIT_PHYSMEM_REGIONS 4 -/* Definition of memblock flags. */ +/** + * enum memblock_flags - definition of memory region attributes + * @MEMBLOCK_NONE: no special request + * @MEMBLOCK_HOTPLUG: hotpluggable region + * @MEMBLOCK_MIRROR: mirrored region + * @MEMBLOCK_NOMAP: don't add to kernel direct mapping + */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ @@ -28,6 +34,13 @@ enum memblock_flags { MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ }; +/** + * struct memblock_region - represents a memory region + * @base: physical address of the region + * @size: size of the region + * @flags: memory region attributes + * @nid: NUMA node id + */ struct memblock_region { phys_addr_t base; phys_addr_t size; @@ -37,14 +50,30 @@ struct memblock_region { #endif }; +/** + * struct memblock_type - collection of memory regions of certain type + * @cnt: number of regions + * @max: size of the allocated array + * @total_size: size of all regions + * @regions: array of regions + * @name: the memory type symbolic name + */ struct memblock_type { - unsigned long cnt; /* number of regions */ - unsigned long max; /* size of the allocated array */ - phys_addr_t total_size; /* size of all regions */ + unsigned long cnt; + unsigned long max; + phys_addr_t total_size; struct memblock_region *regions; char *name; }; +/** + * struct memblock - memblock allocator metadata + * @bottom_up: is bottom up direction? + * @current_limit: physical address of the current allocation limit + * @memory: usabe memory regions + * @reserved: reserved memory regions + * @physmem: all physical memory + */ struct memblock { bool bottom_up; /* is bottom up direction? */ phys_addr_t current_limit; -- cgit v1.2.3 From 6d54228fd1f293d00576ab2c3d2e4992c7cce12f Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 25 Jun 2018 17:26:55 +0200 Subject: libceph: make ceph_osdc_notify{,_ack}() payload_len u32 The wire format dictates that payload_len fits into 4 bytes. Take u32 instead of size_t to reflect that. All callers pass a small integer, so no changes required. Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 0d6ee04b4c41..d6fe7e4df8cf 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -528,12 +528,12 @@ int ceph_osdc_notify_ack(struct ceph_osd_client *osdc, u64 notify_id, u64 cookie, void *payload, - size_t payload_len); + u32 payload_len); int ceph_osdc_notify(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, void *payload, - size_t payload_len, + u32 payload_len, u32 timeout, struct page ***preply_pages, size_t *preply_len); -- cgit v1.2.3 From c9ed51c9123ab5e8f79b7d53a9afd786b43d4fe6 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 27 Jun 2018 16:42:51 +0200 Subject: libceph: change ceph_pagelist_encode_string() to take u32 The wire format dictates that the length of string fits into 4 bytes. Take u32 instead of size_t to reflect that. We were already truncating len in ceph_pagelist_encode_32() -- this just pushes that truncation one level up. Signed-off-by: Ilya Dryomov --- include/linux/ceph/pagelist.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h index 7edcded07641..d0223364349f 100644 --- a/include/linux/ceph/pagelist.h +++ b/include/linux/ceph/pagelist.h @@ -68,7 +68,7 @@ static inline int ceph_pagelist_encode_8(struct ceph_pagelist *pl, u8 v) return ceph_pagelist_append(pl, &v, 1); } static inline int ceph_pagelist_encode_string(struct ceph_pagelist *pl, - char *s, size_t len) + char *s, u32 len) { int ret = ceph_pagelist_encode_32(pl, len); if (ret) -- cgit v1.2.3 From 473bd2d780d1699d81b25f57c0ec4de633a28eb8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 13 Jul 2018 22:18:34 +0200 Subject: libceph: use timespec64 in for keepalive2 and ticket validity ceph_con_keepalive_expired() is the last user of timespec_add() and some of the last uses of ktime_get_real_ts(). Replacing this with timespec64 based interfaces lets us remove that deprecated API. I'm introducing new ceph_encode_timespec64()/ceph_decode_timespec64() here that take timespec64 structures and convert to/from ceph_timespec, which is defined to have an unsigned 32-bit tv_sec member. This extends the range of valid times to year 2106, avoiding the year 2038 overflow. The ceph file system portion still uses the old functions for inode timestamps, this will be done separately after the VFS layer is converted. Signed-off-by: Arnd Bergmann Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/decode.h | 20 +++++++++++++++++++- include/linux/ceph/messenger.h | 2 +- 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index d143ac8879c6..094b9b4a34f3 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -194,8 +194,26 @@ ceph_decode_skip_n(p, end, sizeof(u8), bad) } while (0) /* - * struct ceph_timespec <-> struct timespec + * struct ceph_timespec <-> struct timespec64 */ +static inline void ceph_decode_timespec64(struct timespec64 *ts, + const struct ceph_timespec *tv) +{ + /* + * This will still overflow in year 2106. We could extend + * the protocol to steal two more bits from tv_nsec to + * add three more 136 year epochs after that the way ext4 + * does if necessary. + */ + ts->tv_sec = (time64_t)le32_to_cpu(tv->tv_sec); + ts->tv_nsec = (long)le32_to_cpu(tv->tv_nsec); +} +static inline void ceph_encode_timespec64(struct ceph_timespec *tv, + const struct timespec64 *ts) +{ + tv->tv_sec = cpu_to_le32((u32)ts->tv_sec); + tv->tv_nsec = cpu_to_le32((u32)ts->tv_nsec); +} static inline void ceph_decode_timespec(struct timespec *ts, const struct ceph_timespec *tv) { diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c7dfcb8a1fb2..a718b877c597 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -330,7 +330,7 @@ struct ceph_connection { int in_base_pos; /* bytes read */ __le64 in_temp_ack; /* for reading an ack */ - struct timespec last_keepalive_ack; /* keepalive2 ack stamp */ + struct timespec64 last_keepalive_ack; /* keepalive2 ack stamp */ struct delayed_work work; /* send|recv work */ unsigned long delay; /* current delay interval */ -- cgit v1.2.3 From fac02ddf910814c24f5d9d969dfdab5227f6f3eb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 13 Jul 2018 22:18:37 +0200 Subject: libceph: use timespec64 for r_mtime The request mtime field is used all over ceph, and is currently represented as a 'timespec' structure in Linux. This changes it to timespec64 to allow times beyond 2038, modifying all users at the same time. [ Remove now redundant ts variable in writepage_nounlock(). ] Signed-off-by: Arnd Bergmann Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index d6fe7e4df8cf..02096da01845 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -199,7 +199,7 @@ struct ceph_osd_request { /* set by submitter */ u64 r_snapid; /* for reads, CEPH_NOSNAP o/w */ struct ceph_snap_context *r_snapc; /* for writes */ - struct timespec r_mtime; /* ditto */ + struct timespec64 r_mtime; /* ditto */ u64 r_data_offset; /* ditto */ bool r_linger; /* don't resend on failure */ @@ -253,7 +253,7 @@ struct ceph_osd_linger_request { struct ceph_osd_request_target t; u32 map_dne_bound; - struct timespec mtime; + struct timespec64 mtime; struct kref kref; struct mutex lock; @@ -508,7 +508,7 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_snap_context *sc, u64 off, u64 len, u32 truncate_seq, u64 truncate_size, - struct timespec *mtime, + struct timespec64 *mtime, struct page **pages, int nr_pages); /* watch/notify */ -- cgit v1.2.3 From f7e52d8efe8588c5d4b4c78eb33da81d89486c1a Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 23 Jul 2018 14:11:40 +0200 Subject: libceph: remove now unused ceph_{en,de}code_timespec() Signed-off-by: Ilya Dryomov --- include/linux/ceph/decode.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 094b9b4a34f3..a6c2a48d42e0 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -214,18 +214,6 @@ static inline void ceph_encode_timespec64(struct ceph_timespec *tv, tv->tv_sec = cpu_to_le32((u32)ts->tv_sec); tv->tv_nsec = cpu_to_le32((u32)ts->tv_nsec); } -static inline void ceph_decode_timespec(struct timespec *ts, - const struct ceph_timespec *tv) -{ - ts->tv_sec = (__kernel_time_t)le32_to_cpu(tv->tv_sec); - ts->tv_nsec = (long)le32_to_cpu(tv->tv_nsec); -} -static inline void ceph_encode_timespec(struct ceph_timespec *tv, - const struct timespec *ts) -{ - tv->tv_sec = cpu_to_le32((u32)ts->tv_sec); - tv->tv_nsec = cpu_to_le32((u32)ts->tv_nsec); -} /* * sockaddr_storage <-> ceph_sockaddr -- cgit v1.2.3 From 262614c4294d33b1f19e0d18c0091d9c329b544a Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 26 Jul 2018 15:17:46 +0200 Subject: libceph: store ceph_auth_handshake pointer in ceph_connection We already copy authorizer_reply_buf and authorizer_reply_buf_len into ceph_connection. Factoring out __prepare_write_connect() requires two more: authorizer_buf and authorizer_buf_len. Store the pointer to the handshake in con->auth rather than piling on. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/messenger.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index a718b877c597..021718570b50 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -286,9 +286,8 @@ struct ceph_connection { attempt for this connection, client */ u32 peer_global_seq; /* peer's global seq for this connection */ + struct ceph_auth_handshake *auth; int auth_retry; /* true if we need a newer authorizer */ - void *auth_reply_buf; /* where to put the authorizer reply */ - int auth_reply_buf_len; struct mutex mutex; -- cgit v1.2.3 From 6daca13d2e72bedaaacfc08f873114c9307d5aea Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 27 Jul 2018 19:18:34 +0200 Subject: libceph: add authorizer challenge When a client authenticates with a service, an authorizer is sent with a nonce to the service (ceph_x_authorize_[ab]) and the service responds with a mutation of that nonce (ceph_x_authorize_reply). This lets the client verify the service is who it says it is but it doesn't protect against a replay: someone can trivially capture the exchange and reuse the same authorizer to authenticate themselves. Allow the service to reject an initial authorizer with a random challenge (ceph_x_authorize_challenge). The client then has to respond with an updated authorizer proving they are able to decrypt the service's challenge and that the new authorizer was produced for this specific connection instance. The accepting side requires this challenge and response unconditionally if the client side advertises they have CEPHX_V2 feature bit. This addresses CVE-2018-1128. Link: http://tracker.ceph.com/issues/24836 Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/auth.h | 8 ++++++++ include/linux/ceph/messenger.h | 3 +++ include/linux/ceph/msgr.h | 2 +- 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index e931da8424a4..6728c2ee0205 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -64,6 +64,10 @@ struct ceph_auth_client_ops { /* ensure that an existing authorizer is up to date */ int (*update_authorizer)(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth); + int (*add_authorizer_challenge)(struct ceph_auth_client *ac, + struct ceph_authorizer *a, + void *challenge_buf, + int challenge_buf_len); int (*verify_authorizer_reply)(struct ceph_auth_client *ac, struct ceph_authorizer *a); void (*invalidate_authorizer)(struct ceph_auth_client *ac, @@ -118,6 +122,10 @@ void ceph_auth_destroy_authorizer(struct ceph_authorizer *a); extern int ceph_auth_update_authorizer(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *a); +int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac, + struct ceph_authorizer *a, + void *challenge_buf, + int challenge_buf_len); extern int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac, struct ceph_authorizer *a); extern void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac, diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 021718570b50..fc2b4491ee0a 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -31,6 +31,9 @@ struct ceph_connection_operations { struct ceph_auth_handshake *(*get_authorizer) ( struct ceph_connection *con, int *proto, int force_new); + int (*add_authorizer_challenge)(struct ceph_connection *con, + void *challenge_buf, + int challenge_buf_len); int (*verify_authorizer_reply) (struct ceph_connection *con); int (*invalidate_authorizer)(struct ceph_connection *con); diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h index 73ae2a926548..9e50aede46c8 100644 --- a/include/linux/ceph/msgr.h +++ b/include/linux/ceph/msgr.h @@ -91,7 +91,7 @@ struct ceph_entity_inst { #define CEPH_MSGR_TAG_SEQ 13 /* 64-bit int follows with seen seq number */ #define CEPH_MSGR_TAG_KEEPALIVE2 14 /* keepalive2 byte + ceph_timespec */ #define CEPH_MSGR_TAG_KEEPALIVE2_ACK 15 /* keepalive2 reply */ - +#define CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER 16 /* cephx v2 doing server challenge */ /* * connection negotiation -- cgit v1.2.3 From cc255c76c70f7a87d97939621eae04b600d9f4a1 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 27 Jul 2018 19:25:32 +0200 Subject: libceph: implement CEPHX_V2 calculation mode Derive the signature from the entire buffer (both AES cipher blocks) instead of using just the first half of the first block, leaving out data_crc entirely. This addresses CVE-2018-1129. Link: http://tracker.ceph.com/issues/24837 Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 3901927cf6a0..6b92b3395fa9 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -165,9 +165,9 @@ DEFINE_CEPH_FEATURE(58, 1, FS_FILE_LAYOUT_V2) // overlap DEFINE_CEPH_FEATURE(59, 1, FS_BTIME) DEFINE_CEPH_FEATURE(59, 1, FS_CHANGE_ATTR) // overlap DEFINE_CEPH_FEATURE(59, 1, MSG_ADDR2) // overlap -DEFINE_CEPH_FEATURE(60, 1, BLKIN_TRACING) // *do not share this bit* +DEFINE_CEPH_FEATURE(60, 1, OSD_RECOVERY_DELETES) // *do not share this bit* +DEFINE_CEPH_FEATURE(61, 1, CEPHX_V2) // *do not share this bit* -DEFINE_CEPH_FEATURE(61, 1, RESERVED2) // unused, but slow down! DEFINE_CEPH_FEATURE(62, 1, RESERVED) // do not use; used as a sentinal DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facing @@ -210,7 +210,8 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_SERVER_JEWEL | \ CEPH_FEATURE_MON_STATEFUL_SUB | \ CEPH_FEATURE_CRUSH_TUNABLES5 | \ - CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING) + CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \ + CEPH_FEATURE_CEPHX_V2) #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ -- cgit v1.2.3 From 2afc9166f79b8f6da5f347f48515215ceee4ae37 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 2 Aug 2018 10:51:40 -0700 Subject: scsi: sysfs: Introduce sysfs_{un,}break_active_protection() Introduce these two functions and export them such that the next patch can add calls to these functions from the SCSI core. Signed-off-by: Bart Van Assche Acked-by: Tejun Heo Acked-by: Greg Kroah-Hartman Cc: Signed-off-by: Martin K. Petersen --- include/linux/sysfs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index b8bfdc173ec0..3c12198c0103 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -237,6 +237,9 @@ int __must_check sysfs_create_files(struct kobject *kobj, const struct attribute **attr); int __must_check sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, umode_t mode); +struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, + const struct attribute *attr); +void sysfs_unbreak_active_protection(struct kernfs_node *kn); void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns); bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr); @@ -350,6 +353,17 @@ static inline int sysfs_chmod_file(struct kobject *kobj, return 0; } +static inline struct kernfs_node * +sysfs_break_active_protection(struct kobject *kobj, + const struct attribute *attr) +{ + return NULL; +} + +static inline void sysfs_unbreak_active_protection(struct kernfs_node *kn) +{ +} + static inline void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns) -- cgit v1.2.3 From e7d0748dd71695b94f3a35c8bdc05226a7f3d919 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 2 Aug 2018 15:22:13 -0600 Subject: block: Switch struct packet_command to use struct scsi_sense_hdr There is a lot of needless struct request_sense usage in the CDROM code. These can all be struct scsi_sense_hdr instead, to avoid any confusion over their respective structure sizes. This patch is a lot of noise changing "sense" to "sshdr", but the final code is more readable to distinguish between "sense" meaning "struct request_sense" and "sshdr" meaning "struct scsi_sense_hdr". Reviewed-by: Christoph Hellwig Signed-off-by: Kees Cook Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index e75dfd1f1dec..528271c60018 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -13,6 +13,7 @@ #include /* not really needed, later.. */ #include +#include #include struct packet_command @@ -21,7 +22,7 @@ struct packet_command unsigned char *buffer; unsigned int buflen; int stat; - struct request_sense *sense; + struct scsi_sense_hdr *sshdr; unsigned char data_direction; int quiet; int timeout; -- cgit v1.2.3 From 9a47249d444d344051c7c0e909fad0e88515a5c2 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 31 Jul 2018 21:11:00 +0200 Subject: random: Make crng state queryable It is very useful to be able to know whether or not get_random_bytes_wait / wait_for_random_bytes is going to block or not, or whether plain get_random_bytes is going to return good randomness or bad randomness. The particular use case is for mitigating certain attacks in WireGuard. A handshake packet arrives and is queued up. Elsewhere a worker thread takes items from the queue and processes them. In replying to these items, it needs to use some random data, and it has to be good random data. If we simply block until we can have good randomness, then it's possible for an attacker to fill the queue up with packets waiting to be processed. Upon realizing the queue is full, WireGuard will detect that it's under a denial of service attack, and behave accordingly. A better approach is just to drop incoming handshake packets if the crng is not yet initialized. This patch, therefore, makes that information directly accessible. Signed-off-by: Jason A. Donenfeld Signed-off-by: Theodore Ts'o --- include/linux/random.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index f1c9bc5cd231..445a0ea4ff49 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -36,6 +36,7 @@ extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy; extern void get_random_bytes(void *buf, int nbytes); extern int wait_for_random_bytes(void); +extern bool rng_is_initialized(void); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); extern int __must_check get_random_bytes_arch(void *buf, int nbytes); -- cgit v1.2.3 From 0a4c58f5702858822621fa1177c7d3475f181ccb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:17 -0700 Subject: bpf: add ability to charge bpf maps memory dynamically This commits extends existing bpf maps memory charging API to support dynamic charging/uncharging. This is required to account memory used by maps, if all entries are created dynamically after the map initialization. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5b5ad95cf339..5a4a256473c3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -435,6 +435,8 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); +int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); +void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages); void *bpf_map_area_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); -- cgit v1.2.3 From de9cbbaadba5adf88a19e46df61f7054000838f6 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:18 -0700 Subject: bpf: introduce cgroup storage maps This commit introduces BPF_MAP_TYPE_CGROUP_STORAGE maps: a special type of maps which are implementing the cgroup storage. >From the userspace point of view it's almost a generic hash map with the (cgroup inode id, attachment type) pair used as a key. The only difference is that some operations are restricted: 1) a user can't create new entries, 2) a user can't remove existing entries. The lookup from userspace is o(log(n)). Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/bpf.h | 1 + include/linux/bpf_types.h | 3 +++ 3 files changed, 42 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index d50c2f0a655a..7d00d58869ed 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -4,19 +4,39 @@ #include #include +#include #include struct sock; struct sockaddr; struct cgroup; struct sk_buff; +struct bpf_map; +struct bpf_prog; struct bpf_sock_ops_kern; +struct bpf_cgroup_storage; #ifdef CONFIG_CGROUP_BPF extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +struct bpf_cgroup_storage_map; + +struct bpf_storage_buffer { + struct rcu_head rcu; + char data[0]; +}; + +struct bpf_cgroup_storage { + struct bpf_storage_buffer *buf; + struct bpf_cgroup_storage_map *map; + struct bpf_cgroup_storage_key key; + struct list_head list; + struct rb_node node; + struct rcu_head rcu; +}; + struct bpf_prog_list { struct list_head node; struct bpf_prog *prog; @@ -77,6 +97,15 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum bpf_attach_type type); +struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog); +void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage); +void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, + struct cgroup *cgroup, + enum bpf_attach_type type); +void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); +int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map); +void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -221,6 +250,15 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } +static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog, + struct bpf_map *map) { return 0; } +static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, + struct bpf_map *map) {} +static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( + struct bpf_prog *prog) { return 0; } +static inline void bpf_cgroup_storage_free( + struct bpf_cgroup_storage *storage) {} + #define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5a4a256473c3..9d1e4727495e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -282,6 +282,7 @@ struct bpf_prog_aux { struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ + struct bpf_map *cgroup_storage; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY void *security; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index c5700c2d5549..add08be53b6f 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -37,6 +37,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, perf_event_array_map_ops) #ifdef CONFIG_CGROUPS BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops) #endif +#ifdef CONFIG_CGROUP_BPF +BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops) -- cgit v1.2.3 From aa0ad5b0391e268bdecf6cda31268388844f8afd Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:19 -0700 Subject: bpf: pass a pointer to a cgroup storage using pcpu variable This commit introduces the bpf_cgroup_storage_set() helper, which will be used to pass a pointer to a cgroup storage to the bpf helper. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 7d00d58869ed..9a144ddbbc8f 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -4,6 +4,7 @@ #include #include +#include #include #include @@ -21,6 +22,8 @@ struct bpf_cgroup_storage; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +DECLARE_PER_CPU(void*, bpf_cgroup_storage); + struct bpf_cgroup_storage_map; struct bpf_storage_buffer { @@ -97,6 +100,17 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum bpf_attach_type type); +static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) +{ + struct bpf_storage_buffer *buf; + + if (!storage) + return; + + buf = READ_ONCE(storage->buf); + this_cpu_write(bpf_cgroup_storage, &buf->data[0]); +} + struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog); void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage); void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, @@ -250,6 +264,7 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } +static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) {} static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map) { return 0; } static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, -- cgit v1.2.3 From d7bf2c10af053191e931b58704cd862fccb7f9de Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:20 -0700 Subject: bpf: allocate cgroup storage entries on attaching bpf programs If a bpf program is using cgroup local storage, allocate a bpf_cgroup_storage structure automatically on attaching the program to a cgroup and save the pointer into the corresponding bpf_prog_list entry. Analogically, release the cgroup local storage on detaching of the bpf program. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 9a144ddbbc8f..f91b0f8ff3a9 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -43,6 +43,7 @@ struct bpf_cgroup_storage { struct bpf_prog_list { struct list_head node; struct bpf_prog *prog; + struct bpf_cgroup_storage *storage; }; struct bpf_prog_array; -- cgit v1.2.3 From 394e40a29788820c9c0526b1c3497c9e0ec2a126 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:21 -0700 Subject: bpf: extend bpf_prog_array to store pointers to the cgroup storage This patch converts bpf_prog_array from an array of prog pointers to the array of struct bpf_prog_array_item elements. This allows to save a cgroup storage pointer for each bpf program efficiently attached to a cgroup. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9d1e4727495e..16be67888c30 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -349,9 +349,14 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, * The 'struct bpf_prog_array *' should only be replaced with xchg() * since other cpus are walking the array of pointers in parallel. */ +struct bpf_prog_array_item { + struct bpf_prog *prog; + struct bpf_cgroup_storage *cgroup_storage; +}; + struct bpf_prog_array { struct rcu_head rcu; - struct bpf_prog *progs[0]; + struct bpf_prog_array_item items[0]; }; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); @@ -372,7 +377,8 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, #define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \ ({ \ - struct bpf_prog **_prog, *__prog; \ + struct bpf_prog_array_item *_item; \ + struct bpf_prog *_prog; \ struct bpf_prog_array *_array; \ u32 _ret = 1; \ preempt_disable(); \ @@ -380,10 +386,11 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, _array = rcu_dereference(array); \ if (unlikely(check_non_null && !_array))\ goto _out; \ - _prog = _array->progs; \ - while ((__prog = READ_ONCE(*_prog))) { \ - _ret &= func(__prog, ctx); \ - _prog++; \ + _item = &_array->items[0]; \ + while ((_prog = READ_ONCE(_item->prog))) { \ + bpf_cgroup_storage_set(_item->cgroup_storage); \ + _ret &= func(_prog, ctx); \ + _item++; \ } \ _out: \ rcu_read_unlock(); \ -- cgit v1.2.3 From 3e6a4b3e0289dc9540a2c1d8a20657f4707fbabb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:22 -0700 Subject: bpf/verifier: introduce BPF_PTR_TO_MAP_VALUE BPF_MAP_TYPE_CGROUP_STORAGE maps are special in a way that the access from the bpf program side is lookup-free. That means the result is guaranteed to be a valid pointer to the cgroup storage; no NULL-check is required. This patch introduces BPF_PTR_TO_MAP_VALUE return type, which is required to cause the verifier accept programs, which are not checking the map value pointer for being NULL. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 16be67888c30..ca4ac2a39def 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -155,6 +155,7 @@ enum bpf_arg_type { enum bpf_return_type { RET_INTEGER, /* function returns integer */ RET_VOID, /* function doesn't return anything */ + RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ }; -- cgit v1.2.3 From cd3394317653837e2eb5c5d0904a8996102af9fc Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:24 -0700 Subject: bpf: introduce the bpf_get_local_storage() helper function The bpf_get_local_storage() helper function is used to get a pointer to the bpf local storage from a bpf program. It takes a pointer to a storage map and flags as arguments. Right now it accepts only cgroup storage maps, and flags argument has to be 0. Further it can be extended to support other types of local storage: e.g. thread local storage etc. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ca4ac2a39def..cd8790d2c6ed 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -788,6 +788,8 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; +extern const struct bpf_func_proto bpf_get_local_storage_proto; + /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); -- cgit v1.2.3 From 9f49a5b5c21d58aa84e16cfdc5e99e49faefcb7a Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Sun, 29 Jul 2018 11:34:56 +0300 Subject: RDMA/netdev: Use priv_destructor for netdev cleanup Now that the unregister_netdev flow for IPoIB no longer relies on external code we can now introduce the use of priv_destructor and needs_free_netdev. The rdma_netdev flow is switched to use the netdev common priv_destructor instead of the special free_rdma_netdev and the IPOIB ULP adjusted: - priv_destructor needs to switch to point to the ULP's destructor which will then call the rdma_ndev's in the right order - We need to be careful around the error unwind of register_netdev as it sometimes calls priv_destructor on failure - ULPs need to use ndo_init/uninit to ensure proper ordering of failures around register_netdev Switching to priv_destructor is a necessary pre-requisite to using the rtnl new_link mechanism. The VNIC user for rdma_netdev should also be revised, but that is left for another patch. Signed-off-by: Jason Gunthorpe Signed-off-by: Denis Drozdov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 957199c20a0f..96498ff6beb6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1218,14 +1218,11 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, { return ERR_PTR(-EOPNOTSUPP); } - -static inline void mlx5_rdma_netdev_free(struct net_device *netdev) {} #else struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, struct ib_device *ibdev, const char *name, void (*setup)(struct net_device *)); -void mlx5_rdma_netdev_free(struct net_device *netdev); #endif /* CONFIG_MLX5_CORE_IPOIB */ struct mlx5_profile { -- cgit v1.2.3 From 401c0d7712eb3189023efc9c0708a2ac984ed62e Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 3 Aug 2018 11:50:39 +0200 Subject: spi: spi-mem: Constify spi_mem->name There is no reason to make spi_mem->name modifiable. Moreover, spi_mem_ops->get_name() returns a const char *, which generates a gcc warning when assigning the value returned by spi_mem_ops->get_name() to spi_mem->name. Fixes: 5d27a9c8ea9e ("spi: spi-mem: Extend the SPI mem interface to set a custom memory name") Reported-by: Stephen Rothwell Signed-off-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 0d64ccc4e584..62722fb7472d 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -134,7 +134,7 @@ struct spi_mem_op { struct spi_mem { struct spi_device *spi; void *drvpriv; - char *name; + const char *name; }; /** -- cgit v1.2.3 From 2ad5157650b446f14a719280ba3670303bc4f439 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Wed, 11 Jul 2018 18:42:11 -0500 Subject: mailbox/omap: switch to SPDX license identifier Use the appropriate SPDX license identifier in the OMAP Mailbox driver source files and drop the previous boilerplate license text. Signed-off-by: Suman Anna Signed-off-by: Jassi Brar --- include/linux/omap-mailbox.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/omap-mailbox.h b/include/linux/omap-mailbox.h index c726bd833761..6dbcd2da0332 100644 --- a/include/linux/omap-mailbox.h +++ b/include/linux/omap-mailbox.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * omap-mailbox: interprocessor communication module for OMAP - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef OMAP_MAILBOX_H -- cgit v1.2.3 From 623a6143a845bd485b00ba684f0ccef11835edab Mon Sep 17 00:00:00 2001 From: Houlong Wei Date: Wed, 25 Jul 2018 09:26:40 +0800 Subject: mailbox: mediatek: Add Mediatek CMDQ driver This patch is first version of Mediatek Command Queue(CMDQ) driver. The CMDQ is used to help write registers with critical time limitation, such as updating display configuration during the vblank. It controls Global Command Engine (GCE) hardware to achieve this requirement. Currently, CMDQ only supports display related hardwares, but we expect it can be extended to other hardwares for future requirements. Signed-off-by: Houlong Wei Signed-off-by: HS Liao Signed-off-by: CK Hu Signed-off-by: Jassi Brar --- include/linux/mailbox/mtk-cmdq-mailbox.h | 77 ++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) create mode 100644 include/linux/mailbox/mtk-cmdq-mailbox.h (limited to 'include/linux') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h new file mode 100644 index 000000000000..ccb73422c2fa --- /dev/null +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018 MediaTek Inc. + * + */ + +#ifndef __MTK_CMDQ_MAILBOX_H__ +#define __MTK_CMDQ_MAILBOX_H__ + +#include +#include +#include + +#define CMDQ_INST_SIZE 8 /* instruction is 64-bit */ +#define CMDQ_SUBSYS_SHIFT 16 +#define CMDQ_OP_CODE_SHIFT 24 +#define CMDQ_JUMP_PASS CMDQ_INST_SIZE + +#define CMDQ_WFE_UPDATE BIT(31) +#define CMDQ_WFE_WAIT BIT(15) +#define CMDQ_WFE_WAIT_VALUE 0x1 + +/* + * CMDQ_CODE_MASK: + * set write mask + * format: op mask + * CMDQ_CODE_WRITE: + * write value into target register + * format: op subsys address value + * CMDQ_CODE_JUMP: + * jump by offset + * format: op offset + * CMDQ_CODE_WFE: + * wait for event and clear + * it is just clear if no wait + * format: [wait] op event update:1 to_wait:1 wait:1 + * [clear] op event update:1 to_wait:0 wait:0 + * CMDQ_CODE_EOC: + * end of command + * format: op irq_flag + */ +enum cmdq_code { + CMDQ_CODE_MASK = 0x02, + CMDQ_CODE_WRITE = 0x04, + CMDQ_CODE_JUMP = 0x10, + CMDQ_CODE_WFE = 0x20, + CMDQ_CODE_EOC = 0x40, +}; + +enum cmdq_cb_status { + CMDQ_CB_NORMAL = 0, + CMDQ_CB_ERROR +}; + +struct cmdq_cb_data { + enum cmdq_cb_status sta; + void *data; +}; + +typedef void (*cmdq_async_flush_cb)(struct cmdq_cb_data data); + +struct cmdq_task_cb { + cmdq_async_flush_cb cb; + void *data; +}; + +struct cmdq_pkt { + void *va_base; + dma_addr_t pa_base; + size_t cmd_buf_size; /* command occupied size */ + size_t buf_size; /* real buffer size */ + struct cmdq_task_cb cb; + struct cmdq_task_cb async_cb; + void *cl; +}; + +#endif /* __MTK_CMDQ_MAILBOX_H__ */ -- cgit v1.2.3 From 7cca1ed0bb248b8d5768d17f5afe297a832d66c0 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Tue, 31 Jul 2018 20:25:00 +0200 Subject: netfilter: nf_osf: move nf_osf_fingers to non-uapi header file All warnings (new ones prefixed by >>): >> ./usr/include/linux/netfilter/nf_osf.h:73: userspace cannot reference function or variable defined in the kernel Fixes: f9324952088f ("netfilter: nfnetlink_osf: extract nfnetlink_subsystem code from xt_osf.c") Reported-by: kbuild test robot Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_osf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h index aee460fcbd31..3e455d6f94d5 100644 --- a/include/linux/netfilter/nf_osf.h +++ b/include/linux/netfilter/nf_osf.h @@ -25,6 +25,8 @@ enum osf_fmatch_states { FMATCH_OPT_WRONG, }; +extern struct list_head nf_osf_fingers[2]; + struct nf_osf_finger { struct rcu_head rcu_head; struct list_head finger_entry; -- cgit v1.2.3 From ddba40be59c9be4059288464f8e6f38fbba27495 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Tue, 31 Jul 2018 20:25:01 +0200 Subject: netfilter: nfnetlink_osf: rename nf_osf header file to nfnetlink_osf The first client of the nf_osf.h userspace header is nft_osf, coming in this batch, rename it to nfnetlink_osf.h as there are no userspace clients for this yet, hence this looks consistent with other nfnetlink subsystem. Suggested-by: Jan Engelhardt Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_osf.h | 44 --------------------------------- include/linux/netfilter/nfnetlink_osf.h | 44 +++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+), 44 deletions(-) delete mode 100644 include/linux/netfilter/nf_osf.h create mode 100644 include/linux/netfilter/nfnetlink_osf.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h deleted file mode 100644 index 3e455d6f94d5..000000000000 --- a/include/linux/netfilter/nf_osf.h +++ /dev/null @@ -1,44 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NFOSF_H -#define _NFOSF_H - -#include - -/* Initial window size option state machine: multiple of mss, mtu or - * plain numeric value. Can also be made as plain numeric value which - * is not a multiple of specified value. - */ -enum nf_osf_window_size_options { - OSF_WSS_PLAIN = 0, - OSF_WSS_MSS, - OSF_WSS_MTU, - OSF_WSS_MODULO, - OSF_WSS_MAX, -}; - -enum osf_fmatch_states { - /* Packet does not match the fingerprint */ - FMATCH_WRONG = 0, - /* Packet matches the fingerprint */ - FMATCH_OK, - /* Options do not match the fingerprint, but header does */ - FMATCH_OPT_WRONG, -}; - -extern struct list_head nf_osf_fingers[2]; - -struct nf_osf_finger { - struct rcu_head rcu_head; - struct list_head finger_entry; - struct nf_osf_user_finger finger; -}; - -bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, - int hooknum, struct net_device *in, struct net_device *out, - const struct nf_osf_info *info, struct net *net, - const struct list_head *nf_osf_fingers); - -const char *nf_osf_find(const struct sk_buff *skb, - const struct list_head *nf_osf_fingers); - -#endif /* _NFOSF_H */ diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h new file mode 100644 index 000000000000..a7311bc03d3a --- /dev/null +++ b/include/linux/netfilter/nfnetlink_osf.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NFOSF_H +#define _NFOSF_H + +#include + +/* Initial window size option state machine: multiple of mss, mtu or + * plain numeric value. Can also be made as plain numeric value which + * is not a multiple of specified value. + */ +enum nf_osf_window_size_options { + OSF_WSS_PLAIN = 0, + OSF_WSS_MSS, + OSF_WSS_MTU, + OSF_WSS_MODULO, + OSF_WSS_MAX, +}; + +enum osf_fmatch_states { + /* Packet does not match the fingerprint */ + FMATCH_WRONG = 0, + /* Packet matches the fingerprint */ + FMATCH_OK, + /* Options do not match the fingerprint, but header does */ + FMATCH_OPT_WRONG, +}; + +extern struct list_head nf_osf_fingers[2]; + +struct nf_osf_finger { + struct rcu_head rcu_head; + struct list_head finger_entry; + struct nf_osf_user_finger finger; +}; + +bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, + int hooknum, struct net_device *in, struct net_device *out, + const struct nf_osf_info *info, struct net *net, + const struct list_head *nf_osf_fingers); + +const char *nf_osf_find(const struct sk_buff *skb, + const struct list_head *nf_osf_fingers); + +#endif /* _NFOSF_H */ -- cgit v1.2.3 From 94276fa8a2a4c08ccb2e9d55e88b95dc972ccea3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?M=C3=A1t=C3=A9=20Eckl?= Date: Fri, 3 Aug 2018 13:36:13 +0200 Subject: netfilter: bridge: Expose nf_tables bridge hook priorities through uapi MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Netfilter exposes standard hook priorities in case of ipv4, ipv6 and arp but not in case of bridge. This patch exposes the hook priority values of the bridge family (which are different from the formerly mentioned) via uapi so that they can be used by user-space applications just like the others. Signed-off-by: Máté Eckl Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index b671fdfd212b..fa0686500970 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -5,17 +5,6 @@ #include #include -enum nf_br_hook_priorities { - NF_BR_PRI_FIRST = INT_MIN, - NF_BR_PRI_NAT_DST_BRIDGED = -300, - NF_BR_PRI_FILTER_BRIDGED = -200, - NF_BR_PRI_BRNF = 0, - NF_BR_PRI_NAT_DST_OTHER = 100, - NF_BR_PRI_FILTER_OTHER = 200, - NF_BR_PRI_NAT_SRC = 300, - NF_BR_PRI_LAST = INT_MAX, -}; - #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); -- cgit v1.2.3 From c2b6d621c4ffe9936adf7a55c8b1c769672c306f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 28 Jun 2018 15:53:17 -0400 Subject: new primitive: discard_new_inode() We don't want open-by-handle picking half-set-up in-core struct inode from e.g. mkdir() having failed halfway through. In other words, we don't want such inodes returned by iget_locked() on their way to extinction. However, we can't just have them unhashed - otherwise open-by-handle immediately *after* that would've ended up creating a new in-core inode over the on-disk one that is in process of being freed right under us. Solution: new flag (I_CREATING) set by insert_inode_locked() and removed by unlock_new_inode() and a new primitive (discard_new_inode()) to be used by such halfway-through-setup failure exits instead of unlock_new_inode() / iput() combinations. That primitive unlocks new inode, but leaves I_CREATING in place. iget_locked() treats finding an I_CREATING inode as failure (-ESTALE, once we sort out the error propagation). insert_inode_locked() treats the same as instant -EBUSY. ilookup() treats those as icache miss. [Fix by Dan Carpenter folded in] Signed-off-by: Al Viro --- include/linux/fs.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5c91108846db..a42600565925 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2016,6 +2016,8 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * + * I_CREATING New object's inode in the middle of setting up. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2036,7 +2038,8 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) #define __I_DIRTY_TIME_EXPIRED 12 #define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_WB_SWITCH (1 << 13) -#define I_OVL_INUSE (1 << 14) +#define I_OVL_INUSE (1 << 14) +#define I_CREATING (1 << 15) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) @@ -2919,6 +2922,7 @@ extern void lockdep_annotate_inode_mutex_key(struct inode *inode); static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); +extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); -- cgit v1.2.3 From 5bef915104f32c9d0bb5df6e86a98e31cb524e9a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 29 Jun 2018 19:36:57 -0400 Subject: new helper: inode_fake_hash() open-coded in a quite a few places... Signed-off-by: Al Viro --- include/linux/fs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a42600565925..43941e230e2b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -684,6 +684,17 @@ static inline int inode_unhashed(struct inode *inode) return hlist_unhashed(&inode->i_hash); } +/* + * __mark_inode_dirty expects inodes to be hashed. Since we don't + * want special inodes in the fileset inode space, we make them + * appear hashed, but do not put on any lists. hlist_del() + * will work fine and require no locking. + */ +static inline void inode_fake_hash(struct inode *inode) +{ + hlist_add_fake(&inode->i_hash); +} + /* * inode->i_mutex nesting subclasses for the lock validator: * -- cgit v1.2.3 From 088fe47ce952542389e604e83f533811750aaf7c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 23 Jul 2018 17:26:49 -0500 Subject: signal: Add calculate_sigpending() Add a function calculate_sigpending to test to see if any signals are pending for a new task immediately following fork. Signals have to happen either before or after fork. Today our practice is to push all of the signals to before the fork, but that has the downside that frequent or periodic signals can make fork take much much longer than normal or prevent fork from completing entirely. So we need move signals that we can after the fork to prevent that. This updates the code to set TIF_SIGPENDING on a new task if there are signals or other activities that have moved so that they appear to happen after the fork. As the code today restarts if it sees any such activity this won't immediately have an effect, as there will be no reason for it to set TIF_SIGPENDING immediately after the fork. Adding calculate_sigpending means the code in fork can safely be changed to not always restart if a signal is pending. The new calculate_sigpending function sets sigpending if there are pending bits in jobctl, pending signals, the freezer needs to freeze the new task or the live kernel patching framework need the new thread to take the slow path to userspace. I have verified that setting TIF_SIGPENDING does make a new process take the slow path to userspace before it executes it's first userspace instruction. I have looked at the callers of signal_wake_up and the code paths setting TIF_SIGPENDING and I don't see anything else that needs to be handled. The code probably doesn't need to set TIF_SIGPENDING for the kernel live patching as it uses a separate thread flag as well. But at this point it seems safer reuse the recalc_sigpending logic and get the kernel live patching folks to sort out their story later. V2: I have moved the test into schedule_tail where siglock can be grabbed and recalc_sigpending can be reused directly. Further as the last action of setting up a new task this guarantees that TIF_SIGPENDING will be properly set in the new process. The helper calculate_sigpending takes the siglock and uncontitionally sets TIF_SIGPENDING and let's recalc_sigpending clear TIF_SIGPENDING if it is unnecessary. This allows reusing the existing code and keeps maintenance of the conditions simple. Oleg Nesterov suggested the movement and pointed out the need to take siglock if this code was going to be called while the new task is discoverable. Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 94558ffa82ab..b55fd293c1e5 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -372,6 +372,7 @@ static inline int signal_pending_state(long state, struct task_struct *p) */ extern void recalc_sigpending_and_wake(struct task_struct *t); extern void recalc_sigpending(void); +extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); -- cgit v1.2.3 From 4390e9eadbbb6774b7ba03fde0a0fdf3f07db4cd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 3 Aug 2018 20:10:54 -0500 Subject: fork: Skip setting TIF_SIGPENDING in ptrace_init_task The code in calculate_sigpending will now handle this so it is just redundant and possibly a little confusing to continue setting TIF_SIGPENDING in ptrace_init_task. Suggested-by: Oleg Nesterov Signed-off-by: "Eric W. Biederman" --- include/linux/ptrace.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 037bf0ef1ae9..4f36431c380b 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -214,8 +214,6 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) task_set_jobctl_pending(child, JOBCTL_TRAP_STOP); else sigaddset(&child->pending.signal, SIGSTOP); - - set_tsk_thread_flag(child, TIF_SIGPENDING); } else child->ptracer_cred = NULL; -- cgit v1.2.3 From 924de3b8c9410c404c6eda7abffd282b97b3ff7f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 23 Jul 2018 13:38:00 -0500 Subject: fork: Have new threads join on-going signal group stops There are only two signals that are delivered to every member of a signal group: SIGSTOP and SIGKILL. Signal delivery requires every signal appear to be delivered either before or after a clone syscall. SIGKILL terminates the clone so does not need to be considered. Which leaves only SIGSTOP that needs to be considered when creating new threads. Today in the event of a group stop TIF_SIGPENDING will get set and the fork will restart ensuring the fork syscall participates in the group stop. A fork (especially of a process with a lot of memory) is one of the most expensive system so we really only want to restart a fork when necessary. It is easy so check to see if a SIGSTOP is ongoing and have the new thread join it immediate after the clone completes. Making it appear the clone completed happened just before the SIGSTOP. The calculate_sigpending function will see the bits set in jobctl and set TIF_SIGPENDING to ensure the new task takes the slow path to userspace. V2: The call to task_join_group_stop was moved before the new task is added to the thread group list. This should not matter as sighand->siglock is held over both the addition of the threads, the call to task_join_group_stop and do_signal_stop. But the change is trivial and it is one less thing to worry about when reading the code. Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index b55fd293c1e5..ae2b0b81be25 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -385,6 +385,8 @@ static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) signal_wake_up_state(t, resume ? __TASK_TRACED : 0); } +void task_join_group_stop(struct task_struct *task); + #ifdef TIF_RESTORE_SIGMASK /* * Legacy restore_sigmask accessors. These are inefficient on -- cgit v1.2.3 From d9cfe2ce246845b9cca0ec1b881e826965893c58 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 23 Jul 2018 22:26:05 +0200 Subject: i2c: quirks: add zero length checks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some adapters do not support a message length of 0. Add this as a quirk so drivers don't have to open code it. Signed-off-by: Wolfram Sang Reviewed-by: Niklas Söderlund Reviewed-by: Andy Shevchenko Tested-by: Jarkko Nikula Acked-by: Jarkko Nikula Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index bc8d42f8544f..2a98d0886d2e 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -661,6 +661,10 @@ struct i2c_adapter_quirks { I2C_AQ_COMB_READ_SECOND | I2C_AQ_COMB_SAME_ADDR) /* clock stretching is not supported */ #define I2C_AQ_NO_CLK_STRETCH BIT(4) +/* message cannot have length of 0 */ +#define I2C_AQ_NO_ZERO_LEN_READ BIT(5) +#define I2C_AQ_NO_ZERO_LEN_WRITE BIT(6) +#define I2C_AQ_NO_ZERO_LEN (I2C_AQ_NO_ZERO_LEN_READ | I2C_AQ_NO_ZERO_LEN_WRITE) /* * i2c_adapter is the structure used to identify a physical i2c bus along -- cgit v1.2.3 From 91305f2812624c0cf7ccbb44133b66d3b24676e4 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 1 Aug 2018 18:05:54 +0800 Subject: ptp_qoriq: support automatic configuration for ptp timer This patch is to support automatic configuration for ptp timer. If required ptp dts properties are not provided, driver could try to calculate a set of default configurations to initialize the ptp timer. This makes the driver work for many boards which don't have the required ptp dts properties in current kernel. Also the users could set dts properties by themselves according to their requirement. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/linux/fsl/ptp_qoriq.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index dc3dac40f069..c1f003aadcce 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -127,9 +127,13 @@ struct qoriq_ptp_registers { #define DRIVER "ptp_qoriq" -#define DEFAULT_CKSEL 1 #define N_EXT_TS 2 +#define DEFAULT_CKSEL 1 +#define DEFAULT_TMR_PRSC 2 +#define DEFAULT_FIPER1_PERIOD 1000000000 +#define DEFAULT_FIPER2_PERIOD 100000 + struct qoriq_ptp { void __iomem *base; struct qoriq_ptp_registers regs; -- cgit v1.2.3 From 385114dec8a49b5e5945e77ba7de6356106713f4 Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Thu, 2 Aug 2018 23:34:38 +0000 Subject: net: modify skb_rbtree_purge to return the truesize of all purged skbs. Tested: see the next patch is the series. Suggested-by: Eric Dumazet Signed-off-by: Peter Oskolkov Signed-off-by: Eric Dumazet Cc: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fd3cb1b247df..47848367c816 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2585,7 +2585,7 @@ static inline void __skb_queue_purge(struct sk_buff_head *list) kfree_skb(skb); } -void skb_rbtree_purge(struct rb_root *root); +unsigned int skb_rbtree_purge(struct rb_root *root); void *netdev_alloc_frag(unsigned int fragsz); -- cgit v1.2.3 From fa0f527358bd900ef92f925878ed6bfbd51305cc Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Thu, 2 Aug 2018 23:34:39 +0000 Subject: ip: use rb trees for IP frag queue. Similar to TCP OOO RX queue, it makes sense to use rb trees to store IP fragments, so that OOO fragments are inserted faster. Tested: - a follow-up patch contains a rather comprehensive ip defrag self-test (functional) - ran neper `udp_stream -c -H -F 100 -l 300 -T 20`: netstat --statistics Ip: 282078937 total packets received 0 forwarded 0 incoming packets discarded 946760 incoming packets delivered 18743456 requests sent out 101 fragments dropped after timeout 282077129 reassemblies required 944952 packets reassembled ok 262734239 packet reassembles failed (The numbers/stats above are somewhat better re: reassemblies vs a kernel without this patchset. More comprehensive performance testing TBD). Reported-by: Jann Horn Reported-by: Juha-Matti Tilli Suggested-by: Eric Dumazet Signed-off-by: Peter Oskolkov Signed-off-by: Eric Dumazet Cc: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 47848367c816..7ebdf158a795 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -676,13 +676,16 @@ struct sk_buff { * UDP receive path is one user. */ unsigned long dev_scratch; - int ip_defrag_offset; }; }; - struct rb_node rbnode; /* used in netem & tcp stack */ + struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; }; - struct sock *sk; + + union { + struct sock *sk; + int ip_defrag_offset; + }; union { ktime_t tstamp; -- cgit v1.2.3 From 55f2503c3b69328735e88031ff8d6ba291bd952b Mon Sep 17 00:00:00 2001 From: Pingfan Liu Date: Tue, 31 Jul 2018 16:51:32 +0800 Subject: PM / reboot: Eliminate race between reboot and suspend At present, "systemctl suspend" and "shutdown" can run in parrallel. A system can suspend after devices_shutdown(), and resume. Then the shutdown task goes on to power off. This causes many devices are not really shut off. Hence replacing reboot_mutex with system_transition_mutex (renamed from pm_mutex) to achieve the exclusion. The renaming of pm_mutex as system_transition_mutex can be better to reflect the purpose of the mutex. Signed-off-by: Pingfan Liu Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 440b62f7502e..5a28ac9284f0 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -414,7 +414,7 @@ static inline bool hibernation_available(void) { return false; } #define PM_RESTORE_PREPARE 0x0005 /* Going to restore a saved image */ #define PM_POST_RESTORE 0x0006 /* Restore failed */ -extern struct mutex pm_mutex; +extern struct mutex system_transition_mutex; #ifdef CONFIG_PM_SLEEP void save_processor_state(void); -- cgit v1.2.3 From 86dafed50e2b9b18198cc663775ece819ff113ba Mon Sep 17 00:00:00 2001 From: KarimAllah Ahmed Date: Tue, 10 Jul 2018 11:27:19 +0200 Subject: KVM: Switch 'requests' to be 64-bit (explicitly) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Switch 'requests' to be explicitly 64-bit and update BUILD_BUG_ON check to use the size of "requests" instead of the hard-coded '32'. That gives us a bit more room again for arch-specific requests as we already ran out of space for x86 due to the hard-coded check. The only exception here is ARM32 as it is still 32-bits. Cc: Paolo Bonzini Cc: Radim KrÄmář Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reviewed-by: Jim Mattson Signed-off-by: KarimAllah Ahmed Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5f138b40e433..2840ac74a3d7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -130,7 +130,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQUEST_ARCH_BASE 8 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ - BUILD_BUG_ON((unsigned)(nr) >= 32 - KVM_REQUEST_ARCH_BASE); \ + BUILD_BUG_ON((unsigned)(nr) >= (FIELD_SIZEOF(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ }) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) @@ -224,7 +224,7 @@ struct kvm_vcpu { int vcpu_id; int srcu_idx; int mode; - unsigned long requests; + u64 requests; unsigned long guest_debug; int pre_pcpu; @@ -1131,7 +1131,7 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) * caller. Paired with the smp_mb__after_atomic in kvm_check_request. */ smp_wmb(); - set_bit(req & KVM_REQUEST_MASK, &vcpu->requests); + set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) @@ -1141,12 +1141,12 @@ static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu) { - return test_bit(req & KVM_REQUEST_MASK, &vcpu->requests); + return test_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu) { - clear_bit(req & KVM_REQUEST_MASK, &vcpu->requests); + clear_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) -- cgit v1.2.3 From b08660e59dbdb600c55953787ed2265a0b510f77 Mon Sep 17 00:00:00 2001 From: Tianyu Lan Date: Thu, 19 Jul 2018 08:40:17 +0000 Subject: KVM: x86: Add tlb remote flush callback in kvm_x86_ops. This patch is to provide a way for platforms to register hv tlb remote flush callback and this helps to optimize operation of tlb flush among vcpus for nested virtualization case. Signed-off-by: Lan Tianyu Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2840ac74a3d7..7c7362dd2faa 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -834,6 +834,13 @@ static inline void kvm_arch_free_vm(struct kvm *kvm) } #endif +#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB +static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) +{ + return -ENOTSUPP; +} +#endif + #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA void kvm_arch_register_noncoherent_dma(struct kvm *kvm); void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm); -- cgit v1.2.3 From eac7e072d7e99fad1b6e817c608b03c48205241e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 6 Aug 2018 10:22:35 -0700 Subject: Revert "ata: ahci_platform: allow disabling of hotplug to save power" This reverts commit aece27a2f01be4bb7683790f69cd1bed3a0929a2. Causes boot failure on some devices. http://lore.kernel.org/r/CA+G9fYuKW_jCFZPqG4tz=QY9ROfHO38KiCp9XTA+KaDOFVtcqQ@mail.gmail.com Signed-off-by: Tejun Heo --- include/linux/ahci_platform.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 6396e6982103..1b0a17b22cd3 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -42,7 +42,5 @@ int ahci_platform_suspend_host(struct device *dev); int ahci_platform_resume_host(struct device *dev); int ahci_platform_suspend(struct device *dev); int ahci_platform_resume(struct device *dev); -int ahci_platform_runtime_suspend(struct device *dev); -int ahci_platform_runtime_resume(struct device *dev); #endif /* _AHCI_PLATFORM_H */ -- cgit v1.2.3 From bc2d8d262cba5736332cbc866acb11b1c5748aa9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 7 Aug 2018 08:19:57 +0200 Subject: cpu/hotplug: Fix SMT supported evaluation Josh reported that the late SMT evaluation in cpu_smt_state_init() sets cpu_smt_control to CPU_SMT_NOT_SUPPORTED in case that 'nosmt' was supplied on the kernel command line as it cannot differentiate between SMT disabled by BIOS and SMT soft disable via 'nosmt'. That wreckages the state and makes the sysfs interface unusable. Rework this so that during bringup of the non boot CPUs the availability of SMT is determined in cpu_smt_allowed(). If a newly booted CPU is not a 'primary' thread then set the local cpu_smt_available marker and evaluate this explicitely right after the initial SMP bringup has finished. SMT evaulation on x86 is a trainwreck as the firmware has all the information _before_ booting the kernel, but there is no interface to query it. Fixes: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") Reported-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner --- include/linux/cpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ccdf3a67ce56..b216bd5bfd20 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -178,10 +178,12 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); +extern void cpu_smt_check_topology_early(void); extern void cpu_smt_check_topology(void); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } +static inline void cpu_smt_check_topology_early(void) { } static inline void cpu_smt_check_topology(void) { } #endif -- cgit v1.2.3 From 4231aba000f5a4583dd9f67057aadb68c3eca99d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 27 Jul 2018 21:48:17 +1000 Subject: powerpc/64s: Fix page table fragment refcount race vs speculative references The page table fragment allocator uses the main page refcount racily with respect to speculative references. A customer observed a BUG due to page table page refcount underflow in the fragment allocator. This can be caused by the fragment allocator set_page_count stomping on a speculative reference, and then the speculative failure handler decrements the new reference, and the underflow eventually pops when the page tables are freed. Fix this by using a dedicated field in the struct page for the page table fragment allocator. Fixes: 5c1f6ee9a31c ("powerpc: Reduce PTE table memory wastage") Cc: stable@vger.kernel.org # v3.10+ Reviewed-by: Aneesh Kumar K.V Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- include/linux/mm_types.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 99ce070e7dcb..22651e124071 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -139,7 +139,10 @@ struct page { unsigned long _pt_pad_1; /* compound_head */ pgtable_t pmd_huge_pte; /* protected by page->ptl */ unsigned long _pt_pad_2; /* mapping */ - struct mm_struct *pt_mm; /* x86 pgds only */ + union { + struct mm_struct *pt_mm; /* x86 pgds only */ + atomic_t pt_frag_refcount; /* powerpc */ + }; #if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else -- cgit v1.2.3 From 6fdecfe32f903d9f5f35ee4464fd32ede470dcad Mon Sep 17 00:00:00 2001 From: Arun Parameswaran Date: Tue, 7 Aug 2018 10:02:44 -0700 Subject: net: phy: Add support for Broadcom Omega internal Combo GPHY Add support for the Broadcom Omega SoC internal Combo Ethernet GPHY to the bcm7xxx phy driver. Signed-off-by: Arun Parameswaran Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index daa9234a9baf..949e9af8d9d6 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -45,6 +45,7 @@ #define PHY_ID_BCM7445 0x600d8510 #define PHY_ID_BCM_CYGNUS 0xae025200 +#define PHY_ID_BCM_OMEGA 0xae025100 #define PHY_BCM_OUI_MASK 0xfffffc00 #define PHY_BCM_OUI_1 0x00206000 -- cgit v1.2.3 From d88e61faad526a5850e9330c846641b91cf971e7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 30 Jul 2018 09:36:26 +0200 Subject: iommu: Remove the ->map_sg indirection All iommu drivers use the default_iommu_map_sg implementation, and there is no good reason to ever override it. Just expose it as iommu_map_sg directly and remove the indirection, specially in our post-spectre world where indirect calls are horribly expensive. Signed-off-by: Christoph Hellwig Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7447b0b0579a..87994c265bf5 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -166,8 +166,6 @@ struct iommu_resv_region { * @detach_dev: detach device from an iommu domain * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain - * @map_sg: map a scatter-gather list of physically contiguous memory chunks - * to an iommu domain * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain * @tlb_range_add: Add a given iova range to the flush queue for this domain * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush @@ -201,8 +199,6 @@ struct iommu_ops { phys_addr_t paddr, size_t size, int prot); size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size); - size_t (*map_sg)(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot); void (*flush_iotlb_all)(struct iommu_domain *domain); void (*iotlb_range_add)(struct iommu_domain *domain, unsigned long iova, size_t size); @@ -303,9 +299,8 @@ extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size); extern size_t iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova, size_t size); -extern size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg,unsigned int nents, - int prot); +extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg,unsigned int nents, int prot); extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova); extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); @@ -378,13 +373,6 @@ static inline void iommu_tlb_sync(struct iommu_domain *domain) domain->ops->iotlb_sync(domain); } -static inline size_t iommu_map_sg(struct iommu_domain *domain, - unsigned long iova, struct scatterlist *sg, - unsigned int nents, int prot) -{ - return domain->ops->map_sg(domain, iova, sg, nents, prot); -} - /* PCI device grouping function */ extern struct iommu_group *pci_device_group(struct device *dev); /* Generic device grouping function */ -- cgit v1.2.3 From 8b92d0e3d400390660a26ef7f475524700fb86cf Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 8 Aug 2018 08:35:29 +0200 Subject: nvme.h: fixup ANA group descriptor format ANA Phase 3 draft had the 'reserved' field in the group descriptor format set to '23:17' (so that the first namespace identifier started at byte 24), but that got move with the approved TP to '31:17' (so that the first namespace identifier started at byte 32). Signed-off-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 64c9175723de..a661861e9d56 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -446,7 +446,7 @@ struct nvme_ana_group_desc { __le32 nnsids; __le64 chgcnt; __u8 state; - __u8 rsvd17[7]; + __u8 rsvd17[15]; __le32 nsids[]; }; -- cgit v1.2.3 From 93045d5942da60801e71764597d448cf37a798c1 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Tue, 7 Aug 2018 23:01:05 -0700 Subject: nvme.h: add support for ns write protect definitions Add various definitions from NVMe 1.3 TP 4005. Signed-off-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index a661861e9d56..68e91ef5494c 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -259,7 +259,7 @@ struct nvme_id_ctrl { __le16 awun; __le16 awupf; __u8 nvscc; - __u8 rsvd531; + __u8 nwpc; __le16 acwu; __u8 rsvd534[2]; __le32 sgls; @@ -320,7 +320,9 @@ struct nvme_id_ns { __u8 nvmcap[16]; __u8 rsvd64[28]; __le32 anagrpid; - __u8 rsvd96[8]; + __u8 rsvd96[3]; + __u8 nsattr; + __u8 rsvd100[4]; __u8 nguid[16]; __u8 eui64[8]; struct nvme_lbaf lbaf[16]; @@ -794,6 +796,7 @@ enum { NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, NVME_FEAT_RESV_PERSIST = 0x83, + NVME_FEAT_WRITE_PROTECT = 0x84, NVME_LOG_ERROR = 0x01, NVME_LOG_SMART = 0x02, NVME_LOG_FW_SLOT = 0x03, @@ -807,6 +810,14 @@ enum { NVME_FWACT_ACTV = (2 << 3), }; +/* NVMe Namespace Write Protect State */ +enum { + NVME_NS_NO_WRITE_PROTECT = 0, + NVME_NS_WRITE_PROTECT, + NVME_NS_WRITE_PROTECT_POWER_CYCLE, + NVME_NS_WRITE_PROTECT_PERMANENT, +}; + #define NVME_MAX_CHANGED_NAMESPACES 1024 struct nvme_identify { @@ -1153,6 +1164,8 @@ enum { NVME_SC_SGL_INVALID_OFFSET = 0x16, NVME_SC_SGL_INVALID_SUBTYPE = 0x17, + NVME_SC_NS_WRITE_PROTECTED = 0x20, + NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, NVME_SC_NS_NOT_READY = 0x82, -- cgit v1.2.3 From 0c66847793d1982d1083dc6f7adad60fa265ce9c Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 1 Aug 2018 14:25:39 -0700 Subject: overflow.h: Add arithmetic shift helper Add shift_overflow() helper to assist driver authors in ensuring that shift operations don't cause overflows or other odd conditions. Signed-off-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky [kees: tweaked comments and commit log, dropped unneeded assignment] Signed-off-by: Kees Cook --- include/linux/overflow.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 8712ff70995f..40b48e2133cb 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -202,6 +202,37 @@ #endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ +/** check_shl_overflow() - Calculate a left-shifted value and check overflow + * + * @a: Value to be shifted + * @s: How many bits left to shift + * @d: Pointer to where to store the result + * + * Computes *@d = (@a << @s) + * + * Returns true if '*d' cannot hold the result or when 'a << s' doesn't + * make sense. Example conditions: + * - 'a << s' causes bits to be lost when stored in *d. + * - 's' is garbage (e.g. negative) or so large that the result of + * 'a << s' is guaranteed to be 0. + * - 'a' is negative. + * - 'a << s' sets the sign bit, if any, in '*d'. + * + * '*d' will hold the results of the attempted shift, but is not + * considered "safe for use" if false is returned. + */ +#define check_shl_overflow(a, s, d) ({ \ + typeof(a) _a = a; \ + typeof(s) _s = s; \ + typeof(d) _d = d; \ + u64 _a_full = _a; \ + unsigned int _to_shift = \ + _s >= 0 && _s < 8 * sizeof(*d) ? _s : 0; \ + *_d = (_a_full << _to_shift); \ + (_to_shift != _s || *_d < 0 || _a < 0 || \ + (*_d >> _to_shift) != _a); \ +}) + /** * array_size() - Calculate size of 2-dimensional array. * -- cgit v1.2.3 From 212dfd909ea8b630e5d6fa4d25aeec9c4b4b14a5 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Tue, 7 Aug 2018 22:06:52 +0200 Subject: netfilter: nfnetlink_osf: add missing enum in nfnetlink_osf uapi header xt_osf_window_size_options was originally part of include/uapi/linux/netfilter/xt_osf.h, restore it. Fixes: bfb15f2a95cb ("netfilter: extract Passive OS fingerprint infrastructure from xt_osf") Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_osf.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h index a7311bc03d3a..ecf7dab81e9e 100644 --- a/include/linux/netfilter/nfnetlink_osf.h +++ b/include/linux/netfilter/nfnetlink_osf.h @@ -4,18 +4,6 @@ #include -/* Initial window size option state machine: multiple of mss, mtu or - * plain numeric value. Can also be made as plain numeric value which - * is not a multiple of specified value. - */ -enum nf_osf_window_size_options { - OSF_WSS_PLAIN = 0, - OSF_WSS_MSS, - OSF_WSS_MTU, - OSF_WSS_MODULO, - OSF_WSS_MAX, -}; - enum osf_fmatch_states { /* Packet does not match the fingerprint */ FMATCH_WRONG = 0, -- cgit v1.2.3 From 4717be73c2843a3d6d8546872177a19358f6b7b5 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 25 Jul 2018 17:39:25 +0300 Subject: i2c: core: Parse SDA hold time from firmware There are two drivers already using the SDA hold time setting. It might be more in the future, thus, make I2C core to parse the setting for us if provided by firmware. Signed-off-by: Andy Shevchenko Tested-by: Alexandre Belloni Reviewed-by: Alexandre Belloni Acked-by: Ludovic Desroches Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 2a98d0886d2e..36f357ecdf67 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -564,6 +564,7 @@ struct i2c_lock_operations { * @scl_fall_ns: time SCL signal takes to fall in ns; t(f) in the I2C specification * @scl_int_delay_ns: time IP core additionally needs to setup SCL in ns * @sda_fall_ns: time SDA signal takes to fall in ns; t(f) in the I2C specification + * @sda_hold_ns: time IP core additionally needs to hold SDA in ns */ struct i2c_timings { u32 bus_freq_hz; @@ -571,6 +572,7 @@ struct i2c_timings { u32 scl_fall_ns; u32 scl_int_delay_ns; u32 sda_fall_ns; + u32 sda_hold_ns; }; /** -- cgit v1.2.3 From 342ac8448f1fb213908656ae5581d0f37a5954e8 Mon Sep 17 00:00:00 2001 From: Denis Drozdov Date: Wed, 8 Aug 2018 16:23:48 -0700 Subject: net/mlx5: Use max_num_eqs for calculation of required MSIX vectors New firmware has defined new HCA capability field called "max_num_eqs", that is the number of available EQs after subtracting reserved FW EQs. Before this capability the FW reported the EQ number in "log_max_eqs", the reported value also contained FW reserved EQs, but the driver might be failing to load on 320 cpus systems due to the fact that FW reserved EQs were not available to the driver. Now the driver has to obtain max_num_eqs value from new FW to get real number of EQs available. Signed-off-by: Denis Drozdov Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 60c2308fe062..63e1ce4c4826 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1133,7 +1133,10 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 general_obj_types[0x40]; - u8 reserved_at_440[0x40]; + u8 reserved_at_440[0x20]; + + u8 reserved_at_460[0x10]; + u8 max_num_eqs[0x10]; u8 reserved_at_480[0x3]; u8 log_max_l2_table[0x5]; -- cgit v1.2.3 From cc9c82a8668cf98748bfbaa83c5c092d5115c25b Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Wed, 8 Aug 2018 16:23:49 -0700 Subject: net/mlx5: Rename modify/query_vport state related enums Modify and query vport state commands share the same admin_state and op_mod values, rename the enums to fit them both. In addition, remove the esw prefix from the admin state enum as this also applied for vnic. Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 6 +++--- include/linux/mlx5/mlx5_ifc.h | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index d489494b0a84..11fa4e66afc5 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -946,9 +946,9 @@ enum { }; enum { - MLX5_ESW_VPORT_ADMIN_STATE_DOWN = 0x0, - MLX5_ESW_VPORT_ADMIN_STATE_UP = 0x1, - MLX5_ESW_VPORT_ADMIN_STATE_AUTO = 0x2, + MLX5_VPORT_ADMIN_STATE_DOWN = 0x0, + MLX5_VPORT_ADMIN_STATE_UP = 0x1, + MLX5_VPORT_ADMIN_STATE_AUTO = 0x2, }; enum { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 63e1ce4c4826..6ead9c1a5396 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3764,8 +3764,8 @@ struct mlx5_ifc_query_vport_state_out_bits { }; enum { - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT = 0x0, - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT = 0x1, + MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT = 0x0, + MLX5_VPORT_STATE_OP_MOD_ESW_VPORT = 0x1, }; struct mlx5_ifc_query_vport_state_in_bits { -- cgit v1.2.3 From 29d8ebd44de8999e292dbb4de76744d4a41039ec Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 8 Aug 2018 16:23:51 -0700 Subject: net/mlx5: Remove unused mlx5_query_vport_admin_state mlx5_query_vport_admin_state() is not used anywhere. Remove it. Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/vport.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 9208cb8809ac..7e7c6dfcfb09 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -43,8 +43,6 @@ enum { }; u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport); -u8 mlx5_query_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, - u16 vport); int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport, u8 state); int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, -- cgit v1.2.3 From 74fe7b551f3385fa585d92616c85b3a575b2b2cb Mon Sep 17 00:00:00 2001 From: Crestez Dan Leonard Date: Tue, 7 Aug 2018 17:52:17 +0300 Subject: regmap: Add regmap_noinc_read API The regmap API usually assumes that bulk read operations will read a range of registers but some I2C/SPI devices have certain registers for which a such a read operation will return data from an internal FIFO instead. Add an explicit API to support bulk read without range semantics. Some linux drivers use regmap_bulk_read or regmap_raw_read for such registers, for example mpu6050 or bmi150 from IIO. This only happens to work because when caching is disabled a single regmap read op will map to a single bus read op (as desired). This breaks if caching is enabled and reg+1 happens to be a cacheable register. Without regmap support refactoring a driver to enable regmap caching requires separate I2C and SPI paths. This is exactly what regmap is supposed to help avoid. Suggested-by: Jonathan Cameron Signed-off-by: Crestez Dan Leonard Signed-off-by: Stefan Popa Signed-off-by: Mark Brown --- include/linux/regmap.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4f38068ffb71..19df946499d2 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -268,6 +268,13 @@ typedef void (*regmap_unlock)(void *); * field is NULL but precious_table (see below) is not, the * check is performed on such table (a register is precious if * it belongs to one of the ranges specified by precious_table). + * @readable_noinc_reg: Optional callback returning true if the register + * supports multiple read operations without incrementing + * the register number. If this field is NULL but + * rd_noinc_table (see below) is not, the check is + * performed on such table (a register is no increment + * readable if it belongs to one of the ranges specified + * by rd_noinc_table). * @disable_locking: This regmap is either protected by external means or * is guaranteed not be be accessed from multiple threads. * Don't use any locking mechanisms. @@ -295,6 +302,7 @@ typedef void (*regmap_unlock)(void *); * @rd_table: As above, for read access. * @volatile_table: As above, for volatile registers. * @precious_table: As above, for precious registers. + * @rd_noinc_table: As above, for no increment readable registers. * @reg_defaults: Power on reset values for registers (for use with * register cache support). * @num_reg_defaults: Number of elements in reg_defaults. @@ -344,6 +352,7 @@ struct regmap_config { bool (*readable_reg)(struct device *dev, unsigned int reg); bool (*volatile_reg)(struct device *dev, unsigned int reg); bool (*precious_reg)(struct device *dev, unsigned int reg); + bool (*readable_noinc_reg)(struct device *dev, unsigned int reg); bool disable_locking; regmap_lock lock; @@ -360,6 +369,7 @@ struct regmap_config { const struct regmap_access_table *rd_table; const struct regmap_access_table *volatile_table; const struct regmap_access_table *precious_table; + const struct regmap_access_table *rd_noinc_table; const struct reg_default *reg_defaults; unsigned int num_reg_defaults; enum regcache_type cache_type; @@ -946,6 +956,8 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg, int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val); int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); +int regmap_noinc_read(struct regmap *map, unsigned int reg, + void *val, size_t val_len); int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, size_t val_count); int regmap_update_bits_base(struct regmap *map, unsigned int reg, @@ -1196,6 +1208,13 @@ static inline int regmap_raw_read(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_noinc_read(struct regmap *map, unsigned int reg, + void *val, size_t val_len) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, size_t val_count) { -- cgit v1.2.3 From b1f4267cc5448d20ae0c515a74141e74365e78a3 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 9 Aug 2018 07:47:28 -0700 Subject: block: Remove two superfluous #include directives Commit 12f5b9314545 ("blk-mq: Remove generation seqeunce") removed the only seqcount_t and u64_stats_sync instances from but did not remove the corresponding #include directives. Since these include directives are no longer needed, remove them. Signed-off-by: Bart Van Assche Cc: Christoph Hellwig Cc: Keith Busch Cc: Ming Lei Cc: Jianchao Wang Cc: Hannes Reinecke , Cc: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 050d599f5ea9..d6869e0e2b64 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -27,8 +27,6 @@ #include #include #include -#include -#include struct module; struct scsi_ioctl_command; -- cgit v1.2.3 From 6bad9b210a228d2fe0e0efe26d9b115348529cee Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 9 Aug 2018 07:53:36 -0700 Subject: blkcg: Introduce blkg_root_lookup() This new function will be used in a later patch to verify whether a queue has been dissociated from the cgroup controller before being released. Signed-off-by: Bart Van Assche Cc: Tejun Heo Cc: Christoph Hellwig Cc: Ming Lei Cc: Omar Sandoval Cc: Johannes Thumshirn Cc: Alexandru Moise <00moses.alexander00@gmail.com> Cc: Joseph Qi Cc: Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index f7b910768306..1361cfc9b878 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -341,6 +341,23 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, return __blkg_lookup(blkcg, q, false); } +/** + * blkg_lookup - look up blkg for the specified request queue + * @q: request_queue of interest + * + * Lookup blkg for @q at the root level. See also blkg_lookup(). + */ +static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q) +{ + struct blkcg_gq *blkg; + + rcu_read_lock(); + blkg = blkg_lookup(&blkcg_root, q); + rcu_read_unlock(); + + return blkg; +} + /** * blkg_to_pdata - get policy private data * @blkg: blkg of interest @@ -864,6 +881,7 @@ static inline bool blk_cgroup_congested(void) { return false; } static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } +static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q) { return NULL; } static inline int blkcg_init_queue(struct request_queue *q) { return 0; } static inline void blkcg_drain_queue(struct request_queue *q) { } static inline void blkcg_exit_queue(struct request_queue *q) { } -- cgit v1.2.3 From 209b43759d65b2cc99ce7757249aacc82b03c4e2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michael=20B=C3=BCsch?= Date: Tue, 31 Jul 2018 22:15:09 +0200 Subject: ssb: Remove SSB_WARN_ON, SSB_BUG_ON and SSB_DEBUG Use the standard WARN_ON instead. If a small kernel is desired, WARN_ON can be disabled globally. Also remove SSB_DEBUG. Besides WARN_ON it only adds a tiny debug check. Include this check unconditionally. Signed-off-by: Michael Buesch Signed-off-by: Kalle Valo --- include/linux/ssb/ssb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 3b43655cabe6..0d5a2691e7e9 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -499,11 +499,9 @@ struct ssb_bus { /* Internal-only stuff follows. Do not touch. */ struct list_head list; -#ifdef CONFIG_SSB_DEBUG /* Is the bus already powered up? */ bool powered_up; int power_warn_count; -#endif /* DEBUG */ }; enum ssb_quirks { -- cgit v1.2.3 From cb95deea0b4aa5c7c7423f4e075a3ddcd59e710b Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 9 Jul 2018 15:13:29 -0400 Subject: NFS OFFLOAD_CANCEL xdr Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- include/linux/nfs4.h | 1 + include/linux/nfs_fs_sb.h | 1 + include/linux/nfs_xdr.h | 12 ++++++++++++ 3 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 57ffaa20d564..c44b87293229 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -527,6 +527,7 @@ enum { NFSPROC4_CLNT_LAYOUTSTATS, NFSPROC4_CLNT_CLONE, NFSPROC4_CLNT_COPY, + NFSPROC4_CLNT_OFFLOAD_CANCEL, NFSPROC4_CLNT_LOOKUPP, }; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 2c18d618604e..fbc735f08d7e 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -255,5 +255,6 @@ struct nfs_server { #define NFS_CAP_LAYOUTSTATS (1U << 22) #define NFS_CAP_CLONE (1U << 23) #define NFS_CAP_COPY (1U << 24) +#define NFS_CAP_OFFLOAD_CANCEL (1U << 25) #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 3b7325cfb291..85e928a56cef 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1403,6 +1403,18 @@ struct nfs42_copy_res { struct nfs_commitres commit_res; }; +struct nfs42_offload_status_args { + struct nfs4_sequence_args osa_seq_args; + struct nfs_fh *osa_src_fh; + nfs4_stateid osa_stateid; +}; + +struct nfs42_offload_status_res { + struct nfs4_sequence_res osr_seq_res; + uint64_t osr_count; + int osr_status; +}; + struct nfs42_seek_args { struct nfs4_sequence_args seq_args; -- cgit v1.2.3 From 67aa7444c4beb40aafedd8d2c60bbcc54987adda Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 9 Jul 2018 15:13:30 -0400 Subject: NFS COPY xdr handle async reply If server returns async reply, it must include a callback stateid, wr_callback_id in the write_response4. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 85e928a56cef..06ddfa31cbef 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1391,6 +1391,7 @@ struct nfs42_copy_args { }; struct nfs42_write_res { + nfs4_stateid stateid; u64 count; struct nfs_writeverf verifier; }; -- cgit v1.2.3 From 62164f317972fcd36590578888f33a1994dda519 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 9 Jul 2018 15:13:31 -0400 Subject: NFS add support for asynchronous COPY Change xdr to always send COPY asynchronously. Keep the list copies send in a list under a server structure. Once copy is sent, it waits on a completion structure that will be signalled by the callback thread that receives CB_OFFLOAD. If CB_OFFLOAD returned an error and even if it returned partial bytes, ignore them (as we can't commit without a verifier to match) and return an error. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 9 +++++++++ include/linux/nfs_fs_sb.h | 1 + include/linux/nfs_xdr.h | 1 + 3 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 2f129bbfaae8..645ad8e342f6 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -185,6 +185,15 @@ struct nfs_inode { struct inode vfs_inode; }; +struct nfs4_copy_state { + struct list_head copies; + nfs4_stateid stateid; + struct completion completion; + uint64_t count; + struct nfs_writeverf verf; + int error; +}; + /* * Access bit flags */ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index fbc735f08d7e..f88952d7b9fb 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -208,6 +208,7 @@ struct nfs_server { struct list_head state_owners_lru; struct list_head layouts; struct list_head delegations; + struct list_head ss_copies; unsigned long mig_gen; unsigned long mig_status; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 06ddfa31cbef..bd1c889a9ed9 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1388,6 +1388,7 @@ struct nfs42_copy_args { u64 dst_pos; u64 count; + bool sync; }; struct nfs42_write_res { -- cgit v1.2.3 From bc0c9079b48ddcf1f8a6e1aaa277288b263c78d8 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 9 Jul 2018 15:13:32 -0400 Subject: NFS handle COPY reply CB_OFFLOAD call race It's possible that server replies back with CB_OFFLOAD call and COPY reply at the same time such that client will process CB_OFFLOAD before reply to COPY. For that keep a list of pending callback stateids received and then before waiting on completion check the pending list. Cleanup any pending copies on the client shutdown. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index f88952d7b9fb..bf39d9c92201 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -121,6 +121,7 @@ struct nfs_client { #endif struct net *cl_net; + struct list_head pending_cb_stateids; }; /* -- cgit v1.2.3 From c3ad2c3b02e953ead2b8d52a0c9e70312930c3d0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 23 Jul 2018 15:20:37 -0500 Subject: signal: Don't restart fork when signals come in. Wen Yang and majiang report that a periodic signal received during fork can cause fork to continually restart preventing an application from making progress. The code was being overly pessimistic. Fork needs to guarantee that a signal sent to multiple processes is logically delivered before the fork and just to the forking process or logically delivered after the fork to both the forking process and it's newly spawned child. For signals like periodic timers that are always delivered to a single process fork can safely complete and let them appear to logically delivered after the fork(). While examining this issue I also discovered that fork today will miss signals delivered to multiple processes during the fork and handled by another thread. Similarly the current code will also miss blocked signals that are delivered to multiple process, as those signals will not appear pending during fork. Add a list of each thread that is currently forking, and keep on that list a signal set that records all of the signals sent to multiple processes. When fork completes initialize the new processes shared_pending signal set with it. The calculate_sigpending function will see those signals and set TIF_SIGPENDING causing the new task to take the slow path to userspace to handle those signals. Making it appear as if those signals were received immediately after the fork. It is not possible to send real time signals to multiple processes and exceptions don't go to multiple processes, which means that that are no signals sent to multiple processes that require siginfo. This means it is safe to not bother collecting siginfo on signals sent during fork. The sigaction of a child of fork is initially the same as the sigaction of the parent process. So a signal the parent ignores the child will also initially ignore. Therefore it is safe to ignore signals sent to multiple processes and ignored by the forking process. Signals sent to only a single process or only a single thread and delivered during fork are treated as if they are received after the fork, and generally not dealt with. They won't cause any problems. V2: Added removal from the multiprocess list on failure. V3: Use -ERESTARTNOINTR directly V4: - Don't queue both SIGCONT and SIGSTOP - Initialize signal_struct.multiprocess in init_task - Move setting of shared_pending to before the new task is visible to signals. This prevents signals from comming in before shared_pending.signal is set to delayed.signal and being lost. V5: - rework list add and delete to account for idle threads v6: - Use sigdelsetmask when removing stop signals Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=200447 Reported-by: Wen Yang and Reported-by: majiang Fixes: 4a2c7a7837da ("[PATCH] make fork() atomic wrt pgrp/session signals") Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index ae2b0b81be25..4e9b77fb702d 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -69,6 +69,11 @@ struct thread_group_cputimer { bool checking_timer; }; +struct multiprocess_signals { + sigset_t signal; + struct hlist_node node; +}; + /* * NOTE! "signal_struct" does not have its own * locking, because a shared signal_struct always @@ -90,6 +95,9 @@ struct signal_struct { /* shared signal handling: */ struct sigpending shared_pending; + /* For collecting multiprocess signals during fork */ + struct hlist_head multiprocess; + /* thread group exit support */ int group_exit_code; /* overloaded: -- cgit v1.2.3 From 624c0f0239f04cce78c86afa95eb2841c84fbab1 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 9 Aug 2018 15:38:38 +0200 Subject: phylink: add helper for configuring 2500BaseX modes Add a helper for MAC drivers to use in their validate callback to deal with 2500BaseX vs 1000BaseX modes, where the hardware supports both but it is not possible to automatically select between them. This helper defaults to 1000BaseX, as that is the 802.3 standard, and will allow users to select 2500BaseX either by forcing the speed if AN is disabled, or by changing the advertising mask if AN is enabled. Disabling AN is not recommended as it is only the speed that we're interested in controlling, not the duplex or pause mode parameters. Signed-off-by: Russell King Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phylink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 50eeae025f1e..021fc6595856 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -234,5 +234,6 @@ int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); #define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) void phylink_set_port_modes(unsigned long *bits); +void phylink_helper_basex_speed(struct phylink_link_state *state); #endif -- cgit v1.2.3 From 48ae5554a076c1bca31448d60263e4038def9f6f Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 8 Aug 2018 09:04:29 +0100 Subject: net: stmmac: Add XGMAC 2.10 HWIF entry Add a new entry to HWIF table for XGMAC 2.10. For now we fill it with empty callbacks which will be added in posterior patches. Signed-off-by: Jose Abreu Cc: David S. Miller Cc: Joao Pinto Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 32feac5bbd75..c43e9a01b892 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -190,5 +190,6 @@ struct plat_stmmacenet_data { bool tso_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; + int has_xgmac; }; #endif -- cgit v1.2.3 From 64bed6cbe38bc95689fb9399872d9ce250192f90 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 13 Jul 2018 17:22:24 +0300 Subject: nfsd: fix leaked file lock with nfs exported overlayfs nfsd and lockd call vfs_lock_file() to lock/unlock the inode returned by locks_inode(file). Many places in nfsd/lockd code use the inode returned by file_inode(file) for lock manipulation. With Overlayfs, file_inode() (the underlying inode) is not the same object as locks_inode() (the overlay inode). This can result in "Leaked POSIX lock" messages and eventually to a kernel crash as reported by Eddie Horng: https://marc.info/?l=linux-unionfs&m=153086643202072&w=2 Fix all the call sites in nfsd/lockd that should use locks_inode(). This is a correctness bug that manifested when overlayfs gained NFS export support in v4.16. Reported-by: Eddie Horng Tested-by: Eddie Horng Cc: Jeff Layton Fixes: 8383f1748829 ("ovl: wire up NFS export operations") Cc: stable@vger.kernel.org Signed-off-by: Amir Goldstein Signed-off-by: J. Bruce Fields --- include/linux/lockd/lockd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 4fd95dbeb52f..b065ef406770 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -299,7 +299,7 @@ int nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr); static inline struct inode *nlmsvc_file_inode(struct nlm_file *file) { - return file_inode(file->f_file); + return locks_inode(file->f_file); } static inline int __nlm_privileged_request4(const struct sockaddr *sap) @@ -359,7 +359,7 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp) static inline int nlm_compare_locks(const struct file_lock *fl1, const struct file_lock *fl2) { - return file_inode(fl1->fl_file) == file_inode(fl2->fl_file) + return locks_inode(fl1->fl_file) == locks_inode(fl2->fl_file) && fl1->fl_pid == fl2->fl_pid && fl1->fl_owner == fl2->fl_owner && fl1->fl_start == fl2->fl_start -- cgit v1.2.3 From 3fd9557aec919e2db99365ad5a2c00d04ae8893c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 27 Jul 2018 11:19:05 -0400 Subject: NFSD: Refactor the generic write vector fill helper fill_in_write_vector() is nearly the same logic as svc_fill_write_vector(), but there are a few differences so that the former can handle multiple WRITE payloads in a single COMPOUND. svc_fill_write_vector() can be adjusted so that it can be used in the NFSv4 WRITE code path too. Instead of assuming the pages are coming from rq_args.pages, have the caller pass in the page list. The immediate benefit is a reduction of code duplication. It also prevents the NFSv4 WRITE decoder from passing an empty vector element when the transport has provided the payload in the xdr_buf's page array. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 574368e8a16f..43f88bd7b601 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -496,6 +496,7 @@ void svc_reserve(struct svc_rqst *rqstp, int space); struct svc_pool * svc_pool_for_cpu(struct svc_serv *serv, int cpu); char * svc_print_addr(struct svc_rqst *, char *, size_t); unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, + struct page **pages, struct kvec *first, size_t total); char *svc_fill_symlink_pathname(struct svc_rqst *rqstp, struct kvec *first, size_t total); -- cgit v1.2.3 From 11b4d66ea3313d9b03a83b80458ddee64990e3c3 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 27 Jul 2018 11:19:10 -0400 Subject: NFSD: Handle full-length symlinks I've given up on the idea of zero-copy handling of SYMLINK on the server side. This is because the Linux VFS symlink API requires the symlink pathname to be in a NUL-terminated kmalloc'd buffer. The NUL-termination is going to be problematic (watching out for landing on a page boundary and dealing with a 4096-byte pathname). I don't believe that SYMLINK creation is on a performance path or is requested frequently enough that it will cause noticeable CPU cache pollution due to data copies. There will be two places where a transport callout will be necessary to fill in the rqstp: one will be in the svc_fill_symlink_pathname() helper that is used by NFSv2 and NFSv3, and the other will be in nfsd4_decode_create(). Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 43f88bd7b601..73e130a840ce 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -499,7 +499,8 @@ unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct page **pages, struct kvec *first, size_t total); char *svc_fill_symlink_pathname(struct svc_rqst *rqstp, - struct kvec *first, size_t total); + struct kvec *first, void *p, + size_t total); #define RPC_MAX_ADDRBUFLEN (63U) -- cgit v1.2.3 From 2d2917f7747805a1f4188672f308d82a8ba01700 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 9 Aug 2018 14:04:14 -0600 Subject: PCI: Export pcie_has_flr() pcie_flr() suggests pcie_has_flr() to ensure that PCIe FLR support is present prior to calling. pcie_flr() is exported while pcie_has_flr() is not. Resolve this. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 307b336496f6..bace761deff2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1090,6 +1090,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, enum pci_bus_speed *speed, enum pcie_link_width *width); void pcie_print_link_status(struct pci_dev *dev); +bool pcie_has_flr(struct pci_dev *dev); int pcie_flr(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); -- cgit v1.2.3 From 5e7baf0fcb2a3aef7329f3c7543d4695a46bd321 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Thu, 9 Aug 2018 11:13:49 -0700 Subject: qed/qede: Multi CoS support. This patch adds support for tc mqprio offload, using this different traffic classes on the adapter can be utilized based on configured priority to tc map. For example - tc qdisc add dev eth0 root mqprio num_tc 4 map 0 1 2 3 This will cause SKBs with priority 0,1,2,3 to transmit over tc 0,1,2,3 hardware queues respectively. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 2978fa4add42..a1310482c4ed 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -39,6 +39,10 @@ #include #include +/* 64 max queues * (1 rx + 4 tx-cos + 1 xdp) */ +#define QED_MIN_L2_CONS (2 + NUM_PHYS_TCS_4PORT_K2) +#define QED_MAX_L2_CONS (64 * (QED_MIN_L2_CONS)) + struct qed_queue_start_common_params { /* Should always be relative to entity sending this. */ u8 vport_id; @@ -49,6 +53,8 @@ struct qed_queue_start_common_params { struct qed_sb_info *p_sb; u8 sb_idx; + + u8 tc; }; struct qed_rxq_start_ret_params { -- cgit v1.2.3 From 15693fd37fc3a49da356164ed15b571c175efc34 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 8 Aug 2018 19:40:31 +0800 Subject: net: skbuff.h: fix using plain integer as NULL warning Fixes the following sparse warning: ./include/linux/skbuff.h:2365:58: warning: Using plain integer as NULL pointer Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7ebdf158a795..7e237a63a70c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2362,7 +2362,7 @@ static inline void skb_probe_transport_header(struct sk_buff *skb, if (skb_transport_header_was_set(skb)) return; - if (skb_flow_dissect_flow_keys_basic(skb, &keys, 0, 0, 0, 0, 0)) + if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); else skb_set_transport_header(skb, offset_hint); -- cgit v1.2.3 From bd2e9567db72e37f7f4b90faa5133bc7365b5f65 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 9 Aug 2018 16:19:52 -0500 Subject: PCI: Hide ACS quirk declarations inside PCI core Move declarations for these functions: pci_dev_specific_acs_enabled() pci_dev_specific_enable_acs() from include/linux/pci.h to drivers/pci/pci.h because nothing outside the PCI core needs to use them. Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..1e1ed049dd1c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1876,20 +1876,9 @@ enum pci_fixup_pass { #ifdef CONFIG_PCI_QUIRKS void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev); -int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags); -int pci_dev_specific_enable_acs(struct pci_dev *dev); #else static inline void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev) { } -static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev, - u16 acs_flags) -{ - return -ENOTTY; -} -static inline int pci_dev_specific_enable_acs(struct pci_dev *dev) -{ - return -ENOTTY; -} #endif void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen); -- cgit v1.2.3 From b0768a86585d4d951a30ff565f19598dbbd67897 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 3 Aug 2018 16:58:09 +0900 Subject: net: Export skb_headers_offset_update This is needed for veth XDP which does skb_copy_expand()-like operation. v2: - Drop skb_copy_header part because it has already been exported now. Signed-off-by: Toshiaki Makita Signed-off-by: Daniel Borkmann --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7ebdf158a795..e93b157f526c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1038,6 +1038,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, } struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); +void skb_headers_offset_update(struct sk_buff *skb, int off); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); -- cgit v1.2.3 From 0b19cc0a8694d4295383f88bc3441765875a57bc Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 3 Aug 2018 16:58:15 +0900 Subject: bpf: Make redirect_info accessible from modules We are going to add kern_flags field in redirect_info for kernel internal use. In order to avoid function call to access the flags, make redirect_info accessible from modules. Also as it is now non-static, add prefix bpf_ to redirect_info. v6: - Fix sparse warning around EXPORT_SYMBOL. Signed-off-by: Toshiaki Makita Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index c73dd7396886..4717af8b95e6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -537,6 +537,16 @@ struct sk_msg_buff { struct list_head list; }; +struct bpf_redirect_info { + u32 ifindex; + u32 flags; + struct bpf_map *map; + struct bpf_map *map_to_flush; + unsigned long map_owner; +}; + +DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); + /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) -- cgit v1.2.3 From 2539650fadbf63a431e76535a9de7bff6ea5e409 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 3 Aug 2018 16:58:16 +0900 Subject: xdp: Helpers for disabling napi_direct of xdp_return_frame We need some mechanism to disable napi_direct on calling xdp_return_frame_rx_napi() from some context. When veth gets support of XDP_REDIRECT, it will redirects packets which are redirected from other devices. On redirection veth will reuse xdp_mem_info of the redirection source device to make return_frame work. But in this case .ndo_xdp_xmit() called from veth redirection uses xdp_mem_info which is not guarded by NAPI, because the .ndo_xdp_xmit() is not called directly from the rxq which owns the xdp_mem_info. This approach introduces a flag in bpf_redirect_info to indicate that napi_direct should be disabled even when _rx_napi variant is used as well as helper functions to use it. A NAPI handler who wants to use this flag needs to call xdp_set_return_frame_no_direct() before processing packets, and call xdp_clear_return_frame_no_direct() after xdp_do_flush_map() before exiting NAPI. v4: - Use bpf_redirect_info for storing the flag instead of xdp_mem_info to avoid per-frame copy cost. Signed-off-by: Toshiaki Makita Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 4717af8b95e6..2b072dab32c0 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -543,10 +543,14 @@ struct bpf_redirect_info { struct bpf_map *map; struct bpf_map *map_to_flush; unsigned long map_owner; + u32 kern_flags; }; DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); +/* flags for bpf_redirect_info kern_flags */ +#define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ + /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) @@ -775,6 +779,27 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +static inline bool xdp_return_frame_no_direct(void) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; +} + +static inline void xdp_set_return_frame_no_direct(void) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; +} + +static inline void xdp_clear_return_frame_no_direct(void) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; +} + static inline int xdp_ok_fwd_dev(const struct net_device *fwd, unsigned int pktlen) { -- cgit v1.2.3 From c9fbb2d25295a566b97d62e6904741e8e1702d83 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 10 Aug 2018 10:47:43 +0200 Subject: net: Provide stub for __netif_set_xps_queue if there is no CONFIG_XPS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Building virtio_net driver without CONFIG_XPS fails with: drivers/net/virtio_net.c: In function ‘virtnet_set_affinity’: drivers/net/virtio_net.c:1910:3: error: implicit declaration of function ‘__netif_set_xps_queue’ [-Werror=implicit-function-declaration] __netif_set_xps_queue(vi->dev, mask, i, false); ^ Fixes: 4d99f6602cb5 ("net: allow to call netif_reset_xps_queues() under cpus_read_lock") Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 282e2e95ad5b..ca5ab98053c8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3412,6 +3412,13 @@ static inline int netif_set_xps_queue(struct net_device *dev, { return 0; } + +static inline int __netif_set_xps_queue(struct net_device *dev, + const unsigned long *mask, + u16 index, bool is_rxqs_map) +{ + return 0; +} #endif /** -- cgit v1.2.3 From bff1b208a5d1dbb2355822ef859edcb9be0379e4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 6 Aug 2018 15:50:58 -0400 Subject: tracing: Partial revert of "tracing: Centralize preemptirq tracepoints and unify their usage" Joel Fernandes created a nice patch that cleaned up the duplicate hooks used by lockdep and irqsoff latency tracer. It made both use tracepoints. But it caused lockdep to trigger several false positives. We have not figured out why yet, but removing lockdep from using the trace event hooks and just call its helper functions directly (like it use to), makes the problem go away. This is a partial revert of the clean up patch c3bc8fd637a9 ("tracing: Centralize preemptirq tracepoints and unify their usage") that adds direct calls for lockdep, but also keeps most of the clean up done to get rid of the horrible preprocessor if statements. Link: http://lkml.kernel.org/r/20180806155058.5ee875f4@gandalf.local.home Cc: Peter Zijlstra Reviewed-by: Joel Fernandes (Google) Fixes: c3bc8fd637a9 ("tracing: Centralize preemptirq tracepoints and unify their usage") Signed-off-by: Steven Rostedt (VMware) --- include/linux/irqflags.h | 8 ++++++-- include/linux/lockdep.h | 2 -- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 50edb9cbbd26..21619c92c377 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -19,9 +19,13 @@ #ifdef CONFIG_PROVE_LOCKING extern void trace_softirqs_on(unsigned long ip); extern void trace_softirqs_off(unsigned long ip); + extern void lockdep_hardirqs_on(unsigned long ip); + extern void lockdep_hardirqs_off(unsigned long ip); #else -# define trace_softirqs_on(ip) do { } while (0) -# define trace_softirqs_off(ip) do { } while (0) + static inline void trace_softirqs_on(unsigned long ip) { } + static inline void trace_softirqs_off(unsigned long ip) { } + static inline void lockdep_hardirqs_on(unsigned long ip) { } + static inline void lockdep_hardirqs_off(unsigned long ip) { } #endif #ifdef CONFIG_TRACE_IRQFLAGS diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index a8113357ceeb..b0d0b51c4d85 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -267,7 +267,6 @@ struct held_lock { * Initialization, self-test and debugging-output methods: */ extern void lockdep_init(void); -extern void lockdep_init_early(void); extern void lockdep_reset(void); extern void lockdep_reset_lock(struct lockdep_map *lock); extern void lockdep_free_key_range(void *start, unsigned long size); @@ -408,7 +407,6 @@ static inline void lockdep_on(void) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) -# define lockdep_init_early() do { } while (0) # define lockdep_init_map(lock, name, key, sub) \ do { (void)(name); (void)(key); } while (0) # define lockdep_set_class(lock, key) do { (void)(key); } while (0) -- cgit v1.2.3 From d799a4de0a250f1bdd99765bb8e55a5e2f469a1f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 3 Aug 2018 00:52:18 +0200 Subject: gpio: mmio: Fix up inverted direction registers The bgpio_init() takes one of two arguments to specify a register to set the direction of the GPIO line: either dirout that indicates that a 1 in the bit in that register sets the corresponding line to output, or dirin which indicates that a 1 in the bit in that register sets the corresponding line to input. Conversely setting the bit to 0 on these will turn the line into input and output respectively. One of these can be defined but not both. This means that a platform that sets a bit to 1 for output only defines dirout and a platform that sets a bit to 0 for output only defines dirin. In short this defines the polarity of the direction register. Both can also be left as NULL meaning the GPIO chip is either input only or output only. Tomer Maimon discovered that for get/set chips (those where the get and set registers are defined but no separate clear register, and specifying BGPIOF_READ_OUTPUT_REG_SET so that we say we want to read the output value from the SET register) we are unconditionally reading the value from the SET register when the direction bit is 1 and from the DAT register when the direction bit is 0, not taking the direction bit polarity into account. It would be expected that when the direction bit is inverted (dirin is defined but not dirout) we read the current value from the DAT register when the bit is 1 and from the SET register when the bit is 0. Currently only some versions of ATH79, brcmstb, some versions of CLP711x, GE, IOP and Loongson use the dirin mode (a 1 in the register means input). They are unaffected because BGPIOF_READ_OUTPUT_REG_SET is not set on any of them. (They do not read back the SET register to figure out the output value.) So this is no regression with current drivers. However the behaviour is wrong and does not work with Tomer's new driver where he needs to use the BGIOF_READ_OUTPUT_REG_SET. This fixes the above issue by: - Instead of defining separate functions for the inverted case, set up a flag in the gpio_chip that indicates that the direction is inverted. - Remove the special inverted functions for setting input/output and getting the direction, rely on the flag instead. - Respect this flag in bgpio_get_set() and bgpio_get_set_multiple() Reported-by: Tomer Maimon Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 5382b5183b7e..0ea328e71ec9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -201,6 +201,8 @@ static inline struct gpio_irq_chip *to_gpio_irq_chip(struct irq_chip *chip) * @reg_set: output set register (out=high) for generic GPIO * @reg_clr: output clear register (out=low) for generic GPIO * @reg_dir: direction setting register for generic GPIO + * @bgpio_dir_inverted: indicates that the direction register is inverted + * (gpiolib private state variable) * @bgpio_bits: number of register bits used for a generic GPIO i.e. * * 8 * @bgpio_lock: used to lock chip->bgpio_data. Also, this is needed to keep @@ -267,6 +269,7 @@ struct gpio_chip { void __iomem *reg_set; void __iomem *reg_clr; void __iomem *reg_dir; + bool bgpio_dir_inverted; int bgpio_bits; spinlock_t bgpio_lock; unsigned long bgpio_data; -- cgit v1.2.3 From 5dc4c4b7d4e8115e7cde96a030f98cb3ab2e458c Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Aug 2018 01:01:24 -0700 Subject: bpf: Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY This patch introduces a new map type BPF_MAP_TYPE_REUSEPORT_SOCKARRAY. To unleash the full potential of a bpf prog, it is essential for the userspace to be capable of directly setting up a bpf map which can then be consumed by the bpf prog to make decision. In this case, decide which SO_REUSEPORT sk to serve the incoming request. By adding BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, the userspace has total control and visibility on where a SO_REUSEPORT sk should be located in a bpf map. The later patch will introduce BPF_PROG_TYPE_SK_REUSEPORT such that the bpf prog can directly select a sk from the bpf map. That will raise the programmability of the bpf prog attached to a reuseport group (a group of sk serving the same IP:PORT). For example, in UDP, the bpf prog can peek into the payload (e.g. through the "data" pointer introduced in the later patch) to learn the application level's connection information and then decide which sk to pick from a bpf map. The userspace can tightly couple the sk's location in a bpf map with the application logic in generating the UDP payload's connection information. This connection info contact/API stays within the userspace. Also, when used with map-in-map, the userspace can switch the old-server-process's inner map to a new-server-process's inner map in one call "bpf_map_update_elem(outer_map, &index, &new_reuseport_array)". The bpf prog will then direct incoming requests to the new process instead of the old process. The old process can finish draining the pending requests (e.g. by "accept()") before closing the old-fds. [Note that deleting a fd from a bpf map does not necessary mean the fd is closed] During map_update_elem(), Only SO_REUSEPORT sk (i.e. which has already been added to a reuse->socks[]) can be used. That means a SO_REUSEPORT sk that is "bind()" for UDP or "bind()+listen()" for TCP. These conditions are ensured in "reuseport_array_update_check()". A SO_REUSEPORT sk can only be added once to a map (i.e. the same sk cannot be added twice even to the same map). SO_REUSEPORT already allows another sk to be created for the same IP:PORT. There is no need to re-create a similar usage in the BPF side. When a SO_REUSEPORT is deleted from the "reuse->socks[]" (e.g. "close()"), it will notify the bpf map to remove it from the map also. It is done through "bpf_sk_reuseport_detach()" and it will only be called if >=1 of the "reuse->sock[]" has ever been added to a bpf map. The map_update()/map_delete() has to be in-sync with the "reuse->socks[]". Hence, the same "reuseport_lock" used by "reuse->socks[]" has to be used here also. Care has been taken to ensure the lock is only acquired when the adding sk passes some strict tests. and freeing the map does not require the reuseport_lock. The reuseport_array will also support lookup from the syscall side. It will return a sock_gen_cookie(). The sock_gen_cookie() is on-demand (i.e. a sk's cookie is not generated until the very first map_lookup_elem()). The lookup cookie is 64bits but it goes against the logical userspace expectation on 32bits sizeof(fd) (and as other fd based bpf maps do also). It may catch user in surprise if we enforce value_size=8 while userspace still pass a 32bits fd during update. Supporting different value_size between lookup and update seems unintuitive also. We also need to consider what if other existing fd based maps want to return 64bits value from syscall's lookup in the future. Hence, reuseport_array supports both value_size 4 and 8, and assuming user will usually use value_size=4. The syscall's lookup will return ENOSPC on value_size=4. It will will only return 64bits value from sock_gen_cookie() when user consciously choose value_size=8 (as a signal that lookup is desired) which then requires a 64bits value in both lookup and update. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 28 ++++++++++++++++++++++++++++ include/linux/bpf_types.h | 3 +++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cd8790d2c6ed..db11662faea6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -524,6 +524,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); +int array_map_alloc_check(union bpf_attr *attr); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) @@ -769,6 +770,33 @@ static inline void __xsk_map_flush(struct bpf_map *map) } #endif +#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) +void bpf_sk_reuseport_detach(struct sock *sk); +int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, + void *value); +int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags); +#else +static inline void bpf_sk_reuseport_detach(struct sock *sk) +{ +} + +#ifdef CONFIG_BPF_SYSCALL +static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, + void *key, void *value) +{ + return -EOPNOTSUPP; +} + +static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, + void *key, void *value, + u64 map_flags) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_BPF_SYSCALL */ +#endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */ + /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index add08be53b6f..14fd6c02d258 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -60,4 +60,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #if defined(CONFIG_XDP_SOCKETS) BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) #endif +#ifdef CONFIG_INET +BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops) +#endif #endif -- cgit v1.2.3 From 2dbb9b9e6df67d444fbe425c7f6014858d337adf Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Aug 2018 01:01:25 -0700 Subject: bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT This patch adds a BPF_PROG_TYPE_SK_REUSEPORT which can select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY. Like other non SK_FILTER/CGROUP_SKB program, it requires CAP_SYS_ADMIN. BPF_PROG_TYPE_SK_REUSEPORT introduces "struct sk_reuseport_kern" to store the bpf context instead of using the skb->cb[48]. At the SO_REUSEPORT sk lookup time, it is in the middle of transiting from a lower layer (ipv4/ipv6) to a upper layer (udp/tcp). At this point, it is not always clear where the bpf context can be appended in the skb->cb[48] to avoid saving-and-restoring cb[]. Even putting aside the difference between ipv4-vs-ipv6 and udp-vs-tcp. It is not clear if the lower layer is only ipv4 and ipv6 in the future and will it not touch the cb[] again before transiting to the upper layer. For example, in udp_gro_receive(), it uses the 48 byte NAPI_GRO_CB instead of IP[6]CB and it may still modify the cb[] after calling the udp[46]_lib_lookup_skb(). Because of the above reason, if sk->cb is used for the bpf ctx, saving-and-restoring is needed and likely the whole 48 bytes cb[] has to be saved and restored. Instead of saving, setting and restoring the cb[], this patch opts to create a new "struct sk_reuseport_kern" and setting the needed values in there. The new BPF_PROG_TYPE_SK_REUSEPORT and "struct sk_reuseport_(kern|md)" will serve all ipv4/ipv6 + udp/tcp combinations. There is no protocol specific usage at this point and it is also inline with the current sock_reuseport.c implementation (i.e. no protocol specific requirement). In "struct sk_reuseport_md", this patch exposes data/data_end/len with semantic similar to other existing usages. Together with "bpf_skb_load_bytes()" and "bpf_skb_load_bytes_relative()", the bpf prog can peek anywhere in the skb. The "bind_inany" tells the bpf prog that the reuseport group is bind-ed to a local INANY address which cannot be learned from skb. The new "bind_inany" is added to "struct sock_reuseport" which will be used when running the new "BPF_PROG_TYPE_SK_REUSEPORT" bpf prog in order to avoid repeating the "bind INANY" test on "sk_v6_rcv_saddr/sk->sk_rcv_saddr" every time a bpf prog is run. It can only be properly initialized when a "sk->sk_reuseport" enabled sk is adding to a hashtable (i.e. during "reuseport_alloc()" and "reuseport_add_sock()"). The new "sk_select_reuseport()" is the main helper that the bpf prog will use to select a SO_REUSEPORT sk. It is the only function that can use the new BPF_MAP_TYPE_REUSEPORT_ARRAY. As mentioned in the earlier patch, the validity of a selected sk is checked in run time in "sk_select_reuseport()". Doing the check in verification time is difficult and inflexible (consider the map-in-map use case). The runtime check is to compare the selected sk's reuseport_id with the reuseport_id that we want. This helper will return -EXXX if the selected sk cannot serve the incoming request (e.g. reuseport_id not match). The bpf prog can decide if it wants to do SK_DROP as its discretion. When the bpf prog returns SK_PASS, the kernel will check if a valid sk has been selected (i.e. "reuse_kern->selected_sk != NULL"). If it does , it will use the selected sk. If not, the kernel will select one from "reuse->socks[]" (as before this patch). The SK_DROP and SK_PASS handling logic will be in the next patch. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_types.h | 3 +++ include/linux/filter.h | 15 +++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 14fd6c02d258..cd26c090e7c0 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -29,6 +29,9 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) #ifdef CONFIG_BPF_LIRC_MODE2 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) #endif +#ifdef CONFIG_INET +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/filter.h b/include/linux/filter.h index 2b072dab32c0..70e9d57677fe 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -32,6 +32,7 @@ struct seccomp_data; struct bpf_prog_aux; struct xdp_rxq_info; struct xdp_buff; +struct sock_reuseport; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function @@ -833,6 +834,20 @@ void bpf_warn_invalid_xdp_action(u32 act); struct sock *do_sk_redirect_map(struct sk_buff *skb); struct sock *do_msg_redirect_map(struct sk_msg_buff *md); +#ifdef CONFIG_INET +struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, + struct bpf_prog *prog, struct sk_buff *skb, + u32 hash); +#else +static inline struct sock * +bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, + struct bpf_prog *prog, struct sk_buff *skb, + u32 hash) +{ + return NULL; +} +#endif + #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; extern int bpf_jit_harden; -- cgit v1.2.3 From 8217ca653ec601246832d562207bc24bdf652d2f Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Aug 2018 01:01:26 -0700 Subject: bpf: Enable BPF_PROG_TYPE_SK_REUSEPORT bpf prog in reuseport selection This patch allows a BPF_PROG_TYPE_SK_REUSEPORT bpf prog to select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY introduced in the earlier patch. "bpf_run_sk_reuseport()" will return -ECONNREFUSED when the BPF_PROG_TYPE_SK_REUSEPORT prog returns SK_DROP. The callers, in inet[6]_hashtable.c and ipv[46]/udp.c, are modified to handle this case and return NULL immediately instead of continuing the sk search from its hashtable. It re-uses the existing SO_ATTACH_REUSEPORT_EBPF setsockopt to attach BPF_PROG_TYPE_SK_REUSEPORT. The "sk_reuseport_attach_bpf()" will check if the attaching bpf prog is in the new SK_REUSEPORT or the existing SOCKET_FILTER type and then check different things accordingly. One level of "__reuseport_attach_prog()" call is removed. The "sk_unhashed() && ..." and "sk->sk_reuseport_cb" tests are pushed back to "reuseport_attach_prog()" in sock_reuseport.c. sock_reuseport.c seems to have more knowledge on those test requirements than filter.c. In "reuseport_attach_prog()", after new_prog is attached to reuse->prog, the old_prog (if any) is also directly freed instead of returning the old_prog to the caller and asking the caller to free. The sysctl_optmem_max check is moved back to the "sk_reuseport_attach_filter()" and "sk_reuseport_attach_bpf()". As of other bpf prog types, the new BPF_PROG_TYPE_SK_REUSEPORT is only bounded by the usual "bpf_prog_charge_memlock()" during load time instead of bounded by both bpf_prog_charge_memlock and sysctl_optmem_max. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 70e9d57677fe..5d565c50bcb2 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -753,6 +753,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); +void sk_reuseport_prog_free(struct bpf_prog *prog); int sk_detach_filter(struct sock *sk); int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); -- cgit v1.2.3 From 19e226e8cc5da02f17ed119f9137036c0f0f5d80 Mon Sep 17 00:00:00 2001 From: Caleb Raitto Date: Thu, 9 Aug 2018 18:18:28 -0700 Subject: virtio: Make vp_set_vq_affinity() take a mask. Make vp_set_vq_affinity() take a cpumask instead of taking a single CPU. If there are fewer queues than cores, queue affinity should be able to map to multiple cores. Link: https://patchwork.ozlabs.org/patch/948149/ Suggested-by: Willem de Bruijn Signed-off-by: Caleb Raitto Acked-by: Gonglei Signed-off-by: David S. Miller --- include/linux/virtio_config.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 5559a2d31c46..32baf8e26735 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -79,7 +79,8 @@ struct virtio_config_ops { u64 (*get_features)(struct virtio_device *vdev); int (*finalize_features)(struct virtio_device *vdev); const char *(*bus_name)(struct virtio_device *vdev); - int (*set_vq_affinity)(struct virtqueue *vq, int cpu); + int (*set_vq_affinity)(struct virtqueue *vq, + const struct cpumask *cpu_mask); const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev, int index); }; @@ -236,11 +237,11 @@ const char *virtio_bus_name(struct virtio_device *vdev) * */ static inline -int virtqueue_set_affinity(struct virtqueue *vq, int cpu) +int virtqueue_set_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask) { struct virtio_device *vdev = vq->vdev; if (vdev->config->set_vq_affinity) - return vdev->config->set_vq_affinity(vq, cpu); + return vdev->config->set_vq_affinity(vq, cpu_mask); return 0; } -- cgit v1.2.3 From b86d865cb1cae1e61527ea0b8977078bbf694328 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 10 Aug 2018 13:28:07 -0700 Subject: blkcg: Make blkg_root_lookup() work for queues in bypass mode For legacy queues the only call of blkg_root_lookup() happens after bypass mode has been enabled. Since blkg_lookup() returns NULL for queues in bypass mode, modify the blkg_root_lookup() such that it no longer depends on bypass mode. Rename the function into blk_queue_root_blkg() as suggested by Tejun. Suggested-by: Tejun Heo Fixes: 6bad9b210a22 ("blkcg: Introduce blkg_root_lookup()") Signed-off-by: Bart Van Assche Cc: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1361cfc9b878..34aec30e06c7 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -342,20 +342,14 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, } /** - * blkg_lookup - look up blkg for the specified request queue + * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair * @q: request_queue of interest * * Lookup blkg for @q at the root level. See also blkg_lookup(). */ -static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q) +static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) { - struct blkcg_gq *blkg; - - rcu_read_lock(); - blkg = blkg_lookup(&blkcg_root, q); - rcu_read_unlock(); - - return blkg; + return q->root_blkg; } /** @@ -881,7 +875,8 @@ static inline bool blk_cgroup_congested(void) { return false; } static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } -static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q) { return NULL; } +static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) +{ return NULL; } static inline int blkcg_init_queue(struct request_queue *q) { return 0; } static inline void blkcg_drain_queue(struct request_queue *q) { } static inline void blkcg_exit_queue(struct request_queue *q) { } -- cgit v1.2.3 From b5b1404d0815894de0690de8a1ab58269e56eae6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 12 Aug 2018 12:19:42 -0700 Subject: init: rename and re-order boot_cpu_state_init() This is purely a preparatory patch for upcoming changes during the 4.19 merge window. We have a function called "boot_cpu_state_init()" that isn't really about the bootup cpu state: that is done much earlier by the similarly named "boot_cpu_init()" (note lack of "state" in name). This function initializes some hotplug CPU state, and needs to run after the percpu data has been properly initialized. It even has a comment to that effect. Except it _doesn't_ actually run after the percpu data has been properly initialized. On x86 it happens to do that, but on at least arm and arm64, the percpu base pointers are initialized by the arch-specific 'smp_prepare_boot_cpu()' hook, which ran _after_ boot_cpu_state_init(). This had some unexpected results, and in particular we have a patch pending for the merge window that did the obvious cleanup of using 'this_cpu_write()' in the cpu hotplug init code: - per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE; + this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); which is obviously the right thing to do. Except because of the ordering issue, it actually failed miserably and unexpectedly on arm64. So this just fixes the ordering, and changes the name of the function to be 'boot_cpu_hotplug_init()' to make it obvious that it's about cpu hotplug state, because the core CPU state was supposed to have already been done earlier. Marked for stable, since the (not yet merged) patch that will show this problem is marked for stable. Reported-by: Vlastimil Babka Reported-by: Mian Yousaf Kaukab Suggested-by: Catalin Marinas Acked-by: Thomas Gleixner Cc: Will Deacon Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/cpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a97a63eef59f..3233fbe23594 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -30,7 +30,7 @@ struct cpu { }; extern void boot_cpu_init(void); -extern void boot_cpu_state_init(void); +extern void boot_cpu_hotplug_init(void); extern void cpu_init(void); extern void trap_init(void); -- cgit v1.2.3 From e8d2bec0457962e8f348a9a3627b398f7fe5c5fc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 12 Aug 2018 01:59:17 +0200 Subject: bpf: decouple btf from seq bpf fs dump and enable more maps Commit a26ca7c982cb ("bpf: btf: Add pretty print support to the basic arraymap") and 699c86d6ec21 ("bpf: btf: add pretty print for hash/lru_hash maps") enabled support for BTF and dumping via BPF fs for array and hash/lru map. However, both can be decoupled from each other such that regular BPF maps can be supported for attaching BTF key/value information, while not all maps necessarily need to dump via map_seq_show_elem() callback. The basic sanity check which is a prerequisite for all maps is that key/value size has to match in any case, and some maps can have extra checks via map_check_btf() callback, e.g. probing certain types or indicating no support in general. With that we can also enable retrieving BTF info for per-cpu map types and lpm. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Yonghong Song --- include/linux/bpf.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index db11662faea6..523481a3471b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -23,7 +23,7 @@ struct bpf_prog; struct bpf_map; struct sock; struct seq_file; -struct btf; +struct btf_type; /* map is generic key/value storage optionally accesible by eBPF programs */ struct bpf_map_ops { @@ -48,8 +48,9 @@ struct bpf_map_ops { u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); - int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf, - u32 key_type_id, u32 value_type_id); + int (*map_check_btf)(const struct bpf_map *map, + const struct btf_type *key_type, + const struct btf_type *value_type); }; struct bpf_map { @@ -118,9 +119,13 @@ static inline bool bpf_map_offload_neutral(const struct bpf_map *map) static inline bool bpf_map_support_seq_show(const struct bpf_map *map) { - return map->ops->map_seq_show_elem && map->ops->map_check_btf; + return map->btf && map->ops->map_seq_show_elem; } +int map_check_no_btf(const struct bpf_map *map, + const struct btf_type *key_type, + const struct btf_type *value_type); + extern const struct bpf_map_ops bpf_map_offload_ops; /* function argument constraints */ -- cgit v1.2.3 From 7723628101aaeb1d723786747529b4ea65c5b5c5 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Sun, 12 Aug 2018 10:49:27 -0700 Subject: bpf: Introduce bpf_skb_ancestor_cgroup_id helper == Problem description == It's useful to be able to identify cgroup associated with skb in TC so that a policy can be applied to this skb, and existing bpf_skb_cgroup_id helper can help with this. Though in real life cgroup hierarchy and hierarchy to apply a policy to don't map 1:1. It's often the case that there is a container and corresponding cgroup, but there are many more sub-cgroups inside container, e.g. because it's delegated to containerized application to control resources for its subsystems, or to separate application inside container from infra that belongs to containerization system (e.g. sshd). At the same time it may be useful to apply a policy to container as a whole. If multiple containers like this are run on a host (what is often the case) and many of them have sub-cgroups, it may not be possible to apply per-container policy in TC with existing helpers such as bpf_skb_under_cgroup or bpf_skb_cgroup_id: * bpf_skb_cgroup_id will return id of immediate cgroup associated with skb, i.e. if it's a sub-cgroup inside container, it can't be used to identify container's cgroup; * bpf_skb_under_cgroup can work only with one cgroup and doesn't scale, i.e. if there are N containers on a host and a policy has to be applied to M of them (0 <= M <= N), it'd require M calls to bpf_skb_under_cgroup, and, if M changes, it'd require to rebuild & load new BPF program. == Solution == The patch introduces new helper bpf_skb_ancestor_cgroup_id that can be used to get id of cgroup v2 that is an ancestor of cgroup associated with skb at specified level of cgroup hierarchy. That way admin can place all containers on one level of cgroup hierarchy (what is a good practice in general and already used in many configurations) and identify specific cgroup on this level no matter what sub-cgroup skb is associated with. E.g. if there is a cgroup hierarchy: root/ root/container1/ root/container1/app11/ root/container1/app11/sub-app-a/ root/container1/app12/ root/container2/ root/container2/app21/ root/container2/app22/ root/container2/app22/sub-app-b/ , then having skb associated with root/container1/app11/sub-app-a/ it's possible to get ancestor at level 1, what is container1 and apply policy for this container, or apply another policy if it's container2. Policies can be kept e.g. in a hash map where key is a container cgroup id and value is an action. Levels where container cgroups are created are usually known in advance whether cgroup hierarchy inside container may be hard to predict especially in case when its creation is delegated to containerized application. == Implementation details == The helper gets ancestor by walking parents up to specified level. Another option would be to get different kind of "id" from cgroup->ancestor_ids[level] and use it with idr_find() to get struct cgroup for ancestor. But that would require radix lookup what doesn't seem to be better (at least it's not obviously better). Format of return value of the new helper is same as that of bpf_skb_cgroup_id. Signed-off-by: Andrey Ignatov Signed-off-by: Daniel Borkmann --- include/linux/cgroup.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c9fdf6f57913..32c553556bbd 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -553,6 +553,36 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, return cgrp->ancestor_ids[ancestor->level] == ancestor->id; } +/** + * cgroup_ancestor - find ancestor of cgroup + * @cgrp: cgroup to find ancestor of + * @ancestor_level: level of ancestor to find starting from root + * + * Find ancestor of cgroup at specified level starting from root if it exists + * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at + * @ancestor_level. + * + * This function is safe to call as long as @cgrp is accessible. + */ +static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, + int ancestor_level) +{ + struct cgroup *ptr; + + if (cgrp->level < ancestor_level) + return NULL; + + for (ptr = cgrp; + ptr && ptr->level > ancestor_level; + ptr = cgroup_parent(ptr)) + ; + + if (ptr && ptr->level == ancestor_level) + return ptr; + + return NULL; +} + /** * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry * @task: the task to be tested -- cgit v1.2.3 From 62b0194368147def8c5a77ce604a125d620fc582 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Sat, 4 Aug 2018 10:23:19 +0200 Subject: clocksource: new RISC-V SBI timer driver The RISC-V ISA defines a per-hart real-time clock and timer, which is present on all systems. The clock is accessed via the 'rdtime' pseudo-instruction (which reads a CSR), and the timer is set via an SBI call. Contains various improvements from Atish Patra . Signed-off-by: Dmitriy Cherkasov Signed-off-by: Palmer Dabbelt [hch: remove dead code, add SPDX tags, used riscv_of_processor_hart(), minor cleanups, merged hotplug cpu support and other improvements from Atish] Signed-off-by: Christoph Hellwig Acked-by: Thomas Gleixner Reviewed-by: Atish Patra Signed-off-by: Palmer Dabbelt --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 8796ba387152..554c27f6cfbd 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -125,6 +125,7 @@ enum cpuhp_state { CPUHP_AP_MARCO_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, + CPUHP_AP_RISCV_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING, -- cgit v1.2.3 From 9af18e56d43ca4864ce65c3542c513827c2697de Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sun, 12 Aug 2018 09:14:03 -0400 Subject: cpumask: make cpumask_next_wrap available without smp The kbuild robot shows build failure on machines without CONFIG_SMP: drivers/net/virtio_net.c:1916:10: error: implicit declaration of function 'cpumask_next_wrap' cpumask_next_wrap is exported from lib/cpumask.o, which has lib-$(CONFIG_SMP) += cpumask.o same as other functions, also define it as static inline in the NR_CPUS==1 branch in include/linux/cpumask.h. If wrap is true and next == start, return nr_cpumask_bits, or 1. Else wrap across the range of valid cpus, here [0]. Fixes: 2ca653d607ce ("virtio_net: Stripe queue affinities across cores.") Signed-off-by: Willem de Bruijn Tested-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- include/linux/cpumask.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 57f20a0a7794..147bdec42215 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -159,6 +159,13 @@ static inline unsigned int cpumask_next_and(int n, return n+1; } +static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, + int start, bool wrap) +{ + /* cpu0 unless stop condition, wrap and at cpu0, then nr_cpumask_bits */ + return (wrap && n == 0); +} + /* cpu must be a valid cpu, ie 0, so there's no other choice. */ static inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) -- cgit v1.2.3 From cf916ffbe0c628bb072ea829f300cff1874162ce Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Sun, 29 Apr 2018 09:17:34 -0500 Subject: net/mlx5: Improve argument name for add flow API The last argument to mlx5_add_flow_rules passes the number of destinations in the struct pointed to by the dest arg. Change the name to better reflect this fact. Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index c40f2fc68655..71fb503b2b52 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -177,7 +177,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft, struct mlx5_flow_spec *spec, struct mlx5_flow_act *flow_act, struct mlx5_flow_destination *dest, - int dest_num); + int num_dest); void mlx5_del_flow_rules(struct mlx5_flow_handle *fr); int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler, -- cgit v1.2.3 From e4648aa4f98a87cf0a83f73a5864cede073053a0 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 13 Aug 2018 15:33:01 -0400 Subject: NFS recover from destination server reboot for copies Mark the destination state to indicate a server-side copy is happening. On detecting a reboot and recovering open state check if any state is engaged in a server-side copy, if so, find the copy and mark it and then signal the waiting thread. Upon wakeup, if copy was marked then propage EAGAIN to the nfsd_copy_file_range and restart the copy from scratch. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 645ad8e342f6..a0831e9d19c9 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -192,6 +192,8 @@ struct nfs4_copy_state { uint64_t count; struct nfs_writeverf verf; int error; + int flags; + struct nfs4_state *parent_state; }; /* -- cgit v1.2.3 From 6d43743e9079ac0531b60cde7eadd0f042873344 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Thu, 9 Aug 2018 09:48:52 +0530 Subject: Uprobe: Additional argument arch_uprobe to uprobe_write_opcode() Add addition argument 'arch_uprobe' to uprobe_write_opcode(). We need this in later set of patches. Link: http://lkml.kernel.org/r/20180809041856.1547-3-ravi.bangoria@linux.ibm.com Reviewed-by: Song Liu Acked-by: Srikar Dronamraju Signed-off-by: Ravi Bangoria Signed-off-by: Steven Rostedt (VMware) --- include/linux/uprobes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 0a294e950df8..bb9d2084af03 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -121,7 +121,7 @@ extern bool is_swbp_insn(uprobe_opcode_t *insn); extern bool is_trap_insn(uprobe_opcode_t *insn); extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); -extern int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); +extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); -- cgit v1.2.3 From b72ae8cac0caff86fe414fceb940655c2d1371c9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Sun, 29 Jul 2018 16:16:56 +0300 Subject: PCI: Add PCI_DEVICE_DATA() macro to fully describe device ID entry There are a lot of examples in the kernel where PCI_VDEVICE() is used and still looks not so convenient due to additional driver_data field attached. Introduce PCI_DEVICE_DATA() macro to fully describe device ID entry in shortest possible form. For example, before: { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MRFLD), (kernel_ulong_t) &dwc3_pci_mrfld_properties, }, after: { PCI_DEVICE_DATA(INTEL, MRFLD, &dwc3_pci_mrfld_properties) }, Drivers can be converted later on in independent way. While here, remove the unused macro with the same name from Ralink wireless driver. Signed-off-by: Andy Shevchenko Signed-off-by: Bjorn Helgaas Acked-by: Kalle Valo # for rt2x00 --- include/linux/pci.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..bf3665c534c2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -819,6 +819,21 @@ struct pci_driver { .vendor = PCI_VENDOR_ID_##vend, .device = (dev), \ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0 +/** + * PCI_DEVICE_DATA - macro used to describe a specific PCI device in very short form + * @vend: the vendor name (without PCI_VENDOR_ID_ prefix) + * @dev: the device name (without PCI_DEVICE_ID__ prefix) + * @data: the driver data to be filled + * + * This macro is used to create a struct pci_device_id that matches a + * specific PCI device. The subvendor, and subdevice fields will be set + * to PCI_ANY_ID. + */ +#define PCI_DEVICE_DATA(vend, dev, data) \ + .vendor = PCI_VENDOR_ID_##vend, .device = PCI_DEVICE_ID_##vend##_##dev, \ + .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0, \ + .driver_data = (kernel_ulong_t)(data) + enum { PCI_REASSIGN_ALL_RSRC = 0x00000001, /* Ignore firmware setup */ PCI_REASSIGN_ALL_BUS = 0x00000002, /* Reassign all bus numbers */ -- cgit v1.2.3 From 6855dc41b24619c3d1de3dbd27dd0546b0e45272 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 6 Jun 2018 15:54:11 +0300 Subject: x86: Add entry trampolines to kcore Without program headers for PTI entry trampoline pages, the trampoline virtual addresses do not map to anything. Example before: sudo gdb --quiet vmlinux /proc/kcore Reading symbols from vmlinux...done. [New process 1] Core was generated by `BOOT_IMAGE=/boot/vmlinuz-4.16.0 root=UUID=a6096b83-b763-4101-807e-f33daff63233'. #0 0x0000000000000000 in irq_stack_union () (gdb) x /21ib 0xfffffe0000006000 0xfffffe0000006000: Cannot access memory at address 0xfffffe0000006000 (gdb) quit After: sudo gdb --quiet vmlinux /proc/kcore [sudo] password for ahunter: Reading symbols from vmlinux...done. [New process 1] Core was generated by `BOOT_IMAGE=/boot/vmlinuz-4.16.0-fix-4-00005-gd6e65a8b4072 root=UUID=a6096b83-b7'. #0 0x0000000000000000 in irq_stack_union () (gdb) x /21ib 0xfffffe0000006000 0xfffffe0000006000: swapgs 0xfffffe0000006003: mov %rsp,-0x3e12(%rip) # 0xfffffe00000021f8 0xfffffe000000600a: xchg %ax,%ax 0xfffffe000000600c: mov %cr3,%rsp 0xfffffe000000600f: bts $0x3f,%rsp 0xfffffe0000006014: and $0xffffffffffffe7ff,%rsp 0xfffffe000000601b: mov %rsp,%cr3 0xfffffe000000601e: mov -0x3019(%rip),%rsp # 0xfffffe000000300c 0xfffffe0000006025: pushq $0x2b 0xfffffe0000006027: pushq -0x3e35(%rip) # 0xfffffe00000021f8 0xfffffe000000602d: push %r11 0xfffffe000000602f: pushq $0x33 0xfffffe0000006031: push %rcx 0xfffffe0000006032: push %rdi 0xfffffe0000006033: mov $0xffffffff91a00010,%rdi 0xfffffe000000603a: callq 0xfffffe0000006046 0xfffffe000000603f: pause 0xfffffe0000006041: lfence 0xfffffe0000006044: jmp 0xfffffe000000603f 0xfffffe0000006046: mov %rdi,(%rsp) 0xfffffe000000604a: retq (gdb) quit In addition, entry trampolines all map to the same page. Represent that by giving the corresponding program headers in kcore the same offset. This has the benefit that, when perf tools uses /proc/kcore as a source for kernel object code, samples from different CPU trampolines are aggregated together. Note, such aggregation is normal for profiling i.e. people want to profile the object code, not every different virtual address the object code might be mapped to (across different processes for example). Notes by PeterZ: This also adds the KCORE_REMAP functionality. Signed-off-by: Adrian Hunter Acked-by: Andi Kleen Acked-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Andy Lutomirski Cc: Dave Hansen Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Joerg Roedel Cc: Thomas Gleixner Cc: x86@kernel.org Link: http://lkml.kernel.org/r/1528289651-4113-4-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/kcore.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kcore.h b/include/linux/kcore.h index 8de55e4b5ee9..bc088ef96358 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -12,11 +12,13 @@ enum kcore_type { KCORE_VMEMMAP, KCORE_USER, KCORE_OTHER, + KCORE_REMAP, }; struct kcore_list { struct list_head list; unsigned long addr; + unsigned long vaddr; size_t size; int type; }; @@ -36,11 +38,22 @@ struct vmcoredd_node { #ifdef CONFIG_PROC_KCORE extern void kclist_add(struct kcore_list *, void *, size_t, int type); +static inline +void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz) +{ + m->vaddr = (unsigned long)vaddr; + kclist_add(m, addr, sz, KCORE_REMAP); +} #else static inline void kclist_add(struct kcore_list *new, void *addr, size_t size, int type) { } + +static inline +void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz) +{ +} #endif #endif /* _LINUX_KCORE_H */ -- cgit v1.2.3 From 2538fb89b8f4ee9e1c1759cfb3c7989d9ef1f6e7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 14 Aug 2018 16:48:50 -0700 Subject: PCI: Limit config space size for Netronome NFP5000 Like the NFP4000 and NFP6000, the NFP5000 as an erratum where reading/ writing to PCI config space addresses above 0x600 can cause the NFP to generate PCIe completion timeouts. Limit the NFP5000's PF's config space size to 0x600 bytes as is already done for the NFP4000 and NFP6000. The NFP5000's VF is 0x6003 (PCI_DEVICE_ID_NETRONOME_NFP6000_VF), the same device ID as the NFP6000's VF. Thus, its config space is already limited by the existing use of quirk_nfp6000(). Signed-off-by: Jakub Kicinski Signed-off-by: Bjorn Helgaas Reviewed-by: Tony Egan --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 29502238e510..381fc009551d 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2541,6 +2541,7 @@ #define PCI_DEVICE_ID_NETRONOME_NFP3200 0x3200 #define PCI_DEVICE_ID_NETRONOME_NFP3240 0x3240 #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 +#define PCI_DEVICE_ID_NETRONOME_NFP5000 0x5000 #define PCI_DEVICE_ID_NETRONOME_NFP6000 0x6000 #define PCI_DEVICE_ID_NETRONOME_NFP6000_VF 0x6003 -- cgit v1.2.3 From 30107fa6908b6c2747ee9100b40af813f99483c3 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 3 Aug 2018 14:08:14 +0300 Subject: mfd: bd71837: Core driver for ROHM BD71837 PMIC ROHM BD71837 PMIC MFD driver providing interrupts and support for three subsystems: - clk - Regulators - input/power-key Signed-off-by: Matti Vaittinen Reviewed-by: Enric Balletbo i Serra Signed-off-by: Lee Jones --- include/linux/mfd/rohm-bd718x7.h | 332 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 332 insertions(+) create mode 100644 include/linux/mfd/rohm-bd718x7.h (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h new file mode 100644 index 000000000000..a528747f8aed --- /dev/null +++ b/include/linux/mfd/rohm-bd718x7.h @@ -0,0 +1,332 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (C) 2018 ROHM Semiconductors */ + +#ifndef __LINUX_MFD_BD71837_H__ +#define __LINUX_MFD_BD71837_H__ + +#include + +enum { + BD71837_BUCK1 = 0, + BD71837_BUCK2, + BD71837_BUCK3, + BD71837_BUCK4, + BD71837_BUCK5, + BD71837_BUCK6, + BD71837_BUCK7, + BD71837_BUCK8, + BD71837_LDO1, + BD71837_LDO2, + BD71837_LDO3, + BD71837_LDO4, + BD71837_LDO5, + BD71837_LDO6, + BD71837_LDO7, + BD71837_REGULATOR_CNT, +}; + +#define BD71837_BUCK1_VOLTAGE_NUM 0x40 +#define BD71837_BUCK2_VOLTAGE_NUM 0x40 +#define BD71837_BUCK3_VOLTAGE_NUM 0x40 +#define BD71837_BUCK4_VOLTAGE_NUM 0x40 + +#define BD71837_BUCK5_VOLTAGE_NUM 0x08 +#define BD71837_BUCK6_VOLTAGE_NUM 0x04 +#define BD71837_BUCK7_VOLTAGE_NUM 0x08 +#define BD71837_BUCK8_VOLTAGE_NUM 0x40 + +#define BD71837_LDO1_VOLTAGE_NUM 0x04 +#define BD71837_LDO2_VOLTAGE_NUM 0x02 +#define BD71837_LDO3_VOLTAGE_NUM 0x10 +#define BD71837_LDO4_VOLTAGE_NUM 0x10 +#define BD71837_LDO5_VOLTAGE_NUM 0x10 +#define BD71837_LDO6_VOLTAGE_NUM 0x10 +#define BD71837_LDO7_VOLTAGE_NUM 0x10 + +enum { + BD71837_REG_REV = 0x00, + BD71837_REG_SWRESET = 0x01, + BD71837_REG_I2C_DEV = 0x02, + BD71837_REG_PWRCTRL0 = 0x03, + BD71837_REG_PWRCTRL1 = 0x04, + BD71837_REG_BUCK1_CTRL = 0x05, + BD71837_REG_BUCK2_CTRL = 0x06, + BD71837_REG_BUCK3_CTRL = 0x07, + BD71837_REG_BUCK4_CTRL = 0x08, + BD71837_REG_BUCK5_CTRL = 0x09, + BD71837_REG_BUCK6_CTRL = 0x0A, + BD71837_REG_BUCK7_CTRL = 0x0B, + BD71837_REG_BUCK8_CTRL = 0x0C, + BD71837_REG_BUCK1_VOLT_RUN = 0x0D, + BD71837_REG_BUCK1_VOLT_IDLE = 0x0E, + BD71837_REG_BUCK1_VOLT_SUSP = 0x0F, + BD71837_REG_BUCK2_VOLT_RUN = 0x10, + BD71837_REG_BUCK2_VOLT_IDLE = 0x11, + BD71837_REG_BUCK3_VOLT_RUN = 0x12, + BD71837_REG_BUCK4_VOLT_RUN = 0x13, + BD71837_REG_BUCK5_VOLT = 0x14, + BD71837_REG_BUCK6_VOLT = 0x15, + BD71837_REG_BUCK7_VOLT = 0x16, + BD71837_REG_BUCK8_VOLT = 0x17, + BD71837_REG_LDO1_VOLT = 0x18, + BD71837_REG_LDO2_VOLT = 0x19, + BD71837_REG_LDO3_VOLT = 0x1A, + BD71837_REG_LDO4_VOLT = 0x1B, + BD71837_REG_LDO5_VOLT = 0x1C, + BD71837_REG_LDO6_VOLT = 0x1D, + BD71837_REG_LDO7_VOLT = 0x1E, + BD71837_REG_TRANS_COND0 = 0x1F, + BD71837_REG_TRANS_COND1 = 0x20, + BD71837_REG_VRFAULTEN = 0x21, + BD71837_REG_MVRFLTMASK0 = 0x22, + BD71837_REG_MVRFLTMASK1 = 0x23, + BD71837_REG_MVRFLTMASK2 = 0x24, + BD71837_REG_RCVCFG = 0x25, + BD71837_REG_RCVNUM = 0x26, + BD71837_REG_PWRONCONFIG0 = 0x27, + BD71837_REG_PWRONCONFIG1 = 0x28, + BD71837_REG_RESETSRC = 0x29, + BD71837_REG_MIRQ = 0x2A, + BD71837_REG_IRQ = 0x2B, + BD71837_REG_IN_MON = 0x2C, + BD71837_REG_POW_STATE = 0x2D, + BD71837_REG_OUT32K = 0x2E, + BD71837_REG_REGLOCK = 0x2F, + BD71837_REG_OTPVER = 0xFF, + BD71837_MAX_REGISTER = 0x100, +}; + +#define REGLOCK_PWRSEQ 0x1 +#define REGLOCK_VREG 0x10 + +/* Generic BUCK control masks */ +#define BD71837_BUCK_SEL 0x02 +#define BD71837_BUCK_EN 0x01 +#define BD71837_BUCK_RUN_ON 0x04 + +/* Generic LDO masks */ +#define BD71837_LDO_SEL 0x80 +#define BD71837_LDO_EN 0x40 + +/* BD71837 BUCK ramp rate CTRL reg bits */ +#define BUCK_RAMPRATE_MASK 0xC0 +#define BUCK_RAMPRATE_10P00MV 0x0 +#define BUCK_RAMPRATE_5P00MV 0x1 +#define BUCK_RAMPRATE_2P50MV 0x2 +#define BUCK_RAMPRATE_1P25MV 0x3 + +/* BD71837_REG_BUCK1_VOLT_RUN bits */ +#define BUCK1_RUN_MASK 0x3F +#define BUCK1_RUN_DEFAULT 0x14 + +/* BD71837_REG_BUCK1_VOLT_SUSP bits */ +#define BUCK1_SUSP_MASK 0x3F +#define BUCK1_SUSP_DEFAULT 0x14 + +/* BD71837_REG_BUCK1_VOLT_IDLE bits */ +#define BUCK1_IDLE_MASK 0x3F +#define BUCK1_IDLE_DEFAULT 0x14 + +/* BD71837_REG_BUCK2_VOLT_RUN bits */ +#define BUCK2_RUN_MASK 0x3F +#define BUCK2_RUN_DEFAULT 0x1E + +/* BD71837_REG_BUCK2_VOLT_IDLE bits */ +#define BUCK2_IDLE_MASK 0x3F +#define BUCK2_IDLE_DEFAULT 0x14 + +/* BD71837_REG_BUCK3_VOLT_RUN bits */ +#define BUCK3_RUN_MASK 0x3F +#define BUCK3_RUN_DEFAULT 0x1E + +/* BD71837_REG_BUCK4_VOLT_RUN bits */ +#define BUCK4_RUN_MASK 0x3F +#define BUCK4_RUN_DEFAULT 0x1E + +/* BD71837_REG_BUCK5_VOLT bits */ +#define BUCK5_MASK 0x07 +#define BUCK5_DEFAULT 0x02 + +/* BD71837_REG_BUCK6_VOLT bits */ +#define BUCK6_MASK 0x03 +#define BUCK6_DEFAULT 0x03 + +/* BD71837_REG_BUCK7_VOLT bits */ +#define BUCK7_MASK 0x07 +#define BUCK7_DEFAULT 0x03 + +/* BD71837_REG_BUCK8_VOLT bits */ +#define BUCK8_MASK 0x3F +#define BUCK8_DEFAULT 0x1E + +/* BD71837_REG_IRQ bits */ +#define IRQ_SWRST 0x40 +#define IRQ_PWRON_S 0x20 +#define IRQ_PWRON_L 0x10 +#define IRQ_PWRON 0x08 +#define IRQ_WDOG 0x04 +#define IRQ_ON_REQ 0x02 +#define IRQ_STBY_REQ 0x01 + +/* BD71837_REG_OUT32K bits */ +#define BD71837_OUT32K_EN 0x01 + +/* BD71837 gated clock rate */ +#define BD71837_CLK_RATE 32768 + +/* ROHM BD71837 irqs */ +enum { + BD71837_INT_STBY_REQ, + BD71837_INT_ON_REQ, + BD71837_INT_WDOG, + BD71837_INT_PWRBTN, + BD71837_INT_PWRBTN_L, + BD71837_INT_PWRBTN_S, + BD71837_INT_SWRST +}; + +/* ROHM BD71837 interrupt masks */ +#define BD71837_INT_SWRST_MASK 0x40 +#define BD71837_INT_PWRBTN_S_MASK 0x20 +#define BD71837_INT_PWRBTN_L_MASK 0x10 +#define BD71837_INT_PWRBTN_MASK 0x8 +#define BD71837_INT_WDOG_MASK 0x4 +#define BD71837_INT_ON_REQ_MASK 0x2 +#define BD71837_INT_STBY_REQ_MASK 0x1 + +/* BD71837_REG_LDO1_VOLT bits */ +#define LDO1_MASK 0x03 + +/* BD71837_REG_LDO1_VOLT bits */ +#define LDO2_MASK 0x20 + +/* BD71837_REG_LDO3_VOLT bits */ +#define LDO3_MASK 0x0F + +/* BD71837_REG_LDO4_VOLT bits */ +#define LDO4_MASK 0x0F + +/* BD71837_REG_LDO5_VOLT bits */ +#define LDO5_MASK 0x0F + +/* BD71837_REG_LDO6_VOLT bits */ +#define LDO6_MASK 0x0F + +/* BD71837_REG_LDO7_VOLT bits */ +#define LDO7_MASK 0x0F + +/* Register write induced reset settings */ + +/* + * Even though the bit zero is not SWRESET type we still want to write zero + * to it when changing type. Bit zero is 'SWRESET' trigger bit and if we + * write 1 to it we will trigger the action. So always write 0 to it when + * changning SWRESET action - no matter what we read from it. + */ +#define BD71837_SWRESET_TYPE_MASK 7 +#define BD71837_SWRESET_TYPE_DISABLED 0 +#define BD71837_SWRESET_TYPE_COLD 4 +#define BD71837_SWRESET_TYPE_WARM 6 + +#define BD71837_SWRESET_RESET_MASK 1 +#define BD71837_SWRESET_RESET 1 + +/* Poweroff state transition conditions */ + +#define BD718XX_ON_REQ_POWEROFF_MASK 1 +#define BD718XX_SWRESET_POWEROFF_MASK 2 +#define BD718XX_WDOG_POWEROFF_MASK 4 +#define BD718XX_KEY_L_POWEROFF_MASK 8 + +#define BD718XX_POWOFF_TO_SNVS 0 +#define BD718XX_POWOFF_TO_RDY 0xF + +#define BD718XX_POWOFF_TIME_MASK 0xF0 +enum { + BD718XX_POWOFF_TIME_5MS = 0, + BD718XX_POWOFF_TIME_10MS, + BD718XX_POWOFF_TIME_15MS, + BD718XX_POWOFF_TIME_20MS, + BD718XX_POWOFF_TIME_25MS, + BD718XX_POWOFF_TIME_30MS, + BD718XX_POWOFF_TIME_35MS, + BD718XX_POWOFF_TIME_40MS, + BD718XX_POWOFF_TIME_45MS, + BD718XX_POWOFF_TIME_50MS, + BD718XX_POWOFF_TIME_75MS, + BD718XX_POWOFF_TIME_100MS, + BD718XX_POWOFF_TIME_250MS, + BD718XX_POWOFF_TIME_500MS, + BD718XX_POWOFF_TIME_750MS, + BD718XX_POWOFF_TIME_1500MS +}; + +/* Poweron sequence state transition conditions */ +#define BD718XX_RDY_TO_SNVS_MASK 0xF +#define BD718XX_SNVS_TO_RUN_MASK 0xF0 + +#define BD718XX_PWR_TRIG_KEY_L 1 +#define BD718XX_PWR_TRIG_KEY_S 2 +#define BD718XX_PWR_TRIG_PMIC_ON 4 +#define BD718XX_PWR_TRIG_VSYS_UVLO 8 +#define BD718XX_RDY_TO_SNVS_SIFT 0 +#define BD718XX_SNVS_TO_RUN_SIFT 4 + +#define BD718XX_PWRBTN_PRESS_DURATION_MASK 0xF + +/* Timeout value for detecting short press */ +enum { + BD718XX_PWRBTN_SHORT_PRESS_10MS = 0, + BD718XX_PWRBTN_SHORT_PRESS_500MS, + BD718XX_PWRBTN_SHORT_PRESS_1000MS, + BD718XX_PWRBTN_SHORT_PRESS_1500MS, + BD718XX_PWRBTN_SHORT_PRESS_2000MS, + BD718XX_PWRBTN_SHORT_PRESS_2500MS, + BD718XX_PWRBTN_SHORT_PRESS_3000MS, + BD718XX_PWRBTN_SHORT_PRESS_3500MS, + BD718XX_PWRBTN_SHORT_PRESS_4000MS, + BD718XX_PWRBTN_SHORT_PRESS_4500MS, + BD718XX_PWRBTN_SHORT_PRESS_5000MS, + BD718XX_PWRBTN_SHORT_PRESS_5500MS, + BD718XX_PWRBTN_SHORT_PRESS_6000MS, + BD718XX_PWRBTN_SHORT_PRESS_6500MS, + BD718XX_PWRBTN_SHORT_PRESS_7000MS, + BD718XX_PWRBTN_SHORT_PRESS_7500MS +}; + +/* Timeout value for detecting LONG press */ +enum { + BD718XX_PWRBTN_LONG_PRESS_10MS = 0, + BD718XX_PWRBTN_LONG_PRESS_1S, + BD718XX_PWRBTN_LONG_PRESS_2S, + BD718XX_PWRBTN_LONG_PRESS_3S, + BD718XX_PWRBTN_LONG_PRESS_4S, + BD718XX_PWRBTN_LONG_PRESS_5S, + BD718XX_PWRBTN_LONG_PRESS_6S, + BD718XX_PWRBTN_LONG_PRESS_7S, + BD718XX_PWRBTN_LONG_PRESS_8S, + BD718XX_PWRBTN_LONG_PRESS_9S, + BD718XX_PWRBTN_LONG_PRESS_10S, + BD718XX_PWRBTN_LONG_PRESS_11S, + BD718XX_PWRBTN_LONG_PRESS_12S, + BD718XX_PWRBTN_LONG_PRESS_13S, + BD718XX_PWRBTN_LONG_PRESS_14S, + BD718XX_PWRBTN_LONG_PRESS_15S +}; + +struct bd71837_pmic; +struct bd71837_clk; + +struct bd71837 { + struct device *dev; + struct regmap *regmap; + unsigned long int id; + + int chip_irq; + struct regmap_irq_chip_data *irq_data; + + struct bd71837_pmic *pmic; + struct bd71837_clk *clk; +}; + +#endif /* __LINUX_MFD_BD71837_H__ */ -- cgit v1.2.3 From d2c9281c184bf2b768ac141a7a10586e0643695d Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 7 Aug 2018 10:08:12 +0100 Subject: mfd: madera: Add register definitions for accessory detect Add some register definitions for accessory detection, used by the extcon driver. Signed-off-by: Richard Fitzgerald Signed-off-by: Lee Jones --- include/linux/mfd/madera/registers.h | 51 ++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/registers.h b/include/linux/mfd/madera/registers.h index a6b7c4222c5e..977e06101711 100644 --- a/include/linux/mfd/madera/registers.h +++ b/include/linux/mfd/madera/registers.h @@ -1219,9 +1219,11 @@ #define MADERA_IRQ1_STATUS_33 0x1820 #define MADERA_IRQ1_MASK_1 0x1840 #define MADERA_IRQ1_MASK_2 0x1841 +#define MADERA_IRQ1_MASK_6 0x1845 #define MADERA_IRQ1_MASK_33 0x1860 #define MADERA_IRQ1_RAW_STATUS_1 0x1880 #define MADERA_IRQ1_RAW_STATUS_2 0x1881 +#define MADERA_IRQ1_RAW_STATUS_7 0x1886 #define MADERA_IRQ1_RAW_STATUS_15 0x188E #define MADERA_IRQ1_RAW_STATUS_33 0x18A0 #define MADERA_INTERRUPT_DEBOUNCE_7 0x1A06 @@ -1664,6 +1666,42 @@ #define MADERA_MICB2A_ENA_SHIFT 0 #define MADERA_MICB2A_ENA_WIDTH 1 +/* (0x0225) - HP Ctrl 1L */ +#define MADERA_RMV_SHRT_HP1L 0x4000 +#define MADERA_RMV_SHRT_HP1L_MASK 0x4000 +#define MADERA_RMV_SHRT_HP1L_SHIFT 14 +#define MADERA_RMV_SHRT_HP1L_WIDTH 1 +#define MADERA_HP1L_FLWR 0x0004 +#define MADERA_HP1L_FLWR_MASK 0x0004 +#define MADERA_HP1L_FLWR_SHIFT 2 +#define MADERA_HP1L_FLWR_WIDTH 1 +#define MADERA_HP1L_SHRTI 0x0002 +#define MADERA_HP1L_SHRTI_MASK 0x0002 +#define MADERA_HP1L_SHRTI_SHIFT 1 +#define MADERA_HP1L_SHRTI_WIDTH 1 +#define MADERA_HP1L_SHRTO 0x0001 +#define MADERA_HP1L_SHRTO_MASK 0x0001 +#define MADERA_HP1L_SHRTO_SHIFT 0 +#define MADERA_HP1L_SHRTO_WIDTH 1 + +/* (0x0226) - HP Ctrl 1R */ +#define MADERA_RMV_SHRT_HP1R 0x4000 +#define MADERA_RMV_SHRT_HP1R_MASK 0x4000 +#define MADERA_RMV_SHRT_HP1R_SHIFT 14 +#define MADERA_RMV_SHRT_HP1R_WIDTH 1 +#define MADERA_HP1R_FLWR 0x0004 +#define MADERA_HP1R_FLWR_MASK 0x0004 +#define MADERA_HP1R_FLWR_SHIFT 2 +#define MADERA_HP1R_FLWR_WIDTH 1 +#define MADERA_HP1R_SHRTI 0x0002 +#define MADERA_HP1R_SHRTI_MASK 0x0002 +#define MADERA_HP1R_SHRTI_SHIFT 1 +#define MADERA_HP1R_SHRTI_WIDTH 1 +#define MADERA_HP1R_SHRTO 0x0001 +#define MADERA_HP1R_SHRTO_MASK 0x0001 +#define MADERA_HP1R_SHRTO_SHIFT 0 +#define MADERA_HP1R_SHRTO_WIDTH 1 + /* (0x0293) Accessory_Detect_Mode_1 */ #define MADERA_ACCDET_SRC 0x2000 #define MADERA_ACCDET_SRC_MASK 0x2000 @@ -3766,6 +3804,19 @@ #define MADERA_DSP1_BUS_ERR_EINT1_SHIFT 0 #define MADERA_DSP1_BUS_ERR_EINT1_WIDTH 1 +/* (0x1845) IRQ1_Mask_6 */ +#define MADERA_IM_MICDET2_EINT1 0x0200 +#define MADERA_IM_MICDET2_EINT1_MASK 0x0200 +#define MADERA_IM_MICDET2_EINT1_SHIFT 9 +#define MADERA_IM_MICDET2_EINT1_WIDTH 1 +#define MADERA_IM_MICDET1_EINT1 0x0100 +#define MADERA_IM_MICDET1_EINT1_MASK 0x0100 +#define MADERA_IM_MICDET1_EINT1_SHIFT 8 +#define MADERA_IM_MICDET1_EINT1_WIDTH 1 +#define MADERA_IM_HPDET_EINT1 0x0001 +#define MADERA_IM_HPDET_EINT1_MASK 0x0001 +#define MADERA_IM_HPDET_EINT1_SHIFT 0 +#define MADERA_IM_HPDET_EINT1_WIDTH 1 /* (0x184E) IRQ1_Mask_15 */ #define MADERA_IM_SPK_OVERHEAT_WARN_EINT1 0x0004 #define MADERA_IM_SPK_OVERHEAT_WARN_EINT1_MASK 0x0004 -- cgit v1.2.3 From 817aef260037f33ee0f44c17fe341323d3aebd6d Mon Sep 17 00:00:00 2001 From: Yannik Sembritzki Date: Thu, 16 Aug 2018 14:05:10 +0100 Subject: Replace magic for trusting the secondary keyring with #define Replace the use of a magic number that indicates that verify_*_signature() should use the secondary keyring with a symbol. Signed-off-by: Yannik Sembritzki Signed-off-by: David Howells Cc: keyrings@vger.kernel.org Cc: linux-security-module@vger.kernel.org Signed-off-by: Linus Torvalds --- include/linux/verification.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/verification.h b/include/linux/verification.h index a10549a6c7cd..cfa4730d607a 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -12,6 +12,12 @@ #ifndef _LINUX_VERIFICATION_H #define _LINUX_VERIFICATION_H +/* + * Indicate that both builtin trusted keys and secondary trusted keys + * should be used. + */ +#define VERIFY_USE_SECONDARY_KEYRING ((struct key *)1UL) + /* * The use to which an asymmetric key is being put. */ -- cgit v1.2.3 From 14d32b2525dd3a21c29b0d9edf1748f5dabc1bbc Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Tue, 31 Jul 2018 18:03:32 +0200 Subject: jiffies: add utility function to calculate delta in ms add jiffies_delta_to_msecs() helper func to calculate the delta between two times and eventually 0 if negative. Suggested-by: Eric Dumazet Signed-off-by: Matteo Croce Reviewed-by: Eric Dumazet Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/linux/jiffies.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index a27cf6652327..fa928242567d 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -447,6 +447,11 @@ static inline clock_t jiffies_delta_to_clock_t(long delta) return jiffies_to_clock_t(max(0L, delta)); } +static inline unsigned int jiffies_delta_to_msecs(long delta) +{ + return jiffies_to_msecs(max(0L, delta)); +} + extern unsigned long clock_t_to_jiffies(unsigned long x); extern u64 jiffies_64_to_clock_t(u64 x); extern u64 nsec_to_clock_t(u64 x); -- cgit v1.2.3 From ff93bca769925a2d8fd7f910cdf543d992e17f07 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 14 Aug 2018 15:21:31 -0700 Subject: ila: make lockdep happy again Previously, alloc_ila_locks() and bucket_table_alloc() call spin_lock_init() separately, therefore they have two different lock names and lock class keys. However, after commit b893281715ab ("ila: Call library function alloc_bucket_locks") they both call helper alloc_bucket_spinlocks() which now only has one lock name and lock class key. This causes a few bogus lockdep warnings as reported by syzbot. Fix this by making alloc_bucket_locks() a macro and pass declaration name as lock name and a static lock class key inside the macro. Fixes: b893281715ab ("ila: Call library function alloc_bucket_locks") Reported-by: Cc: Tom Herbert Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/spinlock.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 3190997df9ca..e089157dcf97 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -451,9 +451,20 @@ extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, #define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) -int alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, - size_t max_size, unsigned int cpu_mult, - gfp_t gfp); +int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, + size_t max_size, unsigned int cpu_mult, + gfp_t gfp, const char *name, + struct lock_class_key *key); + +#define alloc_bucket_spinlocks(locks, lock_mask, max_size, cpu_mult, gfp) \ + ({ \ + static struct lock_class_key key; \ + int ret; \ + \ + ret = __alloc_bucket_spinlocks(locks, lock_mask, max_size, \ + cpu_mult, gfp, #locks, &key); \ + ret; \ + }) void free_bucket_spinlocks(spinlock_t *locks); -- cgit v1.2.3 From f6069b9aa9934ede26f41ac0781fce241279ad43 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 17 Aug 2018 23:26:14 +0200 Subject: bpf: fix redirect to map under tail calls Commits 109980b894e9 ("bpf: don't select potentially stale ri->map from buggy xdp progs") and 7c3001313396 ("bpf: fix ri->map_owner pointer on bpf_prog_realloc") tried to mitigate that buggy programs using bpf_redirect_map() helper call do not leave stale maps behind. Idea was to add a map_owner cookie into the per CPU struct redirect_info which was set to prog->aux by the prog making the helper call as a proof that the map is not stale since the prog is implicitly holding a reference to it. This owner cookie could later on get compared with the program calling into BPF whether they match and therefore the redirect could proceed with processing the map safely. In (obvious) hindsight, this approach breaks down when tail calls are involved since the original caller's prog->aux pointer does not have to match the one from one of the progs out of the tail call chain, and therefore the xdp buffer will be dropped instead of redirected. A way around that would be to fix the issue differently (which also allows to remove related work in fast path at the same time): once the life-time of a redirect map has come to its end we use it's map free callback where we need to wait on synchronize_rcu() for current outstanding xdp buffers and remove such a map pointer from the redirect info if found to be present. At that time no program is using this map anymore so we simply invalidate the map pointers to NULL iff they previously pointed to that instance while making sure that the redirect path only reads out the map once. Fixes: 97f91a7cf04f ("bpf: add bpf_redirect_map helper routine") Fixes: 109980b894e9 ("bpf: don't select potentially stale ri->map from buggy xdp progs") Reported-by: Sebastiano Miano Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 5d565c50bcb2..6791a0ac0139 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -543,7 +543,6 @@ struct bpf_redirect_info { u32 flags; struct bpf_map *map; struct bpf_map *map_to_flush; - unsigned long map_owner; u32 kern_flags; }; @@ -781,6 +780,8 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +void bpf_clear_redirect_map(struct bpf_map *map); + static inline bool xdp_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); -- cgit v1.2.3 From e36488c83b6d871b35dd555afb2d434bd61687cf Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 17 Aug 2018 15:43:36 -0700 Subject: bitfield: avoid gcc-8 -Wint-in-bool-context warning Passing an enum into FIELD_GET() produces a long but harmless warning on newer compilers: from include/linux/linkage.h:7, from include/linux/kernel.h:7, from include/linux/skbuff.h:17, from include/linux/if_ether.h:23, from include/linux/etherdevice.h:25, from drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c:63: drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c: In function 'iwl_mvm_rx_mpdu_mq': include/linux/bitfield.h:56:20: error: enum constant in boolean context [-Werror=int-in-bool-context] BUILD_BUG_ON_MSG(!(_mask), _pfx "mask is zero"); \ ^ ... include/linux/bitfield.h:103:3: note: in expansion of macro '__BF_FIELD_CHECK' __BF_FIELD_CHECK(_mask, _reg, 0U, "FIELD_GET: "); \ ^~~~~~~~~~~~~~~~ drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c:1025:21: note: in expansion of macro 'FIELD_GET' le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_SIBG_SYM_OR_USER_NUM_MASK, The problem here is that the caller has no idea how the macro gets expanding, leading to a false-positive. It can be trivially avoided by doing a comparison against zero. This only recently started appearing as the iwlwifi driver was patched to use FIELD_GET. Link: http://lkml.kernel.org/r/20180813220950.194841-1-arnd@arndb.de Fixes: 514c30696fbc ("iwlwifi: add support for IEEE802.11ax") Signed-off-by: Arnd Bergmann Cc: Masahiro Yamada Cc: Johannes Berg Cc: Jakub Kicinski Cc: Andy Shevchenko Cc: Al Viro Cc: David Laight Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitfield.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 65a6981eef7b..3f1ef4450a7c 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -53,7 +53,7 @@ ({ \ BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask), \ _pfx "mask is not constant"); \ - BUILD_BUG_ON_MSG(!(_mask), _pfx "mask is zero"); \ + BUILD_BUG_ON_MSG((_mask) == 0, _pfx "mask is zero"); \ BUILD_BUG_ON_MSG(__builtin_constant_p(_val) ? \ ~((_mask) >> __bf_shf(_mask)) & (_val) : 0, \ _pfx "value too large for the field"); \ -- cgit v1.2.3 From 4cdfffc8722e99be8d400d8fa1fcd615d078ad43 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 17 Aug 2018 15:44:37 -0700 Subject: vfs: discard ATTR_ATTR_FLAG This flag was introduce in 2.1.37pre1 and the only place it was tested was removed in 2.1.43pre1. The flag was never set. Let's discard it properly. Link: http://lkml.kernel.org/r/877en0hewz.fsf@notabene.neil.brown.name Signed-off-by: NeilBrown Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1ec33fd0423f..9d319f1f66f6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -179,7 +179,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ -#define ATTR_ATTR_FLAG (1 << 10) #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) -- cgit v1.2.3 From b3a2369692fedcc439dfaa4f215cf5323a886c88 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 17 Aug 2018 15:45:12 -0700 Subject: include/linux/page_ext.h: drop definition of unused PAGE_EXT_DEBUG_POISON After commit bd33ef368135 ("mm: enable page poisoning early at boot") PAGE_EXT_DEBUG_POISON is not longer used. Remove it. Link: http://lkml.kernel.org/r/20180531135457.20167-2-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Reviewed-by: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_ext.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index ca5461efae2f..bbec618a614b 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -16,18 +16,7 @@ struct page_ext_operations { #ifdef CONFIG_PAGE_EXTENSION -/* - * page_ext->flags bits: - * - * PAGE_EXT_DEBUG_POISON is set for poisoned pages. This is used to - * implement generic debug pagealloc feature. The pages are filled with - * poison patterns and set this flag after free_pages(). The poisoned - * pages are verified whether the patterns are not corrupted and clear - * the flag before alloc_pages(). - */ - enum page_ext_flags { - PAGE_EXT_DEBUG_POISON, /* Page is poisoned */ PAGE_EXT_DEBUG_GUARD, PAGE_EXT_OWNER, #if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) -- cgit v1.2.3 From 10ed63415223b16d7e80ba528556500231814232 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 17 Aug 2018 15:45:15 -0700 Subject: mm/page_ext.c: constify lookup_page_ext() argument lookup_page_ext() finds 'struct page_ext' for a given page. It requires only read access to the given struct page. Current implemnentation takes 'struct page *' as an argument. It makes compiler complain when 'const struct page *' passed. Change the argument to 'const struct page *'. Link: http://lkml.kernel.org/r/20180531135457.20167-3-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Reviewed-by: Andrew Morton Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_ext.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index bbec618a614b..f84f167ec04c 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -50,7 +50,7 @@ static inline void page_ext_init(void) } #endif -struct page_ext *lookup_page_ext(struct page *page); +struct page_ext *lookup_page_ext(const struct page *page); #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; @@ -59,7 +59,7 @@ static inline void pgdat_page_ext_init(struct pglist_data *pgdat) { } -static inline struct page_ext *lookup_page_ext(struct page *page) +static inline struct page_ext *lookup_page_ext(const struct page *page) { return NULL; } -- cgit v1.2.3 From 74c8164e1cdb1eb22f1d49d54e515e81821a8ad0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 17 Aug 2018 15:45:36 -0700 Subject: mpage: mpage_readpages() should submit IO as read-ahead a_ops->readpages() is only ever used for read-ahead, yet we don't flag the IO being submitted as such. Fix that up. Any file system that uses mpage_readpages() as its ->readpages() implementation will now get this right. Since we're passing in whether the IO is read-ahead or not, we don't need to pass in the 'gfp' separately, as it is dependent on the IO being read-ahead. Kill off that member. Add some documentation notes on ->readpages() being purely for read-ahead. Link: http://lkml.kernel.org/r/20180621010725.17813-3-axboe@kernel.dk Signed-off-by: Jens Axboe Reviewed-by: Andrew Morton Cc: Al Viro Cc: Chris Mason Cc: Christoph Hellwig Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9d319f1f66f6..a9242f336f02 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -344,6 +344,10 @@ struct address_space_operations { /* Set a page dirty. Return true if this dirtied it */ int (*set_page_dirty)(struct page *page); + /* + * Reads in the requested pages. Unlike ->readpage(), this is + * PURELY used for read-ahead!. + */ int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); -- cgit v1.2.3 From c9f4cd71383576a916e7fca99c490fc92a289f5a Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 17 Aug 2018 15:45:49 -0700 Subject: mm, huge page: copy target sub-page last when copy huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patch. Because we have put the order algorithm into a separate function, the implementation is quite simple. The patch is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patch, we tested it with vm-scalability run on transparent huge page. With this patch, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. Link: http://lkml.kernel.org/r/20180524005851.4079-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reviewed-by: Mike Kravetz Cc: Andi Kleen Cc: Jan Kara Cc: Michal Hocko Cc: Andrea Arcangeli Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Hugh Dickins Cc: Minchan Kim Cc: Shaohua Li Cc: Christopher Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 68a5121694ef..2fb32d1561eb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2752,7 +2752,8 @@ extern void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page); extern void copy_user_huge_page(struct page *dst, struct page *src, - unsigned long addr, struct vm_area_struct *vma, + unsigned long addr_hint, + struct vm_area_struct *vma, unsigned int pages_per_huge_page); extern long copy_huge_page_from_user(struct page *dst_page, const void __user *usr_src, -- cgit v1.2.3 From 4fbce633910ed80b135b84160a22b219080c8082 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Fri, 17 Aug 2018 15:46:22 -0700 Subject: mm/memory_hotplug.c: make register_mem_sect_under_node() a callback of walk_memory_range() link_mem_sections() and walk_memory_range() share most of the code, so we can use convert link_mem_sections() into a dummy function that calls walk_memory_range() with a callback to register_mem_sect_under_node(). This patch converts register_mem_sect_under_node() in order to match a walk_memory_range's callback, getting rid of the check_nid argument and checking instead if the system is still boothing, since we only have to check for the nid if the system is in such state. Link: http://lkml.kernel.org/r/20180622111839.10071-4-osalvador@techadventures.net Signed-off-by: Oscar Salvador Suggested-by: Pavel Tatashin Tested-by: Reza Arbab Tested-by: Jonathan Cameron Reviewed-by: Pavel Tatashin Cc: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/node.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/node.h b/include/linux/node.h index 6d336e38d155..257bb3d6d014 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -33,10 +33,10 @@ typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) extern int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long nr_pages, bool check_nid); + unsigned long end_pfn); #else static inline int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long nr_pages, bool check_nid) + unsigned long end_pfn) { return 0; } @@ -54,12 +54,14 @@ static inline int register_one_node(int nid) if (node_online(nid)) { struct pglist_data *pgdat = NODE_DATA(nid); + unsigned long start_pfn = pgdat->node_start_pfn; + unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages; error = __register_one_node(nid); if (error) return error; /* link memory sections under this node */ - error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages, true); + error = link_mem_sections(nid, start_pfn, end_pfn); } return error; @@ -69,7 +71,7 @@ extern void unregister_one_node(int nid); extern int register_cpu_under_node(unsigned int cpu, unsigned int nid); extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); extern int register_mem_sect_under_node(struct memory_block *mem_blk, - int nid, bool check_nid); + void *arg); extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, unsigned long phys_index); @@ -99,7 +101,7 @@ static inline int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) return 0; } static inline int register_mem_sect_under_node(struct memory_block *mem_blk, - int nid, bool check_nid) + void *arg) { return 0; } -- cgit v1.2.3 From dc0b58643aff8b378086f25cce6789ccba68cbcb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 17 Aug 2018 15:46:36 -0700 Subject: mm: introduce mem_cgroup_put() helper Introduce the mem_cgroup_put() helper, which helps to eliminate guarding memcg css release with "#ifdef CONFIG_MEMCG" in multiple places. Link: http://lkml.kernel.org/r/20180623000600.5818-2-guro@fb.com Signed-off-by: Roman Gushchin Reviewed-by: Shakeel Butt Reviewed-by: Andrew Morton Acked-by: Johannes Weiner Acked-by: Michal Hocko Acked-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 680d3395fc83..42f4719def32 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -378,6 +378,11 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } +static inline void mem_cgroup_put(struct mem_cgroup *memcg) +{ + css_put(&memcg->css); +} + #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) @@ -850,6 +855,10 @@ static inline bool task_in_mem_cgroup(struct task_struct *task, return true; } +static inline void mem_cgroup_put(struct mem_cgroup *memcg) +{ +} + static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, -- cgit v1.2.3 From d46eb14b735b11927d4bdc2d1854c311af19de6d Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 17 Aug 2018 15:46:39 -0700 Subject: fs: fsnotify: account fsnotify metadata to kmemcg Patch series "Directed kmem charging", v8. The Linux kernel's memory cgroup allows limiting the memory usage of the jobs running on the system to provide isolation between the jobs. All the kernel memory allocated in the context of the job and marked with __GFP_ACCOUNT will also be included in the memory usage and be limited by the job's limit. The kernel memory can only be charged to the memcg of the process in whose context kernel memory was allocated. However there are cases where the allocated kernel memory should be charged to the memcg different from the current processes's memcg. This patch series contains two such concrete use-cases i.e. fsnotify and buffer_head. The fsnotify event objects can consume a lot of system memory for large or unlimited queues if there is either no or slow listener. The events are allocated in the context of the event producer. However they should be charged to the event consumer. Similarly the buffer_head objects can be allocated in a memcg different from the memcg of the page for which buffer_head objects are being allocated. To solve this issue, this patch series introduces mechanism to charge kernel memory to a given memcg. In case of fsnotify events, the memcg of the consumer can be used for charging and for buffer_head, the memcg of the page can be charged. For directed charging, the caller can use the scope API memalloc_[un]use_memcg() to specify the memcg to charge for all the __GFP_ACCOUNT allocations within the scope. This patch (of 2): A lot of memory can be consumed by the events generated for the huge or unlimited queues if there is either no or slow listener. This can cause system level memory pressure or OOMs. So, it's better to account the fsnotify kmem caches to the memcg of the listener. However the listener can be in a different memcg than the memcg of the producer and these allocations happen in the context of the event producer. This patch introduces remote memcg charging API which the producer can use to charge the allocations to the memcg of the listener. There are seven fsnotify kmem caches and among them allocations from dnotify_struct_cache, dnotify_mark_cache, fanotify_mark_cache and inotify_inode_mark_cachep happens in the context of syscall from the listener. So, SLAB_ACCOUNT is enough for these caches. The objects from fsnotify_mark_connector_cachep are not accounted as they are small compared to the notification mark or events and it is unclear whom to account connector to since it is shared by all events attached to the inode. The allocations from the event caches happen in the context of the event producer. For such caches we will need to remote charge the allocations to the listener's memcg. Thus we save the memcg reference in the fsnotify_group structure of the listener. This patch has also moved the members of fsnotify_group to keep the size same, at least for 64 bit build, even with additional member by filling the holes. [shakeelb@google.com: use GFP_KERNEL_ACCOUNT rather than open-coding it] Link: http://lkml.kernel.org/r/20180702215439.211597-1-shakeelb@google.com Link: http://lkml.kernel.org/r/20180627191250.209150-2-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Jan Kara Cc: Amir Goldstein Cc: Greg Thelen Cc: Vladimir Davydov Cc: Roman Gushchin Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fsnotify_backend.h | 12 ++++++++---- include/linux/memcontrol.h | 10 +++++++++- include/linux/sched.h | 3 +++ include/linux/sched/mm.h | 37 +++++++++++++++++++++++++++++++++++++ 4 files changed, 57 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b38964a7a521..a0c4790c5302 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -84,6 +84,8 @@ struct fsnotify_event_private_data; struct fsnotify_fname; struct fsnotify_iter_info; +struct mem_cgroup; + /* * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. @@ -127,6 +129,8 @@ struct fsnotify_event { * everything will be cleaned up. */ struct fsnotify_group { + const struct fsnotify_ops *ops; /* how this group handles things */ + /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. @@ -137,8 +141,6 @@ struct fsnotify_group { */ refcount_t refcnt; /* things with interest in this group */ - const struct fsnotify_ops *ops; /* how this group handles things */ - /* needed to send notification to userspace */ spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ @@ -160,6 +162,8 @@ struct fsnotify_group { atomic_t num_marks; /* 1 for each mark and 1 for not being * past the point of no return when freeing * a group */ + atomic_t user_waits; /* Number of tasks waiting for user + * response */ struct list_head marks_list; /* all inode marks for this group */ struct fasync_struct *fsn_fa; /* async notification */ @@ -167,8 +171,8 @@ struct fsnotify_group { struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ - atomic_t user_waits; /* Number of tasks waiting for user - * response */ + + struct mem_cgroup *memcg; /* memcg to charge allocations */ /* groups can define private fields here or use the void *private */ union { diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 42f4719def32..121e218d2a21 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -373,6 +373,8 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); +struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); + static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; @@ -380,7 +382,8 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ static inline void mem_cgroup_put(struct mem_cgroup *memcg) { - css_put(&memcg->css); + if (memcg) + css_put(&memcg->css); } #define mem_cgroup_from_counter(counter, member) \ @@ -855,6 +858,11 @@ static inline bool task_in_mem_cgroup(struct task_struct *task, return true; } +static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) +{ + return NULL; +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } diff --git a/include/linux/sched.h b/include/linux/sched.h index 95a5018c338e..1827f4a7a6de 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1152,6 +1152,9 @@ struct task_struct { /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; + + /* Used by memcontrol for targeted memcg charge: */ + struct mem_cgroup *active_memcg; #endif #ifdef CONFIG_BLK_CGROUP diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 44d356f5e47c..aebb370a0006 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -248,6 +248,43 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) current->flags = (current->flags & ~PF_MEMALLOC) | flags; } +#ifdef CONFIG_MEMCG +/** + * memalloc_use_memcg - Starts the remote memcg charging scope. + * @memcg: memcg to charge. + * + * This function marks the beginning of the remote memcg charging scope. All the + * __GFP_ACCOUNT allocations till the end of the scope will be charged to the + * given memcg. + * + * NOTE: This function is not nesting safe. + */ +static inline void memalloc_use_memcg(struct mem_cgroup *memcg) +{ + WARN_ON_ONCE(current->active_memcg); + current->active_memcg = memcg; +} + +/** + * memalloc_unuse_memcg - Ends the remote memcg charging scope. + * + * This function marks the end of the remote memcg charging scope started by + * memalloc_use_memcg(). + */ +static inline void memalloc_unuse_memcg(void) +{ + current->active_memcg = NULL; +} +#else +static inline void memalloc_use_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void memalloc_unuse_memcg(void) +{ +} +#endif + #ifdef CONFIG_MEMBARRIER enum { MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), -- cgit v1.2.3 From f745c6f5fe75734f3b35d9d4e6ebe2a7d010ddda Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 17 Aug 2018 15:46:44 -0700 Subject: fs, mm: account buffer_head to kmemcg The buffer_head can consume a significant amount of system memory and is directly related to the amount of page cache. In our production environment we have observed that a lot of machines are spending a significant amount of memory as buffer_head and can not be left as system memory overhead. Charging buffer_head is not as simple as adding __GFP_ACCOUNT to the allocation. The buffer_heads can be allocated in a memcg different from the memcg of the page for which buffer_heads are being allocated. One concrete example is memory reclaim. The reclaim can trigger I/O of pages of any memcg on the system. So, the right way to charge buffer_head is to extract the memcg from the page for which buffer_heads are being allocated and then use targeted memcg charging API. [shakeelb@google.com: use __GFP_ACCOUNT for directed memcg charging] Link: http://lkml.kernel.org/r/20180702220208.213380-1-shakeelb@google.com Link: http://lkml.kernel.org/r/20180627191250.209150-3-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Jan Kara Cc: Amir Goldstein Cc: Greg Thelen Cc: Vladimir Davydov Cc: Roman Gushchin Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 121e218d2a21..50e3e807b427 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -375,6 +375,8 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); +struct mem_cgroup *get_mem_cgroup_from_page(struct page *page); + static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; @@ -863,6 +865,11 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) return NULL; } +static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) +{ + return NULL; +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } -- cgit v1.2.3 From 0207df4fa1a869281ddbf72db6203dbf036b3e1a Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 17 Aug 2018 15:47:04 -0700 Subject: kernel/memremap, kasan: make ZONE_DEVICE with work with KASAN KASAN learns about hotadded memory via the memory hotplug notifier. devm_memremap_pages() intentionally skips calling memory hotplug notifiers. So KASAN doesn't know anything about new memory added by devm_memremap_pages(). This causes a crash when KASAN tries to access non-existent shadow memory: BUG: unable to handle kernel paging request at ffffed0078000000 RIP: 0010:check_memory_region+0x82/0x1e0 Call Trace: memcpy+0x1f/0x50 pmem_do_bvec+0x163/0x720 pmem_make_request+0x305/0xac0 generic_make_request+0x54f/0xcf0 submit_bio+0x9c/0x370 submit_bh_wbc+0x4c7/0x700 block_read_full_page+0x5ef/0x870 do_read_cache_page+0x2b8/0xb30 read_dev_sector+0xbd/0x3f0 read_lba.isra.0+0x277/0x670 efi_partition+0x41a/0x18f0 check_partition+0x30d/0x5e9 rescan_partitions+0x18c/0x840 __blkdev_get+0x859/0x1060 blkdev_get+0x23f/0x810 __device_add_disk+0x9c8/0xde0 pmem_attach_disk+0x9a8/0xf50 nvdimm_bus_probe+0xf3/0x3c0 driver_probe_device+0x493/0xbd0 bus_for_each_drv+0x118/0x1b0 __device_attach+0x1cd/0x2b0 bus_probe_device+0x1ac/0x260 device_add+0x90d/0x1380 nd_async_device_register+0xe/0x50 async_run_entry_fn+0xc3/0x5d0 process_one_work+0xa0a/0x1810 worker_thread+0x87/0xe80 kthread+0x2d7/0x390 ret_from_fork+0x3a/0x50 Add kasan_add_zero_shadow()/kasan_remove_zero_shadow() - post mm_init() interface to map/unmap kasan_zero_page at requested virtual addresses. And use it to add/remove the shadow memory for hotplugged/unplugged device memory. Link: http://lkml.kernel.org/r/20180629164932.740-1-aryabinin@virtuozzo.com Fixes: 41e94a851304 ("add devm_memremap_pages") Signed-off-by: Andrey Ryabinin Reported-by: Dave Chinner Reviewed-by: Dan Williams Tested-by: Dan Williams Cc: Dmitry Vyukov Cc: Alexander Potapenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index de784fd11d12..46aae129917c 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -20,7 +20,7 @@ extern pmd_t kasan_zero_pmd[PTRS_PER_PMD]; extern pud_t kasan_zero_pud[PTRS_PER_PUD]; extern p4d_t kasan_zero_p4d[MAX_PTRS_PER_P4D]; -void kasan_populate_zero_shadow(const void *shadow_start, +int kasan_populate_zero_shadow(const void *shadow_start, const void *shadow_end); static inline void *kasan_mem_to_shadow(const void *addr) @@ -71,6 +71,9 @@ struct kasan_cache { int kasan_module_alloc(void *addr, size_t size); void kasan_free_shadow(const struct vm_struct *vm); +int kasan_add_zero_shadow(void *start, unsigned long size); +void kasan_remove_zero_shadow(void *start, unsigned long size); + size_t ksize(const void *); static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); } size_t kasan_metadata_size(struct kmem_cache *cache); @@ -124,6 +127,14 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object, static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } static inline void kasan_free_shadow(const struct vm_struct *vm) {} +static inline int kasan_add_zero_shadow(void *start, unsigned long size) +{ + return 0; +} +static inline void kasan_remove_zero_shadow(void *start, + unsigned long size) +{} + static inline void kasan_unpoison_slab(const void *ptr) { } static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } -- cgit v1.2.3 From 29ef680ae7c21110af8e6416d84d8a72fc147b14 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 17 Aug 2018 15:47:11 -0700 Subject: memcg, oom: move out_of_memory back to the charge path Commit 3812c8c8f395 ("mm: memcg: do not trap chargers with full callstack on OOM") has changed the ENOMEM semantic of memcg charges. Rather than invoking the oom killer from the charging context it delays the oom killer to the page fault path (pagefault_out_of_memory). This in turn means that many users (e.g. slab or g-u-p) will get ENOMEM when the corresponding memcg hits the hard limit and the memcg is is OOM. This is behavior is inconsistent with !memcg case where the oom killer is invoked from the allocation context and the allocator keeps retrying until it succeeds. The difference in the behavior is user visible. mmap(MAP_POPULATE) might result in not fully populated ranges while the mmap return code doesn't tell that to the userspace. Random syscalls might fail with ENOMEM etc. The primary motivation of the different memcg oom semantic was the deadlock avoidance. Things have changed since then, though. We have an async oom teardown by the oom reaper now and so we do not have to rely on the victim to tear down its memory anymore. Therefore we can return to the original semantic as long as the memcg oom killer is not handed over to the users space. There is still one thing to be careful about here though. If the oom killer is not able to make any forward progress - e.g. because there is no eligible task to kill - then we have to bail out of the charge path to prevent from same class of deadlocks. We have basically two options here. Either we fail the charge with ENOMEM or force the charge and allow overcharge. The first option has been considered more harmful than useful because rare inconsistencies in the ENOMEM behavior is hard to test for and error prone. Basically the same reason why the page allocator doesn't fail allocations under such conditions. The later might allow runaways but those should be really unlikely unless somebody misconfigures the system. E.g. allowing to migrate tasks away from the memcg to a different unlimited memcg with move_charge_at_immigrate disabled. Link: http://lkml.kernel.org/r/20180628151101.25307-1-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Greg Thelen Cc: Johannes Weiner Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 16 ++++++++-------- include/linux/sched.h | 2 +- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 50e3e807b427..57a202f31683 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -507,16 +507,16 @@ unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p); -static inline void mem_cgroup_oom_enable(void) +static inline void mem_cgroup_enter_user_fault(void) { - WARN_ON(current->memcg_may_oom); - current->memcg_may_oom = 1; + WARN_ON(current->in_user_fault); + current->in_user_fault = 1; } -static inline void mem_cgroup_oom_disable(void) +static inline void mem_cgroup_exit_user_fault(void) { - WARN_ON(!current->memcg_may_oom); - current->memcg_may_oom = 0; + WARN_ON(!current->in_user_fault); + current->in_user_fault = 0; } static inline bool task_in_memcg_oom(struct task_struct *p) @@ -961,11 +961,11 @@ static inline void mem_cgroup_handle_over_high(void) { } -static inline void mem_cgroup_oom_enable(void) +static inline void mem_cgroup_enter_user_fault(void) { } -static inline void mem_cgroup_oom_disable(void) +static inline void mem_cgroup_exit_user_fault(void) { } diff --git a/include/linux/sched.h b/include/linux/sched.h index 1827f4a7a6de..066a2c328653 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -722,7 +722,7 @@ struct task_struct { unsigned restore_sigmask:1; #endif #ifdef CONFIG_MEMCG - unsigned memcg_may_oom:1; + unsigned in_user_fault:1; #ifndef CONFIG_SLOB unsigned memcg_kmem_skip_account:1; #endif -- cgit v1.2.3 From 84c07d11aa619c6d24c682f469b10f344f0c02aa Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 17 Aug 2018 15:47:25 -0700 Subject: mm: introduce CONFIG_MEMCG_KMEM as combination of CONFIG_MEMCG && !CONFIG_SLOB Introduce new config option, which is used to replace repeating CONFIG_MEMCG && !CONFIG_SLOB pattern. Next patches add a little more memcg+kmem related code, so let's keep the defines more clearly. Link: http://lkml.kernel.org/r/153063053670.1818.15013136946600481138.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Vladimir Davydov Tested-by: Shakeel Butt Cc: Al Viro Cc: Andrey Ryabinin Cc: Chris Wilson Cc: Greg Kroah-Hartman Cc: Guenter Roeck Cc: "Huang, Ying" Cc: Johannes Weiner Cc: Josef Bacik Cc: Li RongQing Cc: Matthew Wilcox Cc: Matthias Kaehlcke Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Philippe Ombredanne Cc: Roman Gushchin Cc: Sahitya Tummala Cc: Stephen Rothwell Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Waiman Long Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 4 ++-- include/linux/memcontrol.h | 6 +++--- include/linux/sched.h | 2 +- include/linux/slab.h | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 96def9d15b1b..2d23b5b745be 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -42,7 +42,7 @@ struct list_lru_node { spinlock_t lock; /* global list, used for the root cgroup in cgroup aware lrus */ struct list_lru_one lru; -#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) +#ifdef CONFIG_MEMCG_KMEM /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ struct list_lru_memcg __rcu *memcg_lrus; #endif @@ -51,7 +51,7 @@ struct list_lru_node { struct list_lru { struct list_lru_node *node; -#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) +#ifdef CONFIG_MEMCG_KMEM struct list_head list; #endif }; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 57a202f31683..f3c026df7443 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -271,7 +271,7 @@ struct mem_cgroup { bool tcpmem_active; int tcpmem_pressure; -#ifndef CONFIG_SLOB +#ifdef CONFIG_MEMCG_KMEM /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; enum memcg_kmem_state kmem_state; @@ -1231,7 +1231,7 @@ int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, int memcg_kmem_charge(struct page *page, gfp_t gfp, int order); void memcg_kmem_uncharge(struct page *page, int order); -#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) +#ifdef CONFIG_MEMCG_KMEM extern struct static_key_false memcg_kmem_enabled_key; extern struct workqueue_struct *memcg_kmem_cache_wq; @@ -1284,6 +1284,6 @@ static inline void memcg_put_cache_ids(void) { } -#endif /* CONFIG_MEMCG && !CONFIG_SLOB */ +#endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 066a2c328653..789923fbee3a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -723,7 +723,7 @@ struct task_struct { #endif #ifdef CONFIG_MEMCG unsigned in_user_fault:1; -#ifndef CONFIG_SLOB +#ifdef CONFIG_MEMCG_KMEM unsigned memcg_kmem_skip_account:1; #endif #endif diff --git a/include/linux/slab.h b/include/linux/slab.h index 14e3fe4bd6a1..ed9cbddeb4a6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -97,7 +97,7 @@ # define SLAB_FAILSLAB 0 #endif /* Account to memcg */ -#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) +#ifdef CONFIG_MEMCG_KMEM # define SLAB_ACCOUNT ((slab_flags_t __force)0x04000000U) #else # define SLAB_ACCOUNT 0 -- cgit v1.2.3 From b4c2b231c3ba155623591fb6301ed97b95e1c039 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 17 Aug 2018 15:47:29 -0700 Subject: mm: assign id to every memcg-aware shrinker Introduce shrinker::id number, which is used to enumerate memcg-aware shrinkers. The number start from 0, and the code tries to maintain it as small as possible. This will be used to represent a memcg-aware shrinkers in memcg shrinkers map. Since all memcg-aware shrinkers are based on list_lru, which is per-memcg in case of !CONFIG_MEMCG_KMEM only, the new functionality will be under this config option. [ktkhai@virtuozzo.com: v9] Link: http://lkml.kernel.org/r/153112546435.4097.10607140323811756557.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/153063054586.1818.6041047871606697364.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Vladimir Davydov Tested-by: Shakeel Butt Cc: Al Viro Cc: Andrey Ryabinin Cc: Chris Wilson Cc: Greg Kroah-Hartman Cc: Guenter Roeck Cc: "Huang, Ying" Cc: Johannes Weiner Cc: Josef Bacik Cc: Li RongQing Cc: Matthew Wilcox Cc: Matthias Kaehlcke Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Philippe Ombredanne Cc: Roman Gushchin Cc: Sahitya Tummala Cc: Stephen Rothwell Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Waiman Long Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shrinker.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 6794490f25b2..7ca9c18cf130 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -66,6 +66,10 @@ struct shrinker { /* These are for internal use */ struct list_head list; +#ifdef CONFIG_MEMCG_KMEM + /* ID in shrinker_idr */ + int id; +#endif /* objs pending delete, per node */ atomic_long_t *nr_deferred; }; -- cgit v1.2.3 From 0a4465d340282f92719f4e3a56545a848e638d15 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 17 Aug 2018 15:47:37 -0700 Subject: mm, memcg: assign memcg-aware shrinkers bitmap to memcg Imagine a big node with many cpus, memory cgroups and containers. Let we have 200 containers, every container has 10 mounts, and 10 cgroups. All container tasks don't touch foreign containers mounts. If there is intensive pages write, and global reclaim happens, a writing task has to iterate over all memcgs to shrink slab, before it's able to go to shrink_page_list(). Iteration over all the memcg slabs is very expensive: the task has to visit 200 * 10 = 2000 shrinkers for every memcg, and since there are 2000 memcgs, the total calls are 2000 * 2000 = 4000000. So, the shrinker makes 4 million do_shrink_slab() calls just to try to isolate SWAP_CLUSTER_MAX pages in one of the actively writing memcg via shrink_page_list(). I've observed a node spending almost 100% in kernel, making useless iteration over already shrinked slab. This patch adds bitmap of memcg-aware shrinkers to memcg. The size of the bitmap depends on bitmap_nr_ids, and during memcg life it's maintained to be enough to fit bitmap_nr_ids shrinkers. Every bit in the map is related to corresponding shrinker id. Next patches will maintain set bit only for really charged memcg. This will allow shrink_slab() to increase its performance in significant way. See the last patch for the numbers. [ktkhai@virtuozzo.com: v9] Link: http://lkml.kernel.org/r/153112549031.4097.3576147070498769979.stgit@localhost.localdomain [ktkhai@virtuozzo.com: add comment to mem_cgroup_css_online()] Link: http://lkml.kernel.org/r/521f9e5f-c436-b388-fe83-4dc870bfb489@virtuozzo.com Link: http://lkml.kernel.org/r/153063056619.1818.12550500883688681076.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Vladimir Davydov Tested-by: Shakeel Butt Cc: Al Viro Cc: Andrey Ryabinin Cc: Chris Wilson Cc: Greg Kroah-Hartman Cc: Guenter Roeck Cc: "Huang, Ying" Cc: Johannes Weiner Cc: Josef Bacik Cc: Li RongQing Cc: Matthew Wilcox Cc: Matthias Kaehlcke Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Philippe Ombredanne Cc: Roman Gushchin Cc: Sahitya Tummala Cc: Stephen Rothwell Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Waiman Long Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f3c026df7443..2cccbb9e1b3e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -111,6 +111,15 @@ struct lruvec_stat { long count[NR_VM_NODE_STAT_ITEMS]; }; +/* + * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, + * which have elements charged to this memcg. + */ +struct memcg_shrinker_map { + struct rcu_head rcu; + unsigned long map[0]; +}; + /* * per-zone information in memory controller. */ @@ -124,6 +133,9 @@ struct mem_cgroup_per_node { struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; +#ifdef CONFIG_MEMCG_KMEM + struct memcg_shrinker_map __rcu *shrinker_map; +#endif struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ @@ -1262,6 +1274,8 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } +extern int memcg_expand_shrinker_maps(int new_id); + #else #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) -- cgit v1.2.3 From c92e8e10cafeaaedc84f23fed1bfcf9cf07399c2 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 17 Aug 2018 15:47:50 -0700 Subject: fs: propagate shrinker::id to list_lru Add list_lru::shrinker_id field and populate it by registered shrinker id. This will be used to set correct bit in memcg shrinkers map by lru code in next patches, after there appeared the first related to memcg element in list_lru. Link: http://lkml.kernel.org/r/153063059758.1818.14866596416857717800.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Vladimir Davydov Tested-by: Shakeel Butt Cc: Al Viro Cc: Andrey Ryabinin Cc: Chris Wilson Cc: Greg Kroah-Hartman Cc: Guenter Roeck Cc: "Huang, Ying" Cc: Johannes Weiner Cc: Josef Bacik Cc: Li RongQing Cc: Matthew Wilcox Cc: Matthias Kaehlcke Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Philippe Ombredanne Cc: Roman Gushchin Cc: Sahitya Tummala Cc: Stephen Rothwell Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Waiman Long Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 2d23b5b745be..9e75bb33766b 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -53,16 +53,20 @@ struct list_lru { struct list_lru_node *node; #ifdef CONFIG_MEMCG_KMEM struct list_head list; + int shrinker_id; #endif }; void list_lru_destroy(struct list_lru *lru); int __list_lru_init(struct list_lru *lru, bool memcg_aware, - struct lock_class_key *key); - -#define list_lru_init(lru) __list_lru_init((lru), false, NULL) -#define list_lru_init_key(lru, key) __list_lru_init((lru), false, (key)) -#define list_lru_init_memcg(lru) __list_lru_init((lru), true, NULL) + struct lock_class_key *key, struct shrinker *shrinker); + +#define list_lru_init(lru) \ + __list_lru_init((lru), false, NULL, NULL) +#define list_lru_init_key(lru, key) \ + __list_lru_init((lru), false, (key), NULL) +#define list_lru_init_memcg(lru, shrinker) \ + __list_lru_init((lru), true, NULL, shrinker) int memcg_update_all_list_lrus(int num_memcgs); void memcg_drain_all_list_lrus(int src_idx, int dst_idx); -- cgit v1.2.3 From 9bec5c35bfa3d41b046594b5890f772ed737f1fd Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 17 Aug 2018 15:47:58 -0700 Subject: mm/list_lru: pass dst_memcg argument to memcg_drain_list_lru_node() This is just refactoring to allow the next patches to have dst_memcg pointer in memcg_drain_list_lru_node(). Link: http://lkml.kernel.org/r/153063062118.1818.2761273817739499749.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Vladimir Davydov Tested-by: Shakeel Butt Cc: Al Viro Cc: Andrey Ryabinin Cc: Chris Wilson Cc: Greg Kroah-Hartman Cc: Guenter Roeck Cc: "Huang, Ying" Cc: Johannes Weiner Cc: Josef Bacik Cc: Li RongQing Cc: Matthew Wilcox Cc: Matthias Kaehlcke Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Philippe Ombredanne Cc: Roman Gushchin Cc: Sahitya Tummala Cc: Stephen Rothwell Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Waiman Long Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 9e75bb33766b..d9c16f2f2f00 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -69,7 +69,7 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, __list_lru_init((lru), true, NULL, shrinker) int memcg_update_all_list_lrus(int num_memcgs); -void memcg_drain_all_list_lrus(int src_idx, int dst_idx); +void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg); /** * list_lru_add: add an element to the lru list's tail -- cgit v1.2.3 From dfd2f10ccfd7e6bd2a096eaf42e76a7229776322 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 17 Aug 2018 15:48:06 -0700 Subject: mm/memcontrol.c: export mem_cgroup_is_root() This will be used in next patch. Link: http://lkml.kernel.org/r/153063064347.1818.1987011484100392706.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Vladimir Davydov Tested-by: Shakeel Butt Cc: Al Viro Cc: Andrey Ryabinin Cc: Chris Wilson Cc: Greg Kroah-Hartman Cc: Guenter Roeck Cc: "Huang, Ying" Cc: Johannes Weiner Cc: Josef Bacik Cc: Li RongQing Cc: Matthew Wilcox Cc: Matthias Kaehlcke Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Philippe Ombredanne Cc: Roman Gushchin Cc: Sahitya Tummala Cc: Stephen Rothwell Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Waiman Long Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2cccbb9e1b3e..258c8a46959a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -318,6 +318,11 @@ struct mem_cgroup { extern struct mem_cgroup *root_mem_cgroup; +static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) +{ + return (memcg == root_mem_cgroup); +} + static inline bool mem_cgroup_disabled(void) { return !cgroup_subsys_enabled(memory_cgrp_subsys); @@ -784,6 +789,11 @@ void mem_cgroup_split_huge_fixup(struct page *head); struct mem_cgroup; +static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) +{ + return true; +} + static inline bool mem_cgroup_disabled(void) { return true; -- cgit v1.2.3 From fae91d6d8be5e20c47e459dbeb3d43bd5f9486f4 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 17 Aug 2018 15:48:10 -0700 Subject: mm/list_lru.c: set bit in memcg shrinker bitmap on first list_lru item appearance Introduce set_shrinker_bit() function to set shrinker-related bit in memcg shrinker bitmap, and set the bit after the first item is added and in case of reparenting destroyed memcg's items. This will allow next patch to make shrinkers be called only, in case of they have charged objects at the moment, and to improve shrink_slab() performance. [ktkhai@virtuozzo.com: v9] Link: http://lkml.kernel.org/r/153112557572.4097.17315791419810749985.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/153063065671.1818.15914674956134687268.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Vladimir Davydov Tested-by: Shakeel Butt Cc: Al Viro Cc: Andrey Ryabinin Cc: Chris Wilson Cc: Greg Kroah-Hartman Cc: Guenter Roeck Cc: "Huang, Ying" Cc: Johannes Weiner Cc: Josef Bacik Cc: Li RongQing Cc: Matthew Wilcox Cc: Matthias Kaehlcke Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Philippe Ombredanne Cc: Roman Gushchin Cc: Sahitya Tummala Cc: Stephen Rothwell Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Waiman Long Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 258c8a46959a..0e6c515fb698 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1286,6 +1286,8 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) extern int memcg_expand_shrinker_maps(int new_id); +extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, + int nid, int shrinker_id); #else #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) @@ -1308,6 +1310,8 @@ static inline void memcg_put_cache_ids(void) { } +static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, + int nid, int shrinker_id) { } #endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ -- cgit v1.2.3 From 9b996468cfdba09f688f52dba4287de596194613 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 17 Aug 2018 15:48:21 -0700 Subject: mm: add SHRINK_EMPTY shrinker methods return value We need to distinguish the situations when shrinker has very small amount of objects (see vfs_pressure_ratio() called from super_cache_count()), and when it has no objects at all. Currently, in the both of these cases, shrinker::count_objects() returns 0. The patch introduces new SHRINK_EMPTY return value, which will be used for "no objects at all" case. It's is a refactoring mostly, as SHRINK_EMPTY is replaced by 0 by all callers of do_shrink_slab() in this patch, and all the magic will happen in further. Link: http://lkml.kernel.org/r/153063069574.1818.11037751256699341813.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Vladimir Davydov Tested-by: Shakeel Butt Cc: Al Viro Cc: Andrey Ryabinin Cc: Chris Wilson Cc: Greg Kroah-Hartman Cc: Guenter Roeck Cc: "Huang, Ying" Cc: Johannes Weiner Cc: Josef Bacik Cc: Li RongQing Cc: Matthew Wilcox Cc: Matthias Kaehlcke Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Philippe Ombredanne Cc: Roman Gushchin Cc: Sahitya Tummala Cc: Stephen Rothwell Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Waiman Long Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shrinker.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 7ca9c18cf130..b154fd2b084c 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -34,12 +34,15 @@ struct shrink_control { }; #define SHRINK_STOP (~0UL) +#define SHRINK_EMPTY (~0UL - 1) /* * A callback you can register to apply pressure to ageable caches. * * @count_objects should return the number of freeable items in the cache. If - * there are no objects to free or the number of freeable items cannot be - * determined, it should return 0. No deadlock checks should be done during the + * there are no objects to free, it should return SHRINK_EMPTY, while 0 is + * returned in cases of the number of freeable items cannot be determined + * or shrinker should skip this cache for this time (e.g., their number + * is below shrinkable limit). No deadlock checks should be done during the * count callback - the shrinker relies on aggregating scan counts that couldn't * be executed due to potential deadlocks to be run at a later call when the * deadlock condition is no longer pending. -- cgit v1.2.3 From 6518202970c1052148daaef9a8096711775e43a2 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 17 Aug 2018 15:48:57 -0700 Subject: mm/cma: remove unsupported gfp_mask parameter from cma_alloc() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cma_alloc() doesn't really support gfp flags other than __GFP_NOWARN, so convert gfp_mask parameter to boolean no_warn parameter. This will help to avoid giving false feeling that this function supports standard gfp flags and callers can pass __GFP_ZERO to get zeroed buffer, what has already been an issue: see commit dd65a941f6ba ("arm64: dma-mapping: clear buffers allocated with FORCE_CONTIGUOUS flag"). Link: http://lkml.kernel.org/r/20180709122019eucas1p2340da484acfcc932537e6014f4fd2c29~-sqTPJKij2939229392eucas1p2j@eucas1p2.samsung.com Signed-off-by: Marek Szyprowski Acked-by: Michal Hocko Acked-by: Michał Nazarewicz Acked-by: Laura Abbott Acked-by: Vlastimil Babka Reviewed-by: Christoph Hellwig Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cma.h b/include/linux/cma.h index bf90f0bb42bd..190184b5ff32 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -33,7 +33,7 @@ extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, const char *name, struct cma **res_cma); extern struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, - gfp_t gfp_mask); + bool no_warn); extern bool cma_release(struct cma *cma, const struct page *pages, unsigned int count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); -- cgit v1.2.3 From d834c5ab83febf9624ad3b16c3c348aa1e02014c Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 17 Aug 2018 15:49:00 -0700 Subject: kernel/dma: remove unsupported gfp_mask parameter from dma_alloc_from_contiguous() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The CMA memory allocator doesn't support standard gfp flags for memory allocation, so there is no point having it as a parameter for dma_alloc_from_contiguous() function. Replace it by a boolean no_warn argument, which covers all the underlaying cma_alloc() function supports. This will help to avoid giving false feeling that this function supports standard gfp flags and callers can pass __GFP_ZERO to get zeroed buffer, what has already been an issue: see commit dd65a941f6ba ("arm64: dma-mapping: clear buffers allocated with FORCE_CONTIGUOUS flag"). Link: http://lkml.kernel.org/r/20180709122020eucas1p21a71b092975cb4a3b9954ffc63f699d1~-sqUFoa-h2939329393eucas1p2Y@eucas1p2.samsung.com Signed-off-by: Marek Szyprowski Acked-by: Michał Nazarewicz Acked-by: Vlastimil Babka Reviewed-by: Christoph Hellwig Cc: Laura Abbott Cc: Michal Hocko Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dma-contiguous.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index 3c5a4cb3eb95..f247e8aa5e3d 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -112,7 +112,7 @@ static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size, } struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, - unsigned int order, gfp_t gfp_mask); + unsigned int order, bool no_warn); bool dma_release_from_contiguous(struct device *dev, struct page *pages, int count); @@ -145,7 +145,7 @@ int dma_declare_contiguous(struct device *dev, phys_addr_t size, static inline struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, - unsigned int order, gfp_t gfp_mask) + unsigned int order, bool no_warn) { return NULL; } -- cgit v1.2.3 From 40d18ebffb3974272a920c41f2d74431152cae98 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 17 Aug 2018 15:49:07 -0700 Subject: mm/hugetlb: remove gigantic page support for HIGHMEM This reverts ee8f248d266e ("hugetlb: add phys addr to struct huge_bootmem_page"). At one time powerpc used this field and supporting code. However that was removed with commit 79cc38ded1e1 ("powerpc/mm/hugetlb: Add support for reserving gigantic huge pages via kernel command line"). There are no users of this field and supporting code, so remove it. Link: http://lkml.kernel.org/r/20180711195913.1294-1-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Andrew Morton Acked-by: Michal Hocko Cc: "Aneesh Kumar K . V" Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Cannon Matthews Cc: Becky Bruce Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 36fa6a2a82e3..c39d9170a8a0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -348,9 +348,6 @@ struct hstate { struct huge_bootmem_page { struct list_head list; struct hstate *hstate; -#ifdef CONFIG_HIGHMEM - phys_addr_t phys; -#endif }; struct page *alloc_huge_page(struct vm_area_struct *vma, -- cgit v1.2.3 From 35fd1eb1e8212c02f6eae24335a9e5b80f9519b4 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 17 Aug 2018 15:49:21 -0700 Subject: mm/sparse: abstract sparse buffer allocations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "sparse_init rewrite", v6. In sparse_init() we allocate two large buffers to temporary hold usemap and memmap for the whole machine. However, we can avoid doing that if we changed sparse_init() to operated on per-node bases instead of doing it on the whole machine beforehand. As shown by Baoquan http://lkml.kernel.org/r/20180628062857.29658-1-bhe@redhat.com The buffers are large enough to cause machine stop to boot on small memory systems. Another benefit of these changes is that they also obsolete CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER. This patch (of 5): When struct pages are allocated for sparse-vmemmap VA layout, we first try to allocate one large buffer, and than if that fails allocate struct pages for each section as we go. The code that allocates buffer is uses global variables and is spread across several call sites. Cleanup the code by introducing three functions to handle the global buffer: sparse_buffer_init() initialize the buffer sparse_buffer_fini() free the remaining part of the buffer sparse_buffer_alloc() alloc from the buffer, and if buffer is empty return NULL Define these functions in sparse.c instead of sparse-vmemmap.c because later we will use them for non-vmemmap sparse allocations as well. [akpm@linux-foundation.org: use PTR_ALIGN()] [akpm@linux-foundation.org: s/BUG_ON/WARN_ON/] Link: http://lkml.kernel.org/r/20180712203730.8703-2-pasha.tatashin@oracle.com Signed-off-by: Pavel Tatashin Tested-by: Michael Ellerman [powerpc] Reviewed-by: Oscar Salvador Tested-by: Oscar Salvador Cc: Pasha Tatashin Cc: Steven Sistare Cc: Daniel Jordan Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Dan Williams Cc: Jan Kara Cc: Jérôme Glisse Cc: Souptick Joarder Cc: Baoquan He Cc: Greg Kroah-Hartman Cc: Vlastimil Babka Cc: Wei Yang Cc: Dave Hansen Cc: David Rientjes Cc: Ingo Molnar Cc: Abdul Haleem Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2fb32d1561eb..4ace5d50a892 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2671,6 +2671,10 @@ void sparse_mem_maps_populate_node(struct page **map_map, unsigned long map_count, int nodeid); +unsigned long __init section_map_size(void); +void sparse_buffer_init(unsigned long size, int nid); +void sparse_buffer_fini(void); +void *sparse_buffer_alloc(unsigned long size); struct page *sparse_mem_map_populate(unsigned long pnum, int nid, struct vmem_altmap *altmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); -- cgit v1.2.3 From afda57bc13410459fc957e93341ade7bebca36e2 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 17 Aug 2018 15:49:30 -0700 Subject: mm/sparse: move buffer init/fini to the common place MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that both variants of sparse memory use the same buffers to populate memory map, we can move sparse_buffer_init()/sparse_buffer_fini() to the common place. Link: http://lkml.kernel.org/r/20180712203730.8703-4-pasha.tatashin@oracle.com Signed-off-by: Pavel Tatashin Tested-by: Michael Ellerman [powerpc] Tested-by: Oscar Salvador Reviewed-by: Andrew Morton Cc: Pasha Tatashin Cc: Abdul Haleem Cc: Baoquan He Cc: Daniel Jordan Cc: Dan Williams Cc: Dave Hansen Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Jan Kara Cc: Jérôme Glisse Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Souptick Joarder Cc: Steven Sistare Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4ace5d50a892..48040510df05 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2671,9 +2671,6 @@ void sparse_mem_maps_populate_node(struct page **map_map, unsigned long map_count, int nodeid); -unsigned long __init section_map_size(void); -void sparse_buffer_init(unsigned long size, int nid); -void sparse_buffer_fini(void); void *sparse_buffer_alloc(unsigned long size); struct page *sparse_mem_map_populate(unsigned long pnum, int nid, struct vmem_altmap *altmap); -- cgit v1.2.3 From 2a3cb8baef71e4dad4a6ec17f5f0db9e05f46a01 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 17 Aug 2018 15:49:37 -0700 Subject: mm/sparse: delete old sparse_init and enable new one MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename new_sparse_init() to sparse_init() which enables it. Delete old sparse_init() and all the code that became obsolete with. [pasha.tatashin@oracle.com: remove unused sparse_mem_maps_populate_node()] Link: http://lkml.kernel.org/r/20180716174447.14529-6-pasha.tatashin@oracle.com Link: http://lkml.kernel.org/r/20180712203730.8703-6-pasha.tatashin@oracle.com Signed-off-by: Pavel Tatashin Tested-by: Michael Ellerman [powerpc] Tested-by: Oscar Salvador Reviewed-by: Oscar Salvador Cc: Pasha Tatashin Cc: Abdul Haleem Cc: Baoquan He Cc: Daniel Jordan Cc: Dan Williams Cc: Dave Hansen Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Jan Kara Cc: Jérôme Glisse Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Souptick Joarder Cc: Steven Sistare Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 48040510df05..a3cae495f9ce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2665,12 +2665,6 @@ extern int randomize_va_space; const char * arch_vma_name(struct vm_area_struct *vma); void print_vma_addr(char *prefix, unsigned long rip); -void sparse_mem_maps_populate_node(struct page **map_map, - unsigned long pnum_begin, - unsigned long pnum_end, - unsigned long map_count, - int nodeid); - void *sparse_buffer_alloc(unsigned long size); struct page *sparse_mem_map_populate(unsigned long pnum, int nid, struct vmem_altmap *altmap); -- cgit v1.2.3 From 6b51e88199ca4f75ff647eff28efd30bfcb08dc4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 17 Aug 2018 15:49:55 -0700 Subject: mm/list_lru: introduce list_lru_shrink_walk_irq() Provide list_lru_shrink_walk_irq() and let it behave like list_lru_walk_one() except that it locks the spinlock with spin_lock_irq(). This is used by scan_shadow_nodes() because its lock nests within the i_pages lock which is acquired with IRQ. This change allows to use proper locking promitives instead hand crafted lock_irq_disable() plus spin_lock(). There is no EXPORT_SYMBOL provided because the current user is in-kernel only. Add list_lru_shrink_walk_irq() which acquires the spinlock with the proper locking primitives. Link: http://lkml.kernel.org/r/20180716111921.5365-5-bigeasy@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Vladimir Davydov Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index d9c16f2f2f00..aa5efd9351eb 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -166,6 +166,23 @@ unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); +/** + * list_lru_walk_one_irq: walk a list_lru, isolating and disposing freeable items. + * @lru: the lru pointer. + * @nid: the node id to scan from. + * @memcg: the cgroup to scan from. + * @isolate: callback function that is resposible for deciding what to do with + * the item currently being scanned + * @cb_arg: opaque type that will be passed to @isolate + * @nr_to_walk: how many items to scan. + * + * Same as @list_lru_walk_one except that the spinlock is acquired with + * spin_lock_irq(). + */ +unsigned long list_lru_walk_one_irq(struct list_lru *lru, + int nid, struct mem_cgroup *memcg, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk); unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); @@ -178,6 +195,14 @@ list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc, &sc->nr_to_scan); } +static inline unsigned long +list_lru_shrink_walk_irq(struct list_lru *lru, struct shrink_control *sc, + list_lru_walk_cb isolate, void *cb_arg) +{ + return list_lru_walk_one_irq(lru, sc->nid, sc->memcg, isolate, cb_arg, + &sc->nr_to_scan); +} + static inline unsigned long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, void *cb_arg, unsigned long nr_to_walk) -- cgit v1.2.3 From ddbf369c0a33924f76d092985bd20d9310f43d7f Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Fri, 17 Aug 2018 15:49:58 -0700 Subject: mm, vmacache: hash addresses based on pmd When perf profiling a wide variety of different workloads, it was found that vmacache_find() had higher than expected cost: up to 0.08% of cpu utilization in some cases. This was found to rival other core VM functions such as alloc_pages_vma() with thp enabled and default mempolicy, and the conditionals in __get_vma_policy(). VMACACHE_HASH() determines which of the four per-task_struct slots a vma is cached for a particular address. This currently depends on the pfn, so pfn 5212 occupies a different vmacache slot than its neighboring pfn 5213. vmacache_find() iterates through all four of current's vmacache slots when looking up an address. Hashing based on pfn, an address has ~1/VMACACHE_SIZE chance of being cached in the first vmacache slot, or about 25%, *if* the vma is cached. This patch hashes an address by its pmd instead of pte to optimize for workloads with good spatial locality. This results in a higher probability of vmas being cached in the first slot that is checked: normally ~70% on the same workloads instead of 25%. [rientjes@google.com: various updates] Link: http://lkml.kernel.org/r/alpine.DEB.2.21.1807231532290.109445@chino.kir.corp.google.com Link: http://lkml.kernel.org/r/alpine.DEB.2.21.1807091749150.114630@chino.kir.corp.google.com Signed-off-by: David Rientjes Reviewed-by: Andrew Morton Cc: Davidlohr Bueso Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmacache.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h index a5b3aa8d281f..3e9a963edd6a 100644 --- a/include/linux/vmacache.h +++ b/include/linux/vmacache.h @@ -5,12 +5,6 @@ #include #include -/* - * Hash based on the page number. Provides a good hit rate for - * workloads with good locality and those with random accesses as well. - */ -#define VMACACHE_HASH(addr) ((addr >> PAGE_SHIFT) & VMACACHE_MASK) - static inline void vmacache_flush(struct task_struct *tsk) { memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); -- cgit v1.2.3 From 771c035372a036f83353eef46dbb829780330234 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 18 Aug 2018 12:19:56 -0700 Subject: deprecate the '__deprecated' attribute warnings entirely and for good We haven't had lots of deprecation warnings lately, but the rdma use of it made them flare up again. They are not useful. They annoy everybody, and nobody ever does anything about them, because it's always "somebody elses problem". And when people start thinking that warnings are normal, they stop looking at them, and the real warnings that mean something go unnoticed. If you want to get rid of a function, just get rid of it. Convert every user to the new world order. And if you can't do that, then don't annoy everybody else with your marking that says "I couldn't be bothered to fix this, so I'll just spam everybody elses build logs with warnings about my laziness". Make a kernelnewbies wiki page about things that could be cleaned up, write a blog post about it, or talk to people on the mailing lists. But don't add warnings to the kernel build about cleanup that you think should happen but you aren't doing yourself. Don't. Just don't. Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 1 - include/linux/compiler_types.h | 21 ++------------------- 2 files changed, 2 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 573f5a7d42d4..3e70b7d4e9ed 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -103,7 +103,6 @@ #define __always_inline inline __attribute__((always_inline)) #define noinline __attribute__((noinline)) -#define __deprecated __attribute__((deprecated)) #define __packed __attribute__((packed)) #define __weak __attribute__((weak)) #define __alias(symbol) __attribute__((alias(#symbol))) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index a8ba6b04152c..fbf337933fd8 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -111,21 +111,10 @@ struct ftrace_likely_data { #endif /* __ASSEMBLY__ */ #ifdef __KERNEL__ -/* - * Allow us to mark functions as 'deprecated' and have gcc emit a nice - * warning for each use, in hopes of speeding the functions removal. - * Usage is: - * int __deprecated foo(void) - */ -#ifndef __deprecated -# define __deprecated /* unimplemented */ -#endif -#ifdef MODULE -#define __deprecated_for_modules __deprecated -#else +/* Don't. Just don't. */ +#define __deprecated #define __deprecated_for_modules -#endif #ifndef __must_check #define __must_check @@ -135,12 +124,6 @@ struct ftrace_likely_data { #undef __must_check #define __must_check #endif -#ifndef CONFIG_ENABLE_WARN_DEPRECATED -#undef __deprecated -#undef __deprecated_for_modules -#define __deprecated -#define __deprecated_for_modules -#endif #ifndef __malloc #define __malloc -- cgit v1.2.3 From 284ce4011ba60d6c487b668eea729b6294930806 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 13 Jul 2018 21:50:32 -0700 Subject: x86/memory_failure: Introduce {set, clear}_mce_nospec() Currently memory_failure() returns zero if the error was handled. On that result mce_unmap_kpfn() is called to zap the page out of the kernel linear mapping to prevent speculative fetches of potentially poisoned memory. However, in the case of dax mapped devmap pages the page may be in active permanent use by the device driver, so it cannot be unmapped from the kernel. Instead of marking the page not present, marking the page UC should be sufficient for preventing poison from being pre-fetched into the cache. Convert mce_unmap_pfn() to set_mce_nospec() remapping the page as UC, to hide it from speculative accesses. Given that that persistent memory errors can be cleared by the driver, include a facility to restore the page to cacheable operation, clear_mce_nospec(). Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Borislav Petkov Cc: Cc: Acked-by: Tony Luck Signed-off-by: Dan Williams Acked-by: Ingo Molnar Signed-off-by: Dave Jiang --- include/linux/set_memory.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index da5178216da5..2a986d282a97 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -17,6 +17,20 @@ static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif +#ifndef set_mce_nospec +static inline int set_mce_nospec(unsigned long pfn) +{ + return 0; +} +#endif + +#ifndef clear_mce_nospec +static inline int clear_mce_nospec(unsigned long pfn) +{ + return 0; +} +#endif + #ifndef CONFIG_ARCH_HAS_MEM_ENCRYPT static inline int set_memory_encrypted(unsigned long addr, int numpages) { -- cgit v1.2.3 From cafa0010cd51fb711fdcb50fc55f394c5f167a0a Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 20 Aug 2018 13:15:26 -0700 Subject: Raise the minimum required gcc version to 4.6 Various architectures fail to build properly with older versions of the gcc compiler. An example from Guenter Roeck in thread [1]: > > In file included from ./include/linux/mm.h:17:0, > from ./include/linux/pid_namespace.h:7, > from ./include/linux/ptrace.h:10, > from arch/openrisc/kernel/asm-offsets.c:32: > ./include/linux/mm_types.h:497:16: error: flexible array member in otherwise empty struct > > This is just an example with gcc 4.5.1 for or32. I have seen the problem > with gcc 4.4 (for unicore32) as well. So update the minimum required version of gcc to 4.6. [1] https://lore.kernel.org/lkml/20180814170904.GA12768@roeck-us.net/ Miscellanea: - Update Documentation/process/changes.rst - Remove and consolidate version test blocks in compiler-gcc.h for versions lower than 4.6 Signed-off-by: Joe Perches Reviewed-by: Kees Cook Reviewed-by: Nick Desaulniers Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 86 ++++++++++---------------------------------- 1 file changed, 18 insertions(+), 68 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 3e70b7d4e9ed..250b9b7cfd60 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -10,6 +10,10 @@ + __GNUC_MINOR__ * 100 \ + __GNUC_PATCHLEVEL__) +#if GCC_VERSION < 40600 +# error Sorry, your compiler is too old - please upgrade it. +#endif + /* Optimization barrier */ /* The "volatile" is due to gcc bugs */ @@ -58,6 +62,12 @@ #define OPTIMIZER_HIDE_VAR(var) \ __asm__ ("" : "=r" (var) : "0" (var)) +/* + * A trick to suppress uninitialized variable warning without generating any + * code + */ +#define uninitialized_var(x) x = x + #ifdef __CHECKER__ #define __must_be_array(a) 0 #else @@ -91,7 +101,7 @@ * A lot of inline functions can cause havoc with function tracing. */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ - !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) + !defined(CONFIG_OPTIMIZE_INLINING) #define inline \ inline __attribute__((always_inline, unused)) notrace __gnu_inline #else @@ -147,47 +157,13 @@ #define __always_unused __attribute__((unused)) #define __mode(x) __attribute__((mode(x))) -/* gcc version specific checks */ - -#if GCC_VERSION < 30200 -# error Sorry, your compiler is too old - please upgrade it. -#endif - -#if GCC_VERSION < 30300 -# define __used __attribute__((__unused__)) -#else -# define __used __attribute__((__used__)) -#endif - -#ifdef CONFIG_GCOV_KERNEL -# if GCC_VERSION < 30400 -# error "GCOV profiling support for gcc versions below 3.4 not included" -# endif /* __GNUC_MINOR__ */ -#endif /* CONFIG_GCOV_KERNEL */ - -#if GCC_VERSION >= 30400 #define __must_check __attribute__((warn_unused_result)) #define __malloc __attribute__((__malloc__)) -#endif - -#if GCC_VERSION >= 40000 - -/* GCC 4.1.[01] miscompiles __weak */ -#ifdef __KERNEL__ -# if GCC_VERSION >= 40100 && GCC_VERSION <= 40101 -# error Your version of gcc miscompiles the __weak directive -# endif -#endif #define __used __attribute__((__used__)) #define __compiler_offsetof(a, b) \ __builtin_offsetof(a, b) -#if GCC_VERSION >= 40100 -# define __compiletime_object_size(obj) __builtin_object_size(obj, 0) -#endif - -#if GCC_VERSION >= 40300 /* Mark functions as cold. gcc will assume any path leading to a call * to them will be unlikely. This means a lot of manual unlikely()s * are unnecessary now for any paths leading to the usual suspects @@ -206,24 +182,19 @@ #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -#ifndef __CHECKER__ -# define __compiletime_warning(message) __attribute__((warning(message))) -# define __compiletime_error(message) __attribute__((error(message))) -#endif /* __CHECKER__ */ -#endif /* GCC_VERSION >= 40300 */ - -#if GCC_VERSION >= 40400 #define __optimize(level) __attribute__((__optimize__(level))) #define __nostackprotector __optimize("no-stack-protector") -#endif /* GCC_VERSION >= 40400 */ -#if GCC_VERSION >= 40500 +#define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #ifndef __CHECKER__ +#define __compiletime_warning(message) __attribute__((warning(message))) +#define __compiletime_error(message) __attribute__((error(message))) + #ifdef LATENT_ENTROPY_PLUGIN #define __latent_entropy __attribute__((latent_entropy)) #endif -#endif +#endif /* __CHECKER__ */ /* * calling noreturn functions, __builtin_unreachable() and __builtin_trap() @@ -261,10 +232,6 @@ #define randomized_struct_fields_end } __randomize_layout; #endif -#endif /* GCC_VERSION >= 40500 */ - -#if GCC_VERSION >= 40600 - /* * When used with Link Time Optimization, gcc can optimize away C functions or * variables which are referenced only from assembly code. __visible tells the @@ -273,8 +240,7 @@ */ #define __visible __attribute__((externally_visible)) -#endif /* GCC_VERSION >= 40600 */ - +/* gcc version specific checks */ #if GCC_VERSION >= 40900 && !defined(__CHECKER__) /* @@ -308,10 +274,8 @@ * folding in __builtin_bswap*() (yet), so don't set these for it. */ #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__) -#if GCC_VERSION >= 40400 #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ -#endif #if GCC_VERSION >= 40800 #define __HAVE_BUILTIN_BSWAP16__ #endif @@ -340,10 +304,9 @@ * https://gcc.gnu.org/onlinedocs/gcc/Designated-Inits.html */ #define __designated_init __attribute__((designated_init)) +#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif -#endif /* gcc version >= 40000 specific checks */ - #if !defined(__noclone) #define __noclone /* not needed */ #endif @@ -352,16 +315,6 @@ #define __no_sanitize_address #endif -/* - * A trick to suppress uninitialized variable warning without generating any - * code - */ -#define uninitialized_var(x) x = x - -#if GCC_VERSION >= 50100 -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif - /* * Turn individual warnings and errors on and off locally, depending * on version. @@ -374,12 +327,9 @@ #define __diag_GCC_warn warning #define __diag_GCC_error error -/* Compilers before gcc-4.6 do not understand "#pragma GCC diagnostic push" */ -#if GCC_VERSION >= 40600 #define __diag_str1(s) #s #define __diag_str(s) __diag_str1(s) #define __diag(s) _Pragma(__diag_str(GCC diagnostic s)) -#endif #if GCC_VERSION >= 80000 #define __diag_GCC_8(s) __diag(s) -- cgit v1.2.3 From 04f264d3a8b0eb25d378127bd78c3c9a0261c828 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Mon, 20 Aug 2018 15:36:17 -0700 Subject: compiler.h: Allow arch-specific asm/compiler.h We have a need to override the definition of barrier_before_unreachable() for MIPS, which means we either need to add architecture-specific code into linux/compiler-gcc.h or we need to allow the architecture to provide a header that can define the macro before the generic definition. The latter seems like the better approach. A straightforward approach to the per-arch header is to make use of asm-generic to provide a default empty header & adjust architectures which don't need anything specific to make use of that by adding the header to generic-y. Unfortunately this doesn't work so well due to commit 28128c61e08e ("kconfig.h: Include compiler types to avoid missed struct attributes") which caused linux/compiler_types.h to be included in the compilation of every C file via the -include linux/kconfig.h flag in c_flags. Because the -include flag is present for all C files we compile, we need the architecture-provided header to be present before any C files are compiled. If any C files can be compiled prior to the asm-generic header wrappers being generated then we hit a build failure due to missing header. Such cases do exist - one pointed out by the kbuild test robot is the compilation of arch/ia64/kernel/nr-irqs.c, which occurs as part of the archprepare target [1]. This leaves us with a few options: 1) Use generic-y & fix any build failures we find by enforcing ordering such that the asm-generic target occurs before any C compilation, such that linux/compiler_types.h can always include the generated asm-generic wrapper which in turn includes the empty asm-generic header. This would rely on us finding all the problematic cases - I don't know for sure that the ia64 issue is the only one. 2) Add an actual empty header to each architecture, so that we don't need the generated asm-generic wrapper. This seems messy. 3) Give up & add #ifdef CONFIG_MIPS or similar to linux/compiler_types.h. This seems messy too. 4) Include the arch header only when it's actually needed, removing the need for the asm-generic wrapper for all other architectures. This patch allows us to use approach 4, by including an asm/compiler.h header from linux/compiler_types.h after the inclusion of the compiler-specific linux/compiler-*.h header(s). We do this conditionally, only when CONFIG_HAVE_ARCH_COMPILER_H is selected, in order to avoid the need for asm-generic wrappers & the associated build ordering issue described above. The asm/compiler.h header is included after the generic linux/compiler-*.h header(s) for consistency with the way linux/compiler-intel.h & linux/compiler-clang.h are included after the linux/compiler-gcc.h header that they override. [1] https://lists.01.org/pipermail/kbuild-all/2018-August/051175.html Signed-off-by: Paul Burton Reviewed-by: Masahiro Yamada Patchwork: https://patchwork.linux-mips.org/patch/20269/ Cc: Arnd Bergmann Cc: James Hogan Cc: Masahiro Yamada Cc: Ralf Baechle Cc: linux-arch@vger.kernel.org Cc: linux-kbuild@vger.kernel.org Cc: linux-mips@linux-mips.org --- include/linux/compiler_types.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 6b79a9bba9a7..4be464a07612 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -78,6 +78,18 @@ extern void __chk_io_ptr(const volatile void __iomem *); #include #endif +/* + * Some architectures need to provide custom definitions of macros provided + * by linux/compiler-*.h, and can do so using asm/compiler.h. We include that + * conditionally rather than using an asm-generic wrapper in order to avoid + * build failures if any C compilation, which will include this file via an + * -include argument in c_flags, occurs prior to the asm-generic wrappers being + * generated. + */ +#ifdef CONFIG_HAVE_ARCH_COMPILER_H +#include +#endif + /* * Generic compiler-dependent macros required for kernel * build go below this comment. Actual compiler/compiler version -- cgit v1.2.3 From 5ade60dda43c8906d4554374226c2eb11cc2ffba Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 20 Mar 2018 17:07:11 -0400 Subject: ida: Add new API Add ida_alloc(), ida_alloc_min(), ida_alloc_max(), ida_alloc_range() and ida_free(). The ida_alloc_max() and ida_alloc_range() functions differ from ida_simple_get() in that they take an inclusive 'max' parameter instead of an exclusive 'end' parameter. Callers are about evenly split whether they'd like inclusive or exclusive parameters and 'max' is easier to document than 'end'. Change the IDA allocation to first attempt to allocate a bit using existing memory, and only allocate memory afterwards. Also change the behaviour of 'min' > INT_MAX from being a BUG() to returning -ENOSPC. Leave compatibility wrappers in place for ida_simple_get() and ida_simple_remove() to avoid changing all callers. Signed-off-by: Matthew Wilcox --- include/linux/idr.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 56 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index e856f4e0ab35..cd339da0b1aa 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -230,15 +230,68 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id); void ida_remove(struct ida *ida, int id); void ida_destroy(struct ida *ida); -int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end, - gfp_t gfp_mask); -void ida_simple_remove(struct ida *ida, unsigned int id); +int ida_alloc_range(struct ida *, unsigned int min, unsigned int max, gfp_t); +void ida_free(struct ida *, unsigned int id); + +/** + * ida_alloc() - Allocate an unused ID. + * @ida: IDA handle. + * @gfp: Memory allocation flags. + * + * Allocate an ID between 0 and %INT_MAX, inclusive. + * + * Context: Any context. + * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, + * or %-ENOSPC if there are no free IDs. + */ +static inline int ida_alloc(struct ida *ida, gfp_t gfp) +{ + return ida_alloc_range(ida, 0, ~0, gfp); +} + +/** + * ida_alloc_min() - Allocate an unused ID. + * @ida: IDA handle. + * @min: Lowest ID to allocate. + * @gfp: Memory allocation flags. + * + * Allocate an ID between @min and %INT_MAX, inclusive. + * + * Context: Any context. + * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, + * or %-ENOSPC if there are no free IDs. + */ +static inline int ida_alloc_min(struct ida *ida, unsigned int min, gfp_t gfp) +{ + return ida_alloc_range(ida, min, ~0, gfp); +} + +/** + * ida_alloc_max() - Allocate an unused ID. + * @ida: IDA handle. + * @max: Highest ID to allocate. + * @gfp: Memory allocation flags. + * + * Allocate an ID between 0 and @max, inclusive. + * + * Context: Any context. + * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, + * or %-ENOSPC if there are no free IDs. + */ +static inline int ida_alloc_max(struct ida *ida, unsigned int max, gfp_t gfp) +{ + return ida_alloc_range(ida, 0, max, gfp); +} static inline void ida_init(struct ida *ida) { INIT_RADIX_TREE(&ida->ida_rt, IDR_RT_MARKER | GFP_NOWAIT); } +#define ida_simple_get(ida, start, end, gfp) \ + ida_alloc_range(ida, start, (end) - 1, gfp) +#define ida_simple_remove(ida, id) ida_free(ida, id) + /** * ida_get_new - allocate new ID * @ida: idr handle -- cgit v1.2.3 From b03f8e43c9261878bf29d8cc1c3ba458cc98287e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 18 Jun 2018 19:02:48 -0400 Subject: ida: Remove old API Delete ida_pre_get(), ida_get_new(), ida_get_new_above() and ida_remove() from the public API. Some of these functions still exist as internal helpers, but they should not be called by consumers. Signed-off-by: Matthew Wilcox --- include/linux/idr.h | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index cd339da0b1aa..2e1db0e36486 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -225,13 +225,9 @@ struct ida { } #define DEFINE_IDA(name) struct ida name = IDA_INIT(name) -int ida_pre_get(struct ida *ida, gfp_t gfp_mask); -int ida_get_new_above(struct ida *ida, int starting_id, int *p_id); -void ida_remove(struct ida *ida, int id); -void ida_destroy(struct ida *ida); - int ida_alloc_range(struct ida *, unsigned int min, unsigned int max, gfp_t); void ida_free(struct ida *, unsigned int id); +void ida_destroy(struct ida *ida); /** * ida_alloc() - Allocate an unused ID. @@ -292,20 +288,11 @@ static inline void ida_init(struct ida *ida) ida_alloc_range(ida, start, (end) - 1, gfp) #define ida_simple_remove(ida, id) ida_free(ida, id) -/** - * ida_get_new - allocate new ID - * @ida: idr handle - * @p_id: pointer to the allocated handle - * - * Simple wrapper around ida_get_new_above() w/ @starting_id of zero. - */ -static inline int ida_get_new(struct ida *ida, int *p_id) -{ - return ida_get_new_above(ida, 0, p_id); -} - static inline bool ida_is_empty(const struct ida *ida) { return radix_tree_empty(&ida->ida_rt); } + +/* in lib/radix-tree.c */ +int ida_pre_get(struct ida *ida, gfp_t gfp_mask); #endif /* __IDR_H__ */ -- cgit v1.2.3 From fd991a23c8f6ef30692f77409602ccf3614353b2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 21 Aug 2018 22:33:00 +0200 Subject: y2038: Provide aliases for compat helpers As part of the system call rework for 64-bit time_t, we are restructuring the way that compat syscalls deal with 32-bit time_t, reusing the implementation for 32-bit architectures. Christoph Hellwig suggested a rename of the associated types and interfaces to avoid the confusing usage of the 'compat' prefix for 32-bit architectures. To prepare for doing that in linux-4.20, add a set of macros that allows to convert subsystems separately to the new names and avoids some of the nastier merge conflicts. Signed-off-by: Arnd Bergmann Signed-off-by: Thomas Gleixner Acked-by: Christoph Hellwig Cc: y2038@lists.linaro.org Cc: John Stultz Cc: Deepa Dinamani Link: https://lkml.kernel.org/r/20180821203329.2089473-1-arnd@arndb.de --- include/linux/time32.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time32.h b/include/linux/time32.h index 0b14f936100a..d1ae43c13e25 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -207,4 +207,19 @@ static inline s64 timeval_to_ns(const struct timeval *tv) extern struct timeval ns_to_timeval(const s64 nsec); extern struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec); +/* + * New aliases for compat time functions. These will be used to replace + * the compat code so it can be shared between 32-bit and 64-bit builds + * both of which provide compatibility with old 32-bit tasks. + */ +#define old_time32_t compat_time_t +#define old_timeval32 compat_timeval +#define old_timespec32 compat_timespec +#define old_itimerspec32 compat_itimerspec +#define ns_to_old_timeval32 ns_to_compat_timeval +#define get_old_itimerspec32 get_compat_itimerspec64 +#define put_old_itimerspec32 put_compat_itimerspec64 +#define get_old_timespec32 compat_get_timespec64 +#define put_old_timespec32 compat_put_timespec64 + #endif -- cgit v1.2.3 From c4df32c80d04987023844c1fb13734a872c8f2e2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 19 Aug 2018 07:34:47 +0900 Subject: export.h: remove VMLINUX_SYMBOL() and VMLINUX_SYMBOL_STR() With the special case handling for Blackfin and Metag was removed by commit 94e58e0ac312 ("export.h: remove code for prefixing symbols with underscore"), VMLINUX_SYMBOL() is no-op. Replace the remaining usages, then remove the definition of VMLINUX_SYMBOL() and VMLINUX_SYMBOL_STR(). Signed-off-by: Masahiro Yamada --- include/linux/export.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index b768d6dd3c90..c363bde21bbe 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -10,13 +10,6 @@ * hackers place grumpy comments in header files. */ -#define __VMLINUX_SYMBOL(x) x -#define __VMLINUX_SYMBOL_STR(x) #x - -/* Indirect, so macros are expanded before pasting. */ -#define VMLINUX_SYMBOL(x) __VMLINUX_SYMBOL(x) -#define VMLINUX_SYMBOL_STR(x) __VMLINUX_SYMBOL_STR(x) - #ifndef __ASSEMBLY__ struct kernel_symbol { -- cgit v1.2.3 From 16af2d65842d343c2f95733c3993a0b5baab08f9 Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Wed, 22 Aug 2018 21:13:01 +0900 Subject: ata: add an extra argument to ahci_platform_get_resources() Add an extra argument to ahci_platform_get_resources(), that is for the bitmap representing the resource to get in this function. Currently there is no resources to be defined, so all the callers set '0' to the argument. Suggested-by: Hans de Goede Cc: Thierry Reding Cc: Matthias Brugger Cc: Patrice Chotard Cc: Maxime Ripard Signed-off-by: Kunihiko Hayashi Reviewed-by: Hans de Goede Signed-off-by: Tejun Heo --- include/linux/ahci_platform.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 1b0a17b22cd3..6490be1f8a16 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -30,7 +30,7 @@ void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv); int ahci_platform_enable_resources(struct ahci_host_priv *hpriv); void ahci_platform_disable_resources(struct ahci_host_priv *hpriv); struct ahci_host_priv *ahci_platform_get_resources( - struct platform_device *pdev); + struct platform_device *pdev, unsigned int flags); int ahci_platform_init_host(struct platform_device *pdev, struct ahci_host_priv *hpriv, const struct ata_port_info *pi_template, -- cgit v1.2.3 From 9d2ab99573970838108add835442a03e23f8577b Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Wed, 22 Aug 2018 21:13:02 +0900 Subject: ata: libahci_platform: add reset control support Add support to get and control a list of resets for the device as optional and shared. These resets must be kept de-asserted until the device is enabled. This is specified as shared because some SoCs like UniPhier series have common reset controls with all ahci controller instances. However, according to Thierry's view, https://www.spinics.net/lists/linux-ide/msg55357.html some hardware-specific drivers already use their own resets, and the common reset make a path to occur double controls of resets. The ahci_platform_get_resources() can get and control the reset only when the second argument includes AHCI_PLATFORM_GET_RESETS bit. Suggested-by: Hans de Goede Cc: Thierry Reding Signed-off-by: Kunihiko Hayashi Reviewed-by: Hans de Goede Signed-off-by: Tejun Heo --- include/linux/ahci_platform.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 6490be1f8a16..eaedca5fe6fc 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -43,4 +43,6 @@ int ahci_platform_resume_host(struct device *dev); int ahci_platform_suspend(struct device *dev); int ahci_platform_resume(struct device *dev); +#define AHCI_PLATFORM_GET_RESETS 0x01 + #endif /* _AHCI_PLATFORM_H */ -- cgit v1.2.3 From 64d9d13828c6c8e188bba63794eee923df3d69a9 Mon Sep 17 00:00:00 2001 From: Jeremy Cline Date: Tue, 31 Jul 2018 01:37:30 +0000 Subject: fs/quota: Replace XQM_MAXQUOTAS usage with MAXQUOTAS XQM_MAXQUOTAS and MAXQUOTAS are, it appears, equivalent. Replace all usage of XQM_MAXQUOTAS and remove it along with the unused XQM_*QUOTA definitions. Signed-off-by: Jeremy Cline Signed-off-by: Jan Kara --- include/linux/quota.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index ca9772c8e48b..f32dd270b8e3 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -408,13 +408,7 @@ struct qc_type_state { struct qc_state { unsigned int s_incoredqs; /* Number of dquots in core */ - /* - * Per quota type information. The array should really have - * max(MAXQUOTAS, XQM_MAXQUOTAS) entries. BUILD_BUG_ON in - * quota_getinfo() makes sure XQM_MAXQUOTAS is large enough. Once VFS - * supports project quotas, this can be changed to MAXQUOTAS - */ - struct qc_type_state s_state[XQM_MAXQUOTAS]; + struct qc_type_state s_state[MAXQUOTAS]; /* Per quota type information */ }; /* Structure for communicating via ->set_info */ -- cgit v1.2.3 From 92be775a3db343889ab159c44d55315c5ee0be4e Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Tue, 21 Aug 2018 21:51:53 -0700 Subject: mm: struct shrink_control: keep int fields together Patch series "Reorderings in struct shrinker and struct shrink_control". These structures are intensively used during reclaim and, displace other data in cache, so there is no a reason they have int fields not grouped together. This patch (of 2): gfp_t is of unsigned type, so let's move nid to keep them together. Link: http://lkml.kernel.org/r/153199747930.21131.861043607301997810.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: Tetsuo Handa Cc: Chris Wilson Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shrinker.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index b154fd2b084c..d58aaaed34a4 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -12,6 +12,9 @@ struct shrink_control { gfp_t gfp_mask; + /* current node being shrunk (for NUMA aware shrinkers) */ + int nid; + /* * How many objects scan_objects should scan and try to reclaim. * This is reset before every call, so it is safe for callees @@ -26,9 +29,6 @@ struct shrink_control { */ unsigned long nr_scanned; - /* current node being shrunk (for NUMA aware shrinkers) */ - int nid; - /* current memcg being shrunk (for memcg aware shrinkers) */ struct mem_cgroup *memcg; }; -- cgit v1.2.3 From e50ef89b0f58a2cb0e7d496a97b851e0dced62a6 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Tue, 21 Aug 2018 21:51:57 -0700 Subject: mm: struct shrinker: make flags of unsigned type Currently, there are two flags only, so unsigned is more then enough. Also, move int seeks to keep these fields together. Link: http://lkml.kernel.org/r/153199748720.21131.6476256940113102483.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: Tetsuo Handa Cc: Chris Wilson Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shrinker.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index d58aaaed34a4..9443cafd1969 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -63,9 +63,9 @@ struct shrinker { unsigned long (*scan_objects)(struct shrinker *, struct shrink_control *sc); - int seeks; /* seeks to recreate an obj */ long batch; /* reclaim batch size, 0 = default */ - unsigned long flags; + int seeks; /* seeks to recreate an obj */ + unsigned flags; /* These are for internal use */ struct list_head list; -- cgit v1.2.3 From 5d5e8f19544a35ae1609bd96ae6b28c9fcd1baf6 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 21 Aug 2018 21:52:20 -0700 Subject: mm, swap, get_swap_pages: use entry_size instead of cluster in parameter As suggested by Matthew Wilcox, it is better to use "int entry_size" instead of "bool cluster" as parameter to specify whether to operate for huge or normal swap entries. Because this improve the flexibility to support other swap entry size. And Dave Hansen thinks that this improves code readability too. So in this patch, the "bool cluster" parameter of get_swap_pages() is replaced by "int entry_size". And nr_swap_entries() trick is used to reduce the binary size when !CONFIG_TRANSPARENT_HUGE_PAGE. text data bss dec hex filename base 24215 2028 340 26583 67d7 mm/swapfile.o head 24123 2004 340 26467 6763 mm/swapfile.o Link: http://lkml.kernel.org/r/20180720071845.17920-7-ying.huang@intel.com Signed-off-by: "Huang, Ying" Suggested-by: Matthew Wilcox Acked-by: Dave Hansen Cc: Daniel Jordan Cc: Michal Hocko Cc: Johannes Weiner Cc: Shaohua Li Cc: Hugh Dickins Cc: Minchan Kim Cc: Rik van Riel Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 1a8bd05a335e..8e2c11e692ba 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -447,7 +447,7 @@ extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(struct page *page); extern void put_swap_page(struct page *page, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); -extern int get_swap_pages(int n, bool cluster, swp_entry_t swp_entries[]); +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); -- cgit v1.2.3 From 93065ac753e4443840a057bfef4be71ec766fde9 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 21 Aug 2018 21:52:33 -0700 Subject: mm, oom: distinguish blockable mode for mmu notifiers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are several blockable mmu notifiers which might sleep in mmu_notifier_invalidate_range_start and that is a problem for the oom_reaper because it needs to guarantee a forward progress so it cannot depend on any sleepable locks. Currently we simply back off and mark an oom victim with blockable mmu notifiers as done after a short sleep. That can result in selecting a new oom victim prematurely because the previous one still hasn't torn its memory down yet. We can do much better though. Even if mmu notifiers use sleepable locks there is no reason to automatically assume those locks are held. Moreover majority of notifiers only care about a portion of the address space and there is absolutely zero reason to fail when we are unmapping an unrelated range. Many notifiers do really block and wait for HW which is harder to handle and we have to bail out though. This patch handles the low hanging fruit. __mmu_notifier_invalidate_range_start gets a blockable flag and callbacks are not allowed to sleep if the flag is set to false. This is achieved by using trylock instead of the sleepable lock for most callbacks and continue as long as we do not block down the call chain. I think we can improve that even further because there is a common pattern to do a range lookup first and then do something about that. The first part can be done without a sleeping lock in most cases AFAICS. The oom_reaper end then simply retries if there is at least one notifier which couldn't make any progress in !blockable mode. A retry loop is already implemented to wait for the mmap_sem and this is basically the same thing. The simplest way for driver developers to test this code path is to wrap userspace code which uses these notifiers into a memcg and set the hard limit to hit the oom. This can be done e.g. after the test faults in all the mmu notifier managed memory and set the hard limit to something really small. Then we are looking for a proper process tear down. [akpm@linux-foundation.org: coding style fixes] [akpm@linux-foundation.org: minor code simplification] Link: http://lkml.kernel.org/r/20180716115058.5559-1-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Christian König # AMD notifiers Acked-by: Leon Romanovsky # mlx and umem_odp Reported-by: David Rientjes Cc: "David (ChunMing) Zhou" Cc: Paolo Bonzini Cc: Alex Deucher Cc: David Airlie Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Rodrigo Vivi Cc: Doug Ledford Cc: Jason Gunthorpe Cc: Mike Marciniszyn Cc: Dennis Dalessandro Cc: Sudeep Dutt Cc: Ashutosh Dixit Cc: Dimitri Sivanich Cc: Boris Ostrovsky Cc: Juergen Gross Cc: "Jérôme Glisse" Cc: Andrea Arcangeli Cc: Felix Kuehling Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kvm_host.h | 4 ++-- include/linux/mmu_notifier.h | 33 +++++++++++++++++++++++++-------- include/linux/oom.h | 2 +- 3 files changed, 28 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7c7362dd2faa..0205aee44ded 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1289,8 +1289,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, } #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */ -void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end); +int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end, bool blockable); #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 392e6af82701..133ba78820ee 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -151,13 +151,15 @@ struct mmu_notifier_ops { * address space but may still be referenced by sptes until * the last refcount is dropped. * - * If both of these callbacks cannot block, and invalidate_range - * cannot block, mmu_notifier_ops.flags should have - * MMU_INVALIDATE_DOES_NOT_BLOCK set. + * If blockable argument is set to false then the callback cannot + * sleep and has to return with -EAGAIN. 0 should be returned + * otherwise. + * */ - void (*invalidate_range_start)(struct mmu_notifier *mn, + int (*invalidate_range_start)(struct mmu_notifier *mn, struct mm_struct *mm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, + bool blockable); void (*invalidate_range_end)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end); @@ -229,8 +231,9 @@ extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte); -extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, - unsigned long start, unsigned long end); +extern int __mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end, + bool blockable); extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, unsigned long start, unsigned long end, bool only_end); @@ -281,7 +284,15 @@ static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) - __mmu_notifier_invalidate_range_start(mm, start, end); + __mmu_notifier_invalidate_range_start(mm, start, end, true); +} + +static inline int mmu_notifier_invalidate_range_start_nonblock(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + if (mm_has_notifiers(mm)) + return __mmu_notifier_invalidate_range_start(mm, start, end, false); + return 0; } static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, @@ -461,6 +472,12 @@ static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, { } +static inline int mmu_notifier_invalidate_range_start_nonblock(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + return 0; +} + static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, unsigned long start, unsigned long end) { diff --git a/include/linux/oom.h b/include/linux/oom.h index 6adac113e96d..92f70e4c6252 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -95,7 +95,7 @@ static inline int check_stable_address_space(struct mm_struct *mm) return 0; } -void __oom_reap_task_mm(struct mm_struct *mm); +bool __oom_reap_task_mm(struct mm_struct *mm); extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, -- cgit v1.2.3 From a670468f5e0b5fad4db6e4d195f15915dc2a35c1 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 21 Aug 2018 21:53:06 -0700 Subject: mm: zero out the vma in vma_init() Rather than in vm_area_alloc(). To ensure that the various oddball stack-based vmas are in a good state. Some of the callers were zeroing them out, others were not. Acked-by: Kirill A. Shutemov Cc: Russell King Cc: Dmitry Vyukov Cc: Oleg Nesterov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a3cae495f9ce..3a4b87d1a59a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -456,6 +456,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { static const struct vm_operations_struct dummy_vm_ops = {}; + memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); -- cgit v1.2.3 From 89696701ea847786f88ccc1c580fb4c3c20c4a3a Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Tue, 21 Aug 2018 21:53:24 -0700 Subject: mm: remove zone_id() and make use of zone_idx() in is_dev_zone() is_dev_zone() is using zone_id() to check if the zone is ZONE_DEVICE. zone_id() looks pretty much the same as zone_idx(), and while the use of zone_idx() is quite spread in the kernel, zone_id() is only being used by is_dev_zone(). This patch removes zone_id() and makes is_dev_zone() use zone_idx() to check the zone, so we do not have two things with the same functionality around. Link: http://lkml.kernel.org/r/20180730133718.28683-1-osalvador@techadventures.net Signed-off-by: Oscar Salvador Acked-by: Michal Hocko Acked-by: Vlastimil Babka Reviewed-by: Pavel Tatashin Cc: Pasha Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 31 ++++++++++++------------------- 1 file changed, 12 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 32699b2dc52a..3d4577a3ae7e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -755,25 +755,6 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat) return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; } -static inline int zone_id(const struct zone *zone) -{ - struct pglist_data *pgdat = zone->zone_pgdat; - - return zone - pgdat->node_zones; -} - -#ifdef CONFIG_ZONE_DEVICE -static inline bool is_dev_zone(const struct zone *zone) -{ - return zone_id(zone) == ZONE_DEVICE; -} -#else -static inline bool is_dev_zone(const struct zone *zone) -{ - return false; -} -#endif - #include void build_all_zonelists(pg_data_t *pgdat); @@ -824,6 +805,18 @@ static inline int local_memory_node(int node_id) { return node_id; }; */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) +#ifdef CONFIG_ZONE_DEVICE +static inline bool is_dev_zone(const struct zone *zone) +{ + return zone_idx(zone) == ZONE_DEVICE; +} +#else +static inline bool is_dev_zone(const struct zone *zone) +{ + return false; +} +#endif + /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than -- cgit v1.2.3 From c1093b746c0576ed81c4d568d1e39cab651d37e6 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Tue, 21 Aug 2018 21:53:32 -0700 Subject: mm: access zone->node via zone_to_nid() and zone_set_nid() zone->node is configured only when CONFIG_NUMA=y, so it is a good idea to have inline functions to access this field in order to avoid ifdef's in c files. Link: http://lkml.kernel.org/r/20180730101757.28058-3-osalvador@techadventures.net Signed-off-by: Pavel Tatashin Signed-off-by: Oscar Salvador Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Aaron Lu Cc: Dan Williams Cc: David Hildenbrand Cc: Joonsoo Kim Cc: Mel Gorman Cc: Pasha Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 --------- include/linux/mmzone.h | 26 ++++++++++++++++++++------ 2 files changed, 20 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3a4b87d1a59a..a55f5389c491 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -960,15 +960,6 @@ static inline int page_zone_id(struct page *page) return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; } -static inline int zone_to_nid(struct zone *zone) -{ -#ifdef CONFIG_NUMA - return zone->node; -#else - return 0; -#endif -} - #ifdef NODE_NOT_IN_PAGE_FLAGS extern int page_to_nid(const struct page *page); #else diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3d4577a3ae7e..1e22d96734e0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -834,6 +834,25 @@ static inline bool populated_zone(struct zone *zone) return zone->present_pages; } +#ifdef CONFIG_NUMA +static inline int zone_to_nid(struct zone *zone) +{ + return zone->node; +} + +static inline void zone_set_nid(struct zone *zone, int nid) +{ + zone->node = nid; +} +#else +static inline int zone_to_nid(struct zone *zone) +{ + return 0; +} + +static inline void zone_set_nid(struct zone *zone, int nid) {} +#endif + extern int movable_zone; #ifdef CONFIG_HIGHMEM @@ -949,12 +968,7 @@ static inline int zonelist_zone_idx(struct zoneref *zoneref) static inline int zonelist_node_idx(struct zoneref *zoneref) { -#ifdef CONFIG_NUMA - /* zone_to_nid not available in this context */ - return zoneref->zone->node; -#else - return 0; -#endif /* CONFIG_NUMA */ + return zone_to_nid(zoneref->zone); } struct zoneref *__next_zones_zonelist(struct zoneref *z, -- cgit v1.2.3 From 03e85f9d5f1f8c74f127c5f7a87575d74a78d248 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Tue, 21 Aug 2018 21:53:43 -0700 Subject: mm/page_alloc: Introduce free_area_init_core_hotplug Currently, whenever a new node is created/re-used from the memhotplug path, we call free_area_init_node()->free_area_init_core(). But there is some code that we do not really need to run when we are coming from such path. free_area_init_core() performs the following actions: 1) Initializes pgdat internals, such as spinlock, waitqueues and more. 2) Account # nr_all_pages and # nr_kernel_pages. These values are used later on when creating hash tables. 3) Account number of managed_pages per zone, substracting dma_reserved and memmap pages. 4) Initializes some fields of the zone structure data 5) Calls init_currently_empty_zone to initialize all the freelists 6) Calls memmap_init to initialize all pages belonging to certain zone When called from memhotplug path, free_area_init_core() only performs actions #1 and #4. Action #2 is pointless as the zones do not have any pages since either the node was freed, or we are re-using it, eitherway all zones belonging to this node should have 0 pages. For the same reason, action #3 results always in manages_pages being 0. Action #5 and #6 are performed later on when onlining the pages: online_pages()->move_pfn_range_to_zone()->init_currently_empty_zone() online_pages()->move_pfn_range_to_zone()->memmap_init_zone() This patch does two things: First, moves the node/zone initializtion to their own function, so it allows us to create a small version of free_area_init_core, where we only perform: 1) Initialization of pgdat internals, such as spinlock, waitqueues and more 4) Initialization of some fields of the zone structure data These two functions are: pgdat_init_internals() and zone_init_internals(). The second thing this patch does, is to introduce free_area_init_core_hotplug(), the memhotplug version of free_area_init_core(): Currently, we call free_area_init_node() from the memhotplug path. In there, we set some pgdat's fields, and call calculate_node_totalpages(). calculate_node_totalpages() calculates the # of pages the node has. Since the node is either new, or we are re-using it, the zones belonging to this node should not have any pages, so there is no point to calculate this now. Actually, we re-set these values to 0 later on with the calls to: reset_node_managed_pages() reset_node_present_pages() The # of pages per node and the # of pages per zone will be calculated when onlining the pages: online_pages()->move_pfn_range()->move_pfn_range_to_zone()->resize_zone_range() online_pages()->move_pfn_range()->move_pfn_range_to_zone()->resize_pgdat_range() Also, since free_area_init_core/free_area_init_node will now only get called during early init, let us replace __paginginit with __init, so their code gets freed up. [osalvador@techadventures.net: fix section usage] Link: http://lkml.kernel.org/r/20180731101752.GA473@techadventures.net [osalvador@suse.de: v6] Link: http://lkml.kernel.org/r/20180801122348.21588-6-osalvador@techadventures.net Link: http://lkml.kernel.org/r/20180730101757.28058-5-osalvador@techadventures.net Signed-off-by: Oscar Salvador Reviewed-by: Pavel Tatashin Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Pasha Tatashin Cc: Aaron Lu Cc: Dan Williams Cc: David Hildenbrand Cc: Joonsoo Kim Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 1 + include/linux/mm.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 4e9828cda7a2..34a28227068d 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -319,6 +319,7 @@ static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) static inline void remove_memory(int nid, u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ +extern void __ref free_area_init_core_hotplug(int nid); extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); extern int add_memory(int nid, u64 start, u64 size); diff --git a/include/linux/mm.h b/include/linux/mm.h index a55f5389c491..a9e733b5fb76 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2015,7 +2015,7 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) extern void __init pagecache_init(void); extern void free_area_init(unsigned long * zones_size); -extern void free_area_init_node(int nid, unsigned long * zones_size, +extern void __init free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); extern void free_initmem(void); -- cgit v1.2.3 From 3d8b38eb81cac81395f6a823f6bf401b327268e6 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 21 Aug 2018 21:53:54 -0700 Subject: mm, oom: introduce memory.oom.group For some workloads an intervention from the OOM killer can be painful. Killing a random task can bring the workload into an inconsistent state. Historically, there are two common solutions for this problem: 1) enabling panic_on_oom, 2) using a userspace daemon to monitor OOMs and kill all outstanding processes. Both approaches have their downsides: rebooting on each OOM is an obvious waste of capacity, and handling all in userspace is tricky and requires a userspace agent, which will monitor all cgroups for OOMs. In most cases an in-kernel after-OOM cleaning-up mechanism can eliminate the necessity of enabling panic_on_oom. Also, it can simplify the cgroup management for userspace applications. This commit introduces a new knob for cgroup v2 memory controller: memory.oom.group. The knob determines whether the cgroup should be treated as an indivisible workload by the OOM killer. If set, all tasks belonging to the cgroup or to its descendants (if the memory cgroup is not a leaf cgroup) are killed together or not at all. To determine which cgroup has to be killed, we do traverse the cgroup hierarchy from the victim task's cgroup up to the OOMing cgroup (or root) and looking for the highest-level cgroup with memory.oom.group set. Tasks with the OOM protection (oom_score_adj set to -1000) are treated as an exception and are never killed. This patch doesn't change the OOM victim selection algorithm. Link: http://lkml.kernel.org/r/20180802003201.817-4-guro@fb.com Signed-off-by: Roman Gushchin Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: David Rientjes Cc: Tetsuo Handa Cc: Tejun Heo Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0e6c515fb698..652f602167df 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -225,6 +225,11 @@ struct mem_cgroup { */ bool use_hierarchy; + /* + * Should the OOM killer kill all belonging tasks, had it kill one? + */ + bool oom_group; + /* protected by memcg_oom_lock */ bool oom_lock; int under_oom; @@ -542,6 +547,9 @@ static inline bool task_in_memcg_oom(struct task_struct *p) } bool mem_cgroup_oom_synchronize(bool wait); +struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, + struct mem_cgroup *oom_domain); +void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); #ifdef CONFIG_MEMCG_SWAP extern int do_swap_account; @@ -1001,6 +1009,16 @@ static inline bool mem_cgroup_oom_synchronize(bool wait) return false; } +static inline struct mem_cgroup *mem_cgroup_get_oom_group( + struct task_struct *victim, struct mem_cgroup *oom_domain) +{ + return NULL; +} + +static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) +{ +} + static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { -- cgit v1.2.3 From 7e8a6304d5419cbf056a59de92939e5eef039c57 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 21 Aug 2018 21:53:58 -0700 Subject: /proc/meminfo: add percpu populated pages count Currently, percpu memory only exposes allocation and utilization information via debugfs. This more or less is only really useful for understanding the fragmentation and allocation information at a per-chunk level with a few global counters. This is also gated behind a config. BPF and cgroup, for example, have seen an increase in use causing increased use of percpu memory. Let's make it easier for someone to identify how much memory is being used. This patch adds the "Percpu" stat to meminfo to more easily look up how much percpu memory is in use. This number includes the cost for all allocated backing pages and not just insight at the per a unit, per chunk level. Metadata is excluded. I think excluding metadata is fair because the backing memory scales with the numbere of cpus and can quickly outweigh the metadata. It also makes this calculation light. Link: http://lkml.kernel.org/r/20180807184723.74919-1-dennisszhou@gmail.com Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Acked-by: Roman Gushchin Reviewed-by: Andrew Morton Acked-by: David Rientjes Acked-by: Vlastimil Babka Cc: Johannes Weiner Cc: Christoph Lameter Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 296bbe49d5d1..70b7123f38c7 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -149,4 +149,6 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr); (typeof(type) __percpu *)__alloc_percpu(sizeof(type), \ __alignof__(type)) +extern unsigned long pcpu_nr_pages(void); + #endif /* __LINUX_PERCPU_H */ -- cgit v1.2.3 From 5df66d306ec9b1952d3d183fe4e2ced1a7b2bddb Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Tue, 21 Aug 2018 21:54:06 -0700 Subject: mm: fix comment for NODEMASK_ALLOC Currently, NODEMASK_ALLOC allocates a nodemask_t with kmalloc when NODES_SHIFT is higher than 8, otherwise it declares it within the stack. The comment says that the reasoning behind this, is that nodemask_t will be 256 bytes when NODES_SHIFT is higher than 8, but this is not true. For example, NODES_SHIFT = 9 will give us a 64 bytes nodemask_t. Let us fix up the comment for that. Another thing is that it might make sense to let values lower than 128bytes be allocated in the stack. Although this all depends on the depth of the stack (and this changes from function to function), I think that 64 bytes is something we can easily afford. So we could even bump the limit by 1 (from > 8 to > 9). Link: http://lkml.kernel.org/r/20180820085516.9687-1-osalvador@techadventures.net Signed-off-by: Oscar Salvador Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nodemask.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 1fbde8a880d9..5a30ad594ccc 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -518,7 +518,7 @@ static inline int node_random(const nodemask_t *mask) * NODEMASK_ALLOC(type, name) allocates an object with a specified type and * name. */ -#if NODES_SHIFT > 8 /* nodemask_t > 256 bytes */ +#if NODES_SHIFT > 8 /* nodemask_t > 32 bytes */ #define NODEMASK_ALLOC(type, name, gfp_flags) \ type *name = kmalloc(sizeof(*name), gfp_flags) #define NODEMASK_FREE(m) kfree(m) -- cgit v1.2.3 From 891ae71dc4fbd2454a3fa569e115a7ca86630949 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 21 Aug 2018 21:54:37 -0700 Subject: proc: spread "const" a bit Link: http://lkml.kernel.org/r/20180627200614.GB18434@avx2 Signed-off-by: Alexey Dobriyan Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 626fc65c4336..d0e1f1522a78 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -129,7 +129,7 @@ int open_related_ns(struct ns_common *ns, struct ns_common *(*get_ns)(struct ns_common *ns)); /* get the associated pid namespace for a file in procfs */ -static inline struct pid_namespace *proc_pid_ns(struct inode *inode) +static inline struct pid_namespace *proc_pid_ns(const struct inode *inode) { return inode->i_sb->s_fs_info; } -- cgit v1.2.3 From a8dd9c4df18edc873d244790d163564a5d17626b Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 21 Aug 2018 21:54:51 -0700 Subject: proc/kcore: don't grab lock for kclist_add() Patch series "/proc/kcore improvements", v4. This series makes a few improvements to /proc/kcore. It fixes a couple of small issues in v3 but is otherwise the same. Patches 1, 2, and 3 are prep patches. Patch 4 is a fix/cleanup. Patch 5 is another prep patch. Patches 6 and 7 are optimizations to ->read(). Patch 8 makes it possible to enable CRASH_CORE on any architecture, which is needed for patch 9. Patch 9 adds vmcoreinfo to /proc/kcore. This patch (of 9): kclist_add() is only called at init time, so there's no point in grabbing any locks. We're also going to replace the rwlock with a rwsem, which we don't want to try grabbing during early boot. While we're here, mark kclist_add() with __init so that we'll get a warning if it's called from non-init code. Link: http://lkml.kernel.org/r/98208db1faf167aa8b08eebfa968d95c70527739.1531953780.git.osandov@fb.com Signed-off-by: Omar Sandoval Reviewed-by: Andrew Morton Reviewed-by: Bhupesh Sharma Tested-by: Bhupesh Sharma Cc: Alexey Dobriyan Cc: Bhupesh Sharma Cc: Eric Biederman Cc: James Morse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kcore.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kcore.h b/include/linux/kcore.h index 8de55e4b5ee9..c20f296438fb 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -35,7 +35,7 @@ struct vmcoredd_node { }; #ifdef CONFIG_PROC_KCORE -extern void kclist_add(struct kcore_list *, void *, size_t, int type); +void __init kclist_add(struct kcore_list *, void *, size_t, int type); #else static inline void kclist_add(struct kcore_list *new, void *addr, size_t size, int type) -- cgit v1.2.3 From 23c85094fe1895caefdd19ef624ee687ec5f4507 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 21 Aug 2018 21:55:20 -0700 Subject: proc/kcore: add vmcoreinfo note to /proc/kcore The vmcoreinfo information is useful for runtime debugging tools, not just for crash dumps. A lot of this information can be determined by other means, but this is much more convenient, and it only adds a page at most to the file. Link: http://lkml.kernel.org/r/fddbcd08eed76344863303878b12de1c1e2a04b6.1531953780.git.osandov@fb.com Signed-off-by: Omar Sandoval Cc: Alexey Dobriyan Cc: Bhupesh Sharma Cc: Eric Biederman Cc: James Morse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index b511f6d24b42..525510a9f965 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -60,6 +60,8 @@ phys_addr_t paddr_vmcoreinfo_note(void); #define VMCOREINFO_CONFIG(name) \ vmcoreinfo_append_str("CONFIG_%s=y\n", #name) +extern unsigned char *vmcoreinfo_data; +extern size_t vmcoreinfo_size; extern u32 *vmcoreinfo_note; Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, -- cgit v1.2.3 From cedc5b6aab493f6b1b1d381dccc0cc082da7d3d8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 21 Aug 2018 21:55:28 -0700 Subject: kernel.h: documentation for roundup() vs round_up() Things like 3619dec5103d ("dh key: fix rounding up KDF output length") expose the lack of explicit documentation for roundup() vs round_up(). At least we can try to document it better if anyone goes looking. Link: http://lkml.kernel.org/r/20180703041950.GA43464@beast Signed-off-by: Kees Cook Cc: Ingo Molnar Cc: Greg Kroah-Hartman Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 35 ++++++++++++++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 941dc0a5a877..d6aac75b51ba 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -85,7 +85,23 @@ * arguments just once each. */ #define __round_mask(x, y) ((__typeof__(x))((y)-1)) +/** + * round_up - round up to next specified power of 2 + * @x: the value to round + * @y: multiple to round up to (must be a power of 2) + * + * Rounds @x up to next multiple of @y (which must be a power of 2). + * To perform arbitrary rounding up, use roundup() below. + */ #define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) +/** + * round_down - round down to next specified power of 2 + * @x: the value to round + * @y: multiple to round down to (must be a power of 2) + * + * Rounds @x down to next multiple of @y (which must be a power of 2). + * To perform arbitrary rounding down, use rounddown() below. + */ #define round_down(x, y) ((x) & ~__round_mask(x, y)) /** @@ -110,13 +126,30 @@ # define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP(ll,d) #endif -/* The `const' in roundup() prevents gcc-3.3 from calling __divdi3 */ +/** + * roundup - round up to the next specified multiple + * @x: the value to up + * @y: multiple to round up to + * + * Rounds @x up to next multiple of @y. If @y will always be a power + * of 2, consider using the faster round_up(). + * + * The `const' here prevents gcc-3.3 from calling __divdi3 + */ #define roundup(x, y) ( \ { \ const typeof(y) __y = y; \ (((x) + (__y - 1)) / __y) * __y; \ } \ ) +/** + * rounddown - round down to next specified multiple + * @x: the value to round + * @y: multiple to round down to + * + * Rounds @x down to next multiple of @y. If @y will always be a power + * of 2, consider using the faster round_down(). + */ #define rounddown(x, y) ( \ { \ typeof(x) __x = (x); \ -- cgit v1.2.3 From e58dd0de5eadf145895b13451a1fef8ef03946eb Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 21 Aug 2018 21:55:31 -0700 Subject: bdi: use refcount_t for reference counting instead atomic_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This permits avoiding accidental refcounter overflows that might lead to use-after-free situations. Link: http://lkml.kernel.org/r/20180703200141.28415-4-bigeasy@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Suggested-by: Peter Zijlstra Cc: Jens Axboe Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 3 ++- include/linux/backing-dev.h | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 24251762c20c..9a6bc0951cfa 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -12,6 +12,7 @@ #include #include #include +#include struct page; struct device; @@ -75,7 +76,7 @@ enum wb_reason { */ struct bdi_writeback_congested { unsigned long state; /* WB_[a]sync_congested flags */ - atomic_t refcnt; /* nr of attached wb's and blkg */ + refcount_t refcnt; /* nr of attached wb's and blkg */ #ifdef CONFIG_CGROUP_WRITEBACK struct backing_dev_info *__bdi; /* the associated bdi, set to NULL diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 72ca0f3d39f3..c28a47cbe355 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -404,13 +404,13 @@ static inline bool inode_cgwb_enabled(struct inode *inode) static inline struct bdi_writeback_congested * wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) { - atomic_inc(&bdi->wb_congested->refcnt); + refcount_inc(&bdi->wb_congested->refcnt); return bdi->wb_congested; } static inline void wb_congested_put(struct bdi_writeback_congested *congested) { - if (atomic_dec_and_test(&congested->refcnt)) + if (refcount_dec_and_test(&congested->refcnt)) kfree(congested); } -- cgit v1.2.3 From fc37191272a972d449bab3d8247cf52cadf5d4e6 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 21 Aug 2018 21:55:38 -0700 Subject: userns: use refcount_t for reference counting instead atomic_t refcount_t type and corresponding API should be used instead of atomic_t wh en the variable is used as a reference counter. This avoids accidental refcounter overflows that might lead to use-after-free situations. Link: http://lkml.kernel.org/r/20180703200141.28415-6-bigeasy@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Suggested-by: Peter Zijlstra Acked-by: Peter Zijlstra (Intel) Reviewed-by: Andrew Morton Cc: "Eric W. Biederman" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/user.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 96fe289c4c6e..39ad98c09c58 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -4,6 +4,7 @@ #include #include +#include #include struct key; @@ -12,7 +13,7 @@ struct key; * Some day this will be a full-fledged user tracking system.. */ struct user_struct { - atomic_t __count; /* reference count */ + refcount_t __count; /* reference count */ atomic_t processes; /* How many processes does this user have? */ atomic_t sigpending; /* How many pending signals does this user have? */ #ifdef CONFIG_FANOTIFY @@ -59,7 +60,7 @@ extern struct user_struct root_user; extern struct user_struct * alloc_uid(kuid_t); static inline struct user_struct *get_uid(struct user_struct *u) { - atomic_inc(&u->__count); + refcount_inc(&u->__count); return u; } extern void free_uid(struct user_struct *); -- cgit v1.2.3 From 203583990cb675aeddff6d7623f68268068c078c Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 21 Aug 2018 21:55:45 -0700 Subject: linux/compiler.h: don't use bool Appararently, it's possible to have a non-trivial TU include a few headers, including linux/build_bug.h, without ending up with linux/types.h. So the 0day bot sent me config: um-x86_64_defconfig (attached as .config) >> include/linux/compiler.h:316:3: error: unknown type name 'bool'; did you mean '_Bool'? bool __cond = !(condition); \ for something I'm working on. Rather than contributing to the #include madness and including linux/types.h from compiler.h, just use int. Link: http://lkml.kernel.org/r/20180817101036.20969-1-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Cc: Christopher Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 42506e4d1f53..c8eab637a2a7 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -313,7 +313,7 @@ unsigned long read_word_at_a_time(const void *addr) #ifdef __OPTIMIZE__ # define __compiletime_assert(condition, msg, prefix, suffix) \ do { \ - bool __cond = !(condition); \ + int __cond = !(condition); \ extern void prefix ## suffix(void) __compiletime_error(msg); \ if (__cond) \ prefix ## suffix(); \ -- cgit v1.2.3 From a2e514453861dd39b53b7a50b6771bd3f9852078 Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Tue, 21 Aug 2018 21:55:52 -0700 Subject: kernel/hung_task.c: allow to set checking interval separately from timeout Currently task hung checking interval is equal to timeout, as the result hung is detected anywhere between timeout and 2*timeout. This is fine for most interactive environments, but this hurts automated testing setups (syzbot). In an automated setup we need to strictly order CPU lockup < RCU stall < workqueue lockup < task hung < silent loss, so that RCU stall is not detected as task hung and task hung is not detected as silent machine loss. The large variance in task hung detection timeout requires setting silent machine loss timeout to a very large value (e.g. if task hung is 3 mins, then silent loss need to be set to ~7 mins). The additional 3 minutes significantly reduce testing efficiency because usually we crash kernel within a minute, and this can add hours to bug localization process as it needs to do dozens of tests. Allow setting checking interval separately from timeout. This allows to set timeout to, say, 3 minutes, but checking interval to 10 secs. The interval is controlled via a new hung_task_check_interval_secs sysctl, similar to the existing hung_task_timeout_secs sysctl. The default value of 0 results in the current behavior: checking interval is equal to timeout. [akpm@linux-foundation.org: update hung_task_timeout_max's comment] Link: http://lkml.kernel.org/r/20180611111004.203513-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov Cc: Paul E. McKenney Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + include/linux/sched/sysctl.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 789923fbee3a..58eb3a2bc695 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -853,6 +853,7 @@ struct task_struct { #endif #ifdef CONFIG_DETECT_HUNG_TASK unsigned long last_switch_count; + unsigned long last_switch_time; #endif /* Filesystem information: */ struct fs_struct *fs; diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 913488d828cb..a9c32daeb9d8 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -10,6 +10,7 @@ struct ctl_table; extern int sysctl_hung_task_check_count; extern unsigned int sysctl_hung_task_panic; extern unsigned long sysctl_hung_task_timeout_secs; +extern unsigned long sysctl_hung_task_check_interval_secs; extern int sysctl_hung_task_warnings; extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, void __user *buffer, -- cgit v1.2.3 From f922c4abdf7648523589abee9460c87f51630d2f Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 21 Aug 2018 21:56:04 -0700 Subject: module: allow symbol exports to be disabled To allow existing C code to be incorporated into the decompressor or the UEFI stub, introduce a CPP macro that turns all EXPORT_SYMBOL_xxx declarations into nops, and #define it in places where such exports are undesirable. Note that this gets rid of a rather dodgy redefine of linux/export.h's header guard. Link: http://lkml.kernel.org/r/20180704083651.24360-3-ard.biesheuvel@linaro.org Signed-off-by: Ard Biesheuvel Acked-by: Nicolas Pitre Acked-by: Michael Ellerman Reviewed-by: Will Deacon Acked-by: Ingo Molnar Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Bjorn Helgaas Cc: Catalin Marinas Cc: James Morris Cc: James Morris Cc: Jessica Yu Cc: Josh Poimboeuf Cc: Kees Cook Cc: Paul Mackerras Cc: Petr Mladek Cc: Russell King Cc: "Serge E. Hallyn" Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Thomas Garnier Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/export.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index b768d6dd3c90..ea7df303d68d 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -66,7 +66,16 @@ extern struct module __this_module; __attribute__((section("___ksymtab" sec "+" #sym), used)) \ = { (unsigned long)&sym, __kstrtab_##sym } -#if defined(__KSYM_DEPS__) +#if defined(__DISABLE_EXPORTS) + +/* + * Allow symbol exports to be disabled completely so that C code may + * be reused in other execution contexts such as the UEFI stub or the + * decompressor. + */ +#define __EXPORT_SYMBOL(sym, sec) + +#elif defined(__KSYM_DEPS__) /* * For fine grained build dependencies, we want to tell the build system -- cgit v1.2.3 From 7290d58095712a89f845e1bca05334796dd49ed2 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 21 Aug 2018 21:56:09 -0700 Subject: module: use relative references for __ksymtab entries An ordinary arm64 defconfig build has ~64 KB worth of __ksymtab entries, each consisting of two 64-bit fields containing absolute references, to the symbol itself and to a char array containing its name, respectively. When we build the same configuration with KASLR enabled, we end up with an additional ~192 KB of relocations in the .init section, i.e., one 24 byte entry for each absolute reference, which all need to be processed at boot time. Given how the struct kernel_symbol that describes each entry is completely local to module.c (except for the references emitted by EXPORT_SYMBOL() itself), we can easily modify it to contain two 32-bit relative references instead. This reduces the size of the __ksymtab section by 50% for all 64-bit architectures, and gets rid of the runtime relocations entirely for architectures implementing KASLR, either via standard PIE linking (arm64) or using custom host tools (x86). Note that the binary search involving __ksymtab contents relies on each section being sorted by symbol name. This is implemented based on the input section names, not the names in the ksymtab entries, so this patch does not interfere with that. Given that the use of place-relative relocations requires support both in the toolchain and in the module loader, we cannot enable this feature for all architectures. So make it dependent on whether CONFIG_HAVE_ARCH_PREL32_RELOCATIONS is defined. Link: http://lkml.kernel.org/r/20180704083651.24360-4-ard.biesheuvel@linaro.org Signed-off-by: Ard Biesheuvel Acked-by: Jessica Yu Acked-by: Michael Ellerman Reviewed-by: Will Deacon Acked-by: Ingo Molnar Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Bjorn Helgaas Cc: Catalin Marinas Cc: James Morris Cc: James Morris Cc: Josh Poimboeuf Cc: Kees Cook Cc: Nicolas Pitre Cc: Paul Mackerras Cc: Petr Mladek Cc: Russell King Cc: "Serge E. Hallyn" Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Thomas Garnier Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 19 +++++++++++++++++++ include/linux/export.h | 46 +++++++++++++++++++++++++++++++++++----------- 2 files changed, 54 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c8eab637a2a7..681d866efb1e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -280,6 +280,25 @@ unsigned long read_word_at_a_time(const void *addr) #endif /* __KERNEL__ */ +/* + * Force the compiler to emit 'sym' as a symbol, so that we can reference + * it from inline assembler. Necessary in case 'sym' could be inlined + * otherwise, or eliminated entirely due to lack of references that are + * visible to the compiler. + */ +#define __ADDRESSABLE(sym) \ + static void * __attribute__((section(".discard.addressable"), used)) \ + __PASTE(__addressable_##sym, __LINE__) = (void *)&sym; + +/** + * offset_to_ptr - convert a relative memory offset to an absolute pointer + * @off: the address of the 32-bit offset value + */ +static inline void *offset_to_ptr(const int *off) +{ + return (void *)((unsigned long)off + *off); +} + #endif /* __ASSEMBLY__ */ #ifndef __optimize diff --git a/include/linux/export.h b/include/linux/export.h index ea7df303d68d..ae072bc5aacf 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -18,12 +18,6 @@ #define VMLINUX_SYMBOL_STR(x) __VMLINUX_SYMBOL_STR(x) #ifndef __ASSEMBLY__ -struct kernel_symbol -{ - unsigned long value; - const char *name; -}; - #ifdef MODULE extern struct module __this_module; #define THIS_MODULE (&__this_module) @@ -54,17 +48,47 @@ extern struct module __this_module; #define __CRC_SYMBOL(sym, sec) #endif +#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS +#include +/* + * Emit the ksymtab entry as a pair of relative references: this reduces + * the size by half on 64-bit architectures, and eliminates the need for + * absolute relocations that require runtime processing on relocatable + * kernels. + */ +#define __KSYMTAB_ENTRY(sym, sec) \ + __ADDRESSABLE(sym) \ + asm(" .section \"___ksymtab" sec "+" #sym "\", \"a\" \n" \ + " .balign 8 \n" \ + "__ksymtab_" #sym ": \n" \ + " .long " #sym "- . \n" \ + " .long __kstrtab_" #sym "- . \n" \ + " .previous \n") + +struct kernel_symbol { + int value_offset; + int name_offset; +}; +#else +#define __KSYMTAB_ENTRY(sym, sec) \ + static const struct kernel_symbol __ksymtab_##sym \ + __attribute__((section("___ksymtab" sec "+" #sym), used)) \ + = { (unsigned long)&sym, __kstrtab_##sym } + +struct kernel_symbol { + unsigned long value; + const char *name; +}; +#endif + /* For every exported symbol, place a struct in the __ksymtab section */ #define ___EXPORT_SYMBOL(sym, sec) \ extern typeof(sym) sym; \ __CRC_SYMBOL(sym, sec) \ static const char __kstrtab_##sym[] \ - __attribute__((section("__ksymtab_strings"), aligned(1))) \ + __attribute__((section("__ksymtab_strings"), used, aligned(1))) \ = #sym; \ - static const struct kernel_symbol __ksymtab_##sym \ - __used \ - __attribute__((section("___ksymtab" sec "+" #sym), used)) \ - = { (unsigned long)&sym, __kstrtab_##sym } + __KSYMTAB_ENTRY(sym, sec) #if defined(__DISABLE_EXPORTS) -- cgit v1.2.3 From 1b1eeca7e4c19fa76d409d4c7b338dba21f2df45 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 21 Aug 2018 21:56:13 -0700 Subject: init: allow initcall tables to be emitted using relative references Allow the initcall tables to be emitted using relative references that are only half the size on 64-bit architectures and don't require fixups at runtime on relocatable kernels. Link: http://lkml.kernel.org/r/20180704083651.24360-5-ard.biesheuvel@linaro.org Acked-by: James Morris Acked-by: Sergey Senozhatsky Acked-by: Petr Mladek Acked-by: Michael Ellerman Acked-by: Ingo Molnar Signed-off-by: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Bjorn Helgaas Cc: Catalin Marinas Cc: James Morris Cc: Jessica Yu Cc: Josh Poimboeuf Cc: Kees Cook Cc: Nicolas Pitre Cc: Paul Mackerras Cc: Russell King Cc: "Serge E. Hallyn" Cc: Steven Rostedt Cc: Thomas Garnier Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init.h | 44 +++++++++++++++++++++++++++++++++----------- 1 file changed, 33 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index bc27cf03c41e..2538d176dd1f 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -116,8 +116,24 @@ typedef int (*initcall_t)(void); typedef void (*exitcall_t)(void); -extern initcall_t __con_initcall_start[], __con_initcall_end[]; -extern initcall_t __security_initcall_start[], __security_initcall_end[]; +#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS +typedef int initcall_entry_t; + +static inline initcall_t initcall_from_entry(initcall_entry_t *entry) +{ + return offset_to_ptr(entry); +} +#else +typedef initcall_t initcall_entry_t; + +static inline initcall_t initcall_from_entry(initcall_entry_t *entry) +{ + return *entry; +} +#endif + +extern initcall_entry_t __con_initcall_start[], __con_initcall_end[]; +extern initcall_entry_t __security_initcall_start[], __security_initcall_end[]; /* Used for contructor calls. */ typedef void (*ctor_fn_t)(void); @@ -167,9 +183,20 @@ extern bool initcall_debug; * as KEEP() in the linker script. */ -#define __define_initcall(fn, id) \ +#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS +#define ___define_initcall(fn, id, __sec) \ + __ADDRESSABLE(fn) \ + asm(".section \"" #__sec ".init\", \"a\" \n" \ + "__initcall_" #fn #id ": \n" \ + ".long " #fn " - . \n" \ + ".previous \n"); +#else +#define ___define_initcall(fn, id, __sec) \ static initcall_t __initcall_##fn##id __used \ - __attribute__((__section__(".initcall" #id ".init"))) = fn; + __attribute__((__section__(#__sec ".init"))) = fn; +#endif + +#define __define_initcall(fn, id) ___define_initcall(fn, id, .initcall##id) /* * Early initcalls run before initializing SMP. @@ -208,13 +235,8 @@ extern bool initcall_debug; #define __exitcall(fn) \ static exitcall_t __exitcall_##fn __exit_call = fn -#define console_initcall(fn) \ - static initcall_t __initcall_##fn \ - __used __section(.con_initcall.init) = fn - -#define security_initcall(fn) \ - static initcall_t __initcall_##fn \ - __used __section(.security_initcall.init) = fn +#define console_initcall(fn) ___define_initcall(fn,, .con_initcall) +#define security_initcall(fn) ___define_initcall(fn,, .security_initcall) struct obs_kernel_param { const char *str; -- cgit v1.2.3 From c9d8b55fa0191623fccb9ed67d2ff8f9159e9a89 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 21 Aug 2018 21:56:18 -0700 Subject: PCI: Add support for relative addressing in quirk tables Allow the PCI quirk tables to be emitted in a way that avoids absolute references to the hook functions. This reduces the size of the entries, and, more importantly, makes them invariant under runtime relocation (e.g., for KASLR) Link: http://lkml.kernel.org/r/20180704083651.24360-6-ard.biesheuvel@linaro.org Acked-by: Bjorn Helgaas Acked-by: Michael Ellerman Acked-by: Ingo Molnar Signed-off-by: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: James Morris Cc: James Morris Cc: Jessica Yu Cc: Josh Poimboeuf Cc: Kees Cook Cc: Nicolas Pitre Cc: Paul Mackerras Cc: Petr Mladek Cc: Russell King Cc: "Serge E. Hallyn" Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Thomas Garnier Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 9b87f1936906..e72ca8dd6241 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1809,7 +1809,11 @@ struct pci_fixup { u16 device; /* Or PCI_ANY_ID */ u32 class; /* Or PCI_ANY_ID */ unsigned int class_shift; /* should be 0, 8, 16 */ +#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS + int hook_offset; +#else void (*hook)(struct pci_dev *dev); +#endif }; enum pci_fixup_pass { @@ -1823,12 +1827,28 @@ enum pci_fixup_pass { pci_fixup_suspend_late, /* pci_device_suspend_late() */ }; +#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS +#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook) \ + __ADDRESSABLE(hook) \ + asm(".section " #sec ", \"a\" \n" \ + ".balign 16 \n" \ + ".short " #vendor ", " #device " \n" \ + ".long " #class ", " #class_shift " \n" \ + ".long " #hook " - . \n" \ + ".previous \n"); +#define DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook) \ + __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook) +#else /* Anonymous variables would be nice... */ #define DECLARE_PCI_FIXUP_SECTION(section, name, vendor, device, class, \ class_shift, hook) \ static const struct pci_fixup __PASTE(__pci_fixup_##name,__LINE__) __used \ __attribute__((__section__(#section), aligned((sizeof(void *))))) \ = { vendor, device, class, class_shift, hook }; +#endif #define DECLARE_PCI_FIXUP_CLASS_EARLY(vendor, device, class, \ class_shift, hook) \ -- cgit v1.2.3 From 46e0c9be206fa7b11aca75da2d6b8535d0139752 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 21 Aug 2018 21:56:22 -0700 Subject: kernel: tracepoints: add support for relative references To avoid the need for relocating absolute references to tracepoint structures at boot time when running relocatable kernels (which may take a disproportionate amount of space), add the option to emit these tables as relative references instead. Link: http://lkml.kernel.org/r/20180704083651.24360-7-ard.biesheuvel@linaro.org Acked-by: Michael Ellerman Acked-by: Ingo Molnar Acked-by: Steven Rostedt (VMware) Signed-off-by: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Bjorn Helgaas Cc: Catalin Marinas Cc: James Morris Cc: James Morris Cc: Jessica Yu Cc: Josh Poimboeuf Cc: Kees Cook Cc: Nicolas Pitre Cc: Paul Mackerras Cc: Petr Mladek Cc: Russell King Cc: "Serge E. Hallyn" Cc: Sergey Senozhatsky Cc: Thomas Garnier Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracepoint.h | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index d9a084c72541..7f2e16e76ac4 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -249,6 +249,19 @@ extern void syscall_unregfunc(void); return static_key_false(&__tracepoint_##name.key); \ } +#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS +#define __TRACEPOINT_ENTRY(name) \ + asm(" .section \"__tracepoints_ptrs\", \"a\" \n" \ + " .balign 4 \n" \ + " .long __tracepoint_" #name " - . \n" \ + " .previous \n") +#else +#define __TRACEPOINT_ENTRY(name) \ + static struct tracepoint * const __tracepoint_ptr_##name __used \ + __attribute__((section("__tracepoints_ptrs"))) = \ + &__tracepoint_##name +#endif + /* * We have no guarantee that gcc and the linker won't up-align the tracepoint * structures, so we create an array of pointers that will be used for iteration @@ -258,11 +271,9 @@ extern void syscall_unregfunc(void); static const char __tpstrtab_##name[] \ __attribute__((section("__tracepoints_strings"))) = #name; \ struct tracepoint __tracepoint_##name \ - __attribute__((section("__tracepoints"))) = \ + __attribute__((section("__tracepoints"), used)) = \ { __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\ - static struct tracepoint * const __tracepoint_ptr_##name __used \ - __attribute__((section("__tracepoints_ptrs"))) = \ - &__tracepoint_##name; + __TRACEPOINT_ENTRY(name); #define DEFINE_TRACE(name) \ DEFINE_TRACE_FN(name, NULL, NULL); -- cgit v1.2.3 From 9144d75e22cad3c89e6b2ccab551db9ee28d250a Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 21 Aug 2018 21:57:03 -0700 Subject: include/linux/bitops.h: introduce BITS_PER_TYPE net_dim.h has a rather useful extension to BITS_PER_BYTE to compute the number of bits in a type (BITS_PER_BYTE * sizeof(T)), so promote the macro to bitops.h, alongside BITS_PER_BYTE, for wider usage. Link: http://lkml.kernel.org/r/20180706094458.14116-1-chris@chris-wilson.co.uk Signed-off-by: Chris Wilson Reviewed-by: Jani Nikula Cc: Randy Dunlap Cc: Andy Gospodarek Cc: David S. Miller Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 3 ++- include/linux/net_dim.h | 1 - 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index af419012d77d..7ddb1349394d 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -4,7 +4,8 @@ #include #include -#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) +#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) +#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index db99240d00bd..c79e859408e6 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -363,7 +363,6 @@ static inline void net_dim_sample(u16 event_ctr, } #define NET_DIM_NEVENTS 64 -#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) & (BIT_ULL(bits) - 1)) static inline void net_dim_calc_stats(struct net_dim_sample *start, -- cgit v1.2.3 From feba04fd2cf8f6a74865338df2e3e1e94d6cfd13 Mon Sep 17 00:00:00 2001 From: Coly Li Date: Tue, 21 Aug 2018 21:57:11 -0700 Subject: lib: add crc64 calculation routines Patch series "add crc64 calculation as kernel library", v5. This patchset adds basic implementation of crc64 calculation as a Linux kernel library. Since bcache already does crc64 by itself, this patchset also modifies bcache code to use the new crc64 library routine. Currently bcache is the only user of crc64 calculation, another potential user is bcachefs which is on the way to be in mainline kernel. Therefore it makes sense to make crc64 calculation to be a public library. bcache uses crc64 as storage checksum, if a change of crc lib routines results an inconsistent result, the unmatched checksum may make bcache 'think' the on-disk is corrupted, such a change should be avoided or detected as early as possible. Therefore a patch is being prepared which adds a crc test framework, to check consistency of different calculations. This patch (of 2): Add the re-write crc64 calculation routines for Linux kernel. The CRC64 polynomical arithmetic follows ECMA-182 specification, inspired by CRC paper of Dr. Ross N. Williams (see http://www.ross.net/crc/download/crc_v3.txt) and other public domain implementations. All the changes work in this way, - When Linux kernel is built, host program lib/gen_crc64table.c will be compiled to lib/gen_crc64table and executed. - The output of gen_crc64table execution is an array called as lookup table (a.k.a POLY 0x42f0e1eba9ea369) which contain 256 64-bit long numbers, this table is dumped into header file lib/crc64table.h. - Then the header file is included by lib/crc64.c for normal 64bit crc calculation. - Function declaration of the crc64 calculation routines is placed in include/linux/crc64.h Currently bcache is the only user of crc64_be(), another potential user is bcachefs which is on the way to be in mainline kernel. Therefore it makes sense to move crc64 calculation into lib/crc64.c as public code. [colyli@suse.de: fix review comments from v4] Link: http://lkml.kernel.org/r/20180726053352.2781-2-colyli@suse.de Link: http://lkml.kernel.org/r/20180718165545.1622-2-colyli@suse.de Signed-off-by: Coly Li Co-developed-by: Andy Shevchenko Signed-off-by: Andy Shevchenko Reviewed-by: Hannes Reinecke Cc: Greg Kroah-Hartman Cc: Andy Shevchenko Cc: Michael Lyle Cc: Kent Overstreet Cc: Thomas Gleixner Cc: Kate Stewart Cc: Eric Biggers Cc: Randy Dunlap Cc: Noah Massey Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crc64.h | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 include/linux/crc64.h (limited to 'include/linux') diff --git a/include/linux/crc64.h b/include/linux/crc64.h new file mode 100644 index 000000000000..c756e65a1b58 --- /dev/null +++ b/include/linux/crc64.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * See lib/crc64.c for the related specification and polynomial arithmetic. + */ +#ifndef _LINUX_CRC64_H +#define _LINUX_CRC64_H + +#include + +u64 __pure crc64_be(u64 crc, const void *p, size_t len); +#endif /* _LINUX_CRC64_H */ -- cgit v1.2.3 From 52cba1a274818c3ee6299c1a1b476e7bc5037a2f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 21 Aug 2018 21:59:51 -0700 Subject: signal: make force_sigsegv() void Patch series "signal: refactor some functions", v3. This series refactors a bunch of functions in signal.c to simplify parts of the code. The greatest single change is declaring the static do_sigpending() helper as void which makes it possible to remove a bunch of unnecessary checks in the syscalls later on. This patch (of 17): force_sigsegv() returned 0 unconditionally so it doesn't make sense to have it return at all. In addition, there are no callers that check force_sigsegv()'s return value. Link: http://lkml.kernel.org/r/20180602103653.18181-2-christian@brauner.io Signed-off-by: Christian Brauner Reviewed-by: Andrew Morton Cc: Eric W. Biederman Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: James Morris Cc: Kees Cook Cc: Peter Zijlstra Cc: Stephen Smalley Cc: Al Viro Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 113d1ad1ced7..e138ac16c650 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -314,7 +314,7 @@ int force_sig_pkuerr(void __user *addr, u32 pkey); int force_sig_ptrace_errno_trap(int errno, void __user *addr); extern int send_sig_info(int, struct siginfo *, struct task_struct *); -extern int force_sigsegv(int, struct task_struct *); +extern void force_sigsegv(int sig, struct task_struct *p); extern int force_sig_info(int, struct siginfo *, struct task_struct *); extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid); -- cgit v1.2.3 From 67a48a24478841525ba73ec6d64caaf079cf3b7c Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 21 Aug 2018 22:00:34 -0700 Subject: signal: make unhandled_signal() return bool unhandled_signal() already behaves like a boolean function. Let's actually declare it as such too. All callers treat it as such too. Link: http://lkml.kernel.org/r/20180602103653.18181-13-christian@brauner.io Signed-off-by: Christian Brauner Reviewed-by: Andrew Morton Cc: Al Viro Cc: Eric W. Biederman Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: James Morris Cc: Kees Cook Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Stephen Smalley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 3c5200137b24..fa23cae66758 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -287,7 +287,7 @@ static inline void disallow_signal(int sig) extern struct kmem_cache *sighand_cachep; -int unhandled_signal(struct task_struct *tsk, int sig); +extern bool unhandled_signal(struct task_struct *tsk, int sig); /* * In POSIX a signal is sent either to a specific thread (Linux task) -- cgit v1.2.3 From 20ab7218d2507b2dbec9c053c2f1b96054e266b6 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 21 Aug 2018 22:00:54 -0700 Subject: signal: make get_signal() return bool make get_signal() already behaves like a boolean function. Let's actually declare it as such too. Link: http://lkml.kernel.org/r/20180602103653.18181-18-christian@brauner.io Signed-off-by: Christian Brauner Reviewed-by: Andrew Morton Cc: Al Viro Cc: Eric W. Biederman Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: James Morris Cc: Kees Cook Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Stephen Smalley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index fa23cae66758..e3d9e0640e6e 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -265,7 +265,7 @@ extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; -extern int get_signal(struct ksignal *ksig); +extern bool get_signal(struct ksignal *ksig); extern void signal_setup_done(int failed, struct ksignal *ksig, int stepping); extern void exit_signals(struct task_struct *tsk); extern void kernel_sigaction(int, __sighandler_t); -- cgit v1.2.3 From dc2c8c84def6ce450c63529e08c1db100020994e Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 21 Aug 2018 22:01:52 -0700 Subject: ipc: get rid of ids->tables_initialized hack In sysvipc we have an ids->tables_initialized regarding the rhashtable, introduced in 0cfb6aee70bd ("ipc: optimize semget/shmget/msgget for lots of keys") It's there, specifically, to prevent nil pointer dereferences, from using an uninitialized api. Considering how rhashtable_init() can fail (probably due to ENOMEM, if anything), this made the overall ipc initialization capable of failure as well. That alone is ugly, but fine, however I've spotted a few issues regarding the semantics of tables_initialized (however unlikely they may be): - There is inconsistency in what we return to userspace: ipc_addid() returns ENOSPC which is certainly _wrong_, while ipc_obtain_object_idr() returns EINVAL. - After we started using rhashtables, ipc_findkey() can return nil upon !tables_initialized, but the caller expects nil for when the ipc structure isn't found, and can therefore call into ipcget() callbacks. Now that rhashtable initialization cannot fail, we can properly get rid of the hack altogether. [manfred@colorfullife.com: commit id extended to 12 digits] Link: http://lkml.kernel.org/r/20180712185241.4017-10-manfred@colorfullife.com Signed-off-by: Davidlohr Bueso Signed-off-by: Manfred Spraul Cc: Dmitry Vyukov Cc: Herbert Xu Cc: Kees Cook Cc: Michael Kerrisk Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 6cea726612b7..e9ccdfdb1928 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -16,7 +16,6 @@ struct user_namespace; struct ipc_ids { int in_use; unsigned short seq; - bool tables_initialized; struct rw_semaphore rwsem; struct idr ipcs_idr; int max_id; -- cgit v1.2.3 From 27c331a174614208d0b539019583990967ad9479 Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Tue, 21 Aug 2018 22:02:00 -0700 Subject: ipc/util.c: further variable name cleanups The varable names got a mess, thus standardize them again: id: user space id. Called semid, shmid, msgid if the type is known. Most functions use "id" already. idx: "index" for the idr lookup Right now, some functions use lid, ipc_addid() already uses idx as the variable name. seq: sequence number, to avoid quick collisions of the user space id key: user space key, used for the rhash tree Link: http://lkml.kernel.org/r/20180712185241.4017-12-manfred@colorfullife.com Signed-off-by: Manfred Spraul Cc: Dmitry Vyukov Cc: Davidlohr Bueso Cc: Davidlohr Bueso Cc: Herbert Xu Cc: Kees Cook Cc: Michael Kerrisk Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e9ccdfdb1928..6ab8c1bada3f 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -18,7 +18,7 @@ struct ipc_ids { unsigned short seq; struct rw_semaphore rwsem; struct idr ipcs_idr; - int max_id; + int max_idx; #ifdef CONFIG_CHECKPOINT_RESTORE int next_id; #endif -- cgit v1.2.3 From 9abdda5ddab8a899ca8c4b859ef0a7710f40e0dd Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 16 Aug 2018 12:05:59 -0400 Subject: sunrpc: Extract target name into svc_cred NFSv4.0 callback needs to know the GSS target name the client used when it established its lease. That information is available from the GSS context created by gssproxy. Make it available in each svc_cred. Note this will also give us access to the real target service principal name (which is typically "nfs", but spec does not require that). Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svcauth.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 7c3656505847..04e404a07882 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -31,6 +31,7 @@ struct svc_cred { /* name of form servicetype@hostname, passed down by * rpc.svcgssd, or computed from the above: */ char *cr_principal; + char *cr_targ_princ; struct gss_api_mech *cr_gss_mech; }; @@ -39,6 +40,7 @@ static inline void init_svc_cred(struct svc_cred *cred) cred->cr_group_info = NULL; cred->cr_raw_principal = NULL; cred->cr_principal = NULL; + cred->cr_targ_princ = NULL; cred->cr_gss_mech = NULL; } @@ -48,6 +50,7 @@ static inline void free_svc_cred(struct svc_cred *cred) put_group_info(cred->cr_group_info); kfree(cred->cr_raw_principal); kfree(cred->cr_principal); + kfree(cred->cr_targ_princ); gss_mech_put(cred->cr_gss_mech); init_svc_cred(cred); } -- cgit v1.2.3 From 815f0ddb346c196018d4d8f8f55c12b83da1de3f Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Wed, 22 Aug 2018 16:37:24 -0700 Subject: include/linux/compiler*.h: make compiler-*.h mutually exclusive Commit cafa0010cd51 ("Raise the minimum required gcc version to 4.6") recently exposed a brittle part of the build for supporting non-gcc compilers. Both Clang and ICC define __GNUC__, __GNUC_MINOR__, and __GNUC_PATCHLEVEL__ for quick compatibility with code bases that haven't added compiler specific checks for __clang__ or __INTEL_COMPILER. This is brittle, as they happened to get compatibility by posing as a certain version of GCC. This broke when upgrading the minimal version of GCC required to build the kernel, to a version above what ICC and Clang claim to be. Rather than always including compiler-gcc.h then undefining or redefining macros in compiler-intel.h or compiler-clang.h, let's separate out the compiler specific macro definitions into mutually exclusive headers, do more proper compiler detection, and keep shared definitions in compiler_types.h. Fixes: cafa0010cd51 ("Raise the minimum required gcc version to 4.6") Reported-by: Masahiro Yamada Suggested-by: Eli Friedman Suggested-by: Joe Perches Signed-off-by: Nick Desaulniers Signed-off-by: Linus Torvalds --- include/linux/compiler-clang.h | 20 ++-- include/linux/compiler-gcc.h | 88 --------------- include/linux/compiler-intel.h | 13 +-- include/linux/compiler_types.h | 238 ++++++++++++++++++++--------------------- 4 files changed, 127 insertions(+), 232 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 7087446c24c8..b1ce500fe8b3 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -6,11 +6,7 @@ /* Some compiler specific definitions are overwritten here * for Clang compiler */ - -#ifdef uninitialized_var -#undef uninitialized_var #define uninitialized_var(x) x = *(&(x)) -#endif /* same as gcc, this was present in clang-2.6 so we can assume it works * with any version that can compile the kernel @@ -25,14 +21,8 @@ #define __SANITIZE_ADDRESS__ #endif -#undef __no_sanitize_address #define __no_sanitize_address __attribute__((no_sanitize("address"))) -/* Clang doesn't have a way to turn it off per-function, yet. */ -#ifdef __noretpoline -#undef __noretpoline -#endif - /* * Not all versions of clang implement the the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements @@ -40,9 +30,17 @@ * checks. Unfortunately, we don't know which version of gcc clang * pretends to be, so the macro may or may not be defined. */ -#undef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW #if __has_builtin(__builtin_mul_overflow) && \ __has_builtin(__builtin_add_overflow) && \ __has_builtin(__builtin_sub_overflow) #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif + +/* The following are for compatibility with GCC, from compiler-gcc.h, + * and may be redefined here because they should not be shared with other + * compilers, like ICC. + */ +#define barrier() __asm__ __volatile__("" : : : "memory") +#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) +#define __assume_aligned(a, ...) \ + __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 250b9b7cfd60..763bbad1e258 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -75,48 +75,6 @@ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) #endif -/* - * Feature detection for gnu_inline (gnu89 extern inline semantics). Either - * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics, - * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not - * defined so the gnu89 semantics are the default. - */ -#ifdef __GNUC_STDC_INLINE__ -# define __gnu_inline __attribute__((gnu_inline)) -#else -# define __gnu_inline -#endif - -/* - * Force always-inline if the user requests it so via the .config, - * or if gcc is too old. - * GCC does not warn about unused static inline functions for - * -Wunused-function. This turns out to avoid the need for complex #ifdef - * directives. Suppress the warning in clang as well by using "unused" - * function attribute, which is redundant but not harmful for gcc. - * Prefer gnu_inline, so that extern inline functions do not emit an - * externally visible function. This makes extern inline behave as per gnu89 - * semantics rather than c99. This prevents multiple symbol definition errors - * of extern inline functions at link time. - * A lot of inline functions can cause havoc with function tracing. - */ -#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ - !defined(CONFIG_OPTIMIZE_INLINING) -#define inline \ - inline __attribute__((always_inline, unused)) notrace __gnu_inline -#else -#define inline inline __attribute__((unused)) notrace __gnu_inline -#endif - -#define __inline__ inline -#define __inline inline -#define __always_inline inline __attribute__((always_inline)) -#define noinline __attribute__((noinline)) - -#define __packed __attribute__((packed)) -#define __weak __attribute__((weak)) -#define __alias(symbol) __attribute__((alias(#symbol))) - #ifdef RETPOLINE #define __noretpoline __attribute__((indirect_branch("keep"))) #endif @@ -135,55 +93,9 @@ */ #define __naked __attribute__((naked)) noinline __noclone notrace -#define __noreturn __attribute__((noreturn)) - -/* - * From the GCC manual: - * - * Many functions have no effects except the return value and their - * return value depends only on the parameters and/or global - * variables. Such a function can be subject to common subexpression - * elimination and loop optimization just as an arithmetic operator - * would be. - * [...] - */ -#define __pure __attribute__((pure)) -#define __aligned(x) __attribute__((aligned(x))) -#define __aligned_largest __attribute__((aligned)) -#define __printf(a, b) __attribute__((format(printf, a, b))) -#define __scanf(a, b) __attribute__((format(scanf, a, b))) -#define __attribute_const__ __attribute__((__const__)) -#define __maybe_unused __attribute__((unused)) -#define __always_unused __attribute__((unused)) -#define __mode(x) __attribute__((mode(x))) - -#define __must_check __attribute__((warn_unused_result)) -#define __malloc __attribute__((__malloc__)) - -#define __used __attribute__((__used__)) -#define __compiler_offsetof(a, b) \ - __builtin_offsetof(a, b) - -/* Mark functions as cold. gcc will assume any path leading to a call - * to them will be unlikely. This means a lot of manual unlikely()s - * are unnecessary now for any paths leading to the usual suspects - * like BUG(), printk(), panic() etc. [but let's keep them for now for - * older compilers] - * - * Early snapshots of gcc 4.3 don't support this and we can't detect this - * in the preprocessor, but we can live with this because they're unreleased. - * Maketime probing would be overkill here. - * - * gcc also has a __attribute__((__hot__)) to move hot functions into - * a special section, but I don't see any sense in this right now in - * the kernel context - */ -#define __cold __attribute__((__cold__)) - #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) #define __optimize(level) __attribute__((__optimize__(level))) -#define __nostackprotector __optimize("no-stack-protector") #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 547cdc920a3c..4c7f9befa9f6 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -14,10 +14,6 @@ /* Intel ECC compiler doesn't support gcc specific asm stmts. * It uses intrinsics to do the equivalent things. */ -#undef barrier -#undef barrier_data -#undef RELOC_HIDE -#undef OPTIMIZER_HIDE_VAR #define barrier() __memory_barrier() #define barrier_data(ptr) barrier() @@ -38,13 +34,12 @@ #endif -#ifndef __HAVE_BUILTIN_BSWAP16__ /* icc has this, but it's called _bswap16 */ #define __HAVE_BUILTIN_BSWAP16__ #define __builtin_bswap16 _bswap16 -#endif -/* - * icc defines __GNUC__, but does not implement the builtin overflow checkers. +/* The following are for compatibility with GCC, from compiler-gcc.h, + * and may be redefined here because they should not be shared with other + * compilers, like clang. */ -#undef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW +#define __visible __attribute__((externally_visible)) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index fbf337933fd8..90479a0f3986 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -54,32 +54,20 @@ extern void __chk_io_ptr(const volatile void __iomem *); #ifdef __KERNEL__ -#ifdef __GNUC__ -#include -#endif - -#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) -#define notrace __attribute__((hotpatch(0,0))) -#else -#define notrace __attribute__((no_instrument_function)) -#endif - -/* Intel compiler defines __GNUC__. So we will overwrite implementations - * coming from above header files here - */ -#ifdef __INTEL_COMPILER -# include -#endif - -/* Clang compiler defines __GNUC__. So we will overwrite implementations - * coming from above header files here - */ +/* Compiler specific macros. */ #ifdef __clang__ #include +#elif defined(__INTEL_COMPILER) +#include +#elif defined(__GNUC__) +/* The above compilers also define __GNUC__, so order is important here. */ +#include +#else +#error "Unknown compiler" #endif /* - * Generic compiler-dependent macros required for kernel + * Generic compiler-independent macros required for kernel * build go below this comment. Actual compiler/compiler version * specific implementations come from the above header files */ @@ -106,93 +94,19 @@ struct ftrace_likely_data { unsigned long constant; }; -#endif /* __KERNEL__ */ - -#endif /* __ASSEMBLY__ */ - -#ifdef __KERNEL__ - /* Don't. Just don't. */ #define __deprecated #define __deprecated_for_modules -#ifndef __must_check -#define __must_check -#endif - -#ifndef CONFIG_ENABLE_MUST_CHECK -#undef __must_check -#define __must_check -#endif - -#ifndef __malloc -#define __malloc -#endif - -/* - * Allow us to avoid 'defined but not used' warnings on functions and data, - * as well as force them to be emitted to the assembly file. - * - * As of gcc 3.4, static functions that are not marked with attribute((used)) - * may be elided from the assembly file. As of gcc 3.4, static data not so - * marked will not be elided, but this may change in a future gcc version. - * - * NOTE: Because distributions shipped with a backported unit-at-a-time - * compiler in gcc 3.3, we must define __used to be __attribute__((used)) - * for gcc >=3.3 instead of 3.4. - * - * In prior versions of gcc, such functions and data would be emitted, but - * would be warned about except with attribute((unused)). - * - * Mark functions that are referenced only in inline assembly as __used so - * the code is emitted even though it appears to be unreferenced. - */ -#ifndef __used -# define __used /* unimplemented */ -#endif - -#ifndef __maybe_unused -# define __maybe_unused /* unimplemented */ -#endif - -#ifndef __always_unused -# define __always_unused /* unimplemented */ -#endif - -#ifndef noinline -#define noinline -#endif - -/* - * Rather then using noinline to prevent stack consumption, use - * noinline_for_stack instead. For documentation reasons. - */ -#define noinline_for_stack noinline - -#ifndef __always_inline -#define __always_inline inline -#endif - #endif /* __KERNEL__ */ +#endif /* __ASSEMBLY__ */ + /* - * From the GCC manual: - * - * Many functions do not examine any values except their arguments, - * and have no effects except the return value. Basically this is - * just slightly more strict class than the `pure' attribute above, - * since function is not allowed to read global memory. - * - * Note that a function that has pointer arguments and examines the - * data pointed to must _not_ be declared `const'. Likewise, a - * function that calls a non-`const' function usually must not be - * `const'. It does not make sense for a `const' function to return - * `void'. + * The below symbols may be defined for one or more, but not ALL, of the above + * compilers. We don't consider that to be an error, so set them to nothing. + * For example, some of them are for compiler specific plugins. */ -#ifndef __attribute_const__ -# define __attribute_const__ /* unimplemented */ -#endif - #ifndef __designated_init # define __designated_init #endif @@ -214,28 +128,10 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif -/* - * Tell gcc if a function is cold. The compiler will assume any path - * directly leading to the call is unlikely. - */ - -#ifndef __cold -#define __cold -#endif - -/* Simple shorthand for a section definition */ -#ifndef __section -# define __section(S) __attribute__ ((__section__(#S))) -#endif - #ifndef __visible #define __visible #endif -#ifndef __nostackprotector -# define __nostackprotector -#endif - /* * Assume alignment of return value. */ @@ -243,17 +139,23 @@ struct ftrace_likely_data { #define __assume_aligned(a, ...) #endif - /* Are two types/vars the same type (ignoring qualifiers)? */ -#ifndef __same_type -# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) -#endif +#define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) /* Is this type a native word size -- useful for atomic operations */ -#ifndef __native_word -# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) +#define __native_word(t) \ + (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ + sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) + +#ifndef __attribute_const__ +#define __attribute_const__ __attribute__((__const__)) #endif +#ifndef __noclone +#define __noclone +#endif + +/* Helpers for emitting diagnostics in pragmas. */ #ifndef __diag #define __diag(string) #endif @@ -272,4 +174,92 @@ struct ftrace_likely_data { #define __diag_error(compiler, version, option, comment) \ __diag_ ## compiler(version, error, option) +/* + * From the GCC manual: + * + * Many functions have no effects except the return value and their + * return value depends only on the parameters and/or global + * variables. Such a function can be subject to common subexpression + * elimination and loop optimization just as an arithmetic operator + * would be. + * [...] + */ +#define __pure __attribute__((pure)) +#define __aligned(x) __attribute__((aligned(x))) +#define __aligned_largest __attribute__((aligned)) +#define __printf(a, b) __attribute__((format(printf, a, b))) +#define __scanf(a, b) __attribute__((format(scanf, a, b))) +#define __maybe_unused __attribute__((unused)) +#define __always_unused __attribute__((unused)) +#define __mode(x) __attribute__((mode(x))) +#define __malloc __attribute__((__malloc__)) +#define __used __attribute__((__used__)) +#define __noreturn __attribute__((noreturn)) +#define __packed __attribute__((packed)) +#define __weak __attribute__((weak)) +#define __alias(symbol) __attribute__((alias(#symbol))) +#define __cold __attribute__((cold)) +#define __section(S) __attribute__((__section__(#S))) + + +#ifdef CONFIG_ENABLE_MUST_CHECK +#define __must_check __attribute__((warn_unused_result)) +#else +#define __must_check +#endif + +#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) +#define notrace __attribute__((hotpatch(0, 0))) +#else +#define notrace __attribute__((no_instrument_function)) +#endif + +#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) + +/* + * Feature detection for gnu_inline (gnu89 extern inline semantics). Either + * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics, + * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not + * defined so the gnu89 semantics are the default. + */ +#ifdef __GNUC_STDC_INLINE__ +# define __gnu_inline __attribute__((gnu_inline)) +#else +# define __gnu_inline +#endif + +/* + * Force always-inline if the user requests it so via the .config. + * GCC does not warn about unused static inline functions for + * -Wunused-function. This turns out to avoid the need for complex #ifdef + * directives. Suppress the warning in clang as well by using "unused" + * function attribute, which is redundant but not harmful for gcc. + * Prefer gnu_inline, so that extern inline functions do not emit an + * externally visible function. This makes extern inline behave as per gnu89 + * semantics rather than c99. This prevents multiple symbol definition errors + * of extern inline functions at link time. + * A lot of inline functions can cause havoc with function tracing. + */ +#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ + !defined(CONFIG_OPTIMIZE_INLINING) +#define inline \ + inline __attribute__((always_inline, unused)) notrace __gnu_inline +#else +#define inline inline __attribute__((unused)) notrace __gnu_inline +#endif + +#define __inline__ inline +#define __inline inline +#define noinline __attribute__((noinline)) + +#ifndef __always_inline +#define __always_inline inline __attribute__((always_inline)) +#endif + +/* + * Rather then using noinline to prevent stack consumption, use + * noinline_for_stack instead. For documentation reasons. + */ +#define noinline_for_stack noinline + #endif /* __LINUX_COMPILER_TYPES_H */ -- cgit v1.2.3 From 30aba6656f61ed44cba445a3c0d38b296fa9e8f5 Mon Sep 17 00:00:00 2001 From: Salvatore Mesoraca Date: Thu, 23 Aug 2018 17:00:35 -0700 Subject: namei: allow restricted O_CREAT of FIFOs and regular files Disallows open of FIFOs or regular files not owned by the user in world writable sticky directories, unless the owner is the same as that of the directory or the file is opened without the O_CREAT flag. The purpose is to make data spoofing attacks harder. This protection can be turned on and off separately for FIFOs and regular files via sysctl, just like the symlinks/hardlinks protection. This patch is based on Openwall's "HARDEN_FIFO" feature by Solar Designer. This is a brief list of old vulnerabilities that could have been prevented by this feature, some of them even allow for privilege escalation: CVE-2000-1134 CVE-2007-3852 CVE-2008-0525 CVE-2009-0416 CVE-2011-4834 CVE-2015-1838 CVE-2015-7442 CVE-2016-7489 This list is not meant to be complete. It's difficult to track down all vulnerabilities of this kind because they were often reported without any mention of this particular attack vector. In fact, before hardlinks/symlinks restrictions, fifos/regular files weren't the favorite vehicle to exploit them. [s.mesoraca16@gmail.com: fix bug reported by Dan Carpenter] Link: https://lkml.kernel.org/r/20180426081456.GA7060@mwanda Link: http://lkml.kernel.org/r/1524829819-11275-1-git-send-email-s.mesoraca16@gmail.com [keescook@chromium.org: drop pr_warn_ratelimited() in favor of audit changes in the future] [keescook@chromium.org: adjust commit subjet] Link: http://lkml.kernel.org/r/20180416175918.GA13494@beast Signed-off-by: Salvatore Mesoraca Signed-off-by: Kees Cook Suggested-by: Solar Designer Suggested-by: Kees Cook Cc: Al Viro Cc: Dan Carpenter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e5710541183b..33322702c910 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -74,6 +74,8 @@ extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; extern int sysctl_protected_hardlinks; +extern int sysctl_protected_fifos; +extern int sysctl_protected_regular; typedef __kernel_rwf_t rwf_t; -- cgit v1.2.3 From d4ae9916ea2947341180d2b538f48875ff393a86 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 23 Aug 2018 17:00:42 -0700 Subject: mm: soft-offline: close the race against page allocation A process can be killed with SIGBUS(BUS_MCEERR_AR) when it tries to allocate a page that was just freed on the way of soft-offline. This is undesirable because soft-offline (which is about corrected error) is less aggressive than hard-offline (which is about uncorrected error), and we can make soft-offline fail and keep using the page for good reason like "system is busy." Two main changes of this patch are: - setting migrate type of the target page to MIGRATE_ISOLATE. As done in free_unref_page_commit(), this makes kernel bypass pcplist when freeing the page. So we can assume that the page is in freelist just after put_page() returns, - setting PG_hwpoison on free page under zone->lock which protects freelists, so this allows us to avoid setting PG_hwpoison on a page that is decided to be allocated soon. [akpm@linux-foundation.org: tweak set_hwpoison_free_buddy_page() comment] Link: http://lkml.kernel.org/r/1531452366-11661-3-git-send-email-n-horiguchi@ah.jp.nec.com Signed-off-by: Naoya Horiguchi Reported-by: Xishi Qiu Tested-by: Mike Kravetz Cc: Michal Hocko Cc: Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 5 +++++ include/linux/swapops.h | 10 ---------- 2 files changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 901943e4754b..74bee8cecf4c 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -369,8 +369,13 @@ PAGEFLAG_FALSE(Uncached) PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) +extern bool set_hwpoison_free_buddy_page(struct page *page); #else PAGEFLAG_FALSE(HWPoison) +static inline bool set_hwpoison_free_buddy_page(struct page *page) +{ + return 0; +} #define __PG_HWPOISON 0 #endif diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 1d3877c39a00..568a3553d918 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -340,11 +340,6 @@ static inline int is_hwpoison_entry(swp_entry_t entry) return swp_type(entry) == SWP_HWPOISON; } -static inline bool test_set_page_hwpoison(struct page *page) -{ - return TestSetPageHWPoison(page); -} - static inline void num_poisoned_pages_inc(void) { atomic_long_inc(&num_poisoned_pages); @@ -367,11 +362,6 @@ static inline int is_hwpoison_entry(swp_entry_t swp) return 0; } -static inline bool test_set_page_hwpoison(struct page *page) -{ - return false; -} - static inline void num_poisoned_pages_inc(void) { } -- cgit v1.2.3 From 263fade51f7bdd5ad7ebbfe82113a44c5ea4c36c Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 23 Aug 2018 17:01:15 -0700 Subject: docs/mm: make GFP flags descriptions usable as kernel-doc This patch adds DOC: headings for GFP flag descriptions and adjusts the formatting to fit sphinx expectations of paragraphs. Link: http://lkml.kernel.org/r/1532626360-16650-7-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Reviewed-by: Andrew Morton Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 291 +++++++++++++++++++++++++++------------------------- 1 file changed, 154 insertions(+), 137 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index a6afcec53795..24bcc5eec6b4 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -59,29 +59,32 @@ struct vm_area_struct; #define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ #define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) -/* +/** + * DOC: Page mobility and placement hints + * * Page mobility and placement hints + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * These flags provide hints about how mobile the page is. Pages with similar * mobility are placed within the same pageblocks to minimise problems due * to external fragmentation. * - * __GFP_MOVABLE (also a zone modifier) indicates that the page can be - * moved by page migration during memory compaction or can be reclaimed. + * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be + * moved by page migration during memory compaction or can be reclaimed. * - * __GFP_RECLAIMABLE is used for slab allocations that specify - * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. + * %__GFP_RECLAIMABLE is used for slab allocations that specify + * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. * - * __GFP_WRITE indicates the caller intends to dirty the page. Where possible, - * these pages will be spread between local zones to avoid all the dirty - * pages being in one zone (fair zone allocation policy). + * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible, + * these pages will be spread between local zones to avoid all the dirty + * pages being in one zone (fair zone allocation policy). * - * __GFP_HARDWALL enforces the cpuset memory allocation policy. + * %__GFP_HARDWALL enforces the cpuset memory allocation policy. * - * __GFP_THISNODE forces the allocation to be satisified from the requested - * node with no fallbacks or placement policy enforcements. + * %__GFP_THISNODE forces the allocation to be satisified from the requested + * node with no fallbacks or placement policy enforcements. * - * __GFP_ACCOUNT causes the allocation to be accounted to kmemcg. + * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) @@ -89,54 +92,60 @@ struct vm_area_struct; #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) #define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) -/* +/** + * DOC: Watermark modifiers + * * Watermark modifiers -- controls access to emergency reserves + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * - * __GFP_HIGH indicates that the caller is high-priority and that granting - * the request is necessary before the system can make forward progress. - * For example, creating an IO context to clean pages. + * %__GFP_HIGH indicates that the caller is high-priority and that granting + * the request is necessary before the system can make forward progress. + * For example, creating an IO context to clean pages. * - * __GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is - * high priority. Users are typically interrupt handlers. This may be - * used in conjunction with __GFP_HIGH + * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is + * high priority. Users are typically interrupt handlers. This may be + * used in conjunction with %__GFP_HIGH * - * __GFP_MEMALLOC allows access to all memory. This should only be used when - * the caller guarantees the allocation will allow more memory to be freed - * very shortly e.g. process exiting or swapping. Users either should - * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). + * %__GFP_MEMALLOC allows access to all memory. This should only be used when + * the caller guarantees the allocation will allow more memory to be freed + * very shortly e.g. process exiting or swapping. Users either should + * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). * - * __GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. - * This takes precedence over the __GFP_MEMALLOC flag if both are set. + * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. + * This takes precedence over the %__GFP_MEMALLOC flag if both are set. */ #define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) #define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) #define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) #define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) -/* +/** + * DOC: Reclaim modifiers + * * Reclaim modifiers + * ~~~~~~~~~~~~~~~~~ * - * __GFP_IO can start physical IO. + * %__GFP_IO can start physical IO. * - * __GFP_FS can call down to the low-level FS. Clearing the flag avoids the - * allocator recursing into the filesystem which might already be holding - * locks. + * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the + * allocator recursing into the filesystem which might already be holding + * locks. * - * __GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. - * This flag can be cleared to avoid unnecessary delays when a fallback - * option is available. + * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. + * This flag can be cleared to avoid unnecessary delays when a fallback + * option is available. * - * __GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when - * the low watermark is reached and have it reclaim pages until the high - * watermark is reached. A caller may wish to clear this flag when fallback - * options are available and the reclaim is likely to disrupt the system. The - * canonical example is THP allocation where a fallback is cheap but - * reclaim/compaction may cause indirect stalls. + * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when + * the low watermark is reached and have it reclaim pages until the high + * watermark is reached. A caller may wish to clear this flag when fallback + * options are available and the reclaim is likely to disrupt the system. The + * canonical example is THP allocation where a fallback is cheap but + * reclaim/compaction may cause indirect stalls. * - * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. + * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. * * The default allocator behavior depends on the request size. We have a concept - * of so called costly allocations (with order > PAGE_ALLOC_COSTLY_ORDER). + * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER). * !costly allocations are too essential to fail so they are implicitly * non-failing by default (with some exceptions like OOM victims might fail so * the caller still has to check for failures) while costly requests try to be @@ -144,40 +153,40 @@ struct vm_area_struct; * The following three modifiers might be used to override some of these * implicit rules * - * __GFP_NORETRY: The VM implementation will try only very lightweight - * memory direct reclaim to get some memory under memory pressure (thus - * it can sleep). It will avoid disruptive actions like OOM killer. The - * caller must handle the failure which is quite likely to happen under - * heavy memory pressure. The flag is suitable when failure can easily be - * handled at small cost, such as reduced throughput - * - * __GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim - * procedures that have previously failed if there is some indication - * that progress has been made else where. It can wait for other - * tasks to attempt high level approaches to freeing memory such as - * compaction (which removes fragmentation) and page-out. - * There is still a definite limit to the number of retries, but it is - * a larger limit than with __GFP_NORETRY. - * Allocations with this flag may fail, but only when there is - * genuinely little unused memory. While these allocations do not - * directly trigger the OOM killer, their failure indicates that - * the system is likely to need to use the OOM killer soon. The - * caller must handle failure, but can reasonably do so by failing - * a higher-level request, or completing it only in a much less - * efficient manner. - * If the allocation does fail, and the caller is in a position to - * free some non-essential memory, doing so could benefit the system - * as a whole. - * - * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller - * cannot handle allocation failures. The allocation could block - * indefinitely but will never return with failure. Testing for - * failure is pointless. - * New users should be evaluated carefully (and the flag should be - * used only when there is no reasonable failure policy) but it is - * definitely preferable to use the flag rather than opencode endless - * loop around allocator. - * Using this flag for costly allocations is _highly_ discouraged. + * %__GFP_NORETRY: The VM implementation will try only very lightweight + * memory direct reclaim to get some memory under memory pressure (thus + * it can sleep). It will avoid disruptive actions like OOM killer. The + * caller must handle the failure which is quite likely to happen under + * heavy memory pressure. The flag is suitable when failure can easily be + * handled at small cost, such as reduced throughput + * + * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim + * procedures that have previously failed if there is some indication + * that progress has been made else where. It can wait for other + * tasks to attempt high level approaches to freeing memory such as + * compaction (which removes fragmentation) and page-out. + * There is still a definite limit to the number of retries, but it is + * a larger limit than with %__GFP_NORETRY. + * Allocations with this flag may fail, but only when there is + * genuinely little unused memory. While these allocations do not + * directly trigger the OOM killer, their failure indicates that + * the system is likely to need to use the OOM killer soon. The + * caller must handle failure, but can reasonably do so by failing + * a higher-level request, or completing it only in a much less + * efficient manner. + * If the allocation does fail, and the caller is in a position to + * free some non-essential memory, doing so could benefit the system + * as a whole. + * + * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller + * cannot handle allocation failures. The allocation could block + * indefinitely but will never return with failure. Testing for + * failure is pointless. + * New users should be evaluated carefully (and the flag should be + * used only when there is no reasonable failure policy) but it is + * definitely preferable to use the flag rather than opencode endless + * loop around allocator. + * Using this flag for costly allocations is _highly_ discouraged. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) @@ -188,14 +197,17 @@ struct vm_area_struct; #define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) #define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) -/* +/** + * DOC: Action modifiers + * * Action modifiers + * ~~~~~~~~~~~~~~~~ * - * __GFP_NOWARN suppresses allocation failure reports. + * %__GFP_NOWARN suppresses allocation failure reports. * - * __GFP_COMP address compound page metadata. + * %__GFP_COMP address compound page metadata. * - * __GFP_ZERO returns a zeroed page on success. + * %__GFP_ZERO returns a zeroed page on success. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) @@ -208,66 +220,71 @@ struct vm_area_struct; #define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) -/* +/** + * DOC: Useful GFP flag combinations + * + * Useful GFP flag combinations + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * * Useful GFP flag combinations that are commonly used. It is recommended * that subsystems start with one of these combinations and then set/clear - * __GFP_FOO flags as necessary. - * - * GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower - * watermark is applied to allow access to "atomic reserves" - * - * GFP_KERNEL is typical for kernel-internal allocations. The caller requires - * ZONE_NORMAL or a lower zone for direct access but can direct reclaim. - * - * GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is - * accounted to kmemcg. - * - * GFP_NOWAIT is for kernel allocations that should not stall for direct - * reclaim, start physical IO or use any filesystem callback. - * - * GFP_NOIO will use direct reclaim to discard clean pages or slab pages - * that do not require the starting of any physical IO. - * Please try to avoid using this flag directly and instead use - * memalloc_noio_{save,restore} to mark the whole scope which cannot - * perform any IO with a short explanation why. All allocation requests - * will inherit GFP_NOIO implicitly. - * - * GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. - * Please try to avoid using this flag directly and instead use - * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't - * recurse into the FS layer with a short explanation why. All allocation - * requests will inherit GFP_NOFS implicitly. - * - * GFP_USER is for userspace allocations that also need to be directly - * accessibly by the kernel or hardware. It is typically used by hardware - * for buffers that are mapped to userspace (e.g. graphics) that hardware - * still must DMA to. cpuset limits are enforced for these allocations. - * - * GFP_DMA exists for historical reasons and should be avoided where possible. - * The flags indicates that the caller requires that the lowest zone be - * used (ZONE_DMA or 16M on x86-64). Ideally, this would be removed but - * it would require careful auditing as some users really require it and - * others use the flag to avoid lowmem reserves in ZONE_DMA and treat the - * lowest zone as a type of emergency reserve. - * - * GFP_DMA32 is similar to GFP_DMA except that the caller requires a 32-bit - * address. - * - * GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, - * do not need to be directly accessible by the kernel but that cannot - * move once in use. An example may be a hardware allocation that maps - * data directly into userspace but has no addressing limitations. - * - * GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not - * need direct access to but can use kmap() when access is required. They - * are expected to be movable via page reclaim or page migration. Typically, - * pages on the LRU would also be allocated with GFP_HIGHUSER_MOVABLE. - * - * GFP_TRANSHUGE and GFP_TRANSHUGE_LIGHT are used for THP allocations. They are - * compound allocations that will generally fail quickly if memory is not - * available and will not wake kswapd/kcompactd on failure. The _LIGHT - * version does not attempt reclaim/compaction at all and is by default used - * in page fault path, while the non-light is used by khugepaged. + * %__GFP_FOO flags as necessary. + * + * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower + * watermark is applied to allow access to "atomic reserves" + * + * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires + * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. + * + * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is + * accounted to kmemcg. + * + * %GFP_NOWAIT is for kernel allocations that should not stall for direct + * reclaim, start physical IO or use any filesystem callback. + * + * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages + * that do not require the starting of any physical IO. + * Please try to avoid using this flag directly and instead use + * memalloc_noio_{save,restore} to mark the whole scope which cannot + * perform any IO with a short explanation why. All allocation requests + * will inherit GFP_NOIO implicitly. + * + * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. + * Please try to avoid using this flag directly and instead use + * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't + * recurse into the FS layer with a short explanation why. All allocation + * requests will inherit GFP_NOFS implicitly. + * + * %GFP_USER is for userspace allocations that also need to be directly + * accessibly by the kernel or hardware. It is typically used by hardware + * for buffers that are mapped to userspace (e.g. graphics) that hardware + * still must DMA to. cpuset limits are enforced for these allocations. + * + * %GFP_DMA exists for historical reasons and should be avoided where possible. + * The flags indicates that the caller requires that the lowest zone be + * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but + * it would require careful auditing as some users really require it and + * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the + * lowest zone as a type of emergency reserve. + * + * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit + * address. + * + * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, + * do not need to be directly accessible by the kernel but that cannot + * move once in use. An example may be a hardware allocation that maps + * data directly into userspace but has no addressing limitations. + * + * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not + * need direct access to but can use kmap() when access is required. They + * are expected to be movable via page reclaim or page migration. Typically, + * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE. + * + * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They + * are compound allocations that will generally fail quickly if memory is not + * available and will not wake kswapd/kcompactd on failure. The _LIGHT + * version does not attempt reclaim/compaction at all and is by default used + * in page fault path, while the non-light is used by khugepaged. */ #define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) -- cgit v1.2.3 From 2b7403035459c75e193c6b04a293e518a4212de0 Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Thu, 23 Aug 2018 17:01:36 -0700 Subject: mm: Change return type int to vm_fault_t for fault handlers Use new return type vm_fault_t for fault handler. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. Ref-> commit 1c8f422059ae ("mm: change return type to vm_fault_t") The aim is to change the return type of finish_fault() and handle_mm_fault() to vm_fault_t type. As part of that clean up return type of all other recursively called functions have been changed to vm_fault_t type. The places from where handle_mm_fault() is getting invoked will be change to vm_fault_t type but in a separate patch. vmf_error() is the newly introduce inline function in 4.17-rc6. [akpm@linux-foundation.org: don't shadow outer local `ret' in __do_huge_pmd_anonymous_page()] Link: http://lkml.kernel.org/r/20180604171727.GA20279@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 9 +++++---- include/linux/hugetlb.h | 2 +- include/linux/mm.h | 14 +++++++------- include/linux/oom.h | 2 +- include/linux/swapops.h | 5 +++-- include/linux/userfaultfd_k.h | 5 +++-- 6 files changed, 20 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index a8a126259bc4..27e3e32135a8 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -6,7 +6,7 @@ #include /* only for vma_is_dax() */ -extern int do_huge_pmd_anonymous_page(struct vm_fault *vmf); +extern vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *vma); @@ -23,7 +23,7 @@ static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) } #endif -extern int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); +extern vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, @@ -216,7 +216,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags); -extern int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); +extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *huge_zero_page; @@ -321,7 +321,8 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, return NULL; } -static inline int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd) +static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, + pmd_t orig_pmd) { return 0; } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c39d9170a8a0..6b68e345f0ca 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -105,7 +105,7 @@ void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(int, char *); void hugetlb_show_meminfo(void); unsigned long hugetlb_total_pages(void); -int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, +vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, struct vm_area_struct *dst_vma, diff --git a/include/linux/mm.h b/include/linux/mm.h index a9e733b5fb76..8fcc36660de6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -728,10 +728,10 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, +vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, struct page *page); -int finish_fault(struct vm_fault *vmf); -int finish_mkwrite_fault(struct vm_fault *vmf); +vm_fault_t finish_fault(struct vm_fault *vmf); +vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif /* @@ -1403,8 +1403,8 @@ int generic_error_remove_page(struct address_space *mapping, struct page *page); int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU -extern int handle_mm_fault(struct vm_area_struct *vma, unsigned long address, - unsigned int flags); +extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, + unsigned long address, unsigned int flags); extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); @@ -1413,7 +1413,7 @@ void unmap_mapping_pages(struct address_space *mapping, void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); #else -static inline int handle_mm_fault(struct vm_area_struct *vma, +static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { /* should never happen if there's no MMU */ @@ -2563,7 +2563,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ -static inline int vm_fault_to_errno(int vm_fault, int foll_flags) +static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { if (vm_fault & VM_FAULT_OOM) return -ENOMEM; diff --git a/include/linux/oom.h b/include/linux/oom.h index 92f70e4c6252..69864a547663 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -88,7 +88,7 @@ static inline bool mm_is_oom_victim(struct mm_struct *mm) * * Return 0 when the PF is safe VM_FAULT_SIGBUS otherwise. */ -static inline int check_stable_address_space(struct mm_struct *mm) +static inline vm_fault_t check_stable_address_space(struct mm_struct *mm) { if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags))) return VM_FAULT_SIGBUS; diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 568a3553d918..22af9d8a84ae 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -4,6 +4,7 @@ #include #include +#include /* * swapcache pages are stored in the swapper_space radix tree. We want to @@ -134,7 +135,7 @@ static inline struct page *device_private_entry_to_page(swp_entry_t entry) return pfn_to_page(swp_offset(entry)); } -int device_private_entry_fault(struct vm_area_struct *vma, +vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, unsigned long addr, swp_entry_t entry, unsigned int flags, @@ -169,7 +170,7 @@ static inline struct page *device_private_entry_to_page(swp_entry_t entry) return NULL; } -static inline int device_private_entry_fault(struct vm_area_struct *vma, +static inline vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, unsigned long addr, swp_entry_t entry, unsigned int flags, diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index e091f0a11b11..37c9eba75c98 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -28,7 +28,7 @@ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) -extern int handle_userfault(struct vm_fault *vmf, unsigned long reason); +extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, @@ -77,7 +77,8 @@ extern void userfaultfd_unmap_complete(struct mm_struct *mm, #else /* CONFIG_USERFAULTFD */ /* mm helpers */ -static inline int handle_userfault(struct vm_fault *vmf, unsigned long reason) +static inline vm_fault_t handle_userfault(struct vm_fault *vmf, + unsigned long reason) { return VM_FAULT_SIGBUS; } -- cgit v1.2.3 From 25559c22cef879c5cf7119540bfe21fb379d29f3 Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Mon, 9 Jul 2018 08:15:49 +0200 Subject: tee: add kernel internal client interface Adds a kernel internal TEE client interface to be used by other drivers. Reviewed-by: Sumit Garg Tested-by: Sumit Garg Tested-by: Zeng Tao Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 73 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index a2b3dfcee0b5..6cfe05893a76 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -453,6 +453,79 @@ static inline int tee_shm_get_id(struct tee_shm *shm) */ struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); +/** + * tee_client_open_context() - Open a TEE context + * @start: if not NULL, continue search after this context + * @match: function to check TEE device + * @data: data for match function + * @vers: if not NULL, version data of TEE device of the context returned + * + * This function does an operation similar to open("/dev/teeX") in user space. + * A returned context must be released with tee_client_close_context(). + * + * Returns a TEE context of the first TEE device matched by the match() + * callback or an ERR_PTR. + */ +struct tee_context * +tee_client_open_context(struct tee_context *start, + int (*match)(struct tee_ioctl_version_data *, + const void *), + const void *data, struct tee_ioctl_version_data *vers); + +/** + * tee_client_close_context() - Close a TEE context + * @ctx: TEE context to close + * + * Note that all sessions previously opened with this context will be + * closed when this function is called. + */ +void tee_client_close_context(struct tee_context *ctx); + +/** + * tee_client_get_version() - Query version of TEE + * @ctx: TEE context to TEE to query + * @vers: Pointer to version data + */ +void tee_client_get_version(struct tee_context *ctx, + struct tee_ioctl_version_data *vers); + +/** + * tee_client_open_session() - Open a session to a Trusted Application + * @ctx: TEE context + * @arg: Open session arguments, see description of + * struct tee_ioctl_open_session_arg + * @param: Parameters passed to the Trusted Application + * + * Returns < 0 on error else see @arg->ret for result. If @arg->ret + * is TEEC_SUCCESS the session identifier is available in @arg->session. + */ +int tee_client_open_session(struct tee_context *ctx, + struct tee_ioctl_open_session_arg *arg, + struct tee_param *param); + +/** + * tee_client_close_session() - Close a session to a Trusted Application + * @ctx: TEE Context + * @session: Session id + * + * Return < 0 on error else 0, regardless the session will not be + * valid after this function has returned. + */ +int tee_client_close_session(struct tee_context *ctx, u32 session); + +/** + * tee_client_invoke_func() - Invoke a function in a Trusted Application + * @ctx: TEE Context + * @arg: Invoke arguments, see description of + * struct tee_ioctl_invoke_arg + * @param: Parameters passed to the Trusted Application + * + * Returns < 0 on error else see @arg->ret for result. + */ +int tee_client_invoke_func(struct tee_context *ctx, + struct tee_ioctl_invoke_arg *arg, + struct tee_param *param); + static inline bool tee_param_is_memref(struct tee_param *param) { switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) { -- cgit v1.2.3 From 0c36dd37d5b80b43f4e3dc5a1dbfe6dbd86e8f2a Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 21 Aug 2018 17:02:40 +0200 Subject: i2c: remove deprecated attach_adapter callback There aren't any users left. Remove this callback from the 2.4 times. Phew, finally, that took years to reach... Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 36f357ecdf67..b79387fd57da 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -231,7 +231,6 @@ enum i2c_alert_protocol { /** * struct i2c_driver - represent an I2C device driver * @class: What kind of i2c device we instantiate (for detect) - * @attach_adapter: Callback for bus addition (deprecated) * @probe: Callback for device binding - soon to be deprecated * @probe_new: New callback for device binding * @remove: Callback for device unbinding @@ -268,11 +267,6 @@ enum i2c_alert_protocol { struct i2c_driver { unsigned int class; - /* Notifies the driver that a new bus has appeared. You should avoid - * using this, it will be removed in a near future. - */ - int (*attach_adapter)(struct i2c_adapter *) __deprecated; - /* Standard driver model interfaces */ int (*probe)(struct i2c_client *, const struct i2c_device_id *); int (*remove)(struct i2c_client *); -- cgit v1.2.3 From 5d3a01a228c703dad971cad11f14c0512c4c2713 Mon Sep 17 00:00:00 2001 From: Peter Korsgaard Date: Wed, 22 Aug 2018 18:16:07 +0200 Subject: i2c: ocores: update my email address The old @sunsite.dk address is no longer active, so update the references. Signed-off-by: Peter Korsgaard Signed-off-by: Wolfram Sang --- include/linux/platform_data/i2c-ocores.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/i2c-ocores.h b/include/linux/platform_data/i2c-ocores.h index 01edd96fe1f7..113d6b12f650 100644 --- a/include/linux/platform_data/i2c-ocores.h +++ b/include/linux/platform_data/i2c-ocores.h @@ -1,7 +1,7 @@ /* * i2c-ocores.h - definitions for the i2c-ocores interface * - * Peter Korsgaard + * Peter Korsgaard * * This file is licensed under the terms of the GNU General Public License * version 2. This program is licensed "as is" without any warranty of any -- cgit v1.2.3 From 3ad867001c91657c46dcf6656d52eb6080286fd5 Mon Sep 17 00:00:00 2001 From: Lothar Felten Date: Tue, 14 Aug 2018 09:09:37 +0200 Subject: hwmon: (ina2xx) fix sysfs shunt resistor read access fix the sysfs shunt resistor read access: return the shunt resistor value, not the calibration register contents. update email address Signed-off-by: Lothar Felten Signed-off-by: Guenter Roeck --- include/linux/platform_data/ina2xx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ina2xx.h b/include/linux/platform_data/ina2xx.h index 9abc0ca7259b..9f0aa1b48c78 100644 --- a/include/linux/platform_data/ina2xx.h +++ b/include/linux/platform_data/ina2xx.h @@ -1,7 +1,7 @@ /* * Driver for Texas Instruments INA219, INA226 power monitor chips * - * Copyright (C) 2012 Lothar Felten + * Copyright (C) 2012 Lothar Felten * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as -- cgit v1.2.3 From 0c4a1049cf298721eaec4553d3d5039798086e12 Mon Sep 17 00:00:00 2001 From: Sanyog Kale Date: Fri, 27 Jul 2018 14:44:13 +0530 Subject: soundwire: Add support to lock across bus instances Currently, the stream concept is limited to single Master and one or more Codecs. This patch extends the concept to support multiple Master(s) sharing the same reference clock and synchronized in the hardware. Modify sdw_stream_runtime to support a list of sdw_master_runtime for the same. The existing reference to a single m_rt is removed in the next patch. Typically to lock, one would acquire a global lock and then lock bus instances. In this case, the caller framework(ASoC DPCM) guarantees that stream operations on a card are always serialized. So, there is no race condition and hence no need for global lock. Bus lock(s) are acquired to reconfigure the bus while the stream is set-up. So, we add sdw_acquire_bus_lock()/sdw_release_bus_lock() APIs which are used only to reconfigure the bus. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 962971e6a9c7..ccd8dcdf06ab 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -769,6 +769,9 @@ struct sdw_stream_params { * @state: Current state of the stream * @type: Stream type PCM or PDM * @m_rt: Master runtime + * @master_list: List of Master runtime(s) in this stream. + * master_list can contain only one m_rt per Master instance + * for a stream */ struct sdw_stream_runtime { char *name; @@ -776,6 +779,7 @@ struct sdw_stream_runtime { enum sdw_stream_state state; enum sdw_stream_type type; struct sdw_master_runtime *m_rt; + struct list_head master_list; }; struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name); -- cgit v1.2.3 From 48949722ced4daacfa32f13c221f173b87231ead Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Fri, 27 Jul 2018 14:44:14 +0530 Subject: soundwire: Handle multiple master instances in a stream For each SoundWire stream operation, we need to parse master list and operate upon all master runtime. This is a preparatory patch to do the boilerplate conversion of stream handling from single master runtime to handle a list of master runtime. The code to support bank switch for multiple master instances is added in the next patch. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index ccd8dcdf06ab..03df709fb8ef 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -768,7 +768,6 @@ struct sdw_stream_params { * @params: Stream parameters * @state: Current state of the stream * @type: Stream type PCM or PDM - * @m_rt: Master runtime * @master_list: List of Master runtime(s) in this stream. * master_list can contain only one m_rt per Master instance * for a stream @@ -778,7 +777,6 @@ struct sdw_stream_runtime { struct sdw_stream_params params; enum sdw_stream_state state; enum sdw_stream_type type; - struct sdw_master_runtime *m_rt; struct list_head master_list; }; -- cgit v1.2.3 From ce6e74d008ff5c8b43e3bafaa7343bf7eb69593e Mon Sep 17 00:00:00 2001 From: Shreyas NC Date: Fri, 27 Jul 2018 14:44:16 +0530 Subject: soundwire: Add support for multi link bank switch In cases of multiple Masters in a stream, synchronization between multiple Master(s) is achieved by performing bank switch together and using Master methods. Add sdw_ml_bank_switch() to wait for completion of bank switch. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 03df709fb8ef..c6aa2bf847c7 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -678,6 +678,9 @@ struct sdw_master_ops { * @defer_msg: Defer message * @clk_stop_timeout: Clock stop timeout computed * @bank_switch_timeout: Bank switch timeout computed + * @multi_link: Store bus property that indicates if multi links + * are supported. This flag is populated by drivers after reading + * appropriate firmware (ACPI/DT). */ struct sdw_bus { struct device *dev; @@ -694,6 +697,7 @@ struct sdw_bus { struct sdw_defer defer_msg; unsigned int clk_stop_timeout; u32 bank_switch_timeout; + bool multi_link; }; int sdw_add_bus_master(struct sdw_bus *bus); -- cgit v1.2.3 From 9b5c132a1ec98895fe40ba73a19e0a17293122e5 Mon Sep 17 00:00:00 2001 From: Shreyas NC Date: Fri, 27 Jul 2018 14:44:15 +0530 Subject: soundwire: keep track of Masters in a stream A multi link bankswitch can be done if the hardware supports and the stream is handled by multiple Master(s). This preparatory patch adds support to track m_rt in a stream. Modifying m_rt_count and usage is added as part of the next patch. Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index c6aa2bf847c7..df313913e856 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -775,6 +775,7 @@ struct sdw_stream_params { * @master_list: List of Master runtime(s) in this stream. * master_list can contain only one m_rt per Master instance * for a stream + * @m_rt_count: Count of Master runtime(s) in this stream */ struct sdw_stream_runtime { char *name; @@ -782,6 +783,7 @@ struct sdw_stream_runtime { enum sdw_stream_state state; enum sdw_stream_type type; struct list_head master_list; + int m_rt_count; }; struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name); -- cgit v1.2.3 From 976516404ff3fab2a8caa8bd6f5efc1437fed0b8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 14 Aug 2018 14:02:57 +0200 Subject: y2038: remove unused time interfaces After many small patches, at least some of the deprecated interfaces have no remaining users any more and can be removed: current_kernel_time do_settimeofday get_monotonic_boottime get_monotonic_boottime64 get_monotonic_coarse get_monotonic_coarse64 getrawmonotonic64 ktime_get_real_ts timekeeping_clocktai timespec_trunc timespec_valid_strict time_to_tm For many of the remaining time functions, we are missing one or two patches that failed to make it into 4.19, they will be removed in the following merge window. The replacement functions for the removed interfaces are documented in Documentation/core-api/timekeeping.rst. Signed-off-by: Arnd Bergmann --- include/linux/time32.h | 25 ---------------------- include/linux/timekeeping.h | 12 ----------- include/linux/timekeeping32.h | 50 ------------------------------------------- 3 files changed, 87 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time32.h b/include/linux/time32.h index d1ae43c13e25..92c0ca092d93 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -105,16 +105,6 @@ static inline bool timespec_valid(const struct timespec *ts) return true; } -static inline bool timespec_valid_strict(const struct timespec *ts) -{ - if (!timespec_valid(ts)) - return false; - /* Disallow values that could overflow ktime_t */ - if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) - return false; - return true; -} - /** * timespec_to_ns - Convert timespec to nanoseconds * @ts: pointer to the timespec variable to be converted @@ -149,19 +139,6 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) a->tv_nsec = ns; } -/** - * time_to_tm - converts the calendar time to local broken-down time - * - * @totalsecs the number of seconds elapsed since 00:00:00 on January 1, 1970, - * Coordinated Universal Time (UTC). - * @offset offset seconds adding to totalsecs. - * @result pointer to struct tm variable to receive broken-down time - */ -static inline void time_to_tm(time_t totalsecs, int offset, struct tm *result) -{ - time64_to_tm(totalsecs, offset, result); -} - static inline unsigned long mktime(const unsigned int year, const unsigned int mon, const unsigned int day, const unsigned int hour, const unsigned int min, @@ -183,8 +160,6 @@ static inline bool timeval_valid(const struct timeval *tv) return true; } -extern struct timespec timespec_trunc(struct timespec t, unsigned int gran); - /** * timeval_to_ns - Convert timeval to nanoseconds * @ts: pointer to the timeval variable to be converted diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 5d738804e3d6..3faba06411aa 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -266,9 +266,6 @@ extern int update_persistent_clock64(struct timespec64 now); * deprecated aliases, don't use in new code */ #define getnstimeofday64(ts) ktime_get_real_ts64(ts) -#define get_monotonic_boottime64(ts) ktime_get_boottime_ts64(ts) -#define getrawmonotonic64(ts) ktime_get_raw_ts64(ts) -#define timekeeping_clocktai64(ts) ktime_get_clocktai_ts64(ts) static inline struct timespec64 current_kernel_time64(void) { @@ -279,13 +276,4 @@ static inline struct timespec64 current_kernel_time64(void) return ts; } -static inline struct timespec64 get_monotonic_coarse64(void) -{ - struct timespec64 ts; - - ktime_get_coarse_ts64(&ts); - - return ts; -} - #endif diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index 8762c2f45f8b..a4a4991160fb 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -9,26 +9,6 @@ extern void do_gettimeofday(struct timeval *tv); unsigned long get_seconds(void); -static inline struct timespec current_kernel_time(void) -{ - struct timespec64 ts64; - - ktime_get_coarse_real_ts64(&ts64); - - return timespec64_to_timespec(ts64); -} - -/** - * Deprecated. Use do_settimeofday64(). - */ -static inline int do_settimeofday(const struct timespec *ts) -{ - struct timespec64 ts64; - - ts64 = timespec_to_timespec64(*ts); - return do_settimeofday64(&ts64); -} - static inline void getnstimeofday(struct timespec *ts) { struct timespec64 ts64; @@ -45,14 +25,6 @@ static inline void ktime_get_ts(struct timespec *ts) *ts = timespec64_to_timespec(ts64); } -static inline void ktime_get_real_ts(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_real_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - static inline void getrawmonotonic(struct timespec *ts) { struct timespec64 ts64; @@ -61,15 +33,6 @@ static inline void getrawmonotonic(struct timespec *ts) *ts = timespec64_to_timespec(ts64); } -static inline struct timespec get_monotonic_coarse(void) -{ - struct timespec64 ts64; - - ktime_get_coarse_ts64(&ts64); - - return timespec64_to_timespec(ts64); -} - static inline void getboottime(struct timespec *ts) { struct timespec64 ts64; @@ -78,19 +41,6 @@ static inline void getboottime(struct timespec *ts) *ts = timespec64_to_timespec(ts64); } -/* - * Timespec interfaces utilizing the ktime based ones - */ -static inline void get_monotonic_boottime(struct timespec *ts) -{ - *ts = ktime_to_timespec(ktime_get_boottime()); -} - -static inline void timekeeping_clocktai(struct timespec *ts) -{ - *ts = ktime_to_timespec(ktime_get_clocktai()); -} - /* * Persistent clock related interfaces */ -- cgit v1.2.3 From 33e26418193f58d1895f2f968e1953b1caf8deb7 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 14 Aug 2018 15:18:20 +0200 Subject: y2038: make do_gettimeofday() and get_seconds() inline get_seconds() and do_gettimeofday() are only used by a few modules now any more (waiting for the respective patches to get accepted), and they are among the last holdouts of code that is not y2038 safe in the core kernel. Move the implementation into the timekeeping32.h header to clean up the core kernel and isolate the old interfaces further. Signed-off-by: Arnd Bergmann --- include/linux/timekeeping32.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index a4a4991160fb..a502616f7e1c 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -6,8 +6,19 @@ * over time so we can remove the file here. */ -extern void do_gettimeofday(struct timeval *tv); -unsigned long get_seconds(void); +static inline void do_gettimeofday(struct timeval *tv) +{ + struct timespec64 now; + + ktime_get_real_ts64(&now); + tv->tv_sec = now.tv_sec; + tv->tv_usec = now.tv_nsec/1000; +} + +static inline unsigned long get_seconds(void) +{ + return ktime_get_real_seconds(); +} static inline void getnstimeofday(struct timespec *ts) { -- cgit v1.2.3 From 9afc5eee65ca7d717a99d6fe8f4adfe32a40940a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 13 Jul 2018 12:52:28 +0200 Subject: y2038: globally rename compat_time to old_time32 Christoph Hellwig suggested a slightly different path for handling backwards compatibility with the 32-bit time_t based system calls: Rather than simply reusing the compat_sys_* entry points on 32-bit architectures unchanged, we get rid of those entry points and the compat_time types by renaming them to something that makes more sense on 32-bit architectures (which don't have a compat mode otherwise), and then share the entry points under the new name with the 64-bit architectures that use them for implementing the compatibility. The following types and interfaces are renamed here, and moved from linux/compat_time.h to linux/time32.h: old new --- --- compat_time_t old_time32_t struct compat_timeval struct old_timeval32 struct compat_timespec struct old_timespec32 struct compat_itimerspec struct old_itimerspec32 ns_to_compat_timeval() ns_to_old_timeval32() get_compat_itimerspec64() get_old_itimerspec32() put_compat_itimerspec64() put_old_itimerspec32() compat_get_timespec64() get_old_timespec32() compat_put_timespec64() put_old_timespec32() As we already have aliases in place, this patch addresses only the instances that are relevant to the system call interface in particular, not those that occur in device drivers and other modules. Those will get handled separately, while providing the 64-bit version of the respective interfaces. I'm not renaming the timex, rusage and itimerval structures, as we are still debating what the new interface will look like, and whether we will need a replacement at all. This also doesn't change the names of the syscall entry points, which can be done more easily when we actually switch over the 32-bit architectures to use them, at that point we need to change COMPAT_SYSCALL_DEFINEx to SYSCALL_DEFINEx with a new name, e.g. with a _time32 suffix. Suggested-by: Christoph Hellwig Link: https://lore.kernel.org/lkml/20180705222110.GA5698@infradead.org/ Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 96 +++++++++++++++++++++--------------------- include/linux/compat_time.h | 32 -------------- include/linux/elfcore-compat.h | 8 ++-- include/linux/restart_block.h | 4 +- include/linux/syscalls.h | 2 +- include/linux/time32.h | 48 +++++++++++++++------ 6 files changed, 91 insertions(+), 99 deletions(-) delete mode 100644 include/linux/compat_time.h (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 1a3c4f37e908..0e058792ecf6 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -7,7 +7,7 @@ */ #include -#include +#include #include #include /* for HZ */ @@ -116,13 +116,13 @@ struct compat_sel_arg_struct; struct rusage; struct compat_utimbuf { - compat_time_t actime; - compat_time_t modtime; + old_time32_t actime; + old_time32_t modtime; }; struct compat_itimerval { - struct compat_timeval it_interval; - struct compat_timeval it_value; + struct old_timeval32 it_interval; + struct old_timeval32 it_value; }; struct itimerval; @@ -146,7 +146,7 @@ struct compat_timex { compat_long_t constant; compat_long_t precision; compat_long_t tolerance; - struct compat_timeval time; + struct old_timeval32 time; compat_long_t tick; compat_long_t ppsfreq; compat_long_t jitter; @@ -307,8 +307,8 @@ struct compat_rlimit { }; struct compat_rusage { - struct compat_timeval ru_utime; - struct compat_timeval ru_stime; + struct old_timeval32 ru_utime; + struct old_timeval32 ru_stime; compat_long_t ru_maxrss; compat_long_t ru_ixrss; compat_long_t ru_idrss; @@ -457,8 +457,8 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *fr int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); -static inline int compat_timeval_compare(struct compat_timeval *lhs, - struct compat_timeval *rhs) +static inline int old_timeval32_compare(struct old_timeval32 *lhs, + struct old_timeval32 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; @@ -467,8 +467,8 @@ static inline int compat_timeval_compare(struct compat_timeval *lhs, return lhs->tv_usec - rhs->tv_usec; } -static inline int compat_timespec_compare(struct compat_timespec *lhs, - struct compat_timespec *rhs) +static inline int old_timespec32_compare(struct old_timespec32 *lhs, + struct old_timespec32 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; @@ -552,12 +552,12 @@ asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, - struct compat_timespec __user *timeout); + struct old_timespec32 __user *timeout); asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, - struct compat_timespec __user *timeout, + struct old_timespec32 __user *timeout, const struct __compat_aio_sigset __user *usig); /* fs/cookies.c */ @@ -642,11 +642,11 @@ asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timespec __user *tsp, + struct old_timespec32 __user *tsp, void __user *sig); asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, unsigned int nfds, - struct compat_timespec __user *tsp, + struct old_timespec32 __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); @@ -671,15 +671,15 @@ asmlinkage long compat_sys_newfstat(unsigned int fd, /* fs/timerfd.c */ asmlinkage long compat_sys_timerfd_gettime(int ufd, - struct compat_itimerspec __user *otmr); + struct old_itimerspec32 __user *otmr); asmlinkage long compat_sys_timerfd_settime(int ufd, int flags, - const struct compat_itimerspec __user *utmr, - struct compat_itimerspec __user *otmr); + const struct old_itimerspec32 __user *utmr, + struct old_itimerspec32 __user *otmr); /* fs/utimes.c */ asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filename, - struct compat_timespec __user *t, + struct old_timespec32 __user *t, int flags); /* kernel/exit.c */ @@ -691,7 +691,7 @@ asmlinkage long compat_sys_waitid(int, compat_pid_t, /* kernel/futex.c */ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val, - struct compat_timespec __user *utime, u32 __user *uaddr2, + struct old_timespec32 __user *utime, u32 __user *uaddr2, u32 val3); asmlinkage long compat_sys_set_robust_list(struct compat_robust_list_head __user *head, @@ -701,8 +701,8 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, compat_size_t __user *len_ptr); /* kernel/hrtimer.c */ -asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp, - struct compat_timespec __user *rmtp); +asmlinkage long compat_sys_nanosleep(struct old_timespec32 __user *rqtp, + struct old_timespec32 __user *rmtp); /* kernel/itimer.c */ asmlinkage long compat_sys_getitimer(int which, @@ -722,19 +722,19 @@ asmlinkage long compat_sys_timer_create(clockid_t which_clock, struct compat_sigevent __user *timer_event_spec, timer_t __user *created_timer_id); asmlinkage long compat_sys_timer_gettime(timer_t timer_id, - struct compat_itimerspec __user *setting); + struct old_itimerspec32 __user *setting); asmlinkage long compat_sys_timer_settime(timer_t timer_id, int flags, - struct compat_itimerspec __user *new, - struct compat_itimerspec __user *old); + struct old_itimerspec32 __user *new, + struct old_itimerspec32 __user *old); asmlinkage long compat_sys_clock_settime(clockid_t which_clock, - struct compat_timespec __user *tp); + struct old_timespec32 __user *tp); asmlinkage long compat_sys_clock_gettime(clockid_t which_clock, - struct compat_timespec __user *tp); + struct old_timespec32 __user *tp); asmlinkage long compat_sys_clock_getres(clockid_t which_clock, - struct compat_timespec __user *tp); + struct old_timespec32 __user *tp); asmlinkage long compat_sys_clock_nanosleep(clockid_t which_clock, int flags, - struct compat_timespec __user *rqtp, - struct compat_timespec __user *rmtp); + struct old_timespec32 __user *rqtp, + struct old_timespec32 __user *rmtp); /* kernel/ptrace.c */ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, @@ -748,7 +748,7 @@ asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr); asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, - struct compat_timespec __user *interval); + struct old_timespec32 __user *interval); /* kernel/signal.c */ asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, @@ -768,7 +768,7 @@ asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigtimedwait(compat_sigset_t __user *uthese, struct compat_siginfo __user *uinfo, - struct compat_timespec __user *uts, compat_size_t sigsetsize); + struct old_timespec32 __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); /* No generic prototype for rt_sigreturn */ @@ -782,9 +782,9 @@ asmlinkage long compat_sys_setrlimit(unsigned int resource, asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru); /* kernel/time.c */ -asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, +asmlinkage long compat_sys_gettimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); -asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, +asmlinkage long compat_sys_settimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); @@ -798,11 +798,11 @@ asmlinkage long compat_sys_mq_open(const char __user *u_name, asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, compat_size_t msg_len, unsigned int msg_prio, - const struct compat_timespec __user *u_abs_timeout); + const struct old_timespec32 __user *u_abs_timeout); asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, compat_size_t msg_len, unsigned int __user *u_msg_prio, - const struct compat_timespec __user *u_abs_timeout); + const struct old_timespec32 __user *u_abs_timeout); asmlinkage long compat_sys_mq_notify(mqd_t mqdes, const struct compat_sigevent __user *u_notification); asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes, @@ -819,7 +819,7 @@ asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp, /* ipc/sem.c */ asmlinkage long compat_sys_semctl(int semid, int semnum, int cmd, int arg); asmlinkage long compat_sys_semtimedop(int semid, struct sembuf __user *tsems, - unsigned nsems, const struct compat_timespec __user *timeout); + unsigned nsems, const struct old_timespec32 __user *timeout); /* ipc/shm.c */ asmlinkage long compat_sys_shmctl(int first, int second, void __user *uptr); @@ -876,7 +876,7 @@ asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, struct compat_siginfo __user *uinfo); asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, - struct compat_timespec __user *timeout); + struct old_timespec32 __user *timeout); asmlinkage long compat_sys_wait4(compat_pid_t pid, compat_uint_t __user *stat_addr, int options, struct compat_rusage __user *ru); @@ -928,7 +928,7 @@ asmlinkage long compat_sys_pwritev64v2(unsigned long fd, asmlinkage long compat_sys_open(const char __user *filename, int flags, umode_t mode); asmlinkage long compat_sys_utimes(const char __user *filename, - struct compat_timeval __user *t); + struct old_timeval32 __user *t); /* __ARCH_WANT_SYSCALL_NO_FLAGS */ asmlinkage long compat_sys_signalfd(int ufd, @@ -942,15 +942,15 @@ asmlinkage long compat_sys_newlstat(const char __user *filename, struct compat_stat __user *statbuf); /* __ARCH_WANT_SYSCALL_DEPRECATED */ -asmlinkage long compat_sys_time(compat_time_t __user *tloc); +asmlinkage long compat_sys_time(old_time32_t __user *tloc); asmlinkage long compat_sys_utime(const char __user *filename, struct compat_utimbuf __user *t); asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename, - struct compat_timeval __user *t); + struct old_timeval32 __user *t); asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timeval __user *tvp); + struct old_timeval32 __user *tvp); asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len, unsigned flags); @@ -983,7 +983,7 @@ asmlinkage long compat_sys_sigaction(int sig, #endif /* obsolete: kernel/time/time.c */ -asmlinkage long compat_sys_stime(compat_time_t __user *tptr); +asmlinkage long compat_sys_stime(old_time32_t __user *tptr); /* obsolete: net/socket.c */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); @@ -1002,15 +1002,15 @@ static inline bool in_compat_syscall(void) { return is_compat_task(); } #endif /** - * ns_to_compat_timeval - Compat version of ns_to_timeval + * ns_to_old_timeval32 - Compat version of ns_to_timeval * @nsec: the nanoseconds value to be converted * - * Returns the compat_timeval representation of the nsec parameter. + * Returns the old_timeval32 representation of the nsec parameter. */ -static inline struct compat_timeval ns_to_compat_timeval(s64 nsec) +static inline struct old_timeval32 ns_to_old_timeval32(s64 nsec) { struct timeval tv; - struct compat_timeval ctv; + struct old_timeval32 ctv; tv = ns_to_timeval(nsec); ctv.tv_sec = tv.tv_sec; diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h deleted file mode 100644 index e70bfd1d2c3f..000000000000 --- a/include/linux/compat_time.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_COMPAT_TIME_H -#define _LINUX_COMPAT_TIME_H - -#include -#include - -typedef s32 compat_time_t; - -struct compat_timespec { - compat_time_t tv_sec; - s32 tv_nsec; -}; - -struct compat_timeval { - compat_time_t tv_sec; - s32 tv_usec; -}; - -struct compat_itimerspec { - struct compat_timespec it_interval; - struct compat_timespec it_value; -}; - -extern int compat_get_timespec64(struct timespec64 *, const void __user *); -extern int compat_put_timespec64(const struct timespec64 *, void __user *); -extern int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits); -extern int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits); - -#endif /* _LINUX_COMPAT_TIME_H */ diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h index b5f2efdd05e0..7a37f4ce9fd2 100644 --- a/include/linux/elfcore-compat.h +++ b/include/linux/elfcore-compat.h @@ -27,10 +27,10 @@ struct compat_elf_prstatus compat_pid_t pr_ppid; compat_pid_t pr_pgrp; compat_pid_t pr_sid; - struct compat_timeval pr_utime; - struct compat_timeval pr_stime; - struct compat_timeval pr_cutime; - struct compat_timeval pr_cstime; + struct old_timeval32 pr_utime; + struct old_timeval32 pr_stime; + struct old_timeval32 pr_cutime; + struct old_timeval32 pr_cstime; compat_elf_gregset_t pr_reg; #ifdef CONFIG_BINFMT_ELF_FDPIC compat_ulong_t pr_exec_fdpic_loadmap; diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h index 5d83d0c1d06c..bba2920e9c05 100644 --- a/include/linux/restart_block.h +++ b/include/linux/restart_block.h @@ -10,7 +10,7 @@ #include struct timespec; -struct compat_timespec; +struct old_timespec32; struct pollfd; enum timespec_type { @@ -40,7 +40,7 @@ struct restart_block { enum timespec_type type; union { struct __kernel_timespec __user *rmtp; - struct compat_timespec __user *compat_rmtp; + struct old_timespec32 __user *compat_rmtp; }; u64 expires; } nanosleep; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2ff814c92f7f..b3e27e5ee322 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -60,7 +60,7 @@ struct tms; struct utimbuf; struct mq_attr; struct compat_stat; -struct compat_timeval; +struct old_timeval32; struct robust_list_head; struct getcpu_cache; struct old_linux_dirent; diff --git a/include/linux/time32.h b/include/linux/time32.h index 92c0ca092d93..0e0d7304d1a8 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -13,6 +13,31 @@ #define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) +typedef s32 old_time32_t; + +struct old_timespec32 { + old_time32_t tv_sec; + s32 tv_nsec; +}; + +struct old_timeval32 { + old_time32_t tv_sec; + s32 tv_usec; +}; + +struct old_itimerspec32 { + struct old_timespec32 it_interval; + struct old_timespec32 it_value; +}; + +extern int get_old_timespec32(struct timespec64 *, const void __user *); +extern int put_old_timespec32(const struct timespec64 *, void __user *); +extern int get_old_itimerspec32(struct itimerspec64 *its, + const struct old_itimerspec32 __user *uits); +extern int put_old_itimerspec32(const struct itimerspec64 *its, + struct old_itimerspec32 __user *uits); + + #if __BITS_PER_LONG == 64 /* timespec64 is defined as timespec here */ @@ -183,18 +208,17 @@ extern struct timeval ns_to_timeval(const s64 nsec); extern struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec); /* - * New aliases for compat time functions. These will be used to replace - * the compat code so it can be shared between 32-bit and 64-bit builds - * both of which provide compatibility with old 32-bit tasks. + * Old names for the 32-bit time_t interfaces, these will be removed + * when everything uses the new names. */ -#define old_time32_t compat_time_t -#define old_timeval32 compat_timeval -#define old_timespec32 compat_timespec -#define old_itimerspec32 compat_itimerspec -#define ns_to_old_timeval32 ns_to_compat_timeval -#define get_old_itimerspec32 get_compat_itimerspec64 -#define put_old_itimerspec32 put_compat_itimerspec64 -#define get_old_timespec32 compat_get_timespec64 -#define put_old_timespec32 compat_put_timespec64 +#define compat_time_t old_time32_t +#define compat_timeval old_timeval32 +#define compat_timespec old_timespec32 +#define compat_itimerspec old_itimerspec32 +#define ns_to_compat_timeval ns_to_old_timeval32 +#define get_compat_itimerspec64 get_old_itimerspec32 +#define put_compat_itimerspec64 put_old_itimerspec32 +#define compat_get_timespec64 get_old_timespec32 +#define compat_put_timespec64 put_old_timespec32 #endif -- cgit v1.2.3 From 1d8f574708a3fb6f18c85486d0c5217df893c0cf Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 24 Aug 2018 15:08:29 +0100 Subject: arm/arm64: smccc-1.1: Make return values unsigned long An unfortunate consequence of having a strong typing for the input values to the SMC call is that it also affects the type of the return values, limiting r0 to 32 bits and r{1,2,3} to whatever was passed as an input. Let's turn everything into "unsigned long", which satisfies the requirements of both architectures, and allows for the full range of return values. Reported-by: Julien Grall Signed-off-by: Marc Zyngier Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index ca1d2cc2cdfa..5a91ff33720b 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -199,31 +199,31 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define __declare_arg_0(a0, res) \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ + register unsigned long r0 asm("r0") = (u32)a0; \ register unsigned long r1 asm("r1"); \ register unsigned long r2 asm("r2"); \ register unsigned long r3 asm("r3") #define __declare_arg_1(a0, a1, res) \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ - register typeof(a1) r1 asm("r1") = a1; \ + register unsigned long r0 asm("r0") = (u32)a0; \ + register unsigned long r1 asm("r1") = a1; \ register unsigned long r2 asm("r2"); \ register unsigned long r3 asm("r3") #define __declare_arg_2(a0, a1, a2, res) \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ - register typeof(a1) r1 asm("r1") = a1; \ - register typeof(a2) r2 asm("r2") = a2; \ + register unsigned long r0 asm("r0") = (u32)a0; \ + register unsigned long r1 asm("r1") = a1; \ + register unsigned long r2 asm("r2") = a2; \ register unsigned long r3 asm("r3") #define __declare_arg_3(a0, a1, a2, a3, res) \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ - register typeof(a1) r1 asm("r1") = a1; \ - register typeof(a2) r2 asm("r2") = a2; \ - register typeof(a3) r3 asm("r3") = a3 + register unsigned long r0 asm("r0") = (u32)a0; \ + register unsigned long r1 asm("r1") = a1; \ + register unsigned long r2 asm("r2") = a2; \ + register unsigned long r3 asm("r3") = a3 #define __declare_arg_4(a0, a1, a2, a3, a4, res) \ __declare_arg_3(a0, a1, a2, a3, res); \ -- cgit v1.2.3 From eeaceb8b7d1fb64b6030249ca0dd1d902ef3069e Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 16 Aug 2018 20:54:49 +0800 Subject: spi: Introduce one new field to set word delay For some SPI controllers, after each word size (specified by bits_per_word) transimission, the hardware need some delay to make sure the slave has enough time to receive the whole data. So introducing one new 'word_delay' field of struct spi_tansfer for slave devices to set this inter word delay time. Signed-off-by: Baolin Wang Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a64235e05321..d698f9db3484 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -711,6 +711,8 @@ extern void spi_res_release(struct spi_controller *ctlr, * @delay_usecs: microseconds to delay after this transfer before * (optionally) changing the chipselect status, then starting * the next transfer or completing this @spi_message. + * @word_delay: clock cycles to inter word delay after each word size + * (set by bits_per_word) transmission. * @transfer_list: transfers are sequenced through @spi_message.transfers * @tx_sg: Scatterlist for transmit, currently not for client use * @rx_sg: Scatterlist for receive, currently not for client use @@ -793,6 +795,7 @@ struct spi_transfer { u8 bits_per_word; u16 delay_usecs; u32 speed_hz; + u16 word_delay; struct list_head transfer_list; }; -- cgit v1.2.3 From 36156f9241cb0f9e37d998052873ca7501ad4b36 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 27 Aug 2018 10:21:45 +0200 Subject: of: add helper to lookup compatible child node Add of_get_compatible_child() helper that can be used to lookup compatible child nodes. Several drivers currently use of_find_compatible_node() to lookup child nodes while failing to notice that the of_find_ functions search the entire tree depth-first (from a given start node) and therefore can match unrelated nodes. The fact that these functions also drop a reference to the node they start searching from (e.g. the parent node) is typically also overlooked, something which can lead to use-after-free bugs. Signed-off-by: Johan Hovold Signed-off-by: Rob Herring --- include/linux/of.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 4d25e4f952d9..b99a1a8c2952 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -290,6 +290,8 @@ extern struct device_node *of_get_next_child(const struct device_node *node, extern struct device_node *of_get_next_available_child( const struct device_node *node, struct device_node *prev); +extern struct device_node *of_get_compatible_child(const struct device_node *parent, + const char *compatible); extern struct device_node *of_get_child_by_name(const struct device_node *node, const char *name); @@ -632,6 +634,12 @@ static inline bool of_have_populated_dt(void) return false; } +static inline struct device_node *of_get_compatible_child(const struct device_node *parent, + const char *compatible) +{ + return NULL; +} + static inline struct device_node *of_get_child_by_name( const struct device_node *node, const char *name) -- cgit v1.2.3 From fb3739759474d150a9927b920a80ea2afb4c2a51 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Apr 2018 22:01:26 +0200 Subject: asm-generic: Move common compat types to asm-generic/compat.h While converting compat system call handlers to work on 32-bit architectures, I found a number of types used in those handlers that are identical between all architectures. Let's move all the identical ones into asm-generic/compat.h to avoid having to add even more identical definitions of those types. For unknown reasons, mips defines __compat_gid32_t, __compat_uid32_t and compat_caddr_t as signed, while all others have them unsigned. This seems to be a mistake, but I'm leaving it alone here. The other types all differ by size or alignment on at least on architecture. compat_aio_context_t is currently defined in linux/compat.h but also needed for compat_sys_io_getevents(), so let's move it into the same place. While we still have not decided whether the 32-bit time handling will always use the compat syscalls, or in which form, I think this is a useful cleanup that we can merge regardless. Reviewed-by: Christoph Hellwig Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 0e058792ecf6..d376fa8be00d 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -110,8 +110,6 @@ typedef struct compat_sigaltstack { typedef __compat_uid32_t compat_uid_t; typedef __compat_gid32_t compat_gid_t; -typedef compat_ulong_t compat_aio_context_t; - struct compat_sel_arg_struct; struct rusage; -- cgit v1.2.3 From a4f7a3004630f1a0fb130ab1824942a49ce33140 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 09:11:58 +0200 Subject: y2038: Change sys_utimensat() to use __kernel_timespec When 32-bit architectures get changed to support 64-bit time_t, utimensat() needs to use the new __kernel_timespec structure as its argument. The older utime(), utimes() and futimesat() system calls don't need a corresponding change as they are no longer used on C libraries that have 64-bit time support. As we do for the other syscalls that have timespec arguments, we reuse the 'compat' syscall entry points to implement the traditional four interfaces, and only leave the new utimensat() as a native handler, so that the same code gets used on both 32-bit and 64-bit kernels on each syscall. Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b3e27e5ee322..420ac881a610 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -513,7 +513,8 @@ asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user * /* fs/utimes.c */ asmlinkage long sys_utimensat(int dfd, const char __user *filename, - struct timespec __user *utimes, int flags); + struct __kernel_timespec __user *utimes, + int flags); /* kernel/acct.c */ asmlinkage long sys_acct(const char __user *name); -- cgit v1.2.3 From 185cfaf7641e14af85635bb2750da302e32b04e3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 09:11:58 +0200 Subject: y2038: Compile utimes()/futimesat() conditionally There are four generations of utimes() syscalls: utime(), utimes(), futimesat() and utimensat(), each one being a superset of the previous one. For y2038 support, we have to add another one, which is the same as the existing utimensat() but always passes 64-bit times_t based timespec values. There are currently 10 architectures that only use utimensat(), two that use utimes(), futimesat() and utimensat() but not utime(), and 11 architectures that have all four, and those define __ARCH_WANT_SYS_UTIME in order to get a sys_utime implementation. Since all the new architectures only want utimensat(), moving all the legacy entry points into a common __ARCH_WANT_SYS_UTIME guard simplifies the logic. Only alpha and ia64 grow a tiny bit as they now also get an unused sys_utime(), but it didn't seem worth the extra complexity of adding yet another ifdef for those. Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 420ac881a610..95e795fb0593 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -955,8 +955,6 @@ asmlinkage long sys_access(const char __user *filename, int mode); asmlinkage long sys_rename(const char __user *oldname, const char __user *newname); asmlinkage long sys_symlink(const char __user *old, const char __user *new); -asmlinkage long sys_utimes(char __user *filename, - struct timeval __user *utimes); #if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) asmlinkage long sys_stat64(const char __user *filename, struct stat64 __user *statbuf); @@ -986,14 +984,18 @@ asmlinkage long sys_alarm(unsigned int seconds); asmlinkage long sys_getpgrp(void); asmlinkage long sys_pause(void); asmlinkage long sys_time(time_t __user *tloc); +#ifdef __ARCH_WANT_SYS_UTIME asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times); +asmlinkage long sys_utimes(char __user *filename, + struct timeval __user *utimes); +asmlinkage long sys_futimesat(int dfd, const char __user *filename, + struct timeval __user *utimes); +#endif asmlinkage long sys_creat(const char __user *pathname, umode_t mode); asmlinkage long sys_getdents(unsigned int fd, struct linux_dirent __user *dirent, unsigned int count); -asmlinkage long sys_futimesat(int dfd, const char __user *filename, - struct timeval __user *utimes); asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, -- cgit v1.2.3 From 4faea239e529d1d6b3b93fbf08d5e90427961a41 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 12:03:19 +0200 Subject: y2038: utimes: Rework #ifdef guards for compat syscalls After changing over to 64-bit time_t syscalls, many architectures will want compat_sys_utimensat() but not respective handlers for utime(), utimes() and futimesat(). This adds a new __ARCH_WANT_SYS_UTIME32 to complement __ARCH_WANT_SYS_UTIME. For now, all 64-bit architectures that support CONFIG_COMPAT set it, but future 64-bit architectures will not (tile would not have needed it either, but got removed). As older 32-bit architectures get converted to using CONFIG_64BIT_TIME, they will have to use __ARCH_WANT_SYS_UTIME32 instead of __ARCH_WANT_SYS_UTIME. Architectures using the generic syscall ABI don't need either of them as they never had a utime syscall. Since the compat_utimbuf structure is now required outside of CONFIG_COMPAT, I'm moving it into compat_time.h. Signed-off-by: Arnd Bergmann --- changed from last version: - renamed __ARCH_WANT_COMPAT_SYS_UTIME to __ARCH_WANT_SYS_UTIME32 --- include/linux/compat.h | 7 +------ include/linux/time32.h | 5 +++++ 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index d376fa8be00d..6fb5abdb87be 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -113,11 +113,6 @@ typedef __compat_gid32_t compat_gid_t; struct compat_sel_arg_struct; struct rusage; -struct compat_utimbuf { - old_time32_t actime; - old_time32_t modtime; -}; - struct compat_itimerval { struct old_timeval32 it_interval; struct old_timeval32 it_value; @@ -942,7 +937,7 @@ asmlinkage long compat_sys_newlstat(const char __user *filename, /* __ARCH_WANT_SYSCALL_DEPRECATED */ asmlinkage long compat_sys_time(old_time32_t __user *tloc); asmlinkage long compat_sys_utime(const char __user *filename, - struct compat_utimbuf __user *t); + struct old_utimbuf32 __user *t); asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename, struct old_timeval32 __user *t); diff --git a/include/linux/time32.h b/include/linux/time32.h index 0e0d7304d1a8..61904a6c098f 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -30,6 +30,11 @@ struct old_itimerspec32 { struct old_timespec32 it_value; }; +struct old_utimbuf32 { + old_time32_t actime; + old_time32_t modtime; +}; + extern int get_old_timespec32(struct timespec64 *, const void __user *); extern int put_old_timespec32(const struct timespec64 *, void __user *); extern int get_old_itimerspec32(struct itimerspec64 *its, -- cgit v1.2.3 From 474b9c777b20b8340a6ee0f7ba6ebbd6a4bf47e2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 21:59:47 +0200 Subject: y2038: sched: Change sched_rr_get_interval to use __kernel_timespec This is a preparation patch for converting sys_sched_rr_get_interval to work with 64-bit time_t on 32-bit architectures. The 'interval' argument is changed to struct __kernel_timespec, which will be redefined using 64-bit time_t in the future. The compat version of the system call in turn is enabled for compilation with CONFIG_COMPAT_32BIT_TIME so the individual 32-bit architectures can share the handling of the traditional argument with 64-bit architectures providing it for their compat mode. Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 95e795fb0593..5642016a312d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -614,7 +614,7 @@ asmlinkage long sys_sched_yield(void); asmlinkage long sys_sched_get_priority_max(int policy); asmlinkage long sys_sched_get_priority_min(int policy); asmlinkage long sys_sched_rr_get_interval(pid_t pid, - struct timespec __user *interval); + struct __kernel_timespec __user *interval); /* kernel/signal.c */ asmlinkage long sys_restart_syscall(void); -- cgit v1.2.3 From c2e6c8567acdba8db1055b242c34ceb123c6a253 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Apr 2018 13:42:25 +0200 Subject: y2038: socket: Change recvmmsg to use __kernel_timespec This converts the recvmmsg() system call in all its variations to use 'timespec64' internally for its timeout, and have a __kernel_timespec64 argument in the native entry point. This lets us change the type to use 64-bit time_t at a later point while using the 32-bit compat system call emulation for existing user space. Signed-off-by: Arnd Bergmann --- include/linux/socket.h | 4 ++-- include/linux/syscalls.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 7ed4713d5337..8b571e9b9f76 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -348,7 +348,7 @@ struct ucred { extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); -struct timespec; +struct timespec64; /* The __sys_...msg variants allow MSG_CMSG_COMPAT iff * forbid_cmsg_compat==false @@ -358,7 +358,7 @@ extern long __sys_recvmsg(int fd, struct user_msghdr __user *msg, extern long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat); extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, - unsigned int flags, struct timespec *timeout); + unsigned int flags, struct timespec64 *timeout); extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, bool forbid_cmsg_compat); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5642016a312d..fb3a05fab8aa 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -830,7 +830,7 @@ asmlinkage long sys_perf_event_open( asmlinkage long sys_accept4(int, struct sockaddr __user *, int __user *, int); asmlinkage long sys_recvmmsg(int fd, struct mmsghdr __user *msg, unsigned int vlen, unsigned flags, - struct timespec __user *timeout); + struct __kernel_timespec __user *timeout); asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr, int options, struct rusage __user *ru); -- cgit v1.2.3 From 49c39f8464a9af702e9d45800c00a572753aeb06 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Apr 2018 15:56:13 +0200 Subject: y2038: signal: Change rt_sigtimedwait to use __kernel_timespec This changes sys_rt_sigtimedwait() to use get_timespec64(), changing the timeout type to __kernel_timespec, which will be changed to use a 64-bit time_t in the future. Since the do_sigtimedwait() core function changes, we also have to modify the compat version of this system call in the same way. Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index fb3a05fab8aa..2ac3d13a915b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -635,7 +635,7 @@ asmlinkage long sys_rt_sigprocmask(int how, sigset_t __user *set, asmlinkage long sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize); asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese, siginfo_t __user *uinfo, - const struct timespec __user *uts, + const struct __kernel_timespec __user *uts, size_t sigsetsize); asmlinkage long sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo); -- cgit v1.2.3 From 823f18f8b860526fc099c222619a126d57d2ad8c Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Wed, 29 Aug 2018 15:36:10 +0300 Subject: regulator: bd71837: Disable voltage monitoring for LDO3/4 There is a HW quirk in BD71837. The shutdown sequence timings for bucks/LDOs which are enabled via register interface are changed. At PMIC poweroff the voltage for BUCK6/7 is cut immediately at the beginning of shut-down sequence. This causes LDO5/6 voltage monitoring to detect under voltage and force PMIC to emergency state instead of poweroff. Disable voltage monitoring for LDO5 and LDO6 at probe to avoid this. Signed-off-by: Matti Vaittinen Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- include/linux/mfd/rohm-bd718x7.h | 33 ++++++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index a528747f8aed..e8338e5dc10b 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -78,9 +78,9 @@ enum { BD71837_REG_TRANS_COND0 = 0x1F, BD71837_REG_TRANS_COND1 = 0x20, BD71837_REG_VRFAULTEN = 0x21, - BD71837_REG_MVRFLTMASK0 = 0x22, - BD71837_REG_MVRFLTMASK1 = 0x23, - BD71837_REG_MVRFLTMASK2 = 0x24, + BD718XX_REG_MVRFLTMASK0 = 0x22, + BD718XX_REG_MVRFLTMASK1 = 0x23, + BD718XX_REG_MVRFLTMASK2 = 0x24, BD71837_REG_RCVCFG = 0x25, BD71837_REG_RCVNUM = 0x26, BD71837_REG_PWRONCONFIG0 = 0x27, @@ -159,6 +159,33 @@ enum { #define BUCK8_MASK 0x3F #define BUCK8_DEFAULT 0x1E +/* BD718XX Voltage monitoring masks */ +#define BD718XX_BUCK1_VRMON80 0x1 +#define BD718XX_BUCK1_VRMON130 0x2 +#define BD718XX_BUCK2_VRMON80 0x4 +#define BD718XX_BUCK2_VRMON130 0x8 +#define BD718XX_1ST_NODVS_BUCK_VRMON80 0x1 +#define BD718XX_1ST_NODVS_BUCK_VRMON130 0x2 +#define BD718XX_2ND_NODVS_BUCK_VRMON80 0x4 +#define BD718XX_2ND_NODVS_BUCK_VRMON130 0x8 +#define BD718XX_3RD_NODVS_BUCK_VRMON80 0x10 +#define BD718XX_3RD_NODVS_BUCK_VRMON130 0x20 +#define BD718XX_4TH_NODVS_BUCK_VRMON80 0x40 +#define BD718XX_4TH_NODVS_BUCK_VRMON130 0x80 +#define BD718XX_LDO1_VRMON80 0x1 +#define BD718XX_LDO2_VRMON80 0x2 +#define BD718XX_LDO3_VRMON80 0x4 +#define BD718XX_LDO4_VRMON80 0x8 +#define BD718XX_LDO5_VRMON80 0x10 +#define BD718XX_LDO6_VRMON80 0x20 + +/* BD71837 specific voltage monitoring masks */ +#define BD71837_BUCK3_VRMON80 0x10 +#define BD71837_BUCK3_VRMON130 0x20 +#define BD71837_BUCK4_VRMON80 0x40 +#define BD71837_BUCK4_VRMON130 0x80 +#define BD71837_LDO7_VRMON80 0x40 + /* BD71837_REG_IRQ bits */ #define IRQ_SWRST 0x40 #define IRQ_PWRON_S 0x20 -- cgit v1.2.3 From 1b27291b1ea4f1f2090fb07c3425db474cdb99ba Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 18 Jul 2018 14:32:31 -0700 Subject: rcutorture: Add forward-progress tests for RCU grace periods This commit adds a kthread that loops going into and out of RCU read-side critical sections, but also including a cond_resched(), optionally guarded by a check of need_resched(), in that same loop. This commit relies solely on rcu_torture_writer() progress to judge the forward progress of grace periods. Note that Tasks RCU and SRCU are exempted from forward-progress testing due their (intentionally) less-robust forward-progress guarantees. Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 8d9a0ea8f0b5..a6353f3d6094 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -108,6 +108,7 @@ static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) */ static inline void rcu_virt_note_context_switch(int cpu) { } static inline void rcu_cpu_stall_reset(void) { } +static inline int rcu_jiffies_till_stall_check(void) { return 21 * HZ; } static inline void rcu_idle_enter(void) { } static inline void rcu_idle_exit(void) { } static inline void rcu_irq_enter(void) { } -- cgit v1.2.3 From 474e59b476b3390ef9f730515439f21640b61623 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 7 Aug 2018 14:34:44 -0700 Subject: rcutorture: Check GP completion at stutter end The rcu_torture_writer() function invokes stutter_wait() at the end of each writer pass, which occasionally blocks for an extended time period in order to ensure that RCU can handle intermittent loads. But part of handling a busy period is invoking all the callbacks before the end of the idle period induced by stutter_wait(). This commit therefore adds a return value to stutter_wait() indicating whether stutter_wait() actually waited. In addition, this commit causes rcu_torture_writer() to test this value and if set, checks that all the elements of the rcu_tortures[] array have been freed up. Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/torture.h b/include/linux/torture.h index 61dfd93b6ee4..48fad21109fc 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -77,7 +77,7 @@ void torture_shutdown_absorb(const char *title); int torture_shutdown_init(int ssecs, void (*cleanup)(void)); /* Task stuttering, which forces load/no-load transitions. */ -void stutter_wait(const char *title); +bool stutter_wait(const char *title); int torture_stutter_init(int s); /* Initialization and cleanup. */ -- cgit v1.2.3 From 6c5c9581044dd6e0cd284ab653502fb9264f08b6 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Tue, 28 Aug 2018 14:44:28 +0200 Subject: net: add napi_if_scheduled_mark_missed The function napi_if_scheduled_mark_missed is used to check if the NAPI context is scheduled, if so set NAPIF_STATE_MISSED and return true. Used by the AF_XDP zero-copy i40e Tx code implementation in order to make sure that irq affinity is honored by the napi context. Signed-off-by: Magnus Karlsson Signed-off-by: Alexei Starovoitov --- include/linux/netdevice.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ca5ab98053c8..4271f6b4e419 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -535,6 +535,32 @@ static inline void napi_synchronize(const struct napi_struct *n) barrier(); } +/** + * napi_if_scheduled_mark_missed - if napi is running, set the + * NAPIF_STATE_MISSED + * @n: NAPI context + * + * If napi is running, set the NAPIF_STATE_MISSED, and return true if + * NAPI is scheduled. + **/ +static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) +{ + unsigned long val, new; + + do { + val = READ_ONCE(n->state); + if (val & NAPIF_STATE_DISABLE) + return true; + + if (!(val & NAPIF_STATE_SCHED)) + return false; + + new = val | NAPIF_STATE_MISSED; + } while (cmpxchg(&n->state, val, new) != val); + + return true; +} + enum netdev_queue_state_t { __QUEUE_STATE_DRV_XOFF, __QUEUE_STATE_STACK_XOFF, -- cgit v1.2.3 From 679c782de14bd48c19dd74cd1af20a2bc05dd936 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Wed, 22 Aug 2018 20:02:19 +0100 Subject: bpf/verifier: per-register parent pointers By giving each register its own liveness chain, we elide the skip_callee() logic. Instead, each register's parent is the state it inherits from; both check_func_call() and prepare_func_exit() automatically connect reg states to the correct chain since when they copy the reg state across (r1-r5 into the callee as args, and r0 out as the return value) they also copy the parent pointer. Signed-off-by: Edward Cree Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 38b04f559ad3..b42b60a83e19 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -41,6 +41,7 @@ enum bpf_reg_liveness { }; struct bpf_reg_state { + /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; union { /* valid when type == PTR_TO_PACKET */ @@ -59,7 +60,6 @@ struct bpf_reg_state { * came from, when one is tested for != NULL. */ u32 id; - /* Ordering of fields matters. See states_equal() */ /* For scalar types (SCALAR_VALUE), this represents our knowledge of * the actual value. * For pointer types, this represents the variable part of the offset @@ -76,15 +76,15 @@ struct bpf_reg_state { s64 smax_value; /* maximum possible (s64)value */ u64 umin_value; /* minimum possible (u64)value */ u64 umax_value; /* maximum possible (u64)value */ + /* parentage chain for liveness checking */ + struct bpf_reg_state *parent; /* Inside the callee two registers can be both PTR_TO_STACK like * R1=fp-8 and R2=fp-8, but one of them points to this function stack * while another to the caller's stack. To differentiate them 'frameno' * is used which is an index in bpf_verifier_state->frame[] array * pointing to bpf_func_state. - * This field must be second to last, for states_equal() reasons. */ u32 frameno; - /* This field must be last, for states_equal() reasons. */ enum bpf_reg_liveness live; }; @@ -107,7 +107,6 @@ struct bpf_stack_state { */ struct bpf_func_state { struct bpf_reg_state regs[MAX_BPF_REG]; - struct bpf_verifier_state *parent; /* index of call instruction that called into this func */ int callsite; /* stack frame number of this function state from pov of @@ -129,7 +128,6 @@ struct bpf_func_state { struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; - struct bpf_verifier_state *parent; u32 curframe; }; -- cgit v1.2.3 From 9b3004953503462a4fab31b85e44ae446d48f0bd Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Tue, 28 Aug 2018 19:56:58 +0200 Subject: ethtool: drop get_settings and set_settings callbacks Since [gs]et_settings ethtool_ops callbacks have been deprecated in February 2016, all in tree NIC drivers have been converted to provide [gs]et_link_ksettings() and out of tree drivers have had enough time to do the same. Drop get_settings() and set_settings() and implement both ETHTOOL_[GS]SET and ETHTOOL_[GS]LINKSETTINGS only using [gs]et_link_ksettings(). Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- include/linux/ethtool.h | 33 ++++++++++----------------------- 1 file changed, 10 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index f8a2245b70ac..afd9596ce636 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -183,14 +183,6 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, /** * struct ethtool_ops - optional netdev operations - * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings - * API. Get various device settings including Ethernet link - * settings. The @cmd parameter is expected to have been cleared - * before get_settings is called. Returns a negative error code - * or zero. - * @set_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings - * API. Set various device settings including Ethernet link - * settings. Returns a negative error code or zero. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not * implemented, the @driver and @bus_info fields will be filled in @@ -297,19 +289,16 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, ignore the inapplicable fields. * Returns a negative error code or zero. - * @get_link_ksettings: When defined, takes precedence over the - * %get_settings method. Get various device settings - * including Ethernet link settings. The %cmd and - * %link_mode_masks_nwords fields should be ignored (use - * %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), any - * change to them will be overwritten by kernel. Returns a - * negative error code or zero. - * @set_link_ksettings: When defined, takes precedence over the - * %set_settings method. Set various device settings including - * Ethernet link settings. The %cmd and %link_mode_masks_nwords - * fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS - * instead of the latter), any change to them will be overwritten - * by kernel. Returns a negative error code or zero. + * @get_link_ksettings: Get various device settings including Ethernet link + * settings. The %cmd and %link_mode_masks_nwords fields should be + * ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), + * any change to them will be overwritten by kernel. Returns a negative + * error code or zero. + * @set_link_ksettings: Set various device settings including Ethernet link + * settings. The %cmd and %link_mode_masks_nwords fields should be + * ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), + * any change to them will be overwritten by kernel. Returns a negative + * error code or zero. * @get_fecparam: Get the network device Forward Error Correction parameters. * @set_fecparam: Set the network device Forward Error Correction parameters. * @get_ethtool_phy_stats: Return extended statistics about the PHY device. @@ -329,8 +318,6 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * of the generic netdev features interface. */ struct ethtool_ops { - int (*get_settings)(struct net_device *, struct ethtool_cmd *); - int (*set_settings)(struct net_device *, struct ethtool_cmd *); void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); -- cgit v1.2.3 From 755a8bf5579d22eb5636685c516d8dede799e27b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 24 Aug 2018 15:08:30 +0100 Subject: arm/arm64: smccc-1.1: Handle function result as parameters If someone has the silly idea to write something along those lines: extern u64 foo(void); void bar(struct arm_smccc_res *res) { arm_smccc_1_1_smc(0xbad, foo(), res); } they are in for a surprise, as this gets compiled as: 0000000000000588 : 588: a9be7bfd stp x29, x30, [sp, #-32]! 58c: 910003fd mov x29, sp 590: f9000bf3 str x19, [sp, #16] 594: aa0003f3 mov x19, x0 598: aa1e03e0 mov x0, x30 59c: 94000000 bl 0 <_mcount> 5a0: 94000000 bl 0 5a4: aa0003e1 mov x1, x0 5a8: d4000003 smc #0x0 5ac: b4000073 cbz x19, 5b8 5b0: a9000660 stp x0, x1, [x19] 5b4: a9010e62 stp x2, x3, [x19, #16] 5b8: f9400bf3 ldr x19, [sp, #16] 5bc: a8c27bfd ldp x29, x30, [sp], #32 5c0: d65f03c0 ret 5c4: d503201f nop The call to foo "overwrites" the x0 register for the return value, and we end up calling the wrong secure service. A solution is to evaluate all the parameters before assigning anything to specific registers, leading to the expected result: 0000000000000588 : 588: a9be7bfd stp x29, x30, [sp, #-32]! 58c: 910003fd mov x29, sp 590: f9000bf3 str x19, [sp, #16] 594: aa0003f3 mov x19, x0 598: aa1e03e0 mov x0, x30 59c: 94000000 bl 0 <_mcount> 5a0: 94000000 bl 0 5a4: aa0003e1 mov x1, x0 5a8: d28175a0 mov x0, #0xbad 5ac: d4000003 smc #0x0 5b0: b4000073 cbz x19, 5bc 5b4: a9000660 stp x0, x1, [x19] 5b8: a9010e62 stp x2, x3, [x19, #16] 5bc: f9400bf3 ldr x19, [sp, #16] 5c0: a8c27bfd ldp x29, x30, [sp], #32 5c4: d65f03c0 ret Reported-by: Julien Grall Signed-off-by: Marc Zyngier Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 5a91ff33720b..18863d56273c 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -205,41 +205,51 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, register unsigned long r3 asm("r3") #define __declare_arg_1(a0, a1, res) \ + typeof(a1) __a1 = a1; \ struct arm_smccc_res *___res = res; \ register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = a1; \ + register unsigned long r1 asm("r1") = __a1; \ register unsigned long r2 asm("r2"); \ register unsigned long r3 asm("r3") #define __declare_arg_2(a0, a1, a2, res) \ + typeof(a1) __a1 = a1; \ + typeof(a2) __a2 = a2; \ struct arm_smccc_res *___res = res; \ register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = a1; \ - register unsigned long r2 asm("r2") = a2; \ + register unsigned long r1 asm("r1") = __a1; \ + register unsigned long r2 asm("r2") = __a2; \ register unsigned long r3 asm("r3") #define __declare_arg_3(a0, a1, a2, a3, res) \ + typeof(a1) __a1 = a1; \ + typeof(a2) __a2 = a2; \ + typeof(a3) __a3 = a3; \ struct arm_smccc_res *___res = res; \ register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = a1; \ - register unsigned long r2 asm("r2") = a2; \ - register unsigned long r3 asm("r3") = a3 + register unsigned long r1 asm("r1") = __a1; \ + register unsigned long r2 asm("r2") = __a2; \ + register unsigned long r3 asm("r3") = __a3 #define __declare_arg_4(a0, a1, a2, a3, a4, res) \ + typeof(a4) __a4 = a4; \ __declare_arg_3(a0, a1, a2, a3, res); \ - register typeof(a4) r4 asm("r4") = a4 + register unsigned long r4 asm("r4") = __a4 #define __declare_arg_5(a0, a1, a2, a3, a4, a5, res) \ + typeof(a5) __a5 = a5; \ __declare_arg_4(a0, a1, a2, a3, a4, res); \ - register typeof(a5) r5 asm("r5") = a5 + register unsigned long r5 asm("r5") = __a5 #define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res) \ + typeof(a6) __a6 = a6; \ __declare_arg_5(a0, a1, a2, a3, a4, a5, res); \ - register typeof(a6) r6 asm("r6") = a6 + register unsigned long r6 asm("r6") = __a6 #define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res) \ + typeof(a7) __a7 = a7; \ __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res); \ - register typeof(a7) r7 asm("r7") = a7 + register unsigned long r7 asm("r7") = __a7 #define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__) #define __declare_args(count, ...) ___declare_args(count, __VA_ARGS__) -- cgit v1.2.3 From 45cd0faae3715e305bc46e23b34c5ed4d185ceb8 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 27 Aug 2018 15:56:02 +0300 Subject: vfs: add the fadvise() file operation This is going to be used by overlayfs and possibly useful for other filesystems. Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 33322702c910..6c0b4a1c22ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1763,6 +1763,7 @@ struct file_operations { u64); int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; struct inode_operations { @@ -3459,4 +3460,8 @@ static inline bool dir_relax_shared(struct inode *inode) extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); +/* mm/fadvise.c */ +extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, + int advice); + #endif /* _LINUX_FS_H */ -- cgit v1.2.3 From f42b0e18f2e5cf34f73ef1b6327b49040b307a33 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 27 Aug 2018 07:50:47 -0500 Subject: of: add node name compare helper functions In preparation to remove device_node.name pointer, add helper functions for node name comparisons which are a common pattern throughout the kernel. Cc: Frank Rowand Signed-off-by: Rob Herring --- include/linux/of.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index b99a1a8c2952..688c52dd7b3e 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -256,6 +256,9 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags) #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags) +extern bool of_node_name_eq(const struct device_node *np, const char *name); +extern bool of_node_name_prefix(const struct device_node *np, const char *prefix); + static inline const char *of_node_full_name(const struct device_node *np) { return np ? np->full_name : ""; @@ -563,6 +566,16 @@ static inline struct device_node *to_of_node(const struct fwnode_handle *fwnode) return NULL; } +static inline bool of_node_name_eq(const struct device_node *np, const char *name) +{ + return false; +} + +static inline bool of_node_name_prefix(const struct device_node *np, const char *prefix) +{ + return false; +} + static inline const char* of_node_full_name(const struct device_node *np) { return ""; -- cgit v1.2.3 From a4e0109a19c554e44c832958e426303781e1ad30 Mon Sep 17 00:00:00 2001 From: Harshitha Ramamurthy Date: Mon, 20 Aug 2018 08:12:32 -0700 Subject: virtchnl: use u8 type for a field in the virtchnl_filter struct The virtchnl_filter struct has a field called field_flags. A previous commit mistakenly had the type to be a __u8. What we want is for the field to be an unsigned 8 bit value, so let's just use the existing kernel type u8 for that. Signed-off-by: Harshitha Ramamurthy Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 212b3822d180..b41f7bc958ef 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -573,7 +573,7 @@ struct virtchnl_filter { enum virtchnl_flow_type flow_type; enum virtchnl_action action; u32 action_meta; - __u8 field_flags; + u8 field_flags; }; VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); -- cgit v1.2.3 From 82fe39a6bc7b866fc3ffd838e3c5a4cadb328b04 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 24 Aug 2018 16:52:44 +0200 Subject: i2c: refactor function to release a DMA safe buffer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit a) rename to 'put' instead of 'release' to match 'get' when obtaining the buffer b) change the argument order to have the buffer as first argument c) add a new argument telling the function if the message was transferred. This allows the function to be used also in cases where setting up DMA failed, so the buffer needs to be freed without syncing to the message buffer. Also convert the only user. Signed-off-by: Wolfram Sang Reviewed-by: Niklas Söderlund Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index b79387fd57da..65b4eaed1d96 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -855,7 +855,7 @@ static inline u8 i2c_8bit_addr_from_msg(const struct i2c_msg *msg) } u8 *i2c_get_dma_safe_msg_buf(struct i2c_msg *msg, unsigned int threshold); -void i2c_release_dma_safe_msg_buf(struct i2c_msg *msg, u8 *buf); +void i2c_put_dma_safe_msg_buf(u8 *buf, struct i2c_msg *msg, bool xferred); int i2c_handle_smbus_host_notify(struct i2c_adapter *adap, unsigned short addr); /** -- cgit v1.2.3 From 3e31009898699dfca823893054748d85048dc7b3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 21 Jun 2018 12:50:01 -0700 Subject: rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ] --- include/linux/rcutiny.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 8d9a0ea8f0b5..f617ab19bb51 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -115,6 +115,11 @@ static inline void rcu_irq_exit_irqson(void) { } static inline void rcu_irq_enter_irqson(void) { } static inline void rcu_irq_exit(void) { } static inline void exit_rcu(void) { } +static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t) +{ + return false; +} +static inline void rcu_preempt_deferred_qs(struct task_struct *t) { } #ifdef CONFIG_SRCU void rcu_scheduler_starting(void); #else /* #ifndef CONFIG_SRCU */ -- cgit v1.2.3 From fcc878e4dfb70128a73857c609d70570629b0d9e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 28 Jun 2018 07:39:59 -0700 Subject: rcu: Remove now-unused ->b.exp_need_qs field from the rcu_special union The ->b.exp_need_qs field is now set only to false, so this commit removes it. The job this field used to do is now done by the rcu_data structure's ->deferred_qs field, which is a consequence of a better split between task-based (the rcu_node structure's ->exp_tasks field) and CPU-based (the aforementioned rcu_data structure's ->deferred_qs field) tracking of quiescent states for RCU-preempt expedited grace periods. Signed-off-by: Paul E. McKenney --- include/linux/sched.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 977cb57d7bc9..004ca21f7e80 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -571,12 +571,8 @@ union rcu_special { struct { u8 blocked; u8 need_qs; - u8 exp_need_qs; - - /* Otherwise the compiler can store garbage here: */ - u8 pad; } b; /* Bits. */ - u32 s; /* Set of bits. */ + u16 s; /* Set of bits. */ }; enum perf_event_task_context { -- cgit v1.2.3 From d28139c4e96713d52a300fb9036c5be2f45e0741 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 28 Jun 2018 14:45:25 -0700 Subject: rcu: Apply RCU-bh QSes to RCU-sched and RCU-preempt when safe One necessary step towards consolidating the three flavors of RCU is to make sure that the resulting consolidated "one flavor to rule them all" correctly handles networking denial-of-service attacks. One thing that allows RCU-bh to do so is that __do_softirq() invokes rcu_bh_qs() every so often, and so something similar has to happen for consolidated RCU. This must be done carefully. For example, if a preemption-disabled region of code takes an interrupt which does softirq processing before returning, consolidated RCU must ignore the resulting rcu_bh_qs() invocations -- preemption is still disabled, and that means an RCU reader for the consolidated flavor. This commit therefore creates a new rcu_softirq_qs() that is called only from the ksoftirqd task, thus avoiding the interrupted-a-preempted-region problem. This new rcu_softirq_qs() function invokes rcu_sched_qs(), rcu_preempt_qs(), and rcu_preempt_deferred_qs(). The latter call handles any deferred quiescent states. Note that __do_softirq() still invokes rcu_bh_qs(). It will continue to do so until a later stage of cleanup when the RCU-bh flavor is removed. Signed-off-by: Paul E. McKenney [ paulmck: Fix !SMP issue located by kbuild test robot. ] --- include/linux/rcutiny.h | 5 +++++ include/linux/rcutree.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index f617ab19bb51..bcfbc40a7239 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -90,6 +90,11 @@ static inline void kfree_call_rcu(struct rcu_head *head, call_rcu(head, func); } +static inline void rcu_softirq_qs(void) +{ + rcu_sched_qs(); +} + #define rcu_note_context_switch(preempt) \ do { \ rcu_sched_qs(); \ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 914655848ef6..664b580695d6 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -30,6 +30,7 @@ #ifndef __LINUX_RCUTREE_H #define __LINUX_RCUTREE_H +void rcu_softirq_qs(void); void rcu_note_context_switch(bool preempt); int rcu_needs_cpu(u64 basem, u64 *nextevt); void rcu_cpu_stall_reset(void); -- cgit v1.2.3 From 65cfe3583b612a22e12fba9a7bbd2d37ca5ad941 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 1 Jul 2018 07:40:52 -0700 Subject: rcu: Define RCU-bh update API in terms of RCU Now that the main RCU API knows about softirq disabling and softirq's quiescent states, the RCU-bh update code can be dispensed with. This commit therefore removes the RCU-bh update-side implementation and defines RCU-bh's update-side API in terms of that of either RCU-preempt or RCU-sched, depending on the setting of the CONFIG_PREEMPT Kconfig option. In kernels built with CONFIG_RCU_NOCB_CPU=y this has the knock-on effect of reducing by one the number of rcuo kthreads per CPU. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 10 ++++++---- include/linux/rcutiny.h | 10 +++++++--- include/linux/rcutree.h | 8 ++++++-- 3 files changed, 19 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 75e5b393cf44..9ebfd436cec7 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -55,11 +55,15 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func); #define call_rcu call_rcu_sched #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ -void call_rcu_bh(struct rcu_head *head, rcu_callback_t func); void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); void synchronize_sched(void); void rcu_barrier_tasks(void); +static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) +{ + call_rcu(head, func); +} + #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); @@ -104,7 +108,6 @@ static inline int rcu_preempt_depth(void) void rcu_init(void); extern int rcu_scheduler_active __read_mostly; void rcu_sched_qs(void); -void rcu_bh_qs(void); void rcu_check_callbacks(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); @@ -326,8 +329,7 @@ static inline void rcu_preempt_sleep_check(void) { } * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple flavors of pointers to match the multiple flavors of RCU - * (e.g., __rcu_bh, * __rcu_sched, and __srcu), should this make sense in - * the future. + * (e.g., __rcu_sched, and __srcu), should this make sense in the future. */ #ifdef __CHECKER__ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index bcfbc40a7239..ac26c27ccde8 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -56,19 +56,23 @@ static inline void cond_synchronize_sched(unsigned long oldstate) might_sleep(); } -extern void rcu_barrier_bh(void); -extern void rcu_barrier_sched(void); - static inline void synchronize_rcu_expedited(void) { synchronize_sched(); /* Only one CPU, so pretty fast anyway!!! */ } +extern void rcu_barrier_sched(void); + static inline void rcu_barrier(void) { rcu_barrier_sched(); /* Only one CPU, so only one list of callbacks! */ } +static inline void rcu_barrier_bh(void) +{ + rcu_barrier(); +} + static inline void synchronize_rcu_bh(void) { synchronize_sched(); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 664b580695d6..c789c302a2c9 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -45,7 +45,11 @@ static inline void rcu_virt_note_context_switch(int cpu) rcu_note_context_switch(false); } -void synchronize_rcu_bh(void); +static inline void synchronize_rcu_bh(void) +{ + synchronize_rcu(); +} + void synchronize_sched_expedited(void); void synchronize_rcu_expedited(void); @@ -69,7 +73,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); */ static inline void synchronize_rcu_bh_expedited(void) { - synchronize_sched_expedited(); + synchronize_rcu_expedited(); } void rcu_barrier(void); -- cgit v1.2.3 From 82fcecfa81855924cc69f3078113cf63dd6c2964 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 2 Jul 2018 09:04:27 -0700 Subject: rcu: Update comments and help text for no more RCU-bh updaters This commit updates comments and help text to account for the fact that RCU-bh update-side functions are now simple wrappers for their RCU or RCU-sched counterparts. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 12 ++++-------- include/linux/rcupdate_wait.h | 6 +++--- include/linux/rcutree.h | 14 ++------------ 3 files changed, 9 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9ebfd436cec7..8d5740edd63c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -688,14 +688,10 @@ static inline void rcu_read_unlock(void) /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * - * This is equivalent of rcu_read_lock(), but to be used when updates - * are being done using call_rcu_bh() or synchronize_rcu_bh(). Since - * both call_rcu_bh() and synchronize_rcu_bh() consider completion of a - * softirq handler to be a quiescent state, a process in RCU read-side - * critical section must be protected by disabling softirqs. Read-side - * critical sections in interrupt context can use just rcu_read_lock(), - * though this should at least be commented to avoid confusing people - * reading the code. + * This is equivalent of rcu_read_lock(), but also disables softirqs. + * Note that synchronize_rcu() and friends may be used for the update + * side, although synchronize_rcu_bh() is available as a wrapper in the + * short term. Longer term, the _bh update-side API will be eliminated. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index 57f371344152..bc104699560e 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -36,13 +36,13 @@ do { \ * @...: List of call_rcu() functions for the flavors to wait on. * * This macro waits concurrently for multiple flavors of RCU grace periods. - * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait - * on concurrent RCU and RCU-bh grace periods. Waiting on a give SRCU + * For example, synchronize_rcu_mult(call_rcu, call_rcu_sched) would wait + * on concurrent RCU and RCU-sched grace periods. Waiting on a give SRCU * domain requires you to write a wrapper function for that SRCU domain's * call_srcu() function, supplying the corresponding srcu_struct. * * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU - * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called + * or RCU-sched, given that anywhere synchronize_rcu_mult() can be called * is automatically a grace period. */ #define synchronize_rcu_mult(...) \ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index c789c302a2c9..f7a41323aa54 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -58,18 +58,8 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); /** * synchronize_rcu_bh_expedited - Brute-force RCU-bh grace period * - * Wait for an RCU-bh grace period to elapse, but use a "big hammer" - * approach to force the grace period to end quickly. This consumes - * significant time on all CPUs and is unfriendly to real-time workloads, - * so is thus not recommended for any sort of common-case code. In fact, - * if you are using synchronize_rcu_bh_expedited() in a loop, please - * restructure your code to batch your updates, and then use a single - * synchronize_rcu_bh() instead. - * - * Note that it is illegal to call this function while holding any lock - * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal - * to call this function from a CPU-hotplug notifier. Failing to observe - * these restriction will result in deadlock. + * This is a transitional API and will soon be removed, with all + * callers converted to synchronize_rcu_expedited(). */ static inline void synchronize_rcu_bh_expedited(void) { -- cgit v1.2.3 From 45975c7d21a1c0aba97e3d8007e2a7c123145748 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 2 Jul 2018 14:30:37 -0700 Subject: rcu: Define RCU-sched API in terms of RCU for Tree RCU PREEMPT builds Now that RCU-preempt knows about preemption disabling, its implementation of synchronize_rcu() works for synchronize_sched(), and likewise for the other RCU-sched update-side API members. This commit therefore confines the RCU-sched update-side code to CONFIG_PREEMPT=n builds, and defines RCU-sched's update-side API members in terms of those of RCU-preempt. This means that any given build of the Linux kernel has only one update-side flavor of RCU, namely RCU-preempt for CONFIG_PREEMPT=y builds and RCU-sched for CONFIG_PREEMPT=n builds. This in turn means that kernels built with CONFIG_RCU_NOCB_CPU=y have only one rcuo kthread per CPU. Signed-off-by: Paul E. McKenney Cc: Andi Kleen --- include/linux/rcupdate.h | 14 ++++---------- include/linux/rcutiny.h | 7 +++++++ include/linux/rcutree.h | 7 ++++++- 3 files changed, 17 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 8d5740edd63c..94474bb6b5c4 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -49,11 +49,11 @@ /* Exported common interfaces */ -#ifdef CONFIG_PREEMPT_RCU -void call_rcu(struct rcu_head *head, rcu_callback_t func); -#else /* #ifdef CONFIG_PREEMPT_RCU */ +#ifdef CONFIG_TINY_RCU #define call_rcu call_rcu_sched -#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ +#else +void call_rcu(struct rcu_head *head, rcu_callback_t func); +#endif void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); void synchronize_sched(void); @@ -92,11 +92,6 @@ static inline void __rcu_read_unlock(void) preempt_enable(); } -static inline void synchronize_rcu(void) -{ - synchronize_sched(); -} - static inline int rcu_preempt_depth(void) { return 0; @@ -107,7 +102,6 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active __read_mostly; -void rcu_sched_qs(void); void rcu_check_callbacks(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index ac26c27ccde8..df2c0895c5e7 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -36,6 +36,11 @@ static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) /* Never flag non-existent other CPUs! */ static inline bool rcu_eqs_special_set(int cpu) { return false; } +static inline void synchronize_rcu(void) +{ + synchronize_sched(); +} + static inline unsigned long get_state_synchronize_rcu(void) { return 0; @@ -94,6 +99,8 @@ static inline void kfree_call_rcu(struct rcu_head *head, call_rcu(head, func); } +void rcu_sched_qs(void); + static inline void rcu_softirq_qs(void) { rcu_sched_qs(); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index f7a41323aa54..0c44720f0e84 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -45,14 +45,19 @@ static inline void rcu_virt_note_context_switch(int cpu) rcu_note_context_switch(false); } +void synchronize_rcu(void); static inline void synchronize_rcu_bh(void) { synchronize_rcu(); } -void synchronize_sched_expedited(void); void synchronize_rcu_expedited(void); +static inline void synchronize_sched_expedited(void) +{ + synchronize_rcu_expedited(); +} + void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); /** -- cgit v1.2.3 From 709fdce7545c978e69f52eb19082ea3af44332f5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 3 Jul 2018 10:44:44 -0700 Subject: rcu: Express Tiny RCU updates in terms of RCU rather than RCU-sched This commit renames Tiny RCU functions so that the lowest level of functionality is RCU (e.g., synchronize_rcu()) rather than RCU-sched (e.g., synchronize_sched()). This provides greater naming compatibility with Tree RCU, which will in turn permit more LoC removal once the RCU-sched and RCU-bh update-side API is removed. Signed-off-by: Paul E. McKenney [ paulmck: Fix Tiny call_rcu()'s EXPORT_SYMBOL() in response to a bug report from kbuild test robot. ] --- include/linux/rcupdate.h | 12 +++++------- include/linux/rcutiny.h | 34 +++++++++++++++++++--------------- include/linux/rcutree.h | 1 - 3 files changed, 24 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 94474bb6b5c4..1207c6c9bd8b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -49,15 +49,14 @@ /* Exported common interfaces */ -#ifdef CONFIG_TINY_RCU -#define call_rcu call_rcu_sched -#else -void call_rcu(struct rcu_head *head, rcu_callback_t func); +#ifndef CONFIG_TINY_RCU +void synchronize_sched(void); +void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); #endif -void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); -void synchronize_sched(void); +void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); +void synchronize_rcu(void); static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) { @@ -68,7 +67,6 @@ static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) void __rcu_read_lock(void); void __rcu_read_unlock(void); -void synchronize_rcu(void); /* * Defined as a macro as it is a very low level header included from diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index df2c0895c5e7..e66fb8bc2127 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -36,9 +36,9 @@ static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) /* Never flag non-existent other CPUs! */ static inline bool rcu_eqs_special_set(int cpu) { return false; } -static inline void synchronize_rcu(void) +static inline void synchronize_sched(void) { - synchronize_sched(); + synchronize_rcu(); } static inline unsigned long get_state_synchronize_rcu(void) @@ -61,16 +61,11 @@ static inline void cond_synchronize_sched(unsigned long oldstate) might_sleep(); } -static inline void synchronize_rcu_expedited(void) -{ - synchronize_sched(); /* Only one CPU, so pretty fast anyway!!! */ -} +extern void rcu_barrier(void); -extern void rcu_barrier_sched(void); - -static inline void rcu_barrier(void) +static inline void rcu_barrier_sched(void) { - rcu_barrier_sched(); /* Only one CPU, so only one list of callbacks! */ + rcu_barrier(); /* Only one CPU, so only one list of callbacks! */ } static inline void rcu_barrier_bh(void) @@ -88,27 +83,36 @@ static inline void synchronize_rcu_bh_expedited(void) synchronize_sched(); } +static inline void synchronize_rcu_expedited(void) +{ + synchronize_sched(); +} + static inline void synchronize_sched_expedited(void) { synchronize_sched(); } -static inline void kfree_call_rcu(struct rcu_head *head, - rcu_callback_t func) +static inline void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) +{ + call_rcu(head, func); +} + +static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { call_rcu(head, func); } -void rcu_sched_qs(void); +void rcu_qs(void); static inline void rcu_softirq_qs(void) { - rcu_sched_qs(); + rcu_qs(); } #define rcu_note_context_switch(preempt) \ do { \ - rcu_sched_qs(); \ + rcu_qs(); \ rcu_tasks_qs(current); \ } while (0) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 0c44720f0e84..6d30a0809300 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -45,7 +45,6 @@ static inline void rcu_virt_note_context_switch(int cpu) rcu_note_context_switch(false); } -void synchronize_rcu(void); static inline void synchronize_rcu_bh(void) { synchronize_rcu(); -- cgit v1.2.3 From 4c7e9c1434c6fc960774a5475f2fbccbf557fdeb Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 6 Jul 2018 09:54:25 -0700 Subject: rcu: Consolidate RCU-bh update-side function definitions This commit saves a few lines by consolidating the RCU-bh function definitions at the end of include/linux/rcupdate.h. This consolidation also makes it easier to remove them all when the time comes. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 27 ++++++++++++++++++++++----- include/linux/rcutiny.h | 15 --------------- include/linux/rcutree.h | 17 ----------------- 3 files changed, 22 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 1207c6c9bd8b..e530f5739033 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -58,11 +58,6 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void synchronize_rcu(void); -static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) -{ - call_rcu(head, func); -} - #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); @@ -875,4 +870,26 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ +/* Transitional pre-consolidation compatibility definitions. */ + +static inline void synchronize_rcu_bh(void) +{ + synchronize_rcu(); +} + +static inline void synchronize_rcu_bh_expedited(void) +{ + synchronize_rcu_expedited(); +} + +static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) +{ + call_rcu(head, func); +} + +static inline void rcu_barrier_bh(void) +{ + rcu_barrier(); +} + #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index e66fb8bc2127..df82bada9b19 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -68,21 +68,6 @@ static inline void rcu_barrier_sched(void) rcu_barrier(); /* Only one CPU, so only one list of callbacks! */ } -static inline void rcu_barrier_bh(void) -{ - rcu_barrier(); -} - -static inline void synchronize_rcu_bh(void) -{ - synchronize_sched(); -} - -static inline void synchronize_rcu_bh_expedited(void) -{ - synchronize_sched(); -} - static inline void synchronize_rcu_expedited(void) { synchronize_sched(); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 6d30a0809300..94820156aa62 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -45,11 +45,6 @@ static inline void rcu_virt_note_context_switch(int cpu) rcu_note_context_switch(false); } -static inline void synchronize_rcu_bh(void) -{ - synchronize_rcu(); -} - void synchronize_rcu_expedited(void); static inline void synchronize_sched_expedited(void) @@ -59,19 +54,7 @@ static inline void synchronize_sched_expedited(void) void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); -/** - * synchronize_rcu_bh_expedited - Brute-force RCU-bh grace period - * - * This is a transitional API and will soon be removed, with all - * callers converted to synchronize_rcu_expedited(). - */ -static inline void synchronize_rcu_bh_expedited(void) -{ - synchronize_rcu_expedited(); -} - void rcu_barrier(void); -void rcu_barrier_bh(void); void rcu_barrier_sched(void); bool rcu_eqs_special_set(int cpu); unsigned long get_state_synchronize_rcu(void); -- cgit v1.2.3 From a8bb74acd8efe2eb934d524ae20859980975b602 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 6 Jul 2018 11:46:47 -0700 Subject: rcu: Consolidate RCU-sched update-side function definitions This commit saves a few lines by consolidating the RCU-sched function definitions at the end of include/linux/rcupdate.h. This consolidation also makes it easier to remove them all when the time comes. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 38 +++++++++++++++++++++++++++++++------- include/linux/rcutiny.h | 32 +------------------------------- include/linux/rcutree.h | 9 --------- 3 files changed, 32 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e530f5739033..12103e1bbe67 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -48,12 +48,6 @@ #define ulong2long(a) (*(long *)(&(a))) /* Exported common interfaces */ - -#ifndef CONFIG_TINY_RCU -void synchronize_sched(void); -void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); -#endif - void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void synchronize_rcu(void); @@ -170,7 +164,7 @@ void exit_tasks_rcu_finish(void); #define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) rcu_all_qs() #define call_rcu_tasks call_rcu_sched -#define synchronize_rcu_tasks synchronize_sched +#define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU */ @@ -892,4 +886,34 @@ static inline void rcu_barrier_bh(void) rcu_barrier(); } +static inline void synchronize_sched(void) +{ + synchronize_rcu(); +} + +static inline void synchronize_sched_expedited(void) +{ + synchronize_rcu_expedited(); +} + +static inline void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) +{ + call_rcu(head, func); +} + +static inline void rcu_barrier_sched(void) +{ + rcu_barrier(); +} + +static inline unsigned long get_state_synchronize_sched(void) +{ + return get_state_synchronize_rcu(); +} + +static inline void cond_synchronize_sched(unsigned long oldstate) +{ + cond_synchronize_rcu(oldstate); +} + #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index df82bada9b19..7fa4fb9e899e 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -36,11 +36,6 @@ static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) /* Never flag non-existent other CPUs! */ static inline bool rcu_eqs_special_set(int cpu) { return false; } -static inline void synchronize_sched(void) -{ - synchronize_rcu(); -} - static inline unsigned long get_state_synchronize_rcu(void) { return 0; @@ -51,36 +46,11 @@ static inline void cond_synchronize_rcu(unsigned long oldstate) might_sleep(); } -static inline unsigned long get_state_synchronize_sched(void) -{ - return 0; -} - -static inline void cond_synchronize_sched(unsigned long oldstate) -{ - might_sleep(); -} - extern void rcu_barrier(void); -static inline void rcu_barrier_sched(void) -{ - rcu_barrier(); /* Only one CPU, so only one list of callbacks! */ -} - static inline void synchronize_rcu_expedited(void) { - synchronize_sched(); -} - -static inline void synchronize_sched_expedited(void) -{ - synchronize_sched(); -} - -static inline void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) -{ - call_rcu(head, func); + synchronize_rcu(); } static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 94820156aa62..d09a9abe9440 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -46,21 +46,12 @@ static inline void rcu_virt_note_context_switch(int cpu) } void synchronize_rcu_expedited(void); - -static inline void synchronize_sched_expedited(void) -{ - synchronize_rcu_expedited(); -} - void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier(void); -void rcu_barrier_sched(void); bool rcu_eqs_special_set(int cpu); unsigned long get_state_synchronize_rcu(void); void cond_synchronize_rcu(unsigned long oldstate); -unsigned long get_state_synchronize_sched(void); -void cond_synchronize_sched(unsigned long oldstate); void rcu_idle_enter(void); void rcu_idle_exit(void); -- cgit v1.2.3 From 2bd8b1a2afc4463cc503665e98faa5909d1ac462 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 7 Jul 2018 18:12:26 -0700 Subject: rcu: Clean up flavor-related definitions and comments in rcupdate.h Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 12103e1bbe67..d6d543b60a9f 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -119,11 +119,10 @@ static inline void rcu_init_nohz(void) { } * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers * @a: Code that RCU needs to pay attention to. * - * RCU, RCU-bh, and RCU-sched read-side critical sections are forbidden - * in the inner idle loop, that is, between the rcu_idle_enter() and - * the rcu_idle_exit() -- RCU will happily ignore any such read-side - * critical sections. However, things like powertop need tracepoints - * in the inner idle loop. + * RCU read-side critical sections are forbidden in the inner idle loop, + * that is, between the rcu_idle_enter() and the rcu_idle_exit() -- RCU + * will happily ignore any such read-side critical sections. However, + * things like powertop need tracepoints in the inner idle loop. * * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) * will tell RCU that it needs to pay attention, invoke its argument @@ -163,7 +162,7 @@ void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ #define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) rcu_all_qs() -#define call_rcu_tasks call_rcu_sched +#define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } @@ -309,8 +308,8 @@ static inline void rcu_preempt_sleep_check(void) { } * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of - * multiple flavors of pointers to match the multiple flavors of RCU - * (e.g., __rcu_sched, and __srcu), should this make sense in the future. + * multiple pointers markings to match different RCU implementations + * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ @@ -670,9 +669,8 @@ static inline void rcu_read_unlock(void) * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent of rcu_read_lock(), but also disables softirqs. - * Note that synchronize_rcu() and friends may be used for the update - * side, although synchronize_rcu_bh() is available as a wrapper in the - * short term. Longer term, the _bh update-side API will be eliminated. + * Note that anything else that disables softirqs can also serve as + * an RCU read-side critical section. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke @@ -705,10 +703,9 @@ static inline void rcu_read_unlock_bh(void) /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * - * This is equivalent of rcu_read_lock(), but to be used when updates - * are being done using call_rcu_sched() or synchronize_rcu_sched(). - * Read-side critical sections can also be introduced by anything that - * disables preemption, including local_irq_disable() and friends. + * This is equivalent of rcu_read_lock(), but disables preemption. + * Read-side critical sections can also be introduced by anything else + * that disables preemption, including local_irq_disable() and friends. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke -- cgit v1.2.3 From aff5f0369e312b0ab0ca7a2a12dd64b7e39c7091 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 7 Jul 2018 18:12:26 -0700 Subject: rcu: Clean up flavor-related definitions and comments in rculist.h Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 32 +++++++++++++++----------------- 1 file changed, 15 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 4786c2235b98..e91ec9ddcd30 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -182,7 +182,7 @@ static inline void list_replace_rcu(struct list_head *old, * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list - * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. @@ -240,7 +240,7 @@ static inline void __list_splice_init_rcu(struct list_head *list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into - * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, @@ -255,7 +255,7 @@ static inline void list_splice_init_rcu(struct list_head *list, * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into - * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, @@ -359,13 +359,12 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * - * This primitive may safely run concurrently with the _rcu list-mutation - * primitives such as list_add_rcu(), but requires some implicit RCU - * read-side guarding. One example is running within a special - * exception-time environment where preemption is disabled and where - * lockdep cannot be invoked (in which case updaters must use RCU-sched, - * as in synchronize_sched(), call_rcu_sched(), and friends). Another - * example is when items are added to the list, but never deleted. + * This primitive may safely run concurrently with the _rcu + * list-mutation primitives such as list_add_rcu(), but requires some + * implicit RCU read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where lockdep + * cannot be invoked. Another example is when items are added to the list, + * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) @@ -376,13 +375,12 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * @head: the head for your list. * @member: the name of the list_struct within the struct. * - * This primitive may safely run concurrently with the _rcu list-mutation - * primitives such as list_add_rcu(), but requires some implicit RCU - * read-side guarding. One example is running within a special - * exception-time environment where preemption is disabled and where - * lockdep cannot be invoked (in which case updaters must use RCU-sched, - * as in synchronize_sched(), call_rcu_sched(), and friends). Another - * example is when items are added to the list, but never deleted. + * This primitive may safely run concurrently with the _rcu + * list-mutation primitives such as list_add_rcu(), but requires some + * implicit RCU read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where lockdep + * cannot be invoked. Another example is when items are added to the list, + * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ -- cgit v1.2.3 From df8561a0d7e4f5cb72d0aa6be43e154b2027bba6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 7 Jul 2018 18:12:26 -0700 Subject: rcu: Clean up flavor-related definitions and comments in rcupdate_wait.h Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_wait.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index bc104699560e..8a16c3eb3dd0 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -33,17 +33,17 @@ do { \ /** * synchronize_rcu_mult - Wait concurrently for multiple grace periods - * @...: List of call_rcu() functions for the flavors to wait on. + * @...: List of call_rcu() functions for different grace periods to wait on * - * This macro waits concurrently for multiple flavors of RCU grace periods. - * For example, synchronize_rcu_mult(call_rcu, call_rcu_sched) would wait - * on concurrent RCU and RCU-sched grace periods. Waiting on a give SRCU + * This macro waits concurrently for multiple types of RCU grace periods. + * For example, synchronize_rcu_mult(call_rcu, call_rcu_tasks) would wait + * on concurrent RCU and RCU-tasks grace periods. Waiting on a give SRCU * domain requires you to write a wrapper function for that SRCU domain's * call_srcu() function, supplying the corresponding srcu_struct. * - * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU - * or RCU-sched, given that anywhere synchronize_rcu_mult() can be called - * is automatically a grace period. + * If Tiny RCU, tell _wait_rcu_gp() does not bother waiting for RCU, + * given that anywhere synchronize_rcu_mult() can be called is automatically + * a grace period. */ #define synchronize_rcu_mult(...) \ _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) -- cgit v1.2.3 From 4d232dfe1df35254298e7986c4de8c9f63f58c79 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 10 Jul 2018 12:53:40 -0700 Subject: rcu: Remove !PREEMPT code from rcu_note_voluntary_context_switch() Because RCU-tasks exists only in PREEMPT kernels and because RCU-sched no longer exists in PREEMPT kernels, it is no longer necessary for the rcu_note_voluntary_context_switch() macro to do anything for !PREEMPT kernels. This commit therefore removes !PREEMPT-related code from this macro, namely, the rcu_all_qs(). Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index d6d543b60a9f..e4f821165d0b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -150,18 +150,14 @@ static inline void rcu_init_nohz(void) { } if (READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) -#define rcu_note_voluntary_context_switch(t) \ - do { \ - rcu_all_qs(); \ - rcu_tasks_qs(t); \ - } while (0) +#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ #define rcu_tasks_qs(t) do { } while (0) -#define rcu_note_voluntary_context_switch(t) rcu_all_qs() +#define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } -- cgit v1.2.3 From 395a2f097ebdddf2bfa286b6119f1b231025c2f1 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 10 Jul 2018 14:00:14 -0700 Subject: rcu: Define rcu_all_qs() only in !PREEMPT builds Now that rcu_all_qs() is used only in !PREEMPT builds, move it to tree_plugin.h so that it is defined only in those builds. This in turn means that rcu_momentary_dyntick_idle() is only used in !PREEMPT builds, but it is simply marked __maybe_unused in order to keep it near the rest of the dyntick-idle code. Signed-off-by: Paul E. McKenney --- include/linux/rcutree.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index d09a9abe9440..7f83179177d1 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -66,7 +66,9 @@ void rcu_scheduler_starting(void); extern int rcu_scheduler_active __read_mostly; void rcu_end_inkernel_boot(void); bool rcu_is_watching(void); +#ifndef CONFIG_PREEMPT void rcu_all_qs(void); +#endif /* RCUtree hotplug events */ int rcutree_prepare_cpu(unsigned int cpu); -- cgit v1.2.3 From 74de6960c99d8df0d09fb29a7b014cb9c5571e2b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 24 Jul 2018 15:28:09 -0700 Subject: rcu: Provide functions for determining if call_rcu() has been invoked This commit adds rcu_head_init() and rcu_head_after_call_rcu() functions to help RCU users detect when another CPU has passed the specified rcu_head structure and function to call_rcu(). The rcu_head_init() should be invoked before making the structure visible to RCU readers, and then the rcu_head_after_call_rcu() may be invoked from within an RCU read-side critical section on an rcu_head structure that was obtained during a traversal of the data structure in question. The rcu_head_after_call_rcu() function will return true if the rcu_head structure has already been passed (with the specified function) to call_rcu(), otherwise it will return false. If rcu_head_init() has not been invoked on the rcu_head structure or if the rcu_head (AKA callback) has already been invoked, then rcu_head_after_call_rcu() will do WARN_ON_ONCE(). Reported-by: NeilBrown Signed-off-by: Paul E. McKenney [ paulmck: Apply neilb naming feedback. ] --- include/linux/rcupdate.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e4f821165d0b..4db8bcacc51a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -857,6 +857,46 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ +/* Has the specified rcu_head structure been handed to call_rcu()? */ + +/* + * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() + * @rhp: The rcu_head structure to initialize. + * + * If you intend to invoke rcu_head_after_call_rcu() to test whether a + * given rcu_head structure has already been passed to call_rcu(), then + * you must also invoke this rcu_head_init() function on it just after + * allocating that structure. Calls to this function must not race with + * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. + */ +static inline void rcu_head_init(struct rcu_head *rhp) +{ + rhp->func = (rcu_callback_t)~0L; +} + +/* + * rcu_head_after_call_rcu - Has this rcu_head been passed to call_rcu()? + * @rhp: The rcu_head structure to test. + * @func: The function passed to call_rcu() along with @rhp. + * + * Returns @true if the @rhp has been passed to call_rcu() with @func, + * and @false otherwise. Emits a warning in any other case, including + * the case where @rhp has already been invoked after a grace period. + * Calls to this function must not race with callback invocation. One way + * to avoid such races is to enclose the call to rcu_head_after_call_rcu() + * in an RCU read-side critical section that includes a read-side fetch + * of the pointer to the structure containing @rhp. + */ +static inline bool +rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) +{ + if (READ_ONCE(rhp->func) == f) + return true; + WARN_ON_ONCE(READ_ONCE(rhp->func) != (rcu_callback_t)~0L); + return false; +} + + /* Transitional pre-consolidation compatibility definitions. */ static inline void synchronize_rcu_bh(void) -- cgit v1.2.3 From 31ab604bf3232374e6471a2df9a83c4e75538390 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 3 Aug 2018 16:15:54 -0700 Subject: rcu: Remove unused rcu_dynticks_snap() from Tiny RCU The rcu_dynticks_snap() function is defined in include/linux/rcutiny.h, but is no longer used by Tiny RCU. This commit therefore removes it. Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 7fa4fb9e899e..f183683bdf79 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -27,12 +27,6 @@ #include -struct rcu_dynticks; -static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) -{ - return 0; -} - /* Never flag non-existent other CPUs! */ static inline bool rcu_eqs_special_set(int cpu) { return false; } -- cgit v1.2.3 From e0fcba9ac02af5aeb1e1c3e842eab987f817c309 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 14 Aug 2018 08:45:54 -0700 Subject: srcu: Make call_srcu() available during very early boot Event tracing is moving to SRCU in order to take advantage of the fact that SRCU may be safely used from idle and even offline CPUs. However, event tracing can invoke call_srcu() very early in the boot process, even before workqueue_init_early() is invoked (let alone rcu_init()). Therefore, call_srcu()'s attempts to queue work fail miserably. This commit therefore detects this situation, and refrains from attempting to queue work before rcu_init() time, but does everything else that it would have done, and in addition, adds the srcu_struct to a global list. The rcu_init() function now invokes a new srcu_init() function, which is empty if CONFIG_SRCU=n. Otherwise, srcu_init() queues work for each srcu_struct on the list. This all happens early enough in boot that there is but a single CPU with interrupts disabled, which allows synchronization to be dispensed with. Of course, the queued work won't actually be invoked until after workqueue_init() is invoked, which happens shortly after the scheduler is up and running. This means that although call_srcu() may be invoked any time after per-CPU variables have been set up, there is still a very narrow window when synchronize_srcu() won't work, and this window extends from the time that the scheduler starts until the time that workqueue_init() returns. This can be fixed in a manner similar to the fix for synchronize_rcu_expedited() and friends, but until someone actually needs to use synchronize_srcu() during this window, this fix is added churn for no benefit. Finally, note that Tree SRCU's new srcu_init() function invokes queue_work() rather than the queue_delayed_work() function that is invoked post-boot. The reason is that queue_delayed_work() will (as you would expect) post a timer, and timers have not yet been initialized. So use of queue_work() avoids the complaints about use of uninitialized spinlocks that would otherwise result. Besides, some delay is already provide by the aforementioned fact that the queued work won't actually be invoked until after the scheduler is up and running. Requested-by: Steven Rostedt Signed-off-by: Paul E. McKenney Tested-by: Steven Rostedt (VMware) --- include/linux/srcutiny.h | 2 ++ include/linux/srcutree.h | 14 ++++++++------ 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index f41d2fb09f87..2b5c0822e683 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -36,6 +36,7 @@ struct srcu_struct { struct rcu_head *srcu_cb_head; /* Pending callbacks: Head. */ struct rcu_head **srcu_cb_tail; /* Pending callbacks: Tail. */ struct work_struct srcu_work; /* For driving grace periods. */ + struct list_head srcu_boot_entry; /* Early-boot callbacks. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -48,6 +49,7 @@ void srcu_drive_gp(struct work_struct *wp); .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ .srcu_cb_tail = &name.srcu_cb_head, \ .srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \ + .srcu_boot_entry = LIST_HEAD_INIT(name.srcu_boot_entry), \ __SRCU_DEP_MAP_INIT(name) \ } diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 745d4ca4dd50..9cfa4610113a 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -94,6 +94,7 @@ struct srcu_struct { /* callback for the barrier */ /* operation. */ struct delayed_work work; + struct list_head srcu_boot_entry; /* Early-boot callbacks. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -105,12 +106,13 @@ struct srcu_struct { #define SRCU_STATE_SCAN2 2 #define __SRCU_STRUCT_INIT(name, pcpu_name) \ - { \ - .sda = &pcpu_name, \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .srcu_gp_seq_needed = 0 - 1, \ - __SRCU_DEP_MAP_INIT(name) \ - } +{ \ + .sda = &pcpu_name, \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .srcu_gp_seq_needed = -1UL, \ + .srcu_boot_entry = LIST_HEAD_INIT(name.srcu_boot_entry), \ + __SRCU_DEP_MAP_INIT(name) \ +} /* * Define and initialize a srcu struct at build time. -- cgit v1.2.3 From 4e6ea4ef56f9425cd239ffdb6be45b3aeeb347fd Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 14 Aug 2018 14:41:49 -0700 Subject: srcu: Make early-boot call_srcu() reuse workqueue lists Allocating a list_head structure that is almost never used, and, when used, is used only during early boot (rcu_init() and earlier), is a bit wasteful. This commit therefore eliminates that list_head in favor of the one in the work_struct structure. This is safe because the work_struct structure cannot be used until after rcu_init() returns. Reported-by: Steven Rostedt Signed-off-by: Paul E. McKenney Cc: Tejun Heo Cc: Lai Jiangshan Tested-by: Steven Rostedt (VMware) --- include/linux/srcutiny.h | 2 -- include/linux/srcutree.h | 3 +-- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 2b5c0822e683..f41d2fb09f87 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -36,7 +36,6 @@ struct srcu_struct { struct rcu_head *srcu_cb_head; /* Pending callbacks: Head. */ struct rcu_head **srcu_cb_tail; /* Pending callbacks: Tail. */ struct work_struct srcu_work; /* For driving grace periods. */ - struct list_head srcu_boot_entry; /* Early-boot callbacks. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -49,7 +48,6 @@ void srcu_drive_gp(struct work_struct *wp); .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ .srcu_cb_tail = &name.srcu_cb_head, \ .srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \ - .srcu_boot_entry = LIST_HEAD_INIT(name.srcu_boot_entry), \ __SRCU_DEP_MAP_INIT(name) \ } diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 9cfa4610113a..0ae91b3a7406 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -94,7 +94,6 @@ struct srcu_struct { /* callback for the barrier */ /* operation. */ struct delayed_work work; - struct list_head srcu_boot_entry; /* Early-boot callbacks. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -110,7 +109,7 @@ struct srcu_struct { .sda = &pcpu_name, \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq_needed = -1UL, \ - .srcu_boot_entry = LIST_HEAD_INIT(name.srcu_boot_entry), \ + .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ __SRCU_DEP_MAP_INIT(name) \ } -- cgit v1.2.3 From 0413bedabc886c3a56804d1c80a58e99077b1d91 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 28 Aug 2018 15:10:48 -0500 Subject: of: Add device_type access helper functions In preparation to remove direct access to device_node.type, add of_node_is_type() and of_node_get_device_type() helpers to check and retrieve the device type. Cc: Frank Rowand Signed-off-by: Rob Herring --- include/linux/of.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 688c52dd7b3e..99b0ebf49632 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -988,6 +988,18 @@ static inline struct device_node *of_find_matching_node( return of_find_matching_node_and_match(from, matches, NULL); } +static inline const char *of_node_get_device_type(const struct device_node *np) +{ + return of_get_property(np, "type", NULL); +} + +static inline bool of_node_is_type(const struct device_node *np, const char *type) +{ + const char *match = of_node_get_device_type(np); + + return np && match && type && !strcmp(match, type); +} + /** * of_property_count_u8_elems - Count the number of u8 elements in a property * -- cgit v1.2.3 From ef394f3fbecbe61d69450ad8cf0fa8f713c8ce8f Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 31 Aug 2018 14:34:02 +0200 Subject: regulator: da9063: fix DT probing with constraints Commit 1c892e38ce59 ("regulator: da9063: Handle less LDOs on DA9063L") reordered the da9063_regulator_info[] array, but not the DA9063_ID_* regulator ids and not the da9063_matches[] array, because ids are used as indices in the array initializer. This mismatch between regulator id and da9063_regulator_info[] array index causes the driver probe to fail because constraints from DT are not applied to the correct regulator: da9063 0-0058: Device detected (chip-ID: 0x61, var-ID: 0x50) DA9063_BMEM: Bringing 900000uV into 3300000-3300000uV DA9063_LDO9: Bringing 3300000uV into 2500000-2500000uV DA9063_LDO1: Bringing 900000uV into 3300000-3300000uV DA9063_LDO1: failed to apply 3300000-3300000uV constraint(-22) This patch reorders the DA9063_ID_* as apparently intended, and with them the entries in the da90630_matches[] array. Fixes: 1c892e38ce59 ("regulator: da9063: Handle less LDOs on DA9063L") Signed-off-by: Philipp Zabel Reviewed-by: Geert Uytterhoeven Reviewed-by: Marek Vasut Signed-off-by: Mark Brown --- include/linux/mfd/da9063/pdata.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/pdata.h b/include/linux/mfd/da9063/pdata.h index 8a125701ef7b..50bed4f89c1a 100644 --- a/include/linux/mfd/da9063/pdata.h +++ b/include/linux/mfd/da9063/pdata.h @@ -21,7 +21,7 @@ /* * Regulator configuration */ -/* DA9063 regulator IDs */ +/* DA9063 and DA9063L regulator IDs */ enum { /* BUCKs */ DA9063_ID_BCORE1, @@ -37,18 +37,20 @@ enum { DA9063_ID_BMEM_BIO_MERGED, /* When two BUCKs are merged, they cannot be reused separately */ - /* LDOs */ + /* LDOs on both DA9063 and DA9063L */ + DA9063_ID_LDO3, + DA9063_ID_LDO7, + DA9063_ID_LDO8, + DA9063_ID_LDO9, + DA9063_ID_LDO11, + + /* DA9063-only LDOs */ DA9063_ID_LDO1, DA9063_ID_LDO2, - DA9063_ID_LDO3, DA9063_ID_LDO4, DA9063_ID_LDO5, DA9063_ID_LDO6, - DA9063_ID_LDO7, - DA9063_ID_LDO8, - DA9063_ID_LDO9, DA9063_ID_LDO10, - DA9063_ID_LDO11, }; /* Regulators platform data */ -- cgit v1.2.3 From 6b06546206868f723f2061d703a3c3c378dcbf4c Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Fri, 31 Aug 2018 16:22:42 -0400 Subject: Revert "blk-throttle: fix race between blkcg_bio_issue_check() and cgroup_rmdir()" This reverts commit 4c6994806f708559c2812b73501406e21ae5dcd0. Destroying blkgs is tricky because of the nature of the relationship. A blkg should go away when either a blkcg or a request_queue goes away. However, blkg's pin the blkcg to ensure they remain valid. To break this cycle, when a blkcg is offlined, blkgs put back their css ref. This eventually lets css_free() get called which frees the blkcg. The above commit (4c6994806f70) breaks this order of events by trying to destroy blkgs in css_free(). As the blkgs still hold references to the blkcg, css_free() is never called. The race between blkcg_bio_issue_check() and cgroup_rmdir() will be addressed in the following patch by delaying destruction of a blkg until all writeback associated with the blkcg has been finished. Fixes: 4c6994806f70 ("blk-throttle: fix race between blkcg_bio_issue_check() and cgroup_rmdir()") Reviewed-by: Josef Bacik Signed-off-by: Dennis Zhou Cc: Jiufei Xue Cc: Joseph Qi Cc: Tejun Heo Cc: Jens Axboe Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 34aec30e06c7..1615cdd4c797 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -89,7 +89,6 @@ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; - bool offline; }; /* -- cgit v1.2.3 From 59b57717fff8b562825d9d25e0180ad7e8048ca9 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Fri, 31 Aug 2018 16:22:43 -0400 Subject: blkcg: delay blkg destruction until after writeback has finished Currently, blkcg destruction relies on a sequence of events: 1. Destruction starts. blkcg_css_offline() is called and blkgs release their reference to the blkcg. This immediately destroys the cgwbs (writeback). 2. With blkgs giving up their reference, the blkcg ref count should become zero and eventually call blkcg_css_free() which finally frees the blkcg. Jiufei Xue reported that there is a race between blkcg_bio_issue_check() and cgroup_rmdir(). To remedy this, blkg destruction becomes contingent on the completion of all writeback associated with the blkcg. A count of the number of cgwbs is maintained and once that goes to zero, blkg destruction can follow. This should prevent premature blkg destruction related to writeback. The new process for blkcg cleanup is as follows: 1. Destruction starts. blkcg_css_offline() is called which offlines writeback. Blkg destruction is delayed on the cgwb_refcnt count to avoid punting potentially large amounts of outstanding writeback to root while maintaining any ongoing policies. Here, the base cgwb_refcnt is put back. 2. When the cgwb_refcnt becomes zero, blkcg_destroy_blkgs() is called and handles destruction of blkgs. This is where the css reference held by each blkg is released. 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. This finally frees the blkg. It seems in the past blk-throttle didn't do the most understandable things with taking data from a blkg while associating with current. So, the simplification and unification of what blk-throttle is doing caused this. Fixes: 08e18eab0c579 ("block: add bi_blkg to the bio for cgroups") Reviewed-by: Josef Bacik Signed-off-by: Dennis Zhou Cc: Jiufei Xue Cc: Joseph Qi Cc: Tejun Heo Cc: Josef Bacik Cc: Jens Axboe Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1615cdd4c797..6d766a19f2bb 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -56,6 +56,7 @@ struct blkcg { struct list_head all_blkcgs_node; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; + refcount_t cgwb_refcnt; #endif }; @@ -386,6 +387,49 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) return cpd ? cpd->blkcg : NULL; } +extern void blkcg_destroy_blkgs(struct blkcg *blkcg); + +#ifdef CONFIG_CGROUP_WRITEBACK + +/** + * blkcg_cgwb_get - get a reference for blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + */ +static inline void blkcg_cgwb_get(struct blkcg *blkcg) +{ + refcount_inc(&blkcg->cgwb_refcnt); +} + +/** + * blkcg_cgwb_put - put a reference for @blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + * When this count goes to zero, all active wb has finished so the + * blkcg can continue destruction by calling blkcg_destroy_blkgs(). + * This work may occur in cgwb_release_workfn() on the cgwb_release + * workqueue. + */ +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + if (refcount_dec_and_test(&blkcg->cgwb_refcnt)) + blkcg_destroy_blkgs(blkcg); +} + +#else + +static inline void blkcg_cgwb_get(struct blkcg *blkcg) { } + +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + /* wb isn't being accounted, so trigger destruction right away */ + blkcg_destroy_blkgs(blkcg); +} + +#endif + /** * blkg_path - format cgroup path of blkg * @blkg: blkg of interest -- cgit v1.2.3 From c43c5e9f524ec914e7e202f9c5ab91779629ccc6 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Mon, 3 Sep 2018 10:15:33 +0200 Subject: timekeeping: Fix declaration of read_persistent_wall_and_boot_offset() It is read_persistent_wall_and_boot_offset() and not read_persistent_clock_and_boot_offset() Fixes: 3eca993740b8eb40f51 ("timekeeping: Replace read_boot_clock64() with read_persistent_wall_and_boot_offset()") Signed-off-by: Christian Borntraeger Signed-off-by: Thomas Gleixner Cc: Pavel Tatashin Link: https://lkml.kernel.org/r/20180903081533.34366-1-borntraeger@de.ibm.com --- include/linux/timekeeping.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 5d738804e3d6..a5a3cfc3c2fa 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -258,8 +258,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); -void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock, - struct timespec64 *boot_offset); +void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, + struct timespec64 *boot_offset); extern int update_persistent_clock64(struct timespec64 now); /* -- cgit v1.2.3 From 4ac695464763ecf696eaba563eff1c2ab994f6d8 Mon Sep 17 00:00:00 2001 From: Eric Long Date: Tue, 28 Aug 2018 19:09:07 +0800 Subject: dmaengine: sprd: Support DMA link-list mode The Spreadtrum DMA can support the link-list transaction mode, which means DMA controller can do transaction one by one automatically once we linked these transaction by link-list register. Signed-off-by: Eric Long Signed-off-by: Baolin Wang Signed-off-by: Vinod Koul --- include/linux/dma/sprd-dma.h | 69 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma/sprd-dma.h b/include/linux/dma/sprd-dma.h index b0115e340fbc..b42b80e52cc2 100644 --- a/include/linux/dma/sprd-dma.h +++ b/include/linux/dma/sprd-dma.h @@ -58,4 +58,73 @@ enum sprd_dma_int_type { SPRD_DMA_CFGERR_INT, }; +/* + * struct sprd_dma_linklist - DMA link-list address structure + * @virt_addr: link-list virtual address to configure link-list node + * @phy_addr: link-list physical address to link DMA transfer + * + * The Spreadtrum DMA controller supports the link-list mode, that means slaves + * can supply several groups configurations (each configuration represents one + * DMA transfer) saved in memory, and DMA controller will link these groups + * configurations by writing the physical address of each configuration into the + * link-list register. + * + * Just as shown below, the link-list pointer register will be pointed to the + * physical address of 'configuration 1', and the 'configuration 1' link-list + * pointer will be pointed to 'configuration 2', and so on. + * Once trigger the DMA transfer, the DMA controller will load 'configuration + * 1' to its registers automatically, after 'configuration 1' transaction is + * done, DMA controller will load 'configuration 2' automatically, until all + * DMA transactions are done. + * + * Note: The last link-list pointer should point to the physical address + * of 'configuration 1', which can avoid DMA controller loads incorrect + * configuration when the last configuration transaction is done. + * + * DMA controller linklist memory + * ====================== ----------------------- + *| | | configuration 1 |<--- + *| DMA controller | ------->| | | + *| | | | | | + *| | | | | | + *| | | | | | + *| linklist pointer reg |---- ----| linklist pointer | | + * ====================== | ----------------------- | + * | | + * | ----------------------- | + * | | configuration 2 | | + * --->| | | + * | | | + * | | | + * | | | + * ----| linklist pointer | | + * | ----------------------- | + * | | + * | ----------------------- | + * | | configuration 3 | | + * --->| | | + * | | | + * | . | | + * . | + * . | + * . | + * | . | + * | ----------------------- | + * | | configuration n | | + * --->| | | + * | | | + * | | | + * | | | + * | linklist pointer |---- + * ----------------------- + * + * To support the link-list mode, DMA slaves should allocate one segment memory + * from always-on IRAM or dma coherent memory to store these groups of DMA + * configuration, and pass the virtual and physical address to DMA controller. + */ +struct sprd_dma_linklist { + unsigned long virt_addr; + phys_addr_t phy_addr; +}; + #endif -- cgit v1.2.3 From 9da3f2b74054406f87dff7101a569217ffceb29b Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 28 Aug 2018 22:14:20 +0200 Subject: x86/fault: BUG() when uaccess helpers fault on kernel addresses There have been multiple kernel vulnerabilities that permitted userspace to pass completely unchecked pointers through to userspace accessors: - the waitid() bug - commit 96ca579a1ecc ("waitid(): Add missing access_ok() checks") - the sg/bsg read/write APIs - the infiniband read/write APIs These don't happen all that often, but when they do happen, it is hard to test for them properly; and it is probably also hard to discover them with fuzzing. Even when an unmapped kernel address is supplied to such buggy code, it just returns -EFAULT instead of doing a proper BUG() or at least WARN(). Try to make such misbehaving code a bit more visible by refusing to do a fixup in the pagefault handler code when a userspace accessor causes a #PF on a kernel address and the current context isn't whitelisted. Signed-off-by: Jann Horn Signed-off-by: Thomas Gleixner Tested-by: Kees Cook Cc: Andy Lutomirski Cc: kernel-hardening@lists.openwall.com Cc: dvyukov@google.com Cc: Masami Hiramatsu Cc: "Naveen N. Rao" Cc: Anil S Keshavamurthy Cc: "David S. Miller" Cc: Alexander Viro Cc: linux-fsdevel@vger.kernel.org Cc: Borislav Petkov Link: https://lkml.kernel.org/r/20180828201421.157735-7-jannh@google.com --- include/linux/sched.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 977cb57d7bc9..56dd65f1be4f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -739,6 +739,12 @@ struct task_struct { unsigned use_memdelay:1; #endif + /* + * May usercopy functions fault on kernel addresses? + * This is not just a single bit because this can potentially nest. + */ + unsigned int kernel_uaccess_faults_ok; + unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; -- cgit v1.2.3 From 1e6cb72399fd58b38a1c11055ef18fe01f535cda Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 1 Sep 2018 10:41:11 +0300 Subject: fsnotify: add super block object type Add the infrastructure to attach a mark to a super_block struct and detach all attached marks when super block is destroyed. This is going to be used by fanotify backend to setup super block marks. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fs.h | 5 +++++ include/linux/fsnotify_backend.h | 17 ++++++++++++++--- 2 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 33322702c910..2c14801d0aa3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1464,6 +1464,11 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ + +#ifdef CONFIG_FSNOTIFY + __u32 s_fsnotify_mask; + struct fsnotify_mark_connector __rcu *s_fsnotify_marks; +#endif } __randomize_layout; /* Helper functions so that in most cases filesystems will diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b8f4182f42f1..81b88fc9df31 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -206,12 +206,14 @@ struct fsnotify_group { enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_VFSMOUNT, + FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; #define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE) #define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) +#define FSNOTIFY_OBJ_TYPE_SB_FL (1U << FSNOTIFY_OBJ_TYPE_SB) #define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) static inline bool fsnotify_valid_obj_type(unsigned int type) @@ -255,6 +257,7 @@ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) +FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_obj_type(type) \ for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++) @@ -267,8 +270,8 @@ struct fsnotify_mark_connector; typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; /* - * Inode / vfsmount point to this structure which tracks all marks attached to - * the inode / vfsmount. The reference to inode / vfsmount is held by this + * Inode/vfsmount/sb point to this structure which tracks all marks attached to + * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached * to it. The structure is protected by fsnotify_mark_srcu. */ @@ -335,6 +338,7 @@ extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int dat extern int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); +extern void fsnotify_sb_delete(struct super_block *sb); extern u32 fsnotify_get_cookie(void); static inline int fsnotify_inode_watches_children(struct inode *inode) @@ -455,9 +459,13 @@ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *gr { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL); } +/* run all the marks in a group, and clear all of the sn marks */ +static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) +{ + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB_FL); +} extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); -extern void fsnotify_unmount_inodes(struct super_block *sb); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); @@ -484,6 +492,9 @@ static inline void __fsnotify_inode_delete(struct inode *inode) static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} +static inline void fsnotify_sb_delete(struct super_block *sb) +{} + static inline void fsnotify_update_flags(struct dentry *dentry) {} -- cgit v1.2.3 From 3edd79cf5a44b12dbb13bc320f5788aed6562b36 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 3 Sep 2018 16:49:37 +0200 Subject: regulator: Fix 'do-nothing' value for regulators without suspend state Some regulators don't have all states defined and in such cases regulator core should not assume anything. However in current implementation of of_get_regulation_constraints() DO_NOTHING_IN_SUSPEND enable value was set only for regulators which had suspend node defined, otherwise the default 0 value was used, what means DISABLE_IN_SUSPEND. This lead to broken system suspend/resume on boards, which had simple regulator constraints definition (without suspend state nodes). To avoid further mismatches between the default and uninitialized values of the suspend enabled/disabled states, change the values of the them, so default '0' means DO_NOTHING_IN_SUSPEND. Fixes: 72069f9957a1: regulator: leave one item to record whether regulator is enabled Signed-off-by: Marek Szyprowski Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- include/linux/regulator/machine.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 3468703d663a..a459a5e973a7 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -48,9 +48,9 @@ struct regulator; * DISABLE_IN_SUSPEND - turn off regulator in suspend states * ENABLE_IN_SUSPEND - keep regulator on in suspend states */ -#define DO_NOTHING_IN_SUSPEND (-1) -#define DISABLE_IN_SUSPEND 0 -#define ENABLE_IN_SUSPEND 1 +#define DO_NOTHING_IN_SUSPEND 0 +#define DISABLE_IN_SUSPEND 1 +#define ENABLE_IN_SUSPEND 2 /* Regulator active discharge flags */ enum regulator_active_discharge { -- cgit v1.2.3 From 4d18975c78f2d5c91792356501cf369e67594241 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Sat, 1 Sep 2018 16:08:45 +0200 Subject: fbdev: add remove_conflicting_pci_framebuffers() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Almost all PCI drivers using remove_conflicting_framebuffers() wrap it with the same code. v2: add kerneldoc for DRM helper v3: propagate remove_conflicting_framebuffers() return value + move kerneldoc to where function is implemented Signed-off-by: Michał Mirosław Acked-by: Bartlomiej Zolnierkiewicz Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/7db1c278276de420eb45a1b71d06b5eb6bbd49ef.1535810304.git.mirq-linux@rere.qmqm.pl --- include/linux/fb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 3e7e75383d32..3cd375dafd0e 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -632,6 +632,8 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, extern int register_framebuffer(struct fb_info *fb_info); extern int unregister_framebuffer(struct fb_info *fb_info); extern int unlink_framebuffer(struct fb_info *fb_info); +extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, int res_id, + const char *name); extern int remove_conflicting_framebuffers(struct apertures_struct *a, const char *name, bool primary); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); -- cgit v1.2.3 From 9fd0e09a4e86499639653243edfcb417a05c5c46 Mon Sep 17 00:00:00 2001 From: Anthony Wong Date: Fri, 31 Aug 2018 20:06:42 +0800 Subject: r8169: add support for NCube 8168 network card This card identifies itself as: Ethernet controller [0200]: NCube Device [10ff:8168] (rev 06) Subsystem: TP-LINK Technologies Co., Ltd. Device [7470:3468] Adding a new entry to rtl8169_pci_tbl makes the card work. Link: http://launchpad.net/bugs/1788730 Signed-off-by: Anthony Wong Signed-off-by: David S. Miller --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 99d366cb0e9f..d157983b84cf 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3084,4 +3084,6 @@ #define PCI_VENDOR_ID_OCZ 0x1b85 +#define PCI_VENDOR_ID_NCUBE 0x10ff + #endif /* _LINUX_PCI_IDS_H */ -- cgit v1.2.3 From f3569fd613f669c95ad187208ad281995f30cc2a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 7 Aug 2018 14:18:42 -0700 Subject: crypto: shash - Remove VLA usage in unaligned hashing In the quest to remove all stack VLA usage from the kernel[1], this uses the newly defined max alignment to perform unaligned hashing to avoid VLAs, and drops the helper function while adding sanity checks on the resulting buffer sizes. Additionally, the __aligned_largest macro is removed since this helper was the only user. [1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com Signed-off-by: Kees Cook Signed-off-by: Herbert Xu --- include/linux/compiler_types.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3525c179698c..13fee5fe734b 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -198,7 +198,6 @@ struct ftrace_likely_data { */ #define __pure __attribute__((pure)) #define __aligned(x) __attribute__((aligned(x))) -#define __aligned_largest __attribute__((aligned)) #define __printf(a, b) __attribute__((format(printf, a, b))) #define __scanf(a, b) __attribute__((format(scanf, a, b))) #define __maybe_unused __attribute__((unused)) -- cgit v1.2.3 From b76377543b738a6b58b0a7b0a42dd9e16436fee1 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 30 Aug 2018 11:00:15 -0400 Subject: crc-t10dif: Pick better transform if one becomes available T10 CRC library is linked into the kernel thanks to block and SCSI. The crypto accelerators are typically loaded later as modules and are therefore not available when the T10 CRC library is initialized. Use the crypto notifier facility to trigger a switch to a better algorithm if one becomes available after the initial hash has been registered. Use RCU to protect the original transform while the new one is being set up. Suggested-by: Ard Biesheuvel Signed-off-by: Martin K. Petersen Signed-off-by: Herbert Xu --- include/linux/crc-t10dif.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h index 1fe0cfcdea30..6bb0c0bf357b 100644 --- a/include/linux/crc-t10dif.h +++ b/include/linux/crc-t10dif.h @@ -6,6 +6,7 @@ #define CRC_T10DIF_DIGEST_SIZE 2 #define CRC_T10DIF_BLOCK_SIZE 1 +#define CRC_T10DIF_STRING "crct10dif" extern __u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len); -- cgit v1.2.3 From bf97279079be21fc843d90489846d2c73c77ed09 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 29 Aug 2018 17:08:53 +0200 Subject: gpio: ts5500: Use SPDX header Cut some boilerplate, use the SPDX license identifier. Cc: kernel@savoirfairelinux.com Cc: Vivien Didelot Cc: Jerome Oufella Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-ts5500.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-ts5500.h b/include/linux/platform_data/gpio-ts5500.h index b10d11c9bb49..94346d4504cb 100644 --- a/include/linux/platform_data/gpio-ts5500.h +++ b/include/linux/platform_data/gpio-ts5500.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * GPIO (DIO) header for Technologic Systems TS-5500 * * Copyright (c) 2012 Savoir-faire Linux Inc. * Vivien Didelot - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _PDATA_GPIO_TS5500_H -- cgit v1.2.3 From 97feacc05dfb601273fd680d7b805b8e09c1bec7 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 29 Aug 2018 17:16:18 +0200 Subject: gpio: ts5500: Delete platform data handling The TS5500 GPIO driver apparently supports platform data without making any use of it whatsoever. Delete this code, last chance to speak up if you think it is needed. Cc: kernel@savoirfairelinux.com Cc: Vivien Didelot Cc: Jerome Oufella Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-ts5500.h | 24 ------------------------ 1 file changed, 24 deletions(-) delete mode 100644 include/linux/platform_data/gpio-ts5500.h (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-ts5500.h b/include/linux/platform_data/gpio-ts5500.h deleted file mode 100644 index 94346d4504cb..000000000000 --- a/include/linux/platform_data/gpio-ts5500.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * GPIO (DIO) header for Technologic Systems TS-5500 - * - * Copyright (c) 2012 Savoir-faire Linux Inc. - * Vivien Didelot - */ - -#ifndef _PDATA_GPIO_TS5500_H -#define _PDATA_GPIO_TS5500_H - -/** - * struct ts5500_dio_platform_data - TS-5500 pin block configuration - * @base: The GPIO base number to use. - * @strap: The only pin connected to an interrupt in a block is input-only. - * If you need a bidirectional line which can trigger an IRQ, you - * may strap it with an in/out pin. This flag indicates this case. - */ -struct ts5500_dio_platform_data { - int base; - bool strap; -}; - -#endif /* _PDATA_GPIO_TS5500_H */ -- cgit v1.2.3 From aa7e80b220f3a543eefbe4b7e2c5d2b73e2e2ef7 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Mon, 3 Sep 2018 20:19:28 +0300 Subject: net/mlx5: Fix atomic_mode enum values The field atomic_mode is 4 bits wide and therefore can hold values from 0x0 to 0xf. Remove the unnecessary 20 bit shift that made the values be incorrect. While that, remove unused enum values. Fixes: 57cda166bbe0 ("net/mlx5: Add DCT command interface") Signed-off-by: Moni Shoua Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7a452716de4b..d885e9f0e054 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -163,10 +163,7 @@ enum mlx5_dcbx_oper_mode { }; enum mlx5_dct_atomic_mode { - MLX5_ATOMIC_MODE_DCT_OFF = 20, - MLX5_ATOMIC_MODE_DCT_NONE = 0 << MLX5_ATOMIC_MODE_DCT_OFF, - MLX5_ATOMIC_MODE_DCT_IB_COMP = 1 << MLX5_ATOMIC_MODE_DCT_OFF, - MLX5_ATOMIC_MODE_DCT_CX = 2 << MLX5_ATOMIC_MODE_DCT_OFF, + MLX5_ATOMIC_MODE_DCT_CX = 2, }; enum { -- cgit v1.2.3 From afaef01c001537fa97a25092d7f54d764dc7d8c1 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:16:58 +0300 Subject: x86/entry: Add STACKLEAK erasing the kernel stack at the end of syscalls The STACKLEAK feature (initially developed by PaX Team) has the following benefits: 1. Reduces the information that can be revealed through kernel stack leak bugs. The idea of erasing the thread stack at the end of syscalls is similar to CONFIG_PAGE_POISONING and memzero_explicit() in kernel crypto, which all comply with FDP_RIP.2 (Full Residual Information Protection) of the Common Criteria standard. 2. Blocks some uninitialized stack variable attacks (e.g. CVE-2017-17712, CVE-2010-2963). That kind of bugs should be killed by improving C compilers in future, which might take a long time. This commit introduces the code filling the used part of the kernel stack with a poison value before returning to userspace. Full STACKLEAK feature also contains the gcc plugin which comes in a separate commit. The STACKLEAK feature is ported from grsecurity/PaX. More information at: https://grsecurity.net/ https://pax.grsecurity.net/ This code is modified from Brad Spengler/PaX Team's code in the last public patch of grsecurity/PaX based on our understanding of the code. Changes or omissions from the original code are ours and don't reflect the original grsecurity/PaX code. Performance impact: Hardware: Intel Core i7-4770, 16 GB RAM Test #1: building the Linux kernel on a single core 0.91% slowdown Test #2: hackbench -s 4096 -l 2000 -g 15 -f 25 -P 4.2% slowdown So the STACKLEAK description in Kconfig includes: "The tradeoff is the performance impact: on a single CPU system kernel compilation sees a 1% slowdown, other systems and workloads may vary and you are advised to test this feature on your expected workload before deploying it". Signed-off-by: Alexander Popov Acked-by: Thomas Gleixner Reviewed-by: Dave Hansen Acked-by: Ingo Molnar Signed-off-by: Kees Cook --- include/linux/sched.h | 4 ++++ include/linux/stackleak.h | 26 ++++++++++++++++++++++++++ 2 files changed, 30 insertions(+) create mode 100644 include/linux/stackleak.h (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 977cb57d7bc9..c1a23acd24e7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1192,6 +1192,10 @@ struct task_struct { void *security; #endif +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + unsigned long lowest_stack; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h new file mode 100644 index 000000000000..628c2b947b89 --- /dev/null +++ b/include/linux/stackleak.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_STACKLEAK_H +#define _LINUX_STACKLEAK_H + +#include +#include + +/* + * Check that the poison value points to the unused hole in the + * virtual memory map for your platform. + */ +#define STACKLEAK_POISON -0xBEEF +#define STACKLEAK_SEARCH_DEPTH 128 + +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK +#include + +static inline void stackleak_task_init(struct task_struct *t) +{ + t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); +} +#else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ +static inline void stackleak_task_init(struct task_struct *t) { } +#endif + +#endif -- cgit v1.2.3 From c8d126275a5fa59394fe17109bdb9812fed296b8 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:17:01 +0300 Subject: fs/proc: Show STACKLEAK metrics in the /proc file system Introduce CONFIG_STACKLEAK_METRICS providing STACKLEAK information about tasks via the /proc file system. In particular, /proc//stack_depth shows the maximum kernel stack consumption for the current and previous syscalls. Although this information is not precise, it can be useful for estimating the STACKLEAK performance impact for your workloads. Suggested-by: Ingo Molnar Signed-off-by: Alexander Popov Tested-by: Laura Abbott Signed-off-by: Kees Cook --- include/linux/sched.h | 1 + include/linux/stackleak.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c1a23acd24e7..ae9d10e14b82 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1194,6 +1194,7 @@ struct task_struct { #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; + unsigned long prev_lowest_stack; #endif /* diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 628c2b947b89..b911b973d328 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -18,6 +18,9 @@ static inline void stackleak_task_init(struct task_struct *t) { t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); +# ifdef CONFIG_STACKLEAK_METRICS + t->prev_lowest_stack = t->lowest_stack; +# endif } #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } -- cgit v1.2.3 From 964c9dff0091893a9a74a88edf984c6da0b779f7 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:17:03 +0300 Subject: stackleak: Allow runtime disabling of kernel stack erasing Introduce CONFIG_STACKLEAK_RUNTIME_DISABLE option, which provides 'stack_erasing' sysctl. It can be used in runtime to control kernel stack erasing for kernels built with CONFIG_GCC_PLUGIN_STACKLEAK. Suggested-by: Ingo Molnar Signed-off-by: Alexander Popov Tested-by: Laura Abbott Signed-off-by: Kees Cook --- include/linux/stackleak.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index b911b973d328..3d5c3271a9a8 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -22,6 +22,12 @@ static inline void stackleak_task_init(struct task_struct *t) t->prev_lowest_stack = t->lowest_stack; # endif } + +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +int stack_erasing_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +#endif + #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } #endif -- cgit v1.2.3 From 0d6c3011409135ea84e2a231b013a22017ff999a Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 4 Sep 2018 15:31:14 +0200 Subject: HID: core: fix grouping by application commit f07b3c1da92d ("HID: generic: create one input report per application type") was effectively the same as MULTI_INPUT: hidinput->report was never set, so hidinput_match_application() always returned null. Fix that by testing against the real application. Note that this breaks some old eGalax touchscreens that expect MULTI_INPUT instead of HID_QUIRK_INPUT_PER_APP. Enable this quirk for backward compatibility on all non-Win8 touchscreens. link: https://bugzilla.kernel.org/show_bug.cgi?id=200847 link: https://bugzilla.kernel.org/show_bug.cgi?id=200849 link: https://bugs.archlinux.org/task/59699 link: https://github.com/NixOS/nixpkgs/issues/45165 Cc: stable@vger.kernel.org # v4.18+ Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 834e6461a690..d44a78362942 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -526,6 +526,7 @@ struct hid_input { const char *name; bool registered; struct list_head reports; /* the list of reports */ + unsigned int application; /* application usage for this input */ }; enum hid_type { -- cgit v1.2.3 From 7525c9518ea6feabc8154956df0891a59a69d289 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 27 Jul 2018 23:05:42 +0200 Subject: mtd: rawnand: Get rid of the ->read_word() hook Commit c120e75e0e7d ("mtd: nand: use read_oob() instead of cmdfunc() for bad block check") removed this only user of the ->read_word() method but kept the hook in place. Remove it now. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index efb2345359bb..d155470f53c8 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1182,7 +1182,6 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @IO_ADDR_W: [BOARDSPECIFIC] address to write the 8 I/O lines of the * flash device. * @read_byte: [REPLACEABLE] read one byte from the chip - * @read_word: [REPLACEABLE] read one word from the chip * @write_byte: [REPLACEABLE] write a single byte to the chip on the * low 8 I/O lines * @write_buf: [REPLACEABLE] write data from the buffer to the chip @@ -1287,7 +1286,6 @@ struct nand_chip { void __iomem *IO_ADDR_W; uint8_t (*read_byte)(struct mtd_info *mtd); - u16 (*read_word)(struct mtd_info *mtd); void (*write_byte)(struct mtd_info *mtd, uint8_t byte); void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); -- cgit v1.2.3 From ff8648f29fe58c2d94d32a076d2de7b92be4b485 Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Mon, 13 Aug 2018 09:18:46 +0200 Subject: mtd: rawnand: fsl_ifc: fixup SRAM init for newer ctrl versions Newer versions of the IFC controller use a different method of initializing the internal SRAM: Instead of reading from flash, a bit in the NAND configuration register has to be set in order to trigger the self-initializing process. Signed-off-by: Kurt Kanzenbach Signed-off-by: Miquel Raynal --- include/linux/fsl_ifc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h index 3fdfede2f0f3..5f343b796ad9 100644 --- a/include/linux/fsl_ifc.h +++ b/include/linux/fsl_ifc.h @@ -274,6 +274,8 @@ */ /* Auto Boot Mode */ #define IFC_NAND_NCFGR_BOOT 0x80000000 +/* SRAM Initialization */ +#define IFC_NAND_NCFGR_SRAM_INIT_EN 0x20000000 /* Addressing Mode-ROW0+n/COL0 */ #define IFC_NAND_NCFGR_ADDR_MODE_RC0 0x00000000 /* Addressing Mode-ROW0+n/COL0+n */ -- cgit v1.2.3 From 8ce78257965e6cd49720e653867e766ecd38883f Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:41 +0300 Subject: net/mlx5: Add proper NIC TX steering flow tables support Extend the ability to add steering rules to NIC TX flow tables. For now, we are only adding TX bypass (egress) which is used by the RDMA side. This will allow to shape outgoing traffic and tweak it if needed, for example performing encapsulation or rewriting headers. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/device.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 11fa4e66afc5..f2281e69ab39 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1120,6 +1120,12 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE_NIC_RX_MAX(mdev, cap) \ MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive.cap) +#define MLX5_CAP_FLOWTABLE_NIC_TX(mdev, cap) \ + MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit.cap) + +#define MLX5_CAP_FLOWTABLE_NIC_TX_MAX(mdev, cap) \ + MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit.cap) + #define MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_sniffer.cap) -- cgit v1.2.3 From 90c1d1b8da67330b09893d749401a45328b51704 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:42 +0300 Subject: net/mlx5: Export modify header alloc/dealloc functions Those functions will be used by the RDMA side to create modify header actions to be attached to flow steering rules via verbs. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 804516e4f483..0cbf4d5cb1ab 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -196,4 +196,10 @@ int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); +int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, + u8 namespace, u8 num_actions, + void *modify_actions, u32 *modify_header_id); +void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, + u32 modify_header_id); + #endif -- cgit v1.2.3 From 61444b458b01c95e55003d6f0b4d4c936fde51cb Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:44 +0300 Subject: net/mlx5: Break encap/decap into two separated flow table creation flags Today we are able to attach encap and decap actions only to the FDB. In preparation to enable those actions on the NIC flow tables, break the single flag into two. Those flags control whatever a decap or encap operations can be attached to the flow table created. For FDB, if encapsulation is required, we set both of them. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Reviewed-by: Or Gerlitz Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 0cbf4d5cb1ab..0194e62ad66a 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -45,7 +45,8 @@ enum { }; enum { - MLX5_FLOW_TABLE_TUNNEL_EN = BIT(0), + MLX5_FLOW_TABLE_TUNNEL_EN_ENCAP = BIT(0), + MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1), }; #define LEFTOVERS_RULE_NUM 2 -- cgit v1.2.3 From e0e7a3861b6c6b673dc93e291ef11cf5e746b0c2 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:45 +0300 Subject: net/mlx5: Move header encap type to IFC header file Those bits are hardware specification and should be defined in the IFC header file. Signed-off-by: Mark Bloch Reviewed-by: Or Gerlitz Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f043d65b9bac..bd725e0924e5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4848,6 +4848,11 @@ struct mlx5_ifc_alloc_encap_header_out_bits { u8 reserved_at_60[0x20]; }; +enum { + MLX5_HEADER_TYPE_VXLAN = 0x0, + MLX5_HEADER_TYPE_NVGRE = 0x1, +}; + struct mlx5_ifc_alloc_encap_header_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; -- cgit v1.2.3 From 60786f0987c0d9354e5330ee11615b16cdb448fe Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:46 +0300 Subject: {net, RDMA}/mlx5: Rename encap to reformat packet Renames all encap mlx5_{core,ib} code to use the new naming of packet reformat. This change doesn't introduce any function change and is needed to properly reflect the operation being done by this action. For example not only can we encapsulate a packet, but also decapsulate it. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 4 ++-- include/linux/mlx5/mlx5_ifc.h | 50 +++++++++++++++++++++---------------------- 2 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 0194e62ad66a..37d0c08d0966 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -45,7 +45,7 @@ enum { }; enum { - MLX5_FLOW_TABLE_TUNNEL_EN_ENCAP = BIT(0), + MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT = BIT(0), MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1), }; @@ -160,7 +160,7 @@ struct mlx5_flow_act { u32 action; bool has_flow_tag; u32 flow_tag; - u32 encap_id; + u32 reformat_id; u32 modify_id; uintptr_t esp_id; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index bd725e0924e5..c79eaae28e59 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -243,8 +243,8 @@ enum { MLX5_CMD_OP_DEALLOC_FLOW_COUNTER = 0x93a, MLX5_CMD_OP_QUERY_FLOW_COUNTER = 0x93b, MLX5_CMD_OP_MODIFY_FLOW_TABLE = 0x93c, - MLX5_CMD_OP_ALLOC_ENCAP_HEADER = 0x93d, - MLX5_CMD_OP_DEALLOC_ENCAP_HEADER = 0x93e, + MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT = 0x93d, + MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT = 0x93e, MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT = 0x940, MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941, MLX5_CMD_OP_QUERY_MODIFY_HEADER_CONTEXT = 0x942, @@ -336,7 +336,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 modify_root[0x1]; u8 identified_miss_table_mode[0x1]; u8 flow_table_modify[0x1]; - u8 encap[0x1]; + u8 reformat[0x1]; u8 decap[0x1]; u8 reserved_at_9[0x1]; u8 pop_vlan[0x1]; @@ -599,7 +599,7 @@ struct mlx5_ifc_e_switch_cap_bits { u8 vxlan_encap_decap[0x1]; u8 nvgre_encap_decap[0x1]; u8 reserved_at_22[0x9]; - u8 log_max_encap_headers[0x5]; + u8 log_max_packet_reformat_context[0x5]; u8 reserved_2b[0x6]; u8 max_encap_header_size[0xa]; @@ -2394,7 +2394,7 @@ enum { MLX5_FLOW_CONTEXT_ACTION_DROP = 0x2, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST = 0x4, MLX5_FLOW_CONTEXT_ACTION_COUNT = 0x8, - MLX5_FLOW_CONTEXT_ACTION_ENCAP = 0x10, + MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT = 0x10, MLX5_FLOW_CONTEXT_ACTION_DECAP = 0x20, MLX5_FLOW_CONTEXT_ACTION_MOD_HDR = 0x40, MLX5_FLOW_CONTEXT_ACTION_VLAN_POP = 0x80, @@ -2427,7 +2427,7 @@ struct mlx5_ifc_flow_context_bits { u8 reserved_at_a0[0x8]; u8 flow_counter_list_size[0x18]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 modify_header_id[0x20]; @@ -4802,19 +4802,19 @@ struct mlx5_ifc_query_eq_in_bits { u8 reserved_at_60[0x20]; }; -struct mlx5_ifc_encap_header_in_bits { +struct mlx5_ifc_packet_reformat_context_in_bits { u8 reserved_at_0[0x5]; - u8 header_type[0x3]; + u8 reformat_type[0x3]; u8 reserved_at_8[0xe]; - u8 encap_header_size[0xa]; + u8 reformat_data_size[0xa]; u8 reserved_at_20[0x10]; - u8 encap_header[2][0x8]; + u8 reformat_data[2][0x8]; - u8 more_encap_header[0][0x8]; + u8 more_reformat_data[0][0x8]; }; -struct mlx5_ifc_query_encap_header_out_bits { +struct mlx5_ifc_query_packet_reformat_context_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -4822,38 +4822,38 @@ struct mlx5_ifc_query_encap_header_out_bits { u8 reserved_at_40[0xa0]; - struct mlx5_ifc_encap_header_in_bits encap_header[0]; + struct mlx5_ifc_packet_reformat_context_in_bits packet_reformat_context[0]; }; -struct mlx5_ifc_query_encap_header_in_bits { +struct mlx5_ifc_query_packet_reformat_context_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 reserved_at_60[0xa0]; }; -struct mlx5_ifc_alloc_encap_header_out_bits { +struct mlx5_ifc_alloc_packet_reformat_context_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 reserved_at_60[0x20]; }; enum { - MLX5_HEADER_TYPE_VXLAN = 0x0, - MLX5_HEADER_TYPE_NVGRE = 0x1, + MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, + MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, }; -struct mlx5_ifc_alloc_encap_header_in_bits { +struct mlx5_ifc_alloc_packet_reformat_context_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; @@ -4862,10 +4862,10 @@ struct mlx5_ifc_alloc_encap_header_in_bits { u8 reserved_at_40[0xa0]; - struct mlx5_ifc_encap_header_in_bits encap_header; + struct mlx5_ifc_packet_reformat_context_in_bits packet_reformat_context; }; -struct mlx5_ifc_dealloc_encap_header_out_bits { +struct mlx5_ifc_dealloc_packet_reformat_context_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -4874,14 +4874,14 @@ struct mlx5_ifc_dealloc_encap_header_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_dealloc_encap_header_in_bits { +struct mlx5_ifc_dealloc_packet_reformat_context_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; u8 reserved_20[0x10]; u8 op_mod[0x10]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 reserved_60[0x20]; }; @@ -6983,7 +6983,7 @@ struct mlx5_ifc_create_flow_table_out_bits { }; struct mlx5_ifc_flow_table_context_bits { - u8 encap_en[0x1]; + u8 reformat_en[0x1]; u8 decap_en[0x1]; u8 reserved_at_2[0x2]; u8 table_miss_action[0x4]; -- cgit v1.2.3 From bea4e1f6c6c5744d467ebf8b0699f5e391835130 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:47 +0300 Subject: net/mlx5: Expose new packet reformat capabilities Expose new abilities when creating a packet reformat context. The new types which can be created are: MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: Ability to create generic encap operation to be done by the HW. MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2: Ability to create generic decap operation where the inner packet doesn't contain L2. MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: Ability to create generic encap operation to be done by the HW. The L2 of the original packet is dropped. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c79eaae28e59..3a4a2e0567e9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -344,8 +344,12 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_c[0x1]; u8 pop_vlan_2[0x1]; u8 push_vlan_2[0x1]; - u8 reserved_at_f[0x11]; - + u8 reformat_and_vlan_action[0x1]; + u8 reserved_at_10[0x2]; + u8 reformat_l3_tunnel_to_l2[0x1]; + u8 reformat_l2_to_l3_tunnel[0x1]; + u8 reformat_and_modify_action[0x1]; + u8 reserved_at_14[0xb]; u8 reserved_at_20[0x2]; u8 log_max_ft_size[0x6]; u8 log_max_modify_header_context[0x8]; @@ -554,7 +558,13 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 nic_rx_multi_path_tirs[0x1]; u8 nic_rx_multi_path_tirs_fts[0x1]; u8 allow_sniffer_and_nic_rx_shared_tir[0x1]; - u8 reserved_at_3[0x1fd]; + u8 reserved_at_3[0x1d]; + u8 encap_general_header[0x1]; + u8 reserved_at_21[0xa]; + u8 log_max_packet_reformat_context[0x5]; + u8 reserved_at_30[0x6]; + u8 max_encap_header_size[0xa]; + u8 reserved_at_40[0x1c0]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive; @@ -4851,6 +4861,9 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { enum { MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, + MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2, + MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3, + MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, }; struct mlx5_ifc_alloc_packet_reformat_context_in_bits { -- cgit v1.2.3 From 50acec06f3928fc29647aecf1270e54cae583afb Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:49 +0300 Subject: net/mlx5: Export packet reformat alloc/dealloc functions This will allow for the RDMA side to allocate packet reformat context. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 37d0c08d0966..b1c026f1c8ba 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -203,4 +203,13 @@ int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id); +int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + u32 *packet_reformat_id); +void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, + u32 packet_reformat_id); + #endif -- cgit v1.2.3 From 03512ceb60ae4be71ed3129dabb8625224c8ec40 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Fri, 31 Aug 2018 11:31:09 +0300 Subject: ieee80211: remove redundant leading zeroes The defines of IEEE80211_HE_OPERATION_VHT_OPER_INFO and IEEE80211_HE_OPERATION_MULTI_BSSID_AP have leading zeroes that makes the number look like it is bigger than 32 bit. This is misleading, remove it. Signed-off-by: Sara Sharon Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9c03a7d5e400..17ea51d088ae 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1963,8 +1963,8 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000200 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x000ffc00 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 10 -#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x000100000 -#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x000200000 +#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x00100000 +#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x00200000 #define IEEE80211_HE_OPERATION_MULTI_BSSID_AP 0x10000000 #define IEEE80211_HE_OPERATION_TX_BSSID_INDICATOR 0x20000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x40000000 -- cgit v1.2.3 From b0aa75f0b1b2e6bc77128fab36c8ed87e84917cc Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 31 Aug 2018 11:31:16 +0300 Subject: ieee80211: add new VHT capability fields/parsing IEEE 802.11-2016 extended the VHT capability fields to allow indicating the number of spatial streams depending on the actually used bandwidth, add support for decoding this. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 35 +++++++++++++++++++++++++++++++++-- 1 file changed, 33 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 17ea51d088ae..280600a10111 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1460,13 +1460,16 @@ struct ieee80211_ht_operation { * STA can receive. Rate expressed in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest RX data rate supported. - * The top 3 bits of this field are reserved. + * The top 3 bits of this field indicate the Maximum NSTS,total + * (a beamformee capability.) * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams * @tx_highest: Indicates highest long GI VHT PPDU data rate * STA can transmit. Rate expressed in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest TX data rate supported. - * The top 3 bits of this field are reserved. + * The top 2 bits of this field are reserved, the + * 3rd bit from the top indiciates VHT Extended NSS BW + * Capability. */ struct ieee80211_vht_mcs_info { __le16 rx_mcs_map; @@ -1475,6 +1478,13 @@ struct ieee80211_vht_mcs_info { __le16 tx_highest; } __packed; +/* for rx_highest */ +#define IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT 13 +#define IEEE80211_VHT_MAX_NSTS_TOTAL_MASK (7 << IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT) + +/* for tx_highest */ +#define IEEE80211_VHT_EXT_NSS_BW_CAPABLE (1 << 13) + /** * enum ieee80211_vht_mcs_support - VHT MCS support definitions * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the @@ -1650,6 +1660,7 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_SHIFT 2 #define IEEE80211_VHT_CAP_RXLDPC 0x00000010 #define IEEE80211_VHT_CAP_SHORT_GI_80 0x00000020 #define IEEE80211_VHT_CAP_SHORT_GI_160 0x00000040 @@ -1678,6 +1689,26 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB 0x0c000000 #define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 #define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT 30 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_MASK 0xc0000000 + +/** + * ieee80211_get_vht_max_nss - return max NSS for a given bandwidth/MCS + * @cap: VHT capabilities of the peer + * @bw: bandwidth to use + * @mcs: MCS index to use + * @ext_nss_bw_capable: indicates whether or not the local transmitter + * (rate scaling algorithm) can deal with the new logic + * (dot11VHTExtendedNSSBWCapable) + * + * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can + * vary for a given BW/MCS. This function parses the data. + * + * Note: This function is exported by cfg80211. + */ +int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, + enum ieee80211_vht_chanwidth bw, + int mcs, bool ext_nss_bw_capable); /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 -- cgit v1.2.3 From add7453ad62f05c8f1a48675bb4dfed52e6ac878 Mon Sep 17 00:00:00 2001 From: Shaul Triebitz Date: Wed, 5 Sep 2018 08:06:08 +0300 Subject: wireless: align to draft 11ax D3.0 Align to new 11ax draft D3.0. Change/add new MAC and PHY capabilities and update drivers' 11ax capabilities and mac80211's debugfs accordingly. Signed-off-by: Shaul Triebitz Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 72 ++++++++++++++++++++++++++++++----------------- 1 file changed, 46 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 280600a10111..c4809ad8ab46 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1555,11 +1555,11 @@ struct ieee80211_vht_operation { * struct ieee80211_he_cap_elem - HE capabilities element * * This structure is the "HE capabilities element" fixed fields as - * described in P802.11ax_D2.0 section 9.4.2.237.2 and 9.4.2.237.3 + * described in P802.11ax_D3.0 section 9.4.2.237.2 and 9.4.2.237.3 */ struct ieee80211_he_cap_elem { - u8 mac_cap_info[5]; - u8 phy_cap_info[9]; + u8 mac_cap_info[6]; + u8 phy_cap_info[11]; } __packed; #define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 @@ -1738,15 +1738,15 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_1 0x00 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_2 0x10 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_3 0x20 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_4 0x30 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_5 0x40 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_6 0x50 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_7 0x60 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8 0x70 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_MASK 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_1 0x00 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_2 0x10 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_3 0x20 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_4 0x30 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_5 0x40 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_6 0x50 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_7 0x60 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_MASK 0x70 /* Link adaptation is split between byte HE_MAC_CAP1 and * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE @@ -1760,14 +1760,13 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 #define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 -#define IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED 0x04 +#define IEEE80211_HE_MAC_CAP2_TRS 0x04 #define IEEE80211_HE_MAC_CAP2_BSR 0x08 #define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 #define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 #define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 #define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 -#define IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU 0x01 #define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 #define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 @@ -1775,25 +1774,34 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the * same field in the HE capabilities. */ -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_USE_VHT 0x00 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_1 0x08 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2 0x10 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_RESERVED 0x18 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_MASK 0x18 -#define IEEE80211_HE_MAC_CAP3_A_AMSDU_FRAG 0x20 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_USE_VHT 0x00 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_1 0x08 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2 0x10 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_RESERVED 0x18 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK 0x18 +#define IEEE80211_HE_MAC_CAP3_AMSDU_FRAG 0x20 #define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 #define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 #define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 #define IEEE80211_HE_MAC_CAP4_QTP 0x02 #define IEEE80211_HE_MAC_CAP4_BQR 0x04 -#define IEEE80211_HE_MAC_CAP4_SR_RESP 0x08 +#define IEEE80211_HE_MAC_CAP4_SRP_RESP 0x08 #define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 #define IEEE80211_HE_MAC_CAP4_OPS 0x20 #define IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU 0x40 +/* Multi TID agg TX is split between byte #4 and #5 + * The value is a combination of B39,B40,B41 + */ +#define IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39 0x80 + +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 0x01 +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 0x02 +#define IEEE80211_HE_MAC_CAP5_SUBCHAN_SELECVITE_TRANSMISSION 0x04 +#define IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU 0x08 +#define IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX 0x10 /* 802.11ax HE PHY capabilities */ -#define IEEE80211_HE_PHY_CAP0_DUAL_BAND 0x01 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 @@ -1810,10 +1818,10 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 #define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 #define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 -/* Midamble RX Max NSTS is split between byte #2 and byte #3 */ -#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS 0x80 +/* Midamble RX/TX Max NSTS is split between byte #2 and byte #3 */ +#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS 0x80 -#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS 0x01 +#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS 0x01 #define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 #define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 #define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 @@ -1914,7 +1922,19 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 #define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 #define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 -#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_2X_AND_1XLTF 0x20 +#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_TX_2X_AND_1XLTF 0x20 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_20MHZ 0x00 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_40MHZ 0x40 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_80MHZ 0x80 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ 0xc0 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_MASK 0xc0 + +#define IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM 0x01 +#define IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK 0x02 +#define IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU 0x04 +#define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 /* 802.11ax HE TX/RX MCS NSS Support */ #define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) -- cgit v1.2.3 From 1ff2e1a44e02d4bdbb9be67c7d9acc240a67141f Mon Sep 17 00:00:00 2001 From: Harry Cutts Date: Thu, 30 Aug 2018 14:56:19 -0700 Subject: HID: input: Create a utility class for counting scroll events To avoid code duplication, this class counts high-resolution scroll movements and emits the legacy low-resolution events when appropriate. Drivers should be able to create one instance for each scroll wheel that they need to handle. Signed-off-by: Harry Cutts Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 834e6461a690..037e37b0b0e6 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1138,6 +1138,34 @@ static inline u32 hid_report_len(struct hid_report *report) int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, int interrupt); + +/** + * struct hid_scroll_counter - Utility class for processing high-resolution + * scroll events. + * @dev: the input device for which events should be reported. + * @microns_per_hi_res_unit: the amount moved by the user's finger for each + * high-resolution unit reported by the mouse, in + * microns. + * @resolution_multiplier: the wheel's resolution in high-resolution mode as a + * multiple of its lower resolution. For example, if + * moving the wheel by one "notch" would result in a + * value of 1 in low-resolution mode but 8 in + * high-resolution, the multiplier is 8. + * @remainder: counts the number of high-resolution units moved since the last + * low-resolution event (REL_WHEEL or REL_HWHEEL) was sent. Should + * only be used by class methods. + */ +struct hid_scroll_counter { + struct input_dev *dev; + int microns_per_hi_res_unit; + int resolution_multiplier; + + int remainder; +}; + +void hid_scroll_counter_handle_scroll(struct hid_scroll_counter *counter, + int hi_res_value); + /* HID quirks API */ unsigned long hid_lookup_quirk(const struct hid_device *hdev); int hid_quirks_init(char **quirks_param, __u16 bus, int count); -- cgit v1.2.3 From d23df2dc56325c72b51670b1fb400ddd23dc17cd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 3 Sep 2018 12:51:59 -0700 Subject: linux/mod_devicetable.h: fix kernel-doc missing notation for typec_device_id Fix kernel-doc warning for missing struct member description: ../include/linux/mod_devicetable.h:763: warning: Function parameter or member 'driver_data' not described in 'typec_device_id' Fixes: 8a37d87d72f0c ("usb: typec: Bus type for alternate modes") Signed-off-by: Randy Dunlap Cc: Heikki Krogerus Reviewed-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 1298a7daa57d..01797cb4587e 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -754,6 +754,7 @@ struct tb_service_id { * struct typec_device_id - USB Type-C alternate mode identifiers * @svid: Standard or Vendor ID * @mode: Mode index + * @driver_data: Driver specific data */ struct typec_device_id { __u16 svid; -- cgit v1.2.3 From 865e63b04e9b2a658d7f26bd13a71dcd964a9118 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 4 Sep 2018 16:26:11 -0400 Subject: tracing: Add back in rcu_irq_enter/exit_irqson() for rcuidle tracepoints Borislav reported the following splat: ============================= WARNING: suspicious RCU usage 4.19.0-rc1+ #1 Not tainted ----------------------------- ./include/linux/rcupdate.h:631 rcu_read_lock() used illegally while idle! other info that might help us debug this: RCU used illegally from idle CPU! rcu_scheduler_active = 2, debug_locks = 1 RCU used illegally from extended quiescent state! 1 lock held by swapper/0/0: #0: 000000004557ee0e (rcu_read_lock){....}, at: perf_event_output_forward+0x0/0x130 stack backtrace: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.19.0-rc1+ #1 Hardware name: LENOVO 2320CTO/2320CTO, BIOS G2ET86WW (2.06 ) 11/13/2012 Call Trace: dump_stack+0x85/0xcb perf_event_output_forward+0xf6/0x130 __perf_event_overflow+0x52/0xe0 perf_swevent_overflow+0x91/0xb0 perf_tp_event+0x11a/0x350 ? find_held_lock+0x2d/0x90 ? __lock_acquire+0x2ce/0x1350 ? __lock_acquire+0x2ce/0x1350 ? retint_kernel+0x2d/0x2d ? find_held_lock+0x2d/0x90 ? tick_nohz_get_sleep_length+0x83/0xb0 ? perf_trace_cpu+0xbb/0xd0 ? perf_trace_buf_alloc+0x5a/0xa0 perf_trace_cpu+0xbb/0xd0 cpuidle_enter_state+0x185/0x340 do_idle+0x1eb/0x260 cpu_startup_entry+0x5f/0x70 start_kernel+0x49b/0x4a6 secondary_startup_64+0xa4/0xb0 This is due to the tracepoints moving to SRCU usage which does not require RCU to be "watching". But perf uses these tracepoints with RCU and expects it to be. Hence, we still need to add in the rcu_irq_enter/exit_irqson() calls for "rcuidle" tracepoints. This is a temporary fix until we have SRCU working in NMI context, and then perf can be converted to use that instead of normal RCU. Link: http://lkml.kernel.org/r/20180904162611.6a120068@gandalf.local.home Cc: x86-ml Cc: Peter Zijlstra Reported-by: Borislav Petkov Tested-by: Borislav Petkov Reviewed-by: "Paul E. McKenney" Fixes: e6753f23d961d ("tracepoint: Make rcuidle tracepoint callers use SRCU") Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 7f2e16e76ac4..041f7e56a289 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -158,8 +158,10 @@ extern void syscall_unregfunc(void); * For rcuidle callers, use srcu since sched-rcu \ * doesn't work from the idle path. \ */ \ - if (rcuidle) \ + if (rcuidle) { \ idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + rcu_irq_enter_irqson(); \ + } \ \ it_func_ptr = rcu_dereference_raw((tp)->funcs); \ \ @@ -171,8 +173,10 @@ extern void syscall_unregfunc(void); } while ((++it_func_ptr)->func); \ } \ \ - if (rcuidle) \ + if (rcuidle) { \ + rcu_irq_exit_irqson(); \ srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + } \ \ preempt_enable_notrace(); \ } while (0) -- cgit v1.2.3 From 76d5581c870454be5f1f1a106c57985902e7ea20 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Sun, 5 Aug 2018 09:19:33 +0300 Subject: net/mlx5: Fix use-after-free in self-healing flow When the mlx5 health mechanism detects a problem while the driver is in the middle of init_one or remove_one, the driver needs to prevent the health mechanism from scheduling future work; if future work is scheduled, there is a problem with use-after-free: the system WQ tries to run the work item (which has been freed) at the scheduled future time. Prevent this by disabling work item scheduling in the health mechanism when the driver is in the middle of init_one() or remove_one(). Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Jack Morgenstein Reviewed-by: Feras Daoud Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7a452716de4b..aa65f58c6610 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1052,7 +1052,7 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); -void mlx5_stop_health_poll(struct mlx5_core_dev *dev); +void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 8d71e818506718e8d7032ce824b5c74a17d4f7a5 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 21 Aug 2018 16:04:41 +0300 Subject: net/mlx5: Use u16 for Work Queue buffer fragment size Minimal stride size is 16. Hence, the number of strides in a fragment (of PAGE_SIZE) is <= PAGE_SIZE / 16 <= 4K. u16 is sufficient to represent this. Fixes: 388ca8be0037 ("IB/mlx5: Implement fragmented completion queue (CQ)") Signed-off-by: Tariq Toukan Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index aa65f58c6610..3a1258fd8ac3 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -362,7 +362,7 @@ struct mlx5_frag_buf { struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; - u32 frag_sz_m1; + u16 frag_sz_m1; u32 strides_offset; u8 log_sz; u8 log_stride; -- cgit v1.2.3 From a09036221092989b88c55d24d1f12ceb1d7d361f Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 21 Aug 2018 16:07:58 +0300 Subject: net/mlx5: Use u16 for Work Queue buffer strides offset Minimal stride size is 16. Hence, the number of strides in a fragment (of PAGE_SIZE) is <= PAGE_SIZE / 16 <= 4K. u16 is sufficient to represent this. Fixes: d7037ad73daa ("net/mlx5: Fix QP fragmented buffer allocation") Signed-off-by: Tariq Toukan Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3a1258fd8ac3..66d94b4557cf 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -363,7 +363,7 @@ struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; u16 frag_sz_m1; - u32 strides_offset; + u16 strides_offset; u8 log_sz; u8 log_stride; u8 log_frag_strides; @@ -995,7 +995,7 @@ static inline u32 mlx5_base_mkey(const u32 key) } static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, - u32 strides_offset, + u16 strides_offset, struct mlx5_frag_buf_ctrl *fbc) { fbc->log_stride = log_stride; -- cgit v1.2.3 From 83033688b7ade18d2dbbcefa810f02ff66ba549d Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 23 Jul 2018 10:55:39 +0300 Subject: net/mlx5: Change flow counters addlist type to single linked list In order to prevent flow counters stats work function from traversing whole flow counters tree while searching for deleted flow counters, new list to store deleted flow counters will be added to struct mlx5_fc_stats. However, the flow counter structure itself has no space left to store any more data in first cache line. To free space that is needed to store additional list node, convert current addlist double linked list (two pointers per node) to atomic single linked list (one pointer per node). Lockless NULL-terminated single linked list data type doesn't require any additional external synchronization for operations used by flow counters module (add single new element, remove all elements from list and traverse them). Remove addlist_lock that is no longer needed. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7a452716de4b..c00549293982 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -584,9 +584,7 @@ struct mlx5_irq_info { struct mlx5_fc_stats { struct rb_root counters; - struct list_head addlist; - /* protect addlist add/splice operations */ - spinlock_t addlist_lock; + struct llist_head addlist; struct workqueue_struct *wq; struct delayed_work work; -- cgit v1.2.3 From 6e5e22839136fdb466af0aa46ff2404713dff974 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 23 Jul 2018 11:32:05 +0300 Subject: net/mlx5: Add new list to store deleted flow counters In order to prevent flow counters stats work function from traversing whole flow counters tree while searching for deleted flow counters, new list to store deleted flow counters is added to struct mlx5_fc_stats. Lockless NULL-terminated single linked list data type is used due to following reasons: - This use case only needs to add single element to list and remove/iterate whole list. Lockless list doesn't require any additional synchronization for these operations. - First cache line of flow counter data structure only has space to store single additional pointer, which precludes usage of double linked list. Remove flow counter 'deleted' flag that is no longer needed. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c00549293982..4b53ac64004b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -585,6 +585,7 @@ struct mlx5_irq_info { struct mlx5_fc_stats { struct rb_root counters; struct llist_head addlist; + struct llist_head dellist; struct workqueue_struct *wq; struct delayed_work work; -- cgit v1.2.3 From 9aff93d7d0d4b3f3076d7bd12a4ad06ef1cf9804 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Tue, 24 Jul 2018 09:52:11 +0300 Subject: net/mlx5: Store flow counters in a list In order to improve performance of flow counter stats query loop that traverses all configured flow counters, replace rb_tree with double-linked list. This change improves performance of traversing flow counters by removing the tree traversal. (profiling data showed that call to rb_next was most top CPU consumer) However, lookup of flow flow counter in list becomes linear, instead of logarithmic. This problem is fixed by next patch in series, which adds idr for fast lookup. Idr is to be used because it is not an intrusive data structure and doesn't require adding any new members to struct mlx5_fc, which allows its control data part to stay <= 1 cache line in size. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 4b53ac64004b..61bed33e6675 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -583,7 +583,7 @@ struct mlx5_irq_info { }; struct mlx5_fc_stats { - struct rb_root counters; + struct list_head counters; struct llist_head addlist; struct llist_head dellist; -- cgit v1.2.3 From 12d6066c3b29c5606c4a2466f964fbd9ede803c5 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Tue, 24 Jul 2018 16:37:40 +0300 Subject: net/mlx5: Add flow counters idr Previous patch in series changed flow counter storage structure from rb_tree to linked list in order to improve flow counter traversal performance. The drawback of such solution is that flow counter lookup by id becomes linear in complexity. Store pointers to flow counters in idr in order to improve lookup performance to logarithmic again. Idr is non-intrusive data structure and doesn't require extending flow counter struct with new elements. This means that idr can be used for lookup, while linked list from previous patch is used for traversal, and struct mlx5_fc size is <= 2 cache lines. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 61bed33e6675..2a0c845f6bdb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -583,6 +583,8 @@ struct mlx5_irq_info { }; struct mlx5_fc_stats { + spinlock_t counters_idr_lock; /* protects counters_idr */ + struct idr counters_idr; struct list_head counters; struct llist_head addlist; struct llist_head dellist; -- cgit v1.2.3 From 64109f1dc41f25f4a9c6b114e04b6266bf4128ad Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Tue, 5 Jun 2018 09:22:18 +0300 Subject: net/mlx5e: Replace PTP clock lock from RW lock to seq lock Changed "priv.clock.lock" lock from 'rw_lock' to 'seq_lock' in order to improve packet rate performance. Tested on Intel(R) Xeon(R) CPU E5-2660 v2 @ 2.20GHz. Sent 64b packets between two peers connected by ConnectX-5, and measured packet rate for the receiver in three modes: no time-stamping (base rate) time-stamping using rw_lock (old lock) for critical region time-stamping using seq_lock (new lock) for critical region Only the receiver time stamped its packets. The measured packet rate improvements are: Single flow (multiple TX rings to single RX ring): without timestamping: 4.26 (M packets)/sec with rw-lock (old lock): 4.1 (M packets)/sec with seq-lock (new lock): 4.16 (M packets)/sec 1.46% improvement Multiple flows (multiple TX rings to six RX rings): without timestamping: 22 (M packets)/sec with rw-lock (old lock): 11.7 (M packets)/sec with seq-lock (new lock): 21.3 (M packets)/sec 82.05% improvement The packet rate improvement is due to the lack of atomic operations for the 'readers' by the seq-lock. Since there are much more 'readers' than 'writers' contention on this lock, almost all atomic operations are saved. this results in a dramatic decrease in overall cache misses. Signed-off-by: Shay Agroskin Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2a0c845f6bdb..b7fce2c9443d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -805,7 +805,7 @@ struct mlx5_pps { }; struct mlx5_clock { - rwlock_t lock; + seqlock_t lock; struct cyclecounter cycles; struct timecounter tc; struct hwtstamp_config hwtstamp_config; -- cgit v1.2.3 From fa788d986a3aac5069378ed04697bd06f83d3488 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Mon, 3 Sep 2018 16:23:36 +0200 Subject: packet: add sockopt to ignore outgoing packets Currently, the only way to ignore outgoing packets on a packet socket is via the BPF filter. With MSG_ZEROCOPY, packets that are looped into AF_PACKET are copied in dev_queue_xmit_nit(), and this copy happens even if the filter run from packet_rcv() would reject them. So the presence of a packet socket on the interface takes away the benefits of MSG_ZEROCOPY, even if the packet socket is not interested in outgoing packets. (Even when MSG_ZEROCOPY is not used, the skb is unnecessarily cloned, but the cost for that is much lower.) Add a socket option to allow AF_PACKET sockets to ignore outgoing packets to solve this. Note that the *BSDs already have something similar: BIOCSSEESENT/BIOCSDIRECTION and BIOCSDIRFILT. The first intended user is lldpd. Signed-off-by: Vincent Whitchurch Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4271f6b4e419..e2b3bd750c98 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2343,6 +2343,7 @@ static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, struct packet_type { __be16 type; /* This is really htons(ether_type). */ + bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ int (*func) (struct sk_buff *, struct net_device *, -- cgit v1.2.3 From a3f723079df85eafc10c628dabdfcf374b8e1523 Mon Sep 17 00:00:00 2001 From: Denis Bolotin Date: Wed, 5 Sep 2018 18:35:55 +0300 Subject: qed*: Utilize FW 8.37.7.0 This patch adds a new qed firmware with fixes and support for new features. Fixes: - Fix a rare case of device crash with iWARP, iSCSI or FCoE offload. - Fix GRE tunneled traffic when iWARP offload is enabled. - Fix RoCE failure in ib_send_bw when using inline data. - Fix latency optimization flow for inline WQEs. - BigBear 100G fix RDMA: - Reduce task context size. - Application page sizes above 2GB support. - Performance improvements. ETH: - Tenant DCB support. - Replace RSS indirection table update interface. Misc: - Debug Tools changes. Signed-off-by: Denis Bolotin Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 10 +++++----- include/linux/qed/iscsi_common.h | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 0081fa6d1268..03f59a28fefd 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -110,7 +110,7 @@ #define FW_MAJOR_VERSION 8 #define FW_MINOR_VERSION 37 -#define FW_REVISION_VERSION 2 +#define FW_REVISION_VERSION 7 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -931,12 +931,12 @@ struct db_rdma_dpm_params { #define DB_RDMA_DPM_PARAMS_WQE_SIZE_SHIFT 16 #define DB_RDMA_DPM_PARAMS_RESERVED0_MASK 0x1 #define DB_RDMA_DPM_PARAMS_RESERVED0_SHIFT 27 -#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 -#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 28 +#define DB_RDMA_DPM_PARAMS_ACK_REQUEST_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_ACK_REQUEST_SHIFT 28 #define DB_RDMA_DPM_PARAMS_S_FLG_MASK 0x1 #define DB_RDMA_DPM_PARAMS_S_FLG_SHIFT 29 -#define DB_RDMA_DPM_PARAMS_RESERVED1_MASK 0x1 -#define DB_RDMA_DPM_PARAMS_RESERVED1_SHIFT 30 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 30 #define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_MASK 0x1 #define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_SHIFT 31 }; diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index b34c573f2b30..66aba505ec56 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -896,7 +896,7 @@ struct e4_ustorm_iscsi_task_ag_ctx { __le32 exp_cont_len; __le32 total_data_acked; __le32 exp_data_acked; - u8 next_tid_valid; + u8 byte2; u8 byte3; __le16 word1; __le16 next_tid; -- cgit v1.2.3 From 7759eb23fd9808a2e4498cf36a798ed65cde78ae Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 5 Sep 2018 15:45:54 -0600 Subject: block: remove bio_rewind_iter() It is pointed that bio_rewind_iter() is one very bad API[1]: 1) bio size may not be restored after rewinding 2) it causes some bogus change, such as 5151842b9d8732 (block: reset bi_iter.bi_done after splitting bio) 3) rewinding really makes things complicated wrt. bio splitting 4) unnecessary updating of .bi_done in fast path [1] https://marc.info/?t=153549924200005&r=1&w=2 So this patch takes Kent's suggestion to restore one bio into its original state via saving bio iterator(struct bvec_iter) in bio_integrity_prep(), given now bio_rewind_iter() is only used by bio integrity code. Cc: Dmitry Monakhov Cc: Hannes Reinecke Suggested-by: Kent Overstreet Acked-by: Kent Overstreet Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 22 ++++------------------ include/linux/bvec.h | 3 --- 2 files changed, 4 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 51371740d2a8..14b4fa266357 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -170,27 +170,11 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, { iter->bi_sector += bytes >> 9; - if (bio_no_advance_iter(bio)) { + if (bio_no_advance_iter(bio)) iter->bi_size -= bytes; - iter->bi_done += bytes; - } else { + else bvec_iter_advance(bio->bi_io_vec, iter, bytes); /* TODO: It is reasonable to complete bio with error here. */ - } -} - -static inline bool bio_rewind_iter(struct bio *bio, struct bvec_iter *iter, - unsigned int bytes) -{ - iter->bi_sector -= bytes >> 9; - - if (bio_no_advance_iter(bio)) { - iter->bi_size += bytes; - iter->bi_done -= bytes; - return true; - } - - return bvec_iter_rewind(bio->bi_io_vec, iter, bytes); } #define __bio_for_each_segment(bvl, bio, iter, start) \ @@ -353,6 +337,8 @@ struct bio_integrity_payload { unsigned short bip_max_vcnt; /* integrity bio_vec slots */ unsigned short bip_flags; /* control flags */ + struct bvec_iter bio_iter; /* for rewinding parent bio */ + struct work_struct bip_work; /* I/O completion */ struct bio_vec *bip_vec; diff --git a/include/linux/bvec.h b/include/linux/bvec.h index fe7a22dd133b..02c73c6aa805 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -40,8 +40,6 @@ struct bvec_iter { unsigned int bi_idx; /* current index into bvl_vec */ - unsigned int bi_done; /* number of bytes completed */ - unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ }; @@ -85,7 +83,6 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv, bytes -= len; iter->bi_size -= len; iter->bi_bvec_done += len; - iter->bi_done += len; if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) { iter->bi_bvec_done = 0; -- cgit v1.2.3 From cc8a4ea182efac95ad4582053f8a51271fab734d Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 18 Jul 2018 18:09:55 +0200 Subject: platform/chrome: Move mfd/cros_ec_lpc* includes to drivers/platform. The cros-ec-lpc driver lives in drivers/platform because is platform specific, however there are two includes (cros_ec_lpc_mec.h and cros_ec_lpc_reg.h) that lives in include/linux/mfd. These two includes are only used for the platform driver and are not really related to the MFD subsystem, so move the includes from include/linux/mfd to drivers/platform/chrome. Signed-off-by: Enric Balletbo i Serra Signed-off-by: Benson Leung --- include/linux/mfd/cros_ec_lpc_mec.h | 90 ------------------------------------- include/linux/mfd/cros_ec_lpc_reg.h | 61 ------------------------- 2 files changed, 151 deletions(-) delete mode 100644 include/linux/mfd/cros_ec_lpc_mec.h delete mode 100644 include/linux/mfd/cros_ec_lpc_reg.h (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_lpc_mec.h b/include/linux/mfd/cros_ec_lpc_mec.h deleted file mode 100644 index 176496ddc66c..000000000000 --- a/include/linux/mfd/cros_ec_lpc_mec.h +++ /dev/null @@ -1,90 +0,0 @@ -/* - * cros_ec_lpc_mec - LPC variant I/O for Microchip EC - * - * Copyright (C) 2016 Google, Inc - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * This driver uses the Chrome OS EC byte-level message-based protocol for - * communicating the keyboard state (which keys are pressed) from a keyboard EC - * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, - * but everything else (including deghosting) is done here. The main - * motivation for this is to keep the EC firmware as simple as possible, since - * it cannot be easily upgraded and EC flash/IRAM space is relatively - * expensive. - */ - -#ifndef __LINUX_MFD_CROS_EC_MEC_H -#define __LINUX_MFD_CROS_EC_MEC_H - -#include - -enum cros_ec_lpc_mec_emi_access_mode { - /* 8-bit access */ - ACCESS_TYPE_BYTE = 0x0, - /* 16-bit access */ - ACCESS_TYPE_WORD = 0x1, - /* 32-bit access */ - ACCESS_TYPE_LONG = 0x2, - /* - * 32-bit access, read or write of MEC_EMI_EC_DATA_B3 causes the - * EC data register to be incremented. - */ - ACCESS_TYPE_LONG_AUTO_INCREMENT = 0x3, -}; - -enum cros_ec_lpc_mec_io_type { - MEC_IO_READ, - MEC_IO_WRITE, -}; - -/* Access IO ranges 0x800 thru 0x9ff using EMI interface instead of LPC */ -#define MEC_EMI_RANGE_START EC_HOST_CMD_REGION0 -#define MEC_EMI_RANGE_END (EC_LPC_ADDR_MEMMAP + EC_MEMMAP_SIZE) - -/* EMI registers are relative to base */ -#define MEC_EMI_BASE 0x800 -#define MEC_EMI_HOST_TO_EC (MEC_EMI_BASE + 0) -#define MEC_EMI_EC_TO_HOST (MEC_EMI_BASE + 1) -#define MEC_EMI_EC_ADDRESS_B0 (MEC_EMI_BASE + 2) -#define MEC_EMI_EC_ADDRESS_B1 (MEC_EMI_BASE + 3) -#define MEC_EMI_EC_DATA_B0 (MEC_EMI_BASE + 4) -#define MEC_EMI_EC_DATA_B1 (MEC_EMI_BASE + 5) -#define MEC_EMI_EC_DATA_B2 (MEC_EMI_BASE + 6) -#define MEC_EMI_EC_DATA_B3 (MEC_EMI_BASE + 7) - -/* - * cros_ec_lpc_mec_init - * - * Initialize MEC I/O. - */ -void cros_ec_lpc_mec_init(void); - -/* - * cros_ec_lpc_mec_destroy - * - * Cleanup MEC I/O. - */ -void cros_ec_lpc_mec_destroy(void); - -/** - * cros_ec_lpc_io_bytes_mec - Read / write bytes to MEC EMI port - * - * @io_type: MEC_IO_READ or MEC_IO_WRITE, depending on request - * @offset: Base read / write address - * @length: Number of bytes to read / write - * @buf: Destination / source buffer - * - * @return 8-bit checksum of all bytes read / written - */ -u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type, - unsigned int offset, unsigned int length, u8 *buf); - -#endif /* __LINUX_MFD_CROS_EC_MEC_H */ diff --git a/include/linux/mfd/cros_ec_lpc_reg.h b/include/linux/mfd/cros_ec_lpc_reg.h deleted file mode 100644 index 5560bef63c2b..000000000000 --- a/include/linux/mfd/cros_ec_lpc_reg.h +++ /dev/null @@ -1,61 +0,0 @@ -/* - * cros_ec_lpc_reg - LPC access to the Chrome OS Embedded Controller - * - * Copyright (C) 2016 Google, Inc - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * This driver uses the Chrome OS EC byte-level message-based protocol for - * communicating the keyboard state (which keys are pressed) from a keyboard EC - * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, - * but everything else (including deghosting) is done here. The main - * motivation for this is to keep the EC firmware as simple as possible, since - * it cannot be easily upgraded and EC flash/IRAM space is relatively - * expensive. - */ - -#ifndef __LINUX_MFD_CROS_EC_REG_H -#define __LINUX_MFD_CROS_EC_REG_H - -/** - * cros_ec_lpc_read_bytes - Read bytes from a given LPC-mapped address. - * Returns 8-bit checksum of all bytes read. - * - * @offset: Base read address - * @length: Number of bytes to read - * @dest: Destination buffer - */ -u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest); - -/** - * cros_ec_lpc_write_bytes - Write bytes to a given LPC-mapped address. - * Returns 8-bit checksum of all bytes written. - * - * @offset: Base write address - * @length: Number of bytes to write - * @msg: Write data buffer - */ -u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg); - -/** - * cros_ec_lpc_reg_init - * - * Initialize register I/O. - */ -void cros_ec_lpc_reg_init(void); - -/** - * cros_ec_lpc_reg_destroy - * - * Cleanup reg I/O. - */ -void cros_ec_lpc_reg_destroy(void); - -#endif /* __LINUX_MFD_CROS_EC_REG_H */ -- cgit v1.2.3 From e2bbf91cad09118d7500f1fdaaa83d7741d30395 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 18 Jul 2018 18:09:56 +0200 Subject: mfd: cros_ec: Fix and improve kerneldoc comments. cros-ec includes inside the MFD subsystem, specially the file cros_ec_commands.h, has been modified several times and it has grown a lot, unfortunately, we didn't have care too much about the documentation. This patch tries to improve the documentation and also fixes all the issues reported by kerneldoc script. Signed-off-by: Enric Balletbo i Serra Signed-off-by: Benson Leung --- include/linux/mfd/cros_ec.h | 214 +++++++++++++------------ include/linux/mfd/cros_ec_commands.h | 295 ++++++++++++++++++++++------------- 2 files changed, 303 insertions(+), 206 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 20949dde35cd..e44e3ec8a9c7 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -36,7 +36,7 @@ * I2C requires 1 additional byte for requests. * I2C requires 2 additional bytes for responses. * SPI requires up to 32 additional bytes for responses. - * */ + */ #define EC_PROTO_VERSION_UNKNOWN 0 #define EC_MAX_REQUEST_OVERHEAD 1 #define EC_MAX_RESPONSE_OVERHEAD 32 @@ -58,13 +58,14 @@ enum { EC_MAX_MSG_BYTES = 64 * 1024, }; -/* - * @version: Command version number (often 0) - * @command: Command to send (EC_CMD_...) - * @outsize: Outgoing length in bytes - * @insize: Max number of bytes to accept from EC - * @result: EC's response to the command (separate from communication failure) - * @data: Where to put the incoming data from EC and outgoing data to EC +/** + * struct cros_ec_command - Information about a ChromeOS EC command. + * @version: Command version number (often 0). + * @command: Command to send (EC_CMD_...). + * @outsize: Outgoing length in bytes. + * @insize: Max number of bytes to accept from the EC. + * @result: EC's response to the command (separate from communication failure). + * @data: Where to put the incoming data from EC and outgoing data to EC. */ struct cros_ec_command { uint32_t version; @@ -76,48 +77,55 @@ struct cros_ec_command { }; /** - * struct cros_ec_device - Information about a ChromeOS EC device - * - * @phys_name: name of physical comms layer (e.g. 'i2c-4') + * struct cros_ec_device - Information about a ChromeOS EC device. + * @phys_name: Name of physical comms layer (e.g. 'i2c-4'). * @dev: Device pointer for physical comms device - * @was_wake_device: true if this device was set to wake the system from - * sleep at the last suspend - * @cmd_readmem: direct read of the EC memory-mapped region, if supported - * @offset is within EC_LPC_ADDR_MEMMAP region. - * @bytes: number of bytes to read. zero means "read a string" (including - * the trailing '\0'). At most only EC_MEMMAP_SIZE bytes can be read. - * Caller must ensure that the buffer is large enough for the result when - * reading a string. - * - * @priv: Private data - * @irq: Interrupt to use - * @id: Device id - * @din: input buffer (for data from EC) - * @dout: output buffer (for data to EC) - * \note - * These two buffers will always be dword-aligned and include enough - * space for up to 7 word-alignment bytes also, so we can ensure that - * the body of the message is always dword-aligned (64-bit). - * We use this alignment to keep ARM and x86 happy. Probably word - * alignment would be OK, there might be a small performance advantage - * to using dword. - * @din_size: size of din buffer to allocate (zero to use static din) - * @dout_size: size of dout buffer to allocate (zero to use static dout) - * @wake_enabled: true if this device can wake the system from sleep - * @suspended: true if this device had been suspended - * @cmd_xfer: send command to EC and get response - * Returns the number of bytes received if the communication succeeded, but - * that doesn't mean the EC was happy with the command. The caller - * should check msg.result for the EC's result code. - * @pkt_xfer: send packet to EC and get response - * @lock: one transaction at a time - * @mkbp_event_supported: true if this EC supports the MKBP event protocol. - * @event_notifier: interrupt event notifier for transport devices. - * @event_data: raw payload transferred with the MKBP event. - * @event_size: size in bytes of the event data. + * @was_wake_device: True if this device was set to wake the system from + * sleep at the last suspend. + * @cros_class: The class structure for this device. + * @cmd_readmem: Direct read of the EC memory-mapped region, if supported. + * @offset: Is within EC_LPC_ADDR_MEMMAP region. + * @bytes: Number of bytes to read. zero means "read a string" (including + * the trailing '\0'). At most only EC_MEMMAP_SIZE bytes can be + * read. Caller must ensure that the buffer is large enough for the + * result when reading a string. + * @max_request: Max size of message requested. + * @max_response: Max size of message response. + * @max_passthru: Max sice of passthru message. + * @proto_version: The protocol version used for this device. + * @priv: Private data. + * @irq: Interrupt to use. + * @id: Device id. + * @din: Input buffer (for data from EC). This buffer will always be + * dword-aligned and include enough space for up to 7 word-alignment + * bytes also, so we can ensure that the body of the message is always + * dword-aligned (64-bit). We use this alignment to keep ARM and x86 + * happy. Probably word alignment would be OK, there might be a small + * performance advantage to using dword. + * @dout: Output buffer (for data to EC). This buffer will always be + * dword-aligned and include enough space for up to 7 word-alignment + * bytes also, so we can ensure that the body of the message is always + * dword-aligned (64-bit). We use this alignment to keep ARM and x86 + * happy. Probably word alignment would be OK, there might be a small + * performance advantage to using dword. + * @din_size: Size of din buffer to allocate (zero to use static din). + * @dout_size: Size of dout buffer to allocate (zero to use static dout). + * @wake_enabled: True if this device can wake the system from sleep. + * @suspended: True if this device had been suspended. + * @cmd_xfer: Send command to EC and get response. + * Returns the number of bytes received if the communication + * succeeded, but that doesn't mean the EC was happy with the + * command. The caller should check msg.result for the EC's result + * code. + * @pkt_xfer: Send packet to EC and get response. + * @lock: One transaction at a time. + * @mkbp_event_supported: True if this EC supports the MKBP event protocol. + * @event_notifier: Interrupt event notifier for transport devices. + * @event_data: Raw payload transferred with the MKBP event. + * @event_size: Size in bytes of the event data. + * @host_event_wake_mask: Mask of host events that cause wake from suspend. */ struct cros_ec_device { - /* These are used by other drivers that want to talk to the EC */ const char *phys_name; struct device *dev; @@ -153,20 +161,19 @@ struct cros_ec_device { }; /** - * struct cros_ec_sensor_platform - ChromeOS EC sensor platform information - * + * struct cros_ec_sensor_platform - ChromeOS EC sensor platform information. * @sensor_num: Id of the sensor, as reported by the EC. */ struct cros_ec_sensor_platform { u8 sensor_num; }; -/* struct cros_ec_platform - ChromeOS EC platform information - * - * @ec_name: name of EC device (e.g. 'cros-ec', 'cros-pd', ...) - * used in /dev/ and sysfs. - * @cmd_offset: offset to apply for each command. Set when - * registering a devicde behind another one. +/** + * struct cros_ec_platform - ChromeOS EC platform information. + * @ec_name: Name of EC device (e.g. 'cros-ec', 'cros-pd', ...) + * used in /dev/ and sysfs. + * @cmd_offset: Offset to apply for each command. Set when + * registering a device behind another one. */ struct cros_ec_platform { const char *ec_name; @@ -175,16 +182,16 @@ struct cros_ec_platform { struct cros_ec_debugfs; -/* - * struct cros_ec_dev - ChromeOS EC device entry point - * - * @class_dev: Device structure used in sysfs - * @cdev: Character device structure in /dev - * @ec_dev: cros_ec_device structure to talk to the physical device - * @dev: pointer to the platform device - * @debug_info: cros_ec_debugfs structure for debugging information - * @has_kb_wake_angle: true if at least 2 accelerometer are connected to the EC. - * @cmd_offset: offset to apply for each command. +/** + * struct cros_ec_dev - ChromeOS EC device entry point. + * @class_dev: Device structure used in sysfs. + * @cdev: Character device structure in /dev. + * @ec_dev: cros_ec_device structure to talk to the physical device. + * @dev: Pointer to the platform device. + * @debug_info: cros_ec_debugfs structure for debugging information. + * @has_kb_wake_angle: True if at least 2 accelerometer are connected to the EC. + * @cmd_offset: Offset to apply for each command. + * @features: Features supported by the EC. */ struct cros_ec_dev { struct device class_dev; @@ -200,124 +207,129 @@ struct cros_ec_dev { #define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev) /** - * cros_ec_suspend - Handle a suspend operation for the ChromeOS EC device + * cros_ec_suspend() - Handle a suspend operation for the ChromeOS EC device. + * @ec_dev: Device to suspend. * * This can be called by drivers to handle a suspend event. * - * ec_dev: Device to suspend - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_suspend(struct cros_ec_device *ec_dev); /** - * cros_ec_resume - Handle a resume operation for the ChromeOS EC device + * cros_ec_resume() - Handle a resume operation for the ChromeOS EC device. + * @ec_dev: Device to resume. * * This can be called by drivers to handle a resume event. * - * @ec_dev: Device to resume - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_resume(struct cros_ec_device *ec_dev); /** - * cros_ec_prepare_tx - Prepare an outgoing message in the output buffer + * cros_ec_prepare_tx() - Prepare an outgoing message in the output buffer. + * @ec_dev: Device to register. + * @msg: Message to write. * * This is intended to be used by all ChromeOS EC drivers, but at present * only SPI uses it. Once LPC uses the same protocol it can start using it. * I2C could use it now, with a refactor of the existing code. * - * @ec_dev: Device to register - * @msg: Message to write + * Return: 0 on success or negative error code. */ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_check_result - Check ec_msg->result + * cros_ec_check_result() - Check ec_msg->result. + * @ec_dev: EC device. + * @msg: Message to check. * * This is used by ChromeOS EC drivers to check the ec_msg->result for * errors and to warn about them. * - * @ec_dev: EC device - * @msg: Message to check + * Return: 0 on success or negative error code. */ int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_cmd_xfer - Send a command to the ChromeOS EC + * cros_ec_cmd_xfer() - Send a command to the ChromeOS EC. + * @ec_dev: EC device. + * @msg: Message to write. * * Call this to send a command to the ChromeOS EC. This should be used * instead of calling the EC's cmd_xfer() callback directly. * - * @ec_dev: EC device - * @msg: Message to write + * Return: 0 on success or negative error code. */ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_cmd_xfer_status - Send a command to the ChromeOS EC + * cros_ec_cmd_xfer_status() - Send a command to the ChromeOS EC. + * @ec_dev: EC device. + * @msg: Message to write. * * This function is identical to cros_ec_cmd_xfer, except it returns success * status only if both the command was transmitted successfully and the EC * replied with success status. It's not necessary to check msg->result when * using this function. * - * @ec_dev: EC device - * @msg: Message to write - * @return: Num. of bytes transferred on success, <0 on failure + * Return: The number of bytes transferred on success or negative error code. */ int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_remove - Remove a ChromeOS EC + * cros_ec_remove() - Remove a ChromeOS EC. + * @ec_dev: Device to register. * * Call this to deregister a ChromeOS EC, then clean up any private data. * - * @ec_dev: Device to register - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_remove(struct cros_ec_device *ec_dev); /** - * cros_ec_register - Register a new ChromeOS EC, using the provided info + * cros_ec_register() - Register a new ChromeOS EC, using the provided info. + * @ec_dev: Device to register. * * Before calling this, allocate a pointer to a new device and then fill * in all the fields up to the --private-- marker. * - * @ec_dev: Device to register - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_register(struct cros_ec_device *ec_dev); /** - * cros_ec_query_all - Query the protocol version supported by the ChromeOS EC + * cros_ec_query_all() - Query the protocol version supported by the + * ChromeOS EC. + * @ec_dev: Device to register. * - * @ec_dev: Device to register - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_query_all(struct cros_ec_device *ec_dev); /** - * cros_ec_get_next_event - Fetch next event from the ChromeOS EC - * - * @ec_dev: Device to fetch event from + * cros_ec_get_next_event() - Fetch next event from the ChromeOS EC. + * @ec_dev: Device to fetch event from. * @wake_event: Pointer to a bool set to true upon return if the event might be * treated as a wake event. Ignored if null. * - * Returns: 0 on success, Linux error number on failure + * Return: 0 on success or negative error code. */ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); /** - * cros_ec_get_host_event - Return a mask of event set by the EC. + * cros_ec_get_host_event() - Return a mask of event set by the ChromeOS EC. + * @ec_dev: Device to fetch event from. * - * When MKBP is supported, when the EC raises an interrupt, - * We collect the events raised and call the functions in the ec notifier. + * When MKBP is supported, when the EC raises an interrupt, we collect the + * events raised and call the functions in the ec notifier. This function + * is a helper to know which events are raised. * - * This function is a helper to know which events are raised. + * Return: 0 on success or negative error code. */ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 6e1ab9bead28..88100bddf1ab 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -306,15 +306,18 @@ enum host_event_code { /* Host event mask */ #define EC_HOST_EVENT_MASK(event_code) (1UL << ((event_code) - 1)) -/* Arguments at EC_LPC_ADDR_HOST_ARGS */ +/** + * struct ec_lpc_host_args - Arguments at EC_LPC_ADDR_HOST_ARGS + * @flags: The host argument flags. + * @command_version: Command version. + * @data_size: The length of data. + * @checksum: Checksum; sum of command + flags + command_version + data_size + + * all params/response data bytes. + */ struct ec_lpc_host_args { uint8_t flags; uint8_t command_version; uint8_t data_size; - /* - * Checksum; sum of command + flags + command_version + data_size + - * all params/response data bytes. - */ uint8_t checksum; } __packed; @@ -468,54 +471,43 @@ struct ec_lpc_host_args { #define EC_HOST_REQUEST_VERSION 3 -/* Version 3 request from host */ +/** + * struct ec_host_request - Version 3 request from host. + * @struct_version: Should be 3. The EC will return EC_RES_INVALID_HEADER if it + * receives a header with a version it doesn't know how to + * parse. + * @checksum: Checksum of request and data; sum of all bytes including checksum + * should total to 0. + * @command: Command to send (EC_CMD_...) + * @command_version: Command version. + * @reserved: Unused byte in current protocol version; set to 0. + * @data_len: Length of data which follows this header. + */ struct ec_host_request { - /* Struct version (=3) - * - * EC will return EC_RES_INVALID_HEADER if it receives a header with a - * version it doesn't know how to parse. - */ uint8_t struct_version; - - /* - * Checksum of request and data; sum of all bytes including checksum - * should total to 0. - */ uint8_t checksum; - - /* Command code */ uint16_t command; - - /* Command version */ uint8_t command_version; - - /* Unused byte in current protocol version; set to 0 */ uint8_t reserved; - - /* Length of data which follows this header */ uint16_t data_len; } __packed; #define EC_HOST_RESPONSE_VERSION 3 -/* Version 3 response from EC */ +/** + * struct ec_host_response - Version 3 response from EC. + * @struct_version: Struct version (=3). + * @checksum: Checksum of response and data; sum of all bytes including + * checksum should total to 0. + * @result: EC's response to the command (separate from communication failure) + * @data_len: Length of data which follows this header. + * @reserved: Unused bytes in current protocol version; set to 0. + */ struct ec_host_response { - /* Struct version (=3) */ uint8_t struct_version; - - /* - * Checksum of response and data; sum of all bytes including checksum - * should total to 0. - */ uint8_t checksum; - - /* Result code (EC_RES_*) */ uint16_t result; - - /* Length of data which follows this header */ uint16_t data_len; - - /* Unused bytes in current protocol version; set to 0 */ uint16_t reserved; } __packed; @@ -540,6 +532,10 @@ struct ec_host_response { */ #define EC_CMD_PROTO_VERSION 0x00 +/** + * struct ec_response_proto_version - Response to the proto version command. + * @version: The protocol version. + */ struct ec_response_proto_version { uint32_t version; } __packed; @@ -550,12 +546,20 @@ struct ec_response_proto_version { */ #define EC_CMD_HELLO 0x01 +/** + * struct ec_params_hello - Parameters to the hello command. + * @in_data: Pass anything here. + */ struct ec_params_hello { - uint32_t in_data; /* Pass anything here */ + uint32_t in_data; } __packed; +/** + * struct ec_response_hello - Response to the hello command. + * @out_data: Output will be in_data + 0x01020304. + */ struct ec_response_hello { - uint32_t out_data; /* Output will be in_data + 0x01020304 */ + uint32_t out_data; } __packed; /* Get version number */ @@ -567,22 +571,37 @@ enum ec_current_image { EC_IMAGE_RW }; +/** + * struct ec_response_get_version - Response to the get version command. + * @version_string_ro: Null-terminated RO firmware version string. + * @version_string_rw: Null-terminated RW firmware version string. + * @reserved: Unused bytes; was previously RW-B firmware version string. + * @current_image: One of ec_current_image. + */ struct ec_response_get_version { - /* Null-terminated version strings for RO, RW */ char version_string_ro[32]; char version_string_rw[32]; - char reserved[32]; /* Was previously RW-B string */ - uint32_t current_image; /* One of ec_current_image */ + char reserved[32]; + uint32_t current_image; } __packed; /* Read test */ #define EC_CMD_READ_TEST 0x03 +/** + * struct ec_params_read_test - Parameters for the read test command. + * @offset: Starting value for read buffer. + * @size: Size to read in bytes. + */ struct ec_params_read_test { - uint32_t offset; /* Starting value for read buffer */ - uint32_t size; /* Size to read in bytes */ + uint32_t offset; + uint32_t size; } __packed; +/** + * struct ec_response_read_test - Response to the read test command. + * @data: Data returned by the read test command. + */ struct ec_response_read_test { uint32_t data[32]; } __packed; @@ -597,18 +616,27 @@ struct ec_response_read_test { /* Get chip info */ #define EC_CMD_GET_CHIP_INFO 0x05 +/** + * struct ec_response_get_chip_info - Response to the get chip info command. + * @vendor: Null-terminated string for chip vendor. + * @name: Null-terminated string for chip name. + * @revision: Null-terminated string for chip mask version. + */ struct ec_response_get_chip_info { - /* Null-terminated strings */ char vendor[32]; char name[32]; - char revision[32]; /* Mask version */ + char revision[32]; } __packed; /* Get board HW version */ #define EC_CMD_GET_BOARD_VERSION 0x06 +/** + * struct ec_response_board_version - Response to the board version command. + * @board_version: A monotonously incrementing number. + */ struct ec_response_board_version { - uint16_t board_version; /* A monotonously incrementing number. */ + uint16_t board_version; } __packed; /* @@ -621,27 +649,42 @@ struct ec_response_board_version { */ #define EC_CMD_READ_MEMMAP 0x07 +/** + * struct ec_params_read_memmap - Parameters for the read memory map command. + * @offset: Offset in memmap (EC_MEMMAP_*). + * @size: Size to read in bytes. + */ struct ec_params_read_memmap { - uint8_t offset; /* Offset in memmap (EC_MEMMAP_*) */ - uint8_t size; /* Size to read in bytes */ + uint8_t offset; + uint8_t size; } __packed; /* Read versions supported for a command */ #define EC_CMD_GET_CMD_VERSIONS 0x08 +/** + * struct ec_params_get_cmd_versions - Parameters for the get command versions. + * @cmd: Command to check. + */ struct ec_params_get_cmd_versions { - uint8_t cmd; /* Command to check */ + uint8_t cmd; } __packed; +/** + * struct ec_params_get_cmd_versions_v1 - Parameters for the get command + * versions (v1) + * @cmd: Command to check. + */ struct ec_params_get_cmd_versions_v1 { - uint16_t cmd; /* Command to check */ + uint16_t cmd; } __packed; +/** + * struct ec_response_get_cmd_version - Response to the get command versions. + * @version_mask: Mask of supported versions; use EC_VER_MASK() to compare with + * a desired version. + */ struct ec_response_get_cmd_versions { - /* - * Mask of supported versions; use EC_VER_MASK() to compare with a - * desired version. - */ uint32_t version_mask; } __packed; @@ -659,6 +702,11 @@ enum ec_comms_status { EC_COMMS_STATUS_PROCESSING = 1 << 0, /* Processing cmd */ }; +/** + * struct ec_response_get_comms_status - Response to the get comms status + * command. + * @flags: Mask of enum ec_comms_status. + */ struct ec_response_get_comms_status { uint32_t flags; /* Mask of enum ec_comms_status */ } __packed; @@ -685,19 +733,19 @@ struct ec_response_test_protocol { /* EC_RES_IN_PROGRESS may be returned if a command is slow */ #define EC_PROTOCOL_INFO_IN_PROGRESS_SUPPORTED (1 << 0) +/** + * struct ec_response_get_protocol_info - Response to the get protocol info. + * @protocol_versions: Bitmask of protocol versions supported (1 << n means + * version n). + * @max_request_packet_size: Maximum request packet size in bytes. + * @max_response_packet_size: Maximum response packet size in bytes. + * @flags: see EC_PROTOCOL_INFO_* + */ struct ec_response_get_protocol_info { /* Fields which exist if at least protocol version 3 supported */ - - /* Bitmask of protocol versions supported (1 << n means version n)*/ uint32_t protocol_versions; - - /* Maximum request packet size, in bytes */ uint16_t max_request_packet_size; - - /* Maximum response packet size, in bytes */ uint16_t max_response_packet_size; - - /* Flags; see EC_PROTOCOL_INFO_* */ uint32_t flags; } __packed; @@ -708,8 +756,10 @@ struct ec_response_get_protocol_info { /* The upper byte of .flags tells what to do (nothing means "get") */ #define EC_GSV_SET 0x80000000 -/* The lower three bytes of .flags identifies the parameter, if that has - meaning for an individual command. */ +/* + * The lower three bytes of .flags identifies the parameter, if that has + * meaning for an individual command. + */ #define EC_GSV_PARAM_MASK 0x00ffffff struct ec_params_get_set_value { @@ -810,6 +860,7 @@ enum ec_feature_code { #define EC_FEATURE_MASK_0(event_code) (1UL << (event_code % 32)) #define EC_FEATURE_MASK_1(event_code) (1UL << (event_code - 32)) + struct ec_response_get_features { uint32_t flags[2]; } __packed; @@ -820,24 +871,22 @@ struct ec_response_get_features { /* Get flash info */ #define EC_CMD_FLASH_INFO 0x10 -/* Version 0 returns these fields */ +/** + * struct ec_response_flash_info - Response to the flash info command. + * @flash_size: Usable flash size in bytes. + * @write_block_size: Write block size. Write offset and size must be a + * multiple of this. + * @erase_block_size: Erase block size. Erase offset and size must be a + * multiple of this. + * @protect_block_size: Protection block size. Protection offset and size + * must be a multiple of this. + * + * Version 0 returns these fields. + */ struct ec_response_flash_info { - /* Usable flash size, in bytes */ uint32_t flash_size; - /* - * Write block size. Write offset and size must be a multiple - * of this. - */ uint32_t write_block_size; - /* - * Erase block size. Erase offset and size must be a multiple - * of this. - */ uint32_t erase_block_size; - /* - * Protection block size. Protection offset and size must be a - * multiple of this. - */ uint32_t protect_block_size; } __packed; @@ -845,7 +894,22 @@ struct ec_response_flash_info { /* EC flash erases bits to 0 instead of 1 */ #define EC_FLASH_INFO_ERASE_TO_0 (1 << 0) -/* +/** + * struct ec_response_flash_info_1 - Response to the flash info v1 command. + * @flash_size: Usable flash size in bytes. + * @write_block_size: Write block size. Write offset and size must be a + * multiple of this. + * @erase_block_size: Erase block size. Erase offset and size must be a + * multiple of this. + * @protect_block_size: Protection block size. Protection offset and size + * must be a multiple of this. + * @write_ideal_size: Ideal write size in bytes. Writes will be fastest if + * size is exactly this and offset is a multiple of this. + * For example, an EC may have a write buffer which can do + * half-page operations if data is aligned, and a slower + * word-at-a-time write mode. + * @flags: Flags; see EC_FLASH_INFO_* + * * Version 1 returns the same initial fields as version 0, with additional * fields following. * @@ -860,15 +924,7 @@ struct ec_response_flash_info_1 { uint32_t protect_block_size; /* Version 1 adds these fields: */ - /* - * Ideal write size in bytes. Writes will be fastest if size is - * exactly this and offset is a multiple of this. For example, an EC - * may have a write buffer which can do half-page operations if data is - * aligned, and a slower word-at-a-time write mode. - */ uint32_t write_ideal_size; - - /* Flags; see EC_FLASH_INFO_* */ uint32_t flags; } __packed; @@ -879,9 +935,14 @@ struct ec_response_flash_info_1 { */ #define EC_CMD_FLASH_READ 0x11 +/** + * struct ec_params_flash_read - Parameters for the flash read command. + * @offset: Byte offset to read. + * @size: Size to read in bytes. + */ struct ec_params_flash_read { - uint32_t offset; /* Byte offset to read */ - uint32_t size; /* Size to read in bytes */ + uint32_t offset; + uint32_t size; } __packed; /* Write flash */ @@ -891,18 +952,28 @@ struct ec_params_flash_read { /* Version 0 of the flash command supported only 64 bytes of data */ #define EC_FLASH_WRITE_VER0_SIZE 64 +/** + * struct ec_params_flash_write - Parameters for the flash write command. + * @offset: Byte offset to write. + * @size: Size to write in bytes. + */ struct ec_params_flash_write { - uint32_t offset; /* Byte offset to write */ - uint32_t size; /* Size to write in bytes */ + uint32_t offset; + uint32_t size; /* Followed by data to write */ } __packed; /* Erase flash */ #define EC_CMD_FLASH_ERASE 0x13 +/** + * struct ec_params_flash_erase - Parameters for the flash erase command. + * @offset: Byte offset to erase. + * @size: Size to erase in bytes. + */ struct ec_params_flash_erase { - uint32_t offset; /* Byte offset to erase */ - uint32_t size; /* Size to erase in bytes */ + uint32_t offset; + uint32_t size; } __packed; /* @@ -941,21 +1012,28 @@ struct ec_params_flash_erase { /* Entile flash code protected when the EC boots */ #define EC_FLASH_PROTECT_ALL_AT_BOOT (1 << 6) +/** + * struct ec_params_flash_protect - Parameters for the flash protect command. + * @mask: Bits in flags to apply. + * @flags: New flags to apply. + */ struct ec_params_flash_protect { - uint32_t mask; /* Bits in flags to apply */ - uint32_t flags; /* New flags to apply */ + uint32_t mask; + uint32_t flags; } __packed; +/** + * struct ec_response_flash_protect - Response to the flash protect command. + * @flags: Current value of flash protect flags. + * @valid_flags: Flags which are valid on this platform. This allows the + * caller to distinguish between flags which aren't set vs. flags + * which can't be set on this platform. + * @writable_flags: Flags which can be changed given the current protection + * state. + */ struct ec_response_flash_protect { - /* Current value of flash protect flags */ uint32_t flags; - /* - * Flags which are valid on this platform. This allows the caller - * to distinguish between flags which aren't set vs. flags which can't - * be set on this platform. - */ uint32_t valid_flags; - /* Flags which can be changed given the current protection state */ uint32_t writable_flags; } __packed; @@ -982,8 +1060,13 @@ enum ec_flash_region { EC_FLASH_REGION_COUNT, }; +/** + * struct ec_params_flash_region_info - Parameters for the flash region info + * command. + * @region: Flash region; see EC_FLASH_REGION_* + */ struct ec_params_flash_region_info { - uint32_t region; /* enum ec_flash_region */ + uint32_t region; } __packed; struct ec_response_flash_region_info { @@ -1094,7 +1177,9 @@ struct rgb_s { }; #define LB_BATTERY_LEVELS 4 -/* List of tweakable parameters. NOTE: It's __packed so it can be sent in a + +/* + * List of tweakable parameters. NOTE: It's __packed so it can be sent in a * host command, but the alignment is the same regardless. Keep it that way. */ struct lightbar_params_v0 { -- cgit v1.2.3 From 1c96a2f67cd9b617b013f0a7580d76aae7dcd0d7 Mon Sep 17 00:00:00 2001 From: David Frey Date: Sat, 1 Sep 2018 09:50:41 -0700 Subject: regmap: split up regmap_config.use_single_rw Split regmap_config.use_single_rw into use_single_read and use_single_write. This change enables drivers of devices which only support bulk operations in one direction to use the regmap_bulk_*() functions for both directions and have their bulk operation split into single operations only when necessary. Update all struct regmap_config instances where use_single_rw==true to instead set both use_single_read and use_single_write. No attempt was made to evaluate whether it is possible to set only one of use_single_read or use_single_write. Signed-off-by: David Frey Signed-off-by: Mark Brown --- include/linux/regmap.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 379505a53722..6ea9bf9377cb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -315,9 +315,12 @@ typedef void (*regmap_unlock)(void *); * masks are used. * @zero_flag_mask: If set, read_flag_mask and write_flag_mask are used even * if they are both empty. - * @use_single_rw: If set, converts the bulk read and write operations into - * a series of single read and write operations. This is useful - * for device that does not support bulk read and write. + * @use_single_read: If set, converts the bulk read operation into a series of + * single read operations. This is useful for a device that + * does not support bulk read. + * @use_single_write: If set, converts the bulk write operation into a series of + * single write operations. This is useful for a device that + * does not support bulk write. * @can_multi_write: If set, the device supports the multi write mode of bulk * write operations, if clear multi write requests will be * split into individual write operations @@ -380,7 +383,8 @@ struct regmap_config { unsigned long write_flag_mask; bool zero_flag_mask; - bool use_single_rw; + bool use_single_read; + bool use_single_write; bool can_multi_write; enum regmap_endian reg_format_endian; -- cgit v1.2.3 From 00b7d1cf46676ad5e6338e80dc6230e1b6e71b86 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Aug 2018 17:21:45 -0500 Subject: of: make default address and size cells sizes private Only some old OpenFirmware implementations rely on default sizes. Any FDT and modern implementation should have explicit properties. Make the OF_ROOT_NODE_*_CELLS_DEFAULT defines private so we don't get any outside users. This also gets us one step closer to removing the asm/prom.h dependency on Sparc. Cc: "David S. Miller" Cc: Frank Rowand Cc: sparclinux@vger.kernel.org Signed-off-by: Rob Herring --- include/linux/of.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..2141490b368f 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -247,12 +247,6 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) #include #endif -/* Default #address and #size cells. Allow arch asm/prom.h to override */ -#if !defined(OF_ROOT_NODE_ADDR_CELLS_DEFAULT) -#define OF_ROOT_NODE_ADDR_CELLS_DEFAULT 1 -#define OF_ROOT_NODE_SIZE_CELLS_DEFAULT 1 -#endif - #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags) #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags) -- cgit v1.2.3 From ccf640f4c9988653ef884672381b03b9be247bec Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Aug 2018 09:40:24 +0200 Subject: dma-mapping: remove dma_configure There is no good reason for this indirection given that the method always exists. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/dma-mapping.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 1db6a6b46d0d..1c6c7c09bcf2 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -754,14 +754,8 @@ dma_mark_declared_memory_occupied(struct device *dev, #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */ #ifdef CONFIG_HAS_DMA -int dma_configure(struct device *dev); void dma_deconfigure(struct device *dev); #else -static inline int dma_configure(struct device *dev) -{ - return 0; -} - static inline void dma_deconfigure(struct device *dev) {} #endif -- cgit v1.2.3 From dc3c05504d38849f77149cb962caeaedd1efa127 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Aug 2018 10:28:18 +0200 Subject: dma-mapping: remove dma_deconfigure This goes through a lot of hooks just to call arch_teardown_dma_ops. Replace it with a direct call instead. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/acpi.h | 2 -- include/linux/dma-mapping.h | 6 ------ include/linux/of_device.h | 3 --- 3 files changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index de8d3d3fa651..af4628979d13 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -831,8 +831,6 @@ static inline int acpi_dma_configure(struct device *dev, return 0; } -static inline void acpi_dma_deconfigure(struct device *dev) { } - #define ACPI_PTR(_ptr) (NULL) static inline void acpi_device_set_enumerated(struct acpi_device *adev) diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 1c6c7c09bcf2..1423b69f3cc9 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -753,12 +753,6 @@ dma_mark_declared_memory_occupied(struct device *dev, } #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */ -#ifdef CONFIG_HAS_DMA -void dma_deconfigure(struct device *dev); -#else -static inline void dma_deconfigure(struct device *dev) {} -#endif - /* * Managed DMA API */ diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 165fd302b442..8d31e39dd564 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -58,7 +58,6 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma); -void of_dma_deconfigure(struct device *dev); #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, @@ -113,8 +112,6 @@ static inline int of_dma_configure(struct device *dev, { return 0; } -static inline void of_dma_deconfigure(struct device *dev) -{} #endif /* CONFIG_OF */ #endif /* _LINUX_OF_DEVICE_H */ -- cgit v1.2.3 From 46053c73685411915d3de50c5a0045beef32806b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Aug 2018 10:29:02 +0200 Subject: dma-mapping: clear dev->dma_ops in arch_teardown_dma_ops There is no reason to leave the per-device dma_ops around when deconfiguring a device, so move this code from arm64 into the common code. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/dma-mapping.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 1423b69f3cc9..eafd6f318e78 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -664,7 +664,10 @@ static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, #endif #ifndef arch_teardown_dma_ops -static inline void arch_teardown_dma_ops(struct device *dev) { } +static inline void arch_teardown_dma_ops(struct device *dev) +{ + dev->dma_ops = NULL; +} #endif static inline unsigned int dma_get_max_seg_size(struct device *dev) -- cgit v1.2.3 From 02ad0437decf2e5dba975c23b1a89775f4b211e1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 3 Sep 2018 12:55:30 -0700 Subject: gpio: fix kernel-doc notation warning for 'request_key' Fix kernel-doc warning for missing struct member 'request_key': ../include/linux/gpio/driver.h:142: warning: Function parameter or member 'request_key' not described in 'gpio_irq_chip' Fixes: 39c3fd58952d ("kernel/irq: Extend lockdep class for request mutex") Signed-off-by: Randy Dunlap Cc: Andrew Lunn Cc: Thomas Gleixner Cc: Linus Walleij Cc: linux-gpio@vger.kernel.org Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 0ea328e71ec9..4a4f410b5285 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -66,9 +66,15 @@ struct gpio_irq_chip { /** * @lock_key: * - * Per GPIO IRQ chip lockdep classes. + * Per GPIO IRQ chip lockdep class for IRQ lock. */ struct lock_class_key *lock_key; + + /** + * @request_key: + * + * Per GPIO IRQ chip lockdep class for IRQ request. + */ struct lock_class_key *request_key; /** -- cgit v1.2.3 From 4e6b823867e2b8afc2b33740ba930e50b1f92421 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 8 Sep 2018 11:23:14 +0200 Subject: gpiolib: export gpiochip_irq_reqres/relres() GPIO drivers that do not use GPIOLIB_IRQCHIP can hook these into the irq_request_resource and irq_release_resource callbacks of the irq_chip so they correctly 'get' the module and lock the gpio line for IRQ use. This will simplify driver code. Signed-off-by: Hans Verkuil Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 4a4f410b5285..479f1ccaaebd 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -401,6 +401,8 @@ extern struct gpio_chip *gpiochip_find(void *data, int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset); void gpiochip_unlock_as_irq(struct gpio_chip *chip, unsigned int offset); bool gpiochip_line_is_irq(struct gpio_chip *chip, unsigned int offset); +int gpiochip_reqres_irq(struct gpio_chip *chip, unsigned int offset); +void gpiochip_relres_irq(struct gpio_chip *chip, unsigned int offset); /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *chip, unsigned int offset); -- cgit v1.2.3 From 4e9439ddacea06f35acce4d374bf6bd0acf99bc8 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 8 Sep 2018 11:23:16 +0200 Subject: gpiolib: add flag to indicate if the irq is disabled GPIO drivers call gpiochip_(un)lock_as_irq whenever they want to use a gpio as an interrupt. This is done when the irq is requested and it marks the gpio as in use by an interrupt. This is problematic for cases where a gpio pin is used as an interrupt pin, then, after the irq is disabled, is used as a regular gpio pin. Currently it is not possible to do this other than by first freeing the interrupt so gpiochip_unlock_as_irq is called, since an attempt to switch the gpio direction for output will fail since gpiolib believes that the gpio is in use for an interrupt and it does not know that it the irq is actually disabled. There are currently two drivers that would like to be able to do this: the tda998x_drv.c driver where a regular gpio pin needs to be temporarily reconfigured as an interrupt pin during CEC calibration, and the cec-gpio driver where you want to configure the gpio pin as an interrupt while waiting for traffic over the CEC bus, or as a regular pin when receiving or transmitting a CEC message. The solution is to add a new flag that is set when the irq is enabled, and have gpiod_direction_output check for that flag. We also add functions that drivers that do not use GPIOLIB_IRQCHIP can call when they enable/disable the irq. Signed-off-by: Hans Verkuil Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 479f1ccaaebd..9052ccd399fd 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -403,6 +403,8 @@ void gpiochip_unlock_as_irq(struct gpio_chip *chip, unsigned int offset); bool gpiochip_line_is_irq(struct gpio_chip *chip, unsigned int offset); int gpiochip_reqres_irq(struct gpio_chip *chip, unsigned int offset); void gpiochip_relres_irq(struct gpio_chip *chip, unsigned int offset); +void gpiochip_disable_irq(struct gpio_chip *chip, unsigned int offset); +void gpiochip_enable_irq(struct gpio_chip *chip, unsigned int offset); /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *chip, unsigned int offset); -- cgit v1.2.3 From 461c1a7d4733d1dfd5c47b040cf32a5e7eefbc6c Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 8 Sep 2018 11:23:17 +0200 Subject: gpiolib: override irq_enable/disable When using the gpiolib irqchip helpers install irq_enable/disable hooks for the irqchip to ensure that gpiolib knows when the irq is enabled or disabled, allowing drivers to disable the irq and then use it as an output pin, and later switch the direction to input and re-enable the irq. Signed-off-by: Hans Verkuil Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 9052ccd399fd..d8dcd0e44cab 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -144,6 +144,20 @@ struct gpio_irq_chip { * will allocate and map all IRQs during initialization. */ unsigned int first; + + /** + * @irq_enable: + * + * Store old irq_chip irq_enable callback + */ + void (*irq_enable)(struct irq_data *data); + + /** + * @irq_disable: + * + * Store old irq_chip irq_disable callback + */ + void (*irq_disable)(struct irq_data *data); }; static inline struct gpio_irq_chip *to_gpio_irq_chip(struct irq_chip *chip) -- cgit v1.2.3 From 05484e0984487d42e97c417cbb0697fa9d16e7e9 Mon Sep 17 00:00:00 2001 From: Morten Rasmussen Date: Fri, 20 Jul 2018 14:32:31 +0100 Subject: sched/topology: Add SD_ASYM_CPUCAPACITY flag detection The SD_ASYM_CPUCAPACITY sched_domain flag is supposed to mark the sched_domain in the hierarchy where all CPU capacities are visible for any CPU's point of view on asymmetric CPU capacity systems. The scheduler can then take to take capacity asymmetry into account when balancing at this level. It also serves as an indicator for how wide task placement heuristics have to search to consider all available CPU capacities as asymmetric systems might often appear symmetric at smallest level(s) of the sched_domain hierarchy. The flag has been around for while but so far only been set by out-of-tree code in Android kernels. One solution is to let each architecture provide the flag through a custom sched_domain topology array and associated mask and flag functions. However, SD_ASYM_CPUCAPACITY is special in the sense that it depends on the capacity and presence of all CPUs in the system, i.e. when hotplugging all CPUs out except those with one particular CPU capacity the flag should disappear even if the sched_domains don't collapse. Similarly, the flag is affected by cpusets where load-balancing is turned off. Detecting when the flags should be set therefore depends not only on topology information but also the cpuset configuration and hotplug state. The arch code doesn't have easy access to the cpuset configuration. Instead, this patch implements the flag detection in generic code where cpusets and hotplug state is already taken care of. All the arch is responsible for is to implement arch_scale_cpu_capacity() and force a full rebuild of the sched_domain hierarchy if capacities are updated, e.g. later in the boot process when cpufreq has initialized. Signed-off-by: Morten Rasmussen Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dietmar.eggemann@arm.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1532093554-30504-2-git-send-email-morten.rasmussen@arm.com [ Fixed 'CPU' capitalization. ] Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 26347741ba50..6b9976180c1e 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -23,10 +23,10 @@ #define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */ #define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ #define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ -#define SD_ASYM_CPUCAPACITY 0x0040 /* Groups have different max cpu capacities */ -#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share cpu capacity */ +#define SD_ASYM_CPUCAPACITY 0x0040 /* Domain members have different CPU capacities */ +#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share CPU capacity */ #define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */ -#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ +#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share CPU pkg resources */ #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ #define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ -- cgit v1.2.3 From bb1fbdd3c3fd12b612c7d8cdf13bd6bfeebdefa3 Mon Sep 17 00:00:00 2001 From: Morten Rasmussen Date: Fri, 20 Jul 2018 14:32:32 +0100 Subject: sched/topology, drivers/base/arch_topology: Rebuild the sched_domain hierarchy when capacities change The setting of SD_ASYM_CPUCAPACITY depends on the per-CPU capacities. These might not have their final values when the hierarchy is initially built as the values depend on cpufreq to be initialized or the values being set through sysfs. To ensure that the flags are set correctly we need to rebuild the sched_domain hierarchy whenever the reported per-CPU capacity (arch_scale_cpu_capacity()) changes. This patch ensure that a full sched_domain rebuild happens when CPU capacity changes occur. Signed-off-by: Morten Rasmussen Signed-off-by: Peter Zijlstra (Intel) Cc: Greg Kroah-Hartman Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dietmar.eggemann@arm.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1532093554-30504-3-git-send-email-morten.rasmussen@arm.com Signed-off-by: Ingo Molnar --- include/linux/arch_topology.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 2b709416de05..d9bdc1a7f4e7 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -9,6 +9,7 @@ #include void topology_normalize_cpu_scale(void); +int topology_update_cpu_topology(void); struct device_node; bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); -- cgit v1.2.3 From 925b9cd1b89a94b7124d128c80dfc48f78a63098 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 6 Sep 2018 16:18:34 -0400 Subject: locking/rwsem: Make owner store task pointer of last owning reader Currently, when a reader acquires a lock, it only sets the RWSEM_READER_OWNED bit in the owner field. The other bits are simply not used. When debugging hanging cases involving rwsems and readers, the owner value does not provide much useful information at all. This patch modifies the current behavior to always store the task_struct pointer of the last rwsem-acquiring reader in a reader-owned rwsem. This may be useful in debugging rwsem hanging cases especially if only one reader is involved. However, the task in the owner field may not the real owner or one of the real owners at all when the owner value is examined, for example, in a crash dump. So it is just an additional hint about the past history. If CONFIG_DEBUG_RWSEMS=y is enabled, the owner field will be checked at unlock time too to make sure the task pointer value is valid. That does have a slight performance cost and so is only enabled as part of that debug option. From the performance point of view, it is expected that the changes shouldn't have any noticeable performance impact. A rwsem microbenchmark (with 48 worker threads and 1:1 reader/writer ratio) was ran on a 2-socket 24-core 48-thread Haswell system. The locking rates on a 4.19-rc1 based kernel were as follows: 1) Unpatched kernel: 543.3 kops/s 2) Patched kernel: 549.2 kops/s 3) Patched kernel (CONFIG_DEBUG_RWSEMS on): 546.6 kops/s There was actually a slight increase in performance (1.1%) in this particular case. Maybe it was caused by the elimination of a branch or just a testing noise. Turning on the CONFIG_DEBUG_RWSEMS option also had less than the expected impact on performance. The least significant 2 bits of the owner value are now used to designate the rwsem is readers owned and the owners are anonymous. Signed-off-by: Waiman Long Acked-by: Peter Zijlstra Cc: Davidlohr Bueso Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: http://lkml.kernel.org/r/1536265114-10842-1-git-send-email-longman@redhat.com Signed-off-by: Ingo Molnar --- include/linux/rwsem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index ab93b6eae696..67dbb57508b1 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -45,10 +45,10 @@ struct rw_semaphore { }; /* - * Setting bit 0 of the owner field with other non-zero bits will indicate + * Setting bit 1 of the owner field but not bit 0 will indicate * that the rwsem is writer-owned with an unknown owner. */ -#define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-1L) +#define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-2L) extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem); -- cgit v1.2.3 From 719cf71cada1abc4f8727eac918b639a4a502a59 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 20 Aug 2018 16:45:41 +0300 Subject: ACPI / glue: Split dev_is_platform() out of module for wide use There would be useful to have in future the similar API in platform core, as we have, for example, for PCI subsystem, to check if device belongs to it. Thus, split out conditional to a macro dev_is_platform() for wide use. No functional change intended. Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/platform_device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 1a9f38f27f65..c7c081dc6034 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -40,6 +40,7 @@ struct platform_device { #define platform_get_device_id(pdev) ((pdev)->id_entry) +#define dev_is_platform(dev) ((dev)->bus == &platform_bus_type) #define to_platform_device(x) container_of((x), struct platform_device, dev) extern int platform_device_register(struct platform_device *); -- cgit v1.2.3 From d31ca7e5d0fa066d59540859af32ab6f95adb519 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 30 Aug 2018 14:20:04 +0100 Subject: mfd: madera: Add irqchip data pointer into struct madera Put the pointer to struct regmap_irq_chip_data into the parent mfd structure so that the child irqchip driver does not need a trivial private structure to store only this pointer. As the irqchip child driver already has a pointer to the parent struct madera it can use that to store the pointer. This also means that the irqchip driver does not need a double-indirection from its local struct to get at the parent struct madera. Signed-off-by: Richard Fitzgerald Signed-off-by: Lee Jones --- include/linux/mfd/madera/core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/core.h b/include/linux/mfd/madera/core.h index c332681848ef..fe69c0f4398f 100644 --- a/include/linux/mfd/madera/core.h +++ b/include/linux/mfd/madera/core.h @@ -148,6 +148,7 @@ struct snd_soc_dapm_context; * @internal_dcvdd: true if DCVDD is supplied from the internal LDO1 * @pdata: our pdata * @irq_dev: the irqchip child driver device + * @irq_data: pointer to irqchip data for the child irqchip driver * @irq: host irq number from SPI or I2C configuration * @out_clamp: indicates output clamp state for each analogue output * @out_shorted: indicates short circuit state for each analogue output @@ -175,6 +176,7 @@ struct madera { struct madera_pdata pdata; struct device *irq_dev; + struct regmap_irq_chip_data *irq_data; int irq; unsigned int num_micbias; -- cgit v1.2.3 From a318c2432218d3cd189ec8228b8a795666899c2a Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 31 Aug 2018 14:34:02 +0200 Subject: mfd: da9063: Fix DT probing with constraints Commit 1c892e38ce59 ("regulator: da9063: Handle less LDOs on DA9063L") reordered the da9063_regulator_info[] array, but not the DA9063_ID_* regulator ids and not the da9063_matches[] array, because ids are used as indices in the array initializer. This mismatch between regulator id and da9063_regulator_info[] array index causes the driver probe to fail because constraints from DT are not applied to the correct regulator: da9063 0-0058: Device detected (chip-ID: 0x61, var-ID: 0x50) DA9063_BMEM: Bringing 900000uV into 3300000-3300000uV DA9063_LDO9: Bringing 3300000uV into 2500000-2500000uV DA9063_LDO1: Bringing 900000uV into 3300000-3300000uV DA9063_LDO1: failed to apply 3300000-3300000uV constraint(-22) This patch reorders the DA9063_ID_* as apparently intended, and with them the entries in the da90630_matches[] array. Fixes: 1c892e38ce59 ("regulator: da9063: Handle less LDOs on DA9063L") Signed-off-by: Philipp Zabel Reviewed-by: Marek Vasut Reviewed-by: Geert Uytterhoeven Signed-off-by: Lee Jones --- include/linux/mfd/da9063/pdata.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/pdata.h b/include/linux/mfd/da9063/pdata.h index 8a125701ef7b..50bed4f89c1a 100644 --- a/include/linux/mfd/da9063/pdata.h +++ b/include/linux/mfd/da9063/pdata.h @@ -21,7 +21,7 @@ /* * Regulator configuration */ -/* DA9063 regulator IDs */ +/* DA9063 and DA9063L regulator IDs */ enum { /* BUCKs */ DA9063_ID_BCORE1, @@ -37,18 +37,20 @@ enum { DA9063_ID_BMEM_BIO_MERGED, /* When two BUCKs are merged, they cannot be reused separately */ - /* LDOs */ + /* LDOs on both DA9063 and DA9063L */ + DA9063_ID_LDO3, + DA9063_ID_LDO7, + DA9063_ID_LDO8, + DA9063_ID_LDO9, + DA9063_ID_LDO11, + + /* DA9063-only LDOs */ DA9063_ID_LDO1, DA9063_ID_LDO2, - DA9063_ID_LDO3, DA9063_ID_LDO4, DA9063_ID_LDO5, DA9063_ID_LDO6, - DA9063_ID_LDO7, - DA9063_ID_LDO8, - DA9063_ID_LDO9, DA9063_ID_LDO10, - DA9063_ID_LDO11, }; /* Regulators platform data */ -- cgit v1.2.3 From 1a63fe9a2b1f47af5b2b7436b41824b14999c17a Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 10 Sep 2018 17:28:10 +0100 Subject: firmware: arm_scmi: add a getter for power of performance states The SCMI protocol can be used to get power estimates from firmware corresponding to each performance state of a device. Although these power costs are already managed by the SCMI firmware driver, they are not exposed to any external subsystem yet. Fix this by adding a new get_power() interface to the exisiting perf_ops defined for the SCMI protocol. Signed-off-by: Quentin Perret Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index f4c9fc0fc755..3105055c00a7 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -91,6 +91,8 @@ struct scmi_clk_ops { * to sustained performance level mapping * @freq_get: gets the frequency for a given device using sustained frequency * to sustained performance level mapping + * @est_power_get: gets the estimated power cost for a given performance domain + * at a given frequency */ struct scmi_perf_ops { int (*limits_set)(const struct scmi_handle *handle, u32 domain, @@ -110,6 +112,8 @@ struct scmi_perf_ops { unsigned long rate, bool poll); int (*freq_get)(const struct scmi_handle *handle, u32 domain, unsigned long *rate, bool poll); + int (*est_power_get)(const struct scmi_handle *handle, u32 domain, + unsigned long *rate, unsigned long *power); }; /** -- cgit v1.2.3 From 8b69bd7d8a8927d537f134c37bcca6cbfa58e1b2 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 11 Aug 2018 18:43:38 -0700 Subject: ppp: Remove direct skb_queue_head list pointer access. Add a helper, __skb_peek(), and use it in ppp_mp_reconstruct(). Signed-off-by: David S. Miller --- include/linux/skbuff.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 17a13e4785fc..89283b77294d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1592,6 +1592,17 @@ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) return skb; } +/** + * __skb_peek - peek at the head of a non-empty &sk_buff_head + * @list_: list to peek at + * + * Like skb_peek(), but the caller knows that the list is not empty. + */ +static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) +{ + return list_->next; +} + /** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from -- cgit v1.2.3 From a8305bff685252e80b7c60f4f5e7dd2e63e38218 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 29 Jul 2018 20:42:53 -0700 Subject: net: Add and use skb_mark_not_on_list(). An SKB is not on a list if skb->next is NULL. Codify this convention into a helper function and use it where we are dequeueing an SKB and need to mark it as such. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 89283b77294d..c4c9e3f5cd9a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1339,6 +1339,11 @@ static inline void skb_zcopy_abort(struct sk_buff *skb) } } +static inline void skb_mark_not_on_list(struct sk_buff *skb) +{ + skb->next = NULL; +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head -- cgit v1.2.3 From 992cba7e276d438ac8b0a8c17b147b37c8c286f7 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 31 Jul 2018 15:27:56 -0700 Subject: net: Add and use skb_list_del_init(). It documents what is happening, and eliminates the spurious list pointer poisoning. In the long term, in order to get proper list head debugging, we might want to use the list poison value as the indicator that an SKB is a singleton and not on a list. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c4c9e3f5cd9a..e3a53ca4a9b5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1344,6 +1344,12 @@ static inline void skb_mark_not_on_list(struct sk_buff *skb) skb->next = NULL; } +static inline void skb_list_del_init(struct sk_buff *skb) +{ + __list_del_entry(&skb->list); + skb_mark_not_on_list(skb); +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head -- cgit v1.2.3 From 4e69817b106e4fb98f7af463d2f951e7b3603c12 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 6 Aug 2018 02:29:53 +0000 Subject: usb: ehci-sh: convert to SPDX identifiers This patch updates license to use SPDX-License-Identifier instead of verbose license text. Signed-off-by: Kuninori Morimoto Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/ehci-sh.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ehci-sh.h b/include/linux/platform_data/ehci-sh.h index 5c15a738e116..219bd79dabfc 100644 --- a/include/linux/platform_data/ehci-sh.h +++ b/include/linux/platform_data/ehci-sh.h @@ -1,21 +1,9 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * EHCI SuperH driver platform data * * Copyright (C) 2012 Nobuhiro Iwamatsu * Copyright (C) 2012 Renesas Solutions Corp. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #ifndef __USB_EHCI_SH_H -- cgit v1.2.3 From e7a3ff92eaf19eab14e8149758428e680c61706b Mon Sep 17 00:00:00 2001 From: Angelo Dureghello Date: Sun, 19 Aug 2018 19:27:16 +0200 Subject: dmaengine: fsl-edma: add ColdFire mcf5441x edma support This patch adds support for ColdFire mcf5441x-family edma module. The ColdFire edma module is slightly different from fsl-edma, so a new driver is added. But most of the code is common between fsl-edma and mcf-edma so it has been collected into a separate common module fsl-edma-common (patch 1/3). Signed-off-by: Angelo Dureghello Tested-by: Krzysztof Kozlowski Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-mcf-edma.h | 38 ++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/linux/platform_data/dma-mcf-edma.h (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-mcf-edma.h b/include/linux/platform_data/dma-mcf-edma.h new file mode 100644 index 000000000000..d718ccfa3421 --- /dev/null +++ b/include/linux/platform_data/dma-mcf-edma.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Freescale eDMA platform data, ColdFire SoC's family. + * + * Copyright (c) 2017 Angelo Dureghello + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_PLATFORM_DATA_MCF_EDMA_H__ +#define __LINUX_PLATFORM_DATA_MCF_EDMA_H__ + +struct dma_slave_map; + +bool mcf_edma_filter_fn(struct dma_chan *chan, void *param); + +#define MCF_EDMA_FILTER_PARAM(ch) ((void *)ch) + +/** + * struct mcf_edma_platform_data - platform specific data for eDMA engine + * + * @ver The eDMA module version. + * @dma_channels The number of eDMA channels. + */ +struct mcf_edma_platform_data { + int dma_channels; + const struct dma_slave_map *slave_map; + int slavecnt; +}; + +#endif /* __LINUX_PLATFORM_DATA_MCF_EDMA_H__ */ -- cgit v1.2.3 From 04cfcc7ab358e331b32cabde1e853a125f3f8735 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 22 Aug 2018 10:54:02 +0200 Subject: fbdev: Drop FBINFO_CAN_FORCE_OUTPUT flag This was only added for the drm's fbdev emulation support, so that it would try harder to show the Oops. Unfortunately this never really worked reliably, and in practice ended up pushing the real Oops off the screen due to plentyfull locking, sleep-while-atomic and other issues. So we removed all that support from the fbdev emulation a while back. Aside: We've also removed the kgdb support, for similar reasons. Since it's such a small patch I figured I don't split this up into the usual 3-phase removal. Acked-by: Bartlomiej Zolnierkiewicz Cc: Ben Skeggs Cc: Bartlomiej Zolnierkiewicz Cc: Greg Kroah-Hartman Cc: Hans de Goede Cc: Daniel Vetter Cc: Alexander Kapshuk Cc: Kees Cook Cc: Thierry Reding Cc: David Lechner Cc: nouveau@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180822085405.10787-1-daniel.vetter@ffwll.ch --- include/linux/fb.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 3cd375dafd0e..b1db5c5eb671 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -457,10 +457,6 @@ struct fb_tile_ops { */ #define FBINFO_BE_MATH 0x100000 -/* report to the VT layer that this fb driver can accept forced console - output like oopses */ -#define FBINFO_CAN_FORCE_OUTPUT 0x200000 - struct fb_info { atomic_t count; int node; -- cgit v1.2.3 From 8d7fc2994f4d1f431e280c9e21a139c18dc435ec Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 22 Aug 2018 10:54:03 +0200 Subject: vt: Remove vc_panic_force_write It was only used by the panic support in fbcon, which is now gone. Remove this now dead code too. Acked-by: Greg Kroah-Hartman Cc: Greg Kroah-Hartman Cc: Kees Cook Cc: Joe Perches Cc: Daniel Vetter Cc: Meng Xu Cc: Nicolas Pitre Cc: Thomas Meyer Cc: Mike Frysinger Cc: Bartlomiej Zolnierkiewicz Cc: Hans de Goede Cc: Thierry Reding Cc: David Lechner Cc: Philippe Ombredanne Cc: Thomas Gleixner Cc: Kate Stewart Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180822085405.10787-2-daniel.vetter@ffwll.ch --- include/linux/console_struct.h | 1 - include/linux/vt_kern.h | 7 ------- 2 files changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index fea64f2692a0..ab137f97ecbd 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -141,7 +141,6 @@ struct vc_data { struct uni_pagedir *vc_uni_pagedir; struct uni_pagedir **vc_uni_pagedir_loc; /* [!] Location of uni_pagedir variable for this console */ struct uni_screen *vc_uni_screen; /* unicode screen content */ - bool vc_panic_force_write; /* when oops/panic this VC can accept forced output/blanking */ /* additional information is in vt_kern.h */ }; diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 3fd07912909c..8dc77e40bc03 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -135,13 +135,6 @@ extern int do_unbind_con_driver(const struct consw *csw, int first, int last, int deflt); int vty_init(const struct file_operations *console_fops); -static inline bool vt_force_oops_output(struct vc_data *vc) -{ - if (oops_in_progress && vc->vc_panic_force_write && panic_timeout >= 0) - return true; - return false; -} - extern char vt_dont_switch; extern int default_utf8; extern int global_cursor_default; -- cgit v1.2.3 From da6c7707caf3736c1cf968606bd97c07e79625d4 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 22 Aug 2018 10:54:04 +0200 Subject: fbdev: Add FBINFO_HIDE_SMEM_START flag DRM drivers really, really, really don't want random userspace to share buffer behind it's back, bypassing the dma-buf buffer sharing machanism. For that reason we've ruthlessly rejected any IOCTL exposing the physical address of any graphics buffer. Unfortunately fbdev comes with that built-in. We could just set smem_start to 0, but that means we'd have to hand-roll our own fb_mmap implementation. For good reasons many drivers do that, but smem_start/length is still super convenient. Hence instead just stop the leak in the ioctl, to keep fb mmap working as-is. A second patch will set this flag for all drm drivers. Acked-by: Bartlomiej Zolnierkiewicz Cc: Bartlomiej Zolnierkiewicz Cc: Kees Cook Cc: Daniel Vetter Cc: linux-fbdev@vger.kernel.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180822085405.10787-3-daniel.vetter@ffwll.ch --- include/linux/fb.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index b1db5c5eb671..a3cab6dc9b44 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -456,6 +456,13 @@ struct fb_tile_ops { * and host endianness. Drivers should not use this flag. */ #define FBINFO_BE_MATH 0x100000 +/* + * Hide smem_start in the FBIOGET_FSCREENINFO IOCTL. This is used by modern DRM + * drivers to stop userspace from trying to share buffers behind the kernel's + * back. Instead dma-buf based buffer sharing should be used. + */ +#define FBINFO_HIDE_SMEM_START 0x200000 + struct fb_info { atomic_t count; -- cgit v1.2.3 From 56df612afb606dcefba8ab38ab32e052218b6050 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Sep 2018 14:41:28 +0200 Subject: spi: davinci: Remove chip select GPIO pdata The DaVinci SPI can use either: - Internal chip selects (inside the SPI host) - External chip selects (using GPIO) - External chip selects passed in pdata The last way of passing external chip selects through platform data is not used in the kernel. Delete it to make the code simpler when refactoring GPIO. Cc: Sekhar Nori Cc: Kevin Hilman Cc: Michele Dionisio Cc: Frode Isaksen Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- include/linux/platform_data/spi-davinci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/spi-davinci.h b/include/linux/platform_data/spi-davinci.h index f4edcb03c40c..0638fb6353bc 100644 --- a/include/linux/platform_data/spi-davinci.h +++ b/include/linux/platform_data/spi-davinci.h @@ -36,9 +36,6 @@ enum { * @num_chipselect: number of chipselects supported by this SPI master * @intr_line: interrupt line used to connect the SPI IP to the ARM interrupt * controller withn the SoC. Possible values are 0 and 1. - * @chip_sel: list of GPIOs which can act as chip-selects for the SPI. - * SPI_INTERN_CS denotes internal SPI chip-select. Not necessary - * to populate if all chip-selects are internal. * @cshold_bug: set this to true if the SPI controller on your chip requires * a write to CSHOLD bit in between transfers (like in DM355). * @dma_event_q: DMA event queue to use if SPI_IO_TYPE_DMA is used for any @@ -48,7 +45,6 @@ struct davinci_spi_platform_data { u8 version; u8 num_chipselect; u8 intr_line; - u8 *chip_sel; u8 prescaler_limit; bool cshold_bug; enum dma_event_q dma_event_q; -- cgit v1.2.3 From 01c5f85aebaaddfd7e6051fb2ec80c1d4b463554 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Sep 2018 10:59:53 -0600 Subject: blk-cgroup: increase number of supported policies After merging the iolatency policy, we potentially now have 4 policies being registered, but only support 3. This causes one of them to fail loading. Takashi reports that BFQ no longer works for him, because it fails to load due to policy registration failure. Bump to 5 policies, and also add a warning for when we have exceeded the global amount. If we have to touch this again, we should switch to a dynamic scheme instead. Reported-by: Takashi Iwai Reviewed-by: Jeff Moyer Tested-by: Takashi Iwai Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d6869e0e2b64..6980014357d4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -54,7 +54,7 @@ struct blk_stat_callback; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 3 +#define BLKCG_MAX_POLS 5 typedef void (rq_end_io_fn)(struct request *, blk_status_t); -- cgit v1.2.3 From 961366a01904d460066d65a609c3c2e3051c7903 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 19 Jul 2018 21:31:13 -0500 Subject: signal: Remove the siginfo paramater from kernel_dqueue_signal None of the callers use the it so remove it. Reviewed-by: Thomas Gleixner Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 1be35729c2c5..9b6968cbde14 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -272,14 +272,14 @@ extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); -static inline int kernel_dequeue_signal(siginfo_t *info) +static inline int kernel_dequeue_signal(void) { struct task_struct *tsk = current; siginfo_t __info; int ret; spin_lock_irq(&tsk->sighand->siglock); - ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info); + ret = dequeue_signal(tsk, &tsk->blocked, &__info); spin_unlock_irq(&tsk->sighand->siglock); return ret; -- cgit v1.2.3 From 4ff4c31a6e85f4c49fbeebeaa28018d002884b5a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 3 Sep 2018 10:39:04 +0200 Subject: signal: Remove SEND_SIG_FORCED There are no more users of SEND_SIG_FORCED so it may be safely removed. Remove the definition of SEND_SIG_FORCED, it's use in is_si_special, it's use in TP_STORE_SIGINFO, and it's use in __send_signal as without any users the uses of SEND_SIG_FORCED are now unncessary. This makes the code simpler, easier to understand and use. Users of signal sending functions now no longer need to ask themselves do I need to use SEND_SIG_FORCED. Reviewed-by: Thomas Gleixner Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 9b6968cbde14..9e07f3521549 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -477,7 +477,6 @@ static inline int kill_cad_pid(int sig, int priv) /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct siginfo *) 0) #define SEND_SIG_PRIV ((struct siginfo *) 1) -#define SEND_SIG_FORCED ((struct siginfo *) 2) /* * True if we are on the alternate signal stack. -- cgit v1.2.3 From bfc456060d0cbcf6902a436d358b60cb1534668c Mon Sep 17 00:00:00 2001 From: Dennis Dalessandro Date: Fri, 31 Aug 2018 10:34:14 -0700 Subject: IB/hfi1,PCI: Allow bus reset while probing Calling into the new API to reset the secondary bus results in a deadlock. This occurs because the device/bus is already locked at probe time. Reverting back to the old behavior while the API is improved. Link: https://bugzilla.kernel.org/show_bug.cgi?id=200985 Fixes: c6a44ba950d1 ("PCI: Rename pci_try_reset_bus() to pci_reset_bus()") Fixes: 409888e0966e ("IB/hfi1: Use pci_try_reset_bus() for initiating PCI Secondary Bus Reset") Signed-off-by: Dennis Dalessandro Signed-off-by: Bjorn Helgaas Reviewed-by: Michael J. Ruhl Cc: Sinan Kaya --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index e72ca8dd6241..6925828f9f25 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1235,6 +1235,9 @@ void pci_bus_remove_resources(struct pci_bus *bus); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources); +/* Temporary until new and working PCI SBR API in place */ +int pci_bridge_secondary_bus_reset(struct pci_dev *dev); + #define pci_bus_for_each_resource(bus, res, i) \ for (i = 0; \ (res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \ -- cgit v1.2.3 From d765edbb301c0e196015a59b17420558088ea33f Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 10 Aug 2018 23:06:08 +0000 Subject: vmbus: add driver_override support Add support for overriding the default driver for a VMBus device in the same way that it can be done for PCI devices. This patch adds the /sys/bus/vmbus/devices/.../driver_override file and the logic for matching. This is used by driverctl tool to do driver override. https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgitlab.com%2Fdriverctl%2Fdriverctl&data=02%7C01%7Ckys%40microsoft.com%7C42e803feb2c544ef6ea908d5fd538878%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636693457619960040&sdata=kEyYHRIjNZCk%2B37moCSqbrZL426YccNQrsWpENcrZdw%3D&reserved=0 Signed-off-by: Stephen Hemminger Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index efda23cf32c7..2c3798bcb01c 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1125,6 +1125,7 @@ struct hv_device { u16 device_id; struct device device; + char *driver_override; /* Driver name to force a match */ struct vmbus_channel *channel; struct kset *channels_kset; -- cgit v1.2.3 From cdc3d7f346476b4a4d1c4738b7dcdda4b3d5d870 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Sun, 5 Aug 2018 23:18:05 -0400 Subject: media: drm: shmobile: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Reviewed-by: Simon Horman Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/shmob_drm.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/shmob_drm.h b/include/linux/platform_data/shmob_drm.h index ee495d707f17..fe815d7d9f58 100644 --- a/include/linux/platform_data/shmob_drm.h +++ b/include/linux/platform_data/shmob_drm.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm.h -- SH Mobile DRM driver * * Copyright (C) 2012 Renesas Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __SHMOB_DRM_H__ -- cgit v1.2.3 From 7c1a000d466235c875a989971cfda344e6bb1166 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 12 Sep 2018 09:16:07 +0800 Subject: f2fs: add SPDX license identifiers Remove the verbose license text from f2fs files and replace them with SPDX tags. This does not change the license of any of the code. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index f70f8ac9c4f4..1d4b196291d6 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /** * include/linux/f2fs_fs.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _LINUX_F2FS_FS_H #define _LINUX_F2FS_FS_H -- cgit v1.2.3 From dfb06cba8c73c0704710b2e3fbe2c35ac66a01b4 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 5 Sep 2018 13:31:40 -0700 Subject: uaccess: Fix is_source param for check_copy_size() in copy_to_iter_mcsafe() copy_to_iter_mcsafe() is passing in the is_source parameter as "false" to check_copy_size(). This is different than what copy_to_iter() does. Also, the addr parameter passed to check_copy_size() is the source so therefore we should be passing in "true" instead. Fixes: 8780356ef630 ("x86/asm/memcpy_mcsafe: Define copy_to_iter_mcsafe()") Cc: Reported-by: Fan Du Signed-off-by: Dave Jiang Reviewed-by: Vishal Verma Reported-by: Wenwei Tao Signed-off-by: Dan Williams --- include/linux/uio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 409c845d4cd3..422b1c01ee0d 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -172,7 +172,7 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) static __always_inline __must_check size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) { - if (unlikely(!check_copy_size(addr, bytes, false))) + if (unlikely(!check_copy_size(addr, bytes, true))) return 0; else return _copy_to_iter_mcsafe(addr, bytes, i); -- cgit v1.2.3 From 41124fa64d4b298b82266b7ddbefc43540b77b44 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:14 +0200 Subject: net: ethernet: Add helper to remove a supported link mode Some MAC hardware cannot support a subset of link modes. e.g. often 1Gbps Full duplex is supported, but Half duplex is not. Add a helper to remove such a link mode. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index cd6f637cbbfb..9c4c3eca8cf2 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1049,6 +1049,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); +void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From af8d9bb2f2f405ad541794b46f9d7bc70f13e5cb Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:15 +0200 Subject: net: ethernet: Add helper for MACs which support asym pause Rather than have the MAC drivers manipulate phydev members to indicate they support Asym Pause, add a helper function. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9c4c3eca8cf2..e2db819807c1 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1050,6 +1050,7 @@ int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); +void phy_support_asym_pause(struct phy_device *phydev); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From c306ad36184fb7d0bd53f45441f45c1810e88a53 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:16 +0200 Subject: net: ethernet: Add helper for MACs which support pause Rather than have the MAC drivers manipulate phydev members, add a helper function for MACs supporting Pause, but not Asym Pause. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index e2db819807c1..bc5d6c3f1388 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1050,6 +1050,7 @@ int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); +void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, -- cgit v1.2.3 From 70814e819c1139e5e7faacb3700eab5eac559272 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:17 +0200 Subject: net: ethernet: Add helper for set_pauseparam for Asym Pause ethtool can be used to enable/disable pause. Add a helper to configure the PHY when asym pause is supported. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index bc5d6c3f1388..e4062ba7472f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1052,6 +1052,7 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); +void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From 0c122405d4c3ec638ba00865c872ec5a3ed1a6c0 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:18 +0200 Subject: net: ethernet: Add helper for set_pauseparam for Pause ethtool can be used to enable/disable pause. Add a helper to configure the PHY when Pause is supported. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index e4062ba7472f..8521391ebb20 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1052,6 +1052,8 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); +void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, + bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, -- cgit v1.2.3 From 22b7d29926b577ff4f480611380d03268545b787 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:19 +0200 Subject: net: ethernet: Add helper to determine if pause configuration is supported Rather than have MAC drivers open code the test, add a helper in phylib. This will help when we change the type of phydev->supported. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 8521391ebb20..192a1fa0c73b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1055,6 +1055,8 @@ void phy_support_asym_pause(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); +bool phy_validate_pause(struct phy_device *phydev, + struct ethtool_pauseparam *pp); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From 0789724f86a59fa7078d67dfeb1ee4a15ae3c693 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Thu, 26 Jul 2018 15:59:16 +0200 Subject: firmware: meson_sm: Add serial number sysfs entry The Amlogic Meson SoC Secure Monitor implements a call to retrieve an unique SoC ID starting from the GX Family and all new families. The serial number is simply exposed as a sysfs entry under the firmware sysfs directory. Signed-off-by: Neil Armstrong Signed-off-by: Kevin Hilman --- include/linux/firmware/meson/meson_sm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware/meson/meson_sm.h b/include/linux/firmware/meson/meson_sm.h index 37a5eaea69dd..f98c20dd266e 100644 --- a/include/linux/firmware/meson/meson_sm.h +++ b/include/linux/firmware/meson/meson_sm.h @@ -17,6 +17,7 @@ enum { SM_EFUSE_READ, SM_EFUSE_WRITE, SM_EFUSE_USER_MAX, + SM_GET_CHIP_ID, }; struct meson_sm_firmware; -- cgit v1.2.3 From d4983983d98710e4927fdb8de8e987c303b3fba3 Mon Sep 17 00:00:00 2001 From: Maxime Jourdan Date: Thu, 23 Aug 2018 13:49:53 +0200 Subject: soc: amlogic: add meson-canvas driver Amlogic SoCs have a repository of 256 canvas which they use to describe pixel buffers. They contain metadata like width, height, block mode, endianness [..] Many IPs within those SoCs like vdec/vpu rely on those canvas to read/write pixels. Reviewed-by: Jerome Brunet Tested-by: Neil Armstrong Signed-off-by: Maxime Jourdan Signed-off-by: Kevin Hilman --- include/linux/soc/amlogic/meson-canvas.h | 65 ++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) create mode 100644 include/linux/soc/amlogic/meson-canvas.h (limited to 'include/linux') diff --git a/include/linux/soc/amlogic/meson-canvas.h b/include/linux/soc/amlogic/meson-canvas.h new file mode 100644 index 000000000000..b4dde2fbeb3f --- /dev/null +++ b/include/linux/soc/amlogic/meson-canvas.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2018 BayLibre, SAS + */ +#ifndef __SOC_MESON_CANVAS_H +#define __SOC_MESON_CANVAS_H + +#include + +#define MESON_CANVAS_WRAP_NONE 0x00 +#define MESON_CANVAS_WRAP_X 0x01 +#define MESON_CANVAS_WRAP_Y 0x02 + +#define MESON_CANVAS_BLKMODE_LINEAR 0x00 +#define MESON_CANVAS_BLKMODE_32x32 0x01 +#define MESON_CANVAS_BLKMODE_64x64 0x02 + +#define MESON_CANVAS_ENDIAN_SWAP16 0x1 +#define MESON_CANVAS_ENDIAN_SWAP32 0x3 +#define MESON_CANVAS_ENDIAN_SWAP64 0x7 +#define MESON_CANVAS_ENDIAN_SWAP128 0xf + +struct meson_canvas; + +/** + * meson_canvas_get() - get a canvas provider instance + * + * @dev: consumer device pointer + */ +struct meson_canvas *meson_canvas_get(struct device *dev); + +/** + * meson_canvas_alloc() - take ownership of a canvas + * + * @canvas: canvas provider instance retrieved from meson_canvas_get() + * @canvas_index: will be filled with the canvas ID + */ +int meson_canvas_alloc(struct meson_canvas *canvas, u8 *canvas_index); + +/** + * meson_canvas_free() - remove ownership from a canvas + * + * @canvas: canvas provider instance retrieved from meson_canvas_get() + * @canvas_index: canvas ID that was obtained via meson_canvas_alloc() + */ +int meson_canvas_free(struct meson_canvas *canvas, u8 canvas_index); + +/** + * meson_canvas_config() - configure a canvas + * + * @canvas: canvas provider instance retrieved from meson_canvas_get() + * @canvas_index: canvas ID that was obtained via meson_canvas_alloc() + * @addr: physical address to the pixel buffer + * @stride: width of the buffer + * @height: height of the buffer + * @wrap: undocumented + * @blkmode: block mode (linear, 32x32, 64x64) + * @endian: byte swapping (swap16, swap32, swap64, swap128) + */ +int meson_canvas_config(struct meson_canvas *canvas, u8 canvas_index, + u32 addr, u32 stride, u32 height, + unsigned int wrap, unsigned int blkmode, + unsigned int endian); + +#endif -- cgit v1.2.3 From b9762bebc6332b40c33e03dea03e30fa12d9e3ed Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Wed, 5 Sep 2018 23:50:05 +0200 Subject: gpiolib: Pass bitmaps, not integer arrays, to get/set array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Most users of get/set array functions iterate consecutive bits of data, usually a single integer, while processing array of results obtained from, or building an array of values to be passed to those functions. Save time wasted on those iterations by changing the functions' API to accept bitmaps. All current users are updated as well. More benefits from the change are expected as soon as planned support for accepting/passing those bitmaps directly from/to respective GPIO chip callbacks if applicable is implemented. Cc: Jonathan Corbet Cc: Miguel Ojeda Sandonis Cc: Sebastien Bourdelin Cc: Lukas Wunner Cc: Peter Korsgaard Cc: Peter Rosin Cc: Andrew Lunn Cc: Florian Fainelli Cc: "David S. Miller" Cc: Rojhalat Ibrahim Cc: Dominik Brodowski Cc: Russell King Cc: Kishon Vijay Abraham I Cc: Tony Lindgren Cc: Lars-Peter Clausen Cc: Michael Hennerich Cc: Jonathan Cameron Cc: Hartmut Knaack Cc: Peter Meerwald-Stadler Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: Yegor Yefremov Cc: Uwe Kleine-König Signed-off-by: Janusz Krzysztofik Acked-by: Ulf Hansson Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 34 ++++++++++++++++++---------------- 1 file changed, 18 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 21ddbe440030..2b0389f0bec4 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -104,36 +104,38 @@ int gpiod_direction_output_raw(struct gpio_desc *desc, int value); /* Value get/set from non-sleeping context */ int gpiod_get_value(const struct gpio_desc *desc); int gpiod_get_array_value(unsigned int array_size, - struct gpio_desc **desc_array, int *value_array); + struct gpio_desc **desc_array, + unsigned long *value_bitmap); void gpiod_set_value(struct gpio_desc *desc, int value); void gpiod_set_array_value(unsigned int array_size, - struct gpio_desc **desc_array, int *value_array); + struct gpio_desc **desc_array, + unsigned long *value_bitmap); int gpiod_get_raw_value(const struct gpio_desc *desc); int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); void gpiod_set_raw_value(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); /* Value get/set from sleeping context */ int gpiod_get_value_cansleep(const struct gpio_desc *desc); int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); void gpiod_set_value_cansleep(struct gpio_desc *desc, int value); void gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc); int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce); int gpiod_set_transitory(struct gpio_desc *desc, bool transitory); @@ -330,7 +332,7 @@ static inline int gpiod_get_value(const struct gpio_desc *desc) } static inline int gpiod_get_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -343,7 +345,7 @@ static inline void gpiod_set_value(struct gpio_desc *desc, int value) } static inline void gpiod_set_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -356,7 +358,7 @@ static inline int gpiod_get_raw_value(const struct gpio_desc *desc) } static inline int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -369,7 +371,7 @@ static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) } static inline int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -384,7 +386,7 @@ static inline int gpiod_get_value_cansleep(const struct gpio_desc *desc) } static inline int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -397,7 +399,7 @@ static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value) } static inline void gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -410,7 +412,7 @@ static inline int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc) } static inline int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -424,7 +426,7 @@ static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, } static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); -- cgit v1.2.3 From bf9346f5d47b4506aafbc384dfb5796b0adc3f8d Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Wed, 5 Sep 2018 23:50:06 +0200 Subject: gpiolib: Identify arrays matching GPIO hardware Certain GPIO array lookup results may map directly to GPIO pins of a single GPIO chip in hardware order. If that condition is recognized and handled efficiently, significant performance gain of get/set array functions may be possible. While processing a request for an array of GPIO descriptors, identify those which represent corresponding pins of a single GPIO chip. Skip over pins which require open source or open drain special processing. Moreover, identify pins which require inversion. Pass a pointer to that information with the array to the caller so it can benefit from enhanced performance as soon as get/set array functions can accept and make efficient use of it. Cc: Jonathan Corbet Signed-off-by: Janusz Krzysztofik Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 2b0389f0bec4..0ffd71c0a77c 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -17,11 +17,20 @@ struct device; */ struct gpio_desc; +/** + * Opaque descriptor for a structure of GPIO array attributes. This structure + * is attached to struct gpiod_descs obtained from gpiod_get_array() and can be + * passed back to get/set array functions in order to activate fast processing + * path if applicable. + */ +struct gpio_array; + /** * Struct containing an array of descriptors that can be obtained using * gpiod_get_array(). */ struct gpio_descs { + struct gpio_array *info; unsigned int ndescs; struct gpio_desc *desc[]; }; -- cgit v1.2.3 From 77588c14ac868caece82fddbfae7de03b2cec941 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Wed, 5 Sep 2018 23:50:07 +0200 Subject: gpiolib: Pass array info to get/set array functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to make use of array info obtained from gpiod_get_array() and speed up processing of arrays matching single GPIO chip layout, that information must be passed to get/set array functions. Extend the functions' API with that additional parameter and update all users. Pass NULL if a user builds an array itself from single GPIOs. Cc: Jonathan Corbet Cc: Miguel Ojeda Sandonis Cc: Geert Uytterhoeven Cc: Sebastien Bourdelin Cc: Lukas Wunner Cc: Peter Korsgaard Cc: Peter Rosin Cc: Andrew Lunn Cc: Florian Fainelli Cc: "David S. Miller" Cc: Rojhalat Ibrahim Cc: Dominik Brodowski Cc: Russell King Cc: Kishon Vijay Abraham I Cc: Tony Lindgren Cc: Lars-Peter Clausen Cc: Michael Hennerich Cc: Jonathan Cameron Cc: Hartmut Knaack Cc: Peter Meerwald-Stadler Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: Yegor Yefremov Cc: Uwe Kleine-König Signed-off-by: Janusz Krzysztofik Acked-by: Ulf Hansson Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 0ffd71c0a77c..d7fbe30ece84 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -114,36 +114,44 @@ int gpiod_direction_output_raw(struct gpio_desc *desc, int value); int gpiod_get_value(const struct gpio_desc *desc); int gpiod_get_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_value(struct gpio_desc *desc, int value); void gpiod_set_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); int gpiod_get_raw_value(const struct gpio_desc *desc); int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_raw_value(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); /* Value get/set from sleeping context */ int gpiod_get_value_cansleep(const struct gpio_desc *desc); int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_value_cansleep(struct gpio_desc *desc, int value); void gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc); int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce); @@ -341,6 +349,7 @@ static inline int gpiod_get_value(const struct gpio_desc *desc) } static inline int gpiod_get_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -354,6 +363,7 @@ static inline void gpiod_set_value(struct gpio_desc *desc, int value) } static inline void gpiod_set_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -367,6 +377,7 @@ static inline int gpiod_get_raw_value(const struct gpio_desc *desc) } static inline int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -380,6 +391,7 @@ static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) } static inline int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -395,6 +407,7 @@ static inline int gpiod_get_value_cansleep(const struct gpio_desc *desc) } static inline int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -408,6 +421,7 @@ static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value) } static inline void gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -421,6 +435,7 @@ static inline int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc) } static inline int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -435,6 +450,7 @@ static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, } static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ -- cgit v1.2.3 From 1e479c619b2ac983fdea1a8212c7b822b5098da0 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 12 Sep 2018 22:22:45 +0200 Subject: rtc: unexport non devm managed registration Ensure the non managed version of the un/registration functions is not used anymore. No driver is using it anymore and they should not be necessary. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 6aedc30003e7..faf00a1472d4 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -167,17 +167,12 @@ struct rtc_device { #define RTC_TIMESTAMP_BEGIN_2000 946684800LL /* 2000-01-01 00:00:00 */ #define RTC_TIMESTAMP_END_2099 4102444799LL /* 2099-12-31 23:59:59 */ -extern struct rtc_device *rtc_device_register(const char *name, - struct device *dev, - const struct rtc_class_ops *ops, - struct module *owner); extern struct rtc_device *devm_rtc_device_register(struct device *dev, const char *name, const struct rtc_class_ops *ops, struct module *owner); struct rtc_device *devm_rtc_allocate_device(struct device *dev); int __rtc_register_device(struct module *owner, struct rtc_device *rtc); -extern void rtc_device_unregister(struct rtc_device *rtc); extern void devm_rtc_device_unregister(struct device *dev, struct rtc_device *rtc); -- cgit v1.2.3 From 15033f0457dca569b284bef0c8d3ad55fb37eacb Mon Sep 17 00:00:00 2001 From: Andre Naujoks Date: Mon, 10 Sep 2018 10:27:15 +0200 Subject: ipv6: Add sockopt IPV6_MULTICAST_ALL analogue to IP_MULTICAST_ALL The socket option will be enabled by default to ensure current behaviour is not changed. This is the same for the IPv4 version. A socket bound to in6addr_any and a specific port will receive all traffic on that port. Analogue to IP_MULTICAST_ALL, disable this behaviour, if one or more multicast groups were joined (using said socket) and only pass on multicast traffic from groups, which were explicitly joined via this socket. Without this option disabled a socket (system even) joined to multiple multicast groups is very hard to get right. Filtering by destination address has to take place in user space to avoid receiving multicast traffic from other multicast groups, which might have traffic on the same port. The extension of the IP_MULTICAST_ALL socketoption to just apply to ipv6, too, is not done to avoid changing the behaviour of current applications. Signed-off-by: Andre Naujoks Acked-By: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 8415bf1a9776..495e834c1367 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -274,7 +274,8 @@ struct ipv6_pinfo { */ dontfrag:1, autoflowlabel:1, - autoflowlabel_set:1; + autoflowlabel_set:1, + mc_all:1; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; -- cgit v1.2.3 From 37a3a98ef601f89100e3bb657fb0e190b857028c Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 10 Sep 2018 16:20:25 +0200 Subject: ALSA: hda - Enable runtime PM only for discrete GPU The recent change of vga_switcheroo allowed the runtime PM for HD-audio on AMD GPUs, but this also resulted in a regression. When the HD-audio controller driver gets runtime-suspended, HD-audio link is turned off, and the hotplug notification is ignored. This leads to the inconsistent audio state (the connection isn't notified and ELD is ignored). The best fix would be to implement the proper ELD notification via the audio component, but it's still not ready. As a quick workaround, this patch adds the check of runtime_idle and allows the runtime suspend only when the vga_switcheroo is bound with discrete GPU. That is, a system with a single GPU and APU would be again without runtime PM to keep the HD-audio link for the hotplug notification and ELD read out. Also, the codec->auto_runtime_pm flag is set only for the discrete GPU at the time GPU gets bound via vga_switcheroo (i.e. only dGPU is forcibly runtime-PM enabled), so that APU can still get the ELD notification. For identifying which GPU is bound, a new vga_switcheroo client callback, gpu_bound, is implemented. The vga_switcheroo simply calls this when GPU is bound, and tells whether it's dGPU or APU. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=200945 Fixes: 07f4f97d7b4b ("vga_switcheroo: Use device link for HDA controller") Reported-by: Jian-Hong Pan Tested-by: Jian-Hong Pan Acked-by: Lukas Wunner Signed-off-by: Takashi Iwai --- include/linux/vga_switcheroo.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index a34539b7f750..7e6ac0114d55 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -133,15 +133,18 @@ struct vga_switcheroo_handler { * @can_switch: check if the device is in a position to switch now. * Mandatory. The client should return false if a user space process * has one of its device files open + * @gpu_bound: notify the client id to audio client when the GPU is bound. * * Client callbacks. A client can be either a GPU or an audio device on a GPU. * The @set_gpu_state and @can_switch methods are mandatory, @reprobe may be * set to NULL. For audio clients, the @reprobe member is bogus. + * OTOH, @gpu_bound is only for audio clients, and not used for GPU clients. */ struct vga_switcheroo_client_ops { void (*set_gpu_state)(struct pci_dev *dev, enum vga_switcheroo_state); void (*reprobe)(struct pci_dev *dev); bool (*can_switch)(struct pci_dev *dev); + void (*gpu_bound)(struct pci_dev *dev, enum vga_switcheroo_client_id); }; #if defined(CONFIG_VGA_SWITCHEROO) -- cgit v1.2.3 From fe8dd45bb7556246c6b76277b1ba4296c91c2505 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 12 Sep 2018 11:17:06 +0800 Subject: tun: switch to new type of msg_control This patch introduces to a new tun/tap specific msg_control: #define TUN_MSG_UBUF 1 #define TUN_MSG_PTR 2 struct tun_msg_ctl { int type; void *ptr; }; This allows us to pass different kinds of msg_control through sendmsg(). The first supported type is ubuf (TUN_MSG_UBUF) which will be used by the existed vhost_net zerocopy code. The second is XDP buff, which allows vhost_net to pass XDP buff to TUN. This could be used to implement accepting an array of XDP buffs from vhost_net in the following patches. Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/if_tun.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 3d2996dc7d85..12e3eebf0ce6 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -16,9 +16,23 @@ #define __IF_TUN_H #include +#include #define TUN_XDP_FLAG 0x1UL +#define TUN_MSG_UBUF 1 +#define TUN_MSG_PTR 2 +struct tun_msg_ctl { + unsigned short type; + unsigned short num; + void *ptr; +}; + +struct tun_xdp_hdr { + int buflen; + struct virtio_net_hdr gso; +}; + #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); -- cgit v1.2.3 From 7f9c136216c745099f36a4e0c3b2e63eedeb442f Mon Sep 17 00:00:00 2001 From: Venkata Narendra Kumar Gutta Date: Wed, 12 Sep 2018 11:06:32 -0700 Subject: soc: qcom: Add broadcast base for Last Level Cache Controller (LLCC) Currently, broadcast base is set to end of the LLCC banks, which may not be correct always. As the number of banks may vary for each chipset and the broadcast base could be at a different address as well. This info depends on the chipset, so get the broadcast base info from the device tree (DT). Add broadcast base in LLCC driver and use this for broadcast writes. Signed-off-by: Venkata Narendra Kumar Gutta Reviewed-by: Evan Green Signed-off-by: Andy Gross --- include/linux/soc/qcom/llcc-qcom.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 7e3b9c605ab2..c681e795b587 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -70,22 +70,22 @@ struct llcc_slice_config { /** * llcc_drv_data - Data associated with the llcc driver * @regmap: regmap associated with the llcc device + * @bcast_regmap: regmap associated with llcc broadcast offset * @cfg: pointer to the data structure for slice configuration * @lock: mutex associated with each slice * @cfg_size: size of the config data table * @max_slices: max slices as read from device tree - * @bcast_off: Offset of the broadcast bank * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids * @offsets: Pointer to the bank offsets array */ struct llcc_drv_data { struct regmap *regmap; + struct regmap *bcast_regmap; const struct llcc_slice_config *cfg; struct mutex lock; u32 cfg_size; u32 max_slices; - u32 bcast_off; u32 num_banks; unsigned long *bitmap; u32 *offsets; -- cgit v1.2.3 From c081f3060fab316fcf103967a24e502d58488849 Mon Sep 17 00:00:00 2001 From: Venkata Narendra Kumar Gutta Date: Wed, 12 Sep 2018 11:06:33 -0700 Subject: soc: qcom: Add support to register LLCC EDAC driver Cache error reporting controller detects and reports single and double bit errors on Last Level Cache Controller (LLCC) cache. Add required support to register LLCC EDAC driver as platform driver, from LLCC driver. Signed-off-by: Venkata Narendra Kumar Gutta Reviewed-by: Evan Green Signed-off-by: Andy Gross --- include/linux/soc/qcom/llcc-qcom.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index c681e795b587..2e4b34d2617e 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -78,6 +78,7 @@ struct llcc_slice_config { * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids * @offsets: Pointer to the bank offsets array + * @ecc_irq: interrupt for llcc cache error detection and reporting */ struct llcc_drv_data { struct regmap *regmap; @@ -89,6 +90,7 @@ struct llcc_drv_data { u32 num_banks; unsigned long *bitmap; u32 *offsets; + int ecc_irq; }; #if IS_ENABLED(CONFIG_QCOM_LLCC) -- cgit v1.2.3 From 27450653f1db0b9d5b5048a246c850c52ee4aa61 Mon Sep 17 00:00:00 2001 From: Channagoud Kadabi Date: Wed, 12 Sep 2018 11:06:34 -0700 Subject: drivers: edac: Add EDAC driver support for QCOM SoCs Add error reporting driver for Single Bit Errors (SBEs) and Double Bit Errors (DBEs). As of now, this driver supports error reporting for Last Level Cache Controller (LLCC) of Tag RAM and Data RAM. Interrupts are triggered when the errors happen in the cache, the driver handles those interrupts and dumps the syndrome registers. Signed-off-by: Channagoud Kadabi Signed-off-by: Venkata Narendra Kumar Gutta Co-developed-by: Venkata Narendra Kumar Gutta Acked-by: Borislav Petkov Signed-off-by: Andy Gross --- include/linux/soc/qcom/llcc-qcom.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 2e4b34d2617e..69c285b1c990 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -93,6 +93,30 @@ struct llcc_drv_data { int ecc_irq; }; +/** + * llcc_edac_reg_data - llcc edac registers data for each error type + * @name: Name of the error + * @synd_reg: Syndrome register address + * @count_status_reg: Status register address to read the error count + * @ways_status_reg: Status register address to read the error ways + * @reg_cnt: Number of registers + * @count_mask: Mask value to get the error count + * @ways_mask: Mask value to get the error ways + * @count_shift: Shift value to get the error count + * @ways_shift: Shift value to get the error ways + */ +struct llcc_edac_reg_data { + char *name; + u64 synd_reg; + u64 count_status_reg; + u64 ways_status_reg; + u32 reg_cnt; + u32 count_mask; + u32 ways_mask; + u8 count_shift; + u8 ways_shift; +}; + #if IS_ENABLED(CONFIG_QCOM_LLCC) /** * llcc_slice_getd - get llcc slice descriptor -- cgit v1.2.3 From f4926ef76e23e291fcd38bd107c0a9bb8e2db505 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 18 May 2018 15:47:50 -0700 Subject: soc: qcom: geni: Make version macros simpler This macro doesn't work, because it hides a local variable inside of the macro to hold the version and that variable name is called 'ver' and 'version' sometimes. Let's change this to be more explicit. Introduce three macros for the major, minor, and step of the version, and require callers to pass the version in to get the part of the version out. This way we don't hide local variables inside macros and things are less evil overall. Cc: Karthikeyan Ramasubramanian Cc: Sagar Dharia Cc: Girish Mahadevan Signed-off-by: Stephen Boyd Reviewed-by: Douglas Anderson Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/qcom-geni-se.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 5d6144977828..3bcd67fd5548 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -225,19 +225,14 @@ struct geni_se { #define HW_VER_MINOR_SHFT 16 #define HW_VER_STEP_MASK GENMASK(15, 0) +#define GENI_SE_VERSION_MAJOR(ver) ((ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT) +#define GENI_SE_VERSION_MINOR(ver) ((ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT) +#define GENI_SE_VERSION_STEP(ver) (ver & HW_VER_STEP_MASK) + #if IS_ENABLED(CONFIG_QCOM_GENI_SE) u32 geni_se_get_qup_hw_version(struct geni_se *se); -#define geni_se_get_wrapper_version(se, major, minor, step) do { \ - u32 ver; \ -\ - ver = geni_se_get_qup_hw_version(se); \ - major = (ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT; \ - minor = (ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT; \ - step = version & HW_VER_STEP_MASK; \ -} while (0) - /** * geni_se_read_proto() - Read the protocol configured for a serial engine * @se: Pointer to the concerned serial engine. -- cgit v1.2.3 From 7a9cdebdcc17e426fb5287e4a82db1dfe86339b2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 12 Sep 2018 23:57:48 -1000 Subject: mm: get rid of vmacache_flush_all() entirely Jann Horn points out that the vmacache_flush_all() function is not only potentially expensive, it's buggy too. It also happens to be entirely unnecessary, because the sequence number overflow case can be avoided by simply making the sequence number be 64-bit. That doesn't even grow the data structures in question, because the other adjacent fields are already 64-bit. So simplify the whole thing by just making the sequence number overflow case go away entirely, which gets rid of all the complications and makes the code faster too. Win-win. [ Oleg Nesterov points out that the VMACACHE_FULL_FLUSHES statistics also just goes away entirely with this ] Reported-by: Jann Horn Suggested-by: Will Deacon Acked-by: Davidlohr Bueso Cc: Oleg Nesterov Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- include/linux/mm_types_task.h | 2 +- include/linux/vm_event_item.h | 1 - include/linux/vmacache.h | 5 ----- 4 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index cd2bc939efd0..5ed8f6292a53 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -341,7 +341,7 @@ struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - u32 vmacache_seqnum; /* per-thread vmacache */ + u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 5fe87687664c..d7016dcb245e 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -32,7 +32,7 @@ #define VMACACHE_MASK (VMACACHE_SIZE - 1) struct vmacache { - u32 seqnum; + u64 seqnum; struct vm_area_struct *vmas[VMACACHE_SIZE]; }; diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 5c7f010676a7..47a3441cf4c4 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -105,7 +105,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_DEBUG_VM_VMACACHE VMACACHE_FIND_CALLS, VMACACHE_FIND_HITS, - VMACACHE_FULL_FLUSHES, #endif #ifdef CONFIG_SWAP SWAP_RA, diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h index 3e9a963edd6a..6fce268a4588 100644 --- a/include/linux/vmacache.h +++ b/include/linux/vmacache.h @@ -10,7 +10,6 @@ static inline void vmacache_flush(struct task_struct *tsk) memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); } -extern void vmacache_flush_all(struct mm_struct *mm); extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr); @@ -24,10 +23,6 @@ extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, static inline void vmacache_invalidate(struct mm_struct *mm) { mm->vmacache_seqnum++; - - /* deal with overflows */ - if (unlikely(mm->vmacache_seqnum == 0)) - vmacache_flush_all(mm); } #endif /* __LINUX_VMACACHE_H */ -- cgit v1.2.3 From 59104f239b9ed6cf3986e4228173ff2f4c95039e Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 26 Jul 2018 02:37:49 +0000 Subject: drm: shmobile: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Acked-by: Laurent Pinchart Reviewed-by: Simon Horman Signed-off-by: Laurent Pinchart --- include/linux/platform_data/shmob_drm.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/shmob_drm.h b/include/linux/platform_data/shmob_drm.h index ee495d707f17..fe815d7d9f58 100644 --- a/include/linux/platform_data/shmob_drm.h +++ b/include/linux/platform_data/shmob_drm.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm.h -- SH Mobile DRM driver * * Copyright (C) 2012 Renesas Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __SHMOB_DRM_H__ -- cgit v1.2.3 From e21120383f2dce32312f63ffca145ff8a87d41f5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Sep 2018 19:47:09 -0400 Subject: move compat handling of tty ioctls to tty_compat_ioctl() ioctls that are * callable only via tty_ioctl() * not driver-specific * not demand data structure conversions * either always need passing arg as is or always demand compat_ptr() get intercepted in tty_compat_ioctl() from the very beginning and redirecter to tty_ioctl(). As the result, their entries in fs/compat_ioctl.c (some of those had been missing, BTW) got removed, as well as n_tty_compat_ioctl_helper() (now it's never called with any cmd it would accept). Signed-off-by: Al Viro --- include/linux/tty.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index c56e3978b00f..414db2bce715 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -746,8 +746,6 @@ static inline int tty_audit_push(void) /* tty_ioctl.c */ extern int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); -extern long n_tty_compat_ioctl_helper(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); /* vt.c */ -- cgit v1.2.3 From 2f46a2c1d4eb982b82c199e1bd5cddab12681275 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Sep 2018 21:53:32 -0400 Subject: tty_ioctl(): start taking TIOC[SG]SERIAL into separate methods ->set_serial() and ->get_serial() resp., both taking tty and a kernel pointer to serial_struct. Signed-off-by: Al Viro --- include/linux/tty_driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 71dbc891851a..358446247ccd 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -249,6 +249,7 @@ struct tty_struct; struct tty_driver; struct serial_icounter_struct; +struct serial_struct; struct tty_operations { struct tty_struct * (*lookup)(struct tty_driver *driver, @@ -287,6 +288,8 @@ struct tty_operations { int (*set_termiox)(struct tty_struct *tty, struct termiox *tnew); int (*get_icount)(struct tty_struct *tty, struct serial_icounter_struct *icount); + int (*get_serial)(struct tty_struct *tty, struct serial_struct *p); + int (*set_serial)(struct tty_struct *tty, struct serial_struct *p); void (*show_fdinfo)(struct tty_struct *tty, struct seq_file *m); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct tty_driver *driver, int line, char *options); -- cgit v1.2.3 From 52bb6677d530d37055092d86b4eab69dce6c166a Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Fri, 14 Sep 2018 16:00:51 +0800 Subject: net: move definition of pcpu_lstats to header file pcpu_lstats is defined in several files, so unify them as one and move to header file Signed-off-by: Zhang Yu Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e2b3bd750c98..baed5d5088c5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2382,6 +2382,12 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; }; +struct pcpu_lstats { + u64 packets; + u64 bytes; + struct u64_stats_sync syncp; +}; + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ -- cgit v1.2.3 From d58e468b1112dcd1d5193c0a89ff9f98b5a3e8b9 Mon Sep 17 00:00:00 2001 From: Petar Penkov Date: Fri, 14 Sep 2018 07:46:18 -0700 Subject: flow_dissector: implements flow dissector BPF hook Adds a hook for programs of type BPF_PROG_TYPE_FLOW_DISSECTOR and attach type BPF_FLOW_DISSECTOR that is executed in the flow dissector path. The BPF program is per-network namespace. Signed-off-by: Petar Penkov Signed-off-by: Willem de Bruijn Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/linux/skbuff.h | 7 +++++++ 3 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 523481a3471b..988a00797bcd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -212,6 +212,7 @@ enum bpf_reg_type { PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ + PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ }; /* The information passed from prog-specific *_is_valid_access diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index cd26c090e7c0..22083712dd18 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -32,6 +32,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) #ifdef CONFIG_INET BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport) #endif +BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 17a13e4785fc..ce0e863f02a2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -243,6 +243,8 @@ struct scatterlist; struct pipe_inode_info; struct iov_iter; struct napi_struct; +struct bpf_prog; +union bpf_attr; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct nf_conntrack { @@ -1192,6 +1194,11 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); +int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog); + +int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); + bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, -- cgit v1.2.3 From 36f47383c7f9fa0fdc20a92635435ff77ff71a6f Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Fri, 10 Aug 2018 15:13:47 +0200 Subject: mfd: cros: add charger port count command definition A new more command has been added to the ChromeOS embedded controller that allows to get the number of charger port count. Unlike EC_CMD_USB_PD_PORTS, this new command also includes the dedicated port if present. This command will be used to expose the dedicated charger port in the ChromeOS charger driver. Signed-off-by: Fabien Parent Acked-for-MFD-by: Lee Jones Reviewed-by: Enric Balletbo i Serra Signed-off-by: Sebastian Reichel --- include/linux/mfd/cros_ec_commands.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 6e1ab9bead28..20ee71f10865 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -3102,6 +3102,16 @@ struct ec_params_usb_pd_info_request { uint8_t port; } __packed; +/* + * This command will return the number of USB PD charge port + the number + * of dedicated port present. + * EC_CMD_USB_PD_PORTS does NOT include the dedicated ports + */ +#define EC_CMD_CHARGE_PORT_COUNT 0x0105 +struct ec_response_charge_port_count { + uint8_t port_count; +} __packed; + /* Read USB-PD Device discovery info */ #define EC_CMD_USB_PD_DISCOVERY 0x0113 struct ec_params_usb_pd_discovery_entry { -- cgit v1.2.3 From 8f5be0ec23bb9ef3f96659c8dff1340b876600bf Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 13 Aug 2018 09:52:09 +0300 Subject: kernfs: update comment about kernfs_path() return value Now it returns the length of the full path or error code. Signed-off-by: Konstantin Khlebnikov Fixes: 3abb1d90f5d9 ("kernfs: make kernfs_path*() behave in the style of strlcpy()") Acked-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- include/linux/kernfs.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 814643f7ee52..5b36b1287a5a 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -477,10 +477,11 @@ static inline void kernfs_init(void) { } * @buf: buffer to copy @kn's name into * @buflen: size of @buf * - * Builds and returns the full path of @kn in @buf of @buflen bytes. The - * path is built from the end of @buf so the returned pointer usually - * doesn't match @buf. If @buf isn't long enough, @buf is nul terminated - * and %NULL is returned. + * If @kn is NULL result will be "(null)". + * + * Returns the length of the full path. If the full length is equal to or + * greater than @buflen, @buf contains the truncated path with the trailing + * '\0'. On error, -errno is returned. */ static inline int kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) { -- cgit v1.2.3 From 2953d80ff04862b26a2e628fb3948868f54d753d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 31 Aug 2018 20:29:37 +0200 Subject: netfilter: remove obsolete need_conntrack stub as of a0ae2562c6c4b27 ("netfilter: conntrack: remove l3proto abstraction") there are no users anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 03097fa70975..e142b2b5f1ea 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -19,7 +19,4 @@ struct ip_conntrack_stat { unsigned int search_restart; }; -/* call to create an explicit dependency on nf_conntrack. */ -void need_conntrack(void); - #endif /* _NF_CONNTRACK_COMMON_H */ -- cgit v1.2.3 From 0baf9eb25572eea0cf48249c1d152d8373956a7c Mon Sep 17 00:00:00 2001 From: David Lechner Date: Wed, 12 Sep 2018 19:39:17 -0500 Subject: spi: add new SPI_CS_WORD flag This adds a new SPI mode flag, SPI_CS_WORD, that is used to indicate that a SPI device requires the chip select to be toggled after each word that is transferred. Signed-off-by: David Lechner Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a64235e05321..7cc1466111f5 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -163,6 +163,7 @@ struct spi_device { #define SPI_TX_QUAD 0x200 /* transmit with 4 wires */ #define SPI_RX_DUAL 0x400 /* receive with 2 wires */ #define SPI_RX_QUAD 0x800 /* receive with 4 wires */ +#define SPI_CS_WORD 0x1000 /* toggle cs after each word */ int irq; void *controller_state; void *controller_data; @@ -177,7 +178,6 @@ struct spi_device { * the controller talks to each chip, like: * - memory packing (12 bit samples into low bits, others zeroed) * - priority - * - drop chipselect after each word * - chipselect delays * - ... */ -- cgit v1.2.3 From efdfeb079cc3b6c7d9c19959c5ed65ce2510dd1d Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 6 Sep 2018 14:24:36 +0200 Subject: regulator: fixed: Convert to use GPIO descriptor only As we augmented the regulator core to accept a GPIO descriptor instead of a GPIO number, we can augment the fixed GPIO regulator to look up and pass that descriptor directly from device tree or board GPIO descriptor look up tables. Some boards just auto-enumerate their fixed regulator platform devices and I have assumed they get names like "fixed-regulator.0" but it's pretty hard to guess this. I need some testing from board maintainers to be sure. Other boards are straight forward, using just plain "fixed-regulator" (ID -1) or "fixed-regulator.1" hammering down the device ID. It seems the da9055 and da9211 has never got around to actually passing any enable gpio into its platform data (not the in-tree code anyway) so we can just decide to simply pass a descriptor instead. The fixed GPIO-controlled regulator in mach-pxa/ezx.c was confusingly named "*_dummy_supply_device" while it is a very real device backed by a GPIO line. There is nothing dummy about it at all, so I renamed it with the infix *_regulator_* as part of this patch set. Intel MID portions tested by Andy. Tested-by: Andy Shevchenko # Check the x86 BCM stuff Acked-by: Tony Lindgren # OMAP1,2,3 maintainer Signed-off-by: Linus Walleij Reviewed-by: Janusz Krzysztofik Reviewed-by: Mike Rapoport Signed-off-by: Mark Brown --- include/linux/regulator/fixed.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h index 48918be649d4..1a4340ed8e2b 100644 --- a/include/linux/regulator/fixed.h +++ b/include/linux/regulator/fixed.h @@ -24,8 +24,6 @@ struct regulator_init_data; * @supply_name: Name of the regulator supply * @input_supply: Name of the input regulator supply * @microvolts: Output voltage of regulator - * @gpio: GPIO to use for enable control - * set to -EINVAL if not used * @startup_delay: Start-up time in microseconds * @gpio_is_open_drain: Gpio pin is open drain or normal type. * If it is open drain type then HIGH will be set @@ -49,7 +47,6 @@ struct fixed_voltage_config { const char *supply_name; const char *input_supply; int microvolts; - int gpio; unsigned startup_delay; unsigned gpio_is_open_drain:1; unsigned enable_high:1; -- cgit v1.2.3 From 1ccce46c5e8b8a0d2606fb8bb72bff069ffdc3ab Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 14 Aug 2018 17:14:30 -0700 Subject: PCI: Remove unused NFP32xx IDs Defines for NFP32xx are no longer used anywhere, remove them. Signed-off-by: Jakub Kicinski Signed-off-by: Bjorn Helgaas --- include/linux/pci_ids.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d157983b84cf..f4e278493f5b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2539,8 +2539,6 @@ #define PCI_VENDOR_ID_HUAWEI 0x19e5 #define PCI_VENDOR_ID_NETRONOME 0x19ee -#define PCI_DEVICE_ID_NETRONOME_NFP3200 0x3200 -#define PCI_DEVICE_ID_NETRONOME_NFP3240 0x3240 #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 #define PCI_DEVICE_ID_NETRONOME_NFP5000 0x5000 #define PCI_DEVICE_ID_NETRONOME_NFP6000 0x6000 -- cgit v1.2.3 From 6a5f95b5a4f4ff29e4071bc5b95f8f3a2aef046b Mon Sep 17 00:00:00 2001 From: Fieah Lim Date: Tue, 11 Sep 2018 03:59:01 +0800 Subject: cpuidle: Remove unnecessary wrapper cpuidle_get_last_residency() cpuidle_get_last_residency() is just a wrapper for retrieving the last_residency member of struct cpuidle_device. It's also weirdly the only wrapper function for accessing cpuidle_* struct member (by my best guess is it could be a leftover from v2.x). Anyhow, since the only two users (the ladder and menu governors) can access dev->last_residency directly, and it's more intuitive to do it that way, let's just get rid of the wrapper. This patch tidies up CPU idle code a bit without functional changes. Signed-off-by: Fieah Lim [ rjw: Changelog cleanup ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 4325d6fdde9b..d262f620890e 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -99,16 +99,6 @@ struct cpuidle_device { DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices); DECLARE_PER_CPU(struct cpuidle_device, cpuidle_dev); -/** - * cpuidle_get_last_residency - retrieves the last state's residency time - * @dev: the target CPU - */ -static inline int cpuidle_get_last_residency(struct cpuidle_device *dev) -{ - return dev->last_residency; -} - - /**************************** * CPUIDLE DRIVER INTERFACE * ****************************/ -- cgit v1.2.3 From 10c63443b74d1ef5c1b3bb104a9e6e40dc2437ff Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 30 Aug 2018 14:54:03 +0200 Subject: Revert "serial: sh-sci: Remove SCIx_RZ_SCIFA_REGTYPE" This reverts commit 7acece71a517cad83a0842a94d94c13f271b680c. Signed-off-by: Geert Uytterhoeven Acked-by: Chris Brandt Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_sci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index c0e795d95477..1c89611e0e06 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -36,6 +36,7 @@ enum { SCIx_SH4_SCIF_FIFODATA_REGTYPE, SCIx_SH7705_SCIF_REGTYPE, SCIx_HSCIF_REGTYPE, + SCIx_RZ_SCIFA_REGTYPE, SCIx_NR_REGTYPES, }; -- cgit v1.2.3 From 76f99ae5b54d48430d1f0c5512a84da0ff9761e0 Mon Sep 17 00:00:00 2001 From: Dou Liyang Date: Sun, 9 Sep 2018 01:58:38 +0800 Subject: irq/matrix: Spread managed interrupts on allocation Linux spreads out the non managed interrupt across the possible target CPUs to avoid vector space exhaustion. Managed interrupts are treated differently, as for them the vectors are reserved (with guarantee) when the interrupt descriptors are initialized. When the interrupt is requested a real vector is assigned. The assignment logic uses the first CPU in the affinity mask for assignment. If the interrupt has more than one CPU in the affinity mask, which happens when a multi queue device has less queues than CPUs, then doing the same search as for non managed interrupts makes sense as it puts the interrupt on the least interrupt plagued CPU. For single CPU affine vectors that's obviously a NOOP. Restructre the matrix allocation code so it does the 'best CPU' search, add the sanity check for an empty affinity mask and adapt the call site in the x86 vector management code. [ tglx: Added the empty mask check to the core and improved change log ] Signed-off-by: Dou Liyang Signed-off-by: Thomas Gleixner Cc: hpa@zytor.com Link: https://lkml.kernel.org/r/20180908175838.14450-2-dou_liyang@163.com --- include/linux/irq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 201de12a9957..c9bffda04a45 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -1151,7 +1151,8 @@ void irq_matrix_offline(struct irq_matrix *m); void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, bool replace); int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk); void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk); -int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu); +int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, + unsigned int *mapped_cpu); void irq_matrix_reserve(struct irq_matrix *m); void irq_matrix_remove_reserved(struct irq_matrix *m); int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, -- cgit v1.2.3 From 4372ea94d40c5676814fc6d815a64caed963cb9f Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 18 Apr 2018 10:00:47 -0500 Subject: ipmi: Finally get rid of ipmi_user_t and ipmi_smi_t All the users have been removed, we can remove the typedefs. Signed-off-by: Corey Minyard --- include/linux/ipmi.h | 2 +- include/linux/ipmi_smi.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 41f5c086f670..ef61676cfe05 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -27,7 +27,7 @@ struct device; * Opaque type for a IPMI message user. One of these is needed to * send and receive messages. */ -typedef struct ipmi_user *ipmi_user_t; +struct ipmi_user; /* * Stuff coming from the receive interface comes as one of these. diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 7d5fd38d5282..8c4e2ab696c3 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -28,7 +28,7 @@ struct device; */ /* Structure for the low-level drivers. */ -typedef struct ipmi_smi *ipmi_smi_t; +struct ipmi_smi; /* * Messages to/from the lower layer. The smi interface will take one -- cgit v1.2.3 From 05c3d056086a6217a77937b7fa0df35ec75715e6 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Mon, 26 Feb 2018 12:49:16 -0600 Subject: pci:ipmi: Move IPMI PCI class id defines to pci_ids.h Signed-off-by: Corey Minyard Acked-by: Bjorn Helgaas --- include/linux/pci_ids.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d157983b84cf..d4afd8086ed9 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -117,6 +117,10 @@ #define PCI_CLASS_SERIAL_USB_DEVICE 0x0c03fe #define PCI_CLASS_SERIAL_FIBER 0x0c04 #define PCI_CLASS_SERIAL_SMBUS 0x0c05 +#define PCI_CLASS_SERIAL_IPMI 0x0c07 +#define PCI_CLASS_SERIAL_IPMI_SMIC 0x0c0700 +#define PCI_CLASS_SERIAL_IPMI_KCS 0x0c0701 +#define PCI_CLASS_SERIAL_IPMI_BT 0x0c0702 #define PCI_BASE_CLASS_WIRELESS 0x0d #define PCI_CLASS_WIRELESS_RF_CONTROLLER 0x0d10 -- cgit v1.2.3 From 81c4b5bf30de01a0f6b43ccaa1d220f4a0a5d99c Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 8 Sep 2018 09:59:01 +0200 Subject: PCI: hotplug: Constify hotplug_slot_ops Hotplug drivers cannot declare their hotplug_slot_ops const, making them attractive targets for attackers, because upon registration of a hotplug slot, __pci_hp_initialize() writes to the "owner" and "mod_name" members in that struct. Fix by moving these members to struct hotplug_slot and constify every driver's hotplug_slot_ops except for pciehp. pciehp constructs its hotplug_slot_ops at runtime based on the PCIe port's capabilities, hence cannot declare them const. It can be converted to __write_rarely once that's mainlined: http://www.openwall.com/lists/kernel-hardening/2016/11/16/3 Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Tyrel Datwyler # drivers/pci/hotplug/rpa* Acked-by: Andy Shevchenko # drivers/platform/x86 Cc: Len Brown Cc: Scott Murray Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Oliver OHalloran Cc: Gavin Shan Cc: Sebastian Ott Cc: Gerald Schaefer Cc: Corentin Chary Cc: Darren Hart --- include/linux/pci_hotplug.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index a6d6650a0490..372dbe95c207 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -16,8 +16,6 @@ /** * struct hotplug_slot_ops -the callbacks that the hotplug pci core can use - * @owner: The module owner of this structure - * @mod_name: The module name (KBUILD_MODNAME) of this structure * @enable_slot: Called when the user wants to enable a specific pci slot * @disable_slot: Called when the user wants to disable a specific pci slot * @set_attention_status: Called to set the specific slot's attention LED to @@ -46,8 +44,6 @@ * set an LED, enable / disable power, etc.) */ struct hotplug_slot_ops { - struct module *owner; - const char *mod_name; int (*enable_slot) (struct hotplug_slot *slot); int (*disable_slot) (struct hotplug_slot *slot); int (*set_attention_status) (struct hotplug_slot *slot, u8 value); @@ -82,15 +78,19 @@ struct hotplug_slot_info { * this slot. * @private: used by the hotplug pci controller driver to store whatever it * needs. + * @owner: The module owner of this structure + * @mod_name: The module name (KBUILD_MODNAME) of this structure */ struct hotplug_slot { - struct hotplug_slot_ops *ops; + const struct hotplug_slot_ops *ops; struct hotplug_slot_info *info; void *private; /* Variables below this are for use only by the hotplug pci core. */ struct list_head slot_list; struct pci_slot *pci_slot; + struct module *owner; + const char *mod_name; }; static inline const char *hotplug_slot_name(const struct hotplug_slot *slot) -- cgit v1.2.3 From a7da21613c4efcd4cc0235e6a30bec96ae47c619 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 8 Sep 2018 09:59:01 +0200 Subject: PCI: hotplug: Drop hotplug_slot_info Ever since the PCI hotplug core was introduced in 2002, drivers had to allocate and register a struct hotplug_slot_info for every slot: https://git.kernel.org/tglx/history/c/a8a2069f432c Apparently the idea was that drivers furnish the hotplug core with an up-to-date card presence status, power status, latch status and attention indicator status as well as notify the hotplug core of changes thereof. However only 4 out of 12 hotplug drivers bother to notify the hotplug core with pci_hp_change_slot_info() and the hotplug core never made any use of the information: There is just a single macro in pci_hotplug_core.c, GET_STATUS(), which uses the hotplug_slot_info if the driver lacks the corresponding callback in hotplug_slot_ops. The macro is called when the user reads the attribute via sysfs. Now, if the callback isn't defined, the attribute isn't exposed in sysfs in the first place (see e.g. has_power_file()). There are only two situations when the hotplug_slot_info would actually be accessed: * If the driver defines ->enable_slot or ->disable_slot but not ->get_power_status. * If the driver defines ->set_attention_status but not ->get_attention_status. There is no driver doing the former and just a single driver doing the latter, namely pnv_php.c. Amend it with a ->get_attention_status callback. With that, the hotplug_slot_info becomes completely unused by the PCI hotplug core. But a few drivers use it internally as a cache: cpcihp uses it to cache the latch_status and adapter_status. cpqhp uses it to cache the adapter_status. pnv_php and rpaphp use it to cache the attention_status. shpchp uses it to cache all four values. Amend these drivers to cache the information in their private slot struct. shpchp's slot struct already contains members to cache the power_status and adapter_status, so additional members are only needed for the other two values. In the case of cpqphp, the cached value is only accessed in a single place, so instead of caching it, read the current value from the hardware. Caution: acpiphp, cpci, cpqhp, shpchp, asus-wmi and eeepc-laptop populate the hotplug_slot_info with initial values on probe. That code is herewith removed. There is a theoretical chance that the code has side effects without which the driver fails to function, e.g. if the ACPI method to read the adapter status needs to be executed at least once on probe. That seems unlikely to me, still maintainers should review the changes carefully for this possibility. Rafael adds: "I'm not aware of any case in which it will break anything, [...] but if that happens, it may be necessary to add the execution of the control methods in question directly to the initialization part." Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Tyrel Datwyler # drivers/pci/hotplug/rpa* Acked-by: Sebastian Ott # drivers/pci/hotplug/s390* Acked-by: Andy Shevchenko # drivers/platform/x86 Cc: Len Brown Cc: Scott Murray Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Oliver OHalloran Cc: Gavin Shan Cc: Gerald Schaefer Cc: Corentin Chary Cc: Darren Hart --- include/linux/pci_hotplug.h | 30 ------------------------------ 1 file changed, 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 372dbe95c207..6f07a4e1de8d 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -23,17 +23,9 @@ * @hardware_test: Called to run a specified hardware test on the specified * slot. * @get_power_status: Called to get the current power status of a slot. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @get_attention_status: Called to get the current attention status of a slot. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @get_latch_status: Called to get the current latch status of a slot. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @get_adapter_status: Called to get see if an adapter is present in the slot or not. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @reset_slot: Optional interface to allow override of a bus reset for the * slot for cases where a secondary bus reset can result in spurious * hotplug events or where a slot can be reset independent of the bus. @@ -55,27 +47,9 @@ struct hotplug_slot_ops { int (*reset_slot) (struct hotplug_slot *slot, int probe); }; -/** - * struct hotplug_slot_info - used to notify the hotplug pci core of the state of the slot - * @power_status: if power is enabled or not (1/0) - * @attention_status: if the attention light is enabled or not (1/0) - * @latch_status: if the latch (if any) is open or closed (1/0) - * @adapter_status: if there is a pci board present in the slot or not (1/0) - * - * Used to notify the hotplug pci core of the status of a specific slot. - */ -struct hotplug_slot_info { - u8 power_status; - u8 attention_status; - u8 latch_status; - u8 adapter_status; -}; - /** * struct hotplug_slot - used to register a physical slot with the hotplug pci core * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot - * @info: pointer to the &struct hotplug_slot_info for the initial values for - * this slot. * @private: used by the hotplug pci controller driver to store whatever it * needs. * @owner: The module owner of this structure @@ -83,7 +57,6 @@ struct hotplug_slot_info { */ struct hotplug_slot { const struct hotplug_slot_ops *ops; - struct hotplug_slot_info *info; void *private; /* Variables below this are for use only by the hotplug pci core. */ @@ -110,9 +83,6 @@ void pci_hp_del(struct hotplug_slot *slot); void pci_hp_destroy(struct hotplug_slot *slot); void pci_hp_deregister(struct hotplug_slot *slot); -int __must_check pci_hp_change_slot_info(struct hotplug_slot *slot, - struct hotplug_slot_info *info); - /* use a define to avoid include chaining to get THIS_MODULE & friends */ #define pci_hp_register(slot, pbus, devnr, name) \ __pci_hp_register(slot, pbus, devnr, name, THIS_MODULE, KBUILD_MODNAME) -- cgit v1.2.3 From 125450f814418b9f889c9885831467d1b2e25a7d Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 8 Sep 2018 09:59:01 +0200 Subject: PCI: hotplug: Embed hotplug_slot When the PCI hotplug core and its first user, cpqphp, were introduced in February 2002 with historic commit a8a2069f432c, cpqphp allocated a slot struct for its internal use plus a hotplug_slot struct to be registered with the hotplug core and linked the two with pointers: https://git.kernel.org/tglx/history/c/a8a2069f432c Nowadays, the predominant pattern in the tree is to embed ("subclass") such structures in one another and cast to the containing struct with container_of(). But it wasn't until July 2002 that container_of() was introduced with historic commit ec4f214232cf: https://git.kernel.org/tglx/history/c/ec4f214232cf pnv_php, introduced in 2016, did the right thing and embedded struct hotplug_slot in its internal struct pnv_php_slot, but all other drivers cargo-culted cpqphp's design and linked separate structs with pointers. Embedding structs is preferrable to linking them with pointers because it requires fewer allocations, thereby reducing overhead and simplifying error paths. Casting an embedded struct to the containing struct becomes a cheap subtraction rather than a dereference. And having fewer pointers reduces the risk of them pointing nowhere either accidentally or due to an attack. Convert all drivers to embed struct hotplug_slot in their internal slot struct. The "private" pointer in struct hotplug_slot thereby becomes unused, so drop it. Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Tyrel Datwyler # drivers/pci/hotplug/rpa* Acked-by: Sebastian Ott # drivers/pci/hotplug/s390* Acked-by: Andy Shevchenko # drivers/platform/x86 Cc: Len Brown Cc: Scott Murray Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Oliver OHalloran Cc: Gavin Shan Cc: Gerald Schaefer Cc: Corentin Chary Cc: Darren Hart --- include/linux/pci_hotplug.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 6f07a4e1de8d..7acc9f91e72b 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -50,14 +50,11 @@ struct hotplug_slot_ops { /** * struct hotplug_slot - used to register a physical slot with the hotplug pci core * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot - * @private: used by the hotplug pci controller driver to store whatever it - * needs. * @owner: The module owner of this structure * @mod_name: The module name (KBUILD_MODNAME) of this structure */ struct hotplug_slot { const struct hotplug_slot_ops *ops; - void *private; /* Variables below this are for use only by the hotplug pci core. */ struct list_head slot_list; -- cgit v1.2.3 From 8fce3331702316d4bcfeb0771c09ac75d2192bbc Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Mon, 17 Sep 2018 09:22:56 +0100 Subject: net: stmmac: Rework coalesce timer and fix multi-queue races This follows David Miller advice and tries to fix coalesce timer in multi-queue scenarios. We are now using per-queue coalesce values and per-queue TX timer. Coalesce timer default values was changed to 1ms and the coalesce frames to 25. Tested in B2B setup between XGMAC2 and GMAC5. Signed-off-by: Jose Abreu Fixes: ce736788e8a ("net: stmmac: adding multiple buffers for TX") Cc: Florian Fainelli Cc: Neil Armstrong Cc: Jerome Brunet Cc: Martin Blumenstingl Cc: David S. Miller Cc: Joao Pinto Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c43e9a01b892..7ddfc65586b0 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -30,6 +30,7 @@ #define MTL_MAX_RX_QUEUES 8 #define MTL_MAX_TX_QUEUES 8 +#define STMMAC_CH_MAX 8 #define STMMAC_RX_COE_NONE 0 #define STMMAC_RX_COE_TYPE1 1 -- cgit v1.2.3 From 14d73416792afa84f6a7245ee474d2432069da56 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Mon, 17 Sep 2018 18:46:55 +0800 Subject: veth: rename pcpu_vstats as pcpu_lstats struct pcpu_vstats and pcpu_lstats have same members and usage, and pcpu_lstats is used in many files, so rename pcpu_vstats as pcpu_lstats to reduce duplicate definition Signed-off-by: Zhang Yu Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index baed5d5088c5..1cbbf77a685f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2000,7 +2000,6 @@ struct net_device { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; - struct pcpu_vstats __percpu *vstats; }; #if IS_ENABLED(CONFIG_GARP) -- cgit v1.2.3 From efc463adbccf709c5dbaf6cfbf84b7e94b62810a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 16 Apr 2018 14:18:26 -0500 Subject: signal: Simplify tracehook_report_syscall_exit Replace user_single_step_siginfo with user_single_step_report that allocates siginfo structure on the stack and sends it. This allows tracehook_report_syscall_exit to become a simple if statement that calls user_single_step_report or ptrace_report_syscall depending on the value of step. Update the default helper function now called user_single_step_report to explicitly set si_code to SI_USER and to set si_uid and si_pid to 0. The default helper has always been doing this (using memset) but it was far from obvious. The powerpc helper can now just call force_sig_fault. The x86 helper can now just call send_sigtrap. Unfortunately the default implementation of user_single_step_report can not use force_sig_fault as it does not use a SIGTRAP si_code. So it has to carefully setup the siginfo and use use force_sig_info. The net result is code that is easier to understand and simpler to maintain. Ref: 85ec7fd9f8e5 ("ptrace: introduce user_single_step_siginfo() helper") Reviewed-by: Thomas Gleixner Signed-off-by: "Eric W. Biederman" --- include/linux/ptrace.h | 17 +++++++++++------ include/linux/tracehook.h | 13 ++++--------- 2 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 4f36431c380b..1de2235511c8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -336,14 +336,19 @@ static inline void user_enable_block_step(struct task_struct *task) extern void user_enable_block_step(struct task_struct *); #endif /* arch_has_block_step */ -#ifdef ARCH_HAS_USER_SINGLE_STEP_INFO -extern void user_single_step_siginfo(struct task_struct *tsk, - struct pt_regs *regs, siginfo_t *info); +#ifdef ARCH_HAS_USER_SINGLE_STEP_REPORT +extern void user_single_step_report(struct pt_regs *regs); #else -static inline void user_single_step_siginfo(struct task_struct *tsk, - struct pt_regs *regs, siginfo_t *info) +static inline void user_single_step_report(struct pt_regs *regs) { - info->si_signo = SIGTRAP; + siginfo_t info; + clear_siginfo(&info); + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = SI_USER; + info.si_pid = 0; + info.si_uid = 0; + force_sig_info(info.si_signo, &info, current); } #endif diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 05589a3e37f4..40b0b4c1bf7b 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -123,15 +123,10 @@ static inline __must_check int tracehook_report_syscall_entry( */ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) { - if (step) { - siginfo_t info; - clear_siginfo(&info); - user_single_step_siginfo(current, regs, &info); - force_sig_info(SIGTRAP, &info, current); - return; - } - - ptrace_report_syscall(regs); + if (step) + user_single_step_report(regs); + else + ptrace_report_syscall(regs); } /** -- cgit v1.2.3 From 2dfd184abd38fd72d80715fa8b00c9de78490200 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 18 Sep 2018 16:20:18 -0400 Subject: flow_dissector: fix build failure without CONFIG_NET If boolean CONFIG_BPF_SYSCALL is enabled, kernel/bpf/syscall.c will call flow_dissector functions from net/core/flow_dissector.c. This causes this build failure if CONFIG_NET is disabled: kernel/bpf/syscall.o: In function `__x64_sys_bpf': syscall.c:(.text+0x3278): undefined reference to `skb_flow_dissector_bpf_prog_attach' syscall.c:(.text+0x3310): undefined reference to `skb_flow_dissector_bpf_prog_detach' kernel/bpf/syscall.o:(.rodata+0x3f0): undefined reference to `flow_dissector_prog_ops' kernel/bpf/verifier.o:(.rodata+0x250): undefined reference to `flow_dissector_verifier_ops' Analogous to other optional BPF program types in syscall.c, add stubs if the relevant functions are not compiled and move the BPF_PROG_TYPE definition in the #ifdef CONFIG_NET block. Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook") Reported-by: Randy Dunlap Signed-off-by: Willem de Bruijn Acked-by: Randy Dunlap # build-tested Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/linux/bpf_types.h | 2 +- include/linux/skbuff.h | 13 +++++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 22083712dd18..c9bd6fb765b0 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -16,6 +16,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local) BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg) +BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) #endif #ifdef CONFIG_BPF_EVENTS BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) @@ -32,7 +33,6 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) #ifdef CONFIG_INET BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport) #endif -BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ce0e863f02a2..76be85ea392a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1194,10 +1194,23 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); +#ifdef CONFIG_NET int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); +#else +static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} + +static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} +#endif bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, -- cgit v1.2.3 From eb7c8743d6cf489e30091e6656fd4d3306621e9a Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 5 Sep 2018 16:17:14 +0530 Subject: OPP: Pass index to _of_init_opp_table() This is a preparatory patch required for the next commit which will start using OPP table's node pointer in _of_init_opp_table(), which requires the index in order to read the OPP table's phandle. This commit adds the index argument in the call chains in order to get it delivered to _of_init_opp_table(). Tested-by: Niklas Cassel Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 099b31960dec..5d399eeef172 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -79,6 +79,7 @@ struct dev_pm_set_opp_data { #if defined(CONFIG_PM_OPP) struct opp_table *dev_pm_opp_get_opp_table(struct device *dev); +struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev, int index); void dev_pm_opp_put_opp_table(struct opp_table *opp_table); unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); @@ -136,6 +137,11 @@ static inline struct opp_table *dev_pm_opp_get_opp_table(struct device *dev) return ERR_PTR(-ENOTSUPP); } +static inline struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev, int index) +{ + return ERR_PTR(-ENOTSUPP); +} + static inline void dev_pm_opp_put_opp_table(struct opp_table *opp_table) {} static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) -- cgit v1.2.3 From 53dd9dce6979bc54d64a3a09a2fb20187a025be7 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 13 Sep 2018 15:16:22 -0500 Subject: libfdt: Ensure INT_MAX is defined in libfdt_env.h The next update of libfdt has a new dependency on INT_MAX. Update the instances of libfdt_env.h in the kernel to either include the necessary header with the definition or define it locally. Cc: Russell King Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: linux-arm-kernel@lists.infradead.org Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Rob Herring --- include/linux/libfdt_env.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libfdt_env.h b/include/linux/libfdt_env.h index c6ac1fe7ec68..edb0f0c30904 100644 --- a/include/linux/libfdt_env.h +++ b/include/linux/libfdt_env.h @@ -2,6 +2,7 @@ #ifndef LIBFDT_ENV_H #define LIBFDT_ENV_H +#include /* For INT_MAX */ #include #include -- cgit v1.2.3 From 822f312d47f0200dc0999c9f006fe94aa43bd0bd Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 12 Sep 2018 15:33:45 +0200 Subject: kvm: x86: make kvm_{load|put}_guest_fpu() static The functions kvm_load_guest_fpu() kvm_put_guest_fpu() are only used locally, make them static. This requires also that both functions are moved because they are used before their implementation. Those functions were exported (via EXPORT_SYMBOL) before commit e5bb40251a920 ("KVM: Drop kvm_{load,put}_guest_fpu() exports"). Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0205aee44ded..c926698040e0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -733,8 +733,6 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); -- cgit v1.2.3 From f3ecc0ff0457eae93503792c6fc35921fa8a6204 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 19 Aug 2018 14:53:20 +0200 Subject: dma-mapping: move the dma_coherent flag to struct device Various architectures support both coherent and non-coherent dma on a per-device basis. Move the dma_noncoherent flag from the mips archdata field to struct device proper to prepare the infrastructure for reuse on other architectures. Signed-off-by: Christoph Hellwig Acked-by: Paul Burton Acked-by: Greg Kroah-Hartman --- include/linux/device.h | 7 +++++++ include/linux/dma-noncoherent.h | 16 ++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 8f882549edee..983506789402 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -927,6 +927,8 @@ struct dev_links_info { * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. + * @dma_coherent: this particular device is dma coherent, even if the + * architecture supports non-coherent devices. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -1016,6 +1018,11 @@ struct device { bool offline_disabled:1; bool offline:1; bool of_node_reused:1; +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) + bool dma_coherent:1; +#endif }; static inline struct device *kobj_to_dev(struct kobject *kobj) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index a0aa00cc909d..ce9732506ef4 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -4,6 +4,22 @@ #include +#ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H +#include +#elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) +static inline bool dev_is_dma_coherent(struct device *dev) +{ + return dev->dma_coherent; +} +#else +static inline bool dev_is_dma_coherent(struct device *dev) +{ + return true; +} +#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */ + void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, -- cgit v1.2.3 From bc3ec75de5452db59b683487867ba562b950708a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 8 Sep 2018 11:22:43 +0200 Subject: dma-mapping: merge direct and noncoherent ops All the cache maintainance is already stubbed out when not enabled, but merging the two allows us to nicely handle the case where cache maintainance is required for some devices, but not others. Signed-off-by: Christoph Hellwig Acked-by: Paul Burton # MIPS parts --- include/linux/dma-direct.h | 4 ++++ include/linux/dma-mapping.h | 1 - include/linux/dma-noncoherent.h | 5 ----- 3 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 8d9f33febde5..86a59ba5a7f3 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -59,6 +59,10 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); +void *dma_direct_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); +void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_addr, unsigned long attrs); dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index eafd6f318e78..8f2001181cd1 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -136,7 +136,6 @@ struct dma_map_ops { }; extern const struct dma_map_ops dma_direct_ops; -extern const struct dma_map_ops dma_noncoherent_ops; extern const struct dma_map_ops dma_virt_ops; #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index ce9732506ef4..3f503025a0cd 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -24,14 +24,9 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); - -#ifdef CONFIG_DMA_NONCOHERENT_MMAP int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); -#else -#define arch_dma_mmap NULL -#endif /* CONFIG_DMA_NONCOHERENT_MMAP */ #ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, -- cgit v1.2.3 From 58b0440663ec11372befb8ead0ee7099d8878590 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Sep 2018 08:55:28 +0200 Subject: dma-mapping: consolidate the dma mmap implementations The only functional differences (modulo a few missing fixes in the arch code) is that architectures without coherent caches need a hook to convert a virtual or dma address into a pfn, given that we don't have the kernel linear mapping available for the otherwise easy virt_to_page call. As a side effect we can support mmap of the per-device coherent area even on architectures not providing the callback, and we make previous dangerous default methods dma_common_mmap actually save for non-coherent architectures by rejecting it without the right helper. In addition to that we need a hook so that some architectures can override the protection bits when mmaping a dma coherent allocations. Signed-off-by: Christoph Hellwig Acked-by: Paul Burton # MIPS parts --- include/linux/dma-mapping.h | 5 +++-- include/linux/dma-noncoherent.h | 10 ++++++++-- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 8f2001181cd1..c3378d4e0d57 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -444,7 +444,8 @@ dma_cache_sync(struct device *dev, void *vaddr, size_t size, } extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size); + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); void *dma_common_contiguous_remap(struct page *page, size_t size, unsigned long vm_flags, @@ -476,7 +477,7 @@ dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, BUG_ON(!ops); if (ops->mmap) return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs); - return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size); + return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); } #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 3f503025a0cd..9051b055beec 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -24,9 +24,15 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); -int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, +long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, + dma_addr_t dma_addr); + +#ifdef CONFIG_ARCH_HAS_DMA_MMAP_PGPROT +pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs); +#else +# define arch_dma_mmap_pgprot(dev, prot, attrs) pgprot_noncached(prot) +#endif #ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, -- cgit v1.2.3 From 9406a49fd1f4379409ed87b29fdaa259b0441912 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Aug 2018 09:39:38 +0200 Subject: dma-mapping: support non-coherent devices in dma_common_get_sgtable We can use the arch_dma_coherent_to_pfn hook to provide a ->get_sgtable implementation. Note that this isn't an endorsement of this interface (which is a horrible bad idea), but it is required to move arm64 over to the generic code without a loss of functionality. Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index c3378d4e0d57..bd81e74cca7b 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -483,8 +483,8 @@ dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0) int -dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t dma_addr, size_t size); +dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, + dma_addr_t dma_addr, size_t size, unsigned long attrs); static inline int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, @@ -496,7 +496,8 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, if (ops->get_sgtable) return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs); - return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size); + return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size, + attrs); } #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0) -- cgit v1.2.3 From 16caf1fa37db4722d8d8c7bc26177279949d75a6 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 4 Sep 2018 17:18:55 +0200 Subject: usb: chipidea: Add dynamic pinctrl selection Some hardware implementations require to configure pins differently according to the USB role (host/device), this can be an update of the pins routing or a simple GPIO value change. This patch introduces new optional "host" and "device" pinctrls. If these pinctrls are defined by the device, they are respectively selected on host/device role start. If a default pinctrl exist, it is restored on host/device role stop. Signed-off-by: Loic Poulain Signed-off-by: Peter Chen --- include/linux/usb/chipidea.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 07f99362bc90..63758c399e4e 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -77,6 +77,12 @@ struct ci_hdrc_platform_data { struct ci_hdrc_cable vbus_extcon; struct ci_hdrc_cable id_extcon; u32 phy_clkgate_delay_us; + + /* pins */ + struct pinctrl *pctl; + struct pinctrl_state *pins_default; + struct pinctrl_state *pins_host; + struct pinctrl_state *pins_device; }; /* Default offset of capability registers */ -- cgit v1.2.3 From 457b42f0aa1c397745ada6083bf81b9479ab19fe Mon Sep 17 00:00:00 2001 From: Liu Xiang Date: Sun, 22 Jul 2018 21:33:56 +0800 Subject: power: supply: bq27xxx: Add support for BQ27411 According to the datasheet, bq27411 is similar to bq27421. Signed-off-by: Liu Xiang Reviewed-by: Andrew F. Davis Signed-off-by: Sebastian Reichel --- include/linux/power/bq27xxx_battery.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index d6355f49fbae..507c5e214c42 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -24,6 +24,7 @@ enum bq27xxx_chip { BQ27546, BQ27742, BQ27545, /* bq27545 */ + BQ27411, BQ27421, /* bq27421, bq27441, bq27621 */ BQ27425, BQ27426, -- cgit v1.2.3 From bd93227897007bac09c44fe67626035303905900 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 22 Aug 2018 22:43:00 +0200 Subject: USB: EHCI: ehci-mv: remove private_init It's unused. Signed-off-by: Lubomir Rintel Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/mv_usb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mv_usb.h b/include/linux/platform_data/mv_usb.h index 98b7925f1a2d..c0f624aca81c 100644 --- a/include/linux/platform_data/mv_usb.h +++ b/include/linux/platform_data/mv_usb.h @@ -48,6 +48,5 @@ struct mv_usb_platform_data { int (*phy_init)(void __iomem *regbase); void (*phy_deinit)(void __iomem *regbase); int (*set_vbus)(unsigned int vbus); - int (*private_init)(void __iomem *opregs, void __iomem *phyregs); }; #endif -- cgit v1.2.3 From cd7753d371388e712e3ee52b693459f9b71aaac2 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Thu, 20 Sep 2018 14:23:40 +0300 Subject: drivers: base: Helpers for adding device connection descriptions Introducing helpers for adding and removing multiple device connection descriptions at once. Acked-by: Hans de Goede Tested-by: Hans de Goede Signed-off-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 8f882549edee..3f1066a9e1c3 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -773,6 +773,30 @@ struct device *device_connection_find(struct device *dev, const char *con_id); void device_connection_add(struct device_connection *con); void device_connection_remove(struct device_connection *con); +/** + * device_connections_add - Add multiple device connections at once + * @cons: Zero terminated array of device connection descriptors + */ +static inline void device_connections_add(struct device_connection *cons) +{ + struct device_connection *c; + + for (c = cons; c->endpoint[0]; c++) + device_connection_add(c); +} + +/** + * device_connections_remove - Remove multiple device connections at once + * @cons: Zero terminated array of device connection descriptors + */ +static inline void device_connections_remove(struct device_connection *cons) +{ + struct device_connection *c; + + for (c = cons; c->endpoint[0]; c++) + device_connection_remove(c); +} + /** * enum device_link_state - Device link states. * @DL_STATE_NONE: The presence of the drivers is not being tracked. -- cgit v1.2.3 From b1078c355d76769b5ddefc67d143fbd9b6e52c05 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Thu, 20 Sep 2018 13:41:52 +0200 Subject: of: base: Introduce of_alias_get_alias_list() to check alias IDs The function travels the lookup table to record alias ids for the given device match structures and alias stem. This function will be used by serial drivers to check if requested alias is allocated or free to use. Signed-off-by: Michal Simek Reviewed-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- include/linux/of.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..d51457b40725 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -392,6 +392,9 @@ extern int of_phandle_iterator_args(struct of_phandle_iterator *it, extern void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)); extern int of_alias_get_id(struct device_node *np, const char *stem); extern int of_alias_get_highest_id(const char *stem); +extern int of_alias_get_alias_list(const struct of_device_id *matches, + const char *stem, unsigned long *bitmap, + unsigned int nbits); extern int of_machine_is_compatible(const char *compat); @@ -893,6 +896,13 @@ static inline int of_alias_get_highest_id(const char *stem) return -ENOSYS; } +static inline int of_alias_get_alias_list(const struct of_device_id *matches, + const char *stem, unsigned long *bitmap, + unsigned int nbits) +{ + return -ENOSYS; +} + static inline int of_machine_is_compatible(const char *compat) { return 0; -- cgit v1.2.3 From d124b44f09cab67fc6da4a4513417e3e54b01efc Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 18 Sep 2018 18:55:41 +0200 Subject: Compiler Attributes: naked was fixed in gcc 4.6 Commit 9c695203a7dd ("compiler-gcc.h: gcc-4.5 needs noclone and noinline on __naked functions") added noinline and noclone as a workaround for a gcc 4.5 bug, which was resolved in 4.6.0. Since now the minimum gcc supported version is 4.6, we can clean it up. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=44290 and https://godbolt.org/z/h6NMIL Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Cc: Rasmus Villemoes Cc: Eli Friedman Cc: Christopher Li Cc: Kees Cook Cc: Ingo Molnar Cc: Geert Uytterhoeven Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Masahiro Yamada Cc: Joe Perches Cc: Dominique Martinet Cc: Linus Torvalds Cc: linux-sparse@vger.kernel.org Tested-by: Stefan Agner Reviewed-by: Stefan Agner Reviewed-by: Luc Van Oostenryck Reviewed-by: Nick Desaulniers Signed-off-by: Miguel Ojeda Signed-off-by: Greg Kroah-Hartman --- include/linux/compiler-gcc.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 763bbad1e258..25d3dd6b2702 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -84,14 +84,8 @@ * to trace naked functions because then mcount is called without * stack and frame pointer being set up and there is no chance to * restore the lr register to the value before mcount was called. - * - * The asm() bodies of naked functions often depend on standard calling - * conventions, therefore they must be noinline and noclone. - * - * GCC 4.[56] currently fail to enforce this, so we must do so ourselves. - * See GCC PR44290. */ -#define __naked __attribute__((naked)) noinline __noclone notrace +#define __naked __attribute__((naked)) notrace #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -- cgit v1.2.3 From ae596de1a0c8c2c924dc99d23c026259372ab234 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 18 Sep 2018 18:55:42 +0200 Subject: Compiler Attributes: naked can be shared The naked attribute is supported by at least gcc >= 4.6 (for ARM, which is the only current user), gcc >= 8 (for x86), clang >= 3.1 and icc >= 13. See https://godbolt.org/z/350Dyc Therefore, move it out of compiler-gcc.h so that the definition is shared by all compilers. This also fixes Clang support for ARM32 --- 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive"). Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Cc: Rasmus Villemoes Cc: Eli Friedman Cc: Christopher Li Cc: Kees Cook Cc: Ingo Molnar Cc: Geert Uytterhoeven Cc: Greg Kroah-Hartman Cc: Masahiro Yamada Cc: Joe Perches Cc: Dominique Martinet Cc: Linus Torvalds Cc: linux-sparse@vger.kernel.org Suggested-by: Arnd Bergmann Tested-by: Stefan Agner Reviewed-by: Stefan Agner Reviewed-by: Luc Van Oostenryck Reviewed-by: Nick Desaulniers Signed-off-by: Miguel Ojeda Signed-off-by: Greg Kroah-Hartman --- include/linux/compiler-gcc.h | 8 -------- include/linux/compiler_types.h | 8 ++++++++ 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 25d3dd6b2702..4d36b27214fd 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -79,14 +79,6 @@ #define __noretpoline __attribute__((indirect_branch("keep"))) #endif -/* - * it doesn't make sense on ARM (currently the only user of __naked) - * to trace naked functions because then mcount is called without - * stack and frame pointer being set up and there is no chance to - * restore the lr register to the value before mcount was called. - */ -#define __naked __attribute__((naked)) notrace - #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) #define __optimize(level) __attribute__((__optimize__(level))) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3525c179698c..db192becfec4 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -226,6 +226,14 @@ struct ftrace_likely_data { #define notrace __attribute__((no_instrument_function)) #endif +/* + * it doesn't make sense on ARM (currently the only user of __naked) + * to trace naked functions because then mcount is called without + * stack and frame pointer being set up and there is no chance to + * restore the lr register to the value before mcount was called. + */ +#define __naked __attribute__((naked)) notrace + #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) /* -- cgit v1.2.3 From 329357723f5e8e2d7fc3144fb79936b51ce63b76 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Fri, 31 Aug 2018 14:13:22 -0500 Subject: gpio: davinci: Remove unused member of davinci_gpio_controller This was added as part of the patch in the fixes below, but was not needed or used, remove this here. Fixes: 8e11047b8f3c ("gpio: davinci: Add support for multiple GPIO controllers") Tested-by: Keerthy Acked-by: Keerthy Signed-off-by: Andrew F. Davis Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-davinci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index 57a5a35e0073..b8e4957e7568 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -43,7 +43,6 @@ struct davinci_gpio_controller { void __iomem *regs[MAX_REGS_BANKS]; int gpio_unbanked; int irqs[MAX_INT_PER_BANK]; - unsigned int base; }; /* -- cgit v1.2.3 From c36219d9d8df11641d28c6bd0698459485b1709b Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Fri, 31 Aug 2018 14:13:25 -0500 Subject: gpio: davinci: Remove unneeded GPIO macro This macro does nothing and has only one user, remove it. Signed-off-by: Andrew F. Davis Tested-by: Keerthy Acked-by: Keerthy Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-davinci.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index b8e4957e7568..47695b342883 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -45,11 +45,6 @@ struct davinci_gpio_controller { int irqs[MAX_INT_PER_BANK]; }; -/* - * basic gpio routines - */ -#define GPIO(X) (X) /* 0 <= X <= (DAVINCI_N_GPIO - 1) */ - /* Convert GPIO signal to GPIO pin number */ #define GPIO_TO_PIN(bank, gpio) (16 * (bank) + (gpio)) -- cgit v1.2.3 From 79b73ff9b2a3ef312d8fa30894fd963c80ded466 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Fri, 31 Aug 2018 14:13:26 -0500 Subject: gpio: davinci: Move driver local definitions to driver These defines, structs and inline functions are used only internally by the driver, they do not belong in platform_data. Move them. Signed-off-by: Andrew F. Davis Tested-by: Keerthy Acked-by: Keerthy Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-davinci.h | 28 ---------------------------- 1 file changed, 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index 47695b342883..f92a47e18034 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -16,40 +16,12 @@ #ifndef __DAVINCI_GPIO_PLATFORM_H #define __DAVINCI_GPIO_PLATFORM_H -#include -#include - -#include - -#define MAX_REGS_BANKS 5 -#define MAX_INT_PER_BANK 32 - struct davinci_gpio_platform_data { u32 ngpio; u32 gpio_unbanked; }; -struct davinci_gpio_irq_data { - void __iomem *regs; - struct davinci_gpio_controller *chip; - int bank_num; -}; - -struct davinci_gpio_controller { - struct gpio_chip chip; - struct irq_domain *irq_domain; - /* Serialize access to GPIO registers */ - spinlock_t lock; - void __iomem *regs[MAX_REGS_BANKS]; - int gpio_unbanked; - int irqs[MAX_INT_PER_BANK]; -}; - /* Convert GPIO signal to GPIO pin number */ #define GPIO_TO_PIN(bank, gpio) (16 * (bank) + (gpio)) -static inline u32 __gpio_mask(unsigned gpio) -{ - return 1 << (gpio % 32); -} #endif -- cgit v1.2.3 From 60489f085574157c343fc62a32f997fe7346a659 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 20 Sep 2018 09:31:10 +0200 Subject: spi: spi-mem: Add missing description for data.nbytes field Add a description for spi_mem_op.data.nbytes to the kerneldoc header. Fixes: c36ff266dc82 ("spi: Extend the core to ease integration of SPI memory controllers") Signed-off-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 62722fb7472d..0cfbb1ad8d96 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -79,6 +79,8 @@ enum spi_mem_data_dir { * @dummy.buswidth: number of IO lanes used to transmit the dummy bytes * @data.buswidth: number of IO lanes used to send/receive the data * @data.dir: direction of the transfer + * @data.nbytes: number of data bytes to send/receive. Can be zero if the + * operation does not involve transferring data * @data.buf.in: input buffer * @data.buf.out: output buffer */ -- cgit v1.2.3 From c949a8e8b43f2c75567269bcc9a50d704ae3c420 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 20 Sep 2018 09:31:11 +0200 Subject: spi: spi-mem: Move the DMA-able constraint doc to the kerneldoc header We'd better have that documented in the kerneldoc header, so that it's exposed to the doc generated by Sphinx. Signed-off-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 0cfbb1ad8d96..7195fbc234aa 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -81,8 +81,8 @@ enum spi_mem_data_dir { * @data.dir: direction of the transfer * @data.nbytes: number of data bytes to send/receive. Can be zero if the * operation does not involve transferring data - * @data.buf.in: input buffer - * @data.buf.out: output buffer + * @data.buf.in: input buffer (must be DMA-able) + * @data.buf.out: output buffer (must be DMA-able) */ struct spi_mem_op { struct { @@ -105,7 +105,6 @@ struct spi_mem_op { u8 buswidth; enum spi_mem_data_dir dir; unsigned int nbytes; - /* buf.{in,out} must be DMA-able. */ union { void *in; const void *out; -- cgit v1.2.3 From 26683316c92ab2d1b330a3a38548328c9b136ad1 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Mon, 10 Sep 2018 19:47:22 +0200 Subject: ARM: OMAP1: ams-delta-fiq: Use Instead of defining symbols already defined in linux/platform_data/gpio-omap.h, use that header file. Since we include the header into an assembler code, prevent C only bits from being read in. Signed-off-by: Janusz Krzysztofik Signed-off-by: Tony Lindgren --- include/linux/platform_data/gpio-omap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h index 8612855691b2..ed071f76b642 100644 --- a/include/linux/platform_data/gpio-omap.h +++ b/include/linux/platform_data/gpio-omap.h @@ -24,8 +24,10 @@ #ifndef __ASM_ARCH_OMAP_GPIO_H #define __ASM_ARCH_OMAP_GPIO_H +#ifndef __ASSEMBLER__ #include #include +#endif #define OMAP1_MPUIO_BASE 0xfffb5000 @@ -157,6 +159,7 @@ #define OMAP_MPUIO(nr) (OMAP_MAX_GPIO_LINES + (nr)) #define OMAP_GPIO_IS_MPUIO(nr) ((nr) >= OMAP_MAX_GPIO_LINES) +#ifndef __ASSEMBLER__ struct omap_gpio_reg_offs { u16 revision; u16 direction; @@ -215,5 +218,6 @@ static inline void omap2_gpio_resume_after_idle(void) { } #endif +#endif /* __ASSEMBLER__ */ #endif -- cgit v1.2.3 From e9158b35ef9afb3bf24e0404c8fd4cd723eafa5b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Horia=20Geant=C4=83?= Date: Wed, 12 Sep 2018 11:59:26 +0300 Subject: bus: fsl-mc: add support for dpseci device type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Horia Geantă Acked-by: Laurentiu Tudor Signed-off-by: Herbert Xu --- include/linux/fsl/mc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index f27cb14088a4..5160f06ffbac 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -405,6 +405,7 @@ extern struct device_type fsl_mc_bus_dpcon_type; extern struct device_type fsl_mc_bus_dpmcp_type; extern struct device_type fsl_mc_bus_dpmac_type; extern struct device_type fsl_mc_bus_dprtc_type; +extern struct device_type fsl_mc_bus_dpseci_type; static inline bool is_fsl_mc_bus_dprc(const struct fsl_mc_device *mc_dev) { @@ -451,6 +452,11 @@ static inline bool is_fsl_mc_bus_dprtc(const struct fsl_mc_device *mc_dev) return mc_dev->dev.type == &fsl_mc_bus_dprtc_type; } +static inline bool is_fsl_mc_bus_dpseci(const struct fsl_mc_device *mc_dev) +{ + return mc_dev->dev.type == &fsl_mc_bus_dpseci_type; +} + /* * Data Path Buffer Pool (DPBP) API * Contains initialization APIs and runtime control APIs for DPBP -- cgit v1.2.3 From c785896b21dd8e156326ff660050b0074d3431df Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Sat, 15 Sep 2018 21:38:24 -0700 Subject: cpufeature: avoid warning when compiling with clang The table id (second) argument to MODULE_DEVICE_TABLE is often referenced otherwise. This is not the case for CPU features. This leads to warnings when building the kernel with Clang: arch/arm/crypto/aes-ce-glue.c:450:1: warning: variable 'cpu_feature_match_AES' is not needed and will not be emitted [-Wunneeded-internal-declaration] module_cpu_feature_match(AES, aes_init); ^ Avoid warnings by using __maybe_unused, similar to commit 1f318a8bafcf ("modules: mark __inittest/__exittest as __maybe_unused"). Fixes: 67bad2fdb754 ("cpu: add generic support for CPU feature based module autoloading") Signed-off-by: Stefan Agner Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/linux/cpufeature.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufeature.h b/include/linux/cpufeature.h index 986c06c88d81..84d3c81b5978 100644 --- a/include/linux/cpufeature.h +++ b/include/linux/cpufeature.h @@ -45,7 +45,7 @@ * 'asm/cpufeature.h' of your favorite architecture. */ #define module_cpu_feature_match(x, __initfunc) \ -static struct cpu_feature const cpu_feature_match_ ## x[] = \ +static struct cpu_feature const __maybe_unused cpu_feature_match_ ## x[] = \ { { .feature = cpu_feature(x) }, { } }; \ MODULE_DEVICE_TABLE(cpu, cpu_feature_match_ ## x); \ \ -- cgit v1.2.3 From 5d773ff41a7cdf0ef6cc6647435d59f0cf53e7b1 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Mon, 17 Sep 2018 13:30:46 +0300 Subject: net/mlx5: Rename incorrect naming in IFC file Remove a trailing underscore from the multicast/unicast names. Signed-off-by: Mark Bloch Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3a4a2e0567e9..4c7a1d25d73b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2559,8 +2559,8 @@ enum { }; enum { - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_ = 0x1, - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST_ = 0x2, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST = 0x1, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST = 0x2, }; struct mlx5_ifc_tirc_bits { -- cgit v1.2.3 From b57e99b4b8b0ebdf9707424e7ddc0c392bdc5fe6 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 21 Sep 2018 16:44:34 -0700 Subject: block: use nanosecond resolution for iostat Klaus Kusche reported that the I/O busy time in /proc/diskstats was not updating properly on 4.18. This is because we started using ktime to track elapsed time, and we convert nanoseconds to jiffies when we update the partition counter. However, this gets rounded down, so any I/Os that take less than a jiffy are not accounted for. Previously in this case, the value of jiffies would sometimes increment while we were doing I/O, so at least some I/Os were accounted for. Let's convert the stats to use nanoseconds internally. We still report milliseconds as before, now more accurately than ever. The value is still truncated to 32 bits for backwards compatibility. Fixes: 522a777566f5 ("block: consolidate struct request timestamp fields") Cc: stable@vger.kernel.org Reported-by: Klaus Kusche Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/genhd.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 57864422a2c8..25c08c6c7f99 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -83,10 +83,10 @@ struct partition { } __attribute__((packed)); struct disk_stats { + u64 nsecs[NR_STAT_GROUPS]; unsigned long sectors[NR_STAT_GROUPS]; unsigned long ios[NR_STAT_GROUPS]; unsigned long merges[NR_STAT_GROUPS]; - unsigned long ticks[NR_STAT_GROUPS]; unsigned long io_ticks; unsigned long time_in_queue; }; @@ -354,6 +354,9 @@ static inline void free_part_stats(struct hd_struct *part) #endif /* CONFIG_SMP */ +#define part_stat_read_msecs(part, which) \ + div_u64(part_stat_read(part, nsecs[which]), NSEC_PER_MSEC) + #define part_stat_read_accum(part, field) \ (part_stat_read(part, field[STAT_READ]) + \ part_stat_read(part, field[STAT_WRITE]) + \ -- cgit v1.2.3 From 27e6fa996c534c32702aa4d32db0ffa383acd050 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:26 -0400 Subject: blkcg: fix ref count issue with bio_blkcg using task_css The accessor function bio_blkcg either returns the blkcg associated with the bio or finds one in the current context. This can cause an issue when trying to associate a bio with a blkcg. Particularly, it's the third case that is problematic: return css_to_blkcg(task_css(current, io_cgrp_id)); As the above may race against task migration and the cgroup exiting, it is not always ok to take a reference on the blkcg returned from bio_blkcg. This patch adds association ahead of calling bio_blkcg rather than after. This makes association a required and explicit step along the code paths for calling bio_blkcg. blk_get_rl is modified as well to get a reference to the blkcg it may use and blk_put_rl will always put the reference back. Association is also moved above the bio_blkcg call to ensure it will not return NULL in blk-iolatency. BFQ and CFQ utilize this flaw, but due to the complexity, I do not want to address this in this series. I've created a private version of the function with notes not to use it describing the flaw. Hopefully soon, that code can be cleaned up. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 101 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 93 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 6d766a19f2bb..24067a1f8b36 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -230,22 +230,100 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); +/** + * blkcg_css - find the current css + * + * Find the css associated with either the kthread or the current task. + * This may return a dying css, so it is up to the caller to use tryget logic + * to confirm it is alive and well. + */ +static inline struct cgroup_subsys_state *blkcg_css(void) +{ + struct cgroup_subsys_state *css; + + css = kthread_blkcg(); + if (css) + return css; + return task_css(current, io_cgrp_id); +} + +/** + * blkcg_get_css - find and get a reference to the css + * + * Find the css associated with either the kthread or the current task. + * This takes a reference on the blkcg which will need to be managed by the + * caller. + */ +static inline struct cgroup_subsys_state *blkcg_get_css(void) +{ + struct cgroup_subsys_state *css; + + rcu_read_lock(); + + css = kthread_blkcg(); + if (css) { + css_get(css); + } else { + /* + * This is a bit complicated. It is possible task_css is seeing + * an old css pointer here. This is caused by the current + * thread migrating away from this cgroup and this cgroup dying. + * css_tryget() will fail when trying to take a ref on a cgroup + * that's ref count has hit 0. + * + * Therefore, if it does fail, this means current must have + * been swapped away already and this is waiting for it to + * propagate on the polling cpu. Hence the use of cpu_relax(). + */ + while (true) { + css = task_css(current, io_cgrp_id); + if (likely(css_tryget(css))) + break; + cpu_relax(); + } + } + + rcu_read_unlock(); + + return css; +} static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } -static inline struct blkcg *bio_blkcg(struct bio *bio) +/** + * __bio_blkcg - internal version of bio_blkcg for bfq and cfq + * + * DO NOT USE. + * There is a flaw using this version of the function. In particular, this was + * used in a broken paradigm where association was called on the given css. It + * is possible though that the returned css from task_css() is in the process + * of dying due to migration of the current task. So it is improper to assume + * *_get() is going to succeed. Both BFQ and CFQ rely on this logic and will + * take additional work to handle more gracefully. + */ +static inline struct blkcg *__bio_blkcg(struct bio *bio) { - struct cgroup_subsys_state *css; + if (bio && bio->bi_css) + return css_to_blkcg(bio->bi_css); + return css_to_blkcg(blkcg_css()); +} +/** + * bio_blkcg - grab the blkcg associated with a bio + * @bio: target bio + * + * This returns the blkcg associated with a bio, NULL if not associated. + * Callers are expected to either handle NULL or know association has been + * done prior to calling this. + */ +static inline struct blkcg *bio_blkcg(struct bio *bio) +{ if (bio && bio->bi_css) return css_to_blkcg(bio->bi_css); - css = kthread_blkcg(); - if (css) - return css_to_blkcg(css); - return css_to_blkcg(task_css(current, io_cgrp_id)); + return NULL; } static inline bool blk_cgroup_congested(void) @@ -534,6 +612,10 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, rcu_read_lock(); blkcg = bio_blkcg(bio); + if (blkcg) + css_get(&blkcg->css); + else + blkcg = css_to_blkcg(blkcg_get_css()); /* bypass blkg lookup and use @q->root_rl directly for root */ if (blkcg == &blkcg_root) @@ -565,6 +647,8 @@ root_rl: */ static inline void blk_put_rl(struct request_list *rl) { + /* an additional ref is always taken for rl */ + css_put(&rl->blkg->blkcg->css); if (rl->blkg->blkcg != &blkcg_root) blkg_put(rl->blkg); } @@ -805,10 +889,10 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, bool throtl = false; rcu_read_lock(); - blkcg = bio_blkcg(bio); /* associate blkcg if bio hasn't attached one */ - bio_associate_blkcg(bio, &blkcg->css); + bio_associate_blkcg(bio, NULL); + blkcg = bio_blkcg(bio); blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { @@ -930,6 +1014,7 @@ static inline int blkcg_activate_policy(struct request_queue *q, static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } +static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, -- cgit v1.2.3 From 49f4c2dc2b5066e9211101c59cc0828e81d41614 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:27 -0400 Subject: blkcg: update blkg_lookup_create to do locking To know when to create a blkg, the general pattern is to do a blkg_lookup and if that fails, lock and then do a lookup again and if that fails finally create. It doesn't make much sense for everyone who wants to do creation to write this themselves. This changes blkg_lookup_create to do locking and implement this pattern. The old blkg_lookup_create is renamed to __blkg_lookup_create. If a call site wants to do its own error handling or already owns the queue lock, they can use __blkg_lookup_create. This will be used in upcoming patches. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Reviewed-by: Liu Bo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 24067a1f8b36..cc0f238530f6 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -184,6 +184,8 @@ extern struct cgroup_subsys_state * const blkcg_root_css; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); +struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, + struct request_queue *q); struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q); int blkcg_init_queue(struct request_queue *q); @@ -897,7 +899,7 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { spin_lock_irq(q->queue_lock); - blkg = blkg_lookup_create(blkcg, q); + blkg = __blkg_lookup_create(blkcg, q); if (IS_ERR(blkg)) blkg = NULL; spin_unlock_irq(q->queue_lock); -- cgit v1.2.3 From 07b05bcc3213ac9f8c28c9d835b4bf3d5798cc60 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:28 -0400 Subject: blkcg: convert blkg_lookup_create to find closest blkg There are several scenarios where blkg_lookup_create can fail. Examples include the blkcg dying, request_queue is dying, or simply being OOM. At the end of the day, most handle this by simply falling back to the q->root_blkg and calling it a day. This patch implements the notion of closest blkg. During blkg_lookup_create, if it fails to create, return the closest blkg found or the q->root_blkg. blkg_try_get_closest is introduced and used during association so a bio is always attached to a blkg. Acked-by: Tejun Heo Signed-off-by: Dennis Zhou Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index cc0f238530f6..1fbff1bbb651 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -549,6 +549,20 @@ static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) return NULL; } +/** + * blkg_try_get_closest - try and get a blkg ref on the closet blkg + * @blkg: blkg to get + * + * This walks up the blkg tree to find the closest non-dying blkg and returns + * the blkg that it did association with as it may not be the passed in blkg. + */ +static inline struct blkcg_gq *blkg_try_get_closest(struct blkcg_gq *blkg) +{ + while (!atomic_inc_not_zero(&blkg->refcnt)) + blkg = blkg->parent; + + return blkg; +} void __blkg_release_rcu(struct rcu_head *rcu); -- cgit v1.2.3 From a7b39b4e961c4e2b3ed837803a7441a65c90ce33 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:29 -0400 Subject: blkcg: always associate a bio with a blkg Previously, blkg's were only assigned as needed by blk-iolatency and blk-throttle. bio->css was also always being associated while blkg was being looked up and then thrown away in blkcg_bio_issue_check. This patch begins the cleanup of bio->css and bio->bi_blkg by always associating a blkg in blkcg_bio_issue_check. This tries to create the blkg, but if it is not possible, falls back to using the root_blkg of the request_queue. Therefore, a bio will always be associated with a blkg. The duplicate association logic is removed from blk-throttle and blk-iolatency. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 +++ include/linux/blk-cgroup.h | 16 ++-------------- 2 files changed, 5 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 14b4fa266357..829cd0bb407d 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -542,11 +542,14 @@ static inline int bio_associate_blkcg_from_page(struct bio *bio, #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); +int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { return 0; } +static inline int bio_associate_create_blkg(struct request_queue *q, + struct bio *bio) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } static inline void bio_clone_blkcg_association(struct bio *dst, struct bio *src) { } diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1fbff1bbb651..6e33ad1d92b4 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -900,29 +900,17 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { - struct blkcg *blkcg; struct blkcg_gq *blkg; bool throtl = false; rcu_read_lock(); - /* associate blkcg if bio hasn't attached one */ - bio_associate_blkcg(bio, NULL); - blkcg = bio_blkcg(bio); - - blkg = blkg_lookup(blkcg, q); - if (unlikely(!blkg)) { - spin_lock_irq(q->queue_lock); - blkg = __blkg_lookup_create(blkcg, q); - if (IS_ERR(blkg)) - blkg = NULL; - spin_unlock_irq(q->queue_lock); - } + bio_associate_create_blkg(q, bio); + blkg = bio->bi_blkg; throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { - blkg = blkg ?: q->root_blkg; /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the -- cgit v1.2.3 From 5bf9a1f3b4efef7e463105dde8bba4d2397909c2 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:30 -0400 Subject: blkcg: consolidate bio_issue_init to be a part of core bio_issue_init among other things initializes the timestamp for an IO. Rather than have this logic handled by policies, this consolidates it to be on the init paths (normal, clone, bounce clone). Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Reviewed-by: Liu Bo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 6e33ad1d92b4..a6b6e741a75e 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -897,6 +897,12 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg struct bio *bio) { return false; } #endif + +static inline void blkcg_bio_issue_init(struct bio *bio) +{ + bio_issue_init(&bio->bi_issue, bio_sectors(bio)); +} + static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { @@ -922,6 +928,8 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } + blkcg_bio_issue_init(bio); + rcu_read_unlock(); return !throtl; } @@ -1034,6 +1042,7 @@ static inline void blk_put_rl(struct request_list *rl) { } static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } +static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { return true; } -- cgit v1.2.3 From 74b7c02a9bc124ee3df0d77880ee26db0a325516 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:31 -0400 Subject: blkcg: associate a blkg for pages being evicted by swap A prior patch in this series added blkg association to bios issued by cgroups. There are two other paths that we want to attribute work back to the appropriate cgroup: swap and writeback. Here we modify the way swap tags bios to include the blkg. Writeback will be tackle in the next patch. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 829cd0bb407d..c73a870ebc0e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -533,21 +533,26 @@ do { \ disk_devt((bio)->bi_disk) #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -int bio_associate_blkcg_from_page(struct bio *bio, struct page *page); +int bio_associate_blkg_from_page(struct bio *bio, struct page *page); #else -static inline int bio_associate_blkcg_from_page(struct bio *bio, - struct page *page) { return 0; } +static inline int bio_associate_blkg_from_page(struct bio *bio, + struct page *page) { return 0; } #endif #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); +int bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css); int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { return 0; } +static inline int bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css) +{ return 0; } static inline int bio_associate_create_blkg(struct request_queue *q, struct bio *bio) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } -- cgit v1.2.3 From bdc2491708c47601603918a9a20acddef6e1d814 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:32 -0400 Subject: blkcg: associate writeback bios with a blkg One of the goals of this series is to remove a separate reference to the css of the bio. This can and should be accessed via bio_blkcg. In this patch, the wbc_init_bio call is changed such that it must be called after a queue has been associated with the bio. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/writeback.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fdfd04e348f6..738a0c24874f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -246,7 +246,8 @@ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup - * writeback context. + * writeback context. Must be called after the bio has been associated with + * a device. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { @@ -257,7 +258,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) * regular writeback instead of writing things out itself. */ if (wbc->wb) - bio_associate_blkcg(bio, wbc->wb->blkcg_css); + bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); } #else /* CONFIG_CGROUP_WRITEBACK */ -- cgit v1.2.3 From c839e7a03f92bafd71fd145b470dcdc7f43f2d4c Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:33 -0400 Subject: blkcg: remove bio->bi_css and instead use bio->bi_blkg Prior patches ensured that all bios are now associated with some blkg. This now makes bio->bi_css unnecessary as blkg maintains a reference to the blkcg already. This patch removes the field bi_css and transfers corresponding uses to access via bi_blkg. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 9 +++------ include/linux/blk-cgroup.h | 8 ++++---- include/linux/blk_types.h | 1 - 3 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index c73a870ebc0e..e973876625a8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -540,24 +540,21 @@ static inline int bio_associate_blkg_from_page(struct bio *bio, #endif #ifdef CONFIG_BLK_CGROUP -int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); int bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); -void bio_clone_blkcg_association(struct bio *dst, struct bio *src); +void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ -static inline int bio_associate_blkcg(struct bio *bio, - struct cgroup_subsys_state *blkcg_css) { return 0; } static inline int bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { return 0; } static inline int bio_associate_create_blkg(struct request_queue *q, struct bio *bio) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } -static inline void bio_clone_blkcg_association(struct bio *dst, - struct bio *src) { } +static inline void bio_clone_blkg_association(struct bio *dst, + struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index a6b6e741a75e..c41cfcc2b4d8 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -308,8 +308,8 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) */ static inline struct blkcg *__bio_blkcg(struct bio *bio) { - if (bio && bio->bi_css) - return css_to_blkcg(bio->bi_css); + if (bio && bio->bi_blkg) + return bio->bi_blkg->blkcg; return css_to_blkcg(blkcg_css()); } @@ -323,8 +323,8 @@ static inline struct blkcg *__bio_blkcg(struct bio *bio) */ static inline struct blkcg *bio_blkcg(struct bio *bio) { - if (bio && bio->bi_css) - return css_to_blkcg(bio->bi_css); + if (bio && bio->bi_blkg) + return bio->bi_blkg->blkcg; return NULL; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f6dfb30737d8..9578c7ab1eb6 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -178,7 +178,6 @@ struct bio { * release. Read comment on top of bio_associate_current(). */ struct io_context *bi_ioc; - struct cgroup_subsys_state *bi_css; struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; #endif -- cgit v1.2.3 From f0fcb3ec89f37167810e660b0595d9a6155d9807 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:34 -0400 Subject: blkcg: remove additional reference to the css The previous patch in this series removed carrying around a pointer to the css in blkg. However, the blkg association logic still relied on taking a reference on the css to ensure we wouldn't fail in getting a reference for the blkg. Here the implicit dependency on the css is removed. The association continues to rely on the tryget logic walking up the blkg tree. This streamlines the three ways that association can happen: normal, swap, and writeback. Acked-by: Tejun Heo Signed-off-by: Dennis Zhou Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 52 ++++------------------------------------------ include/linux/cgroup.h | 2 ++ 2 files changed, 6 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index c41cfcc2b4d8..2951ea3541b1 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -249,47 +249,6 @@ static inline struct cgroup_subsys_state *blkcg_css(void) return task_css(current, io_cgrp_id); } -/** - * blkcg_get_css - find and get a reference to the css - * - * Find the css associated with either the kthread or the current task. - * This takes a reference on the blkcg which will need to be managed by the - * caller. - */ -static inline struct cgroup_subsys_state *blkcg_get_css(void) -{ - struct cgroup_subsys_state *css; - - rcu_read_lock(); - - css = kthread_blkcg(); - if (css) { - css_get(css); - } else { - /* - * This is a bit complicated. It is possible task_css is seeing - * an old css pointer here. This is caused by the current - * thread migrating away from this cgroup and this cgroup dying. - * css_tryget() will fail when trying to take a ref on a cgroup - * that's ref count has hit 0. - * - * Therefore, if it does fail, this means current must have - * been swapped away already and this is waiting for it to - * propagate on the polling cpu. Hence the use of cpu_relax(). - */ - while (true) { - css = task_css(current, io_cgrp_id); - if (likely(css_tryget(css))) - break; - cpu_relax(); - } - } - - rcu_read_unlock(); - - return css; -} - static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; @@ -628,10 +587,8 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, rcu_read_lock(); blkcg = bio_blkcg(bio); - if (blkcg) - css_get(&blkcg->css); - else - blkcg = css_to_blkcg(blkcg_get_css()); + if (!blkcg) + blkcg = css_to_blkcg(blkcg_css()); /* bypass blkg lookup and use @q->root_rl directly for root */ if (blkcg == &blkcg_root) @@ -646,7 +603,8 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, if (unlikely(!blkg)) goto root_rl; - blkg_get(blkg); + if (!blkg_try_get(blkg)) + goto root_rl; rcu_read_unlock(); return &blkg->rl; root_rl: @@ -663,8 +621,6 @@ root_rl: */ static inline void blk_put_rl(struct request_list *rl) { - /* an additional ref is always taken for rl */ - css_put(&rl->blkg->blkcg->css); if (rl->blkg->blkcg != &blkcg_root) blkg_put(rl->blkg); } diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 32c553556bbd..b8bcbdeb2eac 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -93,6 +93,8 @@ extern struct css_set init_css_set; bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); +struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, + struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, -- cgit v1.2.3 From e2b0989954ae7c80609f77e7ce203bea6d2c54e1 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:35 -0400 Subject: blkcg: cleanup and make blk_get_rl use blkg_lookup_create blk_get_rl is responsible for identifying which request_list a request should be allocated to. Try get logic was added earlier, but semantically the logic was not changed. This patch makes better use of the bio already having a reference to the blkg in the hot path. The cold path uses a better fallback of blkg_lookup_create rather than just blkg_lookup and then falling back to the q->root_rl. If lookup_create fails with anything but -ENODEV, it falls back to q->root_rl. A clarifying comment is added to explain why q->root_rl is used rather than the root blkg's rl. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 34 +++++++++++++++++++++------------- 1 file changed, 21 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 2951ea3541b1..d2f7f1b00fcf 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -586,28 +586,36 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, rcu_read_lock(); - blkcg = bio_blkcg(bio); - if (!blkcg) - blkcg = css_to_blkcg(blkcg_css()); + if (bio && bio->bi_blkg) { + blkcg = bio->bi_blkg->blkcg; + if (blkcg == &blkcg_root) + goto rl_use_root; + + blkg_get(bio->bi_blkg); + rcu_read_unlock(); + return &bio->bi_blkg->rl; + } - /* bypass blkg lookup and use @q->root_rl directly for root */ + blkcg = css_to_blkcg(blkcg_css()); if (blkcg == &blkcg_root) - goto root_rl; + goto rl_use_root; - /* - * Try to use blkg->rl. blkg lookup may fail under memory pressure - * or if either the blkcg or queue is going away. Fall back to - * root_rl in such cases. - */ blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) - goto root_rl; + blkg = __blkg_lookup_create(blkcg, q); if (!blkg_try_get(blkg)) - goto root_rl; + goto rl_use_root; + rcu_read_unlock(); return &blkg->rl; -root_rl: + + /* + * Each blkg has its own request_list, however, the root blkcg + * uses the request_queue's root_rl. This is to avoid most + * overhead for the root blkcg. + */ +rl_use_root: rcu_read_unlock(); return &q->root_rl; } -- cgit v1.2.3 From b3b9f24f5fcc099c41f7dc1d02350635830888e5 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:36 -0400 Subject: blkcg: change blkg reference counting to use percpu_ref Now that every bio is associated with a blkg, this puts the use of blkg_get, blkg_try_get, and blkg_put on the hot path. This switches over the refcnt in blkg to use percpu_ref. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index d2f7f1b00fcf..7ff5d8ba8c7a 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -126,7 +126,7 @@ struct blkcg_gq { struct request_list rl; /* reference count */ - atomic_t refcnt; + struct percpu_ref refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; @@ -490,8 +490,7 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) */ static inline void blkg_get(struct blkcg_gq *blkg) { - WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); - atomic_inc(&blkg->refcnt); + percpu_ref_get(&blkg->refcnt); } /** @@ -503,7 +502,7 @@ static inline void blkg_get(struct blkcg_gq *blkg) */ static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) { - if (atomic_inc_not_zero(&blkg->refcnt)) + if (percpu_ref_tryget(&blkg->refcnt)) return blkg; return NULL; } @@ -517,23 +516,19 @@ static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) */ static inline struct blkcg_gq *blkg_try_get_closest(struct blkcg_gq *blkg) { - while (!atomic_inc_not_zero(&blkg->refcnt)) + while (!percpu_ref_tryget(&blkg->refcnt)) blkg = blkg->parent; return blkg; } -void __blkg_release_rcu(struct rcu_head *rcu); - /** * blkg_put - put a blkg reference * @blkg: blkg to put */ static inline void blkg_put(struct blkcg_gq *blkg) { - WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); - if (atomic_dec_and_test(&blkg->refcnt)) - call_rcu(&blkg->rcu_head, __blkg_release_rcu); + percpu_ref_put(&blkg->refcnt); } /** -- cgit v1.2.3 From 101246ec02b54adf6a77180a01ccbe310add2c32 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:37 -0400 Subject: blkcg: rename blkg_try_get to blkg_tryget blkg reference counting now uses percpu_ref rather than atomic_t. Let's make this consistent with css_tryget. This renames blkg_try_get to blkg_tryget and now returns a bool rather than the blkg or NULL. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 7ff5d8ba8c7a..b7fd08013de2 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -494,27 +494,25 @@ static inline void blkg_get(struct blkcg_gq *blkg) } /** - * blkg_try_get - try and get a blkg reference + * blkg_tryget - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ -static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) +static inline bool blkg_tryget(struct blkcg_gq *blkg) { - if (percpu_ref_tryget(&blkg->refcnt)) - return blkg; - return NULL; + return percpu_ref_tryget(&blkg->refcnt); } /** - * blkg_try_get_closest - try and get a blkg ref on the closet blkg + * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @blkg: blkg to get * * This walks up the blkg tree to find the closest non-dying blkg and returns * the blkg that it did association with as it may not be the passed in blkg. */ -static inline struct blkcg_gq *blkg_try_get_closest(struct blkcg_gq *blkg) +static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) { while (!percpu_ref_tryget(&blkg->refcnt)) blkg = blkg->parent; @@ -599,7 +597,7 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, if (unlikely(!blkg)) blkg = __blkg_lookup_create(blkcg, q); - if (!blkg_try_get(blkg)) + if (!blkg_tryget(blkg)) goto rl_use_root; rcu_read_unlock(); -- cgit v1.2.3 From 9799ccb0e984a5c1311b22a212e7ff96e8b736de Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Sep 2018 08:51:49 -0700 Subject: tcp: add tcp_wstamp_ns socket field TCP will soon provide earliest departure time on TX skbs. It needs to track this in a new variable. tcp_mstamp_refresh() needs to update this variable, and became too big to stay an inline. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 263e37271afd..848f5b25e178 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -248,6 +248,8 @@ struct tcp_sock { syn_smc:1; /* SYN includes SMC */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ + u64 tcp_wstamp_ns; /* departure time for next sent data packet */ + /* RTT measurement */ u64 tcp_mstamp; /* most recent packet received/sent */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ -- cgit v1.2.3 From d3edd06ea8ea9e03de6567fda80b8be57e21a537 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Sep 2018 08:51:50 -0700 Subject: tcp: provide earliest departure time in skb->tstamp Switch internal TCP skb->skb_mstamp to skb->skb_mstamp_ns, from usec units to nsec units. Do not clear skb->tstamp before entering IP stacks in TX, so that qdisc or devices can implement pacing based on the earliest departure time instead of socket sk->sk_pacing_rate Packets are fed with tcp_wstamp_ns, and following patch will update tcp_wstamp_ns when both TCP and sch_fq switch to the earliest departure time mechanism. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e3a53ca4a9b5..86f337e9a81d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -689,7 +689,7 @@ struct sk_buff { union { ktime_t tstamp; - u64 skb_mstamp; + u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every -- cgit v1.2.3 From c798c88f3962ddff89c7aa818986caeecd46ab4c Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Wed, 19 Sep 2018 01:59:00 +0000 Subject: EDAC, ghes: Use CPER module handles to locate DIMMs Use SMBIOS module handle type 17, on platforms which provide valid ones, to locate the corresponding DIMM and thus have per-DIMM error counter updates. Signed-off-by: Fan Wu [ Massage commit message. ] Signed-off-by: Borislav Petkov Reviewed-by: Tyler Baicar Reviewed-by: James Morse Tested-by: Toshi Kani Cc: Mauro Carvalho Chehab Cc: baicar.tyler@gmail.com Cc: john.garry@huawei.com Cc: linux-arm-kernel@lists.infradead.org Cc: linux-edac Cc: shiju.jose@huawei.com Cc: tanxiaofei@huawei.com Cc: wanghuiqiang@huawei.com Link: http://lkml.kernel.org/r/1537322340-1860-1-git-send-email-wufan@codeaurora.org --- include/linux/edac.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index bffb97828ed6..a45ce1f84bfc 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -451,6 +451,8 @@ struct dimm_info { u32 nr_pages; /* number of pages on this dimm */ unsigned csrow, cschannel; /* Points to the old API data */ + + u16 smbios_handle; /* Handle for SMBIOS type 17 */ }; /** -- cgit v1.2.3 From 65a272642ce13aab911f68279c8994cde3282b0a Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 18 May 2018 15:47:50 -0700 Subject: soc: qcom: geni: Make version macros simpler This macro doesn't work, because it hides a local variable inside of the macro to hold the version and that variable name is called 'ver' and 'version' sometimes. Let's change this to be more explicit. Introduce three macros for the major, minor, and step of the version, and require callers to pass the version in to get the part of the version out. This way we don't hide local variables inside macros and things are less evil overall. Cc: Karthikeyan Ramasubramanian Cc: Sagar Dharia Cc: Girish Mahadevan Signed-off-by: Stephen Boyd Reviewed-by: Douglas Anderson Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/qcom-geni-se.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 5d6144977828..3bcd67fd5548 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -225,19 +225,14 @@ struct geni_se { #define HW_VER_MINOR_SHFT 16 #define HW_VER_STEP_MASK GENMASK(15, 0) +#define GENI_SE_VERSION_MAJOR(ver) ((ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT) +#define GENI_SE_VERSION_MINOR(ver) ((ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT) +#define GENI_SE_VERSION_STEP(ver) (ver & HW_VER_STEP_MASK) + #if IS_ENABLED(CONFIG_QCOM_GENI_SE) u32 geni_se_get_qup_hw_version(struct geni_se *se); -#define geni_se_get_wrapper_version(se, major, minor, step) do { \ - u32 ver; \ -\ - ver = geni_se_get_qup_hw_version(se); \ - major = (ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT; \ - minor = (ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT; \ - step = version & HW_VER_STEP_MASK; \ -} while (0) - /** * geni_se_read_proto() - Read the protocol configured for a serial engine * @se: Pointer to the concerned serial engine. -- cgit v1.2.3 From ac3d9dd034e565df2c034ab2ca71f0a9f69153c1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Sep 2018 15:27:38 -0700 Subject: netpoll: make ndo_poll_controller() optional As diagnosed by Song Liu, ndo_poll_controller() can be very dangerous on loaded hosts, since the cpu calling ndo_poll_controller() might steal all NAPI contexts (for all RX/TX queues of the NIC). This capture can last for unlimited amount of time, since one cpu is generally not able to drain all the queues under load. It seems that all networking drivers that do use NAPI for their TX completions, should not provide a ndo_poll_controller(). NAPI drivers have netpoll support already handled in core networking stack, since netpoll_poll_dev() uses poll_napi(dev) to iterate through registered NAPI contexts for a device. This patch allows netpoll_poll_dev() to process NAPI contexts even for drivers not providing ndo_poll_controller(), allowing for following patches in NAPI drivers. Also we export netpoll_poll_dev() so that it can be called by bonding/team drivers in following patches. Reported-by: Song Liu Signed-off-by: Eric Dumazet Tested-by: Song Liu Signed-off-by: David S. Miller --- include/linux/netpoll.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 67662d01130a..3ef82d3a78db 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -49,8 +49,9 @@ struct netpoll_info { }; #ifdef CONFIG_NETPOLL -extern void netpoll_poll_disable(struct net_device *dev); -extern void netpoll_poll_enable(struct net_device *dev); +void netpoll_poll_dev(struct net_device *dev); +void netpoll_poll_disable(struct net_device *dev); +void netpoll_poll_enable(struct net_device *dev); #else static inline void netpoll_poll_disable(struct net_device *dev) { return; } static inline void netpoll_poll_enable(struct net_device *dev) { return; } -- cgit v1.2.3 From 1cc33161a83d20b5462b1e93f95d3ce6388079ee Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Mon, 20 Aug 2018 10:12:47 +0530 Subject: uprobes: Support SDT markers having reference count (semaphore) Userspace Statically Defined Tracepoints[1] are dtrace style markers inside userspace applications. Applications like PostgreSQL, MySQL, Pthread, Perl, Python, Java, Ruby, Node.js, libvirt, QEMU, glib etc have these markers embedded in them. These markers are added by developer at important places in the code. Each marker source expands to a single nop instruction in the compiled code but there may be additional overhead for computing the marker arguments which expands to couple of instructions. In case the overhead is more, execution of it can be omitted by runtime if() condition when no one is tracing on the marker: if (reference_counter > 0) { Execute marker instructions; } Default value of reference counter is 0. Tracer has to increment the reference counter before tracing on a marker and decrement it when done with the tracing. Implement the reference counter logic in core uprobe. User will be able to use it from trace_uprobe as well as from kernel module. New trace_uprobe definition with reference counter will now be: :[(ref_ctr_offset)] where ref_ctr_offset is an optional field. For kernel module, new variant of uprobe_register() has been introduced: uprobe_register_refctr(inode, offset, ref_ctr_offset, consumer) No new variant for uprobe_unregister() because it's assumed to have only one reference counter for one uprobe. [1] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation Note: 'reference counter' is called as 'semaphore' in original Dtrace (or Systemtap, bcc and even in ELF) documentation and code. But the term 'semaphore' is misleading in this context. This is just a counter used to hold number of tracers tracing on a marker. This is not really used for any synchronization. So we are calling it a 'reference counter' in kernel / perf code. Link: http://lkml.kernel.org/r/20180820044250.11659-2-ravi.bangoria@linux.ibm.com Reviewed-by: Masami Hiramatsu [Only trace_uprobe.c] Reviewed-by: Oleg Nesterov Reviewed-by: Song Liu Tested-by: Song Liu Signed-off-by: Ravi Bangoria Signed-off-by: Steven Rostedt (VMware) --- include/linux/uprobes.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index bb9d2084af03..103a48a48872 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -123,6 +123,7 @@ extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); +extern int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern int uprobe_mmap(struct vm_area_struct *vma); @@ -160,6 +161,10 @@ uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { return -ENOSYS; } +static inline int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) +{ + return -ENOSYS; +} static inline int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add) { -- cgit v1.2.3 From a725356b6659469d182d662f22d770d83d3bc7b5 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Tue, 18 Sep 2018 16:34:34 +0300 Subject: vfs: swap names of {do,vfs}_clone_file_range() Commit 031a072a0b8a ("vfs: call vfs_clone_file_range() under freeze protection") created a wrapper do_clone_file_range() around vfs_clone_file_range() moving the freeze protection to former, so overlayfs could call the latter. The more common vfs practice is to call do_xxx helpers from vfs_xxx helpers, where freeze protecction is taken in the vfs_xxx helper, so this anomality could be a source of confusion. It seems that commit 8ede205541ff ("ovl: add reflink/copyfile/dedup support") may have fallen a victim to this confusion - ovl_clone_file_range() calls the vfs_clone_file_range() helper in the hope of getting freeze protection on upper fs, but in fact results in overlayfs allowing to bypass upper fs freeze protection. Swap the names of the two helpers to conform to common vfs practice and call the correct helpers from overlayfs and nfsd. Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c0b4a1c22ff..897eae8faee1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1828,8 +1828,10 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, struct inode *inode_out, loff_t pos_out, u64 *len, bool is_dedupe); +extern int do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); + struct file *file_out, loff_t pos_out, u64 len); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); @@ -2773,19 +2775,6 @@ static inline void file_end_write(struct file *file) __sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE); } -static inline int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len) -{ - int ret; - - file_start_write(file_out); - ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len); - file_end_write(file_out); - - return ret; -} - /* * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. -- cgit v1.2.3 From ec0daae685b20f3bee196719f64d79d1cc40457e Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 20 Sep 2018 12:35:30 -0700 Subject: gpio: omap: Add level wakeup handling for omap4 based SoCs I noticed that unlike omap2 and 3 based SoCs, omap4 based SoCs keep the GPIO clocks enabled for GPIO level interrupts with wakeup enabled. This blocks deeper idle states as the whole domain will stay busy. The GPIO functional clock seems to stay enabled if the wakeup register is enabled and a level interrupt is triggered. In that case the only way to have the GPIO module idle is to reset it. It is possible this has gone unnoticed with OSWR (Open SWitch Retention) and off mode during idle resetting GPIO context most GPIO instances in the earlier Android trees for example. Looks like the way to deal with this is to have omap4 based SoCs only set wake for the duration of idle for level interrupts, and clear level registers for the idle. With level interrupts we can do this as the level interrupt from device will be still there on resume. I've taken the long path to fixing this to avoid yet more hard to read code. I've set up a quirks flag, and a struct for function pointers so we can use these to clean up other quirk handling easier in the later patches. The current level quirk handling is moved to the new functions. Cc: Aaro Koskinen Cc: Ladislav Michl Cc: Tero Kristo Signed-off-by: Tony Lindgren Acked-by: Grygorii Strashko Tested-by: Keerthy Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-omap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h index 8612855691b2..d952151b6e33 100644 --- a/include/linux/platform_data/gpio-omap.h +++ b/include/linux/platform_data/gpio-omap.h @@ -197,6 +197,8 @@ struct omap_gpio_platform_data { bool is_mpuio; /* whether the bank is of type MPUIO */ u32 non_wakeup_gpios; + u32 quirks; /* Version specific quirks mask */ + struct omap_gpio_reg_offs *regs; /* Return context loss count due to PM states changing */ -- cgit v1.2.3 From b764a5863fd834836e65e258303e3a4a81c20f38 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 20 Sep 2018 12:35:31 -0700 Subject: gpio: omap: Remove custom PM calls and use cpu_pm instead For a long time the gpio-omap custom PM calls have been annoying me so let's replace them with cpu_pm instead. This will enable GPIO PM for deeper idle states on omap4. And we can handle GPIO PM for omap2/3/4 in the same way. Note that with this patch we are also slightly changing GPIO PM to be less aggressive for omap3 and only will idle GPIO when PER context may be lost. For omap2, we don't need to save context and don't want to remove any triggering so let's add a quirk flag for that. Let's do this all in a single patch to avoid a situation where old custom calls still are used with new code. Cc: Aaro Koskinen Cc: Keerthy Cc: Ladislav Michl Cc: Tero Kristo Signed-off-by: Tony Lindgren Acked-by: Grygorii Strashko Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-omap.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h index d952151b6e33..8485c6a9a383 100644 --- a/include/linux/platform_data/gpio-omap.h +++ b/include/linux/platform_data/gpio-omap.h @@ -205,17 +205,4 @@ struct omap_gpio_platform_data { int (*get_context_loss_count)(struct device *dev); }; -#if IS_BUILTIN(CONFIG_GPIO_OMAP) -extern void omap2_gpio_prepare_for_idle(int off_mode); -extern void omap2_gpio_resume_after_idle(void); -#else -static inline void omap2_gpio_prepare_for_idle(int off_mode) -{ -} - -static inline void omap2_gpio_resume_after_idle(void) -{ -} -#endif - #endif -- cgit v1.2.3 From 463659a08d7999d5461fa45b35b17686189a70ca Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 13 Sep 2018 07:47:29 -0400 Subject: media: hdmi.h: rename ADOBE_RGB to OPRGB and ADOBE_YCC to OPYCC These names have been renamed in the CTA-861 standard due to trademark issues. Replace them here as well so they are in sync with the standard. Signed-off-by: Hans Verkuil Cc: stable@vger.kernel.org Acked-by: Daniel Vetter Signed-off-by: Mauro Carvalho Chehab --- include/linux/hdmi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index d271ff23984f..4f3febc0f971 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -101,8 +101,8 @@ enum hdmi_extended_colorimetry { HDMI_EXTENDED_COLORIMETRY_XV_YCC_601, HDMI_EXTENDED_COLORIMETRY_XV_YCC_709, HDMI_EXTENDED_COLORIMETRY_S_YCC_601, - HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601, - HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB, + HDMI_EXTENDED_COLORIMETRY_OPYCC_601, + HDMI_EXTENDED_COLORIMETRY_OPRGB, /* The following EC values are only defined in CEA-861-F. */ HDMI_EXTENDED_COLORIMETRY_BT2020_CONST_LUM, -- cgit v1.2.3 From 808c43b7c7f70360ed7b9e43e2cf980f388e71fa Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 21 Sep 2018 17:03:27 -0700 Subject: cgroup: Simplify cgroup_ancestor Simplify cgroup_ancestor function. This is follow-up for commit 7723628101aa ("bpf: Introduce bpf_skb_ancestor_cgroup_id helper") Suggested-by: Tejun Heo Signed-off-by: Andrey Ignatov Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 32c553556bbd..e03a92430383 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -567,20 +567,11 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { - struct cgroup *ptr; - if (cgrp->level < ancestor_level) return NULL; - - for (ptr = cgrp; - ptr && ptr->level > ancestor_level; - ptr = cgroup_parent(ptr)) - ; - - if (ptr && ptr->level == ancestor_level) - return ptr; - - return NULL; + while (cgrp && cgrp->level > ancestor_level) + cgrp = cgroup_parent(cgrp); + return cgrp; } /** -- cgit v1.2.3 From 43b729bfe9cf30ad11499a66e3b7bd300c716d44 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:47 +0200 Subject: block: move integrity_req_gap_{back,front}_merge to blk.h No need to expose these to drivers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 31 ------------------------------- 1 file changed, 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d6869e0e2b64..bc534c857344 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1843,26 +1843,6 @@ queue_max_integrity_segments(struct request_queue *q) return q->limits.max_integrity_segments; } -static inline bool integrity_req_gap_back_merge(struct request *req, - struct bio *next) -{ - struct bio_integrity_payload *bip = bio_integrity(req->bio); - struct bio_integrity_payload *bip_next = bio_integrity(next); - - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], - bip_next->bip_vec[0].bv_offset); -} - -static inline bool integrity_req_gap_front_merge(struct request *req, - struct bio *bio) -{ - struct bio_integrity_payload *bip = bio_integrity(bio); - struct bio_integrity_payload *bip_next = bio_integrity(req->bio); - - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], - bip_next->bip_vec[0].bv_offset); -} - /** * bio_integrity_intervals - Return number of integrity intervals for a bio * @bi: blk_integrity profile for device @@ -1947,17 +1927,6 @@ static inline bool blk_integrity_merge_bio(struct request_queue *rq, return true; } -static inline bool integrity_req_gap_back_merge(struct request *req, - struct bio *next) -{ - return false; -} -static inline bool integrity_req_gap_front_merge(struct request *req, - struct bio *bio) -{ - return false; -} - static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { -- cgit v1.2.3 From e9907009cbfc0c93d987d5a8fdf3d6c3c7b89717 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:48 +0200 Subject: block: move req_gap_{back,front}_merge to blk-merge.c Keep it close to the actual users instead of exposing the function to all drivers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 69 -------------------------------------------------- 1 file changed, 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bc534c857344..b7e676bb01bc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1695,75 +1695,6 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, return __bvec_gap_to_prev(q, bprv, offset); } -/* - * Check if the two bvecs from two bios can be merged to one segment. - * If yes, no need to check gap between the two bios since the 1st bio - * and the 1st bvec in the 2nd bio can be handled in one segment. - */ -static inline bool bios_segs_mergeable(struct request_queue *q, - struct bio *prev, struct bio_vec *prev_last_bv, - struct bio_vec *next_first_bv) -{ - if (!BIOVEC_PHYS_MERGEABLE(prev_last_bv, next_first_bv)) - return false; - if (!BIOVEC_SEG_BOUNDARY(q, prev_last_bv, next_first_bv)) - return false; - if (prev->bi_seg_back_size + next_first_bv->bv_len > - queue_max_segment_size(q)) - return false; - return true; -} - -static inline bool bio_will_gap(struct request_queue *q, - struct request *prev_rq, - struct bio *prev, - struct bio *next) -{ - if (bio_has_data(prev) && queue_virt_boundary(q)) { - struct bio_vec pb, nb; - - /* - * don't merge if the 1st bio starts with non-zero - * offset, otherwise it is quite difficult to respect - * sg gap limit. We work hard to merge a huge number of small - * single bios in case of mkfs. - */ - if (prev_rq) - bio_get_first_bvec(prev_rq->bio, &pb); - else - bio_get_first_bvec(prev, &pb); - if (pb.bv_offset) - return true; - - /* - * We don't need to worry about the situation that the - * merged segment ends in unaligned virt boundary: - * - * - if 'pb' ends aligned, the merged segment ends aligned - * - if 'pb' ends unaligned, the next bio must include - * one single bvec of 'nb', otherwise the 'nb' can't - * merge with 'pb' - */ - bio_get_last_bvec(prev, &pb); - bio_get_first_bvec(next, &nb); - - if (!bios_segs_mergeable(q, prev, &pb, &nb)) - return __bvec_gap_to_prev(q, &pb, nb.bv_offset); - } - - return false; -} - -static inline bool req_gap_back_merge(struct request *req, struct bio *bio) -{ - return bio_will_gap(req->q, req, req->biotail, bio); -} - -static inline bool req_gap_front_merge(struct request *req, struct bio *bio) -{ - return bio_will_gap(req->q, NULL, bio, req->bio); -} - int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); -- cgit v1.2.3 From 27ca1d4ed04ea29dc77b47190a3cc82697023e76 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:49 +0200 Subject: block: move req_gap_back_merge to blk.h No need to expose these helpers outside the block layer. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b7e676bb01bc..1d5e14139795 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1676,25 +1676,6 @@ static inline void put_dev_sector(Sector p) put_page(p.v); } -static inline bool __bvec_gap_to_prev(struct request_queue *q, - struct bio_vec *bprv, unsigned int offset) -{ - return offset || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); -} - -/* - * Check if adding a bio_vec after bprv with offset would create a gap in - * the SG list. Most drivers don't care about this, but some do. - */ -static inline bool bvec_gap_to_prev(struct request_queue *q, - struct bio_vec *bprv, unsigned int offset) -{ - if (!queue_virt_boundary(q)) - return false; - return __bvec_gap_to_prev(q, bprv, offset); -} - int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); -- cgit v1.2.3 From 6a9f5f240adfdced863a098d34f8f05ca6ab9d5f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:50 +0200 Subject: block: simplify BIOVEC_PHYS_MERGEABLE Turn the macro into an inline, move it to blk.h and simplify the arch hooks a bit. Also rename the function to biovec_phys_mergeable as there is no need to shout. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index e973876625a8..e2adb96346f0 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -140,19 +140,6 @@ static inline bool bio_full(struct bio *bio) /* * merge helpers etc */ - -/* Default implementation of BIOVEC_PHYS_MERGEABLE */ -#define __BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ - ((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) - -/* - * allow arch override, for eg virtualized architectures (put in asm/io.h) - */ -#ifndef BIOVEC_PHYS_MERGEABLE -#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ - __BIOVEC_PHYS_MERGEABLE(vec1, vec2) -#endif - #define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \ (((addr1) | (mask)) == (((addr2) - 1) | (mask))) #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \ -- cgit v1.2.3 From 3dccdae54fe836a22cee9dc6df9fd1708ae075ce Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:52 +0200 Subject: block: merge BIOVEC_SEG_BOUNDARY into biovec_phys_mergeable These two checks should always be performed together, so merge them into a single helper. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index e2adb96346f0..9b580e1cb2e8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -137,14 +137,6 @@ static inline bool bio_full(struct bio *bio) */ #define bvec_to_phys(bv) (page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset) -/* - * merge helpers etc - */ -#define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \ - (((addr1) | (mask)) == (((addr2) - 1) | (mask))) -#define BIOVEC_SEG_BOUNDARY(q, b1, b2) \ - __BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q))) - /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it -- cgit v1.2.3 From 6e768461c215eaf8912e6c23e40fdff1cd962aca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:53 +0200 Subject: block: remove bvec_to_phys We only use it in biovec_phys_mergeable and a m68k paravirt driver, so just opencode it there. Also remove the pointless unsigned long cast for the offset in the opencoded instances. Signed-off-by: Christoph Hellwig Reviewed-by: Geert Uytterhoeven Signed-off-by: Jens Axboe --- include/linux/bio.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 9b580e1cb2e8..9ad4b0a487a4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -132,11 +132,6 @@ static inline bool bio_full(struct bio *bio) return bio->bi_vcnt >= bio->bi_max_vecs; } -/* - * will die - */ -#define bvec_to_phys(bv) (page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset) - /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it -- cgit v1.2.3 From bceacbfa48bf132d8d88058904cf5859eeb4f3e6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:54 +0200 Subject: block: don't include io.h from bio.h Now that we don't need an override for BIOVEC_PHYS_MERGEABLE there is no need to drag this header in. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 9ad4b0a487a4..b3d47862b1b4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -24,9 +24,6 @@ #include #ifdef CONFIG_BLOCK - -#include - /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include -- cgit v1.2.3 From 65969e5cb249b765cee261c8f0458ec778b0c22f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:55 +0200 Subject: block: don't include bug.h from bio.h No need to pull in the BUG() defintion. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index b3d47862b1b4..f447b0ebb288 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -21,7 +21,6 @@ #include #include #include -#include #ifdef CONFIG_BLOCK /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ -- cgit v1.2.3 From 40d9f9124822013331367fb4ab59936c3ac944d6 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 24 Sep 2018 12:16:54 -0700 Subject: bus: ti-sysc: Defer suspend as needed We don't care when we suspend but some our children do. In order to avoid tagging various modules with SYSC_QUIRK_RESOURCE_PROVIDER, let's do it automatically by tagging modules that are busy on suspend for noirq suspend. This way we can just do module detection on define DEBUG. Note that we still need to keep SYSC_QUIRK_LEGACY_IDLE flag around so the our legacy single-child devices that set pm_runtime_irq_safe() can manage the interconnect target module themselves. Signed-off-by: Tony Lindgren --- include/linux/platform_data/ti-sysc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 2efa3470a451..1ea3aab972b4 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -46,7 +46,6 @@ struct sysc_regbits { s8 emufree_shift; }; -#define SYSC_QUIRK_RESOURCE_PROVIDER BIT(9) #define SYSC_QUIRK_LEGACY_IDLE BIT(8) #define SYSC_QUIRK_RESET_STATUS BIT(7) #define SYSC_QUIRK_NO_IDLE_ON_INIT BIT(6) -- cgit v1.2.3 From 9ba481e2eb3b932ae5b6278342b256e4f92d2793 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:20 +0300 Subject: net/mlx5: Set uid as part of CQ commands Set uid as part of CQ commands so that the firmware can manage the CQ object in a secured way. The firmware should mark this CQ with the given uid so that it can be used later on only by objects with the same uid. Upon DEVX flows that use this CQ (e.g. create QP command), the pointed CQ must have the same uid as of the issuer uid command. When a command is issued with uid=0 it means that the issuer of the command is trusted (i.e. kernel), in that case any pointed object can be used regardless of its uid. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/cq.h | 1 + include/linux/mlx5/mlx5_ifc.h | 6 +++--- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 0ef6138eca49..31a750570c38 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -61,6 +61,7 @@ struct mlx5_core_cq { int reset_notify_added; struct list_head reset_notify; struct mlx5_eq *eq; + u16 uid; }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4c7a1d25d73b..1a412b355054 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5629,7 +5629,7 @@ enum { struct mlx5_ifc_modify_cq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6404,7 +6404,7 @@ struct mlx5_ifc_destroy_cq_out_bits { struct mlx5_ifc_destroy_cq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7164,7 +7164,7 @@ struct mlx5_ifc_create_cq_out_bits { struct mlx5_ifc_create_cq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From 4ac63ec72587f7426aae15ddfe78e8ab785724dc Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:21 +0300 Subject: net/mlx5: Set uid as part of QP commands Set uid as part of QP commands so that the firmware can manage the QP object in a secured way. That will enable using a QP that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 22 +++++++++++----------- include/linux/mlx5/qp.h | 1 + 2 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1a412b355054..3b6a612787ac 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3394,7 +3394,7 @@ struct mlx5_ifc_sqerr2rts_qp_out_bits { struct mlx5_ifc_sqerr2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3424,7 +3424,7 @@ struct mlx5_ifc_sqd2rts_qp_out_bits { struct mlx5_ifc_sqd2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3629,7 +3629,7 @@ struct mlx5_ifc_rts2rts_qp_out_bits { struct mlx5_ifc_rts2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3659,7 +3659,7 @@ struct mlx5_ifc_rtr2rts_qp_out_bits { struct mlx5_ifc_rtr2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3689,7 +3689,7 @@ struct mlx5_ifc_rst2init_qp_out_bits { struct mlx5_ifc_rst2init_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5192,7 +5192,7 @@ struct mlx5_ifc_qp_2rst_out_bits { struct mlx5_ifc_qp_2rst_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5214,7 +5214,7 @@ struct mlx5_ifc_qp_2err_out_bits { struct mlx5_ifc_qp_2err_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5789,7 +5789,7 @@ struct mlx5_ifc_init2rtr_qp_out_bits { struct mlx5_ifc_init2rtr_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5819,7 +5819,7 @@ struct mlx5_ifc_init2init_qp_out_bits { struct mlx5_ifc_init2init_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6230,7 +6230,7 @@ struct mlx5_ifc_destroy_qp_out_bits { struct mlx5_ifc_destroy_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6895,7 +6895,7 @@ struct mlx5_ifc_create_qp_out_bits { struct mlx5_ifc_create_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 4778d41085d4..fbe322c966bc 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -471,6 +471,7 @@ struct mlx5_core_qp { int qpn; struct mlx5_rsc_debug *dbg; int pid; + u16 uid; }; struct mlx5_core_dct { -- cgit v1.2.3 From d269b3afffcb107375d9cf73127fc2e0181bc90b Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:22 +0300 Subject: net/mlx5: Set uid as part of RQ commands Set uid as part of RQ commands so that the firmware can manage the RQ object in a secured way. That will enable using an RQ that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3b6a612787ac..689631ca27b8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5488,7 +5488,7 @@ enum { struct mlx5_ifc_modify_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6164,7 +6164,7 @@ struct mlx5_ifc_destroy_rq_out_bits { struct mlx5_ifc_destroy_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6847,7 +6847,7 @@ struct mlx5_ifc_create_rq_out_bits { struct mlx5_ifc_create_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From 430ae0d5a3ce1350375690cb6ab29ab6fae4a9ac Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:23 +0300 Subject: net/mlx5: Set uid as part of SQ commands Set uid as part of SQ commands so that the firmware can manage the SQ object in a secured way. That will enable using an SQ that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 689631ca27b8..72dd1e49a799 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5381,7 +5381,7 @@ struct mlx5_ifc_modify_sq_out_bits { struct mlx5_ifc_modify_sq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6096,7 +6096,7 @@ struct mlx5_ifc_destroy_sq_out_bits { struct mlx5_ifc_destroy_sq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6769,7 +6769,7 @@ struct mlx5_ifc_create_sq_out_bits { struct mlx5_ifc_create_sq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From a0d8c054318976927493ffd26055d9d183c9beec Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:24 +0300 Subject: net/mlx5: Set uid as part of SRQ commands Set uid as part of SRQ commands so that the firmware can manage the SRQ object in a secured way. That will enable using an SRQ that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 22 +++++++++++----------- include/linux/mlx5/srq.h | 1 + 3 files changed, 13 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d885e9f0e054..8fb072aa8671 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -474,6 +474,7 @@ struct mlx5_core_srq { atomic_t refcount; struct completion free; + u16 uid; }; struct mlx5_eq_table { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 72dd1e49a799..85f1237d80db 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5524,7 +5524,7 @@ struct mlx5_ifc_rmp_bitmask_bits { struct mlx5_ifc_modify_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5986,7 +5986,7 @@ struct mlx5_ifc_destroy_xrq_out_bits { struct mlx5_ifc_destroy_xrq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6008,7 +6008,7 @@ struct mlx5_ifc_destroy_xrc_srq_out_bits { struct mlx5_ifc_destroy_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6074,7 +6074,7 @@ struct mlx5_ifc_destroy_srq_out_bits { struct mlx5_ifc_destroy_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6208,7 +6208,7 @@ struct mlx5_ifc_destroy_rmp_out_bits { struct mlx5_ifc_destroy_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6641,7 +6641,7 @@ struct mlx5_ifc_create_xrq_out_bits { struct mlx5_ifc_create_xrq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6665,7 +6665,7 @@ struct mlx5_ifc_create_xrc_srq_out_bits { struct mlx5_ifc_create_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6741,7 +6741,7 @@ struct mlx5_ifc_create_srq_out_bits { struct mlx5_ifc_create_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6871,7 +6871,7 @@ struct mlx5_ifc_create_rmp_out_bits { struct mlx5_ifc_create_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7272,7 +7272,7 @@ enum { struct mlx5_ifc_arm_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7300,7 +7300,7 @@ enum { struct mlx5_ifc_arm_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index 24ff23e27c8a..1b1f3c20c6a3 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -61,6 +61,7 @@ struct mlx5_srq_attr { u32 tm_next_tag; u32 tm_hw_phase_cnt; u32 tm_sw_phase_cnt; + u16 uid; }; struct mlx5_core_dev; -- cgit v1.2.3 From 774ea6eea29025218f75bc94c764df9a641db471 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:25 +0300 Subject: net/mlx5: Set uid as part of DCT commands Set uid as part of DCT commands so that the firmware can manage the DCT object in a secured way. That will enable using a DCT that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 85f1237d80db..62c0592a9fdb 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5918,7 +5918,7 @@ struct mlx5_ifc_drain_dct_out_bits { struct mlx5_ifc_drain_dct_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6382,7 +6382,7 @@ struct mlx5_ifc_destroy_dct_out_bits { struct mlx5_ifc_destroy_dct_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7138,7 +7138,7 @@ struct mlx5_ifc_create_dct_out_bits { struct mlx5_ifc_create_dct_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From bd37197554eb28a7fc38e44e005e303c77f788ed Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 20 Sep 2018 21:35:26 +0300 Subject: net/mlx5: Update mlx5_ifc with DEVX UID bits Add DEVX information to WQ, SRQ, CQ, TIR, TIS, QP, RQ, XRCD, PD, MKEY and MCG. Each object that is created/destroyed/modified via verbs will be stamped with a UID based on its user context. This is already done for DEVX objects commands. This will enable the firmware to enforce the usage of kernel objects from the DEVX flow by validating that the same UID is used and the resources are really related to the same user. The addition of *_valid fields are needed to distinguish how various addresses are passed. For non-DEVX callers, all those fields will be zero. Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 67 +++++++++++++++++++++++++++---------------- 1 file changed, 43 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 62c0592a9fdb..68f4d5f9d929 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1290,7 +1290,9 @@ struct mlx5_ifc_wq_bits { u8 reserved_at_118[0x3]; u8 log_wq_sz[0x5]; - u8 reserved_at_120[0x3]; + u8 dbr_umem_valid[0x1]; + u8 wq_umem_valid[0x1]; + u8 reserved_at_122[0x1]; u8 log_hairpin_num_packets[0x5]; u8 reserved_at_128[0x3]; u8 log_hairpin_data_sz[0x5]; @@ -2364,7 +2366,10 @@ struct mlx5_ifc_qpc_bits { u8 dc_access_key[0x40]; - u8 reserved_at_680[0xc0]; + u8 reserved_at_680[0x3]; + u8 dbr_umem_valid[0x1]; + + u8 reserved_at_684[0xbc]; }; struct mlx5_ifc_roce_addr_layout_bits { @@ -2464,7 +2469,7 @@ struct mlx5_ifc_xrc_srqc_bits { u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 reserved_at_22[0x1]; + u8 dbr_umem_valid[0x1]; u8 rlky[0x1]; u8 basic_cyclic_rcv_wqe[0x1]; u8 log_rq_stride[0x3]; @@ -3128,7 +3133,9 @@ enum { struct mlx5_ifc_cqc_bits { u8 status[0x4]; - u8 reserved_at_4[0x4]; + u8 reserved_at_4[0x2]; + u8 dbr_umem_valid[0x1]; + u8 reserved_at_7[0x1]; u8 cqe_sz[0x3]; u8 cc[0x1]; u8 reserved_at_c[0x1]; @@ -5314,7 +5321,7 @@ struct mlx5_ifc_modify_tis_bitmask_bits { struct mlx5_ifc_modify_tis_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5353,7 +5360,7 @@ struct mlx5_ifc_modify_tir_out_bits { struct mlx5_ifc_modify_tir_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5454,7 +5461,7 @@ struct mlx5_ifc_rqt_bitmask_bits { struct mlx5_ifc_modify_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5641,7 +5648,10 @@ struct mlx5_ifc_modify_cq_in_bits { struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_at_280[0x600]; + u8 reserved_at_280[0x40]; + + u8 cq_umem_valid[0x1]; + u8 reserved_at_2c1[0x5bf]; u8 pas[0][0x40]; }; @@ -5962,7 +5972,7 @@ struct mlx5_ifc_detach_from_mcg_out_bits { struct mlx5_ifc_detach_from_mcg_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6030,7 +6040,7 @@ struct mlx5_ifc_destroy_tis_out_bits { struct mlx5_ifc_destroy_tis_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6052,7 +6062,7 @@ struct mlx5_ifc_destroy_tir_out_bits { struct mlx5_ifc_destroy_tir_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6142,7 +6152,7 @@ struct mlx5_ifc_destroy_rqt_out_bits { struct mlx5_ifc_destroy_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6507,7 +6517,7 @@ struct mlx5_ifc_dealloc_xrcd_out_bits { struct mlx5_ifc_dealloc_xrcd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6595,7 +6605,7 @@ struct mlx5_ifc_dealloc_pd_out_bits { struct mlx5_ifc_dealloc_pd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6674,7 +6684,9 @@ struct mlx5_ifc_create_xrc_srq_in_bits { struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_at_280[0x600]; + u8 reserved_at_280[0x40]; + u8 xrc_srq_umem_valid[0x1]; + u8 reserved_at_2c1[0x5bf]; u8 pas[0][0x40]; }; @@ -6693,7 +6705,7 @@ struct mlx5_ifc_create_tis_out_bits { struct mlx5_ifc_create_tis_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6717,7 +6729,7 @@ struct mlx5_ifc_create_tir_out_bits { struct mlx5_ifc_create_tir_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6823,7 +6835,7 @@ struct mlx5_ifc_create_rqt_out_bits { struct mlx5_ifc_create_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6908,7 +6920,10 @@ struct mlx5_ifc_create_qp_in_bits { struct mlx5_ifc_qpc_bits qpc; - u8 reserved_at_800[0x80]; + u8 reserved_at_800[0x60]; + + u8 wq_umem_valid[0x1]; + u8 reserved_at_861[0x1f]; u8 pas[0][0x40]; }; @@ -6970,7 +6985,8 @@ struct mlx5_ifc_create_mkey_in_bits { u8 reserved_at_40[0x20]; u8 pg_access[0x1]; - u8 reserved_at_61[0x1f]; + u8 mkey_umem_valid[0x1]; + u8 reserved_at_62[0x1e]; struct mlx5_ifc_mkc_bits memory_key_mkey_entry; @@ -7173,7 +7189,10 @@ struct mlx5_ifc_create_cq_in_bits { struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_at_280[0x600]; + u8 reserved_at_280[0x60]; + + u8 cq_umem_valid[0x1]; + u8 reserved_at_2e1[0x59f]; u8 pas[0][0x40]; }; @@ -7221,7 +7240,7 @@ struct mlx5_ifc_attach_to_mcg_out_bits { struct mlx5_ifc_attach_to_mcg_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7348,7 +7367,7 @@ struct mlx5_ifc_alloc_xrcd_out_bits { struct mlx5_ifc_alloc_xrcd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7436,7 +7455,7 @@ struct mlx5_ifc_alloc_pd_out_bits { struct mlx5_ifc_alloc_pd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From 2a6db719c92dbfe43c9eea7e4358ea2e51b5004e Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 10 Sep 2018 19:19:16 +0530 Subject: iommu/of: make of_pci_map_rid() available for other devices too iommu-map property is also used by devices with fsl-mc. This patch moves the of_pci_map_rid to generic location, so that it can be used by other busses too. 'of_pci_map_rid' is renamed here to 'of_map_rid' and there is no functional change done in the API. Signed-off-by: Nipun Gupta Reviewed-by: Rob Herring Reviewed-by: Robin Murphy Acked-by: Bjorn Helgaas Signed-off-by: Joerg Roedel --- include/linux/of.h | 11 +++++++++++ include/linux/of_pci.h | 10 ---------- 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..bf577ca3c8e7 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -550,6 +550,10 @@ bool of_console_check(struct device_node *dn, char *name, int index); extern int of_cpu_node_to_id(struct device_node *np); +int of_map_rid(struct device_node *np, u32 rid, + const char *map_name, const char *map_mask_name, + struct device_node **target, u32 *id_out); + #else /* CONFIG_OF */ static inline void of_core_init(void) @@ -952,6 +956,13 @@ static inline int of_cpu_node_to_id(struct device_node *np) return -ENODEV; } +static inline int of_map_rid(struct device_node *np, u32 rid, + const char *map_name, const char *map_mask_name, + struct device_node **target, u32 *id_out) +{ + return -EINVAL; +} + #define of_match_ptr(_ptr) NULL #define of_match_node(_matches, _node) NULL #endif /* CONFIG_OF */ diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index e83d87fc5673..21a89c4880fa 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -14,9 +14,6 @@ struct device_node *of_pci_find_child_device(struct device_node *parent, unsigned int devfn); int of_pci_get_devfn(struct device_node *np); void of_pci_check_probe_only(void); -int of_pci_map_rid(struct device_node *np, u32 rid, - const char *map_name, const char *map_mask_name, - struct device_node **target, u32 *id_out); #else static inline struct device_node *of_pci_find_child_device(struct device_node *parent, unsigned int devfn) @@ -29,13 +26,6 @@ static inline int of_pci_get_devfn(struct device_node *np) return -EINVAL; } -static inline int of_pci_map_rid(struct device_node *np, u32 rid, - const char *map_name, const char *map_mask_name, - struct device_node **target, u32 *id_out) -{ - return -EINVAL; -} - static inline void of_pci_check_probe_only(void) { } #endif -- cgit v1.2.3 From eab03e2a1a3d9d354943aff5ae5e4254ee1ec967 Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 10 Sep 2018 19:19:18 +0530 Subject: iommu/arm-smmu: Add support for the fsl-mc bus Implement bus specific support for the fsl-mc bus including registering arm_smmu_ops and bus specific device add operations. Signed-off-by: Nipun Gupta Reviewed-by: Robin Murphy Signed-off-by: Joerg Roedel --- include/linux/fsl/mc.h | 8 ++++++++ include/linux/iommu.h | 2 ++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index f27cb14088a4..dddaca17d684 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -351,6 +351,14 @@ int mc_send_command(struct fsl_mc_io *mc_io, struct fsl_mc_command *cmd); #define dev_is_fsl_mc(_dev) (0) #endif +/* Macro to check if a device is a container device */ +#define fsl_mc_is_cont_dev(_dev) (to_fsl_mc_device(_dev)->flags & \ + FSL_MC_IS_DPRC) + +/* Macro to get the container device of a MC device */ +#define fsl_mc_cont_dev(_dev) (fsl_mc_is_cont_dev(_dev) ? \ + (_dev) : (_dev)->parent) + /* * module_fsl_mc_driver() - Helper macro for drivers that don't do * anything special in module init/exit. This eliminates a lot of diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 87994c265bf5..70102df4b994 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -377,6 +377,8 @@ static inline void iommu_tlb_sync(struct iommu_domain *domain) extern struct iommu_group *pci_device_group(struct device *dev); /* Generic device grouping function */ extern struct iommu_group *generic_device_group(struct device *dev); +/* FSL-MC device grouping function */ +struct iommu_group *fsl_mc_device_group(struct device *dev); /** * struct iommu_fwspec - per-device IOMMU instance data -- cgit v1.2.3 From e48d194d1204b19655c1a9d78a67f2f01d2fe432 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 25 Sep 2018 09:54:14 +0200 Subject: gpio: Add comments on single direction chips A patch from Ricardo got me thinking about some gpio chip semantics so let's drop in some comments to make things more clear around that. Cc: Ricardo Ribalda Delgado Cc: Bartosz Golaszewski Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index d8dcd0e44cab..f6b95734073f 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -178,9 +178,13 @@ static inline struct gpio_irq_chip *to_gpio_irq_chip(struct irq_chip *chip) * @free: optional hook for chip-specific deactivation, such as * disabling module power and clock; may sleep * @get_direction: returns direction for signal "offset", 0=out, 1=in, - * (same as GPIOF_DIR_XXX), or negative error + * (same as GPIOF_DIR_XXX), or negative error. + * It is recommended to always implement this function, even on + * input-only or output-only gpio chips. * @direction_input: configures signal "offset" as input, or returns error + * This can be omitted on input-only or output-only gpio chips. * @direction_output: configures signal "offset" as output, or returns error + * This can be omitted on input-only or output-only gpio chips. * @get: returns value for signal "offset", 0=low, 1=high, or negative error * @get_multiple: reads values for multiple signals defined by "mask" and * stores them in "bits", returns 0 on success or negative error -- cgit v1.2.3 From bee60e94a1e20ec0b8ffdafae270731d8fda4551 Mon Sep 17 00:00:00 2001 From: Ganapatrao Kulkarni Date: Wed, 5 Sep 2018 09:57:36 +0530 Subject: iommu/iova: Optimise attempts to allocate iova from 32bit address range As an optimisation for PCI devices, there is always first attempt been made to allocate iova from SAC address range. This will lead to unnecessary attempts, when there are no free ranges available. Adding fix to track recently failed iova address size and allow further attempts, only if requested size is lesser than a failed size. The size is updated when any replenish happens. Reviewed-by: Robin Murphy Signed-off-by: Ganapatrao Kulkarni Signed-off-by: Joerg Roedel --- include/linux/iova.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 928442dda565..0b93bf96693e 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -75,6 +75,7 @@ struct iova_domain { unsigned long granule; /* pfn granularity for this domain */ unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; + unsigned long max32_alloc_size; /* Size of last failed allocation */ struct iova anchor; /* rbtree lookup anchor */ struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ -- cgit v1.2.3 From 6af588fed39178c8e118fcf9cb6664e58a1fbe88 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 12 Sep 2018 16:24:12 +0100 Subject: iommu: Add fast hook for getting DMA domains While iommu_get_domain_for_dev() is the robust way for arbitrary IOMMU API callers to retrieve the domain pointer, for DMA ops domains it doesn't scale well for large systems and multi-queue devices, since the momentary refcount adjustment will lead to exclusive cacheline contention when multiple CPUs are operating in parallel on different mappings for the same device. In the case of DMA ops domains, however, this refcounting is actually unnecessary, since they already imply that the group exists and is managed by platform code and IOMMU internals (by virtue of iommu_group_get_for_dev()) such that a reference will already be held for the lifetime of the device. Thus we can avoid the bottleneck by providing a fast lookup specifically for the DMA code to retrieve the default domain it already knows it has set up - a simple read-only dereference plays much nicer with cache-coherency protocols. Signed-off-by: Robin Murphy Tested-by: Will Deacon Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 87994c265bf5..c783648d4060 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -293,6 +293,7 @@ extern int iommu_attach_device(struct iommu_domain *domain, extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); +extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, -- cgit v1.2.3 From 26b86092c4650311256fa2372ced7e1e17d97d7b Mon Sep 17 00:00:00 2001 From: Sohil Mehta Date: Tue, 11 Sep 2018 17:11:36 -0700 Subject: iommu/vt-d: Relocate struct/function declarations to its header files To reuse the static functions and the struct declarations, move them to corresponding header files and export the needed functions. Cc: Lu Baolu Cc: Fenghua Yu Cc: Jacob Pan Cc: Ashok Raj Reviewed-by: Andy Shevchenko Signed-off-by: Gayatri Kammela Signed-off-by: Sohil Mehta Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 28004d74ae04..b7cf32e8ae1f 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -389,6 +389,33 @@ struct pasid_entry; struct pasid_state_entry; struct page_req_dsc; +/* + * 0: Present + * 1-11: Reserved + * 12-63: Context Ptr (12 - (haw-1)) + * 64-127: Reserved + */ +struct root_entry { + u64 lo; + u64 hi; +}; + +/* + * low 64 bits: + * 0: present + * 1: fault processing disable + * 2-3: translation type + * 12-63: address space root + * high 64 bits: + * 0-2: address width + * 3-6: aval + * 8-23: domain id + */ +struct context_entry { + u64 lo; + u64 hi; +}; + struct dmar_domain { int nid; /* node id */ @@ -559,5 +586,8 @@ extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev); #endif extern const struct attribute_group *intel_iommu_groups[]; +bool context_present(struct context_entry *context); +struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, + u8 devfn, int alloc); #endif -- cgit v1.2.3 From 4a2d80dbadb72b998641af32d8dd4b7b39e72aa0 Mon Sep 17 00:00:00 2001 From: Sohil Mehta Date: Tue, 11 Sep 2018 17:11:37 -0700 Subject: iommu/vt-d: Update register definitions to VT-d 3.0 specification Add new register definitions added in the VT-d 3.0 specification. Also include registers that were missing previously. Cc: Lu Baolu Cc: Fenghua Yu Cc: Jacob Pan Cc: Ashok Raj Cc: Gayatri Kammela Signed-off-by: Sohil Mehta Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index b7cf32e8ae1f..3bdb9aa198af 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -72,6 +72,42 @@ #define DMAR_PEDATA_REG 0xe4 /* Page request event interrupt data register */ #define DMAR_PEADDR_REG 0xe8 /* Page request event interrupt addr register */ #define DMAR_PEUADDR_REG 0xec /* Page request event Upper address register */ +#define DMAR_MTRRCAP_REG 0x100 /* MTRR capability register */ +#define DMAR_MTRRDEF_REG 0x108 /* MTRR default type register */ +#define DMAR_MTRR_FIX64K_00000_REG 0x120 /* MTRR Fixed range registers */ +#define DMAR_MTRR_FIX16K_80000_REG 0x128 +#define DMAR_MTRR_FIX16K_A0000_REG 0x130 +#define DMAR_MTRR_FIX4K_C0000_REG 0x138 +#define DMAR_MTRR_FIX4K_C8000_REG 0x140 +#define DMAR_MTRR_FIX4K_D0000_REG 0x148 +#define DMAR_MTRR_FIX4K_D8000_REG 0x150 +#define DMAR_MTRR_FIX4K_E0000_REG 0x158 +#define DMAR_MTRR_FIX4K_E8000_REG 0x160 +#define DMAR_MTRR_FIX4K_F0000_REG 0x168 +#define DMAR_MTRR_FIX4K_F8000_REG 0x170 +#define DMAR_MTRR_PHYSBASE0_REG 0x180 /* MTRR Variable range registers */ +#define DMAR_MTRR_PHYSMASK0_REG 0x188 +#define DMAR_MTRR_PHYSBASE1_REG 0x190 +#define DMAR_MTRR_PHYSMASK1_REG 0x198 +#define DMAR_MTRR_PHYSBASE2_REG 0x1a0 +#define DMAR_MTRR_PHYSMASK2_REG 0x1a8 +#define DMAR_MTRR_PHYSBASE3_REG 0x1b0 +#define DMAR_MTRR_PHYSMASK3_REG 0x1b8 +#define DMAR_MTRR_PHYSBASE4_REG 0x1c0 +#define DMAR_MTRR_PHYSMASK4_REG 0x1c8 +#define DMAR_MTRR_PHYSBASE5_REG 0x1d0 +#define DMAR_MTRR_PHYSMASK5_REG 0x1d8 +#define DMAR_MTRR_PHYSBASE6_REG 0x1e0 +#define DMAR_MTRR_PHYSMASK6_REG 0x1e8 +#define DMAR_MTRR_PHYSBASE7_REG 0x1f0 +#define DMAR_MTRR_PHYSMASK7_REG 0x1f8 +#define DMAR_MTRR_PHYSBASE8_REG 0x200 +#define DMAR_MTRR_PHYSMASK8_REG 0x208 +#define DMAR_MTRR_PHYSBASE9_REG 0x210 +#define DMAR_MTRR_PHYSMASK9_REG 0x218 +#define DMAR_VCCAP_REG 0xe00 /* Virtual command capability register */ +#define DMAR_VCMD_REG 0xe10 /* Virtual command register */ +#define DMAR_VCRSP_REG 0xe20 /* Virtual command response register */ #define OFFSET_STRIDE (9) -- cgit v1.2.3 From ee2636b8670b1ab2a02a65923a9bef59e9199c37 Mon Sep 17 00:00:00 2001 From: Sohil Mehta Date: Tue, 11 Sep 2018 17:11:38 -0700 Subject: iommu/vt-d: Enable base Intel IOMMU debugfs support Add a new config option CONFIG_INTEL_IOMMU_DEBUGFS and do the base enabling for Intel IOMMU debugfs. Cc: Lu Baolu Cc: Fenghua Yu Cc: Ashok Raj Cc: Jacob Pan Co-Developed-by: Gayatri Kammela Signed-off-by: Gayatri Kammela Reviewed-by: Andy Shevchenko Reviewed-by: Lu Baolu Signed-off-by: Sohil Mehta Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 3bdb9aa198af..b0ae25837361 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -621,6 +621,12 @@ extern int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_ extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev); #endif +#ifdef CONFIG_INTEL_IOMMU_DEBUGFS +void intel_iommu_debugfs_init(void); +#else +static inline void intel_iommu_debugfs_init(void) {} +#endif /* CONFIG_INTEL_IOMMU_DEBUGFS */ + extern const struct attribute_group *intel_iommu_groups[]; bool context_present(struct context_entry *context); struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, -- cgit v1.2.3 From 5131e08cd0f8a3faa30c1cdaf53940d6bce1715a Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 19 Sep 2018 11:12:58 +0100 Subject: iommu: Remove .domain_{get,set}_windows Since these are trivially handled by the .domain_{get,set}_attr callbacks when relevant, we can streamline struct iommu_ops for everyone. Signed-off-by: Robin Murphy Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c783648d4060..c08ba5d2d451 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -181,8 +181,6 @@ struct iommu_resv_region { * @apply_resv_region: Temporary helper call-back for iova reserved ranges * @domain_window_enable: Configure and enable a particular window for a domain * @domain_window_disable: Disable a particular window for a domain - * @domain_set_windows: Set the number of windows for a domain - * @domain_get_windows: Return the number of windows for a domain * @of_xlate: add OF master IDs to iommu grouping * @pgsize_bitmap: bitmap of all possible supported page sizes */ @@ -223,10 +221,6 @@ struct iommu_ops { int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot); void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr); - /* Set the number of windows per domain */ - int (*domain_set_windows)(struct iommu_domain *domain, u32 w_count); - /* Get the number of windows per domain */ - u32 (*domain_get_windows)(struct iommu_domain *domain); int (*of_xlate)(struct device *dev, struct of_phandle_args *args); bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); -- cgit v1.2.3 From c2c729415b2d21329104fecaa86878d295f1041f Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:17:42 -0600 Subject: coresight: platform: Cleanup coresight connection handling The platform code parses the component connections and populates a platform-description of the output connections in arrays of fields (which is never freed). This is later copied in the coresight_register to a newly allocated area, represented by coresight_connection(s). This patch cleans up the code dealing with connections by making use of the "coresight_connection" structure right at the platform code and lets the generic driver simply re-use information provided by the platform. Thus making it reader friendly as well as avoiding the wastage of unused memory. Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index d828a6efe0b1..41e1f4333bf2 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -94,20 +94,15 @@ union coresight_dev_subtype { * @cpu: the CPU a source belongs to. Only applicable for ETM/PTMs. * @name: name of the component as shown under sysfs. * @nr_inport: number of input ports for this component. - * @outports: list of remote endpoint port number. - * @child_names:name of all child components connected to this device. - * @child_ports:child component port number the current component is - connected to. * @nr_outport: number of output ports for this component. + * @conns: Array of nr_outport connections from this component */ struct coresight_platform_data { int cpu; const char *name; int nr_inport; - int *outports; - const char **child_names; - int *child_ports; int nr_outport; + struct coresight_connection *conns; }; /** -- cgit v1.2.3 From 7ec786ad193beb5579223174e119805569a7af3b Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:17:54 -0600 Subject: coresight: perf: Remove reset_buffer call back for sinks Right now we issue an update_buffer() and reset_buffer() call backs in succession when we stop tracing an event. The update_buffer is supposed to check the status of the buffer and make sure the ring buffer is updated with the trace data. And we store information about the size of the data collected only to be consumed by the reset_buffer callback which always follows the update_buffer. This was originally designed for handling future IPs which could trigger a buffer overflow interrupt. This patch gets rid of the reset_buffer callback altogether and performs the actions in update_buffer, making it return the size collected. We can always add the support for handling the overflow interrupt case later. This removes some not-so pretty hack (storing the new head in the size field for snapshot mode) and cleans it up a little bit. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 41e1f4333bf2..8e52682b1e90 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -186,7 +186,6 @@ struct coresight_device { * @alloc_buffer: initialises perf's ring buffer for trace collection. * @free_buffer: release memory allocated in @get_config. * @set_buffer: initialises buffer mechanic before a trace session. - * @reset_buffer: finalises buffer mechanic after a trace session. * @update_buffer: update buffer pointers after a trace session. */ struct coresight_ops_sink { @@ -198,10 +197,7 @@ struct coresight_ops_sink { int (*set_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config); - unsigned long (*reset_buffer)(struct coresight_device *csdev, - struct perf_output_handle *handle, - void *sink_config); - void (*update_buffer)(struct coresight_device *csdev, + unsigned long (*update_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config); }; -- cgit v1.2.3 From 3d6e8935758392179645e1b105789b3da329ad38 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:17:56 -0600 Subject: coresight: perf: Remove set_buffer call back In coresight perf mode, we need to prepare the sink before starting a session, which is done via set_buffer call back. We then proceed to enable the tracing. If we fail to start the session successfully, we leave the sink configuration unchanged. In order to make the operation atomic and to avoid yet another call back to clear the buffer, we get rid of the "set_buffer" call back and pass the buffer details via enable() call back to the sink. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 8e52682b1e90..53535821dc25 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -185,18 +185,14 @@ struct coresight_device { * @disable: disables the sink. * @alloc_buffer: initialises perf's ring buffer for trace collection. * @free_buffer: release memory allocated in @get_config. - * @set_buffer: initialises buffer mechanic before a trace session. * @update_buffer: update buffer pointers after a trace session. */ struct coresight_ops_sink { - int (*enable)(struct coresight_device *csdev, u32 mode); + int (*enable)(struct coresight_device *csdev, u32 mode, void *data); void (*disable)(struct coresight_device *csdev); void *(*alloc_buffer)(struct coresight_device *csdev, int cpu, void **pages, int nr_pages, bool overwrite); void (*free_buffer)(void *config); - int (*set_buffer)(struct coresight_device *csdev, - struct perf_output_handle *handle, - void *sink_config); unsigned long (*update_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config); -- cgit v1.2.3 From 2478a6ae4a6a4c8e3f7e9f6f849dffe92e5238e1 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:18:11 -0600 Subject: coresight: Add support for CLAIM tag protocol Coresight architecture defines CLAIM tags for a device to negotiate control of the components (external agent vs self-hosted). Each device has a pair of registers (CLAIMSET & CLAIMCLR) for managing the CLAIM tags. However, the protocol for the CLAIM tags is IMPLEMENTATION DEFINED. PSCI has recommendations for the use of the CLAIM tags to negotiate controls for external agent vs self-hosted use. This patch implements the recommended protocol by PSCI. The claim/disclaim operations are performed from the device specific drivers. The disadvantage is that the calls are sprinkled in each driver, but this makes the operation much simpler. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 53535821dc25..46c67a764877 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -257,6 +257,13 @@ extern int coresight_enable(struct coresight_device *csdev); extern void coresight_disable(struct coresight_device *csdev); extern int coresight_timeout(void __iomem *addr, u32 offset, int position, int value); + +extern int coresight_claim_device(void __iomem *base); +extern int coresight_claim_device_unlocked(void __iomem *base); + +extern void coresight_disclaim_device(void __iomem *base); +extern void coresight_disclaim_device_unlocked(void __iomem *base); + #else static inline struct coresight_device * coresight_register(struct coresight_desc *desc) { return NULL; } @@ -266,6 +273,19 @@ coresight_enable(struct coresight_device *csdev) { return -ENOSYS; } static inline void coresight_disable(struct coresight_device *csdev) {} static inline int coresight_timeout(void __iomem *addr, u32 offset, int position, int value) { return 1; } +static inline int coresight_claim_device_unlocked(void __iomem *base) +{ + return -EINVAL; +} + +static inline int coresight_claim_device(void __iomem *base) +{ + return -EINVAL; +} + +static inline void coresight_disclaim_device(void __iomem *base) {} +static inline void coresight_disclaim_device_unlocked(void __iomem *base) {} + #endif #ifdef CONFIG_OF -- cgit v1.2.3 From 800b932969c53c4044ff9f9fd1ee793a87fa8ef0 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:15 -0700 Subject: vmbus: pass channel to hv_process_channel_removal Rather than passing relid and then looking up the channel. Pass the channel directly, since caller already knows it. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2c3798bcb01c..6c4575c7f46b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1443,7 +1443,7 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, const int *srv_version, int srv_vercnt, int *nego_fw_version, int *nego_srv_version); -void hv_process_channel_removal(u32 relid); +void hv_process_channel_removal(struct vmbus_channel *channel); void vmbus_setevent(struct vmbus_channel *channel); /* -- cgit v1.2.3 From 52a42c2a90226dc61c99bbd0cb096deeb52c334b Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:16 -0700 Subject: vmbus: keep pointer to ring buffer page Avoid going from struct page to virt address (and back) by just keeping pointer to the allocated pages instead of virt address. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 6c4575c7f46b..a6c32d2d090b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -739,7 +739,7 @@ struct vmbus_channel { u32 ringbuffer_gpadlhandle; /* Allocated memory for ring buffer */ - void *ringbuffer_pages; + struct page *ringbuffer_page; u32 ringbuffer_pagecount; struct hv_ring_buffer_info outbound; /* send to parent */ struct hv_ring_buffer_info inbound; /* receive from parent */ -- cgit v1.2.3 From ae6935ed7d424ffa74d634da00767e7b03c98fd3 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:17 -0700 Subject: vmbus: split ring buffer allocation from open The UIO driver needs the ring buffer to be persistent(reused) across open/close. Split the allocation and setup of ring buffer out of vmbus_open. For normal usage vmbus_open/vmbus_close there are no changes; only impacts uio_hv_generic which needs to keep ring buffer memory and reuse when application restarts. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index a6c32d2d090b..b3e24368930a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -741,6 +741,7 @@ struct vmbus_channel { /* Allocated memory for ring buffer */ struct page *ringbuffer_page; u32 ringbuffer_pagecount; + u32 ringbuffer_send_offset; struct hv_ring_buffer_info outbound; /* send to parent */ struct hv_ring_buffer_info inbound; /* receive from parent */ @@ -1021,6 +1022,14 @@ struct vmbus_packet_mpb_array { struct hv_mpb_array range; } __packed; +int vmbus_alloc_ring(struct vmbus_channel *channel, + u32 send_size, u32 recv_size); +void vmbus_free_ring(struct vmbus_channel *channel); + +int vmbus_connect_ring(struct vmbus_channel *channel, + void (*onchannel_callback)(void *context), + void *context); +int vmbus_disconnect_ring(struct vmbus_channel *channel); extern int vmbus_open(struct vmbus_channel *channel, u32 send_ringbuffersize, -- cgit v1.2.3 From bfddabfa230452cea32aae82f9cd85ab22601acf Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:18 -0700 Subject: uio: introduce UIO_MEM_IOVA Introduce the concept of mapping physical memory locations that are normal memory. The new type UIO_MEM_IOVA are similar to existing UIO_MEM_PHYS but the backing memory is not marked as uncached. Also, indent related switch to the currently used style. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- include/linux/uio_driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 6f8b68cd460f..a3cd7cb67a69 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -133,6 +133,7 @@ extern void uio_event_notify(struct uio_info *info); #define UIO_MEM_PHYS 1 #define UIO_MEM_LOGICAL 2 #define UIO_MEM_VIRTUAL 3 +#define UIO_MEM_IOVA 4 /* defines for uio_port->porttype */ #define UIO_PORT_NONE 0 -- cgit v1.2.3 From 1a0afc14b5da329765d6ecd4a79f546b9363ad8c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 25 Sep 2018 13:16:55 -0700 Subject: Revert "dma-mapping: clear dev->dma_ops in arch_teardown_dma_ops" This reverts commit 46053c73685411915d3de50c5a0045beef32806b. This change breaks architectures setting up dma_ops in their own magic way and not using arch_setup_dma_ops, so revert it. Reported-by: Guenter Roeck Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index bd81e74cca7b..d23fc45c8208 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -665,10 +665,7 @@ static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, #endif #ifndef arch_teardown_dma_ops -static inline void arch_teardown_dma_ops(struct device *dev) -{ - dev->dma_ops = NULL; -} +static inline void arch_teardown_dma_ops(struct device *dev) { } #endif static inline unsigned int dma_get_max_seg_size(struct device *dev) -- cgit v1.2.3 From 6f99528e9797794b91b43321fbbc93fe772b0803 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 24 Sep 2018 19:22:49 +0300 Subject: net: core: netlink: add helper refcount dec and lock function Rtnl lock is encapsulated in netlink and cannot be accessed by other modules directly. This means that reference counted objects that rely on rtnl lock cannot use it with refcounter helper function that atomically releases decrements reference and obtains mutex. This patch implements simple wrapper function around refcount_dec_and_lock that obtains rtnl lock if reference counter value reached 0. Signed-off-by: Vlad Buslov Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 5225832bd6ff..9cdd76348d9a 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -6,6 +6,7 @@ #include #include #include +#include #include extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); @@ -34,6 +35,7 @@ extern void rtnl_unlock(void); extern int rtnl_trylock(void); extern int rtnl_is_locked(void); extern int rtnl_lock_killable(void); +extern bool refcount_dec_and_rtnl_lock(refcount_t *r); extern wait_queue_head_t netdev_unregistering_wq; extern struct rw_semaphore pernet_ops_rwsem; -- cgit v1.2.3 From 3a7d0d07a386716b459b00783b11a8211cefcc0f Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 24 Sep 2018 19:22:51 +0300 Subject: net: sched: extend Qdisc with rcu Currently, Qdisc API functions assume that users have rtnl lock taken. To implement rtnl unlocked classifiers update interface, Qdisc API must be extended with functions that do not require rtnl lock. Extend Qdisc structure with rcu. Implement special version of put function qdisc_put_unlocked() that is called without rtnl lock taken. This function only takes rtnl lock if Qdisc reference counter reached zero and is intended to be used as optimization. Signed-off-by: Vlad Buslov Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 9cdd76348d9a..bb9cb84114c1 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -85,6 +85,11 @@ static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev) return rtnl_dereference(dev->ingress_queue); } +static inline struct netdev_queue *dev_ingress_queue_rcu(struct net_device *dev) +{ + return rcu_dereference(dev->ingress_queue); +} + struct netdev_queue *dev_ingress_queue_create(struct net_device *dev); #ifdef CONFIG_NET_INGRESS -- cgit v1.2.3 From 76582671eb5d006a78420776cc5f73195b867e81 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Wed, 12 Sep 2018 12:38:36 -0700 Subject: firmware: xilinx: Add Zynqmp firmware driver This patch is adding communication layer with firmware. Firmware driver provides an interface to firmware APIs. Interface APIs can be used by any driver to communicate to PMUFW(Platform Management Unit). All requests go through ATF. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Signed-off-by: Michal Simek --- include/linux/firmware/xlnx-zynqmp.h | 63 ++++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) create mode 100644 include/linux/firmware/xlnx-zynqmp.h (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h new file mode 100644 index 000000000000..cb63bedf3dcf --- /dev/null +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Xilinx Zynq MPSoC Firmware layer + * + * Copyright (C) 2014-2018 Xilinx + * + * Michal Simek + * Davorin Mista + * Jolly Shah + * Rajan Vaja + */ + +#ifndef __FIRMWARE_ZYNQMP_H__ +#define __FIRMWARE_ZYNQMP_H__ + +#define ZYNQMP_PM_VERSION_MAJOR 1 +#define ZYNQMP_PM_VERSION_MINOR 0 + +#define ZYNQMP_PM_VERSION ((ZYNQMP_PM_VERSION_MAJOR << 16) | \ + ZYNQMP_PM_VERSION_MINOR) + +#define ZYNQMP_TZ_VERSION_MAJOR 1 +#define ZYNQMP_TZ_VERSION_MINOR 0 + +#define ZYNQMP_TZ_VERSION ((ZYNQMP_TZ_VERSION_MAJOR << 16) | \ + ZYNQMP_TZ_VERSION_MINOR) + +/* SMC SIP service Call Function Identifier Prefix */ +#define PM_SIP_SVC 0xC2000000 +#define PM_GET_TRUSTZONE_VERSION 0xa03 + +/* Number of 32bits values in payload */ +#define PAYLOAD_ARG_CNT 4U + +enum pm_api_id { + PM_GET_API_VERSION = 1, +}; + +/* PMU-FW return status codes */ +enum pm_ret_status { + XST_PM_SUCCESS = 0, + XST_PM_INTERNAL = 2000, + XST_PM_CONFLICT, + XST_PM_NO_ACCESS, + XST_PM_INVALID_NODE, + XST_PM_DOUBLE_REQ, + XST_PM_ABORT_SUSPEND, +}; + +struct zynqmp_eemi_ops { + int (*get_api_version)(u32 *version); +}; + +#if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) +const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); +#else +static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) +{ + return NULL; +} +#endif + +#endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 59ecdd778879f171072b663f91de6c3a595e2ed4 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Wed, 12 Sep 2018 12:38:37 -0700 Subject: firmware: xilinx: Add query data API Add ZynqMP firmware query data API to query platform specific information(clocks, pins) from firmware. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Signed-off-by: Michal Simek --- include/linux/firmware/xlnx-zynqmp.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index cb63bedf3dcf..287f42caa623 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -34,6 +34,7 @@ enum pm_api_id { PM_GET_API_VERSION = 1, + PM_QUERY_DATA = 35, }; /* PMU-FW return status codes */ @@ -47,8 +48,27 @@ enum pm_ret_status { XST_PM_ABORT_SUSPEND, }; +enum pm_query_id { + PM_QID_INVALID, +}; + +/** + * struct zynqmp_pm_query_data - PM query data + * @qid: query ID + * @arg1: Argument 1 of query data + * @arg2: Argument 2 of query data + * @arg3: Argument 3 of query data + */ +struct zynqmp_pm_query_data { + u32 qid; + u32 arg1; + u32 arg2; + u32 arg3; +}; + struct zynqmp_eemi_ops { int (*get_api_version)(u32 *version); + int (*query_data)(struct zynqmp_pm_query_data qdata, u32 *out); }; #if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) -- cgit v1.2.3 From f9627312e20721681ea326bd2b7935bf8034b288 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Wed, 12 Sep 2018 12:38:38 -0700 Subject: firmware: xilinx: Add clock APIs Add clock APIs to control clocks through firmware interface. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Signed-off-by: Michal Simek --- include/linux/firmware/xlnx-zynqmp.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 287f42caa623..015e130431e6 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -35,6 +35,15 @@ enum pm_api_id { PM_GET_API_VERSION = 1, PM_QUERY_DATA = 35, + PM_CLOCK_ENABLE, + PM_CLOCK_DISABLE, + PM_CLOCK_GETSTATE, + PM_CLOCK_SETDIVIDER, + PM_CLOCK_GETDIVIDER, + PM_CLOCK_SETRATE, + PM_CLOCK_GETRATE, + PM_CLOCK_SETPARENT, + PM_CLOCK_GETPARENT, }; /* PMU-FW return status codes */ @@ -48,8 +57,20 @@ enum pm_ret_status { XST_PM_ABORT_SUSPEND, }; +enum pm_ioctl_id { + IOCTL_SET_PLL_FRAC_MODE = 8, + IOCTL_GET_PLL_FRAC_MODE, + IOCTL_SET_PLL_FRAC_DATA, + IOCTL_GET_PLL_FRAC_DATA, +}; + enum pm_query_id { PM_QID_INVALID, + PM_QID_CLOCK_GET_NAME, + PM_QID_CLOCK_GET_TOPOLOGY, + PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS, + PM_QID_CLOCK_GET_PARENTS, + PM_QID_CLOCK_GET_ATTRIBUTES, }; /** @@ -69,6 +90,15 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*get_api_version)(u32 *version); int (*query_data)(struct zynqmp_pm_query_data qdata, u32 *out); + int (*clock_enable)(u32 clock_id); + int (*clock_disable)(u32 clock_id); + int (*clock_getstate)(u32 clock_id, u32 *state); + int (*clock_setdivider)(u32 clock_id, u32 divider); + int (*clock_getdivider)(u32 clock_id, u32 *divider); + int (*clock_setrate)(u32 clock_id, u64 rate); + int (*clock_getrate)(u32 clock_id, u64 *rate); + int (*clock_setparent)(u32 clock_id, u32 parent_id); + int (*clock_getparent)(u32 clock_id, u32 *parent_id); }; #if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) -- cgit v1.2.3 From 2ba3c43f09c50eb1c0472decdfba71010d8694dc Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Tue, 4 Sep 2018 15:47:17 +0530 Subject: phy: qcom-ufs: Remove stale methods that handle ref clk Remove ufs_qcom_phy_enable/(disable)_dev_ref_clk() that are not being used by any code. Signed-off-by: Vivek Gautam Reviewed-by: Bjorn Andersson Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy-qcom-ufs.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy/phy-qcom-ufs.h b/include/linux/phy/phy-qcom-ufs.h index 0a2c18a9771d..9dd85071bcce 100644 --- a/include/linux/phy/phy-qcom-ufs.h +++ b/include/linux/phy/phy-qcom-ufs.h @@ -17,20 +17,6 @@ #include "phy.h" -/** - * ufs_qcom_phy_enable_dev_ref_clk() - Enable the device - * ref clock. - * @phy: reference to a generic phy. - */ -void ufs_qcom_phy_enable_dev_ref_clk(struct phy *phy); - -/** - * ufs_qcom_phy_disable_dev_ref_clk() - Disable the device - * ref clock. - * @phy: reference to a generic phy. - */ -void ufs_qcom_phy_disable_dev_ref_clk(struct phy *phy); - int ufs_qcom_phy_set_tx_lane_enable(struct phy *phy, u32 tx_lanes); void ufs_qcom_phy_save_controller_version(struct phy *phy, u8 major, u16 minor, u16 step); -- cgit v1.2.3 From 1e1e465c6d23aa7d1858eb2894408f15770af16c Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Tue, 4 Sep 2018 15:47:18 +0530 Subject: scsi/ufs: qcom: Remove ufs_qcom_phy_*() calls from host The host makes direct calls into phy using ufs_qcom_phy_*() APIs. These APIs are only defined for 20nm qcom-ufs-qmp phy which is not being used by any architecture as yet. Future architectures too are not going to use 20nm ufs phy. So remove these ufs_qcom_phy_*() calls from host to let further change declare the 20nm phy as broken. Also remove couple of stale enum defines for ufs phy. Signed-off-by: Vivek Gautam Acked-by: Martin K. Petersen Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy-qcom-ufs.h | 24 ------------------------ 1 file changed, 24 deletions(-) delete mode 100644 include/linux/phy/phy-qcom-ufs.h (limited to 'include/linux') diff --git a/include/linux/phy/phy-qcom-ufs.h b/include/linux/phy/phy-qcom-ufs.h deleted file mode 100644 index 9dd85071bcce..000000000000 --- a/include/linux/phy/phy-qcom-ufs.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * Copyright (c) 2013-2015, Linux Foundation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 and - * only version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -#ifndef PHY_QCOM_UFS_H_ -#define PHY_QCOM_UFS_H_ - -#include "phy.h" - -int ufs_qcom_phy_set_tx_lane_enable(struct phy *phy, u32 tx_lanes); -void ufs_qcom_phy_save_controller_version(struct phy *phy, - u8 major, u16 minor, u16 step); - -#endif /* PHY_QCOM_UFS_H_ */ -- cgit v1.2.3 From 71e0940d52e107748b270213a01d3b1546657d74 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 21 Sep 2018 09:32:44 -0700 Subject: efi: honour memory reservations passed via a linux specific config table In order to allow the OS to reserve memory persistently across a kexec, introduce a Linux-specific UEFI configuration table that points to the head of a linked list in memory, allowing each kernel to add list items describing memory regions that the next kernel should treat as reserved. This is useful, e.g., for GICv3 based ARM systems that cannot disable DMA access to the LPI tables, forcing them to reuse the same memory region again after a kexec reboot. Tested-by: Jeremy Linton Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 401e4b254e30..a5cb580472c5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -672,6 +672,7 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_LOADER_ENTRY_GUID EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf, 0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f) #define LINUX_EFI_RANDOM_SEED_TABLE_GUID EFI_GUID(0x1ce1e5bc, 0x7ceb, 0x42f2, 0x81, 0xe5, 0x8a, 0xad, 0xf1, 0x80, 0xf5, 0x7b) #define LINUX_EFI_TPM_EVENT_LOG_GUID EFI_GUID(0xb7799cb0, 0xeca2, 0x4943, 0x96, 0x67, 0x1f, 0xae, 0x07, 0xb7, 0x47, 0xfa) +#define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) typedef struct { efi_guid_t guid; @@ -957,6 +958,7 @@ extern struct efi { unsigned long mem_attr_table; /* memory attributes table */ unsigned long rng_seed; /* UEFI firmware random seed */ unsigned long tpm_log; /* TPM2 Event Log table */ + unsigned long mem_reserve; /* Linux EFI memreserve table */ efi_get_time_t *get_time; efi_set_time_t *set_time; efi_get_wakeup_time_t *get_wakeup_time; @@ -1662,4 +1664,10 @@ extern int efi_tpm_eventlog_init(void); /* Workqueue to queue EFI Runtime Services */ extern struct workqueue_struct *efi_rts_wq; +struct linux_efi_memreserve { + phys_addr_t next; + phys_addr_t base; + phys_addr_t size; +}; + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From a23d3bb05ccbd815c79293d2207fedede0b3515d Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 21 Sep 2018 09:32:46 -0700 Subject: efi: add API to reserve memory persistently across kexec reboot Add kernel plumbing to reserve memory regions persistently on a EFI system by adding entries to the MEMRESERVE linked list. Tested-by: Jeremy Linton Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index a5cb580472c5..22e4de9d3700 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1043,6 +1043,7 @@ extern int __init efi_uart_console_only (void); extern u64 efi_mem_desc_end(efi_memory_desc_t *md); extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md); extern void efi_mem_reserve(phys_addr_t addr, u64 size); +extern int efi_mem_reserve_persistent(phys_addr_t addr, u64 size); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource, struct resource *bss_resource); extern void efi_reserve_boot_services(void); -- cgit v1.2.3 From 9dbbedaa6171247c4c7c40b83f05b200a117c2e0 Mon Sep 17 00:00:00 2001 From: Sai Praneeth Date: Tue, 11 Sep 2018 12:15:21 -0700 Subject: efi: Make efi_rts_work accessible to efi page fault handler After the kernel has booted, if any accesses by firmware causes a page fault, the efi page fault handler would freeze efi_rts_wq and schedules a new process. To do this, the efi page fault handler needs efi_rts_work. Hence, make it accessible. There will be no race conditions in accessing this structure, because all the calls to efi runtime services are already serialized. Tested-by: Bhupesh Sharma Suggested-by: Matt Fleming Based-on-code-from: Ricardo Neri Signed-off-by: Sai Praneeth Prakhya Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 22e4de9d3700..a929d2bf41fa 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1662,6 +1662,42 @@ struct linux_efi_tpm_eventlog { extern int efi_tpm_eventlog_init(void); +/* efi_runtime_service() function identifiers */ +enum efi_rts_ids { + GET_TIME, + SET_TIME, + GET_WAKEUP_TIME, + SET_WAKEUP_TIME, + GET_VARIABLE, + GET_NEXT_VARIABLE, + SET_VARIABLE, + QUERY_VARIABLE_INFO, + GET_NEXT_HIGH_MONO_COUNT, + UPDATE_CAPSULE, + QUERY_CAPSULE_CAPS, +}; + +/* + * efi_runtime_work: Details of EFI Runtime Service work + * @arg<1-5>: EFI Runtime Service function arguments + * @status: Status of executing EFI Runtime Service + * @efi_rts_id: EFI Runtime Service function identifier + * @efi_rts_comp: Struct used for handling completions + */ +struct efi_runtime_work { + void *arg1; + void *arg2; + void *arg3; + void *arg4; + void *arg5; + efi_status_t status; + struct work_struct work; + enum efi_rts_ids efi_rts_id; + struct completion efi_rts_comp; +}; + +extern struct efi_runtime_work efi_rts_work; + /* Workqueue to queue EFI Runtime Services */ extern struct workqueue_struct *efi_rts_wq; -- cgit v1.2.3 From 3425d934fc0312f62024163736a7afe4de20c10f Mon Sep 17 00:00:00 2001 From: Sai Praneeth Date: Tue, 11 Sep 2018 12:15:22 -0700 Subject: efi/x86: Handle page faults occurring while running EFI runtime services Memory accesses performed by UEFI runtime services should be limited to: - reading/executing from EFI_RUNTIME_SERVICES_CODE memory regions - reading/writing from/to EFI_RUNTIME_SERVICES_DATA memory regions - reading/writing by-ref arguments - reading/writing from/to the stack. Accesses outside these regions may cause the kernel to hang because the memory region requested by the firmware isn't mapped in efi_pgd, which causes a page fault in ring 0 and the kernel fails to handle it, leading to die(). To save kernel from hanging, add an EFI specific page fault handler which recovers from such faults by 1. If the efi runtime service is efi_reset_system(), reboot the machine through BIOS. 2. If the efi runtime service is _not_ efi_reset_system(), then freeze efi_rts_wq and schedule a new process. The EFI page fault handler offers us two advantages: 1. Avoid potential hangs caused by buggy firmware. 2. Shout loud that the firmware is buggy and hence is not a kernel bug. Tested-by: Bhupesh Sharma Suggested-by: Matt Fleming Based-on-code-from: Ricardo Neri Signed-off-by: Sai Praneeth Prakhya Reviewed-by: Thomas Gleixner [ardb: clarify commit log] Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index a929d2bf41fa..845174e113ce 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1662,8 +1662,13 @@ struct linux_efi_tpm_eventlog { extern int efi_tpm_eventlog_init(void); -/* efi_runtime_service() function identifiers */ +/* + * efi_runtime_service() function identifiers. + * "NONE" is used by efi_recover_from_page_fault() to check if the page + * fault happened while executing an efi runtime service. + */ enum efi_rts_ids { + NONE, GET_TIME, SET_TIME, GET_WAKEUP_TIME, @@ -1673,6 +1678,7 @@ enum efi_rts_ids { SET_VARIABLE, QUERY_VARIABLE_INFO, GET_NEXT_HIGH_MONO_COUNT, + RESET_SYSTEM, UPDATE_CAPSULE, QUERY_CAPSULE_CAPS, }; -- cgit v1.2.3 From dbfe2953f63c640463c630746cd5d9de8b2f63ae Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Tue, 25 Sep 2018 14:38:18 +0200 Subject: x86/speculation: Apply IBPB more strictly to avoid cross-process data leak Currently, IBPB is only issued in cases when switching into a non-dumpable process, the rationale being to protect such 'important and security sensitive' processess (such as GPG) from data leaking into a different userspace process via spectre v2. This is however completely insufficient to provide proper userspace-to-userpace spectrev2 protection, as any process can poison branch buffers before being scheduled out, and the newly scheduled process immediately becomes spectrev2 victim. In order to minimize the performance impact (for usecases that do require spectrev2 protection), issue the barrier only in cases when switching between processess where the victim can't be ptraced by the potential attacker (as in such cases, the attacker doesn't have to bother with branch buffers at all). [ tglx: Split up PTRACE_MODE_NOACCESS_CHK into PTRACE_MODE_SCHED and PTRACE_MODE_IBPB to be able to do ptrace() context tracking reasonably fine-grained ] Fixes: 18bf3c3ea8 ("x86/speculation: Use Indirect Branch Prediction Barrier in context switch") Originally-by: Tim Chen Signed-off-by: Jiri Kosina Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: "WoodhouseDavid" Cc: Andi Kleen Cc: "SchauflerCasey" Link: https://lkml.kernel.org/r/nycvar.YFH.7.76.1809251437340.15880@cbobk.fhfr.pm --- include/linux/ptrace.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 4f36431c380b..e5e5ef513df3 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -62,14 +62,17 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 #define PTRACE_MODE_ATTACH 0x02 #define PTRACE_MODE_NOAUDIT 0x04 -#define PTRACE_MODE_FSCREDS 0x08 -#define PTRACE_MODE_REALCREDS 0x10 +#define PTRACE_MODE_FSCREDS 0x08 +#define PTRACE_MODE_REALCREDS 0x10 +#define PTRACE_MODE_SCHED 0x20 +#define PTRACE_MODE_IBPB 0x40 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) +#define PTRACE_MODE_SPEC_IBPB (PTRACE_MODE_ATTACH_REALCREDS | PTRACE_MODE_IBPB) /** * ptrace_may_access - check whether the caller is permitted to access @@ -87,6 +90,20 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); +/** + * ptrace_may_access - check whether the caller is permitted to access + * a target task. + * @task: target task + * @mode: selects type of access and caller credentials + * + * Returns true on success, false on denial. + * + * Similar to ptrace_may_access(). Only to be called from context switch + * code. Does not call into audit and the regular LSM hooks due to locking + * constraints. + */ +extern bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode); + static inline int ptrace_reparented(struct task_struct *child) { return !same_thread_group(child->real_parent, child->parent); -- cgit v1.2.3 From bca6b067b0b269a7b8ba129e2a918309ca8b4a55 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 26 Sep 2018 14:01:03 -0700 Subject: block: Move power management code into a new source file Move the code for runtime power management from blk-core.c into the new source file blk-pm.c. Move the corresponding declarations from into . For CONFIG_PM=n, leave out the declarations of the functions that are not used in that mode. This patch not only reduces the number of #ifdefs in the block layer core code but also reduces the size of header file and hence should help to reduce the build time of the Linux kernel if CONFIG_PM is not defined. Signed-off-by: Bart Van Assche Reviewed-by: Ming Lei Reviewed-by: Christoph Hellwig Cc: Jianchao Wang Cc: Hannes Reinecke Cc: Johannes Thumshirn Cc: Alan Stern Signed-off-by: Jens Axboe --- include/linux/blk-pm.h | 24 ++++++++++++++++++++++++ include/linux/blkdev.h | 23 ----------------------- 2 files changed, 24 insertions(+), 23 deletions(-) create mode 100644 include/linux/blk-pm.h (limited to 'include/linux') diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h new file mode 100644 index 000000000000..b80c65aba249 --- /dev/null +++ b/include/linux/blk-pm.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _BLK_PM_H_ +#define _BLK_PM_H_ + +struct device; +struct request_queue; + +/* + * block layer runtime pm functions + */ +#ifdef CONFIG_PM +extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); +extern int blk_pre_runtime_suspend(struct request_queue *q); +extern void blk_post_runtime_suspend(struct request_queue *q, int err); +extern void blk_pre_runtime_resume(struct request_queue *q); +extern void blk_post_runtime_resume(struct request_queue *q, int err); +extern void blk_set_runtime_active(struct request_queue *q); +#else +static inline void blk_pm_runtime_init(struct request_queue *q, + struct device *dev) {} +#endif + +#endif /* _BLK_PM_H_ */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1d5e14139795..cd863511dedb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1280,29 +1280,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); -/* - * block layer runtime pm functions - */ -#ifdef CONFIG_PM -extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); -extern int blk_pre_runtime_suspend(struct request_queue *q); -extern void blk_post_runtime_suspend(struct request_queue *q, int err); -extern void blk_pre_runtime_resume(struct request_queue *q); -extern void blk_post_runtime_resume(struct request_queue *q, int err); -extern void blk_set_runtime_active(struct request_queue *q); -#else -static inline void blk_pm_runtime_init(struct request_queue *q, - struct device *dev) {} -static inline int blk_pre_runtime_suspend(struct request_queue *q) -{ - return -ENOSYS; -} -static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {} -static inline void blk_pre_runtime_resume(struct request_queue *q) {} -static inline void blk_post_runtime_resume(struct request_queue *q, int err) {} -static inline void blk_set_runtime_active(struct request_queue *q) {} -#endif - /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests -- cgit v1.2.3 From cd84a62e0078dce09f4ed349bec84f86c9d54b30 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 26 Sep 2018 14:01:04 -0700 Subject: block, scsi: Change the preempt-only flag into a counter The RQF_PREEMPT flag is used for three purposes: - In the SCSI core, for making sure that power management requests are executed even if a device is in the "quiesced" state. - For domain validation by SCSI drivers that use the parallel port. - In the IDE driver, for IDE preempt requests. Rename "preempt-only" into "pm-only" because the primary purpose of this mode is power management. Since the power management core may but does not have to resume a runtime suspended device before performing system-wide suspend and since a later patch will set "pm-only" mode as long as a block device is runtime suspended, make it possible to set "pm-only" mode from more than one context. Since with this change scsi_device_quiesce() is no longer idempotent, make that function return early if it is called for a quiesced queue. Signed-off-by: Bart Van Assche Acked-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Ming Lei Cc: Jianchao Wang Cc: Johannes Thumshirn Cc: Alan Stern Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cd863511dedb..13bb54f26736 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -504,6 +504,12 @@ struct request_queue { * various queue flags, see QUEUE_* below */ unsigned long queue_flags; + /* + * Number of contexts that have called blk_set_pm_only(). If this + * counter is above zero then only RQF_PM and RQF_PREEMPT requests are + * processed. + */ + atomic_t pm_only; /* * ida allocated id for this queue. Used to index queues from @@ -698,7 +704,6 @@ struct request_queue { #define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ -#define QUEUE_FLAG_PREEMPT_ONLY 29 /* only process REQ_PREEMPT requests */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ @@ -736,12 +741,11 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) -#define blk_queue_preempt_only(q) \ - test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags) +#define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) -extern int blk_set_preempt_only(struct request_queue *q); -extern void blk_clear_preempt_only(struct request_queue *q); +extern void blk_set_pm_only(struct request_queue *q); +extern void blk_clear_pm_only(struct request_queue *q); static inline int queue_in_flight(struct request_queue *q) { -- cgit v1.2.3 From 18c9a6bbe0645a05172a900740b9d2d379d54320 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 26 Sep 2018 14:01:07 -0700 Subject: percpu-refcount: Introduce percpu_ref_resurrect() This function will be used in a later patch to switch the struct request_queue q_usage_counter from killed back to live. In contrast to percpu_ref_reinit(), this new function does not require that the refcount is zero. Signed-off-by: Bart Van Assche Acked-by: Tejun Heo Reviewed-by: Ming Lei Cc: Christoph Hellwig Cc: Jianchao Wang Cc: Hannes Reinecke Cc: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/percpu-refcount.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 009cdf3d65b6..b297cd1cd4f1 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -108,6 +108,7 @@ void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); +void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); /** -- cgit v1.2.3 From 6194114324139dc16f3251c67ed853bd6d4ae056 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 24 Sep 2018 21:58:59 +0200 Subject: net: core: add member wol_enabled to struct net_device Add flag wol_enabled to struct net_device indicating whether Wake-on-LAN is enabled. As first user phy_suspend() will use it to decide whether PHY can be suspended or not. Fixes: f1e911d5d0df ("r8169: add basic phylib support") Fixes: e8cfd9d6c772 ("net: phy: call state machine synchronously in phy_stop") Signed-off-by: Heiner Kallweit Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ca5ab98053c8..c7861e4b402c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1730,6 +1730,8 @@ enum netdev_priv_flags { * switch driver and used to set the phys state of the * switch port. * + * @wol_enabled: Wake-on-LAN is enabled + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2014,6 +2016,7 @@ struct net_device { struct lock_class_key *qdisc_tx_busylock; struct lock_class_key *qdisc_running_key; bool proto_down; + unsigned wol_enabled:1; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.2.3 From 6b58859419554fb824e09cfdd73151a195473cbc Mon Sep 17 00:00:00 2001 From: Justin Ernst Date: Tue, 25 Sep 2018 09:34:49 -0500 Subject: EDAC: Raise the maximum number of memory controllers We observe an oops in the skx_edac module during boot: EDAC MC0: Giving out device to module skx_edac controller Skylake Socket#0 IMC#0 EDAC MC1: Giving out device to module skx_edac controller Skylake Socket#0 IMC#1 EDAC MC2: Giving out device to module skx_edac controller Skylake Socket#1 IMC#0 ... EDAC MC13: Giving out device to module skx_edac controller Skylake Socket#0 IMC#1 EDAC MC14: Giving out device to module skx_edac controller Skylake Socket#1 IMC#0 EDAC MC15: Giving out device to module skx_edac controller Skylake Socket#1 IMC#1 Too many memory controllers: 16 EDAC MC: Removed device 0 for skx_edac Skylake Socket#0 IMC#0 We observe there are two memory controllers per socket, with a limit of 16. Raise the maximum number of memory controllers from 16 to 2 * MAX_NUMNODES (1024). [ bp: This is just a band-aid fix until we've sorted out the whole issue with the bus_type association and handling in EDAC and can get rid of this arbitrary limit. ] Signed-off-by: Justin Ernst Signed-off-by: Borislav Petkov Acked-by: Russ Anderson Cc: Mauro Carvalho Chehab Cc: linux-edac@vger.kernel.org Link: https://lkml.kernel.org/r/20180925143449.284634-1-justin.ernst@hpe.com --- include/linux/edac.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index a45ce1f84bfc..1d0c9ea8825d 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -17,6 +17,7 @@ #include #include #include +#include #define EDAC_DEVICE_NAME_LEN 31 @@ -672,6 +673,6 @@ struct mem_ctl_info { /* * Maximum number of memory controllers in the coherent fabric. */ -#define EDAC_MAX_MCS 16 +#define EDAC_MAX_MCS 2 * MAX_NUMNODES #endif -- cgit v1.2.3 From 96a71f21ef1fcc32bea07c612a332a89a213f054 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 21 Sep 2018 21:20:30 +0300 Subject: fanotify: store fanotify_init() flags in group's fanotify_data This averts the need to re-generate flags in fanotify_show_fdinfo() and sets the scene for addition of more upcoming flags without growing new members to the fanotify_data struct. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 4 ++++ include/linux/fsnotify_backend.h | 4 ++-- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 096c96f4f16a..9c5ea3bdfaa0 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -6,4 +6,8 @@ /* not valid from userspace, only kernel internal */ #define FAN_MARK_ONDIR 0x00000100 + +#define FAN_GROUP_FLAG(group, flag) \ + ((group)->fanotify_data.flags & (flag)) + #endif /* _LINUX_FANOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 81b88fc9df31..8e91341cbd8a 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -189,10 +189,10 @@ struct fsnotify_group { /* allows a group to block waiting for a userspace response */ struct list_head access_list; wait_queue_head_t access_waitq; - int f_flags; + int flags; /* flags from fanotify_init() */ + int f_flags; /* event_f_flags from fanotify_init() */ unsigned int max_marks; struct user_struct *user; - bool audit; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; -- cgit v1.2.3 From 9ae033aca8d600e36034d4d0743aad624cec92ed Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Sep 2018 23:51:36 -0700 Subject: jump_label: Abstract jump_entry member accessors In preparation of allowing architectures to use relative references in jump_label entries [which can dramatically reduce the memory footprint], introduce abstractions for references to the 'code' and 'key' members of struct jump_entry. Signed-off-by: Ard Biesheuvel Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Kees Cook Cc: Will Deacon Cc: Catalin Marinas Cc: Steven Rostedt Cc: Martin Schwidefsky Cc: Jessica Yu Link: https://lkml.kernel.org/r/20180919065144.25010-2-ard.biesheuvel@linaro.org --- include/linux/jump_label.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 1a0b6f17a5d6..2eadff9b3b90 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -119,6 +119,40 @@ struct static_key { #ifdef HAVE_JUMP_LABEL #include + +#ifndef __ASSEMBLY__ + +static inline unsigned long jump_entry_code(const struct jump_entry *entry) +{ + return entry->code; +} + +static inline unsigned long jump_entry_target(const struct jump_entry *entry) +{ + return entry->target; +} + +static inline struct static_key *jump_entry_key(const struct jump_entry *entry) +{ + return (struct static_key *)((unsigned long)entry->key & ~1UL); +} + +static inline bool jump_entry_is_branch(const struct jump_entry *entry) +{ + return (unsigned long)entry->key & 1UL; +} + +static inline bool jump_entry_is_init(const struct jump_entry *entry) +{ + return entry->code == 0; +} + +static inline void jump_entry_set_init(struct jump_entry *entry) +{ + entry->code = 0; +} + +#endif #endif #ifndef __ASSEMBLY__ -- cgit v1.2.3 From 50ff18ab497aa22f6a59444625df7508c8918237 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Sep 2018 23:51:37 -0700 Subject: jump_label: Implement generic support for relative references To reduce the size taken up by absolute references in jump label entries themselves and the associated relocation records in the .init segment, add support for emitting them as relative references instead. Note that this requires some extra care in the sorting routine, given that the offsets change when entries are moved around in the jump_entry table. Signed-off-by: Ard Biesheuvel Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Kees Cook Cc: Will Deacon Cc: Catalin Marinas Cc: Steven Rostedt Cc: Martin Schwidefsky Cc: Jessica Yu Link: https://lkml.kernel.org/r/20180919065144.25010-3-ard.biesheuvel@linaro.org --- include/linux/jump_label.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 2eadff9b3b90..2768a925bafa 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -121,6 +121,32 @@ struct static_key { #include #ifndef __ASSEMBLY__ +#ifdef CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE + +struct jump_entry { + s32 code; + s32 target; + long key; // key may be far away from the core kernel under KASLR +}; + +static inline unsigned long jump_entry_code(const struct jump_entry *entry) +{ + return (unsigned long)&entry->code + entry->code; +} + +static inline unsigned long jump_entry_target(const struct jump_entry *entry) +{ + return (unsigned long)&entry->target + entry->target; +} + +static inline struct static_key *jump_entry_key(const struct jump_entry *entry) +{ + long offset = entry->key & ~1L; + + return (struct static_key *)((unsigned long)&entry->key + offset); +} + +#else static inline unsigned long jump_entry_code(const struct jump_entry *entry) { @@ -137,6 +163,8 @@ static inline struct static_key *jump_entry_key(const struct jump_entry *entry) return (struct static_key *)((unsigned long)entry->key & ~1UL); } +#endif + static inline bool jump_entry_is_branch(const struct jump_entry *entry) { return (unsigned long)entry->key & 1UL; -- cgit v1.2.3 From 19483677684b6ca01606f58503cb79cdfbbc7c72 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Sep 2018 23:51:42 -0700 Subject: jump_label: Annotate entries that operate on __init code earlier Jump table entries are mostly read-only, with the exception of the init and module loader code that defuses entries that point into init code when the code being referred to is freed. For robustness, it would be better to move these entries into the ro_after_init section, but clearing the 'code' member of each jump table entry referring to init code at module load time races with the module_enable_ro() call that remaps the ro_after_init section read only, so we'd like to do it earlier. So given that whether such an entry refers to init code can be decided much earlier, we can pull this check forward. Since we may still need the code entry at this point, let's switch to setting a low bit in the 'key' member just like we do to annotate the default state of a jump table entry. Signed-off-by: Ard Biesheuvel Signed-off-by: Thomas Gleixner Reviewed-by: Kees Cook Acked-by: Peter Zijlstra (Intel) Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Will Deacon Cc: Catalin Marinas Cc: Steven Rostedt Cc: Martin Schwidefsky Cc: Jessica Yu Link: https://lkml.kernel.org/r/20180919065144.25010-8-ard.biesheuvel@linaro.org --- include/linux/jump_label.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 2768a925bafa..5df6a621e464 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -141,7 +141,7 @@ static inline unsigned long jump_entry_target(const struct jump_entry *entry) static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { - long offset = entry->key & ~1L; + long offset = entry->key & ~3L; return (struct static_key *)((unsigned long)&entry->key + offset); } @@ -160,7 +160,7 @@ static inline unsigned long jump_entry_target(const struct jump_entry *entry) static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { - return (struct static_key *)((unsigned long)entry->key & ~1UL); + return (struct static_key *)((unsigned long)entry->key & ~3UL); } #endif @@ -172,12 +172,12 @@ static inline bool jump_entry_is_branch(const struct jump_entry *entry) static inline bool jump_entry_is_init(const struct jump_entry *entry) { - return entry->code == 0; + return (unsigned long)entry->key & 2UL; } static inline void jump_entry_set_init(struct jump_entry *entry) { - entry->code = 0; + entry->key |= 2; } #endif @@ -213,7 +213,6 @@ extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); -extern void jump_label_invalidate_initmem(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, @@ -261,8 +260,6 @@ static __always_inline void jump_label_init(void) static_key_initialized = true; } -static inline void jump_label_invalidate_initmem(void) {} - static __always_inline bool static_key_false(struct static_key *key) { if (unlikely(static_key_count(key) > 0)) -- cgit v1.2.3 From c6babb5806b77c6ca7078c3487bb0a29704a4e38 Mon Sep 17 00:00:00 2001 From: Pu Wen Date: Tue, 25 Sep 2018 22:46:11 +0800 Subject: x86/pci, x86/amd_nb: Add Hygon Dhyana support to PCI and northbridge Hygon's PCI vendor ID is 0x1d94, and there are PCI devices 0x1450/0x1463/0x1464 for the host bridge on the Hygon Dhyana platform. Add Hygon Dhyana support to the PCI and northbridge subsystems by using the code path of AMD family 17h. [ bp: Massage commit message, sort local vars into reverse xmas tree order and move the amd_northbridges.num check up. ] Signed-off-by: Pu Wen Signed-off-by: Borislav Petkov Acked-by: Bjorn Helgaas # pci_ids.h Cc: tglx@linutronix.de Cc: mingo@redhat.com Cc: hpa@zytor.com Cc: x86@kernel.org Cc: thomas.lendacky@amd.com Cc: helgaas@kernel.org Cc: linux-pci@vger.kernel.org Link: https://lkml.kernel.org/r/5f8877bd413f2ea0833378dd5454df0720e1c0df.1537885177.git.puwen@hygon.cn --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d157983b84cf..8a0841c73f81 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2561,6 +2561,8 @@ #define PCI_VENDOR_ID_AMAZON 0x1d0f +#define PCI_VENDOR_ID_HYGON 0x1d94 + #define PCI_VENDOR_ID_TEKRAM 0x1de1 #define PCI_DEVICE_ID_TEKRAM_DC290 0xdc29 -- cgit v1.2.3 From b445bfcb9081ae90fec90b828f3aacc565776901 Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Tue, 25 Sep 2018 11:42:28 +0200 Subject: spi: switch to SPDX license identifier Use the appropriate SPDX license identifier and drop the previous license text. Signed-off-by: Marco Felsch Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 7bb36145e2ba..f08824ea1968 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1,15 +1,6 @@ -/* - * Copyright (C) 2005 David Brownell +/* SPDX-License-Identifier: GPL-2.0-or-later * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. + * Copyright (C) 2005 David Brownell */ #ifndef __LINUX_SPI_H -- cgit v1.2.3 From 5f143af7501e7c435c56e181a655493edaa92509 Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Tue, 25 Sep 2018 11:42:29 +0200 Subject: spi: make OF helper available for others The of_find_spi_device_by_node() helper function is useful for other modules too. Export the funciton as GPL like all other spi helper functions and make it available if CONFIG_OF is enabled, because it isn't related to the CONFIG_OF_DYNAMIC context. Finally add a stub if CONFIG_OF isn't enabled, so others must not care about it. Signed-off-by: Marco Felsch Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a64235e05321..e9ebfcd2e932 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1277,7 +1277,6 @@ spi_register_board_info(struct spi_board_info const *info, unsigned n) { return 0; } #endif - /* If you're hotplugging an adapter with devices (parport, usb, etc) * use spi_new_device() to describe each device. You can also call * spi_unregister_device() to start making that device vanish, but @@ -1309,6 +1308,22 @@ spi_transfer_is_last(struct spi_controller *ctlr, struct spi_transfer *xfer) return list_is_last(&xfer->transfer_list, &ctlr->cur_msg->transfers); } +/* OF support code */ +#if IS_ENABLED(CONFIG_OF) + +/* must call put_device() when done with returned spi_device device */ +extern struct spi_device * +of_find_spi_device_by_node(struct device_node *node); + +#else + +static inline struct spi_device * +of_find_spi_device_by_node(struct device_node *node) +{ + return NULL; +} + +#endif /* IS_ENABLED(CONFIG_OF) */ /* Compatibility layer */ #define spi_master spi_controller -- cgit v1.2.3 From ed88660a5372faa67c168c3db5201e33e488c9fd Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 27 Sep 2018 15:55:51 -0700 Subject: block: move call of scheduler's ->completed_request() hook Commit 4bc6339a583c ("block: move blk_stat_add() to __blk_mq_end_request()") consolidated some calls using ktime_get() so we'd only need to call it once. Kyber's ->completed_request() hook also calls ktime_get(), so let's move it to the same place, too. Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/elevator.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index a02deea30185..015bb59c0331 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -111,7 +111,7 @@ struct elevator_mq_ops { void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool); struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); bool (*has_work)(struct blk_mq_hw_ctx *); - void (*completed_request)(struct request *); + void (*completed_request)(struct request *, u64); void (*started_request)(struct request *); void (*requeue_request)(struct request *); struct request *(*former_request)(struct request_queue *, struct request *); -- cgit v1.2.3 From e9e575b8f29445bcde67f421891efa4d6527d987 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Sep 2018 19:10:39 -0700 Subject: gss_krb5: Remove VLA usage of skcipher In the quest to remove all stack VLA usage from the kernel[1], this replaces struct crypto_skcipher and SKCIPHER_REQUEST_ON_STACK() usage with struct crypto_sync_skcipher and SYNC_SKCIPHER_REQUEST_ON_STACK(), which uses a fixed stack size. [1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com Cc: Trond Myklebust Cc: Anna Schumaker Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: YueHaibing Cc: linux-nfs@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: Herbert Xu --- include/linux/sunrpc/gss_krb5.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 7df625d41e35..f6e8ceafafd8 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -71,10 +71,10 @@ struct gss_krb5_enctype { const u32 keyed_cksum; /* is it a keyed cksum? */ const u32 keybytes; /* raw key len, in bytes */ const u32 keylength; /* final key len, in bytes */ - u32 (*encrypt) (struct crypto_skcipher *tfm, + u32 (*encrypt) (struct crypto_sync_skcipher *tfm, void *iv, void *in, void *out, int length); /* encryption function */ - u32 (*decrypt) (struct crypto_skcipher *tfm, + u32 (*decrypt) (struct crypto_sync_skcipher *tfm, void *iv, void *in, void *out, int length); /* decryption function */ u32 (*mk_key) (const struct gss_krb5_enctype *gk5e, @@ -98,12 +98,12 @@ struct krb5_ctx { u32 enctype; u32 flags; const struct gss_krb5_enctype *gk5e; /* enctype-specific info */ - struct crypto_skcipher *enc; - struct crypto_skcipher *seq; - struct crypto_skcipher *acceptor_enc; - struct crypto_skcipher *initiator_enc; - struct crypto_skcipher *acceptor_enc_aux; - struct crypto_skcipher *initiator_enc_aux; + struct crypto_sync_skcipher *enc; + struct crypto_sync_skcipher *seq; + struct crypto_sync_skcipher *acceptor_enc; + struct crypto_sync_skcipher *initiator_enc; + struct crypto_sync_skcipher *acceptor_enc_aux; + struct crypto_sync_skcipher *initiator_enc_aux; u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; s32 endtime; @@ -262,24 +262,24 @@ gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, u32 -krb5_encrypt(struct crypto_skcipher *key, +krb5_encrypt(struct crypto_sync_skcipher *key, void *iv, void *in, void *out, int length); u32 -krb5_decrypt(struct crypto_skcipher *key, +krb5_decrypt(struct crypto_sync_skcipher *key, void *iv, void *in, void *out, int length); int -gss_encrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *outbuf, +gss_encrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *outbuf, int offset, struct page **pages); int -gss_decrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *inbuf, +gss_decrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *inbuf, int offset); s32 krb5_make_seq_num(struct krb5_ctx *kctx, - struct crypto_skcipher *key, + struct crypto_sync_skcipher *key, int direction, u32 seqnum, unsigned char *cksum, unsigned char *buf); @@ -320,12 +320,12 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, int krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, - struct crypto_skcipher *cipher, + struct crypto_sync_skcipher *cipher, unsigned char *cksum); int krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, - struct crypto_skcipher *cipher, + struct crypto_sync_skcipher *cipher, s32 seqnum); void gss_krb5_make_confounder(char *p, u32 conflen); -- cgit v1.2.3 From cac5818c25d0423bda73e2b6997404ed0a7ed9e3 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Wed, 19 Sep 2018 10:10:54 +0000 Subject: crypto: user - Implement a generic crypto statistics This patch implement a generic way to get statistics about all crypto usages. Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu --- include/linux/crypto.h | 110 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 108 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index e8839d3a7559..3634ad6fe202 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -454,6 +454,33 @@ struct compress_alg { * @cra_refcnt: internally used * @cra_destroy: internally used * + * All following statistics are for this crypto_alg + * @encrypt_cnt: number of encrypt requests + * @decrypt_cnt: number of decrypt requests + * @compress_cnt: number of compress requests + * @decompress_cnt: number of decompress requests + * @generate_cnt: number of RNG generate requests + * @seed_cnt: number of times the rng was seeded + * @hash_cnt: number of hash requests + * @sign_cnt: number of sign requests + * @setsecret_cnt: number of setsecrey operation + * @generate_public_key_cnt: number of generate_public_key operation + * @verify_cnt: number of verify operation + * @compute_shared_secret_cnt: number of compute_shared_secret operation + * @encrypt_tlen: total data size handled by encrypt requests + * @decrypt_tlen: total data size handled by decrypt requests + * @compress_tlen: total data size handled by compress requests + * @decompress_tlen: total data size handled by decompress requests + * @generate_tlen: total data size of generated data by the RNG + * @hash_tlen: total data size hashed + * @akcipher_err_cnt: number of error for akcipher requests + * @cipher_err_cnt: number of error for akcipher requests + * @compress_err_cnt: number of error for akcipher requests + * @aead_err_cnt: number of error for akcipher requests + * @hash_err_cnt: number of error for akcipher requests + * @rng_err_cnt: number of error for akcipher requests + * @kpp_err_cnt: number of error for akcipher requests + * * The struct crypto_alg describes a generic Crypto API algorithm and is common * for all of the transformations. Any variable not documented here shall not * be used by a cipher implementation as it is internal to the Crypto API. @@ -487,6 +514,45 @@ struct crypto_alg { void (*cra_destroy)(struct crypto_alg *alg); struct module *cra_module; + + union { + atomic_t encrypt_cnt; + atomic_t compress_cnt; + atomic_t generate_cnt; + atomic_t hash_cnt; + atomic_t setsecret_cnt; + }; + union { + atomic64_t encrypt_tlen; + atomic64_t compress_tlen; + atomic64_t generate_tlen; + atomic64_t hash_tlen; + }; + union { + atomic_t akcipher_err_cnt; + atomic_t cipher_err_cnt; + atomic_t compress_err_cnt; + atomic_t aead_err_cnt; + atomic_t hash_err_cnt; + atomic_t rng_err_cnt; + atomic_t kpp_err_cnt; + }; + union { + atomic_t decrypt_cnt; + atomic_t decompress_cnt; + atomic_t seed_cnt; + atomic_t generate_public_key_cnt; + }; + union { + atomic64_t decrypt_tlen; + atomic64_t decompress_tlen; + }; + union { + atomic_t verify_cnt; + atomic_t compute_shared_secret_cnt; + }; + atomic_t sign_cnt; + } CRYPTO_MINALIGN_ATTR; /* @@ -907,6 +973,38 @@ static inline struct crypto_ablkcipher *crypto_ablkcipher_reqtfm( return __crypto_ablkcipher_cast(req->base.tfm); } +static inline void crypto_stat_ablkcipher_encrypt(struct ablkcipher_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct ablkcipher_tfm *crt = + crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&crt->base->base.__crt_alg->cipher_err_cnt); + } else { + atomic_inc(&crt->base->base.__crt_alg->encrypt_cnt); + atomic64_add(req->nbytes, &crt->base->base.__crt_alg->encrypt_tlen); + } +#endif +} + +static inline void crypto_stat_ablkcipher_decrypt(struct ablkcipher_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct ablkcipher_tfm *crt = + crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&crt->base->base.__crt_alg->cipher_err_cnt); + } else { + atomic_inc(&crt->base->base.__crt_alg->decrypt_cnt); + atomic64_add(req->nbytes, &crt->base->base.__crt_alg->decrypt_tlen); + } +#endif +} + /** * crypto_ablkcipher_encrypt() - encrypt plaintext * @req: reference to the ablkcipher_request handle that holds all information @@ -922,7 +1020,11 @@ static inline int crypto_ablkcipher_encrypt(struct ablkcipher_request *req) { struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - return crt->encrypt(req); + int ret; + + ret = crt->encrypt(req); + crypto_stat_ablkcipher_encrypt(req, ret); + return ret; } /** @@ -940,7 +1042,11 @@ static inline int crypto_ablkcipher_decrypt(struct ablkcipher_request *req) { struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - return crt->decrypt(req); + int ret; + + ret = crt->decrypt(req); + crypto_stat_ablkcipher_decrypt(req, ret); + return ret; } /** -- cgit v1.2.3 From eb2bccb70b979d996ecb769d692b92ff12eabbb7 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 19 Sep 2018 03:13:21 +0200 Subject: rtc: move rtc_add_group/s definitions Move rtc_add_group and rtc_add_groups definition to rtc.h that is available for all RTC drivers. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index faf00a1472d4..c8bb4a2b48c3 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -272,4 +272,20 @@ static inline int rtc_nvmem_register(struct rtc_device *rtc, static inline void rtc_nvmem_unregister(struct rtc_device *rtc) {} #endif +#ifdef CONFIG_RTC_INTF_SYSFS +int rtc_add_group(struct rtc_device *rtc, const struct attribute_group *grp); +int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps); +#else +static inline +int rtc_add_group(struct rtc_device *rtc, const struct attribute_group *grp) +{ + return 0; +} + +static inline +int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps) +{ + return 0; +} +#endif #endif /* _LINUX_RTC_H_ */ -- cgit v1.2.3 From 421c119f558761556afca6a62ad183bc2d8659e0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 24 Sep 2018 14:10:04 +0200 Subject: netfilter: avoid erronous array bounds warning Unfortunately some versions of gcc emit following warning: $ make net/xfrm/xfrm_output.o linux/compiler.h:252:20: warning: array subscript is above array bounds [-Warray-bounds] hook_head = rcu_dereference(net->nf.hooks_arp[hook]); ^~~~~~~~~~~~~~~~~~~~~ xfrm_output_resume passes skb_dst(skb)->ops->family as its 'pf' arg so compiler can't know that we'll never access hooks_arp[]. (NFPROTO_IPV4 or NFPROTO_IPV6 are only possible cases). Avoid this by adding an explicit WARN_ON_ONCE() check. This patch has no effect if the family is a compile-time constant as gcc will remove the switch() construct entirely. Reported-by: David Ahern Signed-off-by: Florian Westphal Reviewed-by: David Ahern Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 07efffd0c759..bbe99d2b28b4 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -215,6 +215,8 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, break; case NFPROTO_ARP: #ifdef CONFIG_NETFILTER_FAMILY_ARP + if (WARN_ON_ONCE(hook >= ARRAY_SIZE(net->nf.hooks_arp))) + break; hook_head = rcu_dereference(net->nf.hooks_arp[hook]); #endif break; -- cgit v1.2.3 From d7b9fd1669d4a4f38281c4e29f1408e1bdce09b3 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:03 -0700 Subject: nvmem: provide nvmem_dev_name() Kernel users don't have any means of checking the names of nvmem devices. Add a routine that returns the name of the nvmem provider. This will be useful for future nvmem notifier subscribers - otherwise they can't check what device is being added/removed. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 4e85447f7860..0389fe00b177 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -55,6 +55,8 @@ ssize_t nvmem_device_cell_read(struct nvmem_device *nvmem, int nvmem_device_cell_write(struct nvmem_device *nvmem, struct nvmem_cell_info *info, void *buf); +const char *nvmem_dev_name(struct nvmem_device *nvmem); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -143,6 +145,12 @@ static inline int nvmem_device_write(struct nvmem_device *nvmem, { return -ENOSYS; } + +static inline const char *nvmem_dev_name(struct nvmem_device *nvmem) +{ + return NULL; +} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) -- cgit v1.2.3 From bf58e8820c48805394ec9e76339f0c4646050432 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:13 -0700 Subject: nvmem: change the signature of nvmem_unregister() We switched the nvmem framework to using kref instead of manually checking the current number of users in nvmem_unregister() so this function can no longer fail. We also converted all remaining users that still checked the return value of nvmem_unregister() to using devm_nvmem_register(). Make the routine return void. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 24def6ad09bb..0f357d0c1e75 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -70,7 +70,7 @@ struct nvmem_config { #if IS_ENABLED(CONFIG_NVMEM) struct nvmem_device *nvmem_register(const struct nvmem_config *cfg); -int nvmem_unregister(struct nvmem_device *nvmem); +void nvmem_unregister(struct nvmem_device *nvmem); struct nvmem_device *devm_nvmem_register(struct device *dev, const struct nvmem_config *cfg); @@ -87,10 +87,7 @@ static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) return ERR_PTR(-ENOSYS); } -static inline int nvmem_unregister(struct nvmem_device *nvmem) -{ - return -ENOSYS; -} +static inline void nvmem_unregister(struct nvmem_device *nvmem) {} static inline struct nvmem_device * devm_nvmem_register(struct device *dev, const struct nvmem_config *c) @@ -101,7 +98,7 @@ devm_nvmem_register(struct device *dev, const struct nvmem_config *c) static inline int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) { - return nvmem_unregister(nvmem); + return -ENOSYS; } -- cgit v1.2.3 From b985f4cba6dbb3b60ad119c6f7e5cbad6f0d7e45 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:15 -0700 Subject: nvmem: add support for cell info Add new structs and routines allowing users to define nvmem cells from machine code. This global list of entries is parsed when a provider is registered and cells are associated with the relevant nvmem_device struct. A possible improvement for the future is to allow users to register cell tables after the nvmem provider has been registered by updating the cell list at each call to nvmem_(add|del)_cell_table(). Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 0f357d0c1e75..5c9f205cac8f 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -67,6 +67,25 @@ struct nvmem_config { struct device *base_dev; }; +/** + * struct nvmem_cell_table - NVMEM cell definitions for given provider + * + * @nvmem_name: Provider name. + * @cells: Array of cell definitions. + * @ncells: Number of cell definitions in the array. + * @node: List node. + * + * This structure together with related helper functions is provided for users + * that don't can't access the nvmem provided structure but wish to register + * cell definitions for it e.g. board files registering an EEPROM device. + */ +struct nvmem_cell_table { + const char *nvmem_name; + const struct nvmem_cell_info *cells; + size_t ncells; + struct list_head node; +}; + #if IS_ENABLED(CONFIG_NVMEM) struct nvmem_device *nvmem_register(const struct nvmem_config *cfg); @@ -77,9 +96,9 @@ struct nvmem_device *devm_nvmem_register(struct device *dev, int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem); -int nvmem_add_cells(struct nvmem_device *nvmem, - const struct nvmem_cell_info *info, - int ncells); +void nvmem_add_cell_table(struct nvmem_cell_table *table); +void nvmem_del_cell_table(struct nvmem_cell_table *table); + #else static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) @@ -102,12 +121,8 @@ devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) } -static inline int nvmem_add_cells(struct nvmem_device *nvmem, - const struct nvmem_cell_info *info, - int ncells) -{ - return -ENOSYS; -} +static inline void nvmem_add_cell_table(struct nvmem_cell_table *table) {} +static inline void nvmem_del_cell_table(struct nvmem_cell_table *table) {} #endif /* CONFIG_NVMEM */ #endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ -- cgit v1.2.3 From 506157be06ba28137b18b7419a4dccfa244f4983 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:17 -0700 Subject: nvmem: add support for cell lookups from machine code Add a way for machine code users to associate devices with nvmem cells. This restores the support for non-DT systems but following a different approach. Cells must now be associated with devices using provided routines and data structures before they can be retrieved using nvmem_cell_get(). It's still possible to define cells statically in nvmem_config but cells created this way still need to be associated with consumers using lookup entries. Note that nvmem_find() must be moved higher in the source file as we want to call it from __nvmem_device_get() for devices that don't have a device node. The signature of __nvmem_device_get() is also changed as it's no longer used to retrieve cells. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 0389fe00b177..27eee3945405 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -29,6 +29,24 @@ struct nvmem_cell_info { unsigned int nbits; }; +/** + * struct nvmem_cell_lookup - cell lookup entry + * + * @nvmem_name: Name of the provider. + * @cell_name: Name of the nvmem cell as defined in the name field of + * struct nvmem_cell_info. + * @dev_id: Name of the consumer device that will be associated with + * this cell. + * @con_id: Connector id for this cell lookup. + */ +struct nvmem_cell_lookup { + const char *nvmem_name; + const char *cell_name; + const char *dev_id; + const char *con_id; + struct list_head node; +}; + #if IS_ENABLED(CONFIG_NVMEM) /* Cell based interface */ @@ -57,6 +75,11 @@ int nvmem_device_cell_write(struct nvmem_device *nvmem, const char *nvmem_dev_name(struct nvmem_device *nvmem); +void nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, + size_t nentries); +void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, + size_t nentries); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -151,6 +174,11 @@ static inline const char *nvmem_dev_name(struct nvmem_device *nvmem) return NULL; } +static inline void +nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} +static inline void +nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) -- cgit v1.2.3 From bee1138bea15a640aaa9e9bb909af5b2762520e0 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:19 -0700 Subject: nvmem: add a notifier chain Add a blocking notifier chain with four events (add and remove for both devices and cells) so that users can get notified about the addition of nvmem resources they're waiting for. We'll use this instead of the at24 setup callback in the mityomapl138 board file. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 27eee3945405..0326b52e906b 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -14,6 +14,7 @@ #include #include +#include struct device; struct device_node; @@ -47,6 +48,13 @@ struct nvmem_cell_lookup { struct list_head node; }; +enum { + NVMEM_ADD = 1, + NVMEM_REMOVE, + NVMEM_CELL_ADD, + NVMEM_CELL_REMOVE, +}; + #if IS_ENABLED(CONFIG_NVMEM) /* Cell based interface */ @@ -80,6 +88,9 @@ void nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries); +int nvmem_register_notifier(struct notifier_block *nb); +int nvmem_unregister_notifier(struct notifier_block *nb); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -179,6 +190,16 @@ nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} static inline void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} +static inline int nvmem_register_notifier(struct notifier_block *nb) +{ + return -ENOSYS; +} + +static inline int nvmem_unregister_notifier(struct notifier_block *nb) +{ + return -ENOSYS; +} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) -- cgit v1.2.3 From b1c1db9883c276fe41a04e9ce8f89576a64b1ac0 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:20 -0700 Subject: nvmem: use SPDX license identifiers Use SPDX license identiefiers to core nvmem files and remove GPL 2.0 license boilerplate. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 5 +---- include/linux/nvmem-provider.h | 5 +---- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 0326b52e906b..d18caae2f7ac 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * nvmem framework consumer. * * Copyright (C) 2015 Srinivas Kandagatla * Copyright (C) 2013 Maxime Ripard - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ #ifndef _LINUX_NVMEM_CONSUMER_H diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 5c9f205cac8f..8ae012f6545a 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * nvmem framework provider. * * Copyright (C) 2015 Srinivas Kandagatla * Copyright (C) 2013 Maxime Ripard - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ #ifndef _LINUX_NVMEM_PROVIDER_H -- cgit v1.2.3 From 165589f0cb52b34db12e15676a034b8f83dfa756 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:21 -0700 Subject: nvmem: make the naming of arguments in nvmem_cell_get() consistent The argument representing the cell name in the nvmem_cell_get() family of functions is not consistend between function prototypes and definitions. Name it 'id' in all those routines. This is in line with other frameworks and can represent both the DT cell name from the nvmem-cell-names property as well as the con_id field from cell lookup entries. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index d18caae2f7ac..e17617fa034f 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -55,8 +55,8 @@ enum { #if IS_ENABLED(CONFIG_NVMEM) /* Cell based interface */ -struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *name); -struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, const char *name); +struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *id); +struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, const char *id); void nvmem_cell_put(struct nvmem_cell *cell); void devm_nvmem_cell_put(struct device *dev, struct nvmem_cell *cell); void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len); @@ -91,13 +91,13 @@ int nvmem_unregister_notifier(struct notifier_block *nb); #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, - const char *name) + const char *id) { return ERR_PTR(-ENOSYS); } static inline struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, - const char *name) + const char *id) { return ERR_PTR(-ENOSYS); } @@ -201,12 +201,12 @@ static inline int nvmem_unregister_notifier(struct notifier_block *nb) #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, - const char *name); + const char *id); struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *name); #else static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, - const char *name) + const char *id) { return ERR_PTR(-ENOSYS); } -- cgit v1.2.3 From 20167b70c894f20cd01e2579fad206de440816ef Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:22 -0700 Subject: nvmem: use EOPNOTSUPP instead of ENOSYS Checkpatch emits warnings when using ENOSYS. Some of the frameworks started using EOPNOTSUPP as return values for API functions when given subsystem is disabled in Kconfig. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 30 +++++++++++++++--------------- include/linux/nvmem-provider.h | 5 ++--- 2 files changed, 17 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index e17617fa034f..312bfa5efd80 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -93,13 +93,13 @@ int nvmem_unregister_notifier(struct notifier_block *nb); static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *id) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, const char *id) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline void devm_nvmem_cell_put(struct device *dev, @@ -113,31 +113,31 @@ static inline void nvmem_cell_put(struct nvmem_cell *cell) static inline void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline int nvmem_cell_write(struct nvmem_cell *cell, const char *buf, size_t len) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_cell_read_u32(struct device *dev, const char *cell_id, u32 *val) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline struct nvmem_device *nvmem_device_get(struct device *dev, const char *name) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline struct nvmem_device *devm_nvmem_device_get(struct device *dev, const char *name) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline void nvmem_device_put(struct nvmem_device *nvmem) @@ -153,28 +153,28 @@ static inline ssize_t nvmem_device_cell_read(struct nvmem_device *nvmem, struct nvmem_cell_info *info, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_device_cell_write(struct nvmem_device *nvmem, struct nvmem_cell_info *info, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_device_read(struct nvmem_device *nvmem, unsigned int offset, size_t bytes, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_device_write(struct nvmem_device *nvmem, unsigned int offset, size_t bytes, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline const char *nvmem_dev_name(struct nvmem_device *nvmem) @@ -189,12 +189,12 @@ nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} static inline int nvmem_register_notifier(struct notifier_block *nb) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_unregister_notifier(struct notifier_block *nb) { - return -ENOSYS; + return -EOPNOTSUPP; } #endif /* CONFIG_NVMEM */ @@ -208,13 +208,13 @@ struct nvmem_device *of_nvmem_device_get(struct device_node *np, static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *name) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } #endif /* CONFIG_NVMEM && CONFIG_OF */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 8ae012f6545a..1e3283c2af77 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -100,7 +100,7 @@ void nvmem_del_cell_table(struct nvmem_cell_table *table); static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline void nvmem_unregister(struct nvmem_device *nvmem) {} @@ -114,8 +114,7 @@ devm_nvmem_register(struct device *dev, const struct nvmem_config *c) static inline int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) { - return -ENOSYS; - + return -EOPNOTSUPP; } static inline void nvmem_add_cell_table(struct nvmem_cell_table *table) {} -- cgit v1.2.3 From 494edd266b945f36908184433dd36eda1719cdb0 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 14 Sep 2018 11:27:46 +0300 Subject: regulator/mfd: Support ROHM BD71847 power management IC BD71847 is reduced version of BD71837. DVS bucks 3 and 4 are removed as is LDO7. Voltage ranges of some regulators are expanded. Add initial support for BD71847 with BD71837 driver. Signed-off-by: Matti Vaittinen Acked-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/rohm-bd718x7.h | 271 ++++++++++++++++++--------------------- 1 file changed, 124 insertions(+), 147 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index e8338e5dc10b..625e3607e069 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -7,106 +7,125 @@ #include enum { - BD71837_BUCK1 = 0, - BD71837_BUCK2, - BD71837_BUCK3, - BD71837_BUCK4, - BD71837_BUCK5, - BD71837_BUCK6, - BD71837_BUCK7, - BD71837_BUCK8, - BD71837_LDO1, - BD71837_LDO2, - BD71837_LDO3, - BD71837_LDO4, - BD71837_LDO5, - BD71837_LDO6, - BD71837_LDO7, - BD71837_REGULATOR_CNT, + BD718XX_TYPE_BD71837 = 0, + BD718XX_TYPE_BD71847, + BD718XX_TYPE_AMOUNT }; -#define BD71837_BUCK1_VOLTAGE_NUM 0x40 -#define BD71837_BUCK2_VOLTAGE_NUM 0x40 -#define BD71837_BUCK3_VOLTAGE_NUM 0x40 -#define BD71837_BUCK4_VOLTAGE_NUM 0x40 +enum { + BD718XX_BUCK1 = 0, + BD718XX_BUCK2, + BD718XX_BUCK3, + BD718XX_BUCK4, + BD718XX_BUCK5, + BD718XX_BUCK6, + BD718XX_BUCK7, + BD718XX_BUCK8, + BD718XX_LDO1, + BD718XX_LDO2, + BD718XX_LDO3, + BD718XX_LDO4, + BD718XX_LDO5, + BD718XX_LDO6, + BD718XX_LDO7, + BD718XX_REGULATOR_AMOUNT, +}; + +/* Common voltage configurations + * + * Note, we support only one range of voltages for each buck/LDO until we + * get pickable ranges support. (See range selection bits for BUCK5 and + * LDO1. On BD71847 also the second no DVS buck and LDO5) + */ + +#define BD718XX_DVS_BUCK_VOLTAGE_NUM 0x3D +#define BD718XX_1ST_NODVS_BUCK_VOLTAGE_NUM 0x08 +#define BD71837_4TH_NODVS_BUCK_VOLTAGE_NUM 0x3D + +#define BD718XX_LDO1_VOLTAGE_NUM 0x04 +#define BD718XX_LDO2_VOLTAGE_NUM 0x02 +#define BD718XX_LDO3_VOLTAGE_NUM 0x10 +#define BD718XX_LDO4_VOLTAGE_NUM 0x0A +#define BD718XX_LDO5_VOLTAGE_NUM 0x10 +#define BD718XX_LDO6_VOLTAGE_NUM 0x0A -#define BD71837_BUCK5_VOLTAGE_NUM 0x08 +/* BD71837 specific voltage configurations */ #define BD71837_BUCK6_VOLTAGE_NUM 0x04 #define BD71837_BUCK7_VOLTAGE_NUM 0x08 -#define BD71837_BUCK8_VOLTAGE_NUM 0x40 - -#define BD71837_LDO1_VOLTAGE_NUM 0x04 -#define BD71837_LDO2_VOLTAGE_NUM 0x02 -#define BD71837_LDO3_VOLTAGE_NUM 0x10 -#define BD71837_LDO4_VOLTAGE_NUM 0x10 -#define BD71837_LDO5_VOLTAGE_NUM 0x10 -#define BD71837_LDO6_VOLTAGE_NUM 0x10 #define BD71837_LDO7_VOLTAGE_NUM 0x10 +/* BD71847 specific voltage configurations */ +#define BD71847_BUCK4_VOLTAGE_NUM 0x04 + +/* Registers specific to BD71837 */ enum { - BD71837_REG_REV = 0x00, - BD71837_REG_SWRESET = 0x01, - BD71837_REG_I2C_DEV = 0x02, - BD71837_REG_PWRCTRL0 = 0x03, - BD71837_REG_PWRCTRL1 = 0x04, - BD71837_REG_BUCK1_CTRL = 0x05, - BD71837_REG_BUCK2_CTRL = 0x06, - BD71837_REG_BUCK3_CTRL = 0x07, - BD71837_REG_BUCK4_CTRL = 0x08, - BD71837_REG_BUCK5_CTRL = 0x09, - BD71837_REG_BUCK6_CTRL = 0x0A, - BD71837_REG_BUCK7_CTRL = 0x0B, - BD71837_REG_BUCK8_CTRL = 0x0C, - BD71837_REG_BUCK1_VOLT_RUN = 0x0D, - BD71837_REG_BUCK1_VOLT_IDLE = 0x0E, - BD71837_REG_BUCK1_VOLT_SUSP = 0x0F, - BD71837_REG_BUCK2_VOLT_RUN = 0x10, - BD71837_REG_BUCK2_VOLT_IDLE = 0x11, - BD71837_REG_BUCK3_VOLT_RUN = 0x12, - BD71837_REG_BUCK4_VOLT_RUN = 0x13, - BD71837_REG_BUCK5_VOLT = 0x14, - BD71837_REG_BUCK6_VOLT = 0x15, - BD71837_REG_BUCK7_VOLT = 0x16, - BD71837_REG_BUCK8_VOLT = 0x17, - BD71837_REG_LDO1_VOLT = 0x18, - BD71837_REG_LDO2_VOLT = 0x19, - BD71837_REG_LDO3_VOLT = 0x1A, - BD71837_REG_LDO4_VOLT = 0x1B, - BD71837_REG_LDO5_VOLT = 0x1C, - BD71837_REG_LDO6_VOLT = 0x1D, - BD71837_REG_LDO7_VOLT = 0x1E, - BD71837_REG_TRANS_COND0 = 0x1F, - BD71837_REG_TRANS_COND1 = 0x20, - BD71837_REG_VRFAULTEN = 0x21, - BD718XX_REG_MVRFLTMASK0 = 0x22, - BD718XX_REG_MVRFLTMASK1 = 0x23, - BD718XX_REG_MVRFLTMASK2 = 0x24, - BD71837_REG_RCVCFG = 0x25, - BD71837_REG_RCVNUM = 0x26, - BD71837_REG_PWRONCONFIG0 = 0x27, - BD71837_REG_PWRONCONFIG1 = 0x28, - BD71837_REG_RESETSRC = 0x29, - BD71837_REG_MIRQ = 0x2A, - BD71837_REG_IRQ = 0x2B, - BD71837_REG_IN_MON = 0x2C, - BD71837_REG_POW_STATE = 0x2D, - BD71837_REG_OUT32K = 0x2E, - BD71837_REG_REGLOCK = 0x2F, - BD71837_REG_OTPVER = 0xFF, - BD71837_MAX_REGISTER = 0x100, + BD71837_REG_BUCK3_CTRL = 0x07, + BD71837_REG_BUCK4_CTRL = 0x08, + BD71837_REG_BUCK3_VOLT_RUN = 0x12, + BD71837_REG_BUCK4_VOLT_RUN = 0x13, + BD71837_REG_LDO7_VOLT = 0x1E, +}; + +/* Registers common for BD71837 and BD71847 */ +enum { + BD718XX_REG_REV = 0x00, + BD718XX_REG_SWRESET = 0x01, + BD718XX_REG_I2C_DEV = 0x02, + BD718XX_REG_PWRCTRL0 = 0x03, + BD718XX_REG_PWRCTRL1 = 0x04, + BD718XX_REG_BUCK1_CTRL = 0x05, + BD718XX_REG_BUCK2_CTRL = 0x06, + BD718XX_REG_1ST_NODVS_BUCK_CTRL = 0x09, + BD718XX_REG_2ND_NODVS_BUCK_CTRL = 0x0A, + BD718XX_REG_3RD_NODVS_BUCK_CTRL = 0x0B, + BD718XX_REG_4TH_NODVS_BUCK_CTRL = 0x0C, + BD718XX_REG_BUCK1_VOLT_RUN = 0x0D, + BD718XX_REG_BUCK1_VOLT_IDLE = 0x0E, + BD718XX_REG_BUCK1_VOLT_SUSP = 0x0F, + BD718XX_REG_BUCK2_VOLT_RUN = 0x10, + BD718XX_REG_BUCK2_VOLT_IDLE = 0x11, + BD718XX_REG_1ST_NODVS_BUCK_VOLT = 0x14, + BD718XX_REG_2ND_NODVS_BUCK_VOLT = 0x15, + BD718XX_REG_3RD_NODVS_BUCK_VOLT = 0x16, + BD718XX_REG_4TH_NODVS_BUCK_VOLT = 0x17, + BD718XX_REG_LDO1_VOLT = 0x18, + BD718XX_REG_LDO2_VOLT = 0x19, + BD718XX_REG_LDO3_VOLT = 0x1A, + BD718XX_REG_LDO4_VOLT = 0x1B, + BD718XX_REG_LDO5_VOLT = 0x1C, + BD718XX_REG_LDO6_VOLT = 0x1D, + BD718XX_REG_TRANS_COND0 = 0x1F, + BD718XX_REG_TRANS_COND1 = 0x20, + BD718XX_REG_VRFAULTEN = 0x21, + BD718XX_REG_MVRFLTMASK0 = 0x22, + BD718XX_REG_MVRFLTMASK1 = 0x23, + BD718XX_REG_MVRFLTMASK2 = 0x24, + BD718XX_REG_RCVCFG = 0x25, + BD718XX_REG_RCVNUM = 0x26, + BD718XX_REG_PWRONCONFIG0 = 0x27, + BD718XX_REG_PWRONCONFIG1 = 0x28, + BD718XX_REG_RESETSRC = 0x29, + BD718XX_REG_MIRQ = 0x2A, + BD718XX_REG_IRQ = 0x2B, + BD718XX_REG_IN_MON = 0x2C, + BD718XX_REG_POW_STATE = 0x2D, + BD718XX_REG_OUT32K = 0x2E, + BD718XX_REG_REGLOCK = 0x2F, + BD718XX_REG_OTPVER = 0xFF, + BD718XX_MAX_REGISTER = 0x100, }; #define REGLOCK_PWRSEQ 0x1 #define REGLOCK_VREG 0x10 /* Generic BUCK control masks */ -#define BD71837_BUCK_SEL 0x02 -#define BD71837_BUCK_EN 0x01 -#define BD71837_BUCK_RUN_ON 0x04 +#define BD718XX_BUCK_SEL 0x02 +#define BD718XX_BUCK_EN 0x01 +#define BD718XX_BUCK_RUN_ON 0x04 /* Generic LDO masks */ -#define BD71837_LDO_SEL 0x80 -#define BD71837_LDO_EN 0x40 +#define BD718XX_LDO_SEL 0x80 +#define BD718XX_LDO_EN 0x40 /* BD71837 BUCK ramp rate CTRL reg bits */ #define BUCK_RAMPRATE_MASK 0xC0 @@ -115,49 +134,27 @@ enum { #define BUCK_RAMPRATE_2P50MV 0x2 #define BUCK_RAMPRATE_1P25MV 0x3 -/* BD71837_REG_BUCK1_VOLT_RUN bits */ -#define BUCK1_RUN_MASK 0x3F -#define BUCK1_RUN_DEFAULT 0x14 - -/* BD71837_REG_BUCK1_VOLT_SUSP bits */ -#define BUCK1_SUSP_MASK 0x3F -#define BUCK1_SUSP_DEFAULT 0x14 +#define DVS_BUCK_RUN_MASK 0x3F +#define DVS_BUCK_SUSP_MASK 0x3F +#define DVS_BUCK_IDLE_MASK 0x3F -/* BD71837_REG_BUCK1_VOLT_IDLE bits */ -#define BUCK1_IDLE_MASK 0x3F -#define BUCK1_IDLE_DEFAULT 0x14 +#define BD718XX_1ST_NODVS_BUCK_MASK 0x07 +#define BD71847_BUCK4_MASK 0x03 +#define BD71837_BUCK6_MASK 0x03 +#define BD718XX_3RD_NODVS_BUCK_MASK 0x07 +#define BD718XX_4TH_NODVS_BUCK_MASK 0x3F -/* BD71837_REG_BUCK2_VOLT_RUN bits */ -#define BUCK2_RUN_MASK 0x3F -#define BUCK2_RUN_DEFAULT 0x1E +#define BD718XX_LDO1_MASK 0x03 +#define BD718XX_LDO2_MASK 0x20 +#define BD718XX_LDO3_MASK 0x0F +#define BD718XX_LDO4_MASK 0x0F +#define BD718XX_LDO6_MASK 0x0F -/* BD71837_REG_BUCK2_VOLT_IDLE bits */ -#define BUCK2_IDLE_MASK 0x3F -#define BUCK2_IDLE_DEFAULT 0x14 +#define BD71837_LDO5_MASK 0x0F +#define BD71847_LDO5_MASK 0x0F -/* BD71837_REG_BUCK3_VOLT_RUN bits */ -#define BUCK3_RUN_MASK 0x3F -#define BUCK3_RUN_DEFAULT 0x1E +#define BD71837_LDO7_MASK 0x0F -/* BD71837_REG_BUCK4_VOLT_RUN bits */ -#define BUCK4_RUN_MASK 0x3F -#define BUCK4_RUN_DEFAULT 0x1E - -/* BD71837_REG_BUCK5_VOLT bits */ -#define BUCK5_MASK 0x07 -#define BUCK5_DEFAULT 0x02 - -/* BD71837_REG_BUCK6_VOLT bits */ -#define BUCK6_MASK 0x03 -#define BUCK6_DEFAULT 0x03 - -/* BD71837_REG_BUCK7_VOLT bits */ -#define BUCK7_MASK 0x07 -#define BUCK7_DEFAULT 0x03 - -/* BD71837_REG_BUCK8_VOLT bits */ -#define BUCK8_MASK 0x3F -#define BUCK8_DEFAULT 0x1E /* BD718XX Voltage monitoring masks */ #define BD718XX_BUCK1_VRMON80 0x1 @@ -221,27 +218,6 @@ enum { #define BD71837_INT_ON_REQ_MASK 0x2 #define BD71837_INT_STBY_REQ_MASK 0x1 -/* BD71837_REG_LDO1_VOLT bits */ -#define LDO1_MASK 0x03 - -/* BD71837_REG_LDO1_VOLT bits */ -#define LDO2_MASK 0x20 - -/* BD71837_REG_LDO3_VOLT bits */ -#define LDO3_MASK 0x0F - -/* BD71837_REG_LDO4_VOLT bits */ -#define LDO4_MASK 0x0F - -/* BD71837_REG_LDO5_VOLT bits */ -#define LDO5_MASK 0x0F - -/* BD71837_REG_LDO6_VOLT bits */ -#define LDO6_MASK 0x0F - -/* BD71837_REG_LDO7_VOLT bits */ -#define LDO7_MASK 0x0F - /* Register write induced reset settings */ /* @@ -341,10 +317,11 @@ enum { BD718XX_PWRBTN_LONG_PRESS_15S }; -struct bd71837_pmic; -struct bd71837_clk; +struct bd718xx_pmic; +struct bd718xx_clk; struct bd71837 { + unsigned int chip_type; struct device *dev; struct regmap *regmap; unsigned long int id; @@ -352,8 +329,8 @@ struct bd71837 { int chip_irq; struct regmap_irq_chip_data *irq_data; - struct bd71837_pmic *pmic; - struct bd71837_clk *clk; + struct bd718xx_pmic *pmic; + struct bd718xx_clk *clk; }; #endif /* __LINUX_MFD_BD71837_H__ */ -- cgit v1.2.3 From 18e4b55fbd2069cee51ef9660b35c65ec13bee6d Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 14 Sep 2018 11:31:36 +0300 Subject: regulator: Support regulators where voltage ranges are selectable For example ROHM BD71837 and ROHM BD71847 Power management ICs have regulators which provide multiple linear ranges. Ranges can be selected by individual non contagious bit in vsel register. Add regmap helper functions for selecting ranges. Signed-off-by: Matti Vaittinen Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 0fd8fbb74763..a9c030192147 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -271,9 +271,16 @@ enum regulator_type { * @ramp_delay: Time to settle down after voltage change (unit: uV/us) * @min_dropout_uV: The minimum dropout voltage this regulator can handle * @linear_ranges: A constant table of possible voltage ranges. - * @n_linear_ranges: Number of entries in the @linear_ranges table. + * @linear_range_selectors: A constant table of voltage range selectors. + * If pickable ranges are used each range must + * have corresponding selector here. + * @n_linear_ranges: Number of entries in the @linear_ranges (and in + * linear_range_selectors if used) table(s). * @volt_table: Voltage mapping table (if table based mapping) * + * @vsel_range_reg: Register for range selector when using pickable ranges + * and regulator_regmap_X_voltage_X_pickable functions. + * @vsel_range_mask: Mask for register bitfield used for range selector * @vsel_reg: Register for selector when using regulator_regmap_X_voltage_ * @vsel_mask: Mask for register bitfield used for selector * @csel_reg: Register for TPS65218 LS3 current regulator @@ -338,10 +345,14 @@ struct regulator_desc { int min_dropout_uV; const struct regulator_linear_range *linear_ranges; + const unsigned int *linear_range_selectors; + int n_linear_ranges; const unsigned int *volt_table; + unsigned int vsel_range_reg; + unsigned int vsel_range_mask; unsigned int vsel_reg; unsigned int vsel_mask; unsigned int csel_reg; @@ -498,18 +509,25 @@ int regulator_mode_to_status(unsigned int); int regulator_list_voltage_linear(struct regulator_dev *rdev, unsigned int selector); +int regulator_list_voltage_pickable_linear_range(struct regulator_dev *rdev, + unsigned int selector); int regulator_list_voltage_linear_range(struct regulator_dev *rdev, unsigned int selector); int regulator_list_voltage_table(struct regulator_dev *rdev, unsigned int selector); int regulator_map_voltage_linear(struct regulator_dev *rdev, int min_uV, int max_uV); +int regulator_map_voltage_pickable_linear_range(struct regulator_dev *rdev, + int min_uV, int max_uV); int regulator_map_voltage_linear_range(struct regulator_dev *rdev, int min_uV, int max_uV); int regulator_map_voltage_iterate(struct regulator_dev *rdev, int min_uV, int max_uV); int regulator_map_voltage_ascend(struct regulator_dev *rdev, int min_uV, int max_uV); +int regulator_get_voltage_sel_pickable_regmap(struct regulator_dev *rdev); +int regulator_set_voltage_sel_pickable_regmap(struct regulator_dev *rdev, + unsigned int sel); int regulator_get_voltage_sel_regmap(struct regulator_dev *rdev); int regulator_set_voltage_sel_regmap(struct regulator_dev *rdev, unsigned sel); int regulator_is_enabled_regmap(struct regulator_dev *rdev); -- cgit v1.2.3 From dd2be639f4a918b335818bf22a937956e552b957 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 14 Sep 2018 11:32:26 +0300 Subject: regulator/mfd: bd718xx: rename bd71837/bd71847 common instances Rename parts of code that support both BD71837 and BD71847 to BD718XX. Signed-off-by: Matti Vaittinen Acked-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/rohm-bd718x7.h | 64 ++++++++++++++++++++-------------------- 1 file changed, 32 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index 625e3607e069..fed5fed75732 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Copyright (C) 2018 ROHM Semiconductors */ -#ifndef __LINUX_MFD_BD71837_H__ -#define __LINUX_MFD_BD71837_H__ +#ifndef __LINUX_MFD_BD718XX_H__ +#define __LINUX_MFD_BD718XX_H__ #include @@ -40,7 +40,7 @@ enum { #define BD718XX_DVS_BUCK_VOLTAGE_NUM 0x3D #define BD718XX_1ST_NODVS_BUCK_VOLTAGE_NUM 0x08 -#define BD71837_4TH_NODVS_BUCK_VOLTAGE_NUM 0x3D +#define BD718XX_4TH_NODVS_BUCK_VOLTAGE_NUM 0x3D #define BD718XX_LDO1_VOLTAGE_NUM 0x04 #define BD718XX_LDO2_VOLTAGE_NUM 0x02 @@ -183,7 +183,7 @@ enum { #define BD71837_BUCK4_VRMON130 0x80 #define BD71837_LDO7_VRMON80 0x40 -/* BD71837_REG_IRQ bits */ +/* BD718XX_REG_IRQ bits */ #define IRQ_SWRST 0x40 #define IRQ_PWRON_S 0x20 #define IRQ_PWRON_L 0x10 @@ -192,31 +192,31 @@ enum { #define IRQ_ON_REQ 0x02 #define IRQ_STBY_REQ 0x01 -/* BD71837_REG_OUT32K bits */ -#define BD71837_OUT32K_EN 0x01 +/* BD718XX_REG_OUT32K bits */ +#define BD718XX_OUT32K_EN 0x01 -/* BD71837 gated clock rate */ -#define BD71837_CLK_RATE 32768 +/* BD7183XX gated clock rate */ +#define BD718XX_CLK_RATE 32768 -/* ROHM BD71837 irqs */ +/* ROHM BD718XX irqs */ enum { - BD71837_INT_STBY_REQ, - BD71837_INT_ON_REQ, - BD71837_INT_WDOG, - BD71837_INT_PWRBTN, - BD71837_INT_PWRBTN_L, - BD71837_INT_PWRBTN_S, - BD71837_INT_SWRST + BD718XX_INT_STBY_REQ, + BD718XX_INT_ON_REQ, + BD718XX_INT_WDOG, + BD718XX_INT_PWRBTN, + BD718XX_INT_PWRBTN_L, + BD718XX_INT_PWRBTN_S, + BD718XX_INT_SWRST }; -/* ROHM BD71837 interrupt masks */ -#define BD71837_INT_SWRST_MASK 0x40 -#define BD71837_INT_PWRBTN_S_MASK 0x20 -#define BD71837_INT_PWRBTN_L_MASK 0x10 -#define BD71837_INT_PWRBTN_MASK 0x8 -#define BD71837_INT_WDOG_MASK 0x4 -#define BD71837_INT_ON_REQ_MASK 0x2 -#define BD71837_INT_STBY_REQ_MASK 0x1 +/* ROHM BD718XX interrupt masks */ +#define BD718XX_INT_SWRST_MASK 0x40 +#define BD718XX_INT_PWRBTN_S_MASK 0x20 +#define BD718XX_INT_PWRBTN_L_MASK 0x10 +#define BD718XX_INT_PWRBTN_MASK 0x8 +#define BD718XX_INT_WDOG_MASK 0x4 +#define BD718XX_INT_ON_REQ_MASK 0x2 +#define BD718XX_INT_STBY_REQ_MASK 0x1 /* Register write induced reset settings */ @@ -226,13 +226,13 @@ enum { * write 1 to it we will trigger the action. So always write 0 to it when * changning SWRESET action - no matter what we read from it. */ -#define BD71837_SWRESET_TYPE_MASK 7 -#define BD71837_SWRESET_TYPE_DISABLED 0 -#define BD71837_SWRESET_TYPE_COLD 4 -#define BD71837_SWRESET_TYPE_WARM 6 +#define BD718XX_SWRESET_TYPE_MASK 7 +#define BD718XX_SWRESET_TYPE_DISABLED 0 +#define BD718XX_SWRESET_TYPE_COLD 4 +#define BD718XX_SWRESET_TYPE_WARM 6 -#define BD71837_SWRESET_RESET_MASK 1 -#define BD71837_SWRESET_RESET 1 +#define BD718XX_SWRESET_RESET_MASK 1 +#define BD718XX_SWRESET_RESET 1 /* Poweroff state transition conditions */ @@ -320,7 +320,7 @@ enum { struct bd718xx_pmic; struct bd718xx_clk; -struct bd71837 { +struct bd718xx { unsigned int chip_type; struct device *dev; struct regmap *regmap; @@ -333,4 +333,4 @@ struct bd71837 { struct bd718xx_clk *clk; }; -#endif /* __LINUX_MFD_BD71837_H__ */ +#endif /* __LINUX_MFD_BD718XX_H__ */ -- cgit v1.2.3 From a4bfc2c28a21f4d5274d813b20fd015a9dc9bcfa Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 14 Sep 2018 11:33:11 +0300 Subject: regulator: bd718XX use pickable ranges Few regulators in BD71837 and BD71847 can output voltages from different voltage ranges. Register interface is arranged so that used range is selected by toggling bits which are not next to actual voltage selection bits. Then the voltage inside selected range is determined by voltage selection bits (as usual). Support BD71837 and BD71847 selectible range voltages using new pickable ranges helpers. Signed-off-by: Matti Vaittinen Signed-off-by: Mark Brown --- include/linux/mfd/rohm-bd718x7.h | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index fed5fed75732..26acf9a92498 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -31,31 +31,27 @@ enum { BD718XX_REGULATOR_AMOUNT, }; -/* Common voltage configurations - * - * Note, we support only one range of voltages for each buck/LDO until we - * get pickable ranges support. (See range selection bits for BUCK5 and - * LDO1. On BD71847 also the second no DVS buck and LDO5) - */ - +/* Common voltage configurations */ #define BD718XX_DVS_BUCK_VOLTAGE_NUM 0x3D -#define BD718XX_1ST_NODVS_BUCK_VOLTAGE_NUM 0x08 #define BD718XX_4TH_NODVS_BUCK_VOLTAGE_NUM 0x3D -#define BD718XX_LDO1_VOLTAGE_NUM 0x04 +#define BD718XX_LDO1_VOLTAGE_NUM 0x08 #define BD718XX_LDO2_VOLTAGE_NUM 0x02 #define BD718XX_LDO3_VOLTAGE_NUM 0x10 #define BD718XX_LDO4_VOLTAGE_NUM 0x0A -#define BD718XX_LDO5_VOLTAGE_NUM 0x10 #define BD718XX_LDO6_VOLTAGE_NUM 0x0A /* BD71837 specific voltage configurations */ +#define BD71837_BUCK5_VOLTAGE_NUM 0x10 #define BD71837_BUCK6_VOLTAGE_NUM 0x04 #define BD71837_BUCK7_VOLTAGE_NUM 0x08 +#define BD71837_LDO5_VOLTAGE_NUM 0x10 #define BD71837_LDO7_VOLTAGE_NUM 0x10 /* BD71847 specific voltage configurations */ -#define BD71847_BUCK4_VOLTAGE_NUM 0x04 +#define BD71847_BUCK3_VOLTAGE_NUM 0x18 +#define BD71847_BUCK4_VOLTAGE_NUM 0x08 +#define BD71847_LDO5_VOLTAGE_NUM 0x20 /* Registers specific to BD71837 */ enum { @@ -139,12 +135,20 @@ enum { #define DVS_BUCK_IDLE_MASK 0x3F #define BD718XX_1ST_NODVS_BUCK_MASK 0x07 -#define BD71847_BUCK4_MASK 0x03 -#define BD71837_BUCK6_MASK 0x03 #define BD718XX_3RD_NODVS_BUCK_MASK 0x07 #define BD718XX_4TH_NODVS_BUCK_MASK 0x3F +#define BD71847_BUCK3_MASK 0x07 +#define BD71847_BUCK3_RANGE_MASK 0xC0 +#define BD71847_BUCK4_MASK 0x03 +#define BD71847_BUCK4_RANGE_MASK 0x40 + +#define BD71837_BUCK5_MASK 0x07 +#define BD71837_BUCK5_RANGE_MASK 0x80 +#define BD71837_BUCK6_MASK 0x03 + #define BD718XX_LDO1_MASK 0x03 +#define BD718XX_LDO1_RANGE_MASK 0x20 #define BD718XX_LDO2_MASK 0x20 #define BD718XX_LDO3_MASK 0x0F #define BD718XX_LDO4_MASK 0x0F @@ -152,10 +156,10 @@ enum { #define BD71837_LDO5_MASK 0x0F #define BD71847_LDO5_MASK 0x0F +#define BD71847_LDO5_RANGE_MASK 0x20 #define BD71837_LDO7_MASK 0x0F - /* BD718XX Voltage monitoring masks */ #define BD718XX_BUCK1_VRMON80 0x1 #define BD718XX_BUCK1_VRMON130 0x2 -- cgit v1.2.3 From fef912bf860e8e7e48a2bfb978a356bba743a8b7 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 28 Sep 2018 08:17:19 +0200 Subject: block: genhd: add 'groups' argument to device_add_disk Update device_add_disk() to take an 'groups' argument so that individual drivers can register a device with additional sysfs attributes. This avoids race condition the driver would otherwise have if these groups were to be created with sysfs_add_groups(). Signed-off-by: Martin Wilck Signed-off-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/genhd.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 57864422a2c8..0b820ff05839 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -399,10 +399,11 @@ static inline void free_part_info(struct hd_struct *part) extern void part_round_stats(struct request_queue *q, int cpu, struct hd_struct *part); /* block/genhd.c */ -extern void device_add_disk(struct device *parent, struct gendisk *disk); +extern void device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups); static inline void add_disk(struct gendisk *disk) { - device_add_disk(NULL, disk); + device_add_disk(NULL, disk, NULL); } extern void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk); static inline void add_disk_no_queue_reg(struct gendisk *disk) -- cgit v1.2.3 From d6112f8def514e019658bcc9b57d53acdb71ca3f Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Fri, 7 Sep 2018 09:16:51 +0300 Subject: PCI: Add support for Immediate Readiness MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PCIe r4.0, sec 7.5.1.1.4 defines a new bit in the Status Register: Immediate Readiness – This optional bit, when Set, indicates the Function is guaranteed to be ready to successfully complete valid configuration accesses at any time following any reset that the host is capable of issuing Configuration Requests to this Function. When this bit is Set, for accesses to this Function, software is exempt from all requirements to delay configuration accesses following any type of reset, including but not limited to the timing requirements defined in Section 6.6. This means that all delays after a Conventional or Function Reset can be skipped. This patch reads such bit and caches its value in a flag inside struct pci_dev to be checked later if we should delay or can skip delays after a reset. While at that, also move the explicit msleep(100) call from pcie_flr() and pci_af_flr() to pci_dev_wait(). Signed-off-by: Felipe Balbi [bhelgaas: rename PCI_STATUS_IMMEDIATE to PCI_STATUS_IMM_READY] Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 6925828f9f25..60da5d7d4310 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -325,6 +325,7 @@ struct pci_dev { pci_power_t current_state; /* Current operating state. In ACPI, this is D0-D3, D0 being fully functional, and D3 being off. */ + unsigned int imm_ready:1; /* Supports Immediate Readiness */ u8 pm_cap; /* PM capability offset */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ -- cgit v1.2.3 From f1f207e43b8a49ac2ee3c36a64de1f84651c6079 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 22 Aug 2018 15:04:40 -0500 Subject: of: Add cpu node iterator for_each_of_cpu_node() Iterating thru cpu nodes is a common pattern. Create a common iterator which can find child nodes either by node name or device_type == cpu. Using the former will allow for eventually dropping device_type properties which are deprecated for FDT. Cc: Frank Rowand Reviewed-by: Geert Uytterhoeven Signed-off-by: Rob Herring --- include/linux/of.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..1aca0dbd35df 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -353,6 +353,8 @@ extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); +extern struct device_node *of_get_next_cpu_node(struct device_node *prev); + #define for_each_property_of_node(dn, pp) \ for (pp = dn->properties; pp != NULL; pp = pp->next) @@ -754,6 +756,11 @@ static inline struct device_node *of_get_cpu_node(int cpu, return NULL; } +static inline struct device_node *of_get_next_cpu_node(struct device_node *prev) +{ + return NULL; +} + static inline int of_n_addr_cells(struct device_node *np) { return 0; @@ -1217,6 +1224,10 @@ static inline int of_property_read_s32(const struct device_node *np, for (child = of_get_next_available_child(parent, NULL); child != NULL; \ child = of_get_next_available_child(parent, child)) +#define for_each_of_cpu_node(cpu) \ + for (cpu = of_get_next_cpu_node(NULL); cpu != NULL; \ + cpu = of_get_next_cpu_node(cpu)) + #define for_each_node_with_property(dn, prop_name) \ for (dn = of_find_node_with_property(NULL, prop_name); dn; \ dn = of_find_node_with_property(dn, prop_name)) -- cgit v1.2.3 From 9e288cefcc551c7b5b04f8abc7099d3451a70f5f Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 25 Sep 2018 09:34:05 +0200 Subject: clk: renesas: Convert to SPDX identifiers This patch updates license to use SPDX-License-Identifier instead of verbose license text. Signed-off-by: Kuninori Morimoto [rebased against clk-spdx] Signed-off-by: Geert Uytterhoeven Reviewed-by: Simon Horman Signed-off-by: Stephen Boyd --- include/linux/clk/renesas.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk/renesas.h b/include/linux/clk/renesas.h index 9ebf1f8243bb..0ebbe2f0b45e 100644 --- a/include/linux/clk/renesas.h +++ b/include/linux/clk/renesas.h @@ -1,14 +1,10 @@ -/* +/* SPDX-License-Identifier: GPL-2.0+ + * * Copyright 2013 Ideas On Board SPRL * Copyright 2013, 2014 Horms Solutions Ltd. * * Contact: Laurent Pinchart * Contact: Simon Horman - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __LINUX_CLK_RENESAS_H_ -- cgit v1.2.3 From 3d0186bb068e6cc6c23dc1d2f0b1cf64894c40ea Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 16 Jun 2018 17:32:07 -0400 Subject: Update email address Redirect some older email addresses that are in the git logs. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 2dfc8006fe64..9e4c86853fa4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -4,7 +4,7 @@ /* * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation - * Author: Matthew Wilcox + * Author: Matthew Wilcox */ #include -- cgit v1.2.3 From 3159f943aafdbacb2f94c38fdaadabf2bbde2a14 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 3 Nov 2017 13:30:42 -0400 Subject: xarray: Replace exceptional entries Introduce xarray value entries and tagged pointers to replace radix tree exceptional entries. This is a slight change in encoding to allow the use of an extra bit (we can now store BITS_PER_LONG - 1 bits in a value entry). It is also a change in emphasis; exceptional entries are intimidating and different. As the comment explains, you can choose to store values or pointers in the xarray and they are both first-class citizens. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 36 ++++------------ include/linux/swapops.h | 19 ++++----- include/linux/xarray.h | 102 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 117 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 34149e8b5f73..e9e76ab4fbbf 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -28,34 +28,26 @@ #include #include #include +#include /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: * * 00 - data pointer - * 01 - internal entry - * 10 - exceptional entry - * 11 - this bit combination is currently unused/reserved + * 10 - internal entry + * x1 - value entry * * The internal entry may be a pointer to the next level in the tree, a * sibling entry, or an indicator that the entry in this slot has been moved * to another location in the tree and the lookup should be restarted. While * NULL fits the 'data pointer' pattern, it means that there is no entry in * the tree for this index (no matter what level of the tree it is found at). - * This means that you cannot store NULL in the tree as a value for the index. + * This means that storing a NULL entry in the tree is the same as deleting + * the entry from the tree. */ #define RADIX_TREE_ENTRY_MASK 3UL -#define RADIX_TREE_INTERNAL_NODE 1UL - -/* - * Most users of the radix tree store pointers but shmem/tmpfs stores swap - * entries in the same tree. They are marked as exceptional entries to - * distinguish them from pointers to struct page. - * EXCEPTIONAL_ENTRY tests the bit, EXCEPTIONAL_SHIFT shifts content past it. - */ -#define RADIX_TREE_EXCEPTIONAL_ENTRY 2 -#define RADIX_TREE_EXCEPTIONAL_SHIFT 2 +#define RADIX_TREE_INTERNAL_NODE 2UL static inline bool radix_tree_is_internal_node(void *ptr) { @@ -83,11 +75,10 @@ static inline bool radix_tree_is_internal_node(void *ptr) /* * @count is the count of every non-NULL element in the ->slots array - * whether that is an exceptional entry, a retry entry, a user pointer, + * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @exceptional is the count of every element in ->slots which is - * either radix_tree_exceptional_entry() or is a sibling entry for an - * exceptional entry. + * either a value entry or a sibling of a value entry. */ struct radix_tree_node { unsigned char shift; /* Bits remaining in each slot */ @@ -268,17 +259,6 @@ static inline int radix_tree_deref_retry(void *arg) return unlikely(radix_tree_is_internal_node(arg)); } -/** - * radix_tree_exceptional_entry - radix_tree_deref_slot gave exceptional entry? - * @arg: value returned by radix_tree_deref_slot - * Returns: 0 if well-aligned pointer, non-0 if exceptional entry. - */ -static inline int radix_tree_exceptional_entry(void *arg) -{ - /* Not unlikely because radix_tree_exception often tested first */ - return (unsigned long)arg & RADIX_TREE_EXCEPTIONAL_ENTRY; -} - /** * radix_tree_exception - radix_tree_deref_slot returned either exception? * @arg: value returned by radix_tree_deref_slot diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 22af9d8a84ae..4d961668e5fc 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -18,9 +18,8 @@ * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ -#define SWP_TYPE_SHIFT(e) ((sizeof(e.val) * 8) - \ - (MAX_SWAPFILES_SHIFT + RADIX_TREE_EXCEPTIONAL_SHIFT)) -#define SWP_OFFSET_MASK(e) ((1UL << SWP_TYPE_SHIFT(e)) - 1) +#define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) +#define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) /* * Store a type+offset into a swp_entry_t in an arch-independent format @@ -29,8 +28,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) { swp_entry_t ret; - ret.val = (type << SWP_TYPE_SHIFT(ret)) | - (offset & SWP_OFFSET_MASK(ret)); + ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK); return ret; } @@ -40,7 +38,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) */ static inline unsigned swp_type(swp_entry_t entry) { - return (entry.val >> SWP_TYPE_SHIFT(entry)); + return (entry.val >> SWP_TYPE_SHIFT); } /* @@ -49,7 +47,7 @@ static inline unsigned swp_type(swp_entry_t entry) */ static inline pgoff_t swp_offset(swp_entry_t entry) { - return entry.val & SWP_OFFSET_MASK(entry); + return entry.val & SWP_OFFSET_MASK; } #ifdef CONFIG_MMU @@ -90,16 +88,13 @@ static inline swp_entry_t radix_to_swp_entry(void *arg) { swp_entry_t entry; - entry.val = (unsigned long)arg >> RADIX_TREE_EXCEPTIONAL_SHIFT; + entry.val = xa_to_value(arg); return entry; } static inline void *swp_to_radix_entry(swp_entry_t entry) { - unsigned long value; - - value = entry.val << RADIX_TREE_EXCEPTIONAL_SHIFT; - return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY); + return xa_mk_value(entry.val); } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 9e4c86853fa4..5c8acfc4ff55 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -5,9 +5,111 @@ * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox + * + * See Documentation/core-api/xarray.rst for how to use the XArray. */ +#include #include +#include + +/* + * The bottom two bits of the entry determine how the XArray interprets + * the contents: + * + * 00: Pointer entry + * 10: Internal entry + * x1: Value entry or tagged pointer + * + * Attempting to store internal entries in the XArray is a bug. + */ + +#define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) + +/** + * xa_mk_value() - Create an XArray entry from an integer. + * @v: Value to store in XArray. + * + * Context: Any context. + * Return: An entry suitable for storing in the XArray. + */ +static inline void *xa_mk_value(unsigned long v) +{ + WARN_ON((long)v < 0); + return (void *)((v << 1) | 1); +} + +/** + * xa_to_value() - Get value stored in an XArray entry. + * @entry: XArray entry. + * + * Context: Any context. + * Return: The value stored in the XArray entry. + */ +static inline unsigned long xa_to_value(const void *entry) +{ + return (unsigned long)entry >> 1; +} + +/** + * xa_is_value() - Determine if an entry is a value. + * @entry: XArray entry. + * + * Context: Any context. + * Return: True if the entry is a value, false if it is a pointer. + */ +static inline bool xa_is_value(const void *entry) +{ + return (unsigned long)entry & 1; +} + +/** + * xa_tag_pointer() - Create an XArray entry for a tagged pointer. + * @p: Plain pointer. + * @tag: Tag value (0, 1 or 3). + * + * If the user of the XArray prefers, they can tag their pointers instead + * of storing value entries. Three tags are available (0, 1 and 3). + * These are distinct from the xa_mark_t as they are not replicated up + * through the array and cannot be searched for. + * + * Context: Any context. + * Return: An XArray entry. + */ +static inline void *xa_tag_pointer(void *p, unsigned long tag) +{ + return (void *)((unsigned long)p | tag); +} + +/** + * xa_untag_pointer() - Turn an XArray entry into a plain pointer. + * @entry: XArray entry. + * + * If you have stored a tagged pointer in the XArray, call this function + * to get the untagged version of the pointer. + * + * Context: Any context. + * Return: A pointer. + */ +static inline void *xa_untag_pointer(void *entry) +{ + return (void *)((unsigned long)entry & ~3UL); +} + +/** + * xa_pointer_tag() - Get the tag stored in an XArray entry. + * @entry: XArray entry. + * + * If you have stored a tagged pointer in the XArray, call this function + * to get the tag of that pointer. + * + * Context: Any context. + * Return: A tag. + */ +static inline unsigned int xa_pointer_tag(void *entry) +{ + return (unsigned long)entry & 3UL; +} #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) -- cgit v1.2.3 From 02c02bf12c5d838603eed44195d3e91f094e2ab2 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 3 Nov 2017 23:09:45 -0400 Subject: xarray: Change definition of sibling entries Instead of storing a pointer to the slot containing the canonical entry, store the offset of the slot. Produces slightly more efficient code (~300 bytes) and simplifies the implementation. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 5 +-- include/linux/xarray.h | 92 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 93 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index e9e76ab4fbbf..60f3d8eb2cb7 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -59,10 +59,7 @@ static inline bool radix_tree_is_internal_node(void *ptr) #define RADIX_TREE_MAX_TAGS 3 -#ifndef RADIX_TREE_MAP_SHIFT -#define RADIX_TREE_MAP_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) -#endif - +#define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 5c8acfc4ff55..4d1cd7a083e8 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -22,6 +22,12 @@ * x1: Value entry or tagged pointer * * Attempting to store internal entries in the XArray is a bug. + * + * Most internal entries are pointers to the next node in the tree. + * The following internal entries have a special meaning: + * + * 0-62: Sibling entries + * 256: Retry entry */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) @@ -111,6 +117,42 @@ static inline unsigned int xa_pointer_tag(void *entry) return (unsigned long)entry & 3UL; } +/* + * xa_mk_internal() - Create an internal entry. + * @v: Value to turn into an internal entry. + * + * Context: Any context. + * Return: An XArray internal entry corresponding to this value. + */ +static inline void *xa_mk_internal(unsigned long v) +{ + return (void *)((v << 2) | 2); +} + +/* + * xa_to_internal() - Extract the value from an internal entry. + * @entry: XArray entry. + * + * Context: Any context. + * Return: The value which was stored in the internal entry. + */ +static inline unsigned long xa_to_internal(const void *entry) +{ + return (unsigned long)entry >> 2; +} + +/* + * xa_is_internal() - Is the entry an internal entry? + * @entry: XArray entry. + * + * Context: Any context. + * Return: %true if the entry is an internal entry. + */ +static inline bool xa_is_internal(const void *entry) +{ + return ((unsigned long)entry & 3) == 2; +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -123,4 +165,54 @@ static inline unsigned int xa_pointer_tag(void *entry) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) +/* Everything below here is the Advanced API. Proceed with caution. */ + +/* + * The xarray is constructed out of a set of 'chunks' of pointers. Choosing + * the best chunk size requires some tradeoffs. A power of two recommends + * itself so that we can walk the tree based purely on shifts and masks. + * Generally, the larger the better; as the number of slots per level of the + * tree increases, the less tall the tree needs to be. But that needs to be + * balanced against the memory consumption of each node. On a 64-bit system, + * xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we + * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. + */ +#ifndef XA_CHUNK_SHIFT +#define XA_CHUNK_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) +#endif +#define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) +#define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) + +/* Private */ +static inline bool xa_is_node(const void *entry) +{ + return xa_is_internal(entry) && (unsigned long)entry > 4096; +} + +/* Private */ +static inline void *xa_mk_sibling(unsigned int offset) +{ + return xa_mk_internal(offset); +} + +/* Private */ +static inline unsigned long xa_to_sibling(const void *entry) +{ + return xa_to_internal(entry); +} + +/** + * xa_is_sibling() - Is the entry a sibling entry? + * @entry: Entry retrieved from the XArray + * + * Return: %true if the entry is a sibling entry. + */ +static inline bool xa_is_sibling(const void *entry) +{ + return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) && + (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); +} + +#define XA_RETRY_ENTRY xa_mk_internal(256) + #endif /* _LINUX_XARRAY_H */ -- cgit v1.2.3 From 492ecf6d6598e7c3b0b1372653ed21da50ddfb09 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Wed, 12 Sep 2018 09:43:25 -0500 Subject: docs: fpga: document fpga manager flags Add flags #defines to kerneldoc documentation in a useful place. Signed-off-by: Alan Tull Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 8942e61f0028..8ab5df769923 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -53,12 +53,20 @@ enum fpga_mgr_states { FPGA_MGR_STATE_OPERATING, }; -/* - * FPGA Manager flags - * FPGA_MGR_PARTIAL_RECONFIG: do partial reconfiguration if supported - * FPGA_MGR_EXTERNAL_CONFIG: FPGA has been configured prior to Linux booting - * FPGA_MGR_BITSTREAM_LSB_FIRST: SPI bitstream bit order is LSB first - * FPGA_MGR_COMPRESSED_BITSTREAM: FPGA bitstream is compressed +/** + * DOC: FPGA Manager flags + * + * Flags used in the &fpga_image_info->flags field + * + * %FPGA_MGR_PARTIAL_RECONFIG: do partial reconfiguration if supported + * + * %FPGA_MGR_EXTERNAL_CONFIG: FPGA has been configured prior to Linux booting + * + * %FPGA_MGR_ENCRYPTED_BITSTREAM: indicates bitstream is encrypted + * + * %FPGA_MGR_BITSTREAM_LSB_FIRST: SPI bitstream bit order is LSB first + * + * %FPGA_MGR_COMPRESSED_BITSTREAM: FPGA bitstream is compressed */ #define FPGA_MGR_PARTIAL_RECONFIG BIT(0) #define FPGA_MGR_EXTERNAL_CONFIG BIT(1) -- cgit v1.2.3 From 29efbc6aea9d9bd9aa9870a9afc1882046303cf9 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:07:27 +0200 Subject: Compiler Attributes: remove unused attributes __optimize and __deprecate_for_modules are unused in the whole kernel tree. Simply drop them. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-gcc.h | 2 -- include/linux/compiler.h | 4 ---- include/linux/compiler_types.h | 1 - 3 files changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 4d36b27214fd..1302b425e625 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -81,8 +81,6 @@ #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -#define __optimize(level) __attribute__((__optimize__(level))) - #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #ifndef __CHECKER__ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 681d866efb1e..7c0157d50964 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -301,10 +301,6 @@ static inline void *offset_to_ptr(const int *off) #endif /* __ASSEMBLY__ */ -#ifndef __optimize -# define __optimize(level) -#endif - /* Compile time object size, -1 for unknown */ #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index db192becfec4..a19562cb047c 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -108,7 +108,6 @@ struct ftrace_likely_data { /* Don't. Just don't. */ #define __deprecated -#define __deprecated_for_modules #endif /* __KERNEL__ */ -- cgit v1.2.3 From 5c67a52f3da0f0d22764f2daec417702695a8112 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:13:37 +0200 Subject: Compiler Attributes: always use the extra-underscores syntax The attribute syntax optionally allows to surround attribute names with "__" in order to avoid collisions with macros of the same name (see https://gcc.gnu.org/onlinedocs/gcc/Attribute-Syntax.html). This homogenizes all attributes to use the syntax with underscores. While there are currently only a handful of cases of some TUs defining macros like "error" which may collide with the attributes, this should prevent futures surprises. This has been done only for "standard" attributes supported by the major compilers. In other words, those of third-party tools (e.g. sparse, plugins...) have not been changed for the moment. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-clang.h | 2 +- include/linux/compiler-gcc.h | 12 ++++++------ include/linux/compiler-intel.h | 2 +- include/linux/compiler.h | 8 ++++---- include/linux/compiler_types.h | 42 +++++++++++++++++++++--------------------- 5 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index b1ce500fe8b3..d11cad61ba5c 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -21,7 +21,7 @@ #define __SANITIZE_ADDRESS__ #endif -#define __no_sanitize_address __attribute__((no_sanitize("address"))) +#define __no_sanitize_address __attribute__((__no_sanitize__("address"))) /* * Not all versions of clang implement the the type-generic versions diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 1302b425e625..7a1de7683df5 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -76,7 +76,7 @@ #endif #ifdef RETPOLINE -#define __noretpoline __attribute__((indirect_branch("keep"))) +#define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) @@ -84,8 +84,8 @@ #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #ifndef __CHECKER__ -#define __compiletime_warning(message) __attribute__((warning(message))) -#define __compiletime_error(message) __attribute__((error(message))) +#define __compiletime_warning(message) __attribute__((__warning__(message))) +#define __compiletime_error(message) __attribute__((__error__(message))) #ifdef LATENT_ENTROPY_PLUGIN #define __latent_entropy __attribute__((latent_entropy)) @@ -134,7 +134,7 @@ * optimizer that something else uses this function or variable, thus preventing * this. */ -#define __visible __attribute__((externally_visible)) +#define __visible __attribute__((__externally_visible__)) /* gcc version specific checks */ @@ -191,7 +191,7 @@ * should not be applied to that function. * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 */ -#define __no_sanitize_address __attribute__((no_sanitize_address)) +#define __no_sanitize_address __attribute__((__no_sanitize_address__)) #endif #if GCC_VERSION >= 50100 @@ -199,7 +199,7 @@ * Mark structures as requiring designated initializers. * https://gcc.gnu.org/onlinedocs/gcc/Designated-Inits.html */ -#define __designated_init __attribute__((designated_init)) +#define __designated_init __attribute__((__designated_init__)) #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 4c7f9befa9f6..fef8bb3e53ef 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -42,4 +42,4 @@ * and may be redefined here because they should not be shared with other * compilers, like clang. */ -#define __visible __attribute__((externally_visible)) +#define __visible __attribute__((__externally_visible__)) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 7c0157d50964..ec4a28bad2c6 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -24,7 +24,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, long ______r; \ static struct ftrace_likely_data \ __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_annotated_branch"))) \ + __attribute__((__section__("_ftrace_annotated_branch"))) \ ______f = { \ .data.func = __func__, \ .data.file = __FILE__, \ @@ -60,7 +60,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, int ______r; \ static struct ftrace_branch_data \ __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_branch"))) \ + __attribute__((__section__("_ftrace_branch"))) \ ______f = { \ .func = __func__, \ .file = __FILE__, \ @@ -146,7 +146,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ - __attribute__((section("___kentry" "+" #sym ), used)) \ + __attribute__((__section__("___kentry" "+" #sym ), used)) \ = (unsigned long)&sym; #endif @@ -287,7 +287,7 @@ unsigned long read_word_at_a_time(const void *addr) * visible to the compiler. */ #define __ADDRESSABLE(sym) \ - static void * __attribute__((section(".discard.addressable"), used)) \ + static void * __attribute__((__section__(".discard.addressable"), used)) \ __PASTE(__addressable_##sym, __LINE__) = (void *)&sym; /** diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index a19562cb047c..8fbdd47dd3d0 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -195,26 +195,26 @@ struct ftrace_likely_data { * would be. * [...] */ -#define __pure __attribute__((pure)) -#define __aligned(x) __attribute__((aligned(x))) -#define __aligned_largest __attribute__((aligned)) -#define __printf(a, b) __attribute__((format(printf, a, b))) -#define __scanf(a, b) __attribute__((format(scanf, a, b))) -#define __maybe_unused __attribute__((unused)) -#define __always_unused __attribute__((unused)) -#define __mode(x) __attribute__((mode(x))) +#define __pure __attribute__((__pure__)) +#define __aligned(x) __attribute__((__aligned__(x))) +#define __aligned_largest __attribute__((__aligned__)) +#define __printf(a, b) __attribute__((__format__(printf, a, b))) +#define __scanf(a, b) __attribute__((__format__(scanf, a, b))) +#define __maybe_unused __attribute__((__unused__)) +#define __always_unused __attribute__((__unused__)) +#define __mode(x) __attribute__((__mode__(x))) #define __malloc __attribute__((__malloc__)) #define __used __attribute__((__used__)) -#define __noreturn __attribute__((noreturn)) -#define __packed __attribute__((packed)) -#define __weak __attribute__((weak)) -#define __alias(symbol) __attribute__((alias(#symbol))) -#define __cold __attribute__((cold)) +#define __noreturn __attribute__((__noreturn__)) +#define __packed __attribute__((__packed__)) +#define __weak __attribute__((__weak__)) +#define __alias(symbol) __attribute__((__alias__(#symbol))) +#define __cold __attribute__((__cold__)) #define __section(S) __attribute__((__section__(#S))) #ifdef CONFIG_ENABLE_MUST_CHECK -#define __must_check __attribute__((warn_unused_result)) +#define __must_check __attribute__((__warn_unused_result__)) #else #define __must_check #endif @@ -222,7 +222,7 @@ struct ftrace_likely_data { #if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) #define notrace __attribute__((hotpatch(0, 0))) #else -#define notrace __attribute__((no_instrument_function)) +#define notrace __attribute__((__no_instrument_function__)) #endif /* @@ -231,7 +231,7 @@ struct ftrace_likely_data { * stack and frame pointer being set up and there is no chance to * restore the lr register to the value before mcount was called. */ -#define __naked __attribute__((naked)) notrace +#define __naked __attribute__((__naked__)) notrace #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) @@ -242,7 +242,7 @@ struct ftrace_likely_data { * defined so the gnu89 semantics are the default. */ #ifdef __GNUC_STDC_INLINE__ -# define __gnu_inline __attribute__((gnu_inline)) +# define __gnu_inline __attribute__((__gnu_inline__)) #else # define __gnu_inline #endif @@ -262,17 +262,17 @@ struct ftrace_likely_data { #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) #define inline \ - inline __attribute__((always_inline, unused)) notrace __gnu_inline + inline __attribute__((__always_inline__, __unused__)) notrace __gnu_inline #else -#define inline inline __attribute__((unused)) notrace __gnu_inline +#define inline inline __attribute__((__unused__)) notrace __gnu_inline #endif #define __inline__ inline #define __inline inline -#define noinline __attribute__((noinline)) +#define noinline __attribute__((__noinline__)) #ifndef __always_inline -#define __always_inline inline __attribute__((always_inline)) +#define __always_inline inline __attribute__((__always_inline__)) #endif /* -- cgit v1.2.3 From c2c640aa04cc4e6caf0ff17ff18b3784e0c99566 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:45:01 +0200 Subject: Compiler Attributes: remove unneeded tests Attributes const and always_inline have tests around them which are unneeded, since they are supported by gcc >= 4.6, clang >= 3 and icc >= 13. https://godbolt.org/z/DFPq37 In the case of gnu_inline, we do not need to test for __GNUC_STDC_INLINE__ because, regardless of the current inlining behavior, we can simply always force the old GCC inlining behavior by using the attribute in all cases. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 8fbdd47dd3d0..5ff9cda893f4 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -158,10 +158,6 @@ struct ftrace_likely_data { (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) -#ifndef __attribute_const__ -#define __attribute_const__ __attribute__((__const__)) -#endif - #ifndef __noclone #define __noclone #endif @@ -196,6 +192,7 @@ struct ftrace_likely_data { * [...] */ #define __pure __attribute__((__pure__)) +#define __attribute_const__ __attribute__((__const__)) #define __aligned(x) __attribute__((__aligned__(x))) #define __aligned_largest __attribute__((__aligned__)) #define __printf(a, b) __attribute__((__format__(printf, a, b))) @@ -211,6 +208,8 @@ struct ftrace_likely_data { #define __alias(symbol) __attribute__((__alias__(#symbol))) #define __cold __attribute__((__cold__)) #define __section(S) __attribute__((__section__(#S))) +#define __always_inline inline __attribute__((__always_inline__)) +#define __gnu_inline __attribute__((__gnu_inline__)) #ifdef CONFIG_ENABLE_MUST_CHECK @@ -235,18 +234,6 @@ struct ftrace_likely_data { #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) -/* - * Feature detection for gnu_inline (gnu89 extern inline semantics). Either - * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics, - * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not - * defined so the gnu89 semantics are the default. - */ -#ifdef __GNUC_STDC_INLINE__ -# define __gnu_inline __attribute__((__gnu_inline__)) -#else -# define __gnu_inline -#endif - /* * Force always-inline if the user requests it so via the .config. * GCC does not warn about unused static inline functions for @@ -271,10 +258,6 @@ struct ftrace_likely_data { #define __inline inline #define noinline __attribute__((__noinline__)) -#ifndef __always_inline -#define __always_inline inline __attribute__((__always_inline__)) -#endif - /* * Rather then using noinline to prevent stack consumption, use * noinline_for_stack instead. For documentation reasons. -- cgit v1.2.3 From ec0bbef66f867854691d5af18c2231d746958e0e Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:25:14 +0200 Subject: Compiler Attributes: homogenize __must_be_array Different definitions of __must_be_array: * gcc: disabled for __CHECKER__ * clang: same definition as gcc's, but without __CHECKER__ * intel: the comment claims __builtin_types_compatible_p() is unsupported; but icc seems to support it since 13.0.1 (released in 2012). See https://godbolt.org/z/S0l6QQ Therefore, we can remove all of them and have a single definition in compiler.h Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-clang.h | 1 - include/linux/compiler-gcc.h | 7 ------- include/linux/compiler-intel.h | 3 --- include/linux/compiler.h | 7 +++++++ 4 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index d11cad61ba5c..fa9532f8d885 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -41,6 +41,5 @@ * compilers, like ICC. */ #define barrier() __asm__ __volatile__("" : : : "memory") -#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) #define __assume_aligned(a, ...) \ __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 7a1de7683df5..3b32bbfa5a49 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -68,13 +68,6 @@ */ #define uninitialized_var(x) x = x -#ifdef __CHECKER__ -#define __must_be_array(a) 0 -#else -/* &a[0] degrades to a pointer: a different type from an array */ -#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) -#endif - #ifdef RETPOLINE #define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index fef8bb3e53ef..6004b4588bd4 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -29,9 +29,6 @@ */ #define OPTIMIZER_HIDE_VAR(var) barrier() -/* Intel ECC compiler doesn't support __builtin_types_compatible_p() */ -#define __must_be_array(a) 0 - #endif /* icc has this, but it's called _bswap16 */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ec4a28bad2c6..165b1d5683ed 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -357,4 +357,11 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") +#ifdef __CHECKER__ +#define __must_be_array(a) 0 +#else +/* &a[0] degrades to a pointer: a different type from an array */ +#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) +#endif + #endif /* __LINUX_COMPILER_H */ -- cgit v1.2.3 From 989bd5000f36052df604888ed12bb6ef390786b7 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Fri, 31 Aug 2018 18:00:16 +0200 Subject: Compiler Attributes: remove unneeded sparse (__CHECKER__) tests Sparse knows about a few more attributes now, so we can remove the __CHECKER__ conditions from them (which, in turn, allow us to move some of them later on to compiler_attributes.h). * assume_aligned: since sparse's commit ffc860b ("sparse: ignore __assume_aligned__ attribute"), included in 0.5.1 * error: since sparse's commit 0a04210 ("sparse: Add 'error' to ignored attributes"), included in 0.5.0 * hotpatch: since sparse's commit 6043210 ("sparse/parse.c: ignore hotpatch attribute"), included in 0.5.1 * warning: since sparse's commit 977365d ("Avoid "attribute 'warning': unknown attribute" warning"), included in 0.4.2 On top of that, __must_be_array does not need it either because: * Even ancient versions of sparse do not have a problem * BUILD_BUG_ON_ZERO() is currently disabled for __CHECKER__ Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-gcc.h | 6 ++---- include/linux/compiler.h | 4 ---- include/linux/compiler_types.h | 2 +- 3 files changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 3b32bbfa5a49..1ca6a51cfaa9 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -76,14 +76,12 @@ #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) -#ifndef __CHECKER__ #define __compiletime_warning(message) __attribute__((__warning__(message))) #define __compiletime_error(message) __attribute__((__error__(message))) -#ifdef LATENT_ENTROPY_PLUGIN +#if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) #define __latent_entropy __attribute__((latent_entropy)) #endif -#endif /* __CHECKER__ */ /* * calling noreturn functions, __builtin_unreachable() and __builtin_trap() @@ -131,7 +129,7 @@ /* gcc version specific checks */ -#if GCC_VERSION >= 40900 && !defined(__CHECKER__) +#if GCC_VERSION >= 40900 /* * __assume_aligned(n, k): Tell the optimizer that the returned * pointer can be assumed to be k modulo n. The second argument is diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 165b1d5683ed..4030a2940d6b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -357,11 +357,7 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") -#ifdef __CHECKER__ -#define __must_be_array(a) 0 -#else /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) -#endif #endif /* __LINUX_COMPILER_H */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 5ff9cda893f4..a3eceb3ad1b3 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -218,7 +218,7 @@ struct ftrace_likely_data { #define __must_check #endif -#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) +#if defined(CC_USING_HOTPATCH) #define notrace __attribute__((hotpatch(0, 0))) #else #define notrace __attribute__((__no_instrument_function__)) -- cgit v1.2.3 From 66dbeef915f275dad6c8656b31667ef9640f5639 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 3 Sep 2018 18:34:18 +0200 Subject: Compiler Attributes: add missing SPDX ID in compiler_types.h Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index a3eceb3ad1b3..ed7c0e4a180e 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_COMPILER_TYPES_H #define __LINUX_COMPILER_TYPES_H -- cgit v1.2.3 From a3f8a30f3f0079c7edfc72e329eee8594fb3e3cb Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 20:36:59 +0200 Subject: Compiler Attributes: use feature checks instead of version checks Instead of using version checks per-compiler to define (or not) each attribute, use __has_attribute to test for them, following the cleanup started with commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive"), which is supported on gcc >= 5, clang >= 2.9 and icc >= 17. In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute by hand. All the attributes that can be unconditionally defined and directly map to compiler attribute(s) (even if optional) have been moved to a new file include/linux/compiler_attributes.h In an effort to make the file as regular as possible, comments stating the purpose of attributes have been removed. Instead, links to the compiler docs have been added (i.e. to gcc and, if available, to clang as well). In addition, they have been sorted. Finally, if an attribute is optional (i.e. if it is guarded by __has_attribute), the reason has been stated for future reference. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-clang.h | 4 - include/linux/compiler-gcc.h | 51 -------- include/linux/compiler-intel.h | 6 - include/linux/compiler_attributes.h | 244 ++++++++++++++++++++++++++++++++++++ include/linux/compiler_types.h | 74 ++--------- 5 files changed, 254 insertions(+), 125 deletions(-) create mode 100644 include/linux/compiler_attributes.h (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index fa9532f8d885..3e7dafb3ea80 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -21,8 +21,6 @@ #define __SANITIZE_ADDRESS__ #endif -#define __no_sanitize_address __attribute__((__no_sanitize__("address"))) - /* * Not all versions of clang implement the the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements @@ -41,5 +39,3 @@ * compilers, like ICC. */ #define barrier() __asm__ __volatile__("" : : : "memory") -#define __assume_aligned(a, ...) \ - __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 1ca6a51cfaa9..cfac027e1625 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -108,9 +108,6 @@ __builtin_unreachable(); \ } while (0) -/* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) - #if defined(RANDSTRUCT_PLUGIN) && !defined(__CHECKER__) #define __randomize_layout __attribute__((randomize_layout)) #define __no_randomize_layout __attribute__((no_randomize_layout)) @@ -119,32 +116,6 @@ #define randomized_struct_fields_end } __randomize_layout; #endif -/* - * When used with Link Time Optimization, gcc can optimize away C functions or - * variables which are referenced only from assembly code. __visible tells the - * optimizer that something else uses this function or variable, thus preventing - * this. - */ -#define __visible __attribute__((__externally_visible__)) - -/* gcc version specific checks */ - -#if GCC_VERSION >= 40900 -/* - * __assume_aligned(n, k): Tell the optimizer that the returned - * pointer can be assumed to be k modulo n. The second argument is - * optional (default 0), so we use a variadic macro to make the - * shorthand. - * - * Beware: Do not apply this to functions which may return - * ERR_PTRs. Also, it is probably unwise to apply it to functions - * returning extra information in the low bits (but in that case the - * compiler should see some alignment anyway, when the return value is - * massaged by 'flags = ptr & 3; ptr &= ~3;'). - */ -#define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) -#endif - /* * GCC 'asm goto' miscompiles certain code sequences: * @@ -176,32 +147,10 @@ #define KASAN_ABI_VERSION 3 #endif -#if GCC_VERSION >= 40902 -/* - * Tell the compiler that address safety instrumentation (KASAN) - * should not be applied to that function. - * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - */ -#define __no_sanitize_address __attribute__((__no_sanitize_address__)) -#endif - #if GCC_VERSION >= 50100 -/* - * Mark structures as requiring designated initializers. - * https://gcc.gnu.org/onlinedocs/gcc/Designated-Inits.html - */ -#define __designated_init __attribute__((__designated_init__)) #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif -#if !defined(__noclone) -#define __noclone /* not needed */ -#endif - -#if !defined(__no_sanitize_address) -#define __no_sanitize_address -#endif - /* * Turn individual warnings and errors on and off locally, depending * on version. diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 6004b4588bd4..517bd14e1222 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -34,9 +34,3 @@ /* icc has this, but it's called _bswap16 */ #define __HAVE_BUILTIN_BSWAP16__ #define __builtin_bswap16 _bswap16 - -/* The following are for compatibility with GCC, from compiler-gcc.h, - * and may be redefined here because they should not be shared with other - * compilers, like clang. - */ -#define __visible __attribute__((__externally_visible__)) diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h new file mode 100644 index 000000000000..f0f9fc398440 --- /dev/null +++ b/include/linux/compiler_attributes.h @@ -0,0 +1,244 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_COMPILER_ATTRIBUTES_H +#define __LINUX_COMPILER_ATTRIBUTES_H + +/* + * The attributes in this file are unconditionally defined and they directly + * map to compiler attribute(s) -- except those that are optional. + * + * Any other "attributes" (i.e. those that depend on a configuration option, + * on a compiler, on an architecture, on plugins, on other attributes...) + * should be defined elsewhere (e.g. compiler_types.h or compiler-*.h). + * + * This file is meant to be sorted (by actual attribute name, + * not by #define identifier). Use the __attribute__((__name__)) syntax + * (i.e. with underscores) to avoid future collisions with other macros. + * If an attribute is optional, state the reason in the comment. + */ + +/* + * To check for optional attributes, we use __has_attribute, which is supported + * on gcc >= 5, clang >= 2.9 and icc >= 17. In the meantime, to support + * 4.6 <= gcc < 5, we implement __has_attribute by hand. + * + * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__ + * depending on the compiler used to build it; however, these attributes have + * no semantic effects for sparse, so it does not matter. Also note that, + * in order to avoid sparse's warnings, even the unsupported ones must be + * defined to 0. + */ +#ifndef __has_attribute +# define __has_attribute(x) __GCC4_has_attribute_##x +# define __GCC4_has_attribute___assume_aligned__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___designated_init__ 0 +# define __GCC4_has_attribute___externally_visible__ 1 +# define __GCC4_has_attribute___noclone__ 1 +# define __GCC4_has_attribute___optimize__ 1 +# define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute + */ +#define __alias(symbol) __attribute__((__alias__(#symbol))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-aligned-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-aligned-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-aligned-variable-attribute + */ +#define __aligned(x) __attribute__((__aligned__(x))) +#define __aligned_largest __attribute__((__aligned__)) + +/* + * Note: users of __always_inline currently do not write "inline" themselves, + * which seems to be required by gcc to apply the attribute according + * to its docs (and also "warning: always_inline function might not be + * inlinable [-Wattributes]" is emitted). + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-always_005finline-function-attribute + * clang: mentioned + */ +#define __always_inline inline __attribute__((__always_inline__)) + +/* + * The second argument is optional (default 0), so we use a variadic macro + * to make the shorthand. + * + * Beware: Do not apply this to functions which may return + * ERR_PTRs. Also, it is probably unwise to apply it to functions + * returning extra information in the low bits (but in that case the + * compiler should see some alignment anyway, when the return value is + * massaged by 'flags = ptr & 3; ptr &= ~3;'). + * + * Optional: only supported since gcc >= 4.9 + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#assume-aligned + */ +#if __has_attribute(__assume_aligned__) +# define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) +#else +# define __assume_aligned(a, ...) +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute + */ +#define __cold __attribute__((__cold__)) + +/* + * Note the long name. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-const-function-attribute + */ +#define __attribute_const__ __attribute__((__const__)) + +/* + * Don't. Just don't. See commit 771c035372a0 ("deprecate the '__deprecated' + * attribute warnings entirely and for good") for more information. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-deprecated-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-deprecated-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-deprecated-variable-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Enumerator-Attributes.html#index-deprecated-enumerator-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#deprecated + */ +#define __deprecated + +/* + * Optional: only supported since gcc >= 5.1 + * Optional: not supported by clang + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-designated_005finit-type-attribute + */ +#if __has_attribute(__designated_init__) +# define __designated_init __attribute__((__designated_init__)) +#else +# define __designated_init +#endif + +/* + * Optional: not supported by clang + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-externally_005fvisible-function-attribute + */ +#if __has_attribute(__externally_visible__) +# define __visible __attribute__((__externally_visible__)) +#else +# define __visible +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-format-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#format + */ +#define __printf(a, b) __attribute__((__format__(printf, a, b))) +#define __scanf(a, b) __attribute__((__format__(scanf, a, b))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-gnu_005finline-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#gnu-inline + */ +#define __gnu_inline __attribute__((__gnu_inline__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-malloc-function-attribute + */ +#define __malloc __attribute__((__malloc__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-mode-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-mode-variable-attribute + */ +#define __mode(x) __attribute__((__mode__(x))) + +/* + * Optional: not supported by clang + * Note: icc does not recognize gcc's no-tracer + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noclone-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-optimize-function-attribute + */ +#if __has_attribute(__noclone__) +# if __has_attribute(__optimize__) +# define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) +# else +# define __noclone __attribute__((__noclone__)) +# endif +#else +# define __noclone +#endif + +/* + * Note the missing underscores. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noinline-function-attribute + * clang: mentioned + */ +#define noinline __attribute__((__noinline__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noreturn-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#noreturn + * clang: https://clang.llvm.org/docs/AttributeReference.html#id1 + */ +#define __noreturn __attribute__((__noreturn__)) + +/* + * Optional: only supported since gcc >= 4.8 + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-no_005fsanitize_005faddress-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#no-sanitize-address-no-address-safety-analysis + */ +#if __has_attribute(__no_sanitize_address__) +# define __no_sanitize_address __attribute__((__no_sanitize_address__)) +#else +# define __no_sanitize_address +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-packed-type-attribute + * clang: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-packed-variable-attribute + */ +#define __packed __attribute__((__packed__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-pure-function-attribute + */ +#define __pure __attribute__((__pure__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-section-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-section-variable-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#section-declspec-allocate + */ +#define __section(S) __attribute__((__section__(#S))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-unused-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-unused-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-unused-variable-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-unused-label-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#maybe-unused-unused + */ +#define __always_unused __attribute__((__unused__)) +#define __maybe_unused __attribute__((__unused__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-used-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-used-variable-attribute + */ +#define __used __attribute__((__used__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute + */ +#define __weak __attribute__((__weak__)) + +#endif /* __LINUX_COMPILER_ATTRIBUTES_H */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index ed7c0e4a180e..3439d7d0249a 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -55,6 +55,9 @@ extern void __chk_io_ptr(const volatile void __iomem *); #ifdef __KERNEL__ +/* Attributes */ +#include + /* Compiler specific macros. */ #ifdef __clang__ #include @@ -79,12 +82,6 @@ extern void __chk_io_ptr(const volatile void __iomem *); #include #endif -/* - * Generic compiler-independent macros required for kernel - * build go below this comment. Actual compiler/compiler version - * specific implementations come from the above header files - */ - struct ftrace_branch_data { const char *func; const char *file; @@ -107,9 +104,6 @@ struct ftrace_likely_data { unsigned long constant; }; -/* Don't. Just don't. */ -#define __deprecated - #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ @@ -119,10 +113,6 @@ struct ftrace_likely_data { * compilers. We don't consider that to be an error, so set them to nothing. * For example, some of them are for compiler specific plugins. */ -#ifndef __designated_init -# define __designated_init -#endif - #ifndef __latent_entropy # define __latent_entropy #endif @@ -140,17 +130,6 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif -#ifndef __visible -#define __visible -#endif - -/* - * Assume alignment of return value. - */ -#ifndef __assume_aligned -#define __assume_aligned(a, ...) -#endif - /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) @@ -159,10 +138,6 @@ struct ftrace_likely_data { (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) -#ifndef __noclone -#define __noclone -#endif - /* Helpers for emitting diagnostics in pragmas. */ #ifndef __diag #define __diag(string) @@ -182,37 +157,6 @@ struct ftrace_likely_data { #define __diag_error(compiler, version, option, comment) \ __diag_ ## compiler(version, error, option) -/* - * From the GCC manual: - * - * Many functions have no effects except the return value and their - * return value depends only on the parameters and/or global - * variables. Such a function can be subject to common subexpression - * elimination and loop optimization just as an arithmetic operator - * would be. - * [...] - */ -#define __pure __attribute__((__pure__)) -#define __attribute_const__ __attribute__((__const__)) -#define __aligned(x) __attribute__((__aligned__(x))) -#define __aligned_largest __attribute__((__aligned__)) -#define __printf(a, b) __attribute__((__format__(printf, a, b))) -#define __scanf(a, b) __attribute__((__format__(scanf, a, b))) -#define __maybe_unused __attribute__((__unused__)) -#define __always_unused __attribute__((__unused__)) -#define __mode(x) __attribute__((__mode__(x))) -#define __malloc __attribute__((__malloc__)) -#define __used __attribute__((__used__)) -#define __noreturn __attribute__((__noreturn__)) -#define __packed __attribute__((__packed__)) -#define __weak __attribute__((__weak__)) -#define __alias(symbol) __attribute__((__alias__(#symbol))) -#define __cold __attribute__((__cold__)) -#define __section(S) __attribute__((__section__(#S))) -#define __always_inline inline __attribute__((__always_inline__)) -#define __gnu_inline __attribute__((__gnu_inline__)) - - #ifdef CONFIG_ENABLE_MUST_CHECK #define __must_check __attribute__((__warn_unused_result__)) #else @@ -246,18 +190,20 @@ struct ftrace_likely_data { * semantics rather than c99. This prevents multiple symbol definition errors * of extern inline functions at link time. * A lot of inline functions can cause havoc with function tracing. + * Do not use __always_inline here, since currently it expands to inline again + * (which would break users of __always_inline). */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) -#define inline \ - inline __attribute__((__always_inline__, __unused__)) notrace __gnu_inline +#define inline inline __attribute__((__always_inline__)) __gnu_inline \ + __maybe_unused notrace #else -#define inline inline __attribute__((__unused__)) notrace __gnu_inline +#define inline inline __gnu_inline \ + __maybe_unused notrace #endif #define __inline__ inline -#define __inline inline -#define noinline __attribute__((__noinline__)) +#define __inline inline /* * Rather then using noinline to prevent stack consumption, use -- cgit v1.2.3 From 06e3727e02f9ee9cf571692cd5c74fc5a8a2af52 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 3 Sep 2018 19:22:13 +0200 Subject: Compiler Attributes: KENTRY used twice the "used" attribute Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4030a2940d6b..17ee9165ca51 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -146,7 +146,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ - __attribute__((__section__("___kentry" "+" #sym ), used)) \ + __attribute__((__section__("___kentry" "+" #sym ))) \ = (unsigned long)&sym; #endif -- cgit v1.2.3 From e04462fb82f8dd98288c0e7ab1eec79c92537d25 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 3 Sep 2018 19:17:50 +0200 Subject: Compiler Attributes: remove uses of __attribute__ from compiler.h Suggested-by: Nick Desaulniers Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 17ee9165ca51..b5fb034fa6fa 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -23,8 +23,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define __branch_check__(x, expect, is_constant) ({ \ long ______r; \ static struct ftrace_likely_data \ - __attribute__((__aligned__(4))) \ - __attribute__((__section__("_ftrace_annotated_branch"))) \ + __aligned(4) \ + __section("_ftrace_annotated_branch") \ ______f = { \ .data.func = __func__, \ .data.file = __FILE__, \ @@ -59,8 +59,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, ({ \ int ______r; \ static struct ftrace_branch_data \ - __attribute__((__aligned__(4))) \ - __attribute__((__section__("_ftrace_branch"))) \ + __aligned(4) \ + __section("_ftrace_branch") \ ______f = { \ .func = __func__, \ .file = __FILE__, \ @@ -146,7 +146,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ - __attribute__((__section__("___kentry" "+" #sym ))) \ + __section("___kentry" "+" #sym ) \ = (unsigned long)&sym; #endif @@ -287,7 +287,7 @@ unsigned long read_word_at_a_time(const void *addr) * visible to the compiler. */ #define __ADDRESSABLE(sym) \ - static void * __attribute__((__section__(".discard.addressable"), used)) \ + static void * __section(".discard.addressable") __used \ __PASTE(__addressable_##sym, __LINE__) = (void *)&sym; /** -- cgit v1.2.3 From 92676236917d8e2e0de1d8612686d3d04a6a245b Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Wed, 19 Sep 2018 01:06:24 +0200 Subject: Compiler Attributes: add support for __nonstring (gcc >= 8) From the GCC manual: nonstring The nonstring variable attribute specifies that an object or member declaration with type array of char, signed char, or unsigned char, or pointer to such a type is intended to store character arrays that do not necessarily contain a terminating NUL. This is useful in detecting uses of such arrays or pointers with functions that expect NUL-terminated strings, and to avoid warnings when such an array or pointer is used as an argument to a bounded string manipulation function such as strncpy. https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html This attribute can be used for documentation purposes (i.e. replacing comments), but it is most helpful when the following warnings are enabled: -Wstringop-overflow Warn for calls to string manipulation functions such as memcpy and strcpy that are determined to overflow the destination buffer. [...] -Wstringop-truncation Warn for calls to bounded string manipulation functions such as strncat, strncpy, and stpncpy that may either truncate the copied string or leave the destination unchanged. [...] In situations where a character array is intended to store a sequence of bytes with no terminating NUL such an array may be annotated with attribute nonstring to avoid this warning. Such arrays, however, are not suitable arguments to functions that expect NUL-terminated strings. To help detect accidental misuses of such arrays GCC issues warnings unless it can prove that the use is safe. https://gcc.gnu.org/onlinedocs/gcc/Warning-Options.html Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Kees Cook Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index f0f9fc398440..6b28c1b7310c 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -34,6 +34,7 @@ # define __GCC4_has_attribute___externally_visible__ 1 # define __GCC4_has_attribute___noclone__ 1 # define __GCC4_has_attribute___optimize__ 1 +# define __GCC4_has_attribute___nonstring__ 0 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) #endif @@ -181,6 +182,19 @@ */ #define noinline __attribute__((__noinline__)) +/* + * Optional: only supported since gcc >= 8 + * Optional: not supported by clang + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-nonstring-variable-attribute + */ +#if __has_attribute(__nonstring__) +# define __nonstring __attribute__((__nonstring__)) +#else +# define __nonstring +#endif + /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noreturn-function-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#noreturn -- cgit v1.2.3 From 9dc6edcf676fe188430e8b119f91280bbf285163 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 Aug 2018 14:24:16 -0400 Subject: SUNRPC: Clean up initialisation of the struct rpc_rqst Move the initialisation back into xprt.c. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 336fd1a19cca..3d80524e92d6 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -325,7 +325,6 @@ struct xprt_class { struct rpc_xprt *xprt_create_transport(struct xprt_create *args); void xprt_connect(struct rpc_task *task); void xprt_reserve(struct rpc_task *task); -void xprt_request_init(struct rpc_task *task); void xprt_retry_reserve(struct rpc_task *task); int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task); int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); -- cgit v1.2.3 From 3021a5bbbf0aa0252f2993b84ee903a0eca0b690 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 14 Aug 2018 13:50:21 -0400 Subject: SUNRPC: The transmitted message must lie in the RPCSEC window of validity If a message has been encoded using RPCSEC_GSS, the server is maintaining a window of sequence numbers that it considers valid. The client should normally be tracking that window, and needs to verify that the sequence number used by the message being transmitted still lies inside the window of validity. So far, we've been able to assume this condition would be realised automatically, since the client has been encoding the message only after taking the socket lock. Once we change that condition, we will need the explicit check. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 2 ++ include/linux/sunrpc/auth_gss.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 58a6765c1c5e..2c97a3933ef9 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -157,6 +157,7 @@ struct rpc_credops { int (*crkey_timeout)(struct rpc_cred *); bool (*crkey_to_expire)(struct rpc_cred *); char * (*crstringify_acceptor)(struct rpc_cred *); + bool (*crneed_reencode)(struct rpc_task *); }; extern const struct rpc_authops authunix_ops; @@ -192,6 +193,7 @@ __be32 * rpcauth_marshcred(struct rpc_task *, __be32 *); __be32 * rpcauth_checkverf(struct rpc_task *, __be32 *); int rpcauth_wrap_req(struct rpc_task *task, kxdreproc_t encode, void *rqstp, __be32 *data, void *obj); int rpcauth_unwrap_resp(struct rpc_task *task, kxdrdproc_t decode, void *rqstp, __be32 *data, void *obj); +bool rpcauth_xmit_need_reencode(struct rpc_task *task); int rpcauth_refreshcred(struct rpc_task *); void rpcauth_invalcred(struct rpc_task *); int rpcauth_uptodatecred(struct rpc_task *); diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h index 0c9eac351aab..30427b729070 100644 --- a/include/linux/sunrpc/auth_gss.h +++ b/include/linux/sunrpc/auth_gss.h @@ -70,6 +70,7 @@ struct gss_cl_ctx { refcount_t count; enum rpc_gss_proc gc_proc; u32 gc_seq; + u32 gc_seq_xmit; spinlock_t gc_seq_lock; struct gss_ctx *gc_gss_ctx; struct xdr_netobj gc_wire_ctx; -- cgit v1.2.3 From 7ebbbc6e7bd023903daa5bd95726edf2d60b559c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 28 Aug 2018 09:00:27 -0400 Subject: SUNRPC: Simplify identification of when the message send/receive is complete Add states to indicate that the message send and receive are not yet complete. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 592653becd91..9e655df70131 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -140,8 +140,10 @@ struct rpc_task_setup { #define RPC_TASK_RUNNING 0 #define RPC_TASK_QUEUED 1 #define RPC_TASK_ACTIVE 2 -#define RPC_TASK_MSG_RECV 3 -#define RPC_TASK_MSG_RECV_WAIT 4 +#define RPC_TASK_NEED_XMIT 3 +#define RPC_TASK_NEED_RECV 4 +#define RPC_TASK_MSG_RECV 5 +#define RPC_TASK_MSG_RECV_WAIT 6 #define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) -- cgit v1.2.3 From d1109aa56c71e19fc117e75bff11384fc7279a3b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 13 Aug 2018 15:48:42 -0400 Subject: SUNRPC: Rename TCP receive-specific state variables Since we will want to introduce similar TCP state variables for the transmission of requests, let's rename the existing ones to label that they are for the receive side. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index ae0f99b9b965..90d5ca8e65f4 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -30,15 +30,17 @@ struct sock_xprt { /* * State of TCP reply receive */ - __be32 tcp_fraghdr, - tcp_xid, - tcp_calldir; + struct { + __be32 fraghdr, + xid, + calldir; - u32 tcp_offset, - tcp_reclen; + u32 offset, + len; - unsigned long tcp_copied, - tcp_flags; + unsigned long copied, + flags; + } recv; /* * Connection of transports -- cgit v1.2.3 From 6c7a64e5a44dbc6d073b83a56a48d0a4099f1dd2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 13 Aug 2018 16:54:57 -0400 Subject: SUNRPC: Add socket transmit queue offset tracking Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 90d5ca8e65f4..005cfb6e7238 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -42,6 +42,13 @@ struct sock_xprt { flags; } recv; + /* + * State of TCP transmit queue + */ + struct { + u32 offset; + } xmit; + /* * Connection of transports */ -- cgit v1.2.3 From cf9946cd6144410ced00d52586ff5a2cb4868fc5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 6 Aug 2018 12:55:34 -0400 Subject: SUNRPC: Refactor the transport request pinning We are going to need to pin for both send and receive. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 3 +-- include/linux/sunrpc/xprt.h | 1 + 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 9e655df70131..8062ce6b18e5 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -142,8 +142,7 @@ struct rpc_task_setup { #define RPC_TASK_ACTIVE 2 #define RPC_TASK_NEED_XMIT 3 #define RPC_TASK_NEED_RECV 4 -#define RPC_TASK_MSG_RECV 5 -#define RPC_TASK_MSG_RECV_WAIT 6 +#define RPC_TASK_MSG_PIN_WAIT 5 #define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 3d80524e92d6..bd743c51a865 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -103,6 +103,7 @@ struct rpc_rqst { /* A cookie used to track the state of the transport connection */ + atomic_t rq_pin; /* * Partial send handling -- cgit v1.2.3 From 359c48c04af25397ecefec1ccf200ddd199617ce Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 29 Aug 2018 09:22:28 -0400 Subject: SUNRPC: Add a helper to wake up a sleeping rpc_task and set its status Add a helper that will wake up a task that is sleeping on a specific queue, and will set the value of task->tk_status. This is mainly intended for use by the transport layer to notify the task of an error condition. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 8062ce6b18e5..8840a420cf4c 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -235,6 +235,9 @@ void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq, struct rpc_task *task); void rpc_wake_up_queued_task(struct rpc_wait_queue *, struct rpc_task *); +void rpc_wake_up_queued_task_set_status(struct rpc_wait_queue *, + struct rpc_task *, + int); void rpc_wake_up(struct rpc_wait_queue *); struct rpc_task *rpc_wake_up_next(struct rpc_wait_queue *); struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq, -- cgit v1.2.3 From 75c84151a9dc7a755c607e6761d8f14a1690dbf0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 31 Aug 2018 10:21:00 -0400 Subject: SUNRPC: Rename xprt->recv_lock to xprt->queue_lock We will use the same lock to protect both the transmit and receive queues. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index bd743c51a865..c25d0a5fda69 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -235,7 +235,7 @@ struct rpc_xprt { */ spinlock_t transport_lock; /* lock transport info */ spinlock_t reserve_lock; /* lock slot table */ - spinlock_t recv_lock; /* lock receive list */ + spinlock_t queue_lock; /* send/receive queue lock */ u32 xid; /* Next XID value to use */ struct rpc_task * snd_task; /* Task blocked in send */ struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ -- cgit v1.2.3 From edc81dcd5b7f699c4049042b35c904396642032e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 Aug 2018 17:55:46 -0400 Subject: SUNRPC: Refactor xprt_transmit() to remove the reply queue code Separate out the action of adding a request to the reply queue so that the backchannel code can simply skip calling it altogether. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index c25d0a5fda69..0250294c904a 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -334,6 +334,7 @@ void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); +void xprt_request_enqueue_receive(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); -- cgit v1.2.3 From 7f3a1d1e1806a0eb9b200e3aed2a04431f2bcc6a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 23 Aug 2018 00:03:43 -0400 Subject: SUNRPC: Refactor xprt_transmit() to remove wait for reply code Allow the caller in clnt.c to call into the code to wait for a reply after calling xprt_transmit(). Again, the reason is that the backchannel code does not need this functionality. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 0250294c904a..4fa2af087cff 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -335,6 +335,7 @@ void xprt_free_slot(struct rpc_xprt *xprt, void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); +void xprt_request_wait_receive(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); -- cgit v1.2.3 From ef3f54347f690d06649c0d7a1f63d3410b3d08d3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 8 Aug 2018 09:23:32 -0400 Subject: SUNRPC: Distinguish between the slot allocation list and receive queue When storing a struct rpc_rqst on the slot allocation list, we currently use the same field 'rq_list' as we use to store the request on the receive queue. Since the structure is never on both lists at the same time, this is OK. However, for clarity, let's make that a union with different names for the different lists so that we can more easily distinguish between the two states. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 4fa2af087cff..9cec2d0811f2 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -82,7 +82,11 @@ struct rpc_rqst { struct page **rq_enc_pages; /* scratch pages for use by gss privacy code */ void (*rq_release_snd_buf)(struct rpc_rqst *); /* release rq_enc_pages */ - struct list_head rq_list; + + union { + struct list_head rq_list; /* Slot allocation list */ + struct list_head rq_recv; /* Receive queue */ + }; void *rq_buffer; /* Call XDR encode buffer */ size_t rq_callsize; @@ -249,7 +253,8 @@ struct rpc_xprt { struct list_head bc_pa_list; /* List of preallocated * backchannel rpc_rqst's */ #endif /* CONFIG_SUNRPC_BACKCHANNEL */ - struct list_head recv; + + struct list_head recv_queue; /* Receive queue */ struct { unsigned long bind_count, /* total number of binds */ -- cgit v1.2.3 From 944b042921a17d1a4e51bb05f8edf2b93d26e36f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 9 Aug 2018 23:33:21 -0400 Subject: SUNRPC: Add a transmission queue for RPC requests Add the queue that will enforce the ordering of RPC task transmission. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 9cec2d0811f2..81a6c2c8dfc7 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -88,6 +88,8 @@ struct rpc_rqst { struct list_head rq_recv; /* Receive queue */ }; + struct list_head rq_xmit; /* Send queue */ + void *rq_buffer; /* Call XDR encode buffer */ size_t rq_callsize; void *rq_rbuffer; /* Reply XDR decode buffer */ @@ -242,6 +244,9 @@ struct rpc_xprt { spinlock_t queue_lock; /* send/receive queue lock */ u32 xid; /* Next XID value to use */ struct rpc_task * snd_task; /* Task blocked in send */ + + struct list_head xmit_queue; /* Send queue */ + struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct svc_serv *bc_serv; /* The RPC service which will */ @@ -339,6 +344,7 @@ void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); +void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); -- cgit v1.2.3 From 762e4e67b356ab7b8fbfc39bc07dc6110121505e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Aug 2018 16:28:28 -0400 Subject: SUNRPC: Refactor RPC call encoding Move the call encoding so that it occurs before the transport connection etc. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 81a6c2c8dfc7..b8a7de161f67 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -347,6 +347,7 @@ bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); +bool xprt_request_need_retransmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); -- cgit v1.2.3 From 902c58872e1e9a2c146a55b0701c0b26cc5a4b24 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 1 Sep 2018 17:21:01 -0400 Subject: SUNRPC: Fix up the back channel transmit Fix up the back channel code to recognise that it has already been transmitted, so does not need to be called again. Also ensure that we set req->rq_task. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/bc_xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index 4397a4824c81..28721cf73ec3 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -34,6 +34,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #ifdef CONFIG_SUNRPC_BACKCHANNEL struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid); void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied); +void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task); void xprt_free_bc_request(struct rpc_rqst *req); int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs); void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs); -- cgit v1.2.3 From 50f484e298218b7271fad8a23bd44c82fb3110e1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 30 Aug 2018 13:27:29 -0400 Subject: SUNRPC: Treat the task and request as separate in the xprt_ops->send_request() When we shift to using the transmit queue, then the task that holds the write lock will not necessarily be the same as the one being transmitted. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index b8a7de161f67..8c2bb078f00c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -140,7 +140,7 @@ struct rpc_xprt_ops { void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - int (*send_request)(struct rpc_task *task); + int (*send_request)(struct rpc_rqst *req, struct rpc_task *task); void (*set_retrans_timeout)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); void (*release_request)(struct rpc_task *task); -- cgit v1.2.3 From 918f3c1fe83c5baa4892b943d3f5ac7191d8fb74 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Sep 2018 11:37:22 -0400 Subject: SUNRPC: Improve latency for interactive tasks One of the intentions with the priority queues was to ensure that no single process can hog the transport. The field task->tk_owner therefore identifies the RPC call's origin, and is intended to allow the RPC layer to organise queues for fairness. This commit therefore modifies the transmit queue to group requests by task->tk_owner, and ensures that we round robin among those groups. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 8c2bb078f00c..e377620b9744 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -89,6 +89,7 @@ struct rpc_rqst { }; struct list_head rq_xmit; /* Send queue */ + struct list_head rq_xmit2; /* Send queue */ void *rq_buffer; /* Call XDR encode buffer */ size_t rq_callsize; -- cgit v1.2.3 From 75891f502f5fc70f52a01af5b924384ed4866907 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 17:37:36 -0400 Subject: SUNRPC: Support for congestion control when queuing is enabled Both RDMA and UDP transports require the request to get a "congestion control" credit before they can be transmitted. Right now, this is done when the request locks the socket. We'd like it to happen when a request attempts to be transmitted for the first time. In order to support retransmission of requests that already hold such credits, we also want to ensure that they get queued first, so that we don't deadlock with requests that have yet to obtain a credit. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index e377620b9744..0d0cc127615e 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -397,6 +397,7 @@ void xprt_complete_rqst(struct rpc_task *task, int copied); void xprt_pin_rqst(struct rpc_rqst *req); void xprt_unpin_rqst(struct rpc_rqst *req); void xprt_release_rqst_cong(struct rpc_task *task); +bool xprt_request_get_cong(struct rpc_xprt *xprt, struct rpc_rqst *req); void xprt_disconnect_done(struct rpc_xprt *xprt); void xprt_force_disconnect(struct rpc_xprt *xprt); void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); @@ -415,6 +416,7 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_BINDING (5) #define XPRT_CLOSING (6) #define XPRT_CONGESTED (9) +#define XPRT_CWND_WAIT (10) static inline void xprt_set_connected(struct rpc_xprt *xprt) { -- cgit v1.2.3 From 36bd7de949f41d586ef7794169af75462b67acbc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 18:41:32 -0400 Subject: SUNRPC: Turn off throttling of RPC slots for TCP sockets The theory was that we would need to grab the socket lock anyway, so we might as well use it to gate the allocation of RPC slots for a TCP socket. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 0d0cc127615e..14c9b4d49fb4 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -343,7 +343,6 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); -void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); -- cgit v1.2.3 From c544577daddb618c7dd5fa7fb98d6a41782f020e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 23:39:27 -0400 Subject: SUNRPC: Clean up transport write space handling Treat socket write space handling in the same way we now treat transport congestion: by denying the XPRT_LOCK until the transport signals that it has free buffer space. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/svc_xprt.h | 1 - include/linux/sunrpc/xprt.h | 5 +++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index c3d72066d4b1..6b7a86c4d6e6 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -84,7 +84,6 @@ struct svc_xprt { struct sockaddr_storage xpt_remote; /* remote peer's address */ size_t xpt_remotelen; /* length of address */ char xpt_remotebuf[INET6_ADDRSTRLEN + 10]; - struct rpc_wait_queue xpt_bc_pending; /* backchannel wait queue */ struct list_head xpt_users; /* callbacks on free */ struct net *xpt_net; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 14c9b4d49fb4..5600242ccbf9 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -387,8 +387,8 @@ int xprt_load_transport(const char *); void xprt_set_retrans_timeout_def(struct rpc_task *task); void xprt_set_retrans_timeout_rtt(struct rpc_task *task); void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status); -void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action); -void xprt_write_space(struct rpc_xprt *xprt); +void xprt_wait_for_buffer_space(struct rpc_xprt *xprt); +bool xprt_write_space(struct rpc_xprt *xprt); void xprt_adjust_cwnd(struct rpc_xprt *xprt, struct rpc_task *task, int result); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid); void xprt_update_rtt(struct rpc_task *task); @@ -416,6 +416,7 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_CLOSING (6) #define XPRT_CONGESTED (9) #define XPRT_CWND_WAIT (10) +#define XPRT_WRITE_SPACE (11) static inline void xprt_set_connected(struct rpc_xprt *xprt) { -- cgit v1.2.3 From adfa71446dd0943ba376eff3e05c7c89582f8038 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 23:58:59 -0400 Subject: SUNRPC: Cleanup: remove the unused 'task' argument from the request_send() Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 5600242ccbf9..823860cce0bc 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -141,7 +141,7 @@ struct rpc_xprt_ops { void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - int (*send_request)(struct rpc_rqst *req, struct rpc_task *task); + int (*send_request)(struct rpc_rqst *req); void (*set_retrans_timeout)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); void (*release_request)(struct rpc_task *task); -- cgit v1.2.3 From 95f7691daa57bbd68caac2bdad79e0b08f4d46c1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 7 Sep 2018 08:35:22 -0400 Subject: SUNRPC: Convert xprt receive queue to use an rbtree If the server is slow, we can find ourselves with quite a lot of entries on the receive queue. Converting the search from an O(n) to O(log(n)) can make a significant difference, particularly since we have to hold a number of locks while searching. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 823860cce0bc..9be399020dab 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -85,7 +85,7 @@ struct rpc_rqst { union { struct list_head rq_list; /* Slot allocation list */ - struct list_head rq_recv; /* Receive queue */ + struct rb_node rq_recv; /* Receive queue */ }; struct list_head rq_xmit; /* Send queue */ @@ -260,7 +260,7 @@ struct rpc_xprt { * backchannel rpc_rqst's */ #endif /* CONFIG_SUNRPC_BACKCHANNEL */ - struct list_head recv_queue; /* Receive queue */ + struct rb_root recv_queue; /* Receive queue */ struct { unsigned long bind_count, /* total number of binds */ -- cgit v1.2.3 From f42f7c283078ce3c1e8368b140e270755b1ae313 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 8 Sep 2018 22:09:48 -0400 Subject: SUNRPC: Fix priority queue fairness Fix up the priority queue to not batch by owner, but by queue, so that we allow '1 << priority' elements to be dequeued before switching to the next priority queue. The owner field is still used to wake up requests in round robin order by owner to avoid single processes hogging the RPC layer by loading the queues. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 8840a420cf4c..7b540c066594 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -189,7 +189,6 @@ struct rpc_timer { struct rpc_wait_queue { spinlock_t lock; struct list_head tasks[RPC_NR_PRIORITY]; /* task queue for each priority level */ - pid_t owner; /* process id of last task serviced */ unsigned char maxpriority; /* maximum priority (0 if queue is not a priority queue) */ unsigned char priority; /* current priority */ unsigned char nr; /* # tasks remaining for cookie */ @@ -205,7 +204,6 @@ struct rpc_wait_queue { * from a single cookie. The aim is to improve * performance of NFS operations such as read/write. */ -#define RPC_BATCH_COUNT 16 #define RPC_IS_PRIORITY(q) ((q)->maxpriority > 0) /* -- cgit v1.2.3 From 431f6eb3570f286036bc8718a908a283f5d99473 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 16 Sep 2018 00:08:20 -0400 Subject: SUNRPC: Add a label for RPC calls that require allocation on receive If the RPC call relies on the receive call allocating pages as buffers, then let's label it so that we a) Don't leak memory by allocating pages for requests that do not expect this behaviour b) Can optimise for the common case where calls do not require allocation. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 2bd68177a442..431829233392 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -58,6 +58,7 @@ struct xdr_buf { flags; /* Flags for data disposition */ #define XDRBUF_READ 0x01 /* target of file read */ #define XDRBUF_WRITE 0x02 /* source of file write */ +#define XDRBUF_SPARSE_PAGES 0x04 /* Page array is sparse */ unsigned int buflen, /* Total length of storage buffer */ len; /* Length of XDR encoded message */ -- cgit v1.2.3 From 9d96acbc7f376dc1ffcedca0c349dd3389187a38 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 13 Sep 2018 12:22:04 -0400 Subject: SUNRPC: Add a bvec array to struct xdr_buf for use with iovec_iter() Add a bvec array to struct xdr_buf, and have the client allocate it when we need to receive data into pages. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 7 +++++++ include/linux/sunrpc/xprt.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 431829233392..745587132a87 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -18,6 +18,7 @@ #include #include +struct bio_vec; struct rpc_rqst; /* @@ -52,6 +53,7 @@ struct xdr_buf { struct kvec head[1], /* RPC header + non-page data */ tail[1]; /* Appended after page data */ + struct bio_vec *bvec; struct page ** pages; /* Array of pages */ unsigned int page_base, /* Start of page data */ page_len, /* Length of page data */ @@ -70,6 +72,8 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len) buf->head[0].iov_base = start; buf->head[0].iov_len = len; buf->tail[0].iov_len = 0; + buf->bvec = NULL; + buf->pages = NULL; buf->page_len = 0; buf->flags = 0; buf->len = 0; @@ -116,6 +120,9 @@ __be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *); void xdr_inline_pages(struct xdr_buf *, unsigned int, struct page **, unsigned int, unsigned int); void xdr_terminate_string(struct xdr_buf *, const u32); +size_t xdr_buf_pagecount(struct xdr_buf *buf); +int xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp); +void xdr_free_bvec(struct xdr_buf *buf); static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int len) { diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 9be399020dab..a4ab4f8d9140 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -141,6 +141,7 @@ struct rpc_xprt_ops { void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); + void (*prepare_request)(struct rpc_rqst *req); int (*send_request)(struct rpc_rqst *req); void (*set_retrans_timeout)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); @@ -343,6 +344,7 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); +void xprt_request_prepare(struct rpc_rqst *req); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); -- cgit v1.2.3 From 277e4ab7d530bf287e02b65cfcd3ea8f489784f6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 14 Sep 2018 09:49:06 -0400 Subject: SUNRPC: Simplify TCP receive code by switching to using iterators Most of this code should also be reusable with other socket types. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 005cfb6e7238..458bfe0137f5 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -31,15 +31,16 @@ struct sock_xprt { * State of TCP reply receive */ struct { - __be32 fraghdr, + struct { + __be32 fraghdr, xid, calldir; + } __attribute__((packed)); u32 offset, len; - unsigned long copied, - flags; + unsigned long copied; } recv; /* @@ -76,21 +77,9 @@ struct sock_xprt { void (*old_error_report)(struct sock *); }; -/* - * TCP receive state flags - */ -#define TCP_RCV_LAST_FRAG (1UL << 0) -#define TCP_RCV_COPY_FRAGHDR (1UL << 1) -#define TCP_RCV_COPY_XID (1UL << 2) -#define TCP_RCV_COPY_DATA (1UL << 3) -#define TCP_RCV_READ_CALLDIR (1UL << 4) -#define TCP_RCV_COPY_CALLDIR (1UL << 5) - /* * TCP RPC flags */ -#define TCP_RPC_REPLY (1UL << 6) - #define XPRT_SOCK_CONNECTING 1U #define XPRT_SOCK_DATA_READY (2) #define XPRT_SOCK_UPD_TIMEOUT (3) -- cgit v1.2.3 From 550aebfe1c573518c35ae85d6ffbdc2d44c92703 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 14 Sep 2018 14:32:45 -0400 Subject: SUNRPC: Allow AF_LOCAL sockets to use the generic stream receive Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 745587132a87..8815be7cae72 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -185,7 +185,6 @@ struct xdr_skb_reader { typedef size_t (*xdr_skb_read_actor)(struct xdr_skb_reader *desc, void *to, size_t len); -size_t xdr_skb_read_bits(struct xdr_skb_reader *desc, void *to, size_t len); extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *); extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int, struct xdr_skb_reader *, xdr_skb_read_actor); -- cgit v1.2.3 From ec846469ba7bdb81e42c04e4e15d8fbf19e426e2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 14 Sep 2018 14:38:05 -0400 Subject: SUNRPC: Unexport xdr_partial_copy_from_skb() It is no longer used outside of net/sunrpc/socklib.c Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 8815be7cae72..43106ffa6788 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -186,8 +186,6 @@ struct xdr_skb_reader { typedef size_t (*xdr_skb_read_actor)(struct xdr_skb_reader *desc, void *to, size_t len); extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *); -extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int, - struct xdr_skb_reader *, xdr_skb_read_actor); extern int xdr_encode_word(struct xdr_buf *, unsigned int, u32); extern int xdr_decode_word(struct xdr_buf *, unsigned int, u32 *); -- cgit v1.2.3 From 1db97eaa0b482a738c715da6edb023d6f99e50b0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 2 Sep 2018 15:11:57 -0400 Subject: NFS: Convert lookups of the lock context to RCU Speed up lookups of an existing lock context by avoiding the inode->i_lock, and using RCU instead. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a0831e9d19c9..d2f4f88a0e66 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -62,6 +62,7 @@ struct nfs_lock_context { struct nfs_open_context *open_context; fl_owner_t lockowner; atomic_t io_count; + struct rcu_head rcu_head; }; struct nfs4_state; -- cgit v1.2.3 From 0de43976fbe716379084f954b1e370c35aa87bf0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 2 Sep 2018 15:57:01 -0400 Subject: NFS: Convert lookups of the open context to RCU Reduce contention on the inode->i_lock by ensuring that we use RCU when looking up the NFS open context. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d2f4f88a0e66..6e0417c02279 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -83,6 +83,7 @@ struct nfs_open_context { struct list_head list; struct nfs4_threshold *mdsthreshold; + struct rcu_head rcu_head; }; struct nfs_open_dir_context { -- cgit v1.2.3 From 8d8928d87960d71f898767185b8c0e4ce3de3cbe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 5 Mar 2018 12:03:00 -0500 Subject: NFSv3: Improve NFSv3 performance when server returns no post-op attributes When the server fails to return post-op attributes, the client's attempt to place read data directly in the page cache fails, and so we have to do an extra copy in order to realign the data with page borders. This patch attempts to detect servers that don't return post-op attributes on read (e.g. for pNFS) and adjusts the placement calculation accordingly. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 3 +++ include/linux/nfs_xdr.h | 3 ++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index bf39d9c92201..0fc0b9135d46 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -228,6 +228,9 @@ struct nfs_server { unsigned short mountd_port; unsigned short mountd_protocol; struct rpc_wait_queue uoc_rpcwaitq; + + /* XDR related information */ + unsigned int read_hdrsize; }; /* Server capabilities */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index bd1c889a9ed9..7f5535e5e852 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -608,6 +608,7 @@ struct nfs_pgio_args { __u32 count; unsigned int pgbase; struct page ** pages; + unsigned int replen; /* used by read */ const u32 * bitmask; /* used by write */ enum nfs3_stable_how stable; /* used by write */ }; @@ -618,9 +619,9 @@ struct nfs_pgio_res { __u32 count; __u32 op_status; int eof; /* used by read */ + unsigned int replen; /* used by read */ struct nfs_writeverf * verf; /* used by write */ const struct nfs_server *server; /* used by write */ - }; /* -- cgit v1.2.3 From 28d52235ee25ba7d843242b4cb3c3f27a8828b5a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 24 Sep 2018 13:15:37 -0400 Subject: NFSv4: Save a few bytes in the nfs_pgio_args/res Save a few bytes by allowing the read/write specific fields of the structures to share storage. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7f5535e5e852..343e44166346 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -608,9 +608,13 @@ struct nfs_pgio_args { __u32 count; unsigned int pgbase; struct page ** pages; - unsigned int replen; /* used by read */ - const u32 * bitmask; /* used by write */ - enum nfs3_stable_how stable; /* used by write */ + union { + unsigned int replen; /* used by read */ + struct { + const u32 * bitmask; /* used by write */ + enum nfs3_stable_how stable; /* used by write */ + }; + }; }; struct nfs_pgio_res { @@ -618,10 +622,16 @@ struct nfs_pgio_res { struct nfs_fattr * fattr; __u32 count; __u32 op_status; - int eof; /* used by read */ - unsigned int replen; /* used by read */ - struct nfs_writeverf * verf; /* used by write */ - const struct nfs_server *server; /* used by write */ + union { + struct { + unsigned int replen; /* used by read */ + int eof; /* used by read */ + }; + struct { + struct nfs_writeverf * verf; /* used by write */ + const struct nfs_server *server; /* used by write */ + }; + }; }; /* -- cgit v1.2.3 From 1c6c4b740df12f2162ae5c3fac337137e2776236 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 25 Sep 2018 12:34:43 -0400 Subject: NFS: Remove private spinlock in struct nfs_pgio_header Now that each struct nfs_pgio_header corresponds to one RPC call, we only have one writer to the struct nfs_pgio_header. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 343e44166346..0e016252cfc6 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1482,11 +1482,10 @@ struct nfs_pgio_header { const struct nfs_rw_ops *rw_ops; struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; - spinlock_t lock; - /* fields protected by lock */ + int pnfs_error; int error; /* merge with pnfs_error */ - unsigned long good_bytes; /* boundary of good data */ + unsigned int good_bytes; /* boundary of good data */ unsigned long flags; /* -- cgit v1.2.3 From 571ed1fd2390f74e4c1f46994f753fb0d29285e4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 29 Sep 2018 16:00:43 -0400 Subject: SUNRPC: Replace krb5_seq_lock with a lockless scheme Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 7df625d41e35..69f749afa617 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -118,7 +118,8 @@ struct krb5_ctx { u8 acceptor_integ[GSS_KRB5_MAX_KEYLEN]; }; -extern spinlock_t krb5_seq_lock; +extern u32 gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx); +extern u64 gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx); /* The length of the Kerberos GSS token header */ #define GSS_KRB5_TOK_HDR_LEN (16) -- cgit v1.2.3 From aef716fa5e6da3919cca22ac2097a90d73d8177f Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 27 Sep 2018 13:55:58 -0700 Subject: RDMA/qedr: Remove enumerated type qed_roce_ll2_tx_dest Clang warns when one enumerated type is explicitly converted to another. drivers/infiniband/hw/qedr/qedr_roce_cm.c:198:28: warning: implicit conversion from enumeration type 'enum qed_roce_ll2_tx_dest' to different enumeration type 'enum qed_ll2_tx_dest' [-Wenum-conversion] ll2_tx_pkt.tx_dest = pkt->tx_dest; ~ ~~~~~^~~~~~~ 1 warning generated. Turns out that QED_ROCE_LL2_TX_DEST_NW and QED_ROCE_LL2_TX_DEST_LB are only used once in the whole tree and QED_ROCE_LL2_TX_DEST_MAX is used nowhere. Remove them and use the equivalent values from qed_ll2_tx_dest in their place. Reported-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Acked-by: Michal Kalderon Signed-off-by: Jason Gunthorpe --- include/linux/qed/qed_rdma_if.h | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index df4d13f7e191..d15f8e4815e3 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -39,15 +39,6 @@ #include #include -enum qed_roce_ll2_tx_dest { - /* Light L2 TX Destination to the Network */ - QED_ROCE_LL2_TX_DEST_NW, - - /* Light L2 TX Destination to the Loopback */ - QED_ROCE_LL2_TX_DEST_LB, - QED_ROCE_LL2_TX_DEST_MAX -}; - #define QED_RDMA_MAX_CNQ_SIZE (0xFFFF) /* rdma interface */ @@ -581,7 +572,7 @@ struct qed_roce_ll2_packet { int n_seg; struct qed_roce_ll2_buffer payload[RDMA_MAX_SGE_PER_SQ_WQE]; int roce_mode; - enum qed_roce_ll2_tx_dest tx_dest; + enum qed_ll2_tx_dest tx_dest; }; enum qed_rdma_type { -- cgit v1.2.3 From d440c52d3151a28358f4c2d52d8583a0aa54ab83 Mon Sep 17 00:00:00 2001 From: Junling Zheng Date: Fri, 28 Sep 2018 20:25:56 +0800 Subject: f2fs: support superblock checksum Now we support crc32 checksum for superblock. Reviewed-by: Chao Yu Signed-off-by: Junling Zheng Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 1d4b196291d6..1db13ff9a3f4 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -109,7 +109,8 @@ struct f2fs_super_block { struct f2fs_device devs[MAX_DEVICES]; /* device list */ __le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */ __u8 hot_ext_count; /* # of hot file extension */ - __u8 reserved[314]; /* valid reserved region */ + __u8 reserved[310]; /* valid reserved region */ + __le32 crc; /* checksum of superblock */ } __packed; /* -- cgit v1.2.3 From cf9af0d5786c008971148f4e06567a98f6a7f9d0 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 27 Sep 2018 13:38:09 +0200 Subject: gpio: Propagate errors from gpiod_set_array_value_complex() Internal helper function gpiod_set_array_value_complex() was changed to return an error value, but not all gpiolib callers were updated to propagate the new error up. Fixes: 3027743f83f867d8 ("gpio: Remove VLA from gpiolib") Signed-off-by: Geert Uytterhoeven Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index d7fbe30ece84..136aeca37740 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -117,10 +117,10 @@ int gpiod_get_array_value(unsigned int array_size, struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_value(struct gpio_desc *desc, int value); -void gpiod_set_array_value(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap); +int gpiod_set_array_value(unsigned int array_size, + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap); int gpiod_get_raw_value(const struct gpio_desc *desc); int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, @@ -139,10 +139,10 @@ int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_value_cansleep(struct gpio_desc *desc, int value); -void gpiod_set_array_value_cansleep(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap); +int gpiod_set_array_value_cansleep(unsigned int array_size, + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap); int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc); int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, @@ -361,13 +361,14 @@ static inline void gpiod_set_value(struct gpio_desc *desc, int value) /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_array_value(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap) +static inline int gpiod_set_array_value(unsigned int array_size, + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); + return 0; } static inline int gpiod_get_raw_value(const struct gpio_desc *desc) { @@ -419,13 +420,14 @@ static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value) /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_array_value_cansleep(unsigned int array_size, +static inline int gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); + return 0; } static inline int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc) { -- cgit v1.2.3 From 3c940660cb1ea6c952bb863040cdacafd5077448 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 27 Sep 2018 13:38:10 +0200 Subject: gpio: Restore indentation of continued lines Fixes: 3027743f83f867d8 ("gpio: Remove VLA from gpiolib") Signed-off-by: Geert Uytterhoeven Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 136aeca37740..0f350616d372 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -128,9 +128,9 @@ int gpiod_get_raw_array_value(unsigned int array_size, unsigned long *value_bitmap); void gpiod_set_raw_value(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap); + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap); /* Value get/set from sleeping context */ int gpiod_get_value_cansleep(const struct gpio_desc *desc); @@ -150,9 +150,9 @@ int gpiod_get_raw_array_value_cansleep(unsigned int array_size, unsigned long *value_bitmap); void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value_cansleep(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap); + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap); int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce); int gpiod_set_transitory(struct gpio_desc *desc, bool transitory); @@ -391,9 +391,9 @@ static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) WARN_ON(1); } static inline int gpiod_set_raw_array_value(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap) + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); -- cgit v1.2.3 From 22839869f21ab3850fbbac9b425ccc4c0023926f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 5 Sep 2018 15:34:42 +0100 Subject: signal: Introduce COMPAT_SIGMINSTKSZ for use in compat_sys_sigaltstack The sigaltstack(2) system call fails with -ENOMEM if the new alternative signal stack is found to be smaller than SIGMINSTKSZ. On architectures such as arm64, where the native value for SIGMINSTKSZ is larger than the compat value, this can result in an unexpected error being reported to a compat task. See, for example: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=904385 This patch fixes the problem by extending do_sigaltstack to take the minimum signal stack size as an additional parameter, allowing the native and compat system call entry code to pass in their respective values. COMPAT_SIGMINSTKSZ is just defined as SIGMINSTKSZ if it has not been defined by the architecture. Cc: Arnd Bergmann Cc: Dominik Brodowski Cc: "Eric W. Biederman" Cc: Andrew Morton Cc: Al Viro Cc: Oleg Nesterov Reported-by: Steve McIntyre Tested-by: Steve McIntyre <93sam@debian.org> Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- include/linux/compat.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 1a3c4f37e908..de0c13bdcd2c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -103,6 +103,9 @@ typedef struct compat_sigaltstack { compat_size_t ss_size; } compat_stack_t; #endif +#ifndef COMPAT_MINSIGSTKSZ +#define COMPAT_MINSIGSTKSZ MINSIGSTKSZ +#endif #define compat_jiffies_to_clock_t(x) \ (((unsigned long)(x) * COMPAT_USER_HZ) / HZ) -- cgit v1.2.3 From 2da274cdf998a1c12afa6b5975db2df1df01edf1 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Thu, 20 Sep 2018 17:10:22 +0100 Subject: iommu/dma: Add support for non-strict mode With the flush queue infrastructure already abstracted into IOVA domains, hooking it up in iommu-dma is pretty simple. Since there is a degree of dependency on the IOMMU driver knowing what to do to play along, we key the whole thing off a domain attribute which will be set on default DMA ops domains to request non-strict invalidation. That way, drivers can indicate the appropriate support by acknowledging the attribute, and we can easily fall back to strict invalidation otherwise. The flush queue callback needs a handle on the iommu_domain which owns our cookie, so we have to add a pointer back to that, but neatly, that's also sufficient to indicate whether we're using a flush queue or not, and thus which way to release IOVAs. The only slight subtlety is switching __iommu_dma_unmap() from calling iommu_unmap() to explicit iommu_unmap_fast()/iommu_tlb_sync() so that we can elide the sync entirely in non-strict mode. Signed-off-by: Zhen Lei [rm: convert to domain attribute, tweak comments and commit message] Signed-off-by: Robin Murphy Signed-off-by: Will Deacon --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 87994c265bf5..decabe8e8dbe 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -124,6 +124,7 @@ enum iommu_attr { DOMAIN_ATTR_FSL_PAMU_ENABLE, DOMAIN_ATTR_FSL_PAMUV1, DOMAIN_ATTR_NESTING, /* two stages of translation */ + DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, DOMAIN_ATTR_MAX, }; -- cgit v1.2.3 From 8ad50c8985d805923f52a80698010a0a5123c07d Mon Sep 17 00:00:00 2001 From: Kristina Martsenko Date: Wed, 26 Sep 2018 17:32:50 +0100 Subject: vgic: Add support for 52bit guest physical address Add support for handling 52bit guest physical address to the VGIC layer. So far we have limited the guest physical address to 48bits, by explicitly masking the upper bits. This patch removes the restriction. We do not have to check if the host supports 52bit as the gpa is always validated during an access. (e.g, kvm_{read/write}_guest, kvm_is_visible_gfn()). Also, the ITS table save-restore is also not affected with the enhancement. The DTE entries already store the bits[51:8] of the ITT_addr (with a 256byte alignment). Cc: Marc Zyngier Cc: Christoffer Dall Reviewed-by: Eric Auger Signed-off-by: Kristina Martsenko [ Macro clean ups, fix PROPBASER and PENDBASER accesses ] Signed-off-by: Suzuki K Poulose Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 8bdbb5f29494..74b0aa9c7499 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -357,6 +357,8 @@ #define GITS_CBASER_RaWaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWt) #define GITS_CBASER_RaWaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWb) +#define GITS_CBASER_ADDRESS(cbaser) ((cbaser) & GENMASK_ULL(51, 12)) + #define GITS_BASER_NR_REGS 8 #define GITS_BASER_VALID (1ULL << 63) @@ -388,6 +390,9 @@ #define GITS_BASER_ENTRY_SIZE_MASK GENMASK_ULL(52, 48) #define GITS_BASER_PHYS_52_to_48(phys) \ (((phys) & GENMASK_ULL(47, 16)) | (((phys) >> 48) & 0xf) << 12) +#define GITS_BASER_ADDR_48_to_52(baser) \ + (((baser) & GENMASK_ULL(47, 16)) | (((baser) >> 12) & 0xf) << 48) + #define GITS_BASER_SHAREABILITY_SHIFT (10) #define GITS_BASER_InnerShareable \ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) -- cgit v1.2.3 From 8bad74f9840f87661f20ced3dc80c84ab4fd55a1 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:36 +0000 Subject: bpf: extend cgroup bpf core to allow multiple cgroup storage types In order to introduce per-cpu cgroup storage, let's generalize bpf cgroup core to support multiple cgroup storage types. Potentially, per-node cgroup storage can be added later. This commit is mostly a formal change that replaces cgroup_storage pointer with a array of cgroup_storage pointers. It doesn't actually introduce a new storage type, it will be done later. Each bpf program is now able to have one cgroup storage of each type. Signed-off-by: Roman Gushchin Acked-by: Song Liu Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 38 ++++++++++++++++++++++++++++---------- include/linux/bpf.h | 11 +++++++++-- 2 files changed, 37 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index f91b0f8ff3a9..e9871b012dac 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -2,6 +2,7 @@ #ifndef _BPF_CGROUP_H #define _BPF_CGROUP_H +#include #include #include #include @@ -22,7 +23,10 @@ struct bpf_cgroup_storage; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) -DECLARE_PER_CPU(void*, bpf_cgroup_storage); +DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); + +#define for_each_cgroup_storage_type(stype) \ + for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) struct bpf_cgroup_storage_map; @@ -43,7 +47,7 @@ struct bpf_cgroup_storage { struct bpf_prog_list { struct list_head node; struct bpf_prog *prog; - struct bpf_cgroup_storage *storage; + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; struct bpf_prog_array; @@ -101,18 +105,29 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum bpf_attach_type type); -static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) +static inline enum bpf_cgroup_storage_type cgroup_storage_type( + struct bpf_map *map) { + return BPF_CGROUP_STORAGE_SHARED; +} + +static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage + *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) +{ + enum bpf_cgroup_storage_type stype; struct bpf_storage_buffer *buf; - if (!storage) - return; + for_each_cgroup_storage_type(stype) { + if (!storage[stype]) + continue; - buf = READ_ONCE(storage->buf); - this_cpu_write(bpf_cgroup_storage, &buf->data[0]); + buf = READ_ONCE(storage[stype]->buf); + this_cpu_write(bpf_cgroup_storage[stype], &buf->data[0]); + } } -struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog); +struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, + enum bpf_cgroup_storage_type stype); void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage); void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, struct cgroup *cgroup, @@ -265,13 +280,14 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } -static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) {} +static inline void bpf_cgroup_storage_set( + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {} static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map) { return 0; } static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map) {} static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( - struct bpf_prog *prog) { return 0; } + struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return 0; } static inline void bpf_cgroup_storage_free( struct bpf_cgroup_storage *storage) {} @@ -293,6 +309,8 @@ static inline void bpf_cgroup_storage_free( #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) +#define for_each_cgroup_storage_type(stype) for (; false; ) + #endif /* CONFIG_CGROUP_BPF */ #endif /* _BPF_CGROUP_H */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 988a00797bcd..b457fbe7b70b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -272,6 +272,13 @@ struct bpf_prog_offload { u32 jited_len; }; +enum bpf_cgroup_storage_type { + BPF_CGROUP_STORAGE_SHARED, + __BPF_CGROUP_STORAGE_MAX +}; + +#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX + struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; @@ -289,7 +296,7 @@ struct bpf_prog_aux { struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ - struct bpf_map *cgroup_storage; + struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY void *security; @@ -358,7 +365,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, */ struct bpf_prog_array_item { struct bpf_prog *prog; - struct bpf_cgroup_storage *cgroup_storage; + struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; struct bpf_prog_array { -- cgit v1.2.3 From f294b37ec7b24a574884cd157497a3748081c0f0 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:40 +0000 Subject: bpf: rework cgroup storage pointer passing To simplify the following introduction of per-cpu cgroup storage, let's rework a bit a mechanism of passing a pointer to a cgroup storage into the bpf_get_local_storage(). Let's save a pointer to the corresponding bpf_cgroup_storage structure, instead of a pointer to the actual buffer. It will help us to handle per-cpu storage later, which has a different way of accessing to the actual data. Signed-off-by: Roman Gushchin Acked-by: Song Liu Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index e9871b012dac..7e0c9a1d48b7 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -23,7 +23,8 @@ struct bpf_cgroup_storage; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) -DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +DECLARE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) @@ -115,15 +116,9 @@ static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { enum bpf_cgroup_storage_type stype; - struct bpf_storage_buffer *buf; - - for_each_cgroup_storage_type(stype) { - if (!storage[stype]) - continue; - buf = READ_ONCE(storage[stype]->buf); - this_cpu_write(bpf_cgroup_storage[stype], &buf->data[0]); - } + for_each_cgroup_storage_type(stype) + this_cpu_write(bpf_cgroup_storage[stype], storage[stype]); } struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, -- cgit v1.2.3 From b741f1630346defcbc8cc60f1a2bdae8b3b0036f Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:43 +0000 Subject: bpf: introduce per-cpu cgroup local storage This commit introduced per-cpu cgroup local storage. Per-cpu cgroup local storage is very similar to simple cgroup storage (let's call it shared), except all the data is per-cpu. The main goal of per-cpu variant is to implement super fast counters (e.g. packet counters), which don't require neither lookups, neither atomic operations. >From userspace's point of view, accessing a per-cpu cgroup storage is similar to other per-cpu map types (e.g. per-cpu hashmaps and arrays). Writing to a per-cpu cgroup storage is not atomic, but is performed by copying longs, so some minimal atomicity is here, exactly as with other per-cpu maps. Signed-off-by: Roman Gushchin Cc: Daniel Borkmann Cc: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 20 +++++++++++++++++++- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + 3 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 7e0c9a1d48b7..588dd5f0bd85 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -37,7 +37,10 @@ struct bpf_storage_buffer { }; struct bpf_cgroup_storage { - struct bpf_storage_buffer *buf; + union { + struct bpf_storage_buffer *buf; + void __percpu *percpu_buf; + }; struct bpf_cgroup_storage_map *map; struct bpf_cgroup_storage_key key; struct list_head list; @@ -109,6 +112,9 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { + if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) + return BPF_CGROUP_STORAGE_PERCPU; + return BPF_CGROUP_STORAGE_SHARED; } @@ -131,6 +137,10 @@ void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map); void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map); +int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); +int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, + void *value, u64 flags); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -285,6 +295,14 @@ static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return 0; } static inline void bpf_cgroup_storage_free( struct bpf_cgroup_storage *storage) {} +static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, + void *value) { + return 0; +} +static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, + void *key, void *value, u64 flags) { + return 0; +} #define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b457fbe7b70b..018299a595c8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -274,6 +274,7 @@ struct bpf_prog_offload { enum bpf_cgroup_storage_type { BPF_CGROUP_STORAGE_SHARED, + BPF_CGROUP_STORAGE_PERCPU, __BPF_CGROUP_STORAGE_MAX }; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index c9bd6fb765b0..5432f4c9f50e 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -43,6 +43,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops) #endif #ifdef CONFIG_CGROUP_BPF BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, cgroup_storage_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops) -- cgit v1.2.3 From c6d4381220a0087ce19dbf6984d92c451bd6b364 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Sep 2018 19:27:24 -0400 Subject: dma-mapping: make the get_required_mask method available unconditionally This save some duplication for ia64, and makes the interface more general. In the long run we want each dma_map_ops instance to fill this out, but this will take a little more prep work. Signed-off-by: Christoph Hellwig Acked-by: Benjamin Herrenschmidt --- include/linux/dma-mapping.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index d23fc45c8208..562af6b45f23 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -130,9 +130,7 @@ struct dma_map_ops { enum dma_data_direction direction); int (*mapping_error)(struct device *dev, dma_addr_t dma_addr); int (*dma_supported)(struct device *dev, u64 mask); -#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK u64 (*get_required_mask)(struct device *dev); -#endif }; extern const struct dma_map_ops dma_direct_ops; -- cgit v1.2.3 From a20bb058375147cb639c7aa17ef86ad68b32d847 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Sep 2018 13:26:13 +0200 Subject: dma-direct: add an explicit dma_direct_get_required_mask This is somewhat modelled after the powerpc version, and differs from the legacy fallback in use fls64 instead of pointlessly splitting up the address into low and high dwords and in that it takes (__)phys_to_dma into account. Signed-off-by: Christoph Hellwig Acked-by: Benjamin Herrenschmidt Reviewed-by: Robin Murphy --- include/linux/dma-direct.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 86a59ba5a7f3..b79496d8c75b 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -55,6 +55,7 @@ static inline void dma_mark_clean(void *addr, size_t size) } #endif /* CONFIG_ARCH_HAS_DMA_MARK_CLEAN */ +u64 dma_direct_get_required_mask(struct device *dev); void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, -- cgit v1.2.3 From b4ebe6063204da58e48600b810a97c29ae9e5d12 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Sep 2018 14:04:08 +0200 Subject: dma-direct: implement complete bus_dma_mask handling Instead of rejecting devices with a too small bus_dma_mask we can handle by taking the bus dma_mask into account for allocations and bounce buffering decisions. Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index b79496d8c75b..fbca184ff5a0 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -27,7 +27,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) if (!dev->dma_mask) return false; - return addr + size - 1 <= *dev->dma_mask; + return addr + size - 1 <= + min_not_zero(*dev->dma_mask, dev->bus_dma_mask); } #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */ -- cgit v1.2.3 From 4d8fcf216c90bc25e34ae2200aa8985ee3158898 Mon Sep 17 00:00:00 2001 From: Alaa Hleihel Date: Wed, 5 Sep 2018 11:43:23 +0300 Subject: net/mlx5e: Avoid unbounded peer devices when unpairing TC hairpin rules If the peer device was already unbound, then do not attempt to modify it's resources, otherwise we will crash on dereferencing non-existing device. Fixes: 5c65c564c962 ("net/mlx5e: Support offloading TC NIC hairpin flows") Signed-off-by: Alaa Hleihel Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/transobj.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index 83a33a1873a6..7f5ca2cd3a32 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -90,6 +90,8 @@ struct mlx5_hairpin { u32 *rqn; u32 *sqn; + + bool peer_gone; }; struct mlx5_hairpin * -- cgit v1.2.3 From 59c9d35ea9cd73c3a55642ec9a0097770baccb93 Mon Sep 17 00:00:00 2001 From: Alaa Hleihel Date: Wed, 5 Sep 2018 17:06:37 +0300 Subject: net/mlx5: Cache the system image guid The system image guid is a read-only field which is used by the TC offloads code to determine if two mlx5 devices belong to the same ASIC while adding flows. Read this once and save it on the core device rather than querying each time an offloaded flow is added. Signed-off-by: Alaa Hleihel Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/vport.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ed73b51f6697..26a92462f4ce 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -838,6 +838,7 @@ struct mlx5_core_dev { u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; u32 qcam[MLX5_ST_SZ_DW(qcam_reg)]; } caps; + u64 sys_image_guid; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; enum mlx5_device_state state; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 7e7c6dfcfb09..9c694808c212 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -121,4 +121,6 @@ int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status); int mlx5_nic_vport_affiliate_multiport(struct mlx5_core_dev *master_mdev, struct mlx5_core_dev *port_mdev); int mlx5_nic_vport_unaffiliate_multiport(struct mlx5_core_dev *port_mdev); + +u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From 783f4a4408e1251d17f333ad56abac24dde988b9 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 27 Sep 2018 16:58:54 -0700 Subject: nvme: call nvme_complete_rq when nvmf_check_ready fails for mpath I/O When an io is rejected by nvmf_check_ready() due to validation of the controller state, the nvmf_fail_nonready_command() will normally return BLK_STS_RESOURCE to requeue and retry. However, if the controller is dying or the I/O is marked for NVMe multipath, the I/O is failed so that the controller can terminate or so that the io can be issued on a different path. Unfortunately, as this reject point is before the transport has accepted the command, blk-mq ends up completing the I/O and never calls nvme_complete_rq(), which is where multipath may preserve or re-route the I/O. The end result is, the device user ends up seeing an EIO error. Example: single path connectivity, controller is under load, and a reset is induced. An I/O is received: a) while the reset state has been set but the queues have yet to be stopped; or b) after queues are started (at end of reset) but before the reconnect has completed. The I/O finishes with an EIO status. This patch makes the following changes: - Adds the HOST_PATH_ERROR pathing status from TP4028 - Modifies the reject point such that it appears to queue successfully, but actually completes the io with the new pathing status and calls nvme_complete_rq(). - nvme_complete_rq() recognizes the new status, avoids resetting the controller (likely was already done in order to get this new status), and calls the multipather to clear the current path that errored. This allows the next command (retry or new command) to select a new path if there is one. Signed-off-by: James Smart Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 68e91ef5494c..818dbe9331be 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1241,6 +1241,7 @@ enum { NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, + NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_DNR = 0x4000, }; -- cgit v1.2.3 From 684bec1092b6991ff2a7751e8a763898576eb5c2 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Mon, 1 Oct 2018 15:55:22 -0700 Subject: Input: i8042 - enable keyboard wakeups by default when s2idle is used Previously, on typical consumer laptops, pressing a key on the keyboard when the system is in suspend would cause it to wake up (default or unconditional behaviour). This happens because the EC generates a SCI interrupt in this scenario. That is no longer true on modern laptops based on Intel WhiskeyLake, including Acer Swift SF314-55G, Asus UX333FA, Asus UX433FN and Asus UX533FD. We confirmed with Asus EC engineers that the "Modern Standby" design has been modified so that the EC no longer generates a SCI in this case; the keyboard controller itself should be used for wakeup. In order to retain the standard behaviour of being able to use the keyboard to wake up the system, enable serio wakeups by default on platforms that are using s2idle. Link: https://lkml.kernel.org/r/CAB4CAwfQ0mPMqCLp95TVjw4J0r5zKPWkSvvkK4cpZUGE--w8bQ@mail.gmail.com Reviewed-by: Rafael J. Wysocki Signed-off-by: Daniel Drake Signed-off-by: Dmitry Torokhov --- include/linux/suspend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 440b62f7502e..206b735f383f 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -251,6 +251,7 @@ static inline bool idle_should_enter_s2idle(void) return unlikely(s2idle_state == S2IDLE_STATE_ENTER); } +extern bool pm_suspend_via_s2idle(void); extern void __init pm_states_init(void); extern void s2idle_set_ops(const struct platform_s2idle_ops *ops); extern void s2idle_wake(void); @@ -282,6 +283,7 @@ static inline void pm_set_suspend_via_firmware(void) {} static inline void pm_set_resume_via_firmware(void) {} static inline bool pm_suspend_via_firmware(void) { return false; } static inline bool pm_resume_via_firmware(void) { return false; } +static inline bool pm_suspend_via_s2idle(void) { return false; } static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } -- cgit v1.2.3 From b596d895fa2957e136a6b398b97b06bd42b51291 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Fri, 3 Aug 2018 13:05:11 -0700 Subject: PM / devfreq: Make update_devfreq() public Currently update_devfreq() is only visible to devfreq governors outside of devfreq.c. Make it public to allow drivers that adjust devfreq policies to cause a re-evaluation of the frequency after a policy change. Signed-off-by: Matthias Kaehlcke Reviewed-by: Brian Norris Reviewed-by: Chanwoo Choi Signed-off-by: MyungJoo Ham --- include/linux/devfreq.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 3aae5b3af87c..e4963b0f45da 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -198,6 +198,14 @@ extern void devm_devfreq_remove_device(struct device *dev, extern int devfreq_suspend_device(struct devfreq *devfreq); extern int devfreq_resume_device(struct devfreq *devfreq); +/** + * update_devfreq() - Reevaluate the device and configure frequency + * @devfreq: the devfreq device + * + * Note: devfreq->lock must be held + */ +extern int update_devfreq(struct devfreq *devfreq); + /* Helper functions for devfreq user device driver with OPP. */ extern struct dev_pm_opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq, u32 flags); -- cgit v1.2.3 From b31cdffa2329fe330cd304ca26c250dd1520fb0a Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:09 +0200 Subject: net: phy: Move linkmode helpers to somewhere public phylink has some useful helpers to working with linkmode bitmaps. Move them to there own header so other code can use them. Signed-off-by: Andrew Lunn Acked-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/linkmode.h | 67 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mii.h | 1 + include/linux/phy.h | 1 + 3 files changed, 69 insertions(+) create mode 100644 include/linux/linkmode.h (limited to 'include/linux') diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h new file mode 100644 index 000000000000..014fb86c7114 --- /dev/null +++ b/include/linux/linkmode.h @@ -0,0 +1,67 @@ +#ifndef __LINKMODE_H +#define __LINKMODE_H + +#include +#include +#include + +static inline void linkmode_zero(unsigned long *dst) +{ + bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_copy(unsigned long *dst, const unsigned long *src) +{ + bitmap_copy(dst, src, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_and(unsigned long *dst, const unsigned long *a, + const unsigned long *b) +{ + bitmap_and(dst, a, b, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_or(unsigned long *dst, const unsigned long *a, + const unsigned long *b) +{ + bitmap_or(dst, a, b, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline bool linkmode_empty(const unsigned long *src) +{ + return bitmap_empty(src, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2) +{ + return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) +{ + __set_bit(nr, addr); +} + +static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) +{ + __clear_bit(nr, addr); +} + +static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) +{ + __change_bit(nr, addr); +} + +static inline int linkmode_test_bit(int nr, volatile unsigned long *addr) +{ + return test_bit(nr, addr); +} + +static inline int linkmode_equal(const unsigned long *src1, + const unsigned long *src2) +{ + return bitmap_equal(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +#endif /* __LINKMODE_H */ diff --git a/include/linux/mii.h b/include/linux/mii.h index 55000ee5c6ad..567047ef0309 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -10,6 +10,7 @@ #include +#include #include struct ethtool_cmd; diff --git a/include/linux/phy.h b/include/linux/phy.h index 192a1fa0c73b..d24cc46748e2 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From ab2a605fa621ecf4ec26603a237822f7772cfa28 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:10 +0200 Subject: net: phy: Add phydev_warn() Not all new style LINK_MODE bits can be converted into old style SUPPORTED bits. We need to warn when such a conversion is attempted. Add a helper for this. Convert all pr_warn() calls to phydev_warn() where possible. Signed-off-by: Andrew Lunn Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index d24cc46748e2..0ab9f89773fd 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -968,6 +968,9 @@ static inline void phy_device_reset(struct phy_device *phydev, int value) #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) +#define phydev_warn(_phydev, format, args...) \ + dev_warn(&_phydev->mdio.dev, format, ##args) + #define phydev_dbg(_phydev, format, args...) \ dev_dbg(&_phydev->mdio.dev, format, ##args) -- cgit v1.2.3 From c4fabb8b3c0d724eb93dabaf346b0dd8a8be7118 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:11 +0200 Subject: net: phy: Add phydev_info() Add phydev_info() and make use of it within the phy drivers and core code. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 0ab9f89773fd..0f6e7bf5e9c5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -968,6 +968,9 @@ static inline void phy_device_reset(struct phy_device *phydev, int value) #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) +#define phydev_info(_phydev, format, args...) \ + dev_info(&_phydev->mdio.dev, format, ##args) + #define phydev_warn(_phydev, format, args...) \ dev_warn(&_phydev->mdio.dev, format, ##args) -- cgit v1.2.3 From edc7ccbbcf32b97c7d26cd556f364eb4f22c4285 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:12 +0200 Subject: net: phy: Add helper to convert MII ADV register to a linkmode The phy_mii_ioctl can be used to write a value into the MII_ADVERTISE register in the PHY. Since this changes the state of the PHY, we need to make the same change to phydev->advertising. Add a helper which can convert the register value to a linkmode. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/mii.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 567047ef0309..8c7da9473ad9 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -303,6 +303,37 @@ static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa) return result | mii_adv_to_ethtool_adv_x(lpa); } +/** + * mii_adv_to_linkmode_adv_t + * @advertising:pointer to destination link mode. + * @adv: value of the MII_ADVERTISE register + * + * A small helper function that translates MII_ADVERTISE bits + * to linkmode advertisement settings. + */ +static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, + u32 adv) +{ + linkmode_zero(advertising); + + if (adv & ADVERTISE_10HALF) + linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, + advertising); + if (adv & ADVERTISE_10FULL) + linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, + advertising); + if (adv & ADVERTISE_100HALF) + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, + advertising); + if (adv & ADVERTISE_100FULL) + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + advertising); + if (adv & ADVERTISE_PAUSE_CAP) + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising); + if (adv & ADVERTISE_PAUSE_ASYM) + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising); +} + /** * mii_advertise_flowctrl - get flow control advertisement flags * @cap: Flow control capabilities (FLOW_CTRL_RX, FLOW_CTRL_TX or both) -- cgit v1.2.3 From 5f991f7bddc991ecc3c8a009ffd76fccff4661c7 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:13 +0200 Subject: net: phy: Add helper for advertise to lcl value Add a helper to convert the local advertising to an LCL capabilities, which is then used to resolve pause flow control settings. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/mii.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 8c7da9473ad9..9ed49c8261d0 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -334,6 +334,25 @@ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising); } +/** + * ethtool_adv_to_lcl_adv_t + * @advertising:pointer to ethtool advertising + * + * A small helper function that translates ethtool advertising to LVL + * pause capabilities. + */ +static inline u32 ethtool_adv_to_lcl_adv_t(u32 advertising) +{ + u32 lcl_adv = 0; + + if (advertising & ADVERTISED_Pause) + lcl_adv |= ADVERTISE_PAUSE_CAP; + if (advertising & ADVERTISED_Asym_Pause) + lcl_adv |= ADVERTISE_PAUSE_ASYM; + + return lcl_adv; +} + /** * mii_advertise_flowctrl - get flow control advertisement flags * @cap: Flow control capabilities (FLOW_CTRL_RX, FLOW_CTRL_TX or both) -- cgit v1.2.3 From f954a04ea18ebfcba1cd2756eaee59eb4978a20e Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:14 +0200 Subject: net: phy: Add limkmode equivalents to some of the MII ethtool helpers Add helpers which take a linkmode rather than a u32 ethtool for advertising settings. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/mii.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 9ed49c8261d0..2da85b02e1c0 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -132,6 +132,34 @@ static inline u32 ethtool_adv_to_mii_adv_t(u32 ethadv) return result; } +/** + * linkmode_adv_to_mii_adv_t + * @advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * MII_ADVERTISE register. + */ +static inline u32 linkmode_adv_to_mii_adv_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, advertising)) + result |= ADVERTISE_10HALF; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, advertising)) + result |= ADVERTISE_10FULL; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, advertising)) + result |= ADVERTISE_100HALF; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, advertising)) + result |= ADVERTISE_100FULL; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising)) + result |= ADVERTISE_PAUSE_CAP; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising)) + result |= ADVERTISE_PAUSE_ASYM; + + return result; +} + /** * mii_adv_to_ethtool_adv_t * @adv: value of the MII_ADVERTISE register @@ -179,6 +207,28 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv) return result; } +/** + * linkmode_adv_to_mii_ctrl1000_t + * advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * MII_CTRL1000 register when in 1000T mode. + */ +static inline u32 linkmode_adv_to_mii_ctrl1000_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, + advertising)) + result |= ADVERTISE_1000HALF; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + advertising)) + result |= ADVERTISE_1000FULL; + + return result; +} + /** * mii_ctrl1000_to_ethtool_adv_t * @adv: value of the MII_CTRL1000 register -- cgit v1.2.3 From 719655a149715f26fc4de904fe0aa83068bd5b9e Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:16 +0200 Subject: net: phy: Replace phy driver features u32 with link_mode bitmap This is one step in allowing phylib to make use of link_mode bitmaps, instead of u32 for supported and advertised features. Convert the phy drivers to use bitmaps to indicates the features they support. Build bitmap equivalents of the u32 values at runtime, and have the drivers point to the appropriate bitmap. These bitmaps are shared, and we don't want a driver to modify them. So mark them __ro_after_init. Within phylib, the features bitmap is currently turned back into a u32. This will be removed once the whole of phylib, and the drivers are converted to use bitmaps. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/linkmode.h | 9 +++++++++ include/linux/phy.h | 24 ++++++++++++++++-------- 2 files changed, 25 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 014fb86c7114..22443d7fb5cd 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -43,6 +43,15 @@ static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) __set_bit(nr, addr); } +static inline void linkmode_set_bit_array(const int *array, int array_size, + unsigned long *addr) +{ + int i; + + for (i = 0; i < array_size; i++) + linkmode_set_bit(array[i], addr); +} + static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) { __clear_bit(nr, addr); diff --git a/include/linux/phy.h b/include/linux/phy.h index 0f6e7bf5e9c5..dff51dd36e52 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -42,13 +42,21 @@ #define PHY_1000BT_FEATURES (SUPPORTED_1000baseT_Half | \ SUPPORTED_1000baseT_Full) -#define PHY_BASIC_FEATURES (PHY_10BT_FEATURES | \ - PHY_100BT_FEATURES | \ - PHY_DEFAULT_FEATURES) - -#define PHY_GBIT_FEATURES (PHY_BASIC_FEATURES | \ - PHY_1000BT_FEATURES) - +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; + +#define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) +#define PHY_BASIC_T1_FEATURES ((unsigned long *)&phy_basic_t1_features) +#define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) +#define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) +#define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) +#define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) +#define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) /* * Set phydev->irq to PHY_POLL if interrupts are not supported, @@ -510,7 +518,7 @@ struct phy_driver { u32 phy_id; char *name; u32 phy_id_mask; - u32 features; + const unsigned long * const features; u32 flags; const void *driver_data; -- cgit v1.2.3 From 9f2959b6b52d43326b2f6a0e0d7ffe6f4fc3b5ca Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 28 Sep 2018 08:51:09 +0200 Subject: net: phy: improve handling delayed work Using mod_delayed_work() allows to simplify handling delayed work and removes the need for the sync parameter in phy_trigger_machine(). Also introduce a helper phy_queue_state_machine() to encapsulate the low-level delayed work calls. No functional change intended. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index dff51dd36e52..3ea87f774a76 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1054,7 +1054,7 @@ void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); -void phy_trigger_machine(struct phy_device *phydev, bool sync); +void phy_trigger_machine(struct phy_device *phydev); int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); -- cgit v1.2.3 From efaffc5e40aeced0bcb497ed7a0a5b8c14abfcdf Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 1 Oct 2018 11:05:24 +0100 Subject: mm, sched/numa: Remove rate-limiting of automatic NUMA balancing migration Rate limiting of page migrations due to automatic NUMA balancing was introduced to mitigate the worst-case scenario of migrating at high frequency due to false sharing or slowly ping-ponging between nodes. Since then, a lot of effort was spent on correctly identifying these pages and avoiding unnecessary migrations and the safety net may no longer be required. Jirka Hladky reported a regression in 4.17 due to a scheduler patch that avoids spreading STREAM tasks wide prematurely. However, once the task was properly placed, it delayed migrating the memory due to rate limiting. Increasing the limit fixed the problem for him. Currently, the limit is hard-coded and does not account for the real capabilities of the hardware. Even if an estimate was attempted, it would not properly account for the number of memory controllers and it could not account for the amount of bandwidth used for normal accesses. Rather than fudging, this patch simply eliminates the rate limiting. However, Jirka reports that a STREAM configuration using multiple processes achieved similar performance to 4.16. In local tests, this patch improved performance of STREAM relative to the baseline but it is somewhat machine-dependent. Most workloads show little or not performance difference implying that there is not a heavily reliance on the throttling mechanism and it is safe to remove. STREAM on 2-socket machine 4.19.0-rc5 4.19.0-rc5 numab-v1r1 noratelimit-v1r1 MB/sec copy 43298.52 ( 0.00%) 44673.38 ( 3.18%) MB/sec scale 30115.06 ( 0.00%) 31293.06 ( 3.91%) MB/sec add 32825.12 ( 0.00%) 34883.62 ( 6.27%) MB/sec triad 32549.52 ( 0.00%) 34906.60 ( 7.24% Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Acked-by: Peter Zijlstra Cc: Jirka Hladky Cc: Linus Torvalds Cc: Linux-MM Cc: Srikar Dronamraju Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181001100525.29789-2-mgorman@techsingularity.net Signed-off-by: Ingo Molnar --- include/linux/mmzone.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1e22d96734e0..3f4c0b167333 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -671,12 +671,6 @@ typedef struct pglist_data { #ifdef CONFIG_NUMA_BALANCING /* Lock serializing the migrate rate limiting window */ spinlock_t numabalancing_migrate_lock; - - /* Rate limiting time interval */ - unsigned long numabalancing_migrate_next_window; - - /* Number of pages migrated during the rate limiting time interval */ - unsigned long numabalancing_migrate_nr_pages; #endif /* * This is a per-node reserve of pages that are not available -- cgit v1.2.3 From 11e37d357f6ba7a9af850a872396082cc0a0001f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 27 Jul 2018 13:38:54 +0100 Subject: irqchip/gic-v3-its: Move pending table allocation to init time Pending tables for the redistributors are currently allocated one at a time as each CPU boots. This is causing some grief for Linux/RT (allocation from within a CPU hotplug notifier is frown upon). Let's move this allocation to take place at init time, when we only have a single CPU. It means we're allocating memory for CPUs that are not online yet, but most system will boot all of their CPUs anyway, so that's not completely wasted. Tested-by: Jeremy Linton Tested-by: Bhupesh Sharma Tested-by: Lei Zhang Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 8bdbb5f29494..266093e845bb 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -585,6 +585,7 @@ struct rdists { void __iomem *rd_base; struct page *pend_page; phys_addr_t phys_base; + bool lpi_enabled; } __percpu *rdist; struct page *prop_page; u64 flags; -- cgit v1.2.3 From e1a2e2010ba9d3c765b2e37a7ae8b332564716f1 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 27 Jul 2018 14:36:00 +0100 Subject: irqchip/gic-v3-its: Keep track of property table's PA and VA We're currently only tracking the page allocated to contain the property table by its struct page. In the future, it is going to be convenient to track both PA and VA for that page instead. Let's do that. Tested-by: Jeremy Linton Tested-by: Bhupesh Sharma Tested-by: Lei Zhang Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 266093e845bb..c2a7b863fc2e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -587,7 +587,8 @@ struct rdists { phys_addr_t phys_base; bool lpi_enabled; } __percpu *rdist; - struct page *prop_page; + phys_addr_t prop_table_pa; + void *prop_table_va; u64 flags; u32 gicd_typer; bool has_vlpis; -- cgit v1.2.3 From 1f83515bebc236d2acda59976a8e852f1a6d50b7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 1 Oct 2018 16:13:45 +0200 Subject: genirq/msi: Allow creation of a tree-based irqdomain for platform-msi platform_msi_create_device_domain() always creates a revmap-based irqdomain, which has the drawback of requiring the number of MSIs that can be allocated ahead of time. This is not always possible, and we sometimes need to use a tree-based irqdomain instead. Add a new platform_msi_create_device_tree_domain() helper to that effect. Reported-by: Miquel Raynal Signed-off-by: Marc Zyngier Signed-off-by: Miquel Raynal Signed-off-by: Marc Zyngier --- include/linux/msi.h | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 5839d8062dfc..0e9c50052ff3 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -317,11 +317,18 @@ int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, int virq, int nvec, msi_alloc_info_t *args); struct irq_domain * -platform_msi_create_device_domain(struct device *dev, - unsigned int nvec, - irq_write_msi_msg_t write_msi_msg, - const struct irq_domain_ops *ops, - void *host_data); +__platform_msi_create_device_domain(struct device *dev, + unsigned int nvec, + bool is_tree, + irq_write_msi_msg_t write_msi_msg, + const struct irq_domain_ops *ops, + void *host_data); + +#define platform_msi_create_device_domain(dev, nvec, write, ops, data) \ + __platform_msi_create_device_domain(dev, nvec, false, write, ops, data) +#define platform_msi_create_device_tree_domain(dev, nvec, write, ops, data) \ + __platform_msi_create_device_domain(dev, nvec, true, write, ops, data) + int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs); void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, -- cgit v1.2.3 From 61ce8d8d8a8168a714de80fc31b3d6ac160fc5b0 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 1 Oct 2018 16:13:51 +0200 Subject: irqchip/irq-mvebu-sei: Add new driver for Marvell SEI This is a cascaded interrupt controller in the AP806 GIC that collapses SEIs (System Error Interrupt) coming from the AP and the CPs (through the ICU). The SEI handles up to 64 interrupts. The first 21 interrupts are wired from the AP. The next 43 interrupts are from the CPs and are triggered through MSI messages. To handle this complexity, the driver has to declare to the upper layer: one IRQ domain for the wired interrupts, one IRQ domain for the MSIs; and acts as a MSI controller ('parent') by declaring an MSI domain. Suggested-by: Haim Boot Suggested-by: Marc Zyngier Signed-off-by: Miquel Raynal Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index dccfa65aee96..068aa46f0d55 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -75,6 +75,7 @@ struct irq_fwspec { enum irq_domain_bus_token { DOMAIN_BUS_ANY = 0, DOMAIN_BUS_WIRED, + DOMAIN_BUS_GENERIC_MSI, DOMAIN_BUS_PCI_MSI, DOMAIN_BUS_PLATFORM_MSI, DOMAIN_BUS_NEXUS, -- cgit v1.2.3 From 9524d6b265f9b2b9a61fceb2ee2ce1c2a83e39ca Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 11 Sep 2018 16:40:20 -0700 Subject: dmaengine: ep93xx: Return proper enum in ep93xx_dma_chan_direction Clang warns when implicitly converting from one enumerated type to another. Avoid this by using the equivalent value from the expected type. In file included from drivers/dma/ep93xx_dma.c:30: ./include/linux/platform_data/dma-ep93xx.h:88:10: warning: implicit conversion from enumeration type 'enum dma_data_direction' to different enumeration type 'enum dma_transfer_direction' [-Wenum-conversion] return DMA_NONE; ~~~~~~ ^~~~~~~~ 1 warning generated. Reported-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-ep93xx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-ep93xx.h b/include/linux/platform_data/dma-ep93xx.h index f8f1f6b952a6..eb9805bb3fe8 100644 --- a/include/linux/platform_data/dma-ep93xx.h +++ b/include/linux/platform_data/dma-ep93xx.h @@ -85,7 +85,7 @@ static inline enum dma_transfer_direction ep93xx_dma_chan_direction(struct dma_chan *chan) { if (!ep93xx_dma_chan_is_m2p(chan)) - return DMA_NONE; + return DMA_TRANS_NONE; /* even channels are for TX, odd for RX */ return (chan->chan_id % 2 == 0) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM; -- cgit v1.2.3 From cc16567e5a8a7bb9439ef61ab80069acdd33f76f Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Oct 2018 11:03:40 +0200 Subject: net: drop unused skb_append_datato_frags() This helper is unused since commit 988cf74deb45 ("inet: Stop generating UFO packets.") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 87e29710373f..119d092c6b13 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1082,11 +1082,6 @@ static inline int skb_pad(struct sk_buff *skb, int pad) } #define dev_kfree_skb(a) consume_skb(a) -int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, - int getfrag(void *from, char *to, int offset, - int len, int odd, struct sk_buff *skb), - void *from, int length); - int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size); -- cgit v1.2.3 From 5bf0961cc6a180c077793f2615a8fd842c655876 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Tue, 2 Oct 2018 06:16:11 -0700 Subject: qed: Add driver support for 20G link speed. Add driver support for configuring/reading the 20G link speed. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8cd34645e892..dee3c9c744f7 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -670,10 +670,11 @@ enum qed_link_mode_bits { QED_LM_1000baseT_Half_BIT = BIT(4), QED_LM_1000baseT_Full_BIT = BIT(5), QED_LM_10000baseKR_Full_BIT = BIT(6), - QED_LM_25000baseKR_Full_BIT = BIT(7), - QED_LM_40000baseLR4_Full_BIT = BIT(8), - QED_LM_50000baseKR2_Full_BIT = BIT(9), - QED_LM_100000baseKR4_Full_BIT = BIT(10), + QED_LM_20000baseKR2_Full_BIT = BIT(7), + QED_LM_25000baseKR_Full_BIT = BIT(8), + QED_LM_40000baseLR4_Full_BIT = BIT(9), + QED_LM_50000baseKR2_Full_BIT = BIT(10), + QED_LM_100000baseKR4_Full_BIT = BIT(11), QED_LM_COUNT = 11 }; -- cgit v1.2.3 From c550f01c810f2197c98e6e3103f81797f5e063be Mon Sep 17 00:00:00 2001 From: Steve Sakoman Date: Thu, 20 Sep 2018 09:20:34 -1000 Subject: serial:serial_core: Allow use of CTS for PPS line discipline Add a "pps_4wire" file to serial ports in sysfs in case the kernel is configured with CONFIG_PPS_CLIENT_LDISC. Writing 1 to the file enables the use of CTS instead of DCD for PPS signal input. This is necessary in case a serial port is not completely wired. Though this affects PPS processing the patch is against the serial core as the source of the serial port PPS event dispatching has to be modified. Furthermore it should be possible to modify the source of serial port PPS event dispatching before changing the line discipline. Signed-off-by: Andreas Steinmetz Signed-off-by: Steve Sakoman Tested-by: Steve Sakoman Tested-by: Eric Gallimore Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 406edae44ca3..079793e5d3fa 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -255,7 +255,8 @@ struct uart_port { struct device *dev; /* parent device */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; - unsigned char unused[2]; + unsigned char pps_4wire; /* CTS instead of DCD */ + unsigned char unused; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ -- cgit v1.2.3 From ad8c0eaa0a418ae8ef3f9217638bb86439399eac Mon Sep 17 00:00:00 2001 From: Nicolas Ferre Date: Wed, 26 Sep 2018 14:58:47 +0200 Subject: tty/serial_core: add ISO7816 infrastructure Add the ISO7816 ioctl and associated accessors and data structure. Drivers can then use this common implementation to handle ISO7816 (smart cards). Signed-off-by: Nicolas Ferre [ludovic.desroches@microchip.com: squash and rebase, removal of gpios, checkpatch fixes] Signed-off-by: Ludovic Desroches Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 079793e5d3fa..4e2ba4894dcc 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -144,6 +144,8 @@ struct uart_port { void (*handle_break)(struct uart_port *); int (*rs485_config)(struct uart_port *, struct serial_rs485 *rs485); + int (*iso7816_config)(struct uart_port *, + struct serial_iso7816 *iso7816); unsigned int irq; /* irq number */ unsigned long irqflags; /* irq flags */ unsigned int uartclk; /* base uart clock */ @@ -261,6 +263,7 @@ struct uart_port { struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ struct serial_rs485 rs485; + struct serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; -- cgit v1.2.3 From f0157160b359b1d263ee9d4e0a435a7ad85bbcea Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 20 Sep 2018 10:27:17 -0600 Subject: PCI: Make link active reporting detection generic The spec has timing requirements when waiting for a link to become active after a conventional reset. Implement those hard delays when waiting for an active link so pciehp and dpc drivers don't need to duplicate this. For devices that don't support data link layer active reporting, wait the fixed time recommended by the PCIe spec. Signed-off-by: Keith Busch [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas Reviewed-by: Sinan Kaya --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 6925828f9f25..896b42032ec5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -402,6 +402,7 @@ struct pci_dev { unsigned int has_secondary_link:1; unsigned int non_compliant_bars:1; /* Broken BARs; ignore them */ unsigned int is_probed:1; /* Device probing in progress */ + unsigned int link_active_reporting:1;/* Device capable of reporting link active */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ -- cgit v1.2.3 From 5f5e4890d57a8af5da72c9d73a4efa9bad43a7a3 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 27 Sep 2018 16:57:05 -0500 Subject: ACPI / property: Allow multiple property compatible _DSD entries It is possible to have _DSD entries where the data is compatible with device properties format but are using different GUID for various reasons. In addition to that there can be many such _DSD entries for a single device such as for PCIe root port used to host a Thunderbolt hierarchy: Scope (\_SB.PCI0.RP21) { Name (_DSD, Package () { ToUUID ("6211e2c0-58a3-4af3-90e1-927a4e0c55a4"), Package () { Package () {"HotPlugSupportInD3", 1} }, ToUUID ("efcc06cc-73ac-4bc3-bff0-76143807c389"), Package () { Package () {"ExternalFacingPort", 1}, Package () {"UID", 0 } } }) } More information about these new _DSD entries can be found in: https://docs.microsoft.com/en-us/windows-hardware/drivers/pci/dsd-for-pcie-root-ports To make these available for drivers via unified device property APIs, modify ACPI property core so that it supports multiple _DSD entries organized in a linked list. We also store GUID of each _DSD entry in struct acpi_device_properties in case there is need to differentiate between entries. The supported GUIDs are then listed in prp_guids array. Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Sakari Ailus --- include/linux/acpi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index de8d3d3fa651..51e3c29663fe 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1074,6 +1074,15 @@ static inline int acpi_node_get_property_reference( NR_FWNODE_REFERENCE_ARGS, args); } +static inline bool acpi_dev_has_props(const struct acpi_device *adev) +{ + return !list_empty(&adev->data.properties); +} + +struct acpi_device_properties * +acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, + const union acpi_object *properties); + int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); int acpi_dev_prop_read_single(struct acpi_device *adev, -- cgit v1.2.3 From 10653022456dc77b398777fd8e95126c77954b49 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 30 Aug 2018 14:54:03 +0200 Subject: Revert "serial: sh-sci: Remove SCIx_RZ_SCIFA_REGTYPE" This reverts commit 7acece71a517cad83a0842a94d94c13f271b680c. Signed-off-by: Geert Uytterhoeven Acked-by: Chris Brandt Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_sci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index c0e795d95477..1c89611e0e06 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -36,6 +36,7 @@ enum { SCIx_SH4_SCIF_FIFODATA_REGTYPE, SCIx_SH7705_SCIF_REGTYPE, SCIx_HSCIF_REGTYPE, + SCIx_RZ_SCIFA_REGTYPE, SCIx_NR_REGTYPES, }; -- cgit v1.2.3 From fd3b339cbb6047dacfa7ccc81c846efcb61032a9 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 1 Oct 2018 12:31:21 +0300 Subject: thunderbolt: Convert rest of the driver files to use SPDX identifier This gets rid of the licence boilerplate duplicated in each file. While there fix doubled space in domain.c author line. No functional changes intended. Signed-off-by: Mika Westerberg Acked-by: Yehezkel Bernat Signed-off-by: Greg Kroah-Hartman --- include/linux/thunderbolt.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index a3ed26082bc1..bf6ec83e60ee 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Thunderbolt service API * @@ -5,10 +6,6 @@ * Copyright (C) 2017, Intel Corporation * Authors: Michael Jamet * Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef THUNDERBOLT_H_ -- cgit v1.2.3 From f3709f69b7c5cba6323cc03c29b64293b93be817 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 2 Oct 2018 13:35:29 -0700 Subject: bpf: Add iterator for spilled registers Add this iterator for spilled registers, it concentrates the details of how to get the current frame's spilled registers into a single macro while clarifying the intention of the code which is calling the macro. Signed-off-by: Joe Stringer Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b42b60a83e19..d0e7f97e8b60 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -131,6 +131,17 @@ struct bpf_verifier_state { u32 curframe; }; +#define bpf_get_spilled_reg(slot, frame) \ + (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ + (frame->stack[slot].slot_type[0] == STACK_SPILL)) \ + ? &frame->stack[slot].spilled_ptr : NULL) + +/* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ +#define bpf_for_each_spilled_reg(iter, frame, reg) \ + for (iter = 0, reg = bpf_get_spilled_reg(iter, frame); \ + iter < frame->allocated_stack / BPF_REG_SIZE; \ + iter++, reg = bpf_get_spilled_reg(iter, frame)) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; -- cgit v1.2.3 From c64b7983288e636356f7f5f652de4813e1cfedac Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 2 Oct 2018 13:35:33 -0700 Subject: bpf: Add PTR_TO_SOCKET verifier type Teach the verifier a little bit about a new type of pointer, a PTR_TO_SOCKET. This pointer type is accessed from BPF through the 'struct bpf_sock' structure. Signed-off-by: Joe Stringer Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 34 ++++++++++++++++++++++++++++++++++ include/linux/bpf_verifier.h | 2 ++ 2 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 018299a595c8..027697b6a22f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -154,6 +154,7 @@ enum bpf_arg_type { ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ + ARG_PTR_TO_SOCKET, /* pointer to bpf_sock */ }; /* type of values returned from helper functions */ @@ -162,6 +163,7 @@ enum bpf_return_type { RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ + RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -213,6 +215,8 @@ enum bpf_reg_type { PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ + PTR_TO_SOCKET, /* reg points to struct bpf_sock */ + PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -343,6 +347,11 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); +typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, + const struct bpf_insn *src, + struct bpf_insn *dst, + struct bpf_prog *prog, + u32 *target_size); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); @@ -836,4 +845,29 @@ extern const struct bpf_func_proto bpf_get_local_storage_proto; void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +#if defined(CONFIG_NET) +bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info); +u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size); +#else +static inline bool bpf_sock_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + return false; +} +static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) +{ + return 0; +} +#endif + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d0e7f97e8b60..a411363098a5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -58,6 +58,8 @@ struct bpf_reg_state { * offset, so they can share range knowledge. * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we * came from, when one is tested for != NULL. + * For PTR_TO_SOCKET this is used to share which pointers retain the + * same reference to the socket, to determine proper reference freeing. */ u32 id; /* For scalar types (SCALAR_VALUE), this represents our knowledge of -- cgit v1.2.3 From fd978bf7fd312581a7ca454a991f0ffb34c4204b Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 2 Oct 2018 13:35:35 -0700 Subject: bpf: Add reference tracking to verifier Allow helper functions to acquire a reference and return it into a register. Specific pointer types such as the PTR_TO_SOCKET will implicitly represent such a reference. The verifier must ensure that these references are released exactly once in each path through the program. To achieve this, this commit assigns an id to the pointer and tracks it in the 'bpf_func_state', then when the function or program exits, verifies that all of the acquired references have been freed. When the pointer is passed to a function that frees the reference, it is removed from the 'bpf_func_state` and all existing copies of the pointer in registers are marked invalid. Signed-off-by: Joe Stringer Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index a411363098a5..7b6fd2ab3263 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -104,6 +104,17 @@ struct bpf_stack_state { u8 slot_type[BPF_REG_SIZE]; }; +struct bpf_reference_state { + /* Track each reference created with a unique id, even if the same + * instruction creates the reference multiple times (eg, via CALL). + */ + int id; + /* Instruction where the allocation of this reference occurred. This + * is used purely to inform the user of a reference leak. + */ + int insn_idx; +}; + /* state of the program: * type of all registers and stack info */ @@ -121,7 +132,9 @@ struct bpf_func_state { */ u32 subprogno; - /* should be second to last. See copy_func_state() */ + /* The following fields should be last. See copy_func_state() */ + int acquired_refs; + struct bpf_reference_state *refs; int allocated_stack; struct bpf_stack_state *stack; }; @@ -217,11 +230,16 @@ __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); -static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) +static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { struct bpf_verifier_state *cur = env->cur_state; - return cur->frame[cur->curframe]->regs; + return cur->frame[cur->curframe]; +} + +static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) +{ + return cur_func(env)->regs; } int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); -- cgit v1.2.3 From 401b25aa1a75e7fe4e3202a6336604269697d705 Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Tue, 2 Oct 2018 22:20:50 -0400 Subject: ext4: convert fault handler to use vm_fault_t type Return type of ext4_page_mkwrite and ext4_filemap_fault are changed to use vm_fault_t type. With this patch all the callers of block_page_mkwrite_return() are changed to handle vm_fault_t. So converting the return type of block_page_mkwrite_return() to vm_fault_t. Signed-off-by: Souptick Joarder Signed-off-by: Theodore Ts'o Reviewed-by: Matthew Wilcox --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 96225a77c112..7b73ef7f902d 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -242,7 +242,7 @@ int block_commit_write(struct page *page, unsigned from, unsigned to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); /* Convert errno to return value from ->page_mkwrite() call */ -static inline int block_page_mkwrite_return(int err) +static inline vm_fault_t block_page_mkwrite_return(int err) { if (err == 0) return VM_FAULT_LOCKED; -- cgit v1.2.3 From f3edc2dbe0ad0bbbd8450cd37328f99acf215fd8 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Mon, 1 Oct 2018 17:02:43 +0100 Subject: net: usbnet: make driver_info const The driver_info field that is used for describing each of the usb-net drivers using the usbnet.c core all declare their information as const and the usbnet.c itself does not try and modify the struct. It is therefore a good idea to make this const in the usbnet.c structure in case anyone tries to modify it. Signed-off-by: Ben Dooks Signed-off-by: Ben Dooks Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index e2ec3582e549..d8860f2d0976 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -28,7 +28,7 @@ struct usbnet { /* housekeeping */ struct usb_device *udev; struct usb_interface *intf; - struct driver_info *driver_info; + const struct driver_info *driver_info; const char *driver_name; void *driver_priv; wait_queue_head_t wait; -- cgit v1.2.3 From 47bd59e538d4e7b3ad9c18bef5c1052657bdff59 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:13 +0200 Subject: mtd: rawnand: plat_nand: Pass a nand_chip object to all platform_nand_ctrl hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. In order to do that, we first need to update the platform_nand_ctrl hooks to take a nand_chip object instead of an mtd_info. We add temporary plat_nand_xxx() wrappers to the do the mtd -> chip conversion, but those will be dropped when patching nand_chip hooks to take a nand_chip object. Signed-off-by: Boris Brezillon Reviewed-by: Alexander Sverdlin Acked-by: Alexander Sverdlin Acked-by: Robert Jarzmik Acked-by: Krzysztof Halasa Acked-by: Paul Burton Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index d155470f53c8..818cdc0a4dbb 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1595,11 +1595,11 @@ struct platform_device; struct platform_nand_ctrl { int (*probe)(struct platform_device *pdev); void (*remove)(struct platform_device *pdev); - int (*dev_ready)(struct mtd_info *mtd); - void (*select_chip)(struct mtd_info *mtd, int chip); - void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); - void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); - void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); + int (*dev_ready)(struct nand_chip *chip); + void (*select_chip)(struct nand_chip *chip, int cs); + void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); + void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); + void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); void *priv; }; -- cgit v1.2.3 From 00ad378f304a091ab2e2df5f944892a6ed558610 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:14 +0200 Subject: mtd: rawnand: Pass a nand_chip object to nand_scan() Let's make the raw NAND API consistent by patching all helpers to take a nand_chip object instead of an mtd_info one. We start with nand_scan(). Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 818cdc0a4dbb..733b228d94a5 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -24,15 +24,16 @@ #include #include +struct nand_chip; struct nand_flash_dev; /* Scan and identify a NAND device */ -int nand_scan_with_ids(struct mtd_info *mtd, int max_chips, +int nand_scan_with_ids(struct nand_chip *chip, int max_chips, struct nand_flash_dev *ids); -static inline int nand_scan(struct mtd_info *mtd, int max_chips) +static inline int nand_scan(struct nand_chip *chip, int max_chips) { - return nand_scan_with_ids(mtd, max_chips, NULL); + return nand_scan_with_ids(chip, max_chips, NULL); } /* Internal helper for board drivers which need to override command function */ -- cgit v1.2.3 From 59ac276f22270fb2094910f9a734c17f41c25e70 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:15 +0200 Subject: mtd: rawnand: Pass a nand_chip object to nand_release() Let's make the raw NAND API consistent by patching all helpers to take a nand_chip object instead of an mtd_info one. Now is nand_release()'s turn. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 733b228d94a5..e9c59f0624ad 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1739,7 +1739,7 @@ int nand_write_data_op(struct nand_chip *chip, const void *buf, */ void nand_cleanup(struct nand_chip *chip); /* Unregister the MTD device and calls nand_cleanup() */ -void nand_release(struct mtd_info *mtd); +void nand_release(struct nand_chip *chip); /* Default extended ID decoding function */ void nand_decode_ext_id(struct nand_chip *chip); -- cgit v1.2.3 From 2b356ab46ebe9b1bc63bda6708b81c9200382e78 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:16 +0200 Subject: mtd: rawnand: Pass a nand_chip object to nand_wait_ready() Let's make the raw NAND API consistent by patching all helpers to take a nand_chip object instead of an mtd_info one. Now is nand_wait_ready()'s turn. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index e9c59f0624ad..55014e42912a 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -37,7 +37,7 @@ static inline int nand_scan(struct nand_chip *chip, int max_chips) } /* Internal helper for board drivers which need to override command function */ -void nand_wait_ready(struct mtd_info *mtd); +void nand_wait_ready(struct nand_chip *chip); /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 -- cgit v1.2.3 From ec47636cd7e7b0dd53e526ec832ebb21b67ad9c6 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:17 +0200 Subject: mtd: rawnand: Pass a nand_chip object to ecc->hwctl() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one. Now is ecc->hwctl()'s turn. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 55014e42912a..029fef900f33 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -647,7 +647,7 @@ struct nand_ecc_ctrl { void *priv; u8 *calc_buf; u8 *code_buf; - void (*hwctl)(struct mtd_info *mtd, int mode); + void (*hwctl)(struct nand_chip *chip, int mode); int (*calculate)(struct mtd_info *mtd, const uint8_t *dat, uint8_t *ecc_code); int (*correct)(struct mtd_info *mtd, uint8_t *dat, uint8_t *read_ecc, -- cgit v1.2.3 From af37d2c3a8c7a05cf5b0fe6b61e2a6b9e357928b Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:18 +0200 Subject: mtd: rawnand: Pass a nand_chip object to ecc->calculate() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one. Now is ecc->calculate()'s turn. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/nand_bch.h | 5 +++-- include/linux/mtd/nand_ecc.h | 4 +++- include/linux/mtd/rawnand.h | 4 ++-- 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand_bch.h b/include/linux/mtd/nand_bch.h index 98f20ef05d60..6db133508960 100644 --- a/include/linux/mtd/nand_bch.h +++ b/include/linux/mtd/nand_bch.h @@ -12,6 +12,7 @@ #define __MTD_NAND_BCH_H__ struct mtd_info; +struct nand_chip; struct nand_bch_control; #if defined(CONFIG_MTD_NAND_ECC_BCH) @@ -21,7 +22,7 @@ static inline int mtd_nand_has_bch(void) { return 1; } /* * Calculate BCH ecc code */ -int nand_bch_calculate_ecc(struct mtd_info *mtd, const u_char *dat, +int nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat, u_char *ecc_code); /* @@ -43,7 +44,7 @@ void nand_bch_free(struct nand_bch_control *nbc); static inline int mtd_nand_has_bch(void) { return 0; } static inline int -nand_bch_calculate_ecc(struct mtd_info *mtd, const u_char *dat, +nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat, u_char *ecc_code) { return -1; diff --git a/include/linux/mtd/nand_ecc.h b/include/linux/mtd/nand_ecc.h index 8a2decf7462c..a514e62ff54f 100644 --- a/include/linux/mtd/nand_ecc.h +++ b/include/linux/mtd/nand_ecc.h @@ -14,6 +14,7 @@ #define __MTD_NAND_ECC_H__ struct mtd_info; +struct nand_chip; /* * Calculate 3 byte ECC code for eccsize byte block @@ -24,7 +25,8 @@ void __nand_calculate_ecc(const u_char *dat, unsigned int eccsize, /* * Calculate 3 byte ECC code for 256/512 byte block */ -int nand_calculate_ecc(struct mtd_info *mtd, const u_char *dat, u_char *ecc_code); +int nand_calculate_ecc(struct nand_chip *chip, const u_char *dat, + u_char *ecc_code); /* * Detect and correct a 1 bit error for eccsize byte block diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 029fef900f33..b2f51b2fb110 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -648,8 +648,8 @@ struct nand_ecc_ctrl { u8 *calc_buf; u8 *code_buf; void (*hwctl)(struct nand_chip *chip, int mode); - int (*calculate)(struct mtd_info *mtd, const uint8_t *dat, - uint8_t *ecc_code); + int (*calculate)(struct nand_chip *chip, const uint8_t *dat, + uint8_t *ecc_code); int (*correct)(struct mtd_info *mtd, uint8_t *dat, uint8_t *read_ecc, uint8_t *calc_ecc); int (*read_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From 00da2ea97229946450c8145d680db480b5da1f94 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:19 +0200 Subject: mtd: rawnand: Pass a nand_chip object to ecc->correct() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one. Now is ecc->correct()'s turn. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/nand_bch.h | 6 +++--- include/linux/mtd/nand_ecc.h | 4 ++-- include/linux/mtd/rawnand.h | 4 ++-- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand_bch.h b/include/linux/mtd/nand_bch.h index 6db133508960..b8106651f807 100644 --- a/include/linux/mtd/nand_bch.h +++ b/include/linux/mtd/nand_bch.h @@ -28,8 +28,8 @@ int nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat, /* * Detect and correct bit errors */ -int nand_bch_correct_data(struct mtd_info *mtd, u_char *dat, u_char *read_ecc, - u_char *calc_ecc); +int nand_bch_correct_data(struct nand_chip *chip, u_char *dat, + u_char *read_ecc, u_char *calc_ecc); /* * Initialize BCH encoder/decoder */ @@ -51,7 +51,7 @@ nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat, } static inline int -nand_bch_correct_data(struct mtd_info *mtd, unsigned char *buf, +nand_bch_correct_data(struct nand_chip *chip, unsigned char *buf, unsigned char *read_ecc, unsigned char *calc_ecc) { return -ENOTSUPP; diff --git a/include/linux/mtd/nand_ecc.h b/include/linux/mtd/nand_ecc.h index a514e62ff54f..b81fecd5e719 100644 --- a/include/linux/mtd/nand_ecc.h +++ b/include/linux/mtd/nand_ecc.h @@ -13,7 +13,6 @@ #ifndef __MTD_NAND_ECC_H__ #define __MTD_NAND_ECC_H__ -struct mtd_info; struct nand_chip; /* @@ -37,6 +36,7 @@ int __nand_correct_data(u_char *dat, u_char *read_ecc, u_char *calc_ecc, /* * Detect and correct a 1 bit error for 256/512 byte block */ -int nand_correct_data(struct mtd_info *mtd, u_char *dat, u_char *read_ecc, u_char *calc_ecc); +int nand_correct_data(struct nand_chip *chip, u_char *dat, u_char *read_ecc, + u_char *calc_ecc); #endif /* __MTD_NAND_ECC_H__ */ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index b2f51b2fb110..24434310d126 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -650,8 +650,8 @@ struct nand_ecc_ctrl { void (*hwctl)(struct nand_chip *chip, int mode); int (*calculate)(struct nand_chip *chip, const uint8_t *dat, uint8_t *ecc_code); - int (*correct)(struct mtd_info *mtd, uint8_t *dat, uint8_t *read_ecc, - uint8_t *calc_ecc); + int (*correct)(struct nand_chip *chip, uint8_t *dat, uint8_t *read_ecc, + uint8_t *calc_ecc); int (*read_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, int oob_required, int page); int (*write_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From b976168757f7f4adf05215884e8557aaa9f6792c Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:20 +0200 Subject: mtd: rawnand: Pass a nand_chip object to ecc->read_xxx() hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle all ecc->read_xxx() hooks at once. Signed-off-by: Boris Brezillon Acked-by: Stefan Agner Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 24434310d126..a5f4a585f749 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -652,14 +652,14 @@ struct nand_ecc_ctrl { uint8_t *ecc_code); int (*correct)(struct nand_chip *chip, uint8_t *dat, uint8_t *read_ecc, uint8_t *calc_ecc); - int (*read_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page); + int (*read_page_raw)(struct nand_chip *chip, uint8_t *buf, + int oob_required, int page); int (*write_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, const uint8_t *buf, int oob_required, int page); - int (*read_page)(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page); - int (*read_subpage)(struct mtd_info *mtd, struct nand_chip *chip, - uint32_t offs, uint32_t len, uint8_t *buf, int page); + int (*read_page)(struct nand_chip *chip, uint8_t *buf, + int oob_required, int page); + int (*read_subpage)(struct nand_chip *chip, uint32_t offs, + uint32_t len, uint8_t *buf, int page); int (*write_subpage)(struct mtd_info *mtd, struct nand_chip *chip, uint32_t offset, uint32_t data_len, const uint8_t *data_buf, int oob_required, int page); @@ -667,9 +667,8 @@ struct nand_ecc_ctrl { const uint8_t *buf, int oob_required, int page); int (*write_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, int page); - int (*read_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, - int page); - int (*read_oob)(struct mtd_info *mtd, struct nand_chip *chip, int page); + int (*read_oob_raw)(struct nand_chip *chip, int page); + int (*read_oob)(struct nand_chip *chip, int page); int (*write_oob)(struct mtd_info *mtd, struct nand_chip *chip, int page); }; @@ -1676,11 +1675,10 @@ int nand_write_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, int page); /* Default read_oob implementation */ -int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); +int nand_read_oob_std(struct nand_chip *chip, int page); /* Default read_oob syndrome implementation */ -int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, - int page); +int nand_read_oob_syndrome(struct nand_chip *chip, int page); /* Wrapper to use in order for controllers/vendors to GET/SET FEATURES */ int nand_get_features(struct nand_chip *chip, int addr, u8 *subfeature_param); @@ -1690,10 +1688,10 @@ int nand_get_set_features_notsupp(struct mtd_info *mtd, struct nand_chip *chip, int addr, u8 *subfeature_param); /* Default read_page_raw implementation */ -int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page); -int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip, - u8 *buf, int oob_required, int page); +int nand_read_page_raw(struct nand_chip *chip, uint8_t *buf, int oob_required, + int page); +int nand_read_page_raw_notsupp(struct nand_chip *chip, u8 *buf, + int oob_required, int page); /* Default write_page_raw implementation */ int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From 767eb6fbdedb7d8b9c7a87d640a8bc8091eba002 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:21 +0200 Subject: mtd: rawnand: Pass a nand_chip object to ecc->write_xxx() hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle all ecc->write_xxx() hooks at once. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 33 +++++++++++++++------------------ 1 file changed, 15 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index a5f4a585f749..527947e81447 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -654,23 +654,21 @@ struct nand_ecc_ctrl { uint8_t *calc_ecc); int (*read_page_raw)(struct nand_chip *chip, uint8_t *buf, int oob_required, int page); - int (*write_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page); + int (*write_page_raw)(struct nand_chip *chip, const uint8_t *buf, + int oob_required, int page); int (*read_page)(struct nand_chip *chip, uint8_t *buf, int oob_required, int page); int (*read_subpage)(struct nand_chip *chip, uint32_t offs, uint32_t len, uint8_t *buf, int page); - int (*write_subpage)(struct mtd_info *mtd, struct nand_chip *chip, - uint32_t offset, uint32_t data_len, - const uint8_t *data_buf, int oob_required, int page); - int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page); - int (*write_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, - int page); + int (*write_subpage)(struct nand_chip *chip, uint32_t offset, + uint32_t data_len, const uint8_t *data_buf, + int oob_required, int page); + int (*write_page)(struct nand_chip *chip, const uint8_t *buf, + int oob_required, int page); + int (*write_oob_raw)(struct nand_chip *chip, int page); int (*read_oob_raw)(struct nand_chip *chip, int page); int (*read_oob)(struct nand_chip *chip, int page); - int (*write_oob)(struct mtd_info *mtd, struct nand_chip *chip, - int page); + int (*write_oob)(struct nand_chip *chip, int page); }; /** @@ -1668,11 +1666,10 @@ int nand_ecc_choose_conf(struct nand_chip *chip, const struct nand_ecc_caps *caps, int oobavail); /* Default write_oob implementation */ -int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); +int nand_write_oob_std(struct nand_chip *chip, int page); /* Default write_oob syndrome implementation */ -int nand_write_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, - int page); +int nand_write_oob_syndrome(struct nand_chip *chip, int page); /* Default read_oob implementation */ int nand_read_oob_std(struct nand_chip *chip, int page); @@ -1694,10 +1691,10 @@ int nand_read_page_raw_notsupp(struct nand_chip *chip, u8 *buf, int oob_required, int page); /* Default write_page_raw implementation */ -int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page); -int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip, - const u8 *buf, int oob_required, int page); +int nand_write_page_raw(struct nand_chip *chip, const uint8_t *buf, + int oob_required, int page); +int nand_write_page_raw_notsupp(struct nand_chip *chip, const u8 *buf, + int oob_required, int page); /* Reset and initialize a NAND device */ int nand_reset(struct nand_chip *chip, int chipnr); -- cgit v1.2.3 From 7e534323c416216e8ac45b5633fb0a5e5137e5b5 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:22 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->read_xxx() hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle all chip->read_xxx() hooks at once. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 527947e81447..f324a82fe6a2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1283,10 +1283,10 @@ struct nand_chip { void __iomem *IO_ADDR_R; void __iomem *IO_ADDR_W; - uint8_t (*read_byte)(struct mtd_info *mtd); + uint8_t (*read_byte)(struct nand_chip *chip); void (*write_byte)(struct mtd_info *mtd, uint8_t byte); void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); - void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); + void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); void (*select_chip)(struct mtd_info *mtd, int chip); int (*block_bad)(struct mtd_info *mtd, loff_t ofs); int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); -- cgit v1.2.3 From c0739d85723a381302907f9613392d7ac8515176 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:23 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->write_xxx() hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle all chip->write_xxx() hooks at once. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index f324a82fe6a2..cd94cb3b9c2e 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1284,8 +1284,8 @@ struct nand_chip { void __iomem *IO_ADDR_W; uint8_t (*read_byte)(struct nand_chip *chip); - void (*write_byte)(struct mtd_info *mtd, uint8_t byte); - void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); + void (*write_byte)(struct nand_chip *chip, uint8_t byte); + void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); void (*select_chip)(struct mtd_info *mtd, int chip); int (*block_bad)(struct mtd_info *mtd, loff_t ofs); -- cgit v1.2.3 From 758b56f58b66bebc5bc2e0e180e1904aafa2b523 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:24 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->select_chip() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->select_chip() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index cd94cb3b9c2e..65a25e89b426 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1287,7 +1287,7 @@ struct nand_chip { void (*write_byte)(struct nand_chip *chip, uint8_t byte); void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); - void (*select_chip)(struct mtd_info *mtd, int chip); + void (*select_chip)(struct nand_chip *chip, int cs); int (*block_bad)(struct mtd_info *mtd, loff_t ofs); int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); -- cgit v1.2.3 From c17556f545c0283f53561c8a38d5cd4e91a35fe5 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:25 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->block_xxx() hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle all chip->block_xxx() hooks at once. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 65a25e89b426..0d8e2708e125 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1288,8 +1288,8 @@ struct nand_chip { void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); void (*select_chip)(struct nand_chip *chip, int cs); - int (*block_bad)(struct mtd_info *mtd, loff_t ofs); - int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); + int (*block_bad)(struct nand_chip *chip, loff_t ofs); + int (*block_markbad)(struct nand_chip *chip, loff_t ofs); void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); int (*dev_ready)(struct mtd_info *mtd); void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column, -- cgit v1.2.3 From 0f808c1602bc75c74399989d47842197118f7e72 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:26 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->cmd_ctrl() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->cmd_ctrl() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 0d8e2708e125..b53ccc7139c2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1290,7 +1290,7 @@ struct nand_chip { void (*select_chip)(struct nand_chip *chip, int cs); int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); - void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); + void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); int (*dev_ready)(struct mtd_info *mtd); void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column, int page_addr); -- cgit v1.2.3 From 50a487e7719caa07e951dfcfd983b2c5517e2f76 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:27 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->dev_ready() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->dev_ready() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index b53ccc7139c2..404ac7d4b279 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1291,7 +1291,7 @@ struct nand_chip { int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); - int (*dev_ready)(struct mtd_info *mtd); + int (*dev_ready)(struct nand_chip *chip); void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column, int page_addr); int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); -- cgit v1.2.3 From 5295cf2e047cf60ac1e14d4789cdf698af45cf2f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:28 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->cmdfunc() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->cmdfunc() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 404ac7d4b279..2a74de9012c4 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1292,7 +1292,7 @@ struct nand_chip { int (*block_markbad)(struct nand_chip *chip, loff_t ofs); void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); int (*dev_ready)(struct nand_chip *chip); - void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column, + void (*cmdfunc)(struct nand_chip *chip, unsigned command, int column, int page_addr); int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); int (*exec_op)(struct nand_chip *chip, -- cgit v1.2.3 From f1d46942e823ffdd8532409c9b1c1f87314bf20f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:29 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->waitfunc() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->waitfunc() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 2a74de9012c4..c00e571d09ca 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1294,7 +1294,7 @@ struct nand_chip { int (*dev_ready)(struct nand_chip *chip); void (*cmdfunc)(struct nand_chip *chip, unsigned command, int column, int page_addr); - int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); + int (*waitfunc)(struct nand_chip *chip); int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); -- cgit v1.2.3 From a2098a9e4f6704471c32230d48b905e51f0cba32 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:30 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->erase() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->erase() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index c00e571d09ca..8c8315d977de 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1298,7 +1298,7 @@ struct nand_chip { int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); - int (*erase)(struct mtd_info *mtd, int page); + int (*erase)(struct nand_chip *chip, int page); int (*set_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*get_features)(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From aa36ff25ffdea656c3b748a5cf141bc884e6275c Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:31 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->{get, set}_features() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->{get,set}_features() hooks. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 8c8315d977de..7c639070c512 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1299,10 +1299,10 @@ struct nand_chip { const struct nand_operation *op, bool check_only); int (*erase)(struct nand_chip *chip, int page); - int (*set_features)(struct mtd_info *mtd, struct nand_chip *chip, - int feature_addr, uint8_t *subfeature_para); - int (*get_features)(struct mtd_info *mtd, struct nand_chip *chip, - int feature_addr, uint8_t *subfeature_para); + int (*set_features)(struct nand_chip *chip, int feature_addr, + uint8_t *subfeature_para); + int (*get_features)(struct nand_chip *chip, int feature_addr, + uint8_t *subfeature_para); int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode); int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, const struct nand_data_interface *conf); @@ -1681,8 +1681,8 @@ int nand_read_oob_syndrome(struct nand_chip *chip, int page); int nand_get_features(struct nand_chip *chip, int addr, u8 *subfeature_param); int nand_set_features(struct nand_chip *chip, int addr, u8 *subfeature_param); /* Stub used by drivers that do not support GET/SET FEATURES operations */ -int nand_get_set_features_notsupp(struct mtd_info *mtd, struct nand_chip *chip, - int addr, u8 *subfeature_param); +int nand_get_set_features_notsupp(struct nand_chip *chip, int addr, + u8 *subfeature_param); /* Default read_page_raw implementation */ int nand_read_page_raw(struct nand_chip *chip, uint8_t *buf, int oob_required, -- cgit v1.2.3 From 2e7f1cec271c209128d0535e0cc1c49d3cf03624 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:32 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->setup_read_retry() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->setup_read_retry() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 7c639070c512..14ce2b078206 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1303,7 +1303,7 @@ struct nand_chip { uint8_t *subfeature_para); int (*get_features)(struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); - int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode); + int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, const struct nand_data_interface *conf); -- cgit v1.2.3 From 858838b87ef542c35b5401a6469d162d103d1d8f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:33 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->setup_data_interface() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->setup_data_interface() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 14ce2b078206..5bfb9d543a8a 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1304,7 +1304,7 @@ struct nand_chip { int (*get_features)(struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); - int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, + int (*setup_data_interface)(struct nand_chip *chip, int chipnr, const struct nand_data_interface *conf); int chip_delay; -- cgit v1.2.3 From 5740d4c4f9bbc97270993147b4756587f92d44c3 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:34 +0200 Subject: mtd: rawnand: Pass a nand_chip object to all nand_xxx_bbt() helpers Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the nand_xxx_bbt() helpers. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 5bfb9d543a8a..e0d98ca7cb45 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1545,9 +1545,9 @@ extern const struct nand_manufacturer_ops amd_nand_manuf_ops; extern const struct nand_manufacturer_ops macronix_nand_manuf_ops; int nand_create_bbt(struct nand_chip *chip); -int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs); -int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs); -int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt); +int nand_markbad_bbt(struct nand_chip *chip, loff_t offs); +int nand_isreserved_bbt(struct nand_chip *chip, loff_t offs); +int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr, int allowbbt); -- cgit v1.2.3 From e4cdf9cb3254b5b4d9b1064c275d8c40f2d82e03 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:35 +0200 Subject: mtd: rawnand: Pass a nand_chip object nand_erase_nand() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the nand_erase_nand() helper. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index e0d98ca7cb45..e6360e1156e7 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1548,7 +1548,7 @@ int nand_create_bbt(struct nand_chip *chip); int nand_markbad_bbt(struct nand_chip *chip, loff_t offs); int nand_isreserved_bbt(struct nand_chip *chip, loff_t offs); int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); -int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr, +int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, int allowbbt); /** -- cgit v1.2.3 From 871a4073f438c61cc4cf7471476d9a8a29ccf620 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sat, 4 Aug 2018 22:59:22 +0200 Subject: mtd: rawnand: Make maxchips an unsigned int There's no good reason to make maxchips a signed integer, since only positive values are valid. Make it an unsigned int. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index e6360e1156e7..e3a96ee7e531 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -28,10 +28,10 @@ struct nand_chip; struct nand_flash_dev; /* Scan and identify a NAND device */ -int nand_scan_with_ids(struct nand_chip *chip, int max_chips, +int nand_scan_with_ids(struct nand_chip *chip, unsigned int max_chips, struct nand_flash_dev *ids); -static inline int nand_scan(struct nand_chip *chip, int max_chips) +static inline int nand_scan(struct nand_chip *chip, unsigned int max_chips) { return nand_scan_with_ids(chip, max_chips, NULL); } -- cgit v1.2.3 From 82fc5099744e5f30cd8c9ee13075f28fb37e9518 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:34 +0200 Subject: mtd: rawnand: Create a legacy struct and move ->IO_ADDR_{R, W} there We regularly have new NAND controller drivers that are making use of fields/hooks that we want to get rid of but can't because of all the legacy drivers that we might break if we do. So, instead of removing those fields/hooks, let's move them to a sub-struct which is clearly documented as deprecated. We start with the ->IO_ADDR_{R,W] fields. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index e3a96ee7e531..6b1dc8fef89d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1172,13 +1172,27 @@ int nand_op_parser_exec_op(struct nand_chip *chip, const struct nand_op_parser *parser, const struct nand_operation *op, bool check_only); +/** + * struct nand_legacy - NAND chip legacy fields/hooks + * @IO_ADDR_R: address to read the 8 I/O lines of the flash device + * @IO_ADDR_W: address to write the 8 I/O lines of the flash device + * + * If you look at this structure you're already wrong. These fields/hooks are + * all deprecated. + */ +struct nand_legacy { + void __iomem *IO_ADDR_R; + void __iomem *IO_ADDR_W; +}; + /** * struct nand_chip - NAND Private Flash Chip Data * @mtd: MTD device registered to the MTD framework - * @IO_ADDR_R: [BOARDSPECIFIC] address to read the 8 I/O lines of the - * flash device - * @IO_ADDR_W: [BOARDSPECIFIC] address to write the 8 I/O lines of the - * flash device. + * @legacy: All legacy fields/hooks. If you develop a new driver, + * don't even try to use any of these fields/hooks, and if + * you're modifying an existing driver that is using those + * fields/hooks, you should consider reworking the driver + * avoid using them. * @read_byte: [REPLACEABLE] read one byte from the chip * @write_byte: [REPLACEABLE] write a single byte to the chip on the * low 8 I/O lines @@ -1280,8 +1294,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip, struct nand_chip { struct mtd_info mtd; - void __iomem *IO_ADDR_R; - void __iomem *IO_ADDR_W; + + struct nand_legacy legacy; uint8_t (*read_byte)(struct nand_chip *chip); void (*write_byte)(struct nand_chip *chip, uint8_t byte); -- cgit v1.2.3 From 716bbbabcc68c2b0e1b805d369c0bd58f4fdea30 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:35 +0200 Subject: mtd: rawnand: Deprecate ->{read, write}_{byte, buf}() hooks All those hooks have been replaced by ->exec_op(). Move them to the nand_legacy struct. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 6b1dc8fef89d..f961efd2eacc 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1176,6 +1176,10 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * struct nand_legacy - NAND chip legacy fields/hooks * @IO_ADDR_R: address to read the 8 I/O lines of the flash device * @IO_ADDR_W: address to write the 8 I/O lines of the flash device + * @read_byte: read one byte from the chip + * @write_byte: write a single byte to the chip on the low 8 I/O lines + * @write_buf: write data from the buffer to the chip + * @read_buf: read data from the chip into the buffer * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1183,6 +1187,10 @@ int nand_op_parser_exec_op(struct nand_chip *chip, struct nand_legacy { void __iomem *IO_ADDR_R; void __iomem *IO_ADDR_W; + u8 (*read_byte)(struct nand_chip *chip); + void (*write_byte)(struct nand_chip *chip, u8 byte); + void (*write_buf)(struct nand_chip *chip, const u8 *buf, int len); + void (*read_buf)(struct nand_chip *chip, u8 *buf, int len); }; /** @@ -1193,11 +1201,6 @@ struct nand_legacy { * you're modifying an existing driver that is using those * fields/hooks, you should consider reworking the driver * avoid using them. - * @read_byte: [REPLACEABLE] read one byte from the chip - * @write_byte: [REPLACEABLE] write a single byte to the chip on the - * low 8 I/O lines - * @write_buf: [REPLACEABLE] write data from the buffer to the chip - * @read_buf: [REPLACEABLE] read data from the chip into the buffer * @select_chip: [REPLACEABLE] select chip nr * @block_bad: [REPLACEABLE] check if a block is bad, using OOB markers * @block_markbad: [REPLACEABLE] mark a block bad @@ -1213,8 +1216,8 @@ struct nand_legacy { * ready. * @exec_op: controller specific method to execute NAND operations. * This method replaces ->cmdfunc(), - * ->{read,write}_{buf,byte,word}(), ->dev_ready() and - * ->waifunc(). + * ->legacy.{read,write}_{buf,byte,word}(), ->dev_ready() + * and ->waifunc(). * @setup_read_retry: [FLASHSPECIFIC] flash (vendor) specific function for * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure @@ -1297,10 +1300,6 @@ struct nand_chip { struct nand_legacy legacy; - uint8_t (*read_byte)(struct nand_chip *chip); - void (*write_byte)(struct nand_chip *chip, uint8_t byte); - void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); - void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); void (*select_chip)(struct nand_chip *chip, int cs); int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); -- cgit v1.2.3 From bf6065c6c08fa3ed7bdf8d28b8062ce8e58c1543 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:36 +0200 Subject: mtd: rawnand: Deprecate ->cmd_ctrl() and ->cmdfunc() Those hooks have been replaced by ->exec_op(). Move them to the nand_legacy struct. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index f961efd2eacc..5ef2004a37a2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -199,10 +199,10 @@ enum nand_ecc_algo { #define NAND_USE_BOUNCE_BUFFER 0x00100000 /* - * In case your controller is implementing ->cmd_ctrl() and is relying on the - * default ->cmdfunc() implementation, you may want to let the core handle the - * tCCS delay which is required when a column change (RNDIN or RNDOUT) is - * requested. + * In case your controller is implementing ->legacy.cmd_ctrl() and is relying + * on the default ->cmdfunc() implementation, you may want to let the core + * handle the tCCS delay which is required when a column change (RNDIN or + * RNDOUT) is requested. * If your controller already takes care of this delay, you don't need to set * this flag. */ @@ -1180,6 +1180,9 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @write_byte: write a single byte to the chip on the low 8 I/O lines * @write_buf: write data from the buffer to the chip * @read_buf: read data from the chip into the buffer + * @cmd_ctrl: hardware specific function for controlling ALE/CLE/nCE. Also used + * to write command and address + * @cmdfunc: hardware specific function for writing commands to the chip. * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1191,6 +1194,9 @@ struct nand_legacy { void (*write_byte)(struct nand_chip *chip, u8 byte); void (*write_buf)(struct nand_chip *chip, const u8 *buf, int len); void (*read_buf)(struct nand_chip *chip, u8 *buf, int len); + void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); + void (*cmdfunc)(struct nand_chip *chip, unsigned command, int column, + int page_addr); }; /** @@ -1204,14 +1210,10 @@ struct nand_legacy { * @select_chip: [REPLACEABLE] select chip nr * @block_bad: [REPLACEABLE] check if a block is bad, using OOB markers * @block_markbad: [REPLACEABLE] mark a block bad - * @cmd_ctrl: [BOARDSPECIFIC] hardwarespecific function for controlling - * ALE/CLE/nCE. Also used to write command and address * @dev_ready: [BOARDSPECIFIC] hardwarespecific function for accessing * device ready/busy line. If set to NULL no access to * ready/busy is available and the ready/busy information * is read from the chip status register. - * @cmdfunc: [REPLACEABLE] hardwarespecific function for writing - * commands to the chip. * @waitfunc: [REPLACEABLE] hardwarespecific function for wait on * ready. * @exec_op: controller specific method to execute NAND operations. @@ -1303,10 +1305,7 @@ struct nand_chip { void (*select_chip)(struct nand_chip *chip, int cs); int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); - void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); int (*dev_ready)(struct nand_chip *chip); - void (*cmdfunc)(struct nand_chip *chip, unsigned command, int column, - int page_addr); int (*waitfunc)(struct nand_chip *chip); int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, -- cgit v1.2.3 From 8395b753d7cad2beb03d374621cc8851f1cb4e01 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:37 +0200 Subject: mtd: rawnand: Deprecate ->dev_ready() and ->waitfunc() Those hooks have been replaced by ->exec_op(). Move them to the nand_legacy struct. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 5ef2004a37a2..15642c028da2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1183,6 +1183,10 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @cmd_ctrl: hardware specific function for controlling ALE/CLE/nCE. Also used * to write command and address * @cmdfunc: hardware specific function for writing commands to the chip. + * @dev_ready: hardware specific function for accessing device ready/busy line. + * If set to NULL no access to ready/busy is available and the + * ready/busy information is read from the chip status register. + * @waitfunc: hardware specific function for wait on ready. * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1197,6 +1201,8 @@ struct nand_legacy { void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); void (*cmdfunc)(struct nand_chip *chip, unsigned command, int column, int page_addr); + int (*dev_ready)(struct nand_chip *chip); + int (*waitfunc)(struct nand_chip *chip); }; /** @@ -1210,16 +1216,10 @@ struct nand_legacy { * @select_chip: [REPLACEABLE] select chip nr * @block_bad: [REPLACEABLE] check if a block is bad, using OOB markers * @block_markbad: [REPLACEABLE] mark a block bad - * @dev_ready: [BOARDSPECIFIC] hardwarespecific function for accessing - * device ready/busy line. If set to NULL no access to - * ready/busy is available and the ready/busy information - * is read from the chip status register. - * @waitfunc: [REPLACEABLE] hardwarespecific function for wait on - * ready. * @exec_op: controller specific method to execute NAND operations. * This method replaces ->cmdfunc(), - * ->legacy.{read,write}_{buf,byte,word}(), ->dev_ready() - * and ->waifunc(). + * ->legacy.{read,write}_{buf,byte,word}(), + * ->legacy.dev_ready() and ->waifunc(). * @setup_read_retry: [FLASHSPECIFIC] flash (vendor) specific function for * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure @@ -1305,8 +1305,6 @@ struct nand_chip { void (*select_chip)(struct nand_chip *chip, int cs); int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); - int (*dev_ready)(struct nand_chip *chip); - int (*waitfunc)(struct nand_chip *chip); int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); -- cgit v1.2.3 From cdc784c743945f445a26f4c0bd60a50a1adb39c4 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:38 +0200 Subject: mtd: rawnand: Deprecate ->block_{bad,markbad}() hooks Those hooks have been overloaded by some drivers for bad reasons: either the driver was not fitting in the NAND framework and should have been an MTD driver (docg4), or it was not properly implementing the OOB read/write request or had a weird layout where BBM are trashed. In any case, we should discourage people from overloading those methods and encourage them to fix their driver instead. Move the ->block_{bad,markbad}() hooks to the nand_legacy struct to make it clear. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 15642c028da2..aa3e931d0206 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1187,6 +1187,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * If set to NULL no access to ready/busy is available and the * ready/busy information is read from the chip status register. * @waitfunc: hardware specific function for wait on ready. + * @block_bad: check if a block is bad, using OOB markers + * @block_markbad: mark a block bad * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1203,6 +1205,8 @@ struct nand_legacy { int page_addr); int (*dev_ready)(struct nand_chip *chip); int (*waitfunc)(struct nand_chip *chip); + int (*block_bad)(struct nand_chip *chip, loff_t ofs); + int (*block_markbad)(struct nand_chip *chip, loff_t ofs); }; /** @@ -1214,8 +1218,6 @@ struct nand_legacy { * fields/hooks, you should consider reworking the driver * avoid using them. * @select_chip: [REPLACEABLE] select chip nr - * @block_bad: [REPLACEABLE] check if a block is bad, using OOB markers - * @block_markbad: [REPLACEABLE] mark a block bad * @exec_op: controller specific method to execute NAND operations. * This method replaces ->cmdfunc(), * ->legacy.{read,write}_{buf,byte,word}(), @@ -1303,8 +1305,6 @@ struct nand_chip { struct nand_legacy legacy; void (*select_chip)(struct nand_chip *chip, int cs); - int (*block_bad)(struct nand_chip *chip, loff_t ofs); - int (*block_markbad)(struct nand_chip *chip, loff_t ofs); int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); @@ -1556,6 +1556,7 @@ extern const struct nand_manufacturer_ops macronix_nand_manuf_ops; int nand_create_bbt(struct nand_chip *chip); int nand_markbad_bbt(struct nand_chip *chip, loff_t offs); +int nand_markbad_bbm(struct nand_chip *chip, loff_t ofs); int nand_isreserved_bbt(struct nand_chip *chip, loff_t offs); int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, -- cgit v1.2.3 From f9ebd1bb41031afc162e9acda7ad044a35bccf82 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:39 +0200 Subject: mtd: rawnand: Deprecate ->erase() The ->erase() hook have been overloaded by some drivers for bad reasons: either the driver was not fitting in the NAND framework and should have been an MTD driver (docg4), or the driver uses a specific path for the ERASE operation (denali), instead of implementing it generically. In any case, we should discourage people from overloading this method and encourage them to implement ->exec_op() instead. Move the ->erase() hook to the nand_legacy struct to make it clear. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index aa3e931d0206..97c6ff7d127e 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1189,6 +1189,7 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @waitfunc: hardware specific function for wait on ready. * @block_bad: check if a block is bad, using OOB markers * @block_markbad: mark a block bad + * @erase: erase function * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1207,6 +1208,7 @@ struct nand_legacy { int (*waitfunc)(struct nand_chip *chip); int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); + int (*erase)(struct nand_chip *chip, int page); }; /** @@ -1228,7 +1230,6 @@ struct nand_legacy { * @buf_align: minimum buffer alignment required by a platform * @dummy_controller: dummy controller implementation for drivers that can * only control a single chip - * @erase: [REPLACEABLE] erase function * @chip_delay: [BOARDSPECIFIC] chip dependent delay for transferring * data from array to read regs (tR). * @state: [INTERN] the current state of the NAND device @@ -1308,7 +1309,6 @@ struct nand_chip { int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); - int (*erase)(struct nand_chip *chip, int page); int (*set_features)(struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*get_features)(struct nand_chip *chip, int feature_addr, -- cgit v1.2.3 From 45240367939b071b9957b970379cf64f9a2934ce Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:40 +0200 Subject: mtd: rawnand: Deprecate ->{set,get}_features() hooks Those hooks should be replaced by a proper ->exec_op() implementation. Move them to the nand_legacy struct to make it clear. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 97c6ff7d127e..02ac70a30c63 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1190,6 +1190,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @block_bad: check if a block is bad, using OOB markers * @block_markbad: mark a block bad * @erase: erase function + * @set_features: set the NAND chip features + * @get_features: get the NAND chip features * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1209,6 +1211,10 @@ struct nand_legacy { int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); int (*erase)(struct nand_chip *chip, int page); + int (*set_features)(struct nand_chip *chip, int feature_addr, + u8 *subfeature_para); + int (*get_features)(struct nand_chip *chip, int feature_addr, + u8 *subfeature_para); }; /** @@ -1279,8 +1285,6 @@ struct nand_legacy { * @blocks_per_die: [INTERN] The number of PEBs in a die * @data_interface: [INTERN] NAND interface timing information * @read_retries: [INTERN] the number of read retry modes supported - * @set_features: [REPLACEABLE] set the NAND chip features - * @get_features: [REPLACEABLE] get the NAND chip features * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this * means the configuration should not be applied but @@ -1309,10 +1313,6 @@ struct nand_chip { int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); - int (*set_features)(struct nand_chip *chip, int feature_addr, - uint8_t *subfeature_para); - int (*get_features)(struct nand_chip *chip, int feature_addr, - uint8_t *subfeature_para); int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); int (*setup_data_interface)(struct nand_chip *chip, int chipnr, const struct nand_data_interface *conf); -- cgit v1.2.3 From 3cece3abebda068e55e19302a6f0fa60cf553737 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:41 +0200 Subject: mtd: rawnand: Deprecate ->chip_delay The wait timeouts and delays are directly extracted from the NAND timings and ->chip_delay is only used in legacy path, so let's move it to the nand_legacy struct to make it clear. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 02ac70a30c63..992d78d29674 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1192,6 +1192,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @erase: erase function * @set_features: set the NAND chip features * @get_features: get the NAND chip features + * @chip_delay: chip dependent delay for transferring data from array to read + * regs (tR). * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1215,6 +1217,7 @@ struct nand_legacy { u8 *subfeature_para); int (*get_features)(struct nand_chip *chip, int feature_addr, u8 *subfeature_para); + int chip_delay; }; /** @@ -1236,8 +1239,6 @@ struct nand_legacy { * @buf_align: minimum buffer alignment required by a platform * @dummy_controller: dummy controller implementation for drivers that can * only control a single chip - * @chip_delay: [BOARDSPECIFIC] chip dependent delay for transferring - * data from array to read regs (tR). * @state: [INTERN] the current state of the NAND device * @oob_poi: "poison value buffer," used for laying out OOB data * before writing @@ -1317,7 +1318,6 @@ struct nand_chip { int (*setup_data_interface)(struct nand_chip *chip, int chipnr, const struct nand_data_interface *conf); - int chip_delay; unsigned int options; unsigned int bbt_options; -- cgit v1.2.3 From 0b4e61c1c26e0f34c9a5f6c35edee16cc26a72fd Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:42 +0200 Subject: mtd: rawnand: Move function prototypes after struct declarations Move nand_scan[_with_ids]() and nand_wait_ready() at the end of the file where all function prototype lies. This will also allow us to get rid of the nand_flash_dev forward declaration. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 992d78d29674..15183b73fed2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -27,18 +27,6 @@ struct nand_chip; struct nand_flash_dev; -/* Scan and identify a NAND device */ -int nand_scan_with_ids(struct nand_chip *chip, unsigned int max_chips, - struct nand_flash_dev *ids); - -static inline int nand_scan(struct nand_chip *chip, unsigned int max_chips) -{ - return nand_scan_with_ids(chip, max_chips, NULL); -} - -/* Internal helper for board drivers which need to override command function */ -void nand_wait_ready(struct nand_chip *chip); - /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 @@ -1739,6 +1727,18 @@ int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len, int nand_write_data_op(struct nand_chip *chip, const void *buf, unsigned int len, bool force_8bit); +/* Scan and identify a NAND device */ +int nand_scan_with_ids(struct nand_chip *chip, unsigned int max_chips, + struct nand_flash_dev *ids); + +static inline int nand_scan(struct nand_chip *chip, unsigned int max_chips) +{ + return nand_scan_with_ids(chip, max_chips, NULL); +} + +/* Internal helper for board drivers which need to override command function */ +void nand_wait_ready(struct nand_chip *chip); + /* * Free resources held by the NAND device, must be called on error after a * sucessful nand_scan(). -- cgit v1.2.3 From 394938eadff2b875c099529452ffb7f7303f1547 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:43 +0200 Subject: mtd: rawnand: Get rid of nand_flash_dev forward declation nand_scan[with_ids]() have been moved at the end of the file. We can now get rid of of the nand_flash_dev forward declaration. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 15183b73fed2..768415ed1159 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -25,7 +25,6 @@ #include struct nand_chip; -struct nand_flash_dev; /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 -- cgit v1.2.3 From d16397d57a90d8c35bef3d8104460bf18e111fa7 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:44 +0200 Subject: mtd: rawnand: Get rid of the duplicate nand_chip forward declaration There's already a forward declaration of nand_chip at the beginning of the file. Get rid of this one. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 768415ed1159..608279104aae 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -210,9 +210,6 @@ enum nand_ecc_algo { #define NAND_CI_CELLTYPE_MSK 0x0C #define NAND_CI_CELLTYPE_SHIFT 2 -/* Keep gcc happy */ -struct nand_chip; - /* ONFI version bits */ #define ONFI_VERSION_1_0 BIT(1) #define ONFI_VERSION_2_0 BIT(2) -- cgit v1.2.3 From 4114f97c41cd3992724f450f595417e4432737a0 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:45 +0200 Subject: mtd: rawnand: Get rid of a few unused definitions Those definitions are not used, let's remove them. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 608279104aae..8aa8b57ca4b1 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -119,10 +119,6 @@ enum nand_ecc_algo { #define NAND_ECC_GENERIC_ERASED_CHECK BIT(0) #define NAND_ECC_MAXIMIZE BIT(1) -/* Bit mask for flags passed to do_nand_read_ecc */ -#define NAND_GET_DEVICE 0x80 - - /* * Option constants for bizarre disfunctionality and real * features. @@ -163,9 +159,7 @@ enum nand_ecc_algo { #define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG /* Macros to identify the above */ -#define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) #define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) -#define NAND_HAS_SUBPAGE_WRITE(chip) !((chip)->options & NAND_NO_SUBPAGE_WRITE) /* Non chip related options */ /* This option skips the bbt scan during initialization. */ @@ -1649,8 +1643,6 @@ static inline int nand_opcode_8bits(unsigned int command) return 0; } -/* get timing characteristics from ONFI timing mode. */ -const struct nand_sdr_timings *onfi_async_timing_mode_to_sdr_timings(int mode); int nand_check_erased_ecc_chunk(void *data, int datalen, void *ecc, int ecclen, -- cgit v1.2.3 From c7921bb32ab616462cefb9c2f3dd81d85d32b948 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:46 +0200 Subject: mtd: rawnand: Move platform_nand_xxx definitions out of rawnand.h platform_nand_xxx definitions are just used by the plat_nand driver. Let's move those definitions out of the core/driver-agnostic rawnand.h header. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/platnand.h | 74 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/rawnand.h | 60 ----------------------------------- 2 files changed, 74 insertions(+), 60 deletions(-) create mode 100644 include/linux/mtd/platnand.h (limited to 'include/linux') diff --git a/include/linux/mtd/platnand.h b/include/linux/mtd/platnand.h new file mode 100644 index 000000000000..bc11eb6b593b --- /dev/null +++ b/include/linux/mtd/platnand.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright © 2000-2010 David Woodhouse + * Steven J. Hill + * Thomas Gleixner + * + * Contains all platform NAND related definitions. + */ + +#ifndef __LINUX_MTD_PLATNAND_H +#define __LINUX_MTD_PLATNAND_H + +#include +#include +#include + +/** + * struct platform_nand_chip - chip level device structure + * @nr_chips: max. number of chips to scan for + * @chip_offset: chip number offset + * @nr_partitions: number of partitions pointed to by partitions (or zero) + * @partitions: mtd partition list + * @chip_delay: R/B delay value in us + * @options: Option flags, e.g. 16bit buswidth + * @bbt_options: BBT option flags, e.g. NAND_BBT_USE_FLASH + * @part_probe_types: NULL-terminated array of probe types + */ +struct platform_nand_chip { + int nr_chips; + int chip_offset; + int nr_partitions; + struct mtd_partition *partitions; + int chip_delay; + unsigned int options; + unsigned int bbt_options; + const char **part_probe_types; +}; + +/** + * struct platform_nand_ctrl - controller level device structure + * @probe: platform specific function to probe/setup hardware + * @remove: platform specific function to remove/teardown hardware + * @dev_ready: platform specific function to read ready/busy pin + * @select_chip: platform specific chip select function + * @cmd_ctrl: platform specific function for controlling + * ALE/CLE/nCE. Also used to write command and address + * @write_buf: platform specific function for write buffer + * @read_buf: platform specific function for read buffer + * @priv: private data to transport driver specific settings + * + * All fields are optional and depend on the hardware driver requirements + */ +struct platform_nand_ctrl { + int (*probe)(struct platform_device *pdev); + void (*remove)(struct platform_device *pdev); + int (*dev_ready)(struct nand_chip *chip); + void (*select_chip)(struct nand_chip *chip, int cs); + void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); + void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); + void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); + void *priv; +}; + +/** + * struct platform_nand_data - container structure for platform-specific data + * @chip: chip level chip structure + * @ctrl: controller level device structure + */ +struct platform_nand_data { + struct platform_nand_chip chip; + struct platform_nand_ctrl ctrl; +}; + +#endif /* __LINUX_MTD_PLATNAND_H */ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 8aa8b57ca4b1..04e11a314e9c 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1540,66 +1540,6 @@ int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, int allowbbt); -/** - * struct platform_nand_chip - chip level device structure - * @nr_chips: max. number of chips to scan for - * @chip_offset: chip number offset - * @nr_partitions: number of partitions pointed to by partitions (or zero) - * @partitions: mtd partition list - * @chip_delay: R/B delay value in us - * @options: Option flags, e.g. 16bit buswidth - * @bbt_options: BBT option flags, e.g. NAND_BBT_USE_FLASH - * @part_probe_types: NULL-terminated array of probe types - */ -struct platform_nand_chip { - int nr_chips; - int chip_offset; - int nr_partitions; - struct mtd_partition *partitions; - int chip_delay; - unsigned int options; - unsigned int bbt_options; - const char **part_probe_types; -}; - -/* Keep gcc happy */ -struct platform_device; - -/** - * struct platform_nand_ctrl - controller level device structure - * @probe: platform specific function to probe/setup hardware - * @remove: platform specific function to remove/teardown hardware - * @dev_ready: platform specific function to read ready/busy pin - * @select_chip: platform specific chip select function - * @cmd_ctrl: platform specific function for controlling - * ALE/CLE/nCE. Also used to write command and address - * @write_buf: platform specific function for write buffer - * @read_buf: platform specific function for read buffer - * @priv: private data to transport driver specific settings - * - * All fields are optional and depend on the hardware driver requirements - */ -struct platform_nand_ctrl { - int (*probe)(struct platform_device *pdev); - void (*remove)(struct platform_device *pdev); - int (*dev_ready)(struct nand_chip *chip); - void (*select_chip)(struct nand_chip *chip, int cs); - void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); - void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); - void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); - void *priv; -}; - -/** - * struct platform_nand_data - container structure for platform-specific data - * @chip: chip level chip structure - * @ctrl: controller level device structure - */ -struct platform_nand_data { - struct platform_nand_chip chip; - struct platform_nand_ctrl ctrl; -}; - /* return the supported asynchronous timing mode. */ static inline int onfi_get_async_timing_mode(struct nand_chip *chip) { -- cgit v1.2.3 From 462f35d3e5e805657b48c76d3e7dd1c37e0ac62c Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:47 +0200 Subject: mtd: rawnand: Inline onfi_get_async_timing_mode() onfi_get_async_timing_mode() is only used in one place inside nand_base.c. Let's inline the code and kill the helper. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 04e11a314e9c..7f0e3dc222ed 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1540,15 +1540,6 @@ int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, int allowbbt); -/* return the supported asynchronous timing mode. */ -static inline int onfi_get_async_timing_mode(struct nand_chip *chip) -{ - if (!chip->parameters.onfi) - return ONFI_TIMING_MODE_UNKNOWN; - - return chip->parameters.onfi->async_timing_mode; -} - int onfi_fill_data_interface(struct nand_chip *chip, enum nand_data_interface_type type, int timing_mode); -- cgit v1.2.3 From 348d56a8c6067f3b2f1799d6f050f3be4bf5904b Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:48 +0200 Subject: mtd: rawnand: Keep all internal stuff private A lot of things defined in rawnand.h should not be exposed to NAND controller drivers and should only be shared by core files. Create the drivers/mtd/nand/raw/internals.h header to store such definitions, and move all private defs to this header. Also remove EXPORT_SYMBOLS() on functions that are not supposed to be exposed. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 96 --------------------------------------------- 1 file changed, 96 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 7f0e3dc222ed..fbe7686cfc59 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -775,24 +775,6 @@ nand_get_sdr_timings(const struct nand_data_interface *conf) return &conf->timings.sdr; } -/** - * struct nand_manufacturer_ops - NAND Manufacturer operations - * @detect: detect the NAND memory organization and capabilities - * @init: initialize all vendor specific fields (like the ->read_retry() - * implementation) if any. - * @cleanup: the ->init() function may have allocated resources, ->cleanup() - * is here to let vendor specific code release those resources. - * @fixup_onfi_param_page: apply vendor specific fixups to the ONFI parameter - * page. This is called after the checksum is verified. - */ -struct nand_manufacturer_ops { - void (*detect)(struct nand_chip *chip); - int (*init)(struct nand_chip *chip); - void (*cleanup)(struct nand_chip *chip); - void (*fixup_onfi_param_page)(struct nand_chip *chip, - struct nand_onfi_params *p); -}; - /** * struct nand_op_cmd_instr - Definition of a command instruction * @opcode: the command to issue in one cycle @@ -1403,27 +1385,6 @@ static inline void *nand_get_manufacturer_data(struct nand_chip *chip) return chip->manufacturer.priv; } -/* - * NAND Flash Manufacturer ID Codes - */ -#define NAND_MFR_TOSHIBA 0x98 -#define NAND_MFR_ESMT 0xc8 -#define NAND_MFR_SAMSUNG 0xec -#define NAND_MFR_FUJITSU 0x04 -#define NAND_MFR_NATIONAL 0x8f -#define NAND_MFR_RENESAS 0x07 -#define NAND_MFR_STMICRO 0x20 -#define NAND_MFR_HYNIX 0xad -#define NAND_MFR_MICRON 0x2c -#define NAND_MFR_AMD 0x01 -#define NAND_MFR_MACRONIX 0xc2 -#define NAND_MFR_EON 0x92 -#define NAND_MFR_SANDISK 0x45 -#define NAND_MFR_INTEL 0x89 -#define NAND_MFR_ATO 0x9b -#define NAND_MFR_WINBOND 0xef - - /* * A helper for defining older NAND chips where the second ID byte fully * defined the chip, including the geometry (chip size, eraseblock size, page @@ -1503,46 +1464,7 @@ struct nand_flash_dev { int onfi_timing_mode_default; }; -/** - * struct nand_manufacturer - NAND Flash Manufacturer structure - * @name: Manufacturer name - * @id: manufacturer ID code of device. - * @ops: manufacturer operations -*/ -struct nand_manufacturer { - int id; - char *name; - const struct nand_manufacturer_ops *ops; -}; - -const struct nand_manufacturer *nand_get_manufacturer(u8 id); - -static inline const char * -nand_manufacturer_name(const struct nand_manufacturer *manufacturer) -{ - return manufacturer ? manufacturer->name : "Unknown"; -} - -extern struct nand_flash_dev nand_flash_ids[]; - -extern const struct nand_manufacturer_ops toshiba_nand_manuf_ops; -extern const struct nand_manufacturer_ops samsung_nand_manuf_ops; -extern const struct nand_manufacturer_ops hynix_nand_manuf_ops; -extern const struct nand_manufacturer_ops micron_nand_manuf_ops; -extern const struct nand_manufacturer_ops amd_nand_manuf_ops; -extern const struct nand_manufacturer_ops macronix_nand_manuf_ops; - int nand_create_bbt(struct nand_chip *chip); -int nand_markbad_bbt(struct nand_chip *chip, loff_t offs); -int nand_markbad_bbm(struct nand_chip *chip, loff_t ofs); -int nand_isreserved_bbt(struct nand_chip *chip, loff_t offs); -int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); -int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, - int allowbbt); - -int onfi_fill_data_interface(struct nand_chip *chip, - enum nand_data_interface_type type, - int timing_mode); /* * Check if it is a SLC nand. @@ -1574,7 +1496,6 @@ static inline int nand_opcode_8bits(unsigned int command) return 0; } - int nand_check_erased_ecc_chunk(void *data, int datalen, void *ecc, int ecclen, void *extraoob, int extraooblen, @@ -1586,18 +1507,9 @@ int nand_ecc_choose_conf(struct nand_chip *chip, /* Default write_oob implementation */ int nand_write_oob_std(struct nand_chip *chip, int page); -/* Default write_oob syndrome implementation */ -int nand_write_oob_syndrome(struct nand_chip *chip, int page); - /* Default read_oob implementation */ int nand_read_oob_std(struct nand_chip *chip, int page); -/* Default read_oob syndrome implementation */ -int nand_read_oob_syndrome(struct nand_chip *chip, int page); - -/* Wrapper to use in order for controllers/vendors to GET/SET FEATURES */ -int nand_get_features(struct nand_chip *chip, int addr, u8 *subfeature_param); -int nand_set_features(struct nand_chip *chip, int addr, u8 *subfeature_param); /* Stub used by drivers that do not support GET/SET FEATURES operations */ int nand_get_set_features_notsupp(struct nand_chip *chip, int addr, u8 *subfeature_param); @@ -1605,14 +1517,10 @@ int nand_get_set_features_notsupp(struct nand_chip *chip, int addr, /* Default read_page_raw implementation */ int nand_read_page_raw(struct nand_chip *chip, uint8_t *buf, int oob_required, int page); -int nand_read_page_raw_notsupp(struct nand_chip *chip, u8 *buf, - int oob_required, int page); /* Default write_page_raw implementation */ int nand_write_page_raw(struct nand_chip *chip, const uint8_t *buf, int oob_required, int page); -int nand_write_page_raw_notsupp(struct nand_chip *chip, const u8 *buf, - int oob_required, int page); /* Reset and initialize a NAND device */ int nand_reset(struct nand_chip *chip, int chipnr); @@ -1622,7 +1530,6 @@ int nand_reset_op(struct nand_chip *chip); int nand_readid_op(struct nand_chip *chip, u8 addr, void *buf, unsigned int len); int nand_status_op(struct nand_chip *chip, u8 *status); -int nand_exit_status_op(struct nand_chip *chip); int nand_erase_op(struct nand_chip *chip, unsigned int eraseblock); int nand_read_page_op(struct nand_chip *chip, unsigned int page, unsigned int offset_in_page, void *buf, unsigned int len); @@ -1666,9 +1573,6 @@ void nand_cleanup(struct nand_chip *chip); /* Unregister the MTD device and calls nand_cleanup() */ void nand_release(struct nand_chip *chip); -/* Default extended ID decoding function */ -void nand_decode_ext_id(struct nand_chip *chip); - /* * External helper for controller drivers that have to implement the WAITRDY * instruction and have no physical pin to check it. -- cgit v1.2.3 From 1c325cc5077a88510afc08b1d2c75bcf18681f21 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:50 +0200 Subject: mtd: rawnand: Move ONFI code to nand_onfi.c This moves ONFI related code to nand_onfi.c and ONFI related struct/macros to include/linux/mtd/onfi.h. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/onfi.h | 178 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/rawnand.h | 164 +--------------------------------------- 2 files changed, 179 insertions(+), 163 deletions(-) create mode 100644 include/linux/mtd/onfi.h (limited to 'include/linux') diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h new file mode 100644 index 000000000000..339ac798568e --- /dev/null +++ b/include/linux/mtd/onfi.h @@ -0,0 +1,178 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright © 2000-2010 David Woodhouse + * Steven J. Hill + * Thomas Gleixner + * + * Contains all ONFI related definitions + */ + +#ifndef __LINUX_MTD_ONFI_H +#define __LINUX_MTD_ONFI_H + +#include + +/* ONFI version bits */ +#define ONFI_VERSION_1_0 BIT(1) +#define ONFI_VERSION_2_0 BIT(2) +#define ONFI_VERSION_2_1 BIT(3) +#define ONFI_VERSION_2_2 BIT(4) +#define ONFI_VERSION_2_3 BIT(5) +#define ONFI_VERSION_3_0 BIT(6) +#define ONFI_VERSION_3_1 BIT(7) +#define ONFI_VERSION_3_2 BIT(8) +#define ONFI_VERSION_4_0 BIT(9) + +/* ONFI features */ +#define ONFI_FEATURE_16_BIT_BUS (1 << 0) +#define ONFI_FEATURE_EXT_PARAM_PAGE (1 << 7) + +/* ONFI timing mode, used in both asynchronous and synchronous mode */ +#define ONFI_TIMING_MODE_0 (1 << 0) +#define ONFI_TIMING_MODE_1 (1 << 1) +#define ONFI_TIMING_MODE_2 (1 << 2) +#define ONFI_TIMING_MODE_3 (1 << 3) +#define ONFI_TIMING_MODE_4 (1 << 4) +#define ONFI_TIMING_MODE_5 (1 << 5) +#define ONFI_TIMING_MODE_UNKNOWN (1 << 6) + +/* ONFI feature number/address */ +#define ONFI_FEATURE_NUMBER 256 +#define ONFI_FEATURE_ADDR_TIMING_MODE 0x1 + +/* Vendor-specific feature address (Micron) */ +#define ONFI_FEATURE_ADDR_READ_RETRY 0x89 +#define ONFI_FEATURE_ON_DIE_ECC 0x90 +#define ONFI_FEATURE_ON_DIE_ECC_EN BIT(3) + +/* ONFI subfeature parameters length */ +#define ONFI_SUBFEATURE_PARAM_LEN 4 + +/* ONFI optional commands SET/GET FEATURES supported? */ +#define ONFI_OPT_CMD_SET_GET_FEATURES (1 << 2) + +struct nand_onfi_params { + /* rev info and features block */ + /* 'O' 'N' 'F' 'I' */ + u8 sig[4]; + __le16 revision; + __le16 features; + __le16 opt_cmd; + u8 reserved0[2]; + __le16 ext_param_page_length; /* since ONFI 2.1 */ + u8 num_of_param_pages; /* since ONFI 2.1 */ + u8 reserved1[17]; + + /* manufacturer information block */ + char manufacturer[12]; + char model[20]; + u8 jedec_id; + __le16 date_code; + u8 reserved2[13]; + + /* memory organization block */ + __le32 byte_per_page; + __le16 spare_bytes_per_page; + __le32 data_bytes_per_ppage; + __le16 spare_bytes_per_ppage; + __le32 pages_per_block; + __le32 blocks_per_lun; + u8 lun_count; + u8 addr_cycles; + u8 bits_per_cell; + __le16 bb_per_lun; + __le16 block_endurance; + u8 guaranteed_good_blocks; + __le16 guaranteed_block_endurance; + u8 programs_per_page; + u8 ppage_attr; + u8 ecc_bits; + u8 interleaved_bits; + u8 interleaved_ops; + u8 reserved3[13]; + + /* electrical parameter block */ + u8 io_pin_capacitance_max; + __le16 async_timing_mode; + __le16 program_cache_timing_mode; + __le16 t_prog; + __le16 t_bers; + __le16 t_r; + __le16 t_ccs; + __le16 src_sync_timing_mode; + u8 src_ssync_features; + __le16 clk_pin_capacitance_typ; + __le16 io_pin_capacitance_typ; + __le16 input_pin_capacitance_typ; + u8 input_pin_capacitance_max; + u8 driver_strength_support; + __le16 t_int_r; + __le16 t_adl; + u8 reserved4[8]; + + /* vendor */ + __le16 vendor_revision; + u8 vendor[88]; + + __le16 crc; +} __packed; + +#define ONFI_CRC_BASE 0x4F4E + +/* Extended ECC information Block Definition (since ONFI 2.1) */ +struct onfi_ext_ecc_info { + u8 ecc_bits; + u8 codeword_size; + __le16 bb_per_lun; + __le16 block_endurance; + u8 reserved[2]; +} __packed; + +#define ONFI_SECTION_TYPE_0 0 /* Unused section. */ +#define ONFI_SECTION_TYPE_1 1 /* for additional sections. */ +#define ONFI_SECTION_TYPE_2 2 /* for ECC information. */ +struct onfi_ext_section { + u8 type; + u8 length; +} __packed; + +#define ONFI_EXT_SECTION_MAX 8 + +/* Extended Parameter Page Definition (since ONFI 2.1) */ +struct onfi_ext_param_page { + __le16 crc; + u8 sig[4]; /* 'E' 'P' 'P' 'S' */ + u8 reserved0[10]; + struct onfi_ext_section sections[ONFI_EXT_SECTION_MAX]; + + /* + * The actual size of the Extended Parameter Page is in + * @ext_param_page_length of nand_onfi_params{}. + * The following are the variable length sections. + * So we do not add any fields below. Please see the ONFI spec. + */ +} __packed; + +/** + * struct onfi_params - ONFI specific parameters that will be reused + * @version: ONFI version (BCD encoded), 0 if ONFI is not supported + * @tPROG: Page program time + * @tBERS: Block erase time + * @tR: Page read time + * @tCCS: Change column setup time + * @async_timing_mode: Supported asynchronous timing mode + * @vendor_revision: Vendor specific revision number + * @vendor: Vendor specific data + */ +struct onfi_params { + int version; + u16 tPROG; + u16 tBERS; + u16 tR; + u16 tCCS; + u16 async_timing_mode; + u16 vendor_revision; + u8 vendor[88]; +}; + +#endif /* __LINUX_MTD_ONFI_H */ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index fbe7686cfc59..f4fc0cce7c55 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -204,147 +205,6 @@ enum nand_ecc_algo { #define NAND_CI_CELLTYPE_MSK 0x0C #define NAND_CI_CELLTYPE_SHIFT 2 -/* ONFI version bits */ -#define ONFI_VERSION_1_0 BIT(1) -#define ONFI_VERSION_2_0 BIT(2) -#define ONFI_VERSION_2_1 BIT(3) -#define ONFI_VERSION_2_2 BIT(4) -#define ONFI_VERSION_2_3 BIT(5) -#define ONFI_VERSION_3_0 BIT(6) -#define ONFI_VERSION_3_1 BIT(7) -#define ONFI_VERSION_3_2 BIT(8) -#define ONFI_VERSION_4_0 BIT(9) - -/* ONFI features */ -#define ONFI_FEATURE_16_BIT_BUS (1 << 0) -#define ONFI_FEATURE_EXT_PARAM_PAGE (1 << 7) - -/* ONFI timing mode, used in both asynchronous and synchronous mode */ -#define ONFI_TIMING_MODE_0 (1 << 0) -#define ONFI_TIMING_MODE_1 (1 << 1) -#define ONFI_TIMING_MODE_2 (1 << 2) -#define ONFI_TIMING_MODE_3 (1 << 3) -#define ONFI_TIMING_MODE_4 (1 << 4) -#define ONFI_TIMING_MODE_5 (1 << 5) -#define ONFI_TIMING_MODE_UNKNOWN (1 << 6) - -/* ONFI feature number/address */ -#define ONFI_FEATURE_NUMBER 256 -#define ONFI_FEATURE_ADDR_TIMING_MODE 0x1 - -/* Vendor-specific feature address (Micron) */ -#define ONFI_FEATURE_ADDR_READ_RETRY 0x89 -#define ONFI_FEATURE_ON_DIE_ECC 0x90 -#define ONFI_FEATURE_ON_DIE_ECC_EN BIT(3) - -/* ONFI subfeature parameters length */ -#define ONFI_SUBFEATURE_PARAM_LEN 4 - -/* ONFI optional commands SET/GET FEATURES supported? */ -#define ONFI_OPT_CMD_SET_GET_FEATURES (1 << 2) - -struct nand_onfi_params { - /* rev info and features block */ - /* 'O' 'N' 'F' 'I' */ - u8 sig[4]; - __le16 revision; - __le16 features; - __le16 opt_cmd; - u8 reserved0[2]; - __le16 ext_param_page_length; /* since ONFI 2.1 */ - u8 num_of_param_pages; /* since ONFI 2.1 */ - u8 reserved1[17]; - - /* manufacturer information block */ - char manufacturer[12]; - char model[20]; - u8 jedec_id; - __le16 date_code; - u8 reserved2[13]; - - /* memory organization block */ - __le32 byte_per_page; - __le16 spare_bytes_per_page; - __le32 data_bytes_per_ppage; - __le16 spare_bytes_per_ppage; - __le32 pages_per_block; - __le32 blocks_per_lun; - u8 lun_count; - u8 addr_cycles; - u8 bits_per_cell; - __le16 bb_per_lun; - __le16 block_endurance; - u8 guaranteed_good_blocks; - __le16 guaranteed_block_endurance; - u8 programs_per_page; - u8 ppage_attr; - u8 ecc_bits; - u8 interleaved_bits; - u8 interleaved_ops; - u8 reserved3[13]; - - /* electrical parameter block */ - u8 io_pin_capacitance_max; - __le16 async_timing_mode; - __le16 program_cache_timing_mode; - __le16 t_prog; - __le16 t_bers; - __le16 t_r; - __le16 t_ccs; - __le16 src_sync_timing_mode; - u8 src_ssync_features; - __le16 clk_pin_capacitance_typ; - __le16 io_pin_capacitance_typ; - __le16 input_pin_capacitance_typ; - u8 input_pin_capacitance_max; - u8 driver_strength_support; - __le16 t_int_r; - __le16 t_adl; - u8 reserved4[8]; - - /* vendor */ - __le16 vendor_revision; - u8 vendor[88]; - - __le16 crc; -} __packed; - -#define ONFI_CRC_BASE 0x4F4E - -/* Extended ECC information Block Definition (since ONFI 2.1) */ -struct onfi_ext_ecc_info { - u8 ecc_bits; - u8 codeword_size; - __le16 bb_per_lun; - __le16 block_endurance; - u8 reserved[2]; -} __packed; - -#define ONFI_SECTION_TYPE_0 0 /* Unused section. */ -#define ONFI_SECTION_TYPE_1 1 /* for additional sections. */ -#define ONFI_SECTION_TYPE_2 2 /* for ECC information. */ -struct onfi_ext_section { - u8 type; - u8 length; -} __packed; - -#define ONFI_EXT_SECTION_MAX 8 - -/* Extended Parameter Page Definition (since ONFI 2.1) */ -struct onfi_ext_param_page { - __le16 crc; - u8 sig[4]; /* 'E' 'P' 'P' 'S' */ - u8 reserved0[10]; - struct onfi_ext_section sections[ONFI_EXT_SECTION_MAX]; - - /* - * The actual size of the Extended Parameter Page is in - * @ext_param_page_length of nand_onfi_params{}. - * The following are the variable length sections. - * So we do not add any fields below. Please see the ONFI spec. - */ -} __packed; - struct jedec_ecc_info { u8 ecc_bits; u8 codeword_size; @@ -423,28 +283,6 @@ struct nand_jedec_params { __le16 crc; } __packed; -/** - * struct onfi_params - ONFI specific parameters that will be reused - * @version: ONFI version (BCD encoded), 0 if ONFI is not supported - * @tPROG: Page program time - * @tBERS: Block erase time - * @tR: Page read time - * @tCCS: Change column setup time - * @async_timing_mode: Supported asynchronous timing mode - * @vendor_revision: Vendor specific revision number - * @vendor: Vendor specific data - */ -struct onfi_params { - int version; - u16 tPROG; - u16 tBERS; - u16 tR; - u16 tCCS; - u16 async_timing_mode; - u16 vendor_revision; - u8 vendor[88]; -}; - /** * struct nand_parameters - NAND generic parameters from the parameter page * @model: Model name -- cgit v1.2.3 From 8ae3fbf81b9cfdd1fec0451181213742b73fdf1a Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:51 +0200 Subject: mtd: rawnand: Move JEDEC code to nand_jedec.c This moves JEDEC related code to nand_jedec.c and JEDEC related struct/macros to include/linux/mtd/jedec.h. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/jedec.h | 91 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/rawnand.h | 79 +-------------------------------------- 2 files changed, 92 insertions(+), 78 deletions(-) create mode 100644 include/linux/mtd/jedec.h (limited to 'include/linux') diff --git a/include/linux/mtd/jedec.h b/include/linux/mtd/jedec.h new file mode 100644 index 000000000000..0b6b59f7cfbd --- /dev/null +++ b/include/linux/mtd/jedec.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright © 2000-2010 David Woodhouse + * Steven J. Hill + * Thomas Gleixner + * + * Contains all JEDEC related definitions + */ + +#ifndef __LINUX_MTD_JEDEC_H +#define __LINUX_MTD_JEDEC_H + +struct jedec_ecc_info { + u8 ecc_bits; + u8 codeword_size; + __le16 bb_per_lun; + __le16 block_endurance; + u8 reserved[2]; +} __packed; + +/* JEDEC features */ +#define JEDEC_FEATURE_16_BIT_BUS (1 << 0) + +struct nand_jedec_params { + /* rev info and features block */ + /* 'J' 'E' 'S' 'D' */ + u8 sig[4]; + __le16 revision; + __le16 features; + u8 opt_cmd[3]; + __le16 sec_cmd; + u8 num_of_param_pages; + u8 reserved0[18]; + + /* manufacturer information block */ + char manufacturer[12]; + char model[20]; + u8 jedec_id[6]; + u8 reserved1[10]; + + /* memory organization block */ + __le32 byte_per_page; + __le16 spare_bytes_per_page; + u8 reserved2[6]; + __le32 pages_per_block; + __le32 blocks_per_lun; + u8 lun_count; + u8 addr_cycles; + u8 bits_per_cell; + u8 programs_per_page; + u8 multi_plane_addr; + u8 multi_plane_op_attr; + u8 reserved3[38]; + + /* electrical parameter block */ + __le16 async_sdr_speed_grade; + __le16 toggle_ddr_speed_grade; + __le16 sync_ddr_speed_grade; + u8 async_sdr_features; + u8 toggle_ddr_features; + u8 sync_ddr_features; + __le16 t_prog; + __le16 t_bers; + __le16 t_r; + __le16 t_r_multi_plane; + __le16 t_ccs; + __le16 io_pin_capacitance_typ; + __le16 input_pin_capacitance_typ; + __le16 clk_pin_capacitance_typ; + u8 driver_strength_support; + __le16 t_adl; + u8 reserved4[36]; + + /* ECC and endurance block */ + u8 guaranteed_good_blocks; + __le16 guaranteed_block_endurance; + struct jedec_ecc_info ecc_info[4]; + u8 reserved5[29]; + + /* reserved */ + u8 reserved6[148]; + + /* vendor */ + __le16 vendor_rev_num; + u8 reserved7[88]; + + /* CRC for Parameter Page */ + __le16 crc; +} __packed; + +#endif /* __LINUX_MTD_JEDEC_H */ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index f4fc0cce7c55..68d09e01fa56 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -205,84 +206,6 @@ enum nand_ecc_algo { #define NAND_CI_CELLTYPE_MSK 0x0C #define NAND_CI_CELLTYPE_SHIFT 2 -struct jedec_ecc_info { - u8 ecc_bits; - u8 codeword_size; - __le16 bb_per_lun; - __le16 block_endurance; - u8 reserved[2]; -} __packed; - -/* JEDEC features */ -#define JEDEC_FEATURE_16_BIT_BUS (1 << 0) - -struct nand_jedec_params { - /* rev info and features block */ - /* 'J' 'E' 'S' 'D' */ - u8 sig[4]; - __le16 revision; - __le16 features; - u8 opt_cmd[3]; - __le16 sec_cmd; - u8 num_of_param_pages; - u8 reserved0[18]; - - /* manufacturer information block */ - char manufacturer[12]; - char model[20]; - u8 jedec_id[6]; - u8 reserved1[10]; - - /* memory organization block */ - __le32 byte_per_page; - __le16 spare_bytes_per_page; - u8 reserved2[6]; - __le32 pages_per_block; - __le32 blocks_per_lun; - u8 lun_count; - u8 addr_cycles; - u8 bits_per_cell; - u8 programs_per_page; - u8 multi_plane_addr; - u8 multi_plane_op_attr; - u8 reserved3[38]; - - /* electrical parameter block */ - __le16 async_sdr_speed_grade; - __le16 toggle_ddr_speed_grade; - __le16 sync_ddr_speed_grade; - u8 async_sdr_features; - u8 toggle_ddr_features; - u8 sync_ddr_features; - __le16 t_prog; - __le16 t_bers; - __le16 t_r; - __le16 t_r_multi_plane; - __le16 t_ccs; - __le16 io_pin_capacitance_typ; - __le16 input_pin_capacitance_typ; - __le16 clk_pin_capacitance_typ; - u8 driver_strength_support; - __le16 t_adl; - u8 reserved4[36]; - - /* ECC and endurance block */ - u8 guaranteed_good_blocks; - __le16 guaranteed_block_endurance; - struct jedec_ecc_info ecc_info[4]; - u8 reserved5[29]; - - /* reserved */ - u8 reserved6[148]; - - /* vendor */ - __le16 vendor_rev_num; - u8 reserved7[88]; - - /* CRC for Parameter Page */ - __le16 crc; -} __packed; - /** * struct nand_parameters - NAND generic parameters from the parameter page * @model: Model name -- cgit v1.2.3 From 309600c14e36d0e78c22fe3df58317965b90f4d1 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 4 Sep 2018 16:23:28 +0200 Subject: mtd: rawnand: Allow selection of ECC byte ordering at runtime Currently, the selection of ECC byte ordering for software hamming is done at compilation time, which doesn't make sense when ECC byte calculation is done in hardware and byte ordering is forced by the hardware engine. In this case, only the correction is done in software and we want to force the byte-ordering no matter the value of CONFIG_MTD_NAND_ECC_SMC. This is typically the case for the FSMC (Smart Media ordering), TMIO and TXX9NDFMC (regular byte ordering) blocks. For all other use cases (pure software implementation, SM FTL and nandecctest), we keep selecting the byte ordering based on the CONFIG_MTD_NAND_ECC_SMC value. It might not be ideal for SM FTL (I'd expect Smart Media ordering to be employed by the Smart Media FTL), but this option doesn't seem to be enabled in the existing _defconfig, so I can't tell setting sm_order to true is the right choice. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/nand_ecc.h | 4 ++-- include/linux/mtd/rawnand.h | 6 ++++++ 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand_ecc.h b/include/linux/mtd/nand_ecc.h index b81fecd5e719..0b3bb156c344 100644 --- a/include/linux/mtd/nand_ecc.h +++ b/include/linux/mtd/nand_ecc.h @@ -19,7 +19,7 @@ struct nand_chip; * Calculate 3 byte ECC code for eccsize byte block */ void __nand_calculate_ecc(const u_char *dat, unsigned int eccsize, - u_char *ecc_code); + u_char *ecc_code, bool sm_order); /* * Calculate 3 byte ECC code for 256/512 byte block @@ -31,7 +31,7 @@ int nand_calculate_ecc(struct nand_chip *chip, const u_char *dat, * Detect and correct a 1 bit error for eccsize byte block */ int __nand_correct_data(u_char *dat, u_char *read_ecc, u_char *calc_ecc, - unsigned int eccsize); + unsigned int eccsize, bool sm_order); /* * Detect and correct a 1 bit error for 256/512 byte block diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 68d09e01fa56..e10b126e148f 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -121,6 +121,12 @@ enum nand_ecc_algo { #define NAND_ECC_GENERIC_ERASED_CHECK BIT(0) #define NAND_ECC_MAXIMIZE BIT(1) +/* + * When using software implementation of Hamming, we can specify which byte + * ordering should be used. + */ +#define NAND_ECC_SOFT_HAMMING_SM_ORDER BIT(2) + /* * Option constants for bizarre disfunctionality and real * features. -- cgit v1.2.3 From 2130b789b3ef6a518b9c9c6f245642620e2b0c0c Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Tue, 28 Aug 2018 16:51:18 +0100 Subject: irqchip/gic: Unify GIC priority definitions LPIs use the same priority value as other GIC interrupts. Make the GIC default priority definition visible to ITS implementation and use this same definition for LPI priorities. Tested-by: Daniel Thompson Signed-off-by: Julien Thierry Cc: Thomas Gleixner Cc: Jason Cooper Cc: Marc Zyngier Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-common.h | 6 ++++++ include/linux/irqchip/arm-gic.h | 5 ----- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h index 0a83b4379f34..9a1a479a2bf4 100644 --- a/include/linux/irqchip/arm-gic-common.h +++ b/include/linux/irqchip/arm-gic-common.h @@ -13,6 +13,12 @@ #include #include +#define GICD_INT_DEF_PRI 0xa0 +#define GICD_INT_DEF_PRI_X4 ((GICD_INT_DEF_PRI << 24) |\ + (GICD_INT_DEF_PRI << 16) |\ + (GICD_INT_DEF_PRI << 8) |\ + GICD_INT_DEF_PRI) + enum gic_type { GIC_V2, GIC_V3, diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 6c4aaf04046c..626179077bb0 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -65,11 +65,6 @@ #define GICD_INT_EN_CLR_X32 0xffffffff #define GICD_INT_EN_SET_SGI 0x0000ffff #define GICD_INT_EN_CLR_PPI 0xffff0000 -#define GICD_INT_DEF_PRI 0xa0 -#define GICD_INT_DEF_PRI_X4 ((GICD_INT_DEF_PRI << 24) |\ - (GICD_INT_DEF_PRI << 16) |\ - (GICD_INT_DEF_PRI << 8) |\ - GICD_INT_DEF_PRI) #define GICD_IIDR_IMPLEMENTER_SHIFT 0 #define GICD_IIDR_IMPLEMENTER_MASK (0xfff << GICD_IIDR_IMPLEMENTER_SHIFT) -- cgit v1.2.3 From 47b00dcf141172c4c1c583701ec91923672cec39 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 10 Aug 2018 11:29:09 +0300 Subject: clk: ti: clkctrl: support multiple clkctrl nodes under a cm node Currently, only one clkctrl node can be added under a specific CM node due to limitation with the implementation. Modify the code to pick-up clockdomain name from the clkctrl node instead of CM node if provided. Also, add a new flag to the TI clock driver so that both modes can be supported simultaneously. Signed-off-by: Tero Kristo Tested-by: Tony Lindgren --- include/linux/clk/ti.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index a8faa38b1ed6..3301bd025a2c 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -290,6 +290,7 @@ struct ti_clk_features { #define TI_CLK_DPLL4_DENY_REPROGRAM BIT(1) #define TI_CLK_DISABLE_CLKDM_CONTROL BIT(2) #define TI_CLK_ERRATA_I810 BIT(3) +#define TI_CLK_CLKCTRL_COMPAT BIT(4) void ti_clk_setup_features(struct ti_clk_features *features); const struct ti_clk_features *ti_clk_get_features(void); -- cgit v1.2.3 From 8b95d1ce3300c411728954473316bd04d0ba9883 Mon Sep 17 00:00:00 2001 From: Russ Dill Date: Tue, 4 Sep 2018 12:19:35 +0530 Subject: clk: Add functions to save/restore clock context en-masse Deep enough power saving mode can result into losing context of the clock registers also, and they need to be restored once coming back from the power saving mode. Hence add functions to save/restore clock context. Signed-off-by: Keerthy Signed-off-by: Russ Dill Acked-by: Tony Lindgren Signed-off-by: Tero Kristo --- include/linux/clk-provider.h | 7 +++++++ include/linux/clk.h | 25 +++++++++++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 08b1aa70a38d..df7379da6269 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -119,6 +119,11 @@ struct clk_duty { * Called with enable_lock held. This function must not * sleep. * + * @save_context: Save the context of the clock in prepration for poweroff. + * + * @restore_context: Restore the context of the clock after a restoration + * of power. + * * @recalc_rate Recalculate the rate of this clock, by querying hardware. The * parent rate is an input parameter. It is up to the caller to * ensure that the prepare_mutex is held across this call. @@ -223,6 +228,8 @@ struct clk_ops { void (*disable)(struct clk_hw *hw); int (*is_enabled)(struct clk_hw *hw); void (*disable_unused)(struct clk_hw *hw); + int (*save_context)(struct clk_hw *hw); + void (*restore_context)(struct clk_hw *hw); unsigned long (*recalc_rate)(struct clk_hw *hw, unsigned long parent_rate); long (*round_rate)(struct clk_hw *hw, unsigned long rate, diff --git a/include/linux/clk.h b/include/linux/clk.h index 4f750c481b82..7da754d79f9d 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -629,6 +629,23 @@ struct clk *clk_get_parent(struct clk *clk); */ struct clk *clk_get_sys(const char *dev_id, const char *con_id); +/** + * clk_save_context - save clock context for poweroff + * + * Saves the context of the clock register for powerstates in which the + * contents of the registers will be lost. Occurs deep within the suspend + * code so locking is not necessary. + */ +int clk_save_context(void); + +/** + * clk_restore_context - restore clock context after poweroff + * + * This occurs with all clocks enabled. Occurs deep within the resume code + * so locking is not necessary. + */ +void clk_restore_context(void); + #else /* !CONFIG_HAVE_CLK */ static inline struct clk *clk_get(struct device *dev, const char *id) @@ -728,6 +745,14 @@ static inline struct clk *clk_get_sys(const char *dev_id, const char *con_id) { return NULL; } + +static inline int clk_save_context(void) +{ + return 0; +} + +static inline void clk_restore_context(void) {} + #endif /* clk_prepare_enable helps cases using clk_enable in non-atomic context. */ -- cgit v1.2.3 From 435365485f40cf12747d1daa2253a4f4b46b8148 Mon Sep 17 00:00:00 2001 From: Keerthy Date: Tue, 4 Sep 2018 12:19:36 +0530 Subject: clk: clk: Add clk_gate_restore_context function The clock gate restore context function enables or disables the gate clocks based on the enable_count. This is done in cases where the clock context is lost and based on the enable_count the clock either needs to be enabled/disabled. Signed-off-by: Keerthy Acked-by: Tony Lindgren Signed-off-by: Tero Kristo --- include/linux/clk-provider.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index df7379da6269..60c51871b04b 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1018,5 +1018,7 @@ static inline void clk_writel(u32 val, u32 __iomem *reg) #endif /* platform dependent I/O accessors */ +void clk_gate_restore_context(struct clk_hw *hw); + #endif /* CONFIG_COMMON_CLK */ #endif /* CLK_PROVIDER_H */ -- cgit v1.2.3 From d6e7bbc148f9fbec8a0117b0d0f420c9710e6d81 Mon Sep 17 00:00:00 2001 From: Russ Dill Date: Tue, 4 Sep 2018 12:19:37 +0530 Subject: clk: ti: Add functions to save/restore clk context SoCs like AM43XX lose clock registers context during RTC-only suspend. Hence add functions to save/restore the clock registers context. Signed-off-by: Keerthy Signed-off-by: Russ Dill Acked-by: Tony Lindgren Signed-off-by: Tero Kristo --- include/linux/clk/ti.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 3301bd025a2c..eacc5df57b99 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -159,6 +159,7 @@ struct clk_hw_omap { const char *clkdm_name; struct clockdomain *clkdm; const struct clk_hw_omap_ops *ops; + u32 context; }; /* @@ -294,6 +295,11 @@ struct ti_clk_features { void ti_clk_setup_features(struct ti_clk_features *features); const struct ti_clk_features *ti_clk_get_features(void); +int omap3_noncore_dpll_save_context(struct clk_hw *hw); +void omap3_noncore_dpll_restore_context(struct clk_hw *hw); + +int omap3_core_dpll_save_context(struct clk_hw *hw); +void omap3_core_dpll_restore_context(struct clk_hw *hw); extern const struct clk_hw_omap_ops clkhwops_omap2xxx_dpll; -- cgit v1.2.3 From 9414229c9c53d3604032aa80f3d2e9ba5770cd4a Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 24 Sep 2018 06:08:07 +0200 Subject: clocksource: Remove obsolete CLOCKSOURCE_OF_DECLARE The macro CLOCKSOURCE_OF_DECLARE was renamed more TIMER_OF_DECLARE, and we kept an alias CLOCKSOURCE_OF_DECLARE in order to smooth the transition for drivers. This change was done 1.5 year ago, we can reasonably remove this backward compatible macro as it is no longer used anywhere. Signed-off-by: Daniel Lezcano --- include/linux/clocksource.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 308918928767..4c58c1e64080 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -257,9 +257,6 @@ extern int clocksource_i8253_init(void); #define TIMER_OF_DECLARE(name, compat, fn) \ OF_DECLARE_1_RET(timer, name, compat, fn) -#define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ - TIMER_OF_DECLARE(name, compat, fn) - #ifdef CONFIG_TIMER_PROBE extern void timer_probe(void); #else -- cgit v1.2.3 From 16fc087b9cb22c9a97307cc24a5413d0df68fe11 Mon Sep 17 00:00:00 2001 From: Yashaswini Raghuram Prathivadi Bhayankaram Date: Fri, 10 Aug 2018 00:17:44 -0700 Subject: virtchnl: Added support to exchange additional speed values Introduced a new virtchnl capability flag and a struct to support exchange of additional supported speeds. Signed-off-by: Yashaswini Raghuram Prathivadi Bhayankaram Signed-off-by: Anirudh Venkataramanan Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index b41f7bc958ef..2c9756bd9c4c 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -252,6 +252,8 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM 0X00400000 #define VIRTCHNL_VF_OFFLOAD_ADQ 0X00800000 +/* Define below the capability flags that are not offloads */ +#define VIRTCHNL_VF_CAP_ADV_LINK_SPEED 0x00000080 #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ VIRTCHNL_VF_OFFLOAD_VLAN | \ VIRTCHNL_VF_OFFLOAD_RSS_PF) @@ -596,10 +598,23 @@ enum virtchnl_event_codes { struct virtchnl_pf_event { enum virtchnl_event_codes event; union { + /* If the PF driver does not support the new speed reporting + * capabilities then use link_event else use link_event_adv to + * get the speed and link information. The ability to understand + * new speeds is indicated by setting the capability flag + * VIRTCHNL_VF_CAP_ADV_LINK_SPEED in vf_cap_flags parameter + * in virtchnl_vf_resource struct and can be used to determine + * which link event struct to use below. + */ struct { enum virtchnl_link_speed link_speed; bool link_status; } link_event; + struct { + /* link_speed provided in Mbps */ + u32 link_speed; + u8 link_status; + } link_event_adv; } event_data; int severity; -- cgit v1.2.3 From 4cd2e0e70af6897ca2247fa1ffb1553ca16b4903 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 18 Apr 2018 17:30:19 -0500 Subject: signal: Introduce copy_siginfo_from_user and use it's return value In preparation for using a smaller version of siginfo in the kernel introduce copy_siginfo_from_user and use it when siginfo is copied from userspace. Make the pattern for using copy_siginfo_from_user and copy_siginfo_from_user32 to capture the return value and return that value on error. This is a necessary prerequisite for using a smaller siginfo in the kernel than the kernel exports to userspace. Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 3d4cd5db30a9..de94c159bfb0 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -22,6 +22,7 @@ static inline void clear_siginfo(struct siginfo *info) } int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from); +int copy_siginfo_from_user(struct siginfo *to, const struct siginfo __user *from); enum siginfo_layout { SIL_KILL, -- cgit v1.2.3 From ae7795bc6187a15ec51cf258abae656a625f9980 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 25 Sep 2018 11:27:20 +0200 Subject: signal: Distinguish between kernel_siginfo and siginfo Linus recently observed that if we did not worry about the padding member in struct siginfo it is only about 48 bytes, and 48 bytes is much nicer than 128 bytes for allocating on the stack and copying around in the kernel. The obvious thing of only adding the padding when userspace is including siginfo.h won't work as there are sigframe definitions in the kernel that embed struct siginfo. So split siginfo in two; kernel_siginfo and siginfo. Keeping the traditional name for the userspace definition. While the version that is used internally to the kernel and ultimately will not be padded to 128 bytes is called kernel_siginfo. The definition of struct kernel_siginfo I have put in include/signal_types.h A set of buildtime checks has been added to verify the two structures have the same field offsets. To make it easy to verify the change kernel_siginfo retains the same size as siginfo. The reduction in size comes in a following change. Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 2 +- include/linux/compat.h | 4 ++-- include/linux/coredump.h | 4 ++-- include/linux/lsm_hooks.h | 4 ++-- include/linux/posix-timers.h | 2 +- include/linux/ptrace.h | 2 +- include/linux/sched.h | 2 +- include/linux/sched/signal.h | 18 +++++++++--------- include/linux/security.h | 6 +++--- include/linux/signal.h | 15 ++++++++------- include/linux/signal_types.h | 11 +++++++++-- 11 files changed, 39 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index c05f24fac4f6..e9f5fe69df31 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -78,7 +78,7 @@ struct linux_binprm { /* Function parameter for binfmt->coredump */ struct coredump_params { - const siginfo_t *siginfo; + const kernel_siginfo_t *siginfo; struct pt_regs *regs; struct file *file; unsigned long limit; diff --git a/include/linux/compat.h b/include/linux/compat.h index 1a3c4f37e908..4565d65b1776 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -452,8 +452,8 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size); long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, unsigned long bitmap_size); -int copy_siginfo_from_user32(siginfo_t *to, const struct compat_siginfo __user *from); -int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *from); +int copy_siginfo_from_user32(kernel_siginfo_t *to, const struct compat_siginfo __user *from); +int copy_siginfo_to_user32(struct compat_siginfo __user *to, const kernel_siginfo_t *from); int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 207aed96a5b7..abf4b4e65dbb 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -17,9 +17,9 @@ extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); extern void dump_truncate(struct coredump_params *cprm); #ifdef CONFIG_COREDUMP -extern void do_coredump(const siginfo_t *siginfo); +extern void do_coredump(const kernel_siginfo_t *siginfo); #else -static inline void do_coredump(const siginfo_t *siginfo) {} +static inline void do_coredump(const kernel_siginfo_t *siginfo) {} #endif #endif /* _LINUX_COREDUMP_H */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 97a020c616ad..bb40f6d34163 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -672,7 +672,7 @@ * Return 0 if permission is granted. * @task_kill: * Check permission before sending signal @sig to @p. @info can be NULL, - * the constant 1, or a pointer to a siginfo structure. If @info is 1 or + * the constant 1, or a pointer to a kernel_siginfo structure. If @info is 1 or * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming * from the kernel and should typically be permitted. * SIGIO signals are handled separately by the send_sigiotask hook in @@ -1606,7 +1606,7 @@ union security_list_options { int (*task_setscheduler)(struct task_struct *p); int (*task_getscheduler)(struct task_struct *p); int (*task_movememory)(struct task_struct *p); - int (*task_kill)(struct task_struct *p, struct siginfo *info, + int (*task_kill)(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred); int (*task_prctl)(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index ee7e987ea1b4..e96581ca7c9d 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -126,5 +126,5 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); -void posixtimer_rearm(struct siginfo *info); +void posixtimer_rearm(struct kernel_siginfo *info); #endif diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 1de2235511c8..d19a795100da 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -341,7 +341,7 @@ extern void user_single_step_report(struct pt_regs *regs); #else static inline void user_single_step_report(struct pt_regs *regs) { - siginfo_t info; + kernel_siginfo_t info; clear_siginfo(&info); info.si_signo = SIGTRAP; info.si_errno = 0; diff --git a/include/linux/sched.h b/include/linux/sched.h index 977cb57d7bc9..2ba88082e1ef 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -960,7 +960,7 @@ struct task_struct { /* Ptrace state: */ unsigned long ptrace_message; - siginfo_t *last_siginfo; + kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; #ifdef CONFIG_TASK_XACCT diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 9e07f3521549..13789d10a50e 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -270,12 +270,12 @@ static inline int signal_group_exit(const struct signal_struct *sig) extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); -extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); +extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *info); static inline int kernel_dequeue_signal(void) { struct task_struct *tsk = current; - siginfo_t __info; + kernel_siginfo_t __info; int ret; spin_lock_irq(&tsk->sighand->siglock); @@ -322,12 +322,12 @@ int force_sig_pkuerr(void __user *addr, u32 pkey); int force_sig_ptrace_errno_trap(int errno, void __user *addr); -extern int send_sig_info(int, struct siginfo *, struct task_struct *); +extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig, struct task_struct *p); -extern int force_sig_info(int, struct siginfo *, struct task_struct *); -extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); -extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid); -extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *, +extern int force_sig_info(int, struct kernel_siginfo *, struct task_struct *); +extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp); +extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid); +extern int kill_pid_info_as_cred(int, struct kernel_siginfo *, struct pid *, const struct cred *); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); @@ -475,8 +475,8 @@ static inline int kill_cad_pid(int sig, int priv) } /* These can be the second arg to send_sig_info/send_group_sig_info. */ -#define SEND_SIG_NOINFO ((struct siginfo *) 0) -#define SEND_SIG_PRIV ((struct siginfo *) 1) +#define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) +#define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) /* * True if we are on the alternate signal stack. diff --git a/include/linux/security.h b/include/linux/security.h index 75f4156c84d7..d170a5b031f3 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -35,7 +35,7 @@ struct linux_binprm; struct cred; struct rlimit; -struct siginfo; +struct kernel_siginfo; struct sembuf; struct kern_ipc_perm; struct audit_context; @@ -361,7 +361,7 @@ int security_task_setrlimit(struct task_struct *p, unsigned int resource, int security_task_setscheduler(struct task_struct *p); int security_task_getscheduler(struct task_struct *p); int security_task_movememory(struct task_struct *p); -int security_task_kill(struct task_struct *p, struct siginfo *info, +int security_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred); int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); @@ -1020,7 +1020,7 @@ static inline int security_task_movememory(struct task_struct *p) } static inline int security_task_kill(struct task_struct *p, - struct siginfo *info, int sig, + struct kernel_siginfo *info, int sig, const struct cred *cred) { return 0; diff --git a/include/linux/signal.h b/include/linux/signal.h index de94c159bfb0..70031b10b918 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -11,18 +11,19 @@ struct task_struct; /* for sysctl */ extern int print_fatal_signals; -static inline void copy_siginfo(struct siginfo *to, const struct siginfo *from) +static inline void copy_siginfo(kernel_siginfo_t *to, + const kernel_siginfo_t *from) { memcpy(to, from, sizeof(*to)); } -static inline void clear_siginfo(struct siginfo *info) +static inline void clear_siginfo(kernel_siginfo_t *info) { memset(info, 0, sizeof(*info)); } -int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from); -int copy_siginfo_from_user(struct siginfo *to, const struct siginfo __user *from); +int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from); +int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from); enum siginfo_layout { SIL_KILL, @@ -258,11 +259,11 @@ struct pt_regs; enum pid_type; extern int next_signal(struct sigpending *pending, sigset_t *mask); -extern int do_send_sig_info(int sig, struct siginfo *info, +extern int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); -extern int group_send_sig_info(int sig, struct siginfo *info, +extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); -extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); +extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 222ae696000b..2a40a9c5e4ad 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -9,6 +9,13 @@ #include #include +typedef struct kernel_siginfo { + union { + __SIGINFO; + int _si_pad[SI_MAX_SIZE/sizeof(int)]; + }; +} kernel_siginfo_t; + /* * Real Time signals may be queued. */ @@ -16,7 +23,7 @@ struct sigqueue { struct list_head list; int flags; - siginfo_t info; + kernel_siginfo_t info; struct user_struct *user; }; @@ -60,7 +67,7 @@ struct old_sigaction { struct ksignal { struct k_sigaction ka; - siginfo_t info; + kernel_siginfo_t info; int sig; }; -- cgit v1.2.3 From 4ce5f9c9e7546915c559ffae594e6d73f918db00 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 25 Sep 2018 12:59:31 +0200 Subject: signal: Use a smaller struct siginfo in the kernel We reserve 128 bytes for struct siginfo but only use about 48 bytes on 64bit and 32 bytes on 32bit. Someday we might use more but it is unlikely to be anytime soon. Userspace seems content with just enough bytes of siginfo to implement sigqueue. Or in the case of checkpoint/restart reinjecting signals the kernel has sent. Reducing the stack footprint and the work to copy siginfo around from 2 cachelines to 1 cachelines seems worth doing even if I don't have benchmarks to show a performance difference. Suggested-by: Linus Torvalds Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 ++ include/linux/signal_types.h | 5 +---- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 70031b10b918..706a499d1eb1 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -22,6 +22,8 @@ static inline void clear_siginfo(kernel_siginfo_t *info) memset(info, 0, sizeof(*info)); } +#define SI_EXPANSION_SIZE (sizeof(struct siginfo) - sizeof(struct kernel_siginfo)) + int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from); int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from); diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 2a40a9c5e4ad..f8a90ae9c6ec 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -10,10 +10,7 @@ #include typedef struct kernel_siginfo { - union { - __SIGINFO; - int _si_pad[SI_MAX_SIZE/sizeof(int)]; - }; + __SIGINFO; } kernel_siginfo_t; /* -- cgit v1.2.3 From 608a0ab2f54ab0e301ad76a41aad979ea0d02670 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 1 Oct 2018 10:41:44 -0400 Subject: SUNRPC: Add lockless lookup of the server's auth domain Avoid taking the global auth_domain_lock in most lookups of the auth domain by adding an RCU protected lookup. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svcauth.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 04e404a07882..3e53a6e2ada7 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -82,6 +82,7 @@ struct auth_domain { struct hlist_node hash; char *name; struct auth_ops *flavour; + struct rcu_head rcu_head; }; /* -- cgit v1.2.3 From fcd29ad17c6ff885dfae58f557e9323941e63ba2 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Thu, 9 Aug 2018 09:55:21 +0300 Subject: net/mlx5: Add Fast teardown support Today mlx5 devices support two teardown modes: 1- Regular teardown 2- Force teardown This change introduces the enhanced version of the "Force teardown" that allows SW to perform teardown in a faster way without the need to reclaim all the pages. Fast teardown provides the following advantages: 1- Fix a FW race condition that could cause command timeout 2- Avoid moving to polling mode 3- Close the vport to prevent PCI ACK to be sent without been scatter to memory Signed-off-by: Feras Daoud Reviewed-by: Majd Dibbiny Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 4 ++++ include/linux/mlx5/mlx5_ifc.h | 6 ++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 11fa4e66afc5..e9b502d5bcc1 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -504,6 +504,10 @@ struct health_buffer { __be16 ext_synd; }; +enum mlx5_cmd_addr_l_sz_offset { + MLX5_NIC_IFC_OFFSET = 8, +}; + struct mlx5_init_seg { __be32 fw_rev; __be32 cmdif_rev_fw_sub; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f043d65b9bac..6e8a882052b1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -896,7 +896,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_mkey[0x6]; u8 reserved_at_f0[0x8]; u8 dump_fill_mkey[0x1]; - u8 reserved_at_f9[0x3]; + u8 reserved_at_f9[0x2]; + u8 fast_teardown[0x1]; u8 log_max_eq[0x4]; u8 max_indirection[0x8]; @@ -3352,12 +3353,13 @@ struct mlx5_ifc_teardown_hca_out_bits { u8 reserved_at_40[0x3f]; - u8 force_state[0x1]; + u8 state[0x1]; }; enum { MLX5_TEARDOWN_HCA_IN_PROFILE_GRACEFUL_CLOSE = 0x0, MLX5_TEARDOWN_HCA_IN_PROFILE_FORCE_CLOSE = 0x1, + MLX5_TEARDOWN_HCA_IN_PROFILE_PREPARE_FAST_TEARDOWN = 0x2, }; struct mlx5_ifc_teardown_hca_in_bits { -- cgit v1.2.3 From 5f26bdceb9c0a5e6c696aa2899d077cd3ae93413 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 2 Oct 2018 23:42:02 +0200 Subject: cpuidle: menu: Fix wakeup statistics updates for polling state If the CPU exits the "polling" state due to the time limit in the loop in poll_idle(), this is not a real wakeup and it just means that the "polling" state selection was not adequate. The governor mispredicted short idle duration, but had a more suitable state been selected, the CPU might have spent more time in it. In fact, there is no reason to expect that there would have been a wakeup event earlier than the next timer in that case. Handling such cases as regular wakeups in menu_update() may cause the menu governor to make suboptimal decisions going forward, but ignoring them altogether would not be correct either, because every time menu_select() is invoked, it makes a separate new attempt to predict the idle duration taking distinct time to the closest timer event as input and the outcomes of all those attempts should be recorded. For this reason, make menu_update() always assume that if the "polling" state was exited due to the time limit, the next proper wakeup event for the CPU would be the next timer event (not including the tick). Fixes: a37b969a61c1 "cpuidle: poll_state: Add time limit to poll_idle()" Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) Reviewed-by: Daniel Lezcano --- include/linux/cpuidle.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index d262f620890e..faed7a8977e8 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -81,6 +81,7 @@ struct cpuidle_device { unsigned int registered:1; unsigned int enabled:1; unsigned int use_deepest_state:1; + unsigned int poll_time_limit:1; unsigned int cpu; int last_residency; -- cgit v1.2.3 From c06c4d8090513f2974dfdbed2ac98634357ac475 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Wed, 3 Oct 2018 14:30:53 -0700 Subject: x86/objtool: Use asm macros to work around GCC inlining bugs As described in: 77b0bf55bc67: ("kbuild/Makefile: Prepare for using macros in inline assembly code to work around asm() related GCC inlining bugs") GCC's inlining heuristics are broken with common asm() patterns used in kernel code, resulting in the effective disabling of inlining. In the case of objtool the resulting borkage can be significant, since all the annotations of objtool are discarded during linkage and never inlined, yet GCC bogusly considers most functions affected by objtool annotations as 'too large'. The workaround is to set an assembly macro and call it from the inline assembly block. As a result GCC considers the inline assembly block as a single instruction. (Which it isn't, but that's the best we can get.) This increases the kernel size slightly: text data bss dec hex filename 18140829 10224724 2957312 31322865 1ddf2f1 ./vmlinux before 18140970 10225412 2957312 31323694 1ddf62e ./vmlinux after (+829) The number of static text symbols (i.e. non-inlined functions) is reduced: Before: 40321 After: 40302 (-19) [ mingo: Rewrote the changelog. ] Tested-by: Kees Cook Signed-off-by: Nadav Amit Reviewed-by: Josh Poimboeuf Acked-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Christopher Li Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-sparse@vger.kernel.org Link: http://lkml.kernel.org/r/20181003213100.189959-4-namit@vmware.com Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 56 +++++++++++++++++++++++++++++++++++++----------- 1 file changed, 43 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 681d866efb1e..1921545c6351 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -99,22 +99,13 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, * unique, to convince GCC not to merge duplicate inline asm statements. */ #define annotate_reachable() ({ \ - asm volatile("%c0:\n\t" \ - ".pushsection .discard.reachable\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__COUNTER__)); \ + asm volatile("ANNOTATE_REACHABLE counter=%c0" \ + : : "i" (__COUNTER__)); \ }) #define annotate_unreachable() ({ \ - asm volatile("%c0:\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__COUNTER__)); \ + asm volatile("ANNOTATE_UNREACHABLE counter=%c0" \ + : : "i" (__COUNTER__)); \ }) -#define ASM_UNREACHABLE \ - "999:\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long 999b - .\n\t" \ - ".popsection\n\t" #else #define annotate_reachable() #define annotate_unreachable() @@ -299,6 +290,45 @@ static inline void *offset_to_ptr(const int *off) return (void *)((unsigned long)off + *off); } +#else /* __ASSEMBLY__ */ + +#ifdef __KERNEL__ +#ifndef LINKER_SCRIPT + +#ifdef CONFIG_STACK_VALIDATION +.macro ANNOTATE_UNREACHABLE counter:req +\counter: + .pushsection .discard.unreachable + .long \counter\()b -. + .popsection +.endm + +.macro ANNOTATE_REACHABLE counter:req +\counter: + .pushsection .discard.reachable + .long \counter\()b -. + .popsection +.endm + +.macro ASM_UNREACHABLE +999: + .pushsection .discard.unreachable + .long 999b - . + .popsection +.endm +#else /* CONFIG_STACK_VALIDATION */ +.macro ANNOTATE_UNREACHABLE counter:req +.endm + +.macro ANNOTATE_REACHABLE counter:req +.endm + +.macro ASM_UNREACHABLE +.endm +#endif /* CONFIG_STACK_VALIDATION */ + +#endif /* LINKER_SCRIPT */ +#endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ #ifndef __optimize -- cgit v1.2.3 From 34845c939082093354a6ffbb1ebff599e30b9b22 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 26 Sep 2018 15:20:03 +0200 Subject: reset: Grammar s/more then once/more than once/ Fix grammar in reset_control_get_exclusive() documentation comment. Signed-off-by: Geert Uytterhoeven Signed-off-by: Philipp Zabel --- include/linux/reset.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reset.h b/include/linux/reset.h index 09732c36f351..29af6d6b2f4b 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -116,7 +116,7 @@ static inline int device_reset_optional(struct device *dev) * @id: reset line name * * Returns a struct reset_control or IS_ERR() condition containing errno. - * If this function is called more then once for the same reset_control it will + * If this function is called more than once for the same reset_control it will * return -EBUSY. * * See reset_control_get_shared for details on shared references to -- cgit v1.2.3 From b723a7911d028fb55f67a63c4c4d895f72e059d4 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:32 +0300 Subject: fanotify: fix collision of internal and uapi mark flags The new mark flag FAN_MARK_FILESYSTEMS collides with existing internal flag FAN_MARK_ONDIR. Change internal flag value to avoid the collision. Fixes: d54f4fba889b ("fanotify: add API to attach/detach super block mark") Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 9c5ea3bdfaa0..e70fccc3757e 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -5,7 +5,7 @@ #include /* not valid from userspace, only kernel internal */ -#define FAN_MARK_ONDIR 0x00000100 +#define FAN_MARK_ONDIR 0x80000000 #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) -- cgit v1.2.3 From 007d1e8395eaa59b0e7ad9eb2b53a40859446a88 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:33 +0300 Subject: fsnotify: generalize handling of extra event flags FS_EVENT_ON_CHILD gets a special treatment in fsnotify() because it is not a flag specifying an event type, but rather an extra flags that may be reported along with another event and control the handling of the event by the backend. FS_ISDIR is also an "extra flag" and not an "event type" and therefore desrves the same treatment. With inotify/dnotify backends it was never possible to set FS_ISDIR in mark masks, so it did not matter. With fanotify backend, mark adding code jumps through hoops to avoid setting the FS_ISDIR in the commulative object mask. Separate the constant ALL_FSNOTIFY_EVENTS to ALL_FSNOTIFY_FLAGS and ALL_FSNOTIFY_EVENTS, so the latter can be used to test for specific event types. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8e91341cbd8a..135b973e44d1 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -68,15 +68,20 @@ #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM) +/* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN | \ FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE | \ FS_DELETE | FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ - FS_OPEN_PERM | FS_ACCESS_PERM | FS_EXCL_UNLINK | \ - FS_ISDIR | FS_IN_ONESHOT | FS_DN_RENAME | \ + FS_OPEN_PERM | FS_ACCESS_PERM | FS_DN_RENAME) + +/* Extra flags that may be reported with event or control handling of events */ +#define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ FS_DN_MULTISHOT | FS_EVENT_ON_CHILD) +#define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) + struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; -- cgit v1.2.3 From a72fd224e37bf6a0630bce302deebbccbc236ba2 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:34 +0300 Subject: fanotify: simplify handling of FAN_ONDIR fanotify mark add/remove code jumps through hoops to avoid setting the FS_ISDIR in the commulative object mask. That was just papering over a bug in fsnotify() handling of the FS_ISDIR extra flag. This bug is now fixed, so all the hoops can be removed along with the unneeded internal flag FAN_MARK_ONDIR. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index e70fccc3757e..a8c3fc54276d 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -4,9 +4,6 @@ #include -/* not valid from userspace, only kernel internal */ -#define FAN_MARK_ONDIR 0x80000000 - #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) -- cgit v1.2.3 From 23c9deeb3285d34fd243abb3d6b9f07db60c3cf4 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:35 +0300 Subject: fanotify: deprecate uapi FAN_ALL_* constants We do not want to add new bits to the FAN_ALL_* uapi constants because they have been exposed to userspace. If there are programs out there using these constants, those programs could break if re-compiled with modified FAN_ALL_* constants and run on an old kernel. We deprecate the uapi constants FAN_ALL_* and define new FANOTIFY_* constants for internal use to replace them. New feature bits will be added only to the new constants. Cc: Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index a8c3fc54276d..4519b0988afe 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -7,4 +7,51 @@ #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) +/* + * Flags allowed to be passed from/to userspace. + * + * We intentionally do not add new bits to the old FAN_ALL_* constants, because + * they are uapi exposed constants. If there are programs out there using + * these constant, the programs may break if re-compiled with new uapi headers + * and then run on an old kernel. + */ +#define FANOTIFY_CLASS_BITS (FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \ + FAN_CLASS_PRE_CONTENT) + +#define FANOTIFY_INIT_FLAGS (FANOTIFY_CLASS_BITS | \ + FAN_CLOEXEC | FAN_NONBLOCK | \ + FAN_UNLIMITED_QUEUE | FAN_UNLIMITED_MARKS) + +#define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ + FAN_MARK_FILESYSTEM) + +#define FANOTIFY_MARK_FLAGS (FANOTIFY_MARK_TYPE_BITS | \ + FAN_MARK_ADD | \ + FAN_MARK_REMOVE | \ + FAN_MARK_DONT_FOLLOW | \ + FAN_MARK_ONLYDIR | \ + FAN_MARK_IGNORED_MASK | \ + FAN_MARK_IGNORED_SURV_MODIFY | \ + FAN_MARK_FLUSH) + +/* Events that user can request to be notified on */ +#define FANOTIFY_EVENTS (FAN_ACCESS | FAN_MODIFY | \ + FAN_CLOSE | FAN_OPEN) + +/* Events that require a permission response from user */ +#define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM) + +/* Events that may be reported to user */ +#define FANOTIFY_OUTGOING_EVENTS (FANOTIFY_EVENTS | \ + FANOTIFY_PERM_EVENTS | \ + FAN_Q_OVERFLOW) + +/* Do not use these old uapi constants internally */ +#undef FAN_ALL_CLASS_BITS +#undef FAN_ALL_INIT_FLAGS +#undef FAN_ALL_MARK_FLAGS +#undef FAN_ALL_EVENTS +#undef FAN_ALL_PERM_EVENTS +#undef FAN_ALL_OUTGOING_EVENTS + #endif /* _LINUX_FANOTIFY_H */ -- cgit v1.2.3 From bdd5a46fe30653cb4d26c7c787a22159bf79eed9 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:37 +0300 Subject: fanotify: add BUILD_BUG_ON() to count the bits of fanotify constants Also define the FANOTIFY_EVENT_FLAGS consisting of the extra flags FAN_ONDIR and FAN_ON_CHILD. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 4519b0988afe..caf55c67fc6c 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -41,11 +41,17 @@ /* Events that require a permission response from user */ #define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM) +/* Extra flags that may be reported with event or control handling of events */ +#define FANOTIFY_EVENT_FLAGS (FAN_EVENT_ON_CHILD | FAN_ONDIR) + /* Events that may be reported to user */ #define FANOTIFY_OUTGOING_EVENTS (FANOTIFY_EVENTS | \ FANOTIFY_PERM_EVENTS | \ FAN_Q_OVERFLOW) +#define ALL_FANOTIFY_EVENT_BITS (FANOTIFY_OUTGOING_EVENTS | \ + FANOTIFY_EVENT_FLAGS) + /* Do not use these old uapi constants internally */ #undef FAN_ALL_CLASS_BITS #undef FAN_ALL_INIT_FLAGS -- cgit v1.2.3 From bbb4c4323a4d9cb5ca04db904aa3050a7586839a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 4 Oct 2018 14:27:55 +0100 Subject: dns: Allow the dns resolver to retrieve a server set Allow the DNS resolver to retrieve a set of servers and their associated addresses, ports, preference and weight ratings. In terms of communication with userspace, "srv=1" is added to the callout string (the '1' indicating the maximum data version supported by the kernel) to ask the userspace side for this. If the userspace side doesn't recognise it, it will ignore the option and return the usual text address list. If the userspace side does recognise it, it will return some binary data that begins with a zero byte that would cause the string parsers to give an error. The second byte contains the version of the data in the blob (this may be between 1 and the version specified in the callout data). The remainder of the payload is version-specific. In version 1, the payload looks like (note that this is packed): u8 Non-string marker (ie. 0) u8 Content (0 => Server list) u8 Version (ie. 1) u8 Source (eg. DNS_RECORD_FROM_DNS_SRV) u8 Status (eg. DNS_LOOKUP_GOOD) u8 Number of servers foreach-server { u16 Name length (LE) u16 Priority (as per SRV record) (LE) u16 Weight (as per SRV record) (LE) u16 Port (LE) u8 Source (eg. DNS_RECORD_FROM_NSS) u8 Status (eg. DNS_LOOKUP_GOT_NOT_FOUND) u8 Protocol (eg. DNS_SERVER_PROTOCOL_UDP) u8 Number of addresses char[] Name (not NUL-terminated) foreach-address { u8 Family (AF_INET{,6}) union { u8[4] ipv4_addr u8[16] ipv6_addr } } } This can then be used to fetch a whole cell's VL-server configuration for AFS, for example. Signed-off-by: David Howells Signed-off-by: David S. Miller --- include/linux/dns_resolver.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h index 6ac3cad9aef1..34a744a1bafc 100644 --- a/include/linux/dns_resolver.h +++ b/include/linux/dns_resolver.h @@ -24,11 +24,9 @@ #ifndef _LINUX_DNS_RESOLVER_H #define _LINUX_DNS_RESOLVER_H -#ifdef __KERNEL__ +#include extern int dns_query(const char *type, const char *name, size_t namelen, const char *options, char **_result, time64_t *_expiry); -#endif /* KERNEL */ - #endif /* _LINUX_DNS_RESOLVER_H */ -- cgit v1.2.3 From 817e9bc8cc04e5c70592525b96812c46c1aa1c46 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 4 Oct 2018 09:57:23 -0700 Subject: Revert "serial:serial_core: Allow use of CTS for PPS line discipline" This reverts commit c550f01c810f2197c98e6e3103f81797f5e063be. Turns out the samsung tty driver is mucking around in the "unused" port fields and this patch breaks that code :( So we need to fix that driver up before this can be accepted. Reported-by: Stephen Rothwell Cc: Steve Sakoman Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 4e2ba4894dcc..047fa67d039b 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -257,8 +257,7 @@ struct uart_port { struct device *dev; /* parent device */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; - unsigned char pps_4wire; /* CTS instead of DCD */ - unsigned char unused; + unsigned char unused[2]; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ -- cgit v1.2.3 From 5d5a0ab1a7918fce5ca5c0fb1871a3e2000f85de Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 1 Oct 2018 10:54:51 -0500 Subject: of: Fix property name in of_node_get_device_type Commit 0413bedabc88 ("of: Add device_type access helper functions") added a new helper not yet used in preparation for some treewide clean up of accesses to 'device_type' properties. Unfortunately, there's an error and 'type' was used for the property name. Fix this. Fixes: 0413bedabc88 ("of: Add device_type access helper functions") Cc: Frank Rowand Signed-off-by: Rob Herring --- include/linux/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index f581531d797e..04cef4490efc 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -991,7 +991,7 @@ static inline struct device_node *of_find_matching_node( static inline const char *of_node_get_device_type(const struct device_node *np) { - return of_get_property(np, "type", NULL); + return of_get_property(np, "device_type", NULL); } static inline bool of_node_is_type(const struct device_node *np, const char *type) -- cgit v1.2.3 From 479adb89a97b0a33e5a9d702119872cc82ca21aa Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 4 Oct 2018 13:28:08 -0700 Subject: cgroup: Fix dom_cgrp propagation when enabling threaded mode A cgroup which is already a threaded domain may be converted into a threaded cgroup if the prerequisite conditions are met. When this happens, all threaded descendant should also have their ->dom_cgrp updated to the new threaded domain cgroup. Unfortunately, this propagation was missing leading to the following failure. # cd /sys/fs/cgroup/unified # cat cgroup.subtree_control # show that no controllers are enabled # mkdir -p mycgrp/a/b/c # echo threaded > mycgrp/a/b/cgroup.type At this point, the hierarchy looks as follows: mycgrp [d] a [dt] b [t] c [inv] Now let's make node "a" threaded (and thus "mycgrp" s made "domain threaded"): # echo threaded > mycgrp/a/cgroup.type By this point, we now have a hierarchy that looks as follows: mycgrp [dt] a [t] b [t] c [inv] But, when we try to convert the node "c" from "domain invalid" to "threaded", we get ENOTSUP on the write(): # echo threaded > mycgrp/a/b/c/cgroup.type sh: echo: write error: Operation not supported This patch fixes the problem by * Moving the opencoded ->dom_cgrp save and restoration in cgroup_enable_threaded() into cgroup_{save|restore}_control() so that mulitple cgroups can be handled. * Updating all threaded descendants' ->dom_cgrp to point to the new dom_cgrp when enabling threaded mode. Signed-off-by: Tejun Heo Reported-and-tested-by: "Michael Kerrisk (man-pages)" Reported-by: Amin Jamali Reported-by: Joao De Almeida Pereira Link: https://lore.kernel.org/r/CAKgNAkhHYCMn74TCNiMJ=ccLd7DcmXSbvw3CbZ1YREeG7iJM5g@mail.gmail.com Fixes: 454000adaa2a ("cgroup: introduce cgroup->dom_cgrp and threaded css_set handling") Cc: stable@vger.kernel.org # v4.14+ --- include/linux/cgroup-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index ff20b677fb9f..22254c1fe1c5 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -412,6 +412,7 @@ struct cgroup { * specific task are charged to the dom_cgrp. */ struct cgroup *dom_cgrp; + struct cgroup *old_dom_cgrp; /* used while enabling threaded */ /* per-cpu recursive resource statistics */ struct cgroup_rstat_cpu __percpu *rstat_cpu; -- cgit v1.2.3 From d67f34c19a679436dd2963b588015e119279e7a8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 17 Sep 2018 14:45:34 +0200 Subject: clocksource: Provide clocksource_arch_init() Architectures have extra archdata in the clocksource, e.g. for VDSO support. There are no sanity checks or general initializations for this available. Add support for that. Signed-off-by: Thomas Gleixner Acked-by: Andy Lutomirski Acked-by: John Stultz Cc: Peter Zijlstra Cc: Matt Rickard Cc: Stephen Boyd Cc: Florian Weimer Cc: "K. Y. Srinivasan" Cc: Vitaly Kuznetsov Cc: devel@linuxdriverproject.org Cc: virtualization@lists.linux-foundation.org Cc: Paolo Bonzini Cc: Arnd Bergmann Cc: Juergen Gross Link: https://lkml.kernel.org/r/20180917130706.973042587@linutronix.de --- include/linux/clocksource.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 308918928767..6e6b86f9046d 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -241,6 +241,11 @@ static inline void __clocksource_update_freq_khz(struct clocksource *cs, u32 khz __clocksource_update_freq_scale(cs, 1000, khz); } +#ifdef CONFIG_ARCH_CLOCKSOURCE_INIT +extern void clocksource_arch_init(struct clocksource *cs); +#else +static inline void clocksource_arch_init(struct clocksource *cs) { } +#endif extern int timekeeping_notify(struct clocksource *clock); -- cgit v1.2.3 From fae29f135ef4a86228d3ce13b61babf0d3031118 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 25 Sep 2018 12:35:18 -0400 Subject: hwrng: core - document the quality field quality field is currently documented as being 'per mill'. In fact the math involved is: add_hwgenerator_randomness((void *)rng_fillbuf, rc, rc * current_quality * 8 >> 10); thus the actual definition is "bits of entropy per 1024 bits of input". The current documentation seems to have confused multiple people in the past, let's fix the documentation to match code. An alternative is to change core to match driver expectations, replacing rc * current_quality * 8 >> 10 with rc * current_quality / 1000 but that has performance costs, so probably isn't a good option. Fixes: 0f734e6e768 ("hwrng: add per-device entropy derating") Reported-by: "Dr. David Alan Gilbert" Signed-off-by: Michael S. Tsirkin Signed-off-by: Herbert Xu --- include/linux/hw_random.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index bee0827766a3..c0b93e0ff0c0 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -33,7 +33,8 @@ * and max is a multiple of 4 and >= 32 bytes. * @priv: Private data, for use by the RNG driver. * @quality: Estimation of true entropy in RNG's bitstream - * (per mill). + * (in bits of entropy per 1024 bits of input; + * valid values: 1 to 1024, or 0 for unknown). */ struct hwrng { const char *name; -- cgit v1.2.3 From 9d2f67e43b73e8af7438be219b66a5de0cfa8bd9 Mon Sep 17 00:00:00 2001 From: Jianfeng Tan Date: Sat, 29 Sep 2018 15:41:27 +0000 Subject: net/packet: fix packet drop as of virtio gso When we use raw socket as the vhost backend, a packet from virito with gso offloading information, cannot be sent out in later validaton at xmit path, as we did not set correct skb->protocol which is further used for looking up the gso function. To fix this, we set this field according to virito hdr information. Fixes: e858fae2b0b8f4 ("virtio_net: use common code for virtio_net_hdr and skb GSO conversion") Signed-off-by: Jianfeng Tan Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 9397628a1967..cb462f9ab7dd 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -5,6 +5,24 @@ #include #include +static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, + const struct virtio_net_hdr *hdr) +{ + switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + case VIRTIO_NET_HDR_GSO_UDP: + skb->protocol = cpu_to_be16(ETH_P_IP); + break; + case VIRTIO_NET_HDR_GSO_TCPV6: + skb->protocol = cpu_to_be16(ETH_P_IPV6); + break; + default: + return -EINVAL; + } + + return 0; +} + static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian) -- cgit v1.2.3 From 661b8d1b0e3a745e25f05adef2ebd00d830eeea7 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Mon, 1 Oct 2018 14:51:33 +0200 Subject: net: add umem reference in netdev{_rx}_queue These references to the umem will be used to store information on what kind of AF_XDP umem that is bound to a queue id, if any. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann --- include/linux/netdevice.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1cbbf77a685f..8318f79586c2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -609,6 +609,9 @@ struct netdev_queue { /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; +#ifdef CONFIG_XDP_SOCKETS + struct xdp_umem *umem; +#endif /* * write-mostly part */ @@ -738,6 +741,9 @@ struct netdev_rx_queue { struct kobject kobj; struct net_device *dev; struct xdp_rxq_info xdp_rxq; +#ifdef CONFIG_XDP_SOCKETS + struct xdp_umem *umem; +#endif } ____cacheline_aligned_in_smp; /* -- cgit v1.2.3 From c2a90025ad09d830c8d8ae69f485eac6aaaa2472 Mon Sep 17 00:00:00 2001 From: Quentin Schulz Date: Thu, 4 Oct 2018 14:22:03 +0200 Subject: phy: add QSGMII and PCIE modes Prepare for upcoming phys that'll handle QSGMII or PCIe. Reviewed-by: Florian Fainelli Signed-off-by: Quentin Schulz Signed-off-by: David S. Miller --- include/linux/phy/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 9713aebdd348..03b319f89a34 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -37,9 +37,11 @@ enum phy_mode { PHY_MODE_USB_OTG, PHY_MODE_SGMII, PHY_MODE_2500SGMII, + PHY_MODE_QSGMII, PHY_MODE_10GKR, PHY_MODE_UFS_HS_A, PHY_MODE_UFS_HS_B, + PHY_MODE_PCIE, }; /** -- cgit v1.2.3 From 017b1660df89f5fb4bfe66c34e35f7d2031100c7 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Oct 2018 15:51:29 -0700 Subject: mm: migration: fix migration of huge PMD shared pages The page migration code employs try_to_unmap() to try and unmap the source page. This is accomplished by using rmap_walk to find all vmas where the page is mapped. This search stops when page mapcount is zero. For shared PMD huge pages, the page map count is always 1 no matter the number of mappings. Shared mappings are tracked via the reference count of the PMD page. Therefore, try_to_unmap stops prematurely and does not completely unmap all mappings of the source page. This problem can result is data corruption as writes to the original source page can happen after contents of the page are copied to the target page. Hence, data is lost. This problem was originally seen as DB corruption of shared global areas after a huge page was soft offlined due to ECC memory errors. DB developers noticed they could reproduce the issue by (hotplug) offlining memory used to back huge pages. A simple testcase can reproduce the problem by creating a shared PMD mapping (note that this must be at least PUD_SIZE in size and PUD_SIZE aligned (1GB on x86)), and using migrate_pages() to migrate process pages between nodes while continually writing to the huge pages being migrated. To fix, have the try_to_unmap_one routine check for huge PMD sharing by calling huge_pmd_unshare for hugetlbfs huge pages. If it is a shared mapping it will be 'unshared' which removes the page table entry and drops the reference on the PMD page. After this, flush caches and TLB. mmu notifiers are called before locking page tables, but we can not be sure of PMD sharing until page tables are locked. Therefore, check for the possibility of PMD sharing before locking so that notifiers can prepare for the worst possible case. Link: http://lkml.kernel.org/r/20180823205917.16297-2-mike.kravetz@oracle.com [mike.kravetz@oracle.com: make _range_in_vma() a static inline] Link: http://lkml.kernel.org/r/6063f215-a5c8-2f0c-465a-2c515ddc952d@oracle.com Fixes: 39dde65c9940 ("shared page table for hugetlb page") Signed-off-by: Mike Kravetz Acked-by: Kirill A. Shutemov Reviewed-by: Naoya Horiguchi Acked-by: Michal Hocko Cc: Vlastimil Babka Cc: Davidlohr Bueso Cc: Jerome Glisse Cc: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/hugetlb.h | 14 ++++++++++++++ include/linux/mm.h | 6 ++++++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6b68e345f0ca..087fd5f48c91 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -140,6 +140,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pd(struct vm_area_struct *vma, @@ -170,6 +172,18 @@ static inline unsigned long hugetlb_total_pages(void) return 0; } +static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, + pte_t *ptep) +{ + return 0; +} + +static inline void adjust_range_if_pmd_sharing_possible( + struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} + #define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; }) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) diff --git a/include/linux/mm.h b/include/linux/mm.h index a61ebe8ad4ca..0416a7204be3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2455,6 +2455,12 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, return vma; } +static inline bool range_in_vma(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + return (vma && vma->vm_start <= start && end <= vma->vm_end); +} + #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); -- cgit v1.2.3 From 1bb89893d4fa8275333b3ed74fb0379d63025f9a Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Fri, 14 Sep 2018 19:37:23 -0500 Subject: remoteproc: Add missing kernel-doc comment for auto-boot The commit ddf711872c9d ("remoteproc: Introduce auto-boot flag") introduced the auto-boot flag but missed adding the corresponding kernel-doc comment. Add the same. Signed-off-by: Suman Anna Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index e3c5d856b6da..75f9ca05b865 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -439,6 +439,7 @@ struct rproc_dump_segment { * @cached_table: copy of the resource table * @table_sz: size of @cached_table * @has_iommu: flag to indicate if remote processor is behind an MMU + * @auto_boot: flag to indicate if remote processor should be auto-started * @dump_segments: list of segments in the firmware */ struct rproc { -- cgit v1.2.3 From 992b649a3f013465d8128da02e5449def662a4c3 Mon Sep 17 00:00:00 2001 From: Lianbo Jiang Date: Sun, 30 Sep 2018 16:37:41 +0800 Subject: kdump, proc/vmcore: Enable kdumping encrypted memory with SME enabled In the kdump kernel, the memory of the first kernel needs to be dumped into the vmcore file. If SME is enabled in the first kernel, the old memory has to be remapped with the memory encryption mask in order to access it properly. Split copy_oldmem_page() functionality to handle encrypted memory properly. [ bp: Heavily massage everything. ] Signed-off-by: Lianbo Jiang Signed-off-by: Borislav Petkov Cc: kexec@lists.infradead.org Cc: tglx@linutronix.de Cc: mingo@redhat.com Cc: hpa@zytor.com Cc: akpm@linux-foundation.org Cc: dan.j.williams@intel.com Cc: bhelgaas@google.com Cc: baiyaowei@cmss.chinamobile.com Cc: tiwai@suse.de Cc: brijesh.singh@amd.com Cc: dyoung@redhat.com Cc: bhe@redhat.com Cc: jroedel@suse.de Link: https://lkml.kernel.org/r/be7b47f9-6be6-e0d1-2c2a-9125bc74b818@redhat.com --- include/linux/crash_dump.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 3e4ba9d753c8..f774c5eb9e3c 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -26,6 +26,10 @@ extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); +extern ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, + size_t csize, unsigned long offset, + int userbuf); + void vmcore_cleanup(void); /* Architecture code defines this if there are other possible ELF -- cgit v1.2.3 From 99c65fa7c59ff558e70db8aa61bbdece5d3a9588 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 8 Oct 2018 00:20:07 -0700 Subject: dma-debug: Check for drivers mapping invalid addresses in dma_map_single() I recently debugged a DMA mapping oops where a driver was trying to map a buffer returned from request_firmware() with dma_map_single(). Memory returned from request_firmware() is mapped into the vmalloc region and this isn't a valid region to map with dma_map_single() per the DMA documentation's "What memory is DMA'able?" section. Unfortunately, we don't really check that in the DMA debugging code, so enabling DMA debugging doesn't help catch this problem. Let's add a new DMA debug function to check for a vmalloc address or an invalid virtual address and print a warning if this happens. This makes it a little easier to debug these sorts of problems, instead of seeing odd behavior or crashes when drivers attempt to map the vmalloc space for DMA. Cc: Marek Szyprowski Reviewed-by: Robin Murphy Signed-off-by: Stephen Boyd Signed-off-by: Christoph Hellwig --- include/linux/dma-debug.h | 8 ++++++++ include/linux/dma-mapping.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index a785f2507159..30213adbb6b9 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -32,6 +32,9 @@ extern void dma_debug_add_bus(struct bus_type *bus); extern int dma_debug_resize_entries(u32 num_entries); +extern void debug_dma_map_single(struct device *dev, const void *addr, + unsigned long len); + extern void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, int direction, dma_addr_t dma_addr, @@ -103,6 +106,11 @@ static inline int dma_debug_resize_entries(u32 num_entries) return 0; } +static inline void debug_dma_map_single(struct device *dev, const void *addr, + unsigned long len) +{ +} + static inline void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, int direction, dma_addr_t dma_addr, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 562af6b45f23..547a48bcfa3d 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -229,6 +229,7 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, dma_addr_t addr; BUG_ON(!valid_dma_direction(dir)); + debug_dma_map_single(dev, ptr, size); addr = ops->map_page(dev, virt_to_page(ptr), offset_in_page(ptr), size, dir, attrs); -- cgit v1.2.3 From c941ce9c282cc606e6517356fcc186a9da2b4ab9 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Sun, 7 Oct 2018 12:56:47 +0100 Subject: bpf: add verifier callback to get stack usage info for offloaded progs In preparation for BPF-to-BPF calls in offloaded programs, add a new function attribute to the struct bpf_prog_offload_ops so that drivers supporting eBPF offload can hook at the end of program verification, and potentially extract information collected by the verifier. Implement a minimal callback (returning 0) in the drivers providing the structs, namely netdevsim and nfp. This will be useful in the nfp driver, in later commits, to extract the number of subprograms as well as the stack depth for those subprograms. Signed-off-by: Quentin Monnet Reviewed-by: Jiong Wang Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 1 + include/linux/bpf_verifier.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 027697b6a22f..9b558713447f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -263,6 +263,7 @@ struct bpf_verifier_ops { struct bpf_prog_offload_ops { int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); + int (*finalize)(struct bpf_verifier_env *env); }; struct bpf_prog_offload { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7b6fd2ab3263..9e8056ec20fa 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -245,5 +245,6 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); +int bpf_prog_offload_finalize(struct bpf_verifier_env *env); #endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From cbf6d82cad4a507475d92d380228302fe668dd94 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Thu, 30 Aug 2018 01:32:05 +0200 Subject: mmc: core: add helper to see if a host is doing a retune MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a helper to allow host drivers checking if a retune is in progress. Signed-off-by: Niklas Söderlund Reviewed-by: Wolfram Sang Tested-by: Wolfram Sang Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index beed7121c781..2a5fe75dd082 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -569,6 +569,11 @@ static inline bool mmc_can_retune(struct mmc_host *host) return host->can_retune == 1; } +static inline bool mmc_doing_retune(struct mmc_host *host) +{ + return host->doing_retune == 1; +} + static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data) { return data->flags & MMC_DATA_WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE; -- cgit v1.2.3 From 9ef986a697c6d733d86e76d9870b4f1f60512b7a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 20 Sep 2018 16:01:10 -0700 Subject: mmc: mmci: Drop support for pdata GPIO numbers All the machines using the MMCI are passing GPIOs for the card detect and write protect using the device tree or descriptor table (one single case, Integrator/AP IM-PD1). Drop support for passing global GPIO numbers through platform data, noone is using it. Signed-off-by: Linus Walleij Signed-off-by: Ulf Hansson --- include/linux/amba/mmci.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h index da8357ba11bc..c92ebc39fc1f 100644 --- a/include/linux/amba/mmci.h +++ b/include/linux/amba/mmci.h @@ -18,20 +18,13 @@ * mask into a value to be binary (or set some other custom bits * in MMCIPWR) or:ed and written into the MMCIPWR register of the * block. May also control external power based on the power_mode. - * @status: if no GPIO read function was given to the block in - * gpio_wp (below) this function will be called to determine - * whether a card is present in the MMC slot or not - * @gpio_wp: read this GPIO pin to see if the card is write protected - * @gpio_cd: read this GPIO pin to detect card insertion - * @cd_invert: true if the gpio_cd pin value is active low + * @status: if no GPIO line was given to the block in this function will + * be called to determine whether a card is present in the MMC slot or not */ struct mmci_platform_data { unsigned int ocr_mask; int (*ios_handler)(struct device *, struct mmc_ios *); unsigned int (*status)(struct device *); - int gpio_wp; - int gpio_cd; - bool cd_invert; }; #endif -- cgit v1.2.3 From 43b7358df63adff21aa81b349d9080954bf1c372 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 23 Sep 2018 09:03:21 +0200 Subject: mmc: sdhci: pxav3: Delete GPIO handling The platform data for the PXAv3 driver allows passing a card detect GPIO, but this code is not used in the kernel. In order to not encourage the use of the old global GPIO numberspace we need to remove this. Card detect (and write protect) GPIO can easily be added into the driver using machine descriptor tables instead, and the descriptor-based (gpiod) variants of the slot GPIO APIs. Cc: Jisheng Zhang Cc: Adrian Hunter Signed-off-by: Linus Walleij Reviewed-by: Jisheng Zhang Acked-by: Adrian Hunter Signed-off-by: Ulf Hansson --- include/linux/platform_data/pxa_sdhci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/pxa_sdhci.h b/include/linux/platform_data/pxa_sdhci.h index 9e20c2fb4ffd..4977c06d8a86 100644 --- a/include/linux/platform_data/pxa_sdhci.h +++ b/include/linux/platform_data/pxa_sdhci.h @@ -33,8 +33,6 @@ * 1: choose feedback clk + delay value * 2: choose internal clk * @clk_delay_enable: enable clk_delay or not, used on pxa910 - * @ext_cd_gpio: gpio pin used for external CD line - * @ext_cd_gpio_invert: invert values for external CD gpio line * @max_speed: the maximum speed supported * @host_caps: Standard MMC host capabilities bit field. * @quirks: quirks of platfrom @@ -46,8 +44,6 @@ struct sdhci_pxa_platdata { unsigned int clk_delay_cycles; unsigned int clk_delay_sel; bool clk_delay_enable; - unsigned int ext_cd_gpio; - bool ext_cd_gpio_invert; unsigned int max_speed; u32 host_caps; u32 host_caps2; -- cgit v1.2.3 From 7838a8ddc80b2aa82d364d39042ca422f7748885 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 24 Sep 2018 13:30:50 +0200 Subject: mmc: omap_hsmmc: Kill off cover detection Cover detection appears to be a feature protecting the SD card on mobile phones with a slide-cover, such as some Nokia phones. The idea seems to be to not allow access to the SD card when the cover is open. It is only usable with platform data from board files, but no board file in the kernel is using it, yet it takes up a sizeable chunk of code in the OMAP HSMMC driver. Since we do not add new board files for the OMAPs any target that need this should anyway reimplement it properly using the device tree, so delete this legacy code. The driver is marked as orphan in MAINTAINERS by the way. Cc: Tony Lindgren Cc: linux-omap@vger.kernel.org Signed-off-by: Linus Walleij Acked-by: Tony Lindgren Acked-by: Kishon Vijay Abraham I Signed-off-by: Ulf Hansson --- include/linux/platform_data/hsmmc-omap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h index 73d9098ada2d..c055d7eda085 100644 --- a/include/linux/platform_data/hsmmc-omap.h +++ b/include/linux/platform_data/hsmmc-omap.h @@ -71,7 +71,6 @@ struct omap_hsmmc_platform_data { char *version; int gpio_cd; /* gpio (card detect) */ - int gpio_cod; /* gpio (cover detect) */ int gpio_wp; /* gpio (write protect) */ /* if we have special card, init it using this callback */ void (*init_card)(struct mmc_card *card); -- cgit v1.2.3 From e63201f19438372fcb45977d8e14c6ab5807d55b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 24 Sep 2018 13:30:51 +0200 Subject: mmc: omap_hsmmc: Delete platform data GPIO CD and WP The OMAP HSMMC driver has some elaborate and hairy handling for passing GPIO card detect and write protect lines from a boardfile into the driver: the machine defines a struct omap2_hsmmc_info that is copied into struct omap_hsmmc_platform_data by omap_hsmmc_pdata_init() in arch/arm/mach-omap2/hsmmc.c. However the .gpio_cd and .gpio_wp fields are not copied from omap2_hsmmc_info to omap_hsmmc_platform_data by omap_hsmmc_pdata_init() so they remain unused. The only platform defining omap2_hsmmc_info also define both to -1, unused. It turn out there are no boardfiles passing any valid GPIO lines into the OMAP HSMMC driver at all. And since we are not going to add any more OMAP2 boardfiles, we can delete this card detect and write protect handling altogether. This seems to also fix a bug: the card detect callback mmc_gpio_get_cd() in the slot GPIO core needs to be called by drivers utilizing slot GPIO. It appears the the boardfile quirks were not doing this right, so this would only get called for boardfiles, i.e. since no boardfile was using it, never. Just assign mmc_gpio_get_cd() unconditionally to omap_hsmmc_ops .get_cd() so card detects from the device tree works. AFAICT card detect with GPIO lines assigned from mmc_of_parse() are not working at the moment, but that is no regression since it probably never worked. Cc: Tony Lindgren Cc: linux-omap@vger.kernel.org Signed-off-by: Linus Walleij Acked-by: Tony Lindgren Signed-off-by: Ulf Hansson --- include/linux/platform_data/hsmmc-omap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h index c055d7eda085..85da11916bd5 100644 --- a/include/linux/platform_data/hsmmc-omap.h +++ b/include/linux/platform_data/hsmmc-omap.h @@ -70,8 +70,6 @@ struct omap_hsmmc_platform_data { /* string specifying a particular variant of hardware */ char *version; - int gpio_cd; /* gpio (card detect) */ - int gpio_wp; /* gpio (write protect) */ /* if we have special card, init it using this callback */ void (*init_card)(struct mmc_card *card); -- cgit v1.2.3 From d0a6a87e40da49cfc7954c491d3065a25a641b29 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:38 +0300 Subject: fanotify: support reporting thread id instead of process id In order to identify which thread triggered the event in a multi-threaded program, add the FAN_REPORT_TID flag in fanotify_init to opt-in for reporting the event creator's thread id information. Signed-off-by: nixiaoming Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index caf55c67fc6c..a5a60691e48b 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -19,6 +19,7 @@ FAN_CLASS_PRE_CONTENT) #define FANOTIFY_INIT_FLAGS (FANOTIFY_CLASS_BITS | \ + FAN_REPORT_TID | \ FAN_CLOEXEC | FAN_NONBLOCK | \ FAN_UNLIMITED_QUEUE | FAN_UNLIMITED_MARKS) -- cgit v1.2.3 From 0792a2c8e0bbda3605b8d42c6b9635be7b19982a Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 11 Sep 2018 20:18:44 -0400 Subject: macintosh: Use common code to access RTC Now that the 68k Mac port has adopted the via-pmu driver, the same RTC code can be shared between m68k and powerpc. Replace duplicated code in arch/powerpc and arch/m68k with common RTC accessors for Cuda and PMU. Drop the problematic WARN_ON which was introduced in commit 22db552b50fa ("powerpc/powermac: Fix rtc read/write functions"). Tested-by: Stan Johnson Signed-off-by: Finn Thain Cc: Geert Uytterhoeven Cc: Arnd Bergmann Acked-by: Geert Uytterhoeven Signed-off-by: Michael Ellerman --- include/linux/cuda.h | 4 ++++ include/linux/pmu.h | 4 ++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cuda.h b/include/linux/cuda.h index 056867f09a01..45bfe9d61271 100644 --- a/include/linux/cuda.h +++ b/include/linux/cuda.h @@ -8,6 +8,7 @@ #ifndef _LINUX_CUDA_H #define _LINUX_CUDA_H +#include #include @@ -16,4 +17,7 @@ extern int cuda_request(struct adb_request *req, void (*done)(struct adb_request *), int nbytes, ...); extern void cuda_poll(void); +extern time64_t cuda_get_time(void); +extern int cuda_set_rtc_time(struct rtc_time *tm); + #endif /* _LINUX_CUDA_H */ diff --git a/include/linux/pmu.h b/include/linux/pmu.h index 9ac8fc60ad49..52453a24a24f 100644 --- a/include/linux/pmu.h +++ b/include/linux/pmu.h @@ -9,6 +9,7 @@ #ifndef _LINUX_PMU_H #define _LINUX_PMU_H +#include #include @@ -36,6 +37,9 @@ static inline void pmu_resume(void) extern void pmu_enable_irled(int on); +extern time64_t pmu_get_time(void); +extern int pmu_set_rtc_time(struct rtc_time *tm); + extern void pmu_restart(void); extern void pmu_shutdown(void); extern void pmu_unlock(void); -- cgit v1.2.3 From edbee095fafb4b727b51032bdc41e345f95bbc20 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Sun, 7 Oct 2018 21:04:42 +0800 Subject: firmware: imx: add SCU firmware driver support The System Controller Firmware (SCFW) is a low-level system function which runs on a dedicated Cortex-M core to provide power, clock, and resource management. It exists on some i.MX8 processors. e.g. i.MX8QM (QM, QP), and i.MX8QX (QXP, DX). This patch implements the SCU firmware IPC function and the common message sending API sc_call_rpc. Cc: Shawn Guo Cc: Fabio Estevam Cc: Jassi Brar Reviewed-by: Sascha Hauer Signed-off-by: Dong Aisheng Signed-off-by: Shawn Guo --- include/linux/firmware/imx/ipc.h | 59 ++++ include/linux/firmware/imx/sci.h | 16 + include/linux/firmware/imx/types.h | 617 +++++++++++++++++++++++++++++++++++++ 3 files changed, 692 insertions(+) create mode 100644 include/linux/firmware/imx/ipc.h create mode 100644 include/linux/firmware/imx/sci.h create mode 100644 include/linux/firmware/imx/types.h (limited to 'include/linux') diff --git a/include/linux/firmware/imx/ipc.h b/include/linux/firmware/imx/ipc.h new file mode 100644 index 000000000000..6312c8cb084a --- /dev/null +++ b/include/linux/firmware/imx/ipc.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2018 NXP + * + * Header file for the IPC implementation. + */ + +#ifndef _SC_IPC_H +#define _SC_IPC_H + +#include +#include + +#define IMX_SC_RPC_VERSION 1 +#define IMX_SC_RPC_MAX_MSG 8 + +struct imx_sc_ipc; + +enum imx_sc_rpc_svc { + IMX_SC_RPC_SVC_UNKNOWN = 0, + IMX_SC_RPC_SVC_RETURN = 1, + IMX_SC_RPC_SVC_PM = 2, + IMX_SC_RPC_SVC_RM = 3, + IMX_SC_RPC_SVC_TIMER = 5, + IMX_SC_RPC_SVC_PAD = 6, + IMX_SC_RPC_SVC_MISC = 7, + IMX_SC_RPC_SVC_IRQ = 8, + IMX_SC_RPC_SVC_ABORT = 9 +}; + +struct imx_sc_rpc_msg { + uint8_t ver; + uint8_t size; + uint8_t svc; + uint8_t func; +}; + +/* + * This is an function to send an RPC message over an IPC channel. + * It is called by client-side SCFW API function shims. + * + * @param[in] ipc IPC handle + * @param[in,out] msg handle to a message + * @param[in] have_resp response flag + * + * If have_resp is true then this function waits for a response + * and returns the result in msg. + */ +int imx_scu_call_rpc(struct imx_sc_ipc *ipc, void *msg, bool have_resp); + +/* + * This function gets the default ipc handle used by SCU + * + * @param[out] ipc sc ipc handle + * + * @return Returns an error code (0 = success, failed if < 0) + */ +int imx_scu_get_handle(struct imx_sc_ipc **ipc); +#endif /* _SC_IPC_H */ diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h new file mode 100644 index 000000000000..ff3227ad8d7c --- /dev/null +++ b/include/linux/firmware/imx/sci.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2016 Freescale Semiconductor, Inc. + * Copyright 2017~2018 NXP + * + * Header file containing the public System Controller Interface (SCI) + * definitions. + */ + +#ifndef _SC_SCI_H +#define _SC_SCI_H + +#include +#include + +#endif /* _SC_SCI_H */ diff --git a/include/linux/firmware/imx/types.h b/include/linux/firmware/imx/types.h new file mode 100644 index 000000000000..9cbf0c4a6069 --- /dev/null +++ b/include/linux/firmware/imx/types.h @@ -0,0 +1,617 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2016 Freescale Semiconductor, Inc. + * Copyright 2017~2018 NXP + * + * Header file containing types used across multiple service APIs. + */ + +#ifndef _SC_TYPES_H +#define _SC_TYPES_H + +/* + * This type is used to indicate a resource. Resources include peripherals + * and bus masters (but not memory regions). Note items from list should + * never be changed or removed (only added to at the end of the list). + */ +enum imx_sc_rsrc { + IMX_SC_R_A53 = 0, + IMX_SC_R_A53_0 = 1, + IMX_SC_R_A53_1 = 2, + IMX_SC_R_A53_2 = 3, + IMX_SC_R_A53_3 = 4, + IMX_SC_R_A72 = 5, + IMX_SC_R_A72_0 = 6, + IMX_SC_R_A72_1 = 7, + IMX_SC_R_A72_2 = 8, + IMX_SC_R_A72_3 = 9, + IMX_SC_R_CCI = 10, + IMX_SC_R_DB = 11, + IMX_SC_R_DRC_0 = 12, + IMX_SC_R_DRC_1 = 13, + IMX_SC_R_GIC_SMMU = 14, + IMX_SC_R_IRQSTR_M4_0 = 15, + IMX_SC_R_IRQSTR_M4_1 = 16, + IMX_SC_R_SMMU = 17, + IMX_SC_R_GIC = 18, + IMX_SC_R_DC_0_BLIT0 = 19, + IMX_SC_R_DC_0_BLIT1 = 20, + IMX_SC_R_DC_0_BLIT2 = 21, + IMX_SC_R_DC_0_BLIT_OUT = 22, + IMX_SC_R_DC_0_CAPTURE0 = 23, + IMX_SC_R_DC_0_CAPTURE1 = 24, + IMX_SC_R_DC_0_WARP = 25, + IMX_SC_R_DC_0_INTEGRAL0 = 26, + IMX_SC_R_DC_0_INTEGRAL1 = 27, + IMX_SC_R_DC_0_VIDEO0 = 28, + IMX_SC_R_DC_0_VIDEO1 = 29, + IMX_SC_R_DC_0_FRAC0 = 30, + IMX_SC_R_DC_0_FRAC1 = 31, + IMX_SC_R_DC_0 = 32, + IMX_SC_R_GPU_2_PID0 = 33, + IMX_SC_R_DC_0_PLL_0 = 34, + IMX_SC_R_DC_0_PLL_1 = 35, + IMX_SC_R_DC_1_BLIT0 = 36, + IMX_SC_R_DC_1_BLIT1 = 37, + IMX_SC_R_DC_1_BLIT2 = 38, + IMX_SC_R_DC_1_BLIT_OUT = 39, + IMX_SC_R_DC_1_CAPTURE0 = 40, + IMX_SC_R_DC_1_CAPTURE1 = 41, + IMX_SC_R_DC_1_WARP = 42, + IMX_SC_R_DC_1_INTEGRAL0 = 43, + IMX_SC_R_DC_1_INTEGRAL1 = 44, + IMX_SC_R_DC_1_VIDEO0 = 45, + IMX_SC_R_DC_1_VIDEO1 = 46, + IMX_SC_R_DC_1_FRAC0 = 47, + IMX_SC_R_DC_1_FRAC1 = 48, + IMX_SC_R_DC_1 = 49, + IMX_SC_R_GPU_3_PID0 = 50, + IMX_SC_R_DC_1_PLL_0 = 51, + IMX_SC_R_DC_1_PLL_1 = 52, + IMX_SC_R_SPI_0 = 53, + IMX_SC_R_SPI_1 = 54, + IMX_SC_R_SPI_2 = 55, + IMX_SC_R_SPI_3 = 56, + IMX_SC_R_UART_0 = 57, + IMX_SC_R_UART_1 = 58, + IMX_SC_R_UART_2 = 59, + IMX_SC_R_UART_3 = 60, + IMX_SC_R_UART_4 = 61, + IMX_SC_R_EMVSIM_0 = 62, + IMX_SC_R_EMVSIM_1 = 63, + IMX_SC_R_DMA_0_CH0 = 64, + IMX_SC_R_DMA_0_CH1 = 65, + IMX_SC_R_DMA_0_CH2 = 66, + IMX_SC_R_DMA_0_CH3 = 67, + IMX_SC_R_DMA_0_CH4 = 68, + IMX_SC_R_DMA_0_CH5 = 69, + IMX_SC_R_DMA_0_CH6 = 70, + IMX_SC_R_DMA_0_CH7 = 71, + IMX_SC_R_DMA_0_CH8 = 72, + IMX_SC_R_DMA_0_CH9 = 73, + IMX_SC_R_DMA_0_CH10 = 74, + IMX_SC_R_DMA_0_CH11 = 75, + IMX_SC_R_DMA_0_CH12 = 76, + IMX_SC_R_DMA_0_CH13 = 77, + IMX_SC_R_DMA_0_CH14 = 78, + IMX_SC_R_DMA_0_CH15 = 79, + IMX_SC_R_DMA_0_CH16 = 80, + IMX_SC_R_DMA_0_CH17 = 81, + IMX_SC_R_DMA_0_CH18 = 82, + IMX_SC_R_DMA_0_CH19 = 83, + IMX_SC_R_DMA_0_CH20 = 84, + IMX_SC_R_DMA_0_CH21 = 85, + IMX_SC_R_DMA_0_CH22 = 86, + IMX_SC_R_DMA_0_CH23 = 87, + IMX_SC_R_DMA_0_CH24 = 88, + IMX_SC_R_DMA_0_CH25 = 89, + IMX_SC_R_DMA_0_CH26 = 90, + IMX_SC_R_DMA_0_CH27 = 91, + IMX_SC_R_DMA_0_CH28 = 92, + IMX_SC_R_DMA_0_CH29 = 93, + IMX_SC_R_DMA_0_CH30 = 94, + IMX_SC_R_DMA_0_CH31 = 95, + IMX_SC_R_I2C_0 = 96, + IMX_SC_R_I2C_1 = 97, + IMX_SC_R_I2C_2 = 98, + IMX_SC_R_I2C_3 = 99, + IMX_SC_R_I2C_4 = 100, + IMX_SC_R_ADC_0 = 101, + IMX_SC_R_ADC_1 = 102, + IMX_SC_R_FTM_0 = 103, + IMX_SC_R_FTM_1 = 104, + IMX_SC_R_CAN_0 = 105, + IMX_SC_R_CAN_1 = 106, + IMX_SC_R_CAN_2 = 107, + IMX_SC_R_DMA_1_CH0 = 108, + IMX_SC_R_DMA_1_CH1 = 109, + IMX_SC_R_DMA_1_CH2 = 110, + IMX_SC_R_DMA_1_CH3 = 111, + IMX_SC_R_DMA_1_CH4 = 112, + IMX_SC_R_DMA_1_CH5 = 113, + IMX_SC_R_DMA_1_CH6 = 114, + IMX_SC_R_DMA_1_CH7 = 115, + IMX_SC_R_DMA_1_CH8 = 116, + IMX_SC_R_DMA_1_CH9 = 117, + IMX_SC_R_DMA_1_CH10 = 118, + IMX_SC_R_DMA_1_CH11 = 119, + IMX_SC_R_DMA_1_CH12 = 120, + IMX_SC_R_DMA_1_CH13 = 121, + IMX_SC_R_DMA_1_CH14 = 122, + IMX_SC_R_DMA_1_CH15 = 123, + IMX_SC_R_DMA_1_CH16 = 124, + IMX_SC_R_DMA_1_CH17 = 125, + IMX_SC_R_DMA_1_CH18 = 126, + IMX_SC_R_DMA_1_CH19 = 127, + IMX_SC_R_DMA_1_CH20 = 128, + IMX_SC_R_DMA_1_CH21 = 129, + IMX_SC_R_DMA_1_CH22 = 130, + IMX_SC_R_DMA_1_CH23 = 131, + IMX_SC_R_DMA_1_CH24 = 132, + IMX_SC_R_DMA_1_CH25 = 133, + IMX_SC_R_DMA_1_CH26 = 134, + IMX_SC_R_DMA_1_CH27 = 135, + IMX_SC_R_DMA_1_CH28 = 136, + IMX_SC_R_DMA_1_CH29 = 137, + IMX_SC_R_DMA_1_CH30 = 138, + IMX_SC_R_DMA_1_CH31 = 139, + IMX_SC_R_UNUSED1 = 140, + IMX_SC_R_UNUSED2 = 141, + IMX_SC_R_UNUSED3 = 142, + IMX_SC_R_UNUSED4 = 143, + IMX_SC_R_GPU_0_PID0 = 144, + IMX_SC_R_GPU_0_PID1 = 145, + IMX_SC_R_GPU_0_PID2 = 146, + IMX_SC_R_GPU_0_PID3 = 147, + IMX_SC_R_GPU_1_PID0 = 148, + IMX_SC_R_GPU_1_PID1 = 149, + IMX_SC_R_GPU_1_PID2 = 150, + IMX_SC_R_GPU_1_PID3 = 151, + IMX_SC_R_PCIE_A = 152, + IMX_SC_R_SERDES_0 = 153, + IMX_SC_R_MATCH_0 = 154, + IMX_SC_R_MATCH_1 = 155, + IMX_SC_R_MATCH_2 = 156, + IMX_SC_R_MATCH_3 = 157, + IMX_SC_R_MATCH_4 = 158, + IMX_SC_R_MATCH_5 = 159, + IMX_SC_R_MATCH_6 = 160, + IMX_SC_R_MATCH_7 = 161, + IMX_SC_R_MATCH_8 = 162, + IMX_SC_R_MATCH_9 = 163, + IMX_SC_R_MATCH_10 = 164, + IMX_SC_R_MATCH_11 = 165, + IMX_SC_R_MATCH_12 = 166, + IMX_SC_R_MATCH_13 = 167, + IMX_SC_R_MATCH_14 = 168, + IMX_SC_R_PCIE_B = 169, + IMX_SC_R_SATA_0 = 170, + IMX_SC_R_SERDES_1 = 171, + IMX_SC_R_HSIO_GPIO = 172, + IMX_SC_R_MATCH_15 = 173, + IMX_SC_R_MATCH_16 = 174, + IMX_SC_R_MATCH_17 = 175, + IMX_SC_R_MATCH_18 = 176, + IMX_SC_R_MATCH_19 = 177, + IMX_SC_R_MATCH_20 = 178, + IMX_SC_R_MATCH_21 = 179, + IMX_SC_R_MATCH_22 = 180, + IMX_SC_R_MATCH_23 = 181, + IMX_SC_R_MATCH_24 = 182, + IMX_SC_R_MATCH_25 = 183, + IMX_SC_R_MATCH_26 = 184, + IMX_SC_R_MATCH_27 = 185, + IMX_SC_R_MATCH_28 = 186, + IMX_SC_R_LCD_0 = 187, + IMX_SC_R_LCD_0_PWM_0 = 188, + IMX_SC_R_LCD_0_I2C_0 = 189, + IMX_SC_R_LCD_0_I2C_1 = 190, + IMX_SC_R_PWM_0 = 191, + IMX_SC_R_PWM_1 = 192, + IMX_SC_R_PWM_2 = 193, + IMX_SC_R_PWM_3 = 194, + IMX_SC_R_PWM_4 = 195, + IMX_SC_R_PWM_5 = 196, + IMX_SC_R_PWM_6 = 197, + IMX_SC_R_PWM_7 = 198, + IMX_SC_R_GPIO_0 = 199, + IMX_SC_R_GPIO_1 = 200, + IMX_SC_R_GPIO_2 = 201, + IMX_SC_R_GPIO_3 = 202, + IMX_SC_R_GPIO_4 = 203, + IMX_SC_R_GPIO_5 = 204, + IMX_SC_R_GPIO_6 = 205, + IMX_SC_R_GPIO_7 = 206, + IMX_SC_R_GPT_0 = 207, + IMX_SC_R_GPT_1 = 208, + IMX_SC_R_GPT_2 = 209, + IMX_SC_R_GPT_3 = 210, + IMX_SC_R_GPT_4 = 211, + IMX_SC_R_KPP = 212, + IMX_SC_R_MU_0A = 213, + IMX_SC_R_MU_1A = 214, + IMX_SC_R_MU_2A = 215, + IMX_SC_R_MU_3A = 216, + IMX_SC_R_MU_4A = 217, + IMX_SC_R_MU_5A = 218, + IMX_SC_R_MU_6A = 219, + IMX_SC_R_MU_7A = 220, + IMX_SC_R_MU_8A = 221, + IMX_SC_R_MU_9A = 222, + IMX_SC_R_MU_10A = 223, + IMX_SC_R_MU_11A = 224, + IMX_SC_R_MU_12A = 225, + IMX_SC_R_MU_13A = 226, + IMX_SC_R_MU_5B = 227, + IMX_SC_R_MU_6B = 228, + IMX_SC_R_MU_7B = 229, + IMX_SC_R_MU_8B = 230, + IMX_SC_R_MU_9B = 231, + IMX_SC_R_MU_10B = 232, + IMX_SC_R_MU_11B = 233, + IMX_SC_R_MU_12B = 234, + IMX_SC_R_MU_13B = 235, + IMX_SC_R_ROM_0 = 236, + IMX_SC_R_FSPI_0 = 237, + IMX_SC_R_FSPI_1 = 238, + IMX_SC_R_IEE = 239, + IMX_SC_R_IEE_R0 = 240, + IMX_SC_R_IEE_R1 = 241, + IMX_SC_R_IEE_R2 = 242, + IMX_SC_R_IEE_R3 = 243, + IMX_SC_R_IEE_R4 = 244, + IMX_SC_R_IEE_R5 = 245, + IMX_SC_R_IEE_R6 = 246, + IMX_SC_R_IEE_R7 = 247, + IMX_SC_R_SDHC_0 = 248, + IMX_SC_R_SDHC_1 = 249, + IMX_SC_R_SDHC_2 = 250, + IMX_SC_R_ENET_0 = 251, + IMX_SC_R_ENET_1 = 252, + IMX_SC_R_MLB_0 = 253, + IMX_SC_R_DMA_2_CH0 = 254, + IMX_SC_R_DMA_2_CH1 = 255, + IMX_SC_R_DMA_2_CH2 = 256, + IMX_SC_R_DMA_2_CH3 = 257, + IMX_SC_R_DMA_2_CH4 = 258, + IMX_SC_R_USB_0 = 259, + IMX_SC_R_USB_1 = 260, + IMX_SC_R_USB_0_PHY = 261, + IMX_SC_R_USB_2 = 262, + IMX_SC_R_USB_2_PHY = 263, + IMX_SC_R_DTCP = 264, + IMX_SC_R_NAND = 265, + IMX_SC_R_LVDS_0 = 266, + IMX_SC_R_LVDS_0_PWM_0 = 267, + IMX_SC_R_LVDS_0_I2C_0 = 268, + IMX_SC_R_LVDS_0_I2C_1 = 269, + IMX_SC_R_LVDS_1 = 270, + IMX_SC_R_LVDS_1_PWM_0 = 271, + IMX_SC_R_LVDS_1_I2C_0 = 272, + IMX_SC_R_LVDS_1_I2C_1 = 273, + IMX_SC_R_LVDS_2 = 274, + IMX_SC_R_LVDS_2_PWM_0 = 275, + IMX_SC_R_LVDS_2_I2C_0 = 276, + IMX_SC_R_LVDS_2_I2C_1 = 277, + IMX_SC_R_M4_0_PID0 = 278, + IMX_SC_R_M4_0_PID1 = 279, + IMX_SC_R_M4_0_PID2 = 280, + IMX_SC_R_M4_0_PID3 = 281, + IMX_SC_R_M4_0_PID4 = 282, + IMX_SC_R_M4_0_RGPIO = 283, + IMX_SC_R_M4_0_SEMA42 = 284, + IMX_SC_R_M4_0_TPM = 285, + IMX_SC_R_M4_0_PIT = 286, + IMX_SC_R_M4_0_UART = 287, + IMX_SC_R_M4_0_I2C = 288, + IMX_SC_R_M4_0_INTMUX = 289, + IMX_SC_R_M4_0_SIM = 290, + IMX_SC_R_M4_0_WDOG = 291, + IMX_SC_R_M4_0_MU_0B = 292, + IMX_SC_R_M4_0_MU_0A0 = 293, + IMX_SC_R_M4_0_MU_0A1 = 294, + IMX_SC_R_M4_0_MU_0A2 = 295, + IMX_SC_R_M4_0_MU_0A3 = 296, + IMX_SC_R_M4_0_MU_1A = 297, + IMX_SC_R_M4_1_PID0 = 298, + IMX_SC_R_M4_1_PID1 = 299, + IMX_SC_R_M4_1_PID2 = 300, + IMX_SC_R_M4_1_PID3 = 301, + IMX_SC_R_M4_1_PID4 = 302, + IMX_SC_R_M4_1_RGPIO = 303, + IMX_SC_R_M4_1_SEMA42 = 304, + IMX_SC_R_M4_1_TPM = 305, + IMX_SC_R_M4_1_PIT = 306, + IMX_SC_R_M4_1_UART = 307, + IMX_SC_R_M4_1_I2C = 308, + IMX_SC_R_M4_1_INTMUX = 309, + IMX_SC_R_M4_1_SIM = 310, + IMX_SC_R_M4_1_WDOG = 311, + IMX_SC_R_M4_1_MU_0B = 312, + IMX_SC_R_M4_1_MU_0A0 = 313, + IMX_SC_R_M4_1_MU_0A1 = 314, + IMX_SC_R_M4_1_MU_0A2 = 315, + IMX_SC_R_M4_1_MU_0A3 = 316, + IMX_SC_R_M4_1_MU_1A = 317, + IMX_SC_R_SAI_0 = 318, + IMX_SC_R_SAI_1 = 319, + IMX_SC_R_SAI_2 = 320, + IMX_SC_R_IRQSTR_SCU2 = 321, + IMX_SC_R_IRQSTR_DSP = 322, + IMX_SC_R_UNUSED5 = 323, + IMX_SC_R_UNUSED6 = 324, + IMX_SC_R_AUDIO_PLL_0 = 325, + IMX_SC_R_PI_0 = 326, + IMX_SC_R_PI_0_PWM_0 = 327, + IMX_SC_R_PI_0_PWM_1 = 328, + IMX_SC_R_PI_0_I2C_0 = 329, + IMX_SC_R_PI_0_PLL = 330, + IMX_SC_R_PI_1 = 331, + IMX_SC_R_PI_1_PWM_0 = 332, + IMX_SC_R_PI_1_PWM_1 = 333, + IMX_SC_R_PI_1_I2C_0 = 334, + IMX_SC_R_PI_1_PLL = 335, + IMX_SC_R_SC_PID0 = 336, + IMX_SC_R_SC_PID1 = 337, + IMX_SC_R_SC_PID2 = 338, + IMX_SC_R_SC_PID3 = 339, + IMX_SC_R_SC_PID4 = 340, + IMX_SC_R_SC_SEMA42 = 341, + IMX_SC_R_SC_TPM = 342, + IMX_SC_R_SC_PIT = 343, + IMX_SC_R_SC_UART = 344, + IMX_SC_R_SC_I2C = 345, + IMX_SC_R_SC_MU_0B = 346, + IMX_SC_R_SC_MU_0A0 = 347, + IMX_SC_R_SC_MU_0A1 = 348, + IMX_SC_R_SC_MU_0A2 = 349, + IMX_SC_R_SC_MU_0A3 = 350, + IMX_SC_R_SC_MU_1A = 351, + IMX_SC_R_SYSCNT_RD = 352, + IMX_SC_R_SYSCNT_CMP = 353, + IMX_SC_R_DEBUG = 354, + IMX_SC_R_SYSTEM = 355, + IMX_SC_R_SNVS = 356, + IMX_SC_R_OTP = 357, + IMX_SC_R_VPU_PID0 = 358, + IMX_SC_R_VPU_PID1 = 359, + IMX_SC_R_VPU_PID2 = 360, + IMX_SC_R_VPU_PID3 = 361, + IMX_SC_R_VPU_PID4 = 362, + IMX_SC_R_VPU_PID5 = 363, + IMX_SC_R_VPU_PID6 = 364, + IMX_SC_R_VPU_PID7 = 365, + IMX_SC_R_VPU_UART = 366, + IMX_SC_R_VPUCORE = 367, + IMX_SC_R_VPUCORE_0 = 368, + IMX_SC_R_VPUCORE_1 = 369, + IMX_SC_R_VPUCORE_2 = 370, + IMX_SC_R_VPUCORE_3 = 371, + IMX_SC_R_DMA_4_CH0 = 372, + IMX_SC_R_DMA_4_CH1 = 373, + IMX_SC_R_DMA_4_CH2 = 374, + IMX_SC_R_DMA_4_CH3 = 375, + IMX_SC_R_DMA_4_CH4 = 376, + IMX_SC_R_ISI_CH0 = 377, + IMX_SC_R_ISI_CH1 = 378, + IMX_SC_R_ISI_CH2 = 379, + IMX_SC_R_ISI_CH3 = 380, + IMX_SC_R_ISI_CH4 = 381, + IMX_SC_R_ISI_CH5 = 382, + IMX_SC_R_ISI_CH6 = 383, + IMX_SC_R_ISI_CH7 = 384, + IMX_SC_R_MJPEG_DEC_S0 = 385, + IMX_SC_R_MJPEG_DEC_S1 = 386, + IMX_SC_R_MJPEG_DEC_S2 = 387, + IMX_SC_R_MJPEG_DEC_S3 = 388, + IMX_SC_R_MJPEG_ENC_S0 = 389, + IMX_SC_R_MJPEG_ENC_S1 = 390, + IMX_SC_R_MJPEG_ENC_S2 = 391, + IMX_SC_R_MJPEG_ENC_S3 = 392, + IMX_SC_R_MIPI_0 = 393, + IMX_SC_R_MIPI_0_PWM_0 = 394, + IMX_SC_R_MIPI_0_I2C_0 = 395, + IMX_SC_R_MIPI_0_I2C_1 = 396, + IMX_SC_R_MIPI_1 = 397, + IMX_SC_R_MIPI_1_PWM_0 = 398, + IMX_SC_R_MIPI_1_I2C_0 = 399, + IMX_SC_R_MIPI_1_I2C_1 = 400, + IMX_SC_R_CSI_0 = 401, + IMX_SC_R_CSI_0_PWM_0 = 402, + IMX_SC_R_CSI_0_I2C_0 = 403, + IMX_SC_R_CSI_1 = 404, + IMX_SC_R_CSI_1_PWM_0 = 405, + IMX_SC_R_CSI_1_I2C_0 = 406, + IMX_SC_R_HDMI = 407, + IMX_SC_R_HDMI_I2S = 408, + IMX_SC_R_HDMI_I2C_0 = 409, + IMX_SC_R_HDMI_PLL_0 = 410, + IMX_SC_R_HDMI_RX = 411, + IMX_SC_R_HDMI_RX_BYPASS = 412, + IMX_SC_R_HDMI_RX_I2C_0 = 413, + IMX_SC_R_ASRC_0 = 414, + IMX_SC_R_ESAI_0 = 415, + IMX_SC_R_SPDIF_0 = 416, + IMX_SC_R_SPDIF_1 = 417, + IMX_SC_R_SAI_3 = 418, + IMX_SC_R_SAI_4 = 419, + IMX_SC_R_SAI_5 = 420, + IMX_SC_R_GPT_5 = 421, + IMX_SC_R_GPT_6 = 422, + IMX_SC_R_GPT_7 = 423, + IMX_SC_R_GPT_8 = 424, + IMX_SC_R_GPT_9 = 425, + IMX_SC_R_GPT_10 = 426, + IMX_SC_R_DMA_2_CH5 = 427, + IMX_SC_R_DMA_2_CH6 = 428, + IMX_SC_R_DMA_2_CH7 = 429, + IMX_SC_R_DMA_2_CH8 = 430, + IMX_SC_R_DMA_2_CH9 = 431, + IMX_SC_R_DMA_2_CH10 = 432, + IMX_SC_R_DMA_2_CH11 = 433, + IMX_SC_R_DMA_2_CH12 = 434, + IMX_SC_R_DMA_2_CH13 = 435, + IMX_SC_R_DMA_2_CH14 = 436, + IMX_SC_R_DMA_2_CH15 = 437, + IMX_SC_R_DMA_2_CH16 = 438, + IMX_SC_R_DMA_2_CH17 = 439, + IMX_SC_R_DMA_2_CH18 = 440, + IMX_SC_R_DMA_2_CH19 = 441, + IMX_SC_R_DMA_2_CH20 = 442, + IMX_SC_R_DMA_2_CH21 = 443, + IMX_SC_R_DMA_2_CH22 = 444, + IMX_SC_R_DMA_2_CH23 = 445, + IMX_SC_R_DMA_2_CH24 = 446, + IMX_SC_R_DMA_2_CH25 = 447, + IMX_SC_R_DMA_2_CH26 = 448, + IMX_SC_R_DMA_2_CH27 = 449, + IMX_SC_R_DMA_2_CH28 = 450, + IMX_SC_R_DMA_2_CH29 = 451, + IMX_SC_R_DMA_2_CH30 = 452, + IMX_SC_R_DMA_2_CH31 = 453, + IMX_SC_R_ASRC_1 = 454, + IMX_SC_R_ESAI_1 = 455, + IMX_SC_R_SAI_6 = 456, + IMX_SC_R_SAI_7 = 457, + IMX_SC_R_AMIX = 458, + IMX_SC_R_MQS_0 = 459, + IMX_SC_R_DMA_3_CH0 = 460, + IMX_SC_R_DMA_3_CH1 = 461, + IMX_SC_R_DMA_3_CH2 = 462, + IMX_SC_R_DMA_3_CH3 = 463, + IMX_SC_R_DMA_3_CH4 = 464, + IMX_SC_R_DMA_3_CH5 = 465, + IMX_SC_R_DMA_3_CH6 = 466, + IMX_SC_R_DMA_3_CH7 = 467, + IMX_SC_R_DMA_3_CH8 = 468, + IMX_SC_R_DMA_3_CH9 = 469, + IMX_SC_R_DMA_3_CH10 = 470, + IMX_SC_R_DMA_3_CH11 = 471, + IMX_SC_R_DMA_3_CH12 = 472, + IMX_SC_R_DMA_3_CH13 = 473, + IMX_SC_R_DMA_3_CH14 = 474, + IMX_SC_R_DMA_3_CH15 = 475, + IMX_SC_R_DMA_3_CH16 = 476, + IMX_SC_R_DMA_3_CH17 = 477, + IMX_SC_R_DMA_3_CH18 = 478, + IMX_SC_R_DMA_3_CH19 = 479, + IMX_SC_R_DMA_3_CH20 = 480, + IMX_SC_R_DMA_3_CH21 = 481, + IMX_SC_R_DMA_3_CH22 = 482, + IMX_SC_R_DMA_3_CH23 = 483, + IMX_SC_R_DMA_3_CH24 = 484, + IMX_SC_R_DMA_3_CH25 = 485, + IMX_SC_R_DMA_3_CH26 = 486, + IMX_SC_R_DMA_3_CH27 = 487, + IMX_SC_R_DMA_3_CH28 = 488, + IMX_SC_R_DMA_3_CH29 = 489, + IMX_SC_R_DMA_3_CH30 = 490, + IMX_SC_R_DMA_3_CH31 = 491, + IMX_SC_R_AUDIO_PLL_1 = 492, + IMX_SC_R_AUDIO_CLK_0 = 493, + IMX_SC_R_AUDIO_CLK_1 = 494, + IMX_SC_R_MCLK_OUT_0 = 495, + IMX_SC_R_MCLK_OUT_1 = 496, + IMX_SC_R_PMIC_0 = 497, + IMX_SC_R_PMIC_1 = 498, + IMX_SC_R_SECO = 499, + IMX_SC_R_CAAM_JR1 = 500, + IMX_SC_R_CAAM_JR2 = 501, + IMX_SC_R_CAAM_JR3 = 502, + IMX_SC_R_SECO_MU_2 = 503, + IMX_SC_R_SECO_MU_3 = 504, + IMX_SC_R_SECO_MU_4 = 505, + IMX_SC_R_HDMI_RX_PWM_0 = 506, + IMX_SC_R_A35 = 507, + IMX_SC_R_A35_0 = 508, + IMX_SC_R_A35_1 = 509, + IMX_SC_R_A35_2 = 510, + IMX_SC_R_A35_3 = 511, + IMX_SC_R_DSP = 512, + IMX_SC_R_DSP_RAM = 513, + IMX_SC_R_CAAM_JR1_OUT = 514, + IMX_SC_R_CAAM_JR2_OUT = 515, + IMX_SC_R_CAAM_JR3_OUT = 516, + IMX_SC_R_VPU_DEC_0 = 517, + IMX_SC_R_VPU_ENC_0 = 518, + IMX_SC_R_CAAM_JR0 = 519, + IMX_SC_R_CAAM_JR0_OUT = 520, + IMX_SC_R_PMIC_2 = 521, + IMX_SC_R_DBLOGIC = 522, + IMX_SC_R_HDMI_PLL_1 = 523, + IMX_SC_R_BOARD_R0 = 524, + IMX_SC_R_BOARD_R1 = 525, + IMX_SC_R_BOARD_R2 = 526, + IMX_SC_R_BOARD_R3 = 527, + IMX_SC_R_BOARD_R4 = 528, + IMX_SC_R_BOARD_R5 = 529, + IMX_SC_R_BOARD_R6 = 530, + IMX_SC_R_BOARD_R7 = 531, + IMX_SC_R_MJPEG_DEC_MP = 532, + IMX_SC_R_MJPEG_ENC_MP = 533, + IMX_SC_R_VPU_TS_0 = 534, + IMX_SC_R_VPU_MU_0 = 535, + IMX_SC_R_VPU_MU_1 = 536, + IMX_SC_R_VPU_MU_2 = 537, + IMX_SC_R_VPU_MU_3 = 538, + IMX_SC_R_VPU_ENC_1 = 539, + IMX_SC_R_VPU = 540, + IMX_SC_R_LAST +}; + +/* NOTE - please add by replacing some of the UNUSED from above! */ + +/* + * This type is used to indicate a control. + */ +enum imx_sc_ctrl { + IMX_SC_C_TEMP = 0, + IMX_SC_C_TEMP_HI = 1, + IMX_SC_C_TEMP_LOW = 2, + IMX_SC_C_PXL_LINK_MST1_ADDR = 3, + IMX_SC_C_PXL_LINK_MST2_ADDR = 4, + IMX_SC_C_PXL_LINK_MST_ENB = 5, + IMX_SC_C_PXL_LINK_MST1_ENB = 6, + IMX_SC_C_PXL_LINK_MST2_ENB = 7, + IMX_SC_C_PXL_LINK_SLV1_ADDR = 8, + IMX_SC_C_PXL_LINK_SLV2_ADDR = 9, + IMX_SC_C_PXL_LINK_MST_VLD = 10, + IMX_SC_C_PXL_LINK_MST1_VLD = 11, + IMX_SC_C_PXL_LINK_MST2_VLD = 12, + IMX_SC_C_SINGLE_MODE = 13, + IMX_SC_C_ID = 14, + IMX_SC_C_PXL_CLK_POLARITY = 15, + IMX_SC_C_LINESTATE = 16, + IMX_SC_C_PCIE_G_RST = 17, + IMX_SC_C_PCIE_BUTTON_RST = 18, + IMX_SC_C_PCIE_PERST = 19, + IMX_SC_C_PHY_RESET = 20, + IMX_SC_C_PXL_LINK_RATE_CORRECTION = 21, + IMX_SC_C_PANIC = 22, + IMX_SC_C_PRIORITY_GROUP = 23, + IMX_SC_C_TXCLK = 24, + IMX_SC_C_CLKDIV = 25, + IMX_SC_C_DISABLE_50 = 26, + IMX_SC_C_DISABLE_125 = 27, + IMX_SC_C_SEL_125 = 28, + IMX_SC_C_MODE = 29, + IMX_SC_C_SYNC_CTRL0 = 30, + IMX_SC_C_KACHUNK_CNT = 31, + IMX_SC_C_KACHUNK_SEL = 32, + IMX_SC_C_SYNC_CTRL1 = 33, + IMX_SC_C_DPI_RESET = 34, + IMX_SC_C_MIPI_RESET = 35, + IMX_SC_C_DUAL_MODE = 36, + IMX_SC_C_VOLTAGE = 37, + IMX_SC_C_PXL_LINK_SEL = 38, + IMX_SC_C_OFS_SEL = 39, + IMX_SC_C_OFS_AUDIO = 40, + IMX_SC_C_OFS_PERIPH = 41, + IMX_SC_C_OFS_IRQ = 42, + IMX_SC_C_RST0 = 43, + IMX_SC_C_RST1 = 44, + IMX_SC_C_SEL0 = 45, + IMX_SC_C_LAST +}; + +#endif /* _SC_TYPES_H */ -- cgit v1.2.3 From 15e1f2bc8b3b2d238b9e06b128d4a09d28f11733 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Sun, 7 Oct 2018 21:04:43 +0800 Subject: firmware: imx: add misc svc support Add SCU MISC SVC support which provides misc control get/set functions. Cc: Shawn Guo Reviewed-by: Sascha Hauer Signed-off-by: Dong Aisheng Signed-off-by: Shawn Guo --- include/linux/firmware/imx/sci.h | 1 + include/linux/firmware/imx/svc/misc.h | 55 +++++++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) create mode 100644 include/linux/firmware/imx/svc/misc.h (limited to 'include/linux') diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h index ff3227ad8d7c..29ada609de03 100644 --- a/include/linux/firmware/imx/sci.h +++ b/include/linux/firmware/imx/sci.h @@ -13,4 +13,5 @@ #include #include +#include #endif /* _SC_SCI_H */ diff --git a/include/linux/firmware/imx/svc/misc.h b/include/linux/firmware/imx/svc/misc.h new file mode 100644 index 000000000000..e21c49aba92f --- /dev/null +++ b/include/linux/firmware/imx/svc/misc.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2016 Freescale Semiconductor, Inc. + * Copyright 2017~2018 NXP + * + * Header file containing the public API for the System Controller (SC) + * Miscellaneous (MISC) function. + * + * MISC_SVC (SVC) Miscellaneous Service + * + * Module for the Miscellaneous (MISC) service. + */ + +#ifndef _SC_MISC_API_H +#define _SC_MISC_API_H + +#include + +/* + * This type is used to indicate RPC MISC function calls. + */ +enum imx_misc_func { + IMX_SC_MISC_FUNC_UNKNOWN = 0, + IMX_SC_MISC_FUNC_SET_CONTROL = 1, + IMX_SC_MISC_FUNC_GET_CONTROL = 2, + IMX_SC_MISC_FUNC_SET_MAX_DMA_GROUP = 4, + IMX_SC_MISC_FUNC_SET_DMA_GROUP = 5, + IMX_SC_MISC_FUNC_SECO_IMAGE_LOAD = 8, + IMX_SC_MISC_FUNC_SECO_AUTHENTICATE = 9, + IMX_SC_MISC_FUNC_DEBUG_OUT = 10, + IMX_SC_MISC_FUNC_WAVEFORM_CAPTURE = 6, + IMX_SC_MISC_FUNC_BUILD_INFO = 15, + IMX_SC_MISC_FUNC_UNIQUE_ID = 19, + IMX_SC_MISC_FUNC_SET_ARI = 3, + IMX_SC_MISC_FUNC_BOOT_STATUS = 7, + IMX_SC_MISC_FUNC_BOOT_DONE = 14, + IMX_SC_MISC_FUNC_OTP_FUSE_READ = 11, + IMX_SC_MISC_FUNC_OTP_FUSE_WRITE = 17, + IMX_SC_MISC_FUNC_SET_TEMP = 12, + IMX_SC_MISC_FUNC_GET_TEMP = 13, + IMX_SC_MISC_FUNC_GET_BOOT_DEV = 16, + IMX_SC_MISC_FUNC_GET_BUTTON_STATUS = 18, +}; + +/* + * Control Functions + */ + +int imx_sc_misc_set_control(struct imx_sc_ipc *ipc, u32 resource, + u8 ctrl, u32 val); + +int imx_sc_misc_get_control(struct imx_sc_ipc *ipc, u32 resource, + u8 ctrl, u32 *val); + +#endif /* _SC_MISC_API_H */ -- cgit v1.2.3 From 4a19edb60d0203cd5bf95a8b46ea8f63fd41194c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 7 Oct 2018 20:16:22 -0700 Subject: netlink: Pass extack to dump handlers Declare extack in netlink_dump and pass to dump handlers via netlink_callback. Add any extack message after the dump_done_errno allowing error messages to be returned. This will be useful when strict checking is done on dump requests, returning why the dump fails EINVAL. Signed-off-by: David Ahern Acked-by: Christian Brauner Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 71f121b66ca8..88c8a2d83eb3 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -176,6 +176,7 @@ struct netlink_callback { void *data; /* the module that dump function belong to */ struct module *module; + struct netlink_ext_ack *extack; u16 family; u16 min_dump_alloc; unsigned int prev_seq, seq; -- cgit v1.2.3 From 89d35528d17d25819a755a2b52931e911baebc66 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 7 Oct 2018 20:16:27 -0700 Subject: netlink: Add new socket option to enable strict checking on dumps Add a new socket option, NETLINK_DUMP_STRICT_CHK, that userspace can use via setsockopt to request strict checking of headers and attributes on dump requests. To get dump features such as kernel side filtering based on data in the header or attributes appended to the dump request, userspace must call setsockopt() for NETLINK_DUMP_STRICT_CHK and a non-zero value. Since the netlink sock and its flags are private to the af_netlink code, the strict checking flag is passed to dump handlers via a flag in the netlink_callback struct. For old userspace on new kernel there is no impact as all of the data checks in later patches are wrapped in a check on the new strict flag. For new userspace on old kernel, the setsockopt will fail and even if new userspace sets data in the headers and appended attributes the kernel will silently ignore it. Moving forward when the setsockopt succeeds, the new userspace on old kernel means the dump request can pass an attribute the kernel does not understand. The dump will then fail as the older kernel does not understand it. New userspace on new kernel setting the socket option gets the benefit of the improved data dump. Kernel side the NETLINK_DUMP_STRICT_CHK uapi is converted to a generic NETLINK_F_STRICT_CHK flag which can potentially be leveraged for tighter checking on the NEW, DEL, and SET commands. Signed-off-by: David Ahern Acked-by: Christian Brauner Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 88c8a2d83eb3..72580f1a72a2 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -179,6 +179,7 @@ struct netlink_callback { struct netlink_ext_ack *extack; u16 family; u16 min_dump_alloc; + bool strict_check; unsigned int prev_seq, seq; long args[6]; }; -- cgit v1.2.3 From 5390a8df769ec9ba9c995191bb0867430f602ebb Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Tue, 11 Sep 2018 18:40:06 +0300 Subject: mtd: spi-nor: add support to non-uniform SFDP SPI NOR flash memories Based on Cyrille Pitchen's patch https://lkml.org/lkml/2017/3/22/935. This patch is a transitional patch in introducing the support of SFDP SPI memories with non-uniform erase sizes like Spansion s25fs512s. Non-uniform erase maps will be used later when initialized based on the SFDP data. Introduce the memory erase map which splits the memory array into one or many erase regions. Each erase region supports up to 4 erase types, as defined by the JEDEC JESD216B (SFDP) specification. To be backward compatible, the erase map of uniform SPI NOR flash memories is initialized so it contains only one erase region and this erase region supports only one erase command. Hence a single size is used to erase any sector/block of the memory. Besides, since the algorithm used to erase sectors on non-uniform SPI NOR flash memories is quite expensive, when possible, the erase map is tuned to come back to the uniform case. The 'erase with the best command, move forward and repeat' approach was suggested by Cristian Birsan in a brainstorm session, so: Suggested-by: Cristian Birsan Signed-off-by: Tudor Ambarus Reviewed-by: Marek Vasut Signed-off-by: Boris Brezillon --- include/linux/mtd/spi-nor.h | 107 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 107 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index c922e97f205a..894cbf88bf2e 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -238,6 +238,94 @@ enum spi_nor_option_flags { SNOR_F_BROKEN_RESET = BIT(6), }; +/** + * struct spi_nor_erase_type - Structure to describe a SPI NOR erase type + * @size: the size of the sector/block erased by the erase type. + * JEDEC JESD216B imposes erase sizes to be a power of 2. + * @size_shift: @size is a power of 2, the shift is stored in + * @size_shift. + * @size_mask: the size mask based on @size_shift. + * @opcode: the SPI command op code to erase the sector/block. + * @idx: Erase Type index as sorted in the Basic Flash Parameter + * Table. It will be used to synchronize the supported + * Erase Types with the ones identified in the SFDP + * optional tables. + */ +struct spi_nor_erase_type { + u32 size; + u32 size_shift; + u32 size_mask; + u8 opcode; + u8 idx; +}; + +/** + * struct spi_nor_erase_command - Used for non-uniform erases + * The structure is used to describe a list of erase commands to be executed + * once we validate that the erase can be performed. The elements in the list + * are run-length encoded. + * @list: for inclusion into the list of erase commands. + * @count: how many times the same erase command should be + * consecutively used. + * @size: the size of the sector/block erased by the command. + * @opcode: the SPI command op code to erase the sector/block. + */ +struct spi_nor_erase_command { + struct list_head list; + u32 count; + u32 size; + u8 opcode; +}; + +/** + * struct spi_nor_erase_region - Structure to describe a SPI NOR erase region + * @offset: the offset in the data array of erase region start. + * LSB bits are used as a bitmask encoding flags to + * determine if this region is overlaid, if this region is + * the last in the SPI NOR flash memory and to indicate + * all the supported erase commands inside this region. + * The erase types are sorted in ascending order with the + * smallest Erase Type size being at BIT(0). + * @size: the size of the region in bytes. + */ +struct spi_nor_erase_region { + u64 offset; + u64 size; +}; + +#define SNOR_ERASE_TYPE_MAX 4 +#define SNOR_ERASE_TYPE_MASK GENMASK_ULL(SNOR_ERASE_TYPE_MAX - 1, 0) + +#define SNOR_LAST_REGION BIT(4) +#define SNOR_OVERLAID_REGION BIT(5) + +#define SNOR_ERASE_FLAGS_MAX 6 +#define SNOR_ERASE_FLAGS_MASK GENMASK_ULL(SNOR_ERASE_FLAGS_MAX - 1, 0) + +/** + * struct spi_nor_erase_map - Structure to describe the SPI NOR erase map + * @regions: array of erase regions. The regions are consecutive in + * address space. Walking through the regions is done + * incrementally. + * @uniform_region: a pre-allocated erase region for SPI NOR with a uniform + * sector size (legacy implementation). + * @erase_type: an array of erase types shared by all the regions. + * The erase types are sorted in ascending order, with the + * smallest Erase Type size being the first member in the + * erase_type array. + * @uniform_erase_type: bitmask encoding erase types that can erase the + * entire memory. This member is completed at init by + * uniform and non-uniform SPI NOR flash memories if they + * support at least one erase type that can erase the + * entire memory. + */ +struct spi_nor_erase_map { + struct spi_nor_erase_region *regions; + struct spi_nor_erase_region uniform_region; + struct spi_nor_erase_type erase_type[SNOR_ERASE_TYPE_MAX]; + u8 uniform_erase_type; +}; + /** * struct flash_info - Forward declaration of a structure used internally by * spi_nor_scan() @@ -262,6 +350,7 @@ struct flash_info; * @write_proto: the SPI protocol for write operations * @reg_proto the SPI protocol for read_reg/write_reg/erase operations * @cmd_buf: used by the write_reg + * @erase_map: the erase map of the SPI NOR * @prepare: [OPTIONAL] do some preparations for the * read/write/erase/lock/unlock operations * @unprepare: [OPTIONAL] do some post work after the @@ -297,6 +386,7 @@ struct spi_nor { bool sst_write_second; u32 flags; u8 cmd_buf[SPI_NOR_MAX_CMD_SIZE]; + struct spi_nor_erase_map erase_map; int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops); void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops); @@ -317,6 +407,23 @@ struct spi_nor { void *priv; }; +static u64 __maybe_unused +spi_nor_region_is_last(const struct spi_nor_erase_region *region) +{ + return region->offset & SNOR_LAST_REGION; +} + +static u64 __maybe_unused +spi_nor_region_end(const struct spi_nor_erase_region *region) +{ + return (region->offset & ~SNOR_ERASE_FLAGS_MASK) + region->size; +} + +static bool __maybe_unused spi_nor_has_uniform_erase(const struct spi_nor *nor) +{ + return !!nor->erase_map.uniform_erase_type; +} + static inline void spi_nor_set_flash_node(struct spi_nor *nor, struct device_node *np) { -- cgit v1.2.3 From b038e8e3be724dd293a0849f5fe267fdddcca9dd Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Tue, 11 Sep 2018 18:40:07 +0300 Subject: mtd: spi-nor: parse SFDP Sector Map Parameter Table Add support for the SFDP (JESD216B) Sector Map Parameter Table. This table is optional, but when available, we parse it to identify the location and size of sectors within the main data array of the flash memory device and to identify which Erase Types are supported by each sector. Signed-off-by: Tudor Ambarus Reviewed-by: Marek Vasut Signed-off-by: Boris Brezillon --- include/linux/mtd/spi-nor.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 894cbf88bf2e..7f0c7303575e 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -419,6 +419,18 @@ spi_nor_region_end(const struct spi_nor_erase_region *region) return (region->offset & ~SNOR_ERASE_FLAGS_MASK) + region->size; } +static void __maybe_unused +spi_nor_region_mark_end(struct spi_nor_erase_region *region) +{ + region->offset |= SNOR_LAST_REGION; +} + +static void __maybe_unused +spi_nor_region_mark_overlay(struct spi_nor_erase_region *region) +{ + region->offset |= SNOR_OVERLAID_REGION; +} + static bool __maybe_unused spi_nor_has_uniform_erase(const struct spi_nor *nor) { return !!nor->erase_map.uniform_erase_type; -- cgit v1.2.3 From b8d62f33b7b225935649ab165d901fe8dd7f95e5 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 8 Oct 2018 13:17:26 +0200 Subject: genirq: Fix grammar s/an /a / Fix a grammar mistake in . [ mingo: While at it also fix another similar error in another comment as well. ] Signed-off-by: Geert Uytterhoeven Cc: Jiri Kosina Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181008111726.26286-1-geert%2Brenesas@glider.be Signed-off-by: Ingo Molnar --- include/linux/interrupt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index eeceac3376fc..1d6711c28271 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -45,7 +45,7 @@ * IRQF_PERCPU - Interrupt is per cpu * IRQF_NOBALANCING - Flag to exclude this interrupt from irq balancing * IRQF_IRQPOLL - Interrupt is used for polling (only the interrupt that is - * registered first in an shared interrupt is considered for + * registered first in a shared interrupt is considered for * performance reasons) * IRQF_ONESHOT - Interrupt is not reenabled after the hardirq handler finished. * Used by threaded interrupts which need to keep the -- cgit v1.2.3 From e054637597ba36d3729ba6a3a3dd7aad8e2a3003 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Sat, 6 Oct 2018 16:53:19 +0530 Subject: mm, sched/numa: Remove remaining traces of NUMA rate-limiting Remove the leftover pglist_data::numabalancing_migrate_lock and its initialization, we stopped using this lock with: efaffc5e40ae ("mm, sched/numa: Remove rate-limiting of automatic NUMA balancing migration") [ mingo: Rewrote the changelog. ] Signed-off-by: Srikar Dronamraju Acked-by: Mel Gorman Cc: Linus Torvalds Cc: Linux-MM Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1538824999-31230-1-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/mmzone.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3f4c0b167333..d4b0c79d2924 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -667,10 +667,6 @@ typedef struct pglist_data { enum zone_type kcompactd_classzone_idx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; -#endif -#ifdef CONFIG_NUMA_BALANCING - /* Lock serializing the migrate rate limiting window */ - spinlock_t numabalancing_migrate_lock; #endif /* * This is a per-node reserve of pages that are not available -- cgit v1.2.3 From 8ca2b56cd7da98fc8f8d787bb706b9d6c8674a3b Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 3 Oct 2018 13:07:18 -0400 Subject: locking/lockdep: Make class->ops a percpu counter and move it under CONFIG_DEBUG_LOCKDEP=y A sizable portion of the CPU cycles spent on the __lock_acquire() is used up by the atomic increment of the class->ops stat counter. By taking it out from the lock_class structure and changing it to a per-cpu per-lock-class counter, we can reduce the amount of cacheline contention on the class structure when multiple CPUs are trying to acquire locks of the same class simultaneously. To limit the increase in memory consumption because of the percpu nature of that counter, it is now put back under the CONFIG_DEBUG_LOCKDEP config option. So the memory consumption increase will only occur if CONFIG_DEBUG_LOCKDEP is defined. The lock_class structure, however, is reduced in size by 16 bytes on 64-bit archs after ops removal and a minor restructuring of the fields. This patch also fixes a bug in the increment code as the counter is of the 'unsigned long' type, but atomic_inc() was used to increment it. Signed-off-by: Waiman Long Acked-by: Peter Zijlstra Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: http://lkml.kernel.org/r/d66681f3-8781-9793-1dcf-2436a284550b@redhat.com Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b0d0b51c4d85..1fd82ff99c65 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -99,13 +99,8 @@ struct lock_class { */ unsigned int version; - /* - * Statistics counter: - */ - unsigned long ops; - - const char *name; int name_version; + const char *name; #ifdef CONFIG_LOCK_STAT unsigned long contention_point[LOCKSTAT_POINTS]; -- cgit v1.2.3 From 78d8f8f1a1800cf6068ffcac7a14cda19ae693d8 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 5 Oct 2018 11:41:13 -0700 Subject: mfd: cros: add "base attached" MKBP switch definition This adds a "base attached" switch definition to the MKBP protocol that is used by Whiskers driver to properly determine device state (clamshell vs tablet mode). Signed-off-by: Dmitry Torokhov Acked-by: Lee Jones Signed-off-by: Jiri Kosina --- include/linux/mfd/cros_ec_commands.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 6e1ab9bead28..7690f0793965 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -2132,6 +2132,7 @@ struct ec_response_get_next_event_v1 { /* Switches */ #define EC_MKBP_LID_OPEN 0 #define EC_MKBP_TABLET_MODE 1 +#define EC_MKBP_BASE_ATTACHED 2 /*****************************************************************************/ /* Temperature sensor commands */ -- cgit v1.2.3 From 53c99bd665a2649341ed6aed358ab56a3eedcd00 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 31 Aug 2018 10:42:24 +0200 Subject: init: add arch_call_rest_init to allow stack switching With CONFIG_VMAP_STACK=y the kernel stack of all tasks should be allocated in the vmalloc space. The initial stack used for all the early init code is in the init_thread_union. To be able to switch from this early stack to a properly allocated stack from vmalloc the architecture needs a switch-over point. Introduce the arch_call_rest_init() function with a weak definition in init/main.c with the only purpose to call rest_init() from the end of start_kernel(). The architecture override can then do the necessary magic to switch to the new vmalloc'ed stack. Signed-off-by: Martin Schwidefsky --- include/linux/start_kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/start_kernel.h b/include/linux/start_kernel.h index 4b268d86a784..8b369a41c03c 100644 --- a/include/linux/start_kernel.h +++ b/include/linux/start_kernel.h @@ -9,5 +9,7 @@ up something else. */ extern asmlinkage void __init start_kernel(void); +extern void __init arch_call_rest_init(void); +extern void __ref rest_init(void); #endif /* _LINUX_START_KERNEL_H */ -- cgit v1.2.3 From dde709d1361ab50d3b9f2824f72b4374f5582e84 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Mon, 20 Nov 2017 11:16:14 +0100 Subject: compiler: introduce __no_sanitize_address_or_inline Due to conflict between kasan instrumentation and inlining https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 functions which are defined as inline could not be called from functions defined with __no_sanitize_address. Introduce __no_sanitize_address_or_inline which would expand to __no_sanitize_address when the kernel is built with kasan support and to inline otherwise. This helps to avoid disabling kasan instrumentation for entire files. Reviewed-by: Martin Schwidefsky Signed-off-by: Vasily Gorbik Signed-off-by: Martin Schwidefsky --- include/linux/compiler-gcc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 763bbad1e258..997ade08a79d 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -208,6 +208,12 @@ * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 */ #define __no_sanitize_address __attribute__((no_sanitize_address)) +#ifdef CONFIG_KASAN +#define __no_sanitize_address_or_inline \ + __no_sanitize_address __maybe_unused notrace +#else +#define __no_sanitize_address_or_inline inline +#endif #endif #if GCC_VERSION >= 50100 @@ -225,6 +231,7 @@ #if !defined(__no_sanitize_address) #define __no_sanitize_address +#define __no_sanitize_address_or_inline inline #endif /* -- cgit v1.2.3 From 3b0296b8c893adb17b422179b9e779e4c32aa347 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Mon, 8 Oct 2018 11:21:44 -0700 Subject: firmware: xilinx: Add zynqmp IOCTL API for device control Add ZynqMP firmware IOCTL API to control and configure devices like PLLs, SD, Gem, etc. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Acked-by: Olof Johansson Signed-off-by: Michal Simek --- include/linux/firmware/xlnx-zynqmp.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 015e130431e6..7a9db0861803 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -34,7 +34,8 @@ enum pm_api_id { PM_GET_API_VERSION = 1, - PM_QUERY_DATA = 35, + PM_IOCTL = 34, + PM_QUERY_DATA, PM_CLOCK_ENABLE, PM_CLOCK_DISABLE, PM_CLOCK_GETSTATE, @@ -99,6 +100,7 @@ struct zynqmp_eemi_ops { int (*clock_getrate)(u32 clock_id, u64 *rate); int (*clock_setparent)(u32 clock_id, u32 parent_id); int (*clock_getparent)(u32 clock_id, u32 *parent_id); + int (*ioctl)(u32 node_id, u32 ioctl_id, u32 arg1, u32 arg2, u32 *out); }; #if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) -- cgit v1.2.3 From 3fde0e16d016ecb273f0fa404b5d56b947fc0576 Mon Sep 17 00:00:00 2001 From: Jolly Shah Date: Mon, 8 Oct 2018 11:21:46 -0700 Subject: drivers: clk: Add ZynqMP clock driver This patch adds CCF compliant clock driver for ZynqMP. Clock driver queries supported clock information from firmware and regiters pll and output clocks with CCF. Signed-off-by: Rajan Vaja Signed-off-by: Tejas Patel Signed-off-by: Shubhrajyoti Datta Signed-off-by: Jolly Shah Acked-by: Olof Johansson Reviewed-by: Stephen Boyd Signed-off-by: Michal Simek --- include/linux/firmware/xlnx-zynqmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 7a9db0861803..3c3c28eff56a 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -72,6 +72,7 @@ enum pm_query_id { PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS, PM_QID_CLOCK_GET_PARENTS, PM_QID_CLOCK_GET_ATTRIBUTES, + PM_QID_CLOCK_GET_NUM_CLOCKS = 12, }; /** -- cgit v1.2.3 From 7ed1d91a9ed61afe438ba51cbf49cb567ab7dca8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 13:06:58 +0200 Subject: dma-mapping: translate __GFP_NOFAIL to DMA_ATTR_NO_WARN This allows all dma_map_ops instances to entirely rely on DMA_ATTR_NO_WARN going forward. Signed-off-by: Christoph Hellwig Acked-by: Robin Murphy --- include/linux/dma-mapping.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 547a48bcfa3d..15bd41447025 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -558,9 +558,11 @@ static inline void dma_free_attrs(struct device *dev, size_t size, } static inline void *dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) + dma_addr_t *dma_handle, gfp_t gfp) { - return dma_alloc_attrs(dev, size, dma_handle, flag, 0); + + return dma_alloc_attrs(dev, size, dma_handle, gfp, + (gfp & __GFP_NOWARN) ? DMA_ATTR_NO_WARN : 0); } static inline void dma_free_coherent(struct device *dev, size_t size, @@ -794,8 +796,12 @@ static inline void dmam_release_declared_memory(struct device *dev) static inline void *dma_alloc_wc(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t gfp) { - return dma_alloc_attrs(dev, size, dma_addr, gfp, - DMA_ATTR_WRITE_COMBINE); + unsigned long attrs = DMA_ATTR_NO_WARN; + + if (gfp & __GFP_NOWARN) + attrs |= DMA_ATTR_NO_WARN; + + return dma_alloc_attrs(dev, size, dma_addr, gfp, attrs); } #ifndef dma_alloc_writecombine #define dma_alloc_writecombine dma_alloc_wc -- cgit v1.2.3 From d7b6801673f95e5f72efd3ffba1bcbb606883049 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Tue, 9 Oct 2018 13:11:32 +0200 Subject: lightnvm: combine 1.2 and 2.0 command flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add nvm_set_flags helper to enable core to appropriately set the command flags for read/write/erase depending on which version a drive supports. The flags arguments can be distilled into the access hint, scrambling, and program/erase suspend. Replace the access hint with a "is_seq" parameter. The rest of the flags are dependent on the command opcode, which is trivial to detect and set. Signed-off-by: Matias Bjørling Reviewed-by: Javier González Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index e9e0d1c7eaf5..8acc2fe277d6 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -305,6 +305,8 @@ struct nvm_rq { u64 ppa_status; /* ppa media status */ int error; + int is_seq; /* Sequential hint flag. 1.2 only */ + void *private; }; -- cgit v1.2.3 From 656e33ca3d405196f94133babc4e38454a49cb73 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Tue, 9 Oct 2018 13:11:34 +0200 Subject: lightnvm: move device L2P detection to core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A 1.2 device is able to manage the logical to physical mapping table internally or leave it to the host. A target only supports one of those approaches, and therefore must check on initialization. Move this check to core to avoid each target implement the check. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 8acc2fe277d6..f4a84694e5e2 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -495,9 +495,15 @@ typedef void (nvm_tgt_exit_fn)(void *, bool); typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *); typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *); +enum { + NVM_TGT_F_DEV_L2P = 0, + NVM_TGT_F_HOST_L2P = 1 << 0, +}; + struct nvm_tgt_type { const char *name; unsigned int version[3]; + int flags; /* target entry points */ nvm_tgt_make_rq_fn *make_rq; -- cgit v1.2.3 From aff3fb18f957de93e629c7d3d2c4ef1f360aa511 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Tue, 9 Oct 2018 13:11:36 +0200 Subject: lightnvm: move bad block and chunk state logic to core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit pblk implements two data paths for recovery line state. One for 1.2 and another for 2.0, instead of having pblk implement these, combine them in the core to reduce complexity and make available to other targets. The new interface will adhere to the 2.0 chunk definition, including managing open chunks with an active write pointer. To provide this interface, a 1.2 device recovers the state of the chunks by manually detecting if a chunk is either free/open/close/offline, and if open, scanning the flash pages sequentially to find the next writeable page. This process takes on average ~10 seconds on a device with 64 dies, 1024 blocks and 60us read access time. The process can be parallelized but is left out for maintenance simplicity, as the 1.2 specification is deprecated. For 2.0 devices, the logic is maintained internally in the drive and retrieved through the 2.0 interface. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index f4a84694e5e2..0106984400bc 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -86,8 +86,8 @@ struct nvm_chk_meta; typedef int (nvm_id_fn)(struct nvm_dev *); typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, u8 *); typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct ppa_addr *, int, int); -typedef int (nvm_get_chk_meta_fn)(struct nvm_dev *, struct nvm_chk_meta *, - sector_t, int); +typedef int (nvm_get_chk_meta_fn)(struct nvm_dev *, sector_t, int, + struct nvm_chk_meta *); typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); typedef int (nvm_submit_io_sync_fn)(struct nvm_dev *, struct nvm_rq *); typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *); @@ -532,18 +532,13 @@ extern struct nvm_dev *nvm_alloc_dev(int); extern int nvm_register(struct nvm_dev *); extern void nvm_unregister(struct nvm_dev *); - -extern int nvm_get_chunk_meta(struct nvm_tgt_dev *tgt_dev, - struct nvm_chk_meta *meta, struct ppa_addr ppa, - int nchks); - -extern int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr *, +extern int nvm_get_chunk_meta(struct nvm_tgt_dev *, struct ppa_addr, + int, struct nvm_chk_meta *); +extern int nvm_set_chunk_meta(struct nvm_tgt_dev *, struct ppa_addr *, int, int); extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *); extern int nvm_submit_io_sync(struct nvm_tgt_dev *, struct nvm_rq *); extern void nvm_end_io(struct nvm_rq *); -extern int nvm_bb_tbl_fold(struct nvm_dev *, u8 *, int); -extern int nvm_get_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr, u8 *); #else /* CONFIG_NVM */ struct nvm_dev_ops; -- cgit v1.2.3 From 2cf99bbd106f89fc72f778e8ad9d5538f1ef939b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Javier=20Gonz=C3=A1lez?= Date: Tue, 9 Oct 2018 13:11:41 +0200 Subject: lightnvm: pblk: add helpers for chunk addresses MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implement helpers to go from ppas to a chunk within a line and an address within a chunk. These helpers will be used on the patches adding trace support in pblk, which will be sent in this window. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 0106984400bc..77743a02ec0d 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -487,6 +487,25 @@ static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev, return l; } +static inline u64 dev_to_chunk_addr(struct nvm_dev *dev, void *addrf, + struct ppa_addr p) +{ + struct nvm_geo *geo = &dev->geo; + u64 caddr; + + if (geo->version == NVM_OCSSD_SPEC_12) { + struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)addrf; + + caddr = (u64)p.g.pg << ppaf->pg_offset; + caddr |= (u64)p.g.pl << ppaf->pln_offset; + caddr |= (u64)p.g.sec << ppaf->sec_offset; + } else { + caddr = p.m.sec; + } + + return caddr; +} + typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, -- cgit v1.2.3 From d68a9344041b6dd304ff382d0c7805869f09944f Mon Sep 17 00:00:00 2001 From: Hans Holmberg Date: Tue, 9 Oct 2018 13:11:46 +0200 Subject: lightnvm: introduce nvm_rq_to_ppa_list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a number of places in the lightnvm subsystem where the user iterates over the ppa list. Before iterating, the user must know if it is a single or multiple LBAs due to vector commands using either the nvm_rq ->ppa_addr or ->ppa_list fields on command submission, which leads to open-coding the if/else statement. Instead of having multiple if/else's, move it into a function that can be called by its users. A nice side effect of this cleanup is that this patch fixes up a bunch of cases where we don't consider the single-ppa case in pblk. Signed-off-by: Hans Holmberg Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 77743a02ec0d..50ac5b21297c 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -320,6 +320,11 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata) return rqdata + 1; } +static inline struct ppa_addr *nvm_rq_to_ppa_list(struct nvm_rq *rqd) +{ + return (rqd->nr_ppas > 1) ? rqd->ppa_list : &rqd->ppa_addr; +} + enum { NVM_BLK_ST_FREE = 0x1, /* Free block */ NVM_BLK_ST_TGT = 0x2, /* Block in use by target */ -- cgit v1.2.3 From 7f985f9a691dc25ddcfc9dc7ff21199f5ee1569c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Javier=20Gonz=C3=A1lez?= Date: Tue, 9 Oct 2018 13:11:56 +0200 Subject: lightnvm: move ppa transformations to core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Continuing the effort of moving 1.2 and 2.0 specific code to core, move 64_to_32 and 32_to_64 ppa helpers from pblk to core. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 83 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 50ac5b21297c..eb7300c20f24 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -511,6 +511,89 @@ static inline u64 dev_to_chunk_addr(struct nvm_dev *dev, void *addrf, return caddr; } +static inline struct ppa_addr nvm_ppa32_to_ppa64(struct nvm_dev *dev, + void *addrf, u32 ppa32) +{ + struct ppa_addr ppa64; + + ppa64.ppa = 0; + + if (ppa32 == -1) { + ppa64.ppa = ADDR_EMPTY; + } else if (ppa32 & (1U << 31)) { + ppa64.c.line = ppa32 & ((~0U) >> 1); + ppa64.c.is_cached = 1; + } else { + struct nvm_geo *geo = &dev->geo; + + if (geo->version == NVM_OCSSD_SPEC_12) { + struct nvm_addrf_12 *ppaf = addrf; + + ppa64.g.ch = (ppa32 & ppaf->ch_mask) >> + ppaf->ch_offset; + ppa64.g.lun = (ppa32 & ppaf->lun_mask) >> + ppaf->lun_offset; + ppa64.g.blk = (ppa32 & ppaf->blk_mask) >> + ppaf->blk_offset; + ppa64.g.pg = (ppa32 & ppaf->pg_mask) >> + ppaf->pg_offset; + ppa64.g.pl = (ppa32 & ppaf->pln_mask) >> + ppaf->pln_offset; + ppa64.g.sec = (ppa32 & ppaf->sec_mask) >> + ppaf->sec_offset; + } else { + struct nvm_addrf *lbaf = addrf; + + ppa64.m.grp = (ppa32 & lbaf->ch_mask) >> + lbaf->ch_offset; + ppa64.m.pu = (ppa32 & lbaf->lun_mask) >> + lbaf->lun_offset; + ppa64.m.chk = (ppa32 & lbaf->chk_mask) >> + lbaf->chk_offset; + ppa64.m.sec = (ppa32 & lbaf->sec_mask) >> + lbaf->sec_offset; + } + } + + return ppa64; +} + +static inline u32 nvm_ppa64_to_ppa32(struct nvm_dev *dev, + void *addrf, struct ppa_addr ppa64) +{ + u32 ppa32 = 0; + + if (ppa64.ppa == ADDR_EMPTY) { + ppa32 = ~0U; + } else if (ppa64.c.is_cached) { + ppa32 |= ppa64.c.line; + ppa32 |= 1U << 31; + } else { + struct nvm_geo *geo = &dev->geo; + + if (geo->version == NVM_OCSSD_SPEC_12) { + struct nvm_addrf_12 *ppaf = addrf; + + ppa32 |= ppa64.g.ch << ppaf->ch_offset; + ppa32 |= ppa64.g.lun << ppaf->lun_offset; + ppa32 |= ppa64.g.blk << ppaf->blk_offset; + ppa32 |= ppa64.g.pg << ppaf->pg_offset; + ppa32 |= ppa64.g.pl << ppaf->pln_offset; + ppa32 |= ppa64.g.sec << ppaf->sec_offset; + } else { + struct nvm_addrf *lbaf = addrf; + + ppa32 |= ppa64.m.grp << lbaf->ch_offset; + ppa32 |= ppa64.m.pu << lbaf->lun_offset; + ppa32 |= ppa64.m.chk << lbaf->chk_offset; + ppa32 |= ppa64.m.sec << lbaf->sec_offset; + } + } + + return ppa32; +} + + typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, -- cgit v1.2.3 From bf82fa2f584f1c6e12df8c04fca715d53e7f32d5 Mon Sep 17 00:00:00 2001 From: Hans Holmberg Date: Tue, 9 Oct 2018 13:11:59 +0200 Subject: lightnvm: pblk: fix mapping issue on failed writes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On 1.2-devices, the mapping-out of remaning sectors in the failed-write's block can result in an infinite loop, stalling the write pipeline, fix this. Fixes: 6a3abf5beef6 ("lightnvm: pblk: rework write error recovery path") Signed-off-by: Hans Holmberg Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index eb7300c20f24..2fdeac1a420d 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -593,6 +593,42 @@ static inline u32 nvm_ppa64_to_ppa32(struct nvm_dev *dev, return ppa32; } +static inline int nvm_next_ppa_in_chk(struct nvm_tgt_dev *dev, + struct ppa_addr *ppa) +{ + struct nvm_geo *geo = &dev->geo; + int last = 0; + + if (geo->version == NVM_OCSSD_SPEC_12) { + int sec = ppa->g.sec; + + sec++; + if (sec == geo->ws_min) { + int pg = ppa->g.pg; + + sec = 0; + pg++; + if (pg == geo->num_pg) { + int pl = ppa->g.pl; + + pg = 0; + pl++; + if (pl == geo->num_pln) + last = 1; + + ppa->g.pl = pl; + } + ppa->g.pg = pg; + } + ppa->g.sec = sec; + } else { + ppa->m.sec++; + if (ppa->m.sec == geo->clba) + last = 1; + } + + return last; +} typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); -- cgit v1.2.3 From 7d49b28a80b830c3ca876d33bedc58d62a78e16f Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Tue, 25 Sep 2018 23:58:41 -0400 Subject: smp,cpumask: introduce on_each_cpu_cond_mask Introduce a variant of on_each_cpu_cond that iterates only over the CPUs in a cpumask, in order to avoid making callbacks for every single CPU in the system when we only need to test a subset. Cc: npiggin@gmail.com Cc: mingo@kernel.org Cc: will.deacon@arm.com Cc: songliubraving@fb.com Cc: kernel-team@fb.com Cc: hpa@zytor.com Cc: luto@kernel.org Signed-off-by: Rik van Riel Signed-off-by: Peter Zijlstra (Intel) Link: http://lkml.kernel.org/r/20180926035844.1420-5-riel@surriel.com --- include/linux/smp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 9fb239e12b82..a56f08ff3097 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -53,6 +53,10 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), smp_call_func_t func, void *info, bool wait, gfp_t gfp_flags); +void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info), + smp_call_func_t func, void *info, bool wait, + gfp_t gfp_flags, const struct cpumask *mask); + int smp_call_function_single_async(int cpu, call_single_data_t *csd); #ifdef CONFIG_SMP -- cgit v1.2.3 From f2e74abfaad446765ce0350aed1d9c5eed5b1b36 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:38 +0200 Subject: remoteproc: add release ops in rproc_mem_entry struct Memory entry could be allocated in different ways (ioremap, dma_alloc_coherent, internal RAM allocator...). This patch introduces a release ops in rproc_mem_entry structure to associate dedicated release mechanism to each memory entry descriptor in order to keep remoteproc core generic. Signed-off-by: Loic Pallardy Acked-by: Bjorn Andersson Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 75f9ca05b865..4116e92d4b3d 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -305,12 +305,15 @@ struct fw_rsc_vdev { struct fw_rsc_vdev_vring vring[0]; } __packed; +struct rproc; + /** * struct rproc_mem_entry - memory entry descriptor * @va: virtual address * @dma: dma address * @len: length, in bytes * @da: device address + * @release: release associated memory * @priv: associated data * @node: list node */ @@ -321,9 +324,9 @@ struct rproc_mem_entry { u32 da; void *priv; struct list_head node; + int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; -struct rproc; struct firmware; /** -- cgit v1.2.3 From 3265230c5b05fe919291d09e266a8aedc85ebad0 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:39 +0200 Subject: remoteproc: add name in rproc_mem_entry struct Add name field in struct rproc_mem_entry. This new field will be used to match memory area requested in resource table with pre-registered carveout. Signed-off-by: Loic Pallardy Acked-by: Bjorn Andersson Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 4116e92d4b3d..19908c930f47 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -315,6 +315,7 @@ struct rproc; * @da: device address * @release: release associated memory * @priv: associated data + * @name: associated memory region name (optional) * @node: list node */ struct rproc_mem_entry { @@ -323,6 +324,7 @@ struct rproc_mem_entry { int len; u32 da; void *priv; + char name[32]; struct list_head node; int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; -- cgit v1.2.3 From 72029c901a0244ca2e1eb09e1c453413a17f5787 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:40 +0200 Subject: remoteproc: add helper function to allocate and init rproc_mem_entry struct This patch introduces rproc_mem_entry_init helper function to simplify rproc_mem_entry structure allocation and filling by client. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 19908c930f47..9e2b84fa2efa 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -559,6 +559,12 @@ int rproc_add(struct rproc *rproc); int rproc_del(struct rproc *rproc); void rproc_free(struct rproc *rproc); +struct rproc_mem_entry * +rproc_mem_entry_init(struct device *dev, + void *va, dma_addr_t dma, int len, u32 da, + int (*release)(struct rproc *, struct rproc_mem_entry *), + const char *name, ...); + int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); -- cgit v1.2.3 From 15c0b0258e4f1c3c817f34d092d2cc6ff5178bdd Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:41 +0200 Subject: remoteproc: introduce rproc_add_carveout function This patch introduces a new API to allow platform driver to register platform specific carveout regions. Signed-off-by: Loic Pallardy Acked-by: Bjorn Andersson Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 9e2b84fa2efa..8a350265d883 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -559,6 +559,8 @@ int rproc_add(struct rproc *rproc); int rproc_del(struct rproc *rproc); void rproc_free(struct rproc *rproc); +void rproc_add_carveout(struct rproc *rproc, struct rproc_mem_entry *mem); + struct rproc_mem_entry * rproc_mem_entry_init(struct device *dev, void *va, dma_addr_t dma, int len, u32 da, -- cgit v1.2.3 From d7c51706d0956472b7c0530b1bf8fba32d82ee6b Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:43 +0200 Subject: remoteproc: add alloc ops in rproc_mem_entry struct Memory entry could be allocated in different ways (ioremap, dma_alloc_coherent, internal RAM allocator...). This patch introduces an alloc ops in rproc_mem_entry structure to associate dedicated allocation mechanism to each memory entry descriptor in order to do remote core agnostic from memory allocators. The introduction of this ops allows to perform allocation of all registered carveout at the same time, just before calling rproc_start(). It simplifies and makes uniform carveout management whatever origin. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 8a350265d883..d251c091303c 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -317,6 +317,9 @@ struct rproc; * @priv: associated data * @name: associated memory region name (optional) * @node: list node + * @rsc_offset: offset in resource table + * @flags: iommu protection flags + * @alloc: specific memory allocator function */ struct rproc_mem_entry { void *va; @@ -326,6 +329,9 @@ struct rproc_mem_entry { void *priv; char name[32]; struct list_head node; + u32 rsc_offset; + u32 flags; + int (*alloc)(struct rproc *rproc, struct rproc_mem_entry *mem); int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; @@ -564,6 +570,7 @@ void rproc_add_carveout(struct rproc *rproc, struct rproc_mem_entry *mem); struct rproc_mem_entry * rproc_mem_entry_init(struct device *dev, void *va, dma_addr_t dma, int len, u32 da, + int (*alloc)(struct rproc *, struct rproc_mem_entry *), int (*release)(struct rproc *, struct rproc_mem_entry *), const char *name, ...); -- cgit v1.2.3 From 1429cca1175f4cb64dd5d61ffd6037895a41d672 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:44 +0200 Subject: remoteproc: add helper function to allocate rproc_mem_entry from reserved memory This patch introduces rproc_res_mem_entry_init() helper function to allocate a rproc_mem_entry structure from a reserved memory region. In that case, rproc_mem_entry structure has no alloc and release ops. It will be used to assigned the specified reserved memory to any rproc sub device. Relation between rproc_mem_entry and rproc sub device will be done by name. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index d251c091303c..d4cabe8da507 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -319,6 +319,7 @@ struct rproc; * @node: list node * @rsc_offset: offset in resource table * @flags: iommu protection flags + * @of_resm_idx: reserved memory phandle index * @alloc: specific memory allocator function */ struct rproc_mem_entry { @@ -331,6 +332,7 @@ struct rproc_mem_entry { struct list_head node; u32 rsc_offset; u32 flags; + u32 of_resm_idx; int (*alloc)(struct rproc *rproc, struct rproc_mem_entry *mem); int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; @@ -574,6 +576,10 @@ rproc_mem_entry_init(struct device *dev, int (*release)(struct rproc *, struct rproc_mem_entry *), const char *name, ...); +struct rproc_mem_entry * +rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, int len, + u32 da, const char *name, ...); + int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); -- cgit v1.2.3 From f8ec92a9f63b3b11e399409141b7868bb405e6b5 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Fri, 5 Oct 2018 08:52:58 +0200 Subject: gpiolib: Add init_valid_mask exported function Add a function that allows initializing the valid_mask from gpiochip_add_data. This prevents race conditions during gpiochip initialization. If the function is not exported, then the old behaviour is respected, this is, set all gpios as valid. Signed-off-by: Ricardo Ribalda Delgado Tested-by: Jeffrey Hugo Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index f6b95734073f..c5a51af8f76e 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -280,6 +280,9 @@ struct gpio_chip { void (*dbg_show)(struct seq_file *s, struct gpio_chip *chip); + + int (*init_valid_mask)(struct gpio_chip *chip); + int base; u16 ngpio; const char *const *names; @@ -318,7 +321,9 @@ struct gpio_chip { /** * @need_valid_mask: * - * If set core allocates @valid_mask with all bits set to one. + * If set core allocates @valid_mask with all its values initialized + * with init_valid_mask() or set to one if init_valid_mask() is not + * defined */ bool need_valid_mask; -- cgit v1.2.3 From 3e779a2e7f909015f21428b66834127496110b6d Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 8 Oct 2018 09:32:13 -0700 Subject: gpio: Assign gpio_irq_chip::parents to non-stack pointer gpiochip_set_cascaded_irqchip() is passed 'parent_irq' as an argument and then the address of that argument is assigned to the gpio chips gpio_irq_chip 'parents' pointer shortly thereafter. This can't ever work, because we've just assigned some stack address to a pointer that we plan to dereference later in gpiochip_irq_map(). I ran into this issue with the KASAN report below when gpiochip_irq_map() tried to setup the parent irq with a total junk pointer for the 'parents' array. BUG: KASAN: stack-out-of-bounds in gpiochip_irq_map+0x228/0x248 Read of size 4 at addr ffffffc0dde472e0 by task swapper/0/1 CPU: 7 PID: 1 Comm: swapper/0 Not tainted 4.14.72 #34 Call trace: [] dump_backtrace+0x0/0x718 [] show_stack+0x20/0x2c [] __dump_stack+0x20/0x28 [] dump_stack+0x80/0xbc [] print_address_description+0x70/0x238 [] kasan_report+0x1cc/0x260 [] __asan_report_load4_noabort+0x2c/0x38 [] gpiochip_irq_map+0x228/0x248 [] irq_domain_associate+0x114/0x2ec [] irq_create_mapping+0x120/0x234 [] irq_create_fwspec_mapping+0x4c8/0x88c [] irq_create_of_mapping+0x180/0x210 [] of_irq_get+0x138/0x198 [] spi_drv_probe+0x94/0x178 [] driver_probe_device+0x51c/0x824 [] __device_attach_driver+0x148/0x20c [] bus_for_each_drv+0x120/0x188 [] __device_attach+0x19c/0x2dc [] device_initial_probe+0x20/0x2c [] bus_probe_device+0x80/0x154 [] device_add+0x9b8/0xbdc [] spi_add_device+0x1b8/0x380 [] spi_register_controller+0x111c/0x1378 [] spi_geni_probe+0x4dc/0x6f8 [] platform_drv_probe+0xdc/0x130 [] driver_probe_device+0x51c/0x824 [] __driver_attach+0x100/0x194 [] bus_for_each_dev+0x104/0x16c [] driver_attach+0x48/0x54 [] bus_add_driver+0x274/0x498 [] driver_register+0x1ac/0x230 [] __platform_driver_register+0xcc/0xdc [] spi_geni_driver_init+0x1c/0x24 [] do_one_initcall+0x240/0x3dc [] kernel_init_freeable+0x378/0x468 [] kernel_init+0x14/0x110 [] ret_from_fork+0x10/0x18 The buggy address belongs to the page: page:ffffffbf037791c0 count:0 mapcount:0 mapping: (null) index:0x0 flags: 0x4000000000000000() raw: 4000000000000000 0000000000000000 0000000000000000 00000000ffffffff raw: ffffffbf037791e0 ffffffbf037791e0 0000000000000000 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffffffc0dde47180: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffc0dde47200: f1 f1 f1 f1 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f2 f2 >ffffffc0dde47280: f2 f2 00 00 00 00 00 00 00 00 00 00 f3 f3 f3 f3 ^ ffffffc0dde47300: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffc0dde47380: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Let's leave around one unsigned int in the gpio_irq_chip struct for the single parent irq case and repoint the 'parents' array at it. This way code is left mostly intact to setup parents and we waste an extra few bytes per structure of which there should be only a handful in a system. Cc: Evan Green Cc: Thierry Reding Cc: Grygorii Strashko Fixes: e0d897289813 ("gpio: Implement tighter IRQ chip integration") Signed-off-by: Stephen Boyd Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 0ea328e71ec9..a4d5eb37744a 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -94,6 +94,13 @@ struct gpio_irq_chip { */ unsigned int num_parents; + /** + * @parent_irq: + * + * For use by gpiochip_set_cascaded_irqchip() + */ + unsigned int parent_irq; + /** * @parents: * -- cgit v1.2.3 From 5039563e7c25eccd7fec1de6706011009d1c5665 Mon Sep 17 00:00:00 2001 From: Trent Piepho Date: Thu, 20 Sep 2018 19:18:32 +0000 Subject: spi: Add driver_override SPI device attribute MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This attribute works the same was as the identically named attribute for PCI, AMBA, and platform devices. For reference, see: commit 3cf385713460 ("ARM: 8256/1: driver coamba: add device binding path 'driver_override'") commit 3d713e0e382e ("driver core: platform: add device binding path 'driver_override'") commit 782a985d7af2 ("PCI: Introduce new device binding path using pci_dev.driver_override") If the name of a driver is written to this attribute, then the device will bind to the named driver and only the named driver. The device will bind to the driver even if the driver does not list the device in its id table. This behavior is different than the driver's bind attribute, which only allows binding to devices that are listed as supported by the driver. It can be used to bind a generic driver, like spidev, to a device. Signed-off-by: Trent Piepho Reviewed-by: Jan Kundrát Tested-by: Jan Kundrát Reviewed-by: Geert Uytterhoeven Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index f08824ea1968..3de9958ca28b 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -159,6 +159,7 @@ struct spi_device { void *controller_state; void *controller_data; char modalias[SPI_NAME_SIZE]; + const char *driver_override; int cs_gpio; /* chip select gpio */ /* the statistics */ -- cgit v1.2.3 From 52916982af48d9f9fc01ad825259de1eb3a9b25e Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:35 -0600 Subject: PCI/P2PDMA: Support peer-to-peer memory Some PCI devices may have memory mapped in a BAR space that's intended for use in peer-to-peer transactions. To enable such transactions the memory must be registered with ZONE_DEVICE pages so it can be used by DMA interfaces in existing drivers. Add an interface for other subsystems to find and allocate chunks of P2P memory as necessary to facilitate transfers between two PCI peers: struct pci_dev *pci_p2pmem_find[_many](); int pci_p2pdma_distance[_many](); void *pci_alloc_p2pmem(); The new interface requires a driver to collect a list of client devices involved in the transaction then call pci_p2pmem_find() to obtain any suitable P2P memory. Alternatively, if the caller knows a device which provides P2P memory, they can use pci_p2pdma_distance() to determine if it is usable. With a suitable p2pmem device, memory can then be allocated with pci_alloc_p2pmem() for use in DMA transactions. Depending on hardware, using peer-to-peer memory may reduce the bandwidth of the transfer but can significantly reduce pressure on system memory. This may be desirable in many cases: for example a system could be designed with a small CPU connected to a PCIe switch by a small number of lanes which would maximize the number of lanes available to connect to NVMe devices. The code is designed to only utilize the p2pmem device if all the devices involved in a transfer are behind the same PCI bridge. This is because we have no way of knowing whether peer-to-peer routing between PCIe Root Ports is supported (PCIe r4.0, sec 1.3.1). Additionally, the benefits of P2P transfers that go through the RC is limited to only reducing DRAM usage and, in some cases, coding convenience. The PCI-SIG may be exploring adding a new capability bit to advertise whether this is possible for future hardware. This commit includes significant rework and feedback from Christoph Hellwig. Signed-off-by: Christoph Hellwig Signed-off-by: Logan Gunthorpe [bhelgaas: fold in fix from Keith Busch : https://lore.kernel.org/linux-pci/20181012155920.15418-1-keith.busch@intel.com, to address comment from Dan Carpenter , fold in https://lore.kernel.org/linux-pci/20181017160510.17926-1-logang@deltatee.com] Signed-off-by: Bjorn Helgaas --- include/linux/memremap.h | 5 +++ include/linux/mm.h | 18 +++++++++ include/linux/pci-p2pdma.h | 92 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 4 ++ 4 files changed, 119 insertions(+) create mode 100644 include/linux/pci-p2pdma.h (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index f91f9e763557..9553370ebdad 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -53,11 +53,16 @@ struct vmem_altmap { * wakeup event whenever a page is unpinned and becomes idle. This * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). + * + * MEMORY_DEVICE_PCI_P2PDMA: + * Device memory residing in a PCI BAR intended for use with Peer-to-Peer + * transactions. */ enum memory_type { MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_PUBLIC, MEMORY_DEVICE_FS_DAX, + MEMORY_DEVICE_PCI_P2PDMA, }; /* diff --git a/include/linux/mm.h b/include/linux/mm.h index a61ebe8ad4ca..2055df412a77 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -890,6 +890,19 @@ static inline bool is_device_public_page(const struct page *page) page->pgmap->type == MEMORY_DEVICE_PUBLIC; } +#ifdef CONFIG_PCI_P2PDMA +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; +} +#else /* CONFIG_PCI_P2PDMA */ +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return false; +} +#endif /* CONFIG_PCI_P2PDMA */ + #else /* CONFIG_DEV_PAGEMAP_OPS */ static inline void dev_pagemap_get_ops(void) { @@ -913,6 +926,11 @@ static inline bool is_device_public_page(const struct page *page) { return false; } + +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return false; +} #endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline void get_page(struct page *page) diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h new file mode 100644 index 000000000000..7bdaacfd5892 --- /dev/null +++ b/include/linux/pci-p2pdma.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PCI Peer 2 Peer DMA support. + * + * Copyright (c) 2016-2018, Logan Gunthorpe + * Copyright (c) 2016-2017, Microsemi Corporation + * Copyright (c) 2017, Christoph Hellwig + * Copyright (c) 2018, Eideticom Inc. + */ + +#ifndef _LINUX_PCI_P2PDMA_H +#define _LINUX_PCI_P2PDMA_H + +#include + +struct block_device; +struct scatterlist; + +#ifdef CONFIG_PCI_P2PDMA +int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, + u64 offset); +int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients, + int num_clients, bool verbose); +bool pci_has_p2pmem(struct pci_dev *pdev); +struct pci_dev *pci_p2pmem_find_many(struct device **clients, int num_clients); +void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size); +void pci_free_p2pmem(struct pci_dev *pdev, void *addr, size_t size); +pci_bus_addr_t pci_p2pmem_virt_to_bus(struct pci_dev *pdev, void *addr); +struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, + unsigned int *nents, u32 length); +void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl); +void pci_p2pmem_publish(struct pci_dev *pdev, bool publish); +#else /* CONFIG_PCI_P2PDMA */ +static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, + size_t size, u64 offset) +{ + return -EOPNOTSUPP; +} +static inline int pci_p2pdma_distance_many(struct pci_dev *provider, + struct device **clients, int num_clients, bool verbose) +{ + return -1; +} +static inline bool pci_has_p2pmem(struct pci_dev *pdev) +{ + return false; +} +static inline struct pci_dev *pci_p2pmem_find_many(struct device **clients, + int num_clients) +{ + return NULL; +} +static inline void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size) +{ + return NULL; +} +static inline void pci_free_p2pmem(struct pci_dev *pdev, void *addr, + size_t size) +{ +} +static inline pci_bus_addr_t pci_p2pmem_virt_to_bus(struct pci_dev *pdev, + void *addr) +{ + return 0; +} +static inline struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, + unsigned int *nents, u32 length) +{ + return NULL; +} +static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev, + struct scatterlist *sgl) +{ +} +static inline void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) +{ +} +#endif /* CONFIG_PCI_P2PDMA */ + + +static inline int pci_p2pdma_distance(struct pci_dev *provider, + struct device *client, bool verbose) +{ + return pci_p2pdma_distance_many(provider, &client, 1, verbose); +} + +static inline struct pci_dev *pci_p2pmem_find(struct device *client) +{ + return pci_p2pmem_find_many(&client, 1); +} + +#endif /* _LINUX_PCI_P2P_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 6925828f9f25..bf5277768f69 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -281,6 +281,7 @@ struct pcie_link_state; struct pci_vpd; struct pci_sriov; struct pci_ats; +struct pci_p2pdma; /* The pci_dev structure describes PCI devices */ struct pci_dev { @@ -438,6 +439,9 @@ struct pci_dev { #endif #ifdef CONFIG_PCI_PASID u16 pasid_features; +#endif +#ifdef CONFIG_PCI_P2PDMA + struct pci_p2pdma *p2pdma; #endif phys_addr_t rom; /* Physical address if not from BAR */ size_t romlen; /* Length if not from BAR */ -- cgit v1.2.3 From df2fc43d09d3ee5ede82cab9299df5e78aa427b5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 13 Sep 2018 11:17:23 +0200 Subject: list: introduce list_bulk_move_tail helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move all entries between @first and including @last before @head. This is useful for LRU lists where a whole block of entries should be moved to the end of the list. Used as a band aid in TTM, but better placed in the common list headers. Acked-by: Dave Airlie Signed-off-by: Christian König Reviewed-by: Huang Rui Reviewed-by: Junwei Zhang Signed-off-by: Alex Deucher --- include/linux/list.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index de04cc5ed536..edb7628e46ed 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -183,6 +183,29 @@ static inline void list_move_tail(struct list_head *list, list_add_tail(list, head); } +/** + * list_bulk_move_tail - move a subsection of a list to its tail + * @head: the head that will follow our entry + * @first: first entry to move + * @last: last entry to move, can be the same as first + * + * Move all entries between @first and including @last before @head. + * All three entries must belong to the same linked list. + */ +static inline void list_bulk_move_tail(struct list_head *head, + struct list_head *first, + struct list_head *last) +{ + first->prev->next = last->next; + last->next->prev = first->prev; + + head->prev->next = first; + first->prev = head->prev; + + last->next = head; + head->prev = last; +} + /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test -- cgit v1.2.3 From 18b01b16e8bae9cd227909f6e6d2783d74855f65 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Oct 2018 16:08:22 +0200 Subject: PCI: Remove pci_unmap_addr() wrappers for DMA API Only some of these were still used by the cxgb4 driver, and that despite the fact that the driver otherwise uses the generic DMA API. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- include/linux/pci-dma.h | 12 ------------ include/linux/pci.h | 1 - 2 files changed, 13 deletions(-) delete mode 100644 include/linux/pci-dma.h (limited to 'include/linux') diff --git a/include/linux/pci-dma.h b/include/linux/pci-dma.h deleted file mode 100644 index 0f7aa7353ca3..000000000000 --- a/include/linux/pci-dma.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_PCI_DMA_H -#define _LINUX_PCI_DMA_H - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) DEFINE_DMA_UNMAP_ADDR(ADDR_NAME); -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) DEFINE_DMA_UNMAP_LEN(LEN_NAME); -#define pci_unmap_addr dma_unmap_addr -#define pci_unmap_addr_set dma_unmap_addr_set -#define pci_unmap_len dma_unmap_len -#define pci_unmap_len_set dma_unmap_len_set - -#endif diff --git a/include/linux/pci.h b/include/linux/pci.h index 6925828f9f25..e938e80e59c1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1342,7 +1342,6 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, /* kmem_cache style wrapper around pci_alloc_consistent() */ -#include #include #define pci_pool dma_pool -- cgit v1.2.3 From a6f44cf9f5cc60471cf06f3d5391fc6041eb37a5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Oct 2018 16:08:23 +0200 Subject: PCI: Remove pci_set_dma_seg_boundary() The two callers can just use dma_set_seg_boundary() directly. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- include/linux/pci-dma-compat.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h index c3f1b44ade29..558a109ab497 100644 --- a/include/linux/pci-dma-compat.h +++ b/include/linux/pci-dma-compat.h @@ -125,12 +125,6 @@ static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, { return dma_set_max_seg_size(&dev->dev, size); } - -static inline int pci_set_dma_seg_boundary(struct pci_dev *dev, - unsigned long mask) -{ - return dma_set_seg_boundary(&dev->dev, mask); -} #else static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) { return -EIO; } @@ -139,9 +133,6 @@ static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size) { return -EIO; } -static inline int pci_set_dma_seg_boundary(struct pci_dev *dev, - unsigned long mask) -{ return -EIO; } #endif #endif -- cgit v1.2.3 From b0da3498c587c20e64799c4c7ba65a31314b2182 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Oct 2018 16:08:24 +0200 Subject: PCI: Remove pci_set_dma_max_seg_size() The few callers can just use dma_set_max_seg_size ()directly. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- include/linux/pci-dma-compat.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h index 558a109ab497..cb1adf0b78a9 100644 --- a/include/linux/pci-dma-compat.h +++ b/include/linux/pci-dma-compat.h @@ -119,20 +119,11 @@ static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) { return dma_set_coherent_mask(&dev->dev, mask); } - -static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, - unsigned int size) -{ - return dma_set_max_seg_size(&dev->dev, size); -} #else static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) { return -EIO; } static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) { return -EIO; } -static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, - unsigned int size) -{ return -EIO; } #endif #endif -- cgit v1.2.3 From f6a8a19bb11b46d60250ddc4e3e1ba6aa166f488 Mon Sep 17 00:00:00 2001 From: Denis Drozdov Date: Tue, 14 Aug 2018 14:08:51 +0300 Subject: RDMA/netdev: Hoist alloc_netdev_mqs out of the driver netdev has several interfaces that expect to call alloc_netdev_mqs from the core code, with the driver only providing the arguments. This is incompatible with the rdma_netdev interface that returns the netdev directly. Thus re-organize the API used by ipoib so that the verbs core code calls alloc_netdev_mqs for the driver. This is done by allowing the drivers to provide the allocation parameters via a 'get_params' callback and then initializing an allocated netdev as a second step. Fixes: cd565b4b51e5 ("IB/IPoIB: Support acceleration options callbacks") Signed-off-by: Jason Gunthorpe Signed-off-by: Denis Drozdov Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 26a92462f4ce..4b75796cac23 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1228,21 +1228,15 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); -#ifndef CONFIG_MLX5_CORE_IPOIB -static inline -struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, - struct ib_device *ibdev, - const char *name, - void (*setup)(struct net_device *)) -{ - return ERR_PTR(-EOPNOTSUPP); -} -#else +#ifdef CONFIG_MLX5_CORE_IPOIB struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, struct ib_device *ibdev, const char *name, void (*setup)(struct net_device *)); #endif /* CONFIG_MLX5_CORE_IPOIB */ +int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, + struct ib_device *device, + struct rdma_netdev_alloc_params *params); struct mlx5_profile { u64 mask; -- cgit v1.2.3 From 37fdffb217a45609edccbb8b407d031143f551c0 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 21 Aug 2018 14:41:41 +0300 Subject: net/mlx5: WQ, fixes for fragmented WQ buffers API mlx5e netdevice used to calculate fragment edges by a call to mlx5_wq_cyc_get_frag_size(). This calculation did not give the correct indication for queues smaller than a PAGE_SIZE, (broken by default on PowerPC, where PAGE_SIZE == 64KB). Here it is replaced by the correct new calls/API. Since (TX/RX) Work Queues buffers are fragmented, here we introduce changes to the API in core driver, so that it gets a stride index and returns the index of last stride on same fragment, and an additional wrapping function that returns the number of physically contiguous strides that can be written contiguously to the work queue. This obsoletes the following API functions, and their buggy usage in EN driver: * mlx5_wq_cyc_get_frag_size() * mlx5_wq_cyc_ctr2fragix() The new API improves modularity and hides the details of such calculation for mlx5e netdevice and mlx5_ib rdma drivers. New calculation is also more efficient, and improves performance as follows: Packet rate test: pktgen, UDP / IPv4, 64byte, single ring, 8K ring size. Before: 16,477,619 pps After: 17,085,793 pps 3.7% improvement Fixes: 3a2f70331226 ("net/mlx5: Use order-0 allocations for all WQ types") Signed-off-by: Tariq Toukan Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 66d94b4557cf..88a041b73abf 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1032,6 +1032,14 @@ static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, ((fbc->frag_sz_m1 & ix) << fbc->log_stride); } +static inline u32 +mlx5_frag_buf_get_idx_last_contig_stride(struct mlx5_frag_buf_ctrl *fbc, u32 ix) +{ + u32 last_frag_stride_idx = (ix + fbc->strides_offset) | fbc->frag_sz_m1; + + return min_t(u32, last_frag_stride_idx - fbc->strides_offset, fbc->sz_m1); +} + int mlx5_cmd_init(struct mlx5_core_dev *dev); void mlx5_cmd_cleanup(struct mlx5_core_dev *dev); void mlx5_cmd_use_events(struct mlx5_core_dev *dev); -- cgit v1.2.3 From a36700589b85443e28170be59fa11c8a104130a5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 10 Oct 2018 20:29:44 -0500 Subject: signal: Guard against negative signal numbers in copy_siginfo_from_user32 While fixing an out of bounds array access in known_siginfo_layout reported by the kernel test robot it became apparent that the same bug exists in siginfo_layout and affects copy_siginfo_from_user32. The straight forward fix that makes guards against making this mistake in the future and should keep the code size small is to just take an unsigned signal number instead of a signed signal number, as I did to fix known_siginfo_layout. Cc: stable@vger.kernel.org Fixes: cc731525f26a ("signal: Remove kernel interal si_code magic") Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 706a499d1eb1..200ed96a05af 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -40,7 +40,7 @@ enum siginfo_layout { SIL_SYS, }; -enum siginfo_layout siginfo_layout(int sig, int si_code); +enum siginfo_layout siginfo_layout(unsigned sig, int si_code); /* * Define some primitives to manipulate sigset_t. -- cgit v1.2.3 From a6ca88b241d5e929e6e60b12ad8cd288f0ffa256 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 1 Oct 2018 22:36:36 -0700 Subject: trace_uprobe: support reference counter in fd-based uprobe This patch enables uprobes with reference counter in fd-based uprobe. Highest 32 bits of perf_event_attr.config is used to stored offset of the reference count (semaphore). Format information in /sys/bus/event_source/devices/uprobe/format/ is updated to reflect this new feature. Link: http://lkml.kernel.org/r/20181002053636.1896903-1-songliubraving@fb.com Cc: Oleg Nesterov Acked-by: Peter Zijlstra (Intel) Reviewed-and-tested-by: Ravi Bangoria Signed-off-by: Song Liu Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 78a010e19ed4..4130a5497d40 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -575,7 +575,8 @@ extern int bpf_get_kprobe_info(const struct perf_event *event, bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS -extern int perf_uprobe_init(struct perf_event *event, bool is_retprobe); +extern int perf_uprobe_init(struct perf_event *event, + unsigned long ref_ctr_offset, bool is_retprobe); extern void perf_uprobe_destroy(struct perf_event *event); extern int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, -- cgit v1.2.3 From 68c0d69dee594e1488aebe12aa50fd79a3e5e5b5 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 5 Oct 2018 16:59:04 -0700 Subject: hwmon: (core) Add hwmon_in_enable attribute According to hwmon ABI, in%d_enable is a sysfs interface that allows user space to enable and disable the input sensor. So this patch just simply adds the attribute to the list. Signed-off-by: Nicolin Chen Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 9493d4a388db..99e0c1b0b5fb 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -118,6 +118,7 @@ enum hwmon_in_attributes { hwmon_in_max_alarm, hwmon_in_lcrit_alarm, hwmon_in_crit_alarm, + hwmon_in_enable, }; #define HWMON_I_INPUT BIT(hwmon_in_input) @@ -135,6 +136,7 @@ enum hwmon_in_attributes { #define HWMON_I_MAX_ALARM BIT(hwmon_in_max_alarm) #define HWMON_I_LCRIT_ALARM BIT(hwmon_in_lcrit_alarm) #define HWMON_I_CRIT_ALARM BIT(hwmon_in_crit_alarm) +#define HWMON_I_ENABLE BIT(hwmon_in_enable) enum hwmon_curr_attributes { hwmon_curr_input, -- cgit v1.2.3 From b048ae6e6c7062809e4398f4d0bfe80870715d3c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Oct 2018 17:18:19 -0700 Subject: LSM: Rename .security_initcall section to .lsm_info In preparation for switching from initcall to just a regular set of pointers in a section, rename the internal section name. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler Reviewed-by: James Morris Reviewed-by: John Johansen Signed-off-by: James Morris --- include/linux/init.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 2538d176dd1f..77636539e77c 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -133,7 +133,7 @@ static inline initcall_t initcall_from_entry(initcall_entry_t *entry) #endif extern initcall_entry_t __con_initcall_start[], __con_initcall_end[]; -extern initcall_entry_t __security_initcall_start[], __security_initcall_end[]; +extern initcall_entry_t __start_lsm_info[], __end_lsm_info[]; /* Used for contructor calls. */ typedef void (*ctor_fn_t)(void); @@ -236,7 +236,7 @@ extern bool initcall_debug; static exitcall_t __exitcall_##fn __exit_call = fn #define console_initcall(fn) ___define_initcall(fn,, .con_initcall) -#define security_initcall(fn) ___define_initcall(fn,, .security_initcall) +#define security_initcall(fn) ___define_initcall(fn,, .lsm_info) struct obs_kernel_param { const char *str; -- cgit v1.2.3 From 5b89c1bd4c7e5c5ca8c5374fde35ecee6e16496c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Oct 2018 17:18:21 -0700 Subject: LSM: Convert from initcall to struct lsm_info In preparation for doing more interesting LSM init probing, this converts the existing initcall system into an explicit call into a function pointer from a section-collected struct lsm_info array. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler Reviewed-by: James Morris Reviewed-by: John Johansen Signed-off-by: James Morris --- include/linux/init.h | 2 -- include/linux/lsm_hooks.h | 12 ++++++++++++ include/linux/module.h | 1 - 3 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 77636539e77c..9c2aba1dbabf 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -133,7 +133,6 @@ static inline initcall_t initcall_from_entry(initcall_entry_t *entry) #endif extern initcall_entry_t __con_initcall_start[], __con_initcall_end[]; -extern initcall_entry_t __start_lsm_info[], __end_lsm_info[]; /* Used for contructor calls. */ typedef void (*ctor_fn_t)(void); @@ -236,7 +235,6 @@ extern bool initcall_debug; static exitcall_t __exitcall_##fn __exit_call = fn #define console_initcall(fn) ___define_initcall(fn,, .con_initcall) -#define security_initcall(fn) ___define_initcall(fn,, .lsm_info) struct obs_kernel_param { const char *str; diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 97a020c616ad..d13059feca09 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2039,6 +2039,18 @@ extern char *lsm_names; extern void security_add_hooks(struct security_hook_list *hooks, int count, char *lsm); +struct lsm_info { + int (*init)(void); /* Required. */ +}; + +extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; + +#define security_initcall(lsm) \ + static struct lsm_info __lsm_##lsm \ + __used __section(.lsm_info.init) \ + __aligned(sizeof(unsigned long)) \ + = { .init = lsm, } + #ifdef CONFIG_SECURITY_SELINUX_DISABLE /* * Assuring the safety of deleting a security module is up to diff --git a/include/linux/module.h b/include/linux/module.h index f807f15bebbe..264979283756 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -123,7 +123,6 @@ extern void cleanup_module(void); #define late_initcall_sync(fn) module_init(fn) #define console_initcall(fn) module_init(fn) -#define security_initcall(fn) module_init(fn) /* Each module must use one module_init(). */ #define module_init(initfn) \ -- cgit v1.2.3 From 3d6e5f6dcf6561e57b6466e43e14029fb196028d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Oct 2018 17:18:23 -0700 Subject: LSM: Convert security_initcall() into DEFINE_LSM() Instead of using argument-based initializers, switch to defining the contents of struct lsm_info on a per-LSM basis. This also drops the final use of the now inaccurate "initcall" naming. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler Reviewed-by: James Morris Signed-off-by: James Morris --- include/linux/lsm_hooks.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d13059feca09..9c6b4198ff5a 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2045,11 +2045,10 @@ struct lsm_info { extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; -#define security_initcall(lsm) \ +#define DEFINE_LSM(lsm) \ static struct lsm_info __lsm_##lsm \ __used __section(.lsm_info.init) \ - __aligned(sizeof(unsigned long)) \ - = { .init = lsm, } + __aligned(sizeof(unsigned long)) #ifdef CONFIG_SECURITY_SELINUX_DISABLE /* -- cgit v1.2.3 From 07aed2f2af5a5892ced035dbcf3993f630825fc3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Oct 2018 17:18:24 -0700 Subject: LSM: Record LSM name in struct lsm_info In preparation for making LSM selections outside of the LSMs, include the name of LSMs in struct lsm_info. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler Signed-off-by: James Morris --- include/linux/lsm_hooks.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 9c6b4198ff5a..ae159b02f3ab 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2040,6 +2040,7 @@ extern void security_add_hooks(struct security_hook_list *hooks, int count, char *lsm); struct lsm_info { + const char *name; /* Required. */ int (*init)(void); /* Required. */ }; -- cgit v1.2.3 From af7d6cce53694a88d6a1bb60c9a239a6a5144459 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 9 Oct 2018 17:48:14 +0200 Subject: net: ipv4: update fnhe_pmtu when first hop's MTU changes Since commit 5aad1de5ea2c ("ipv4: use separate genid for next hop exceptions"), exceptions get deprecated separately from cached routes. In particular, administrative changes don't clear PMTU anymore. As Stefano described in commit e9fa1495d738 ("ipv6: Reflect MTU changes on PMTU of exceptions for MTU-less routes"), the PMTU discovered before the local MTU change can become stale: - if the local MTU is now lower than the PMTU, that PMTU is now incorrect - if the local MTU was the lowest value in the path, and is increased, we might discover a higher PMTU Similarly to what commit e9fa1495d738 did for IPv6, update PMTU in those cases. If the exception was locked, the discovered PMTU was smaller than the minimal accepted PMTU. In that case, if the new local MTU is smaller than the current PMTU, let PMTU discovery figure out if locking of the exception is still needed. To do this, we need to know the old link MTU in the NETDEV_CHANGEMTU notifier. By the time the notifier is called, dev->mtu has been changed. This patch adds the old MTU as additional information in the notifier structure, and a new call_netdevice_notifiers_u32() function. Fixes: 5aad1de5ea2c ("ipv4: use separate genid for next hop exceptions") Signed-off-by: Sabrina Dubroca Reviewed-by: Stefano Brivio Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c7861e4b402c..d837dad24b4c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2458,6 +2458,13 @@ struct netdev_notifier_info { struct netlink_ext_ack *extack; }; +struct netdev_notifier_info_ext { + struct netdev_notifier_info info; /* must be first */ + union { + u32 mtu; + } ext; +}; + struct netdev_notifier_change_info { struct netdev_notifier_info info; /* must be first */ unsigned int flags_changed; -- cgit v1.2.3 From ce76d938dd98817f998c905e01fbb99b072c0bf6 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 5 Oct 2018 15:43:05 +0300 Subject: lib: Add memcat_p(): paste 2 pointer arrays together This adds a helper to paste 2 pointer arrays together, useful for merging various types of attribute arrays. There are a few places in the kernel tree where this is open coded, and I just added one more in the STM class. The naming is inspired by memset_p() and memcat(), and partial credit for it goes to Andy Shevchenko. This patch adds the function wrapped in a type-enforcing macro and a test module. Signed-off-by: Alexander Shishkin Reviewed-by: Andy Shevchenko Tested-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/string.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 4a5a0eb7df51..27d0482e5e05 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -131,6 +131,13 @@ static inline void *memset_p(void **p, void *v, __kernel_size_t n) return memset64((uint64_t *)p, (uintptr_t)v, n); } +extern void **__memcat_p(void **a, void **b); +#define memcat_p(a, b) ({ \ + BUILD_BUG_ON_MSG(!__same_type(*(a), *(b)), \ + "type mismatch in memcat_p()"); \ + (typeof(*a) *)__memcat_p((void **)(a), (void **)(b)); \ +}) + #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif -- cgit v1.2.3 From f458e832ba510f843807fc2c2906a8fb59554c9f Mon Sep 17 00:00:00 2001 From: Chaitanya T K Date: Sat, 6 Oct 2018 19:34:59 +0200 Subject: mac80211: minstrel: Enable STBC and LDPC for VHT Rates If peer support reception of STBC and LDPC, enable them for better performance. Signed-off-by: Chaitanya TK Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index c4809ad8ab46..0ef67f837ae1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1670,6 +1670,7 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_VHT_CAP_RXSTBC_3 0x00000300 #define IEEE80211_VHT_CAP_RXSTBC_4 0x00000400 #define IEEE80211_VHT_CAP_RXSTBC_MASK 0x00000700 +#define IEEE80211_VHT_CAP_RXSTBC_SHIFT 8 #define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 #define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 #define IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT 13 -- cgit v1.2.3 From 55ef8262f2b1b31762b045b14182db3cc8f607d1 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 10 Oct 2018 19:09:28 +0200 Subject: spi: pxa2xx: Use an enum for type That seems to be the correct type. Signed-off-by: Lubomir Rintel Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 13b4244d44c1..262e1f318836 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -217,7 +217,7 @@ struct ssp_device { const char *label; int port_id; - int type; + enum pxa_ssp_type type; int use_count; int irq; -- cgit v1.2.3 From 87ae1d2d70772d661162de03e56c8d1cc5f12650 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 10 Oct 2018 19:09:29 +0200 Subject: spi: pxa2xx: Add devicetree support The MMP2 platform, that uses device tree, has this controller. Let's add devicetree alongside platform & PCI. Signed-off-by: Lubomir Rintel Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 262e1f318836..979087e021f3 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -196,6 +196,7 @@ enum pxa_ssp_type { PXA27x_SSP, PXA3xx_SSP, PXA168_SSP, + MMP2_SSP, PXA910_SSP, CE4100_SSP, QUARK_X1000_SSP, -- cgit v1.2.3 From 81b45683487a51b0f4d3b29d37f20d6d078544e4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 26 Aug 2018 03:16:29 +0900 Subject: compiler.h: give up __compiletime_assert_fallback() __compiletime_assert_fallback() is supposed to stop building earlier by using the negative-array-size method in case the compiler does not support "error" attribute, but has never worked like that. You can simply try: BUILD_BUG_ON(1); GCC immediately terminates the build, but Clang does not report anything because Clang does not support the "error" attribute now. It will later fail at link time, but __compiletime_assert_fallback() is not working at least. The root cause is commit 1d6a0d19c855 ("bug.h: prevent double evaluation of `condition' in BUILD_BUG_ON"). Prior to that commit, BUILD_BUG_ON() was checked by the negative-array-size method *and* the link-time trick. Since that commit, the negative-array-size is not effective because '__cond' is no longer constant. As the comment in says, GCC (and Clang as well) only emits the error for obvious cases. When '__cond' is a variable, ((void)sizeof(char[1 - 2 * __cond])) ... is not obvious for the compiler to know the array size is negative. Reverting that commit would break BUILD_BUG() because negative-size-array is evaluated before the code is optimized out. Let's give up __compiletime_assert_fallback(). This commit does not change the current behavior since it just rips off the useless code. Signed-off-by: Masahiro Yamada Reviewed-by: Kees Cook Reviewed-by: Nick Desaulniers Signed-off-by: Kees Cook --- include/linux/compiler.h | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 681d866efb1e..87c776c3ce73 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -314,29 +314,14 @@ static inline void *offset_to_ptr(const int *off) #endif #ifndef __compiletime_error # define __compiletime_error(message) -/* - * Sparse complains of variable sized arrays due to the temporary variable in - * __compiletime_assert. Unfortunately we can't just expand it out to make - * sparse see a constant array size without breaking compiletime_assert on old - * versions of GCC (e.g. 4.2.4), so hide the array from sparse altogether. - */ -# ifndef __CHECKER__ -# define __compiletime_error_fallback(condition) \ - do { ((void)sizeof(char[1 - 2 * condition])); } while (0) -# endif -#endif -#ifndef __compiletime_error_fallback -# define __compiletime_error_fallback(condition) do { } while (0) #endif #ifdef __OPTIMIZE__ # define __compiletime_assert(condition, msg, prefix, suffix) \ do { \ - int __cond = !(condition); \ extern void prefix ## suffix(void) __compiletime_error(msg); \ - if (__cond) \ + if (!(condition)) \ prefix ## suffix(); \ - __compiletime_error_fallback(__cond); \ } while (0) #else # define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0) -- cgit v1.2.3 From 953923c09fe83255ae11845db1c9eb576ba73df8 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 11 Oct 2018 11:06:29 -0400 Subject: dm: rename DM_TYPE_MQ_REQUEST_BASED to DM_TYPE_REQUEST_BASED Now that request-based DM is only using blk-mq, there is no need to differentiate between legacy "rq" and new "mq". We're back to a single request-based DM -- and there was much rejoicing! Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 6fb0808e87c8..8d937754aa0c 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -26,9 +26,8 @@ enum dm_queue_mode { DM_TYPE_NONE = 0, DM_TYPE_BIO_BASED = 1, DM_TYPE_REQUEST_BASED = 2, - DM_TYPE_MQ_REQUEST_BASED = 3, - DM_TYPE_DAX_BIO_BASED = 4, - DM_TYPE_NVME_BIO_BASED = 5, + DM_TYPE_DAX_BIO_BASED = 3, + DM_TYPE_NVME_BIO_BASED = 4, }; typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t; -- cgit v1.2.3 From 3f2aa244ee1a0d17ed5b6c86564d2c1b24d1c96b Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Wed, 3 Oct 2018 13:21:07 +0100 Subject: TC: Set DMA masks for devices Fix a TURBOchannel support regression with commit 205e1b7f51e4 ("dma-mapping: warn when there is no coherent_dma_mask") that caused coherent DMA allocations to produce a warning such as: defxx: v1.11 2014/07/01 Lawrence V. Stefani and others tc1: DEFTA at MMIO addr = 0x1e900000, IRQ = 20, Hardware addr = 08-00-2b-a3-a3-29 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1 at ./include/linux/dma-mapping.h:516 dfx_dev_register+0x670/0x678 Modules linked in: CPU: 0 PID: 1 Comm: swapper Not tainted 4.19.0-rc6 #2 Stack : ffffffff8009ffc0 fffffffffffffec0 0000000000000000 ffffffff80647650 0000000000000000 0000000000000000 ffffffff806f5f80 ffffffffffffffff 0000000000000000 0000000000000000 0000000000000001 ffffffff8065d4e8 98000000031b6300 ffffffff80563478 ffffffff805685b0 ffffffffffffffff 0000000000000000 ffffffff805d6720 0000000000000204 ffffffff80388df8 0000000000000000 0000000000000009 ffffffff8053efd0 ffffffff806657d0 0000000000000000 ffffffff803177f8 0000000000000000 ffffffff806d0000 9800000003078000 980000000307b9e0 000000001e900000 ffffffff80067940 0000000000000000 ffffffff805d6720 0000000000000204 ffffffff80388df8 ffffffff805176c0 ffffffff8004dc78 0000000000000000 ffffffff80067940 ... Call Trace: [] show_stack+0xa0/0x130 [] __warn+0x128/0x170 ---[ end trace b1d1e094f67f3bb2 ]--- This is because the TURBOchannel bus driver fails to set the coherent DMA mask for devices enumerated. Set the regular and coherent DMA masks for TURBOchannel devices then, observing that the bus protocol supports a 34-bit (16GiB) DMA address space, by interpreting the value presented in the address cycle across the 32 `ad' lines as a 32-bit word rather than byte address[1]. The architectural size of the TURBOchannel DMA address space exceeds the maximum amount of RAM any actual TURBOchannel system in existence may have, hence both masks are the same. This removes the warning shown above. References: [1] "TURBOchannel Hardware Specification", EK-369AA-OD-007B, Digital Equipment Corporation, January 1993, Section "DMA", pp. 1-15 -- 1-17 Signed-off-by: Maciej W. Rozycki Signed-off-by: Paul Burton Patchwork: https://patchwork.linux-mips.org/patch/20835/ Fixes: 205e1b7f51e4 ("dma-mapping: warn when there is no coherent_dma_mask") Cc: stable@vger.kernel.org # 4.16+ Cc: Ralf Baechle --- include/linux/tc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tc.h b/include/linux/tc.h index f92511e57cdb..a60639f37963 100644 --- a/include/linux/tc.h +++ b/include/linux/tc.h @@ -84,6 +84,7 @@ struct tc_dev { device. */ struct device dev; /* Generic device interface. */ struct resource resource; /* Address space of this device. */ + u64 dma_mask; /* DMA addressable range. */ char vendor[9]; char name[9]; char firmware[9]; -- cgit v1.2.3 From 4822e902f9bdffaea2817471365e000966f0d1a1 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 11 Oct 2018 10:07:06 +0300 Subject: block: describe difference between flags IO_STAT and STATS This adds reasonable comments, but they definitely needs better names. Signed-off-by: Konstantin Khlebnikov Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dee46c20701b..61207560e826 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -108,7 +108,7 @@ typedef __u32 __bitwise req_flags_t; #define RQF_QUIET ((__force req_flags_t)(1 << 11)) /* elevator private data attached */ #define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) -/* account I/O stat */ +/* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) /* request came from our alloc pool */ #define RQF_ALLOCED ((__force req_flags_t)(1 << 14)) @@ -116,7 +116,7 @@ typedef __u32 __bitwise req_flags_t; #define RQF_PM ((__force req_flags_t)(1 << 15)) /* on IO scheduler merge hash */ #define RQF_HASHED ((__force req_flags_t)(1 << 16)) -/* IO stats tracking on */ +/* track IO completion time */ #define RQF_STATS ((__force req_flags_t)(1 << 17)) /* Look at ->special_vec for the actual data payload instead of the bio chain. */ @@ -685,7 +685,7 @@ struct request_queue { #define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ #define QUEUE_FLAG_NONROT 9 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ -#define QUEUE_FLAG_IO_STAT 10 /* do IO stats */ +#define QUEUE_FLAG_IO_STAT 10 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_DISCARD 11 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 12 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 13 /* Contributes to random pool */ @@ -699,7 +699,7 @@ struct request_queue { #define QUEUE_FLAG_FUA 21 /* device supports FUA writes */ #define QUEUE_FLAG_FLUSH_NQ 22 /* flush not queueuable */ #define QUEUE_FLAG_DAX 23 /* device supports DAX */ -#define QUEUE_FLAG_STATS 24 /* track rq completion times */ +#define QUEUE_FLAG_STATS 24 /* track IO start and completion times */ #define QUEUE_FLAG_POLL_STATS 25 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ -- cgit v1.2.3 From 5fd752b6b3a2233972ce1726df8bdb40886113a9 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 11 Oct 2018 12:07:14 +0800 Subject: leds: core: Introduce LED pattern trigger This patch adds a new LED trigger that LED device can configure to employ software or hardware pattern engine. Consumers can write 'pattern' file to enable the software pattern which alters the brightness for the specified duration with one software timer. Moreover consumers can write 'hw_pattern' file to enable the hardware pattern for some LED controllers which can autonomously control brightness over time, according to some preprogrammed hardware patterns. Signed-off-by: Raphael Teysseyre Signed-off-by: Baolin Wang Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 834683d603f9..7393a316d9fa 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -22,6 +22,7 @@ #include struct device; +struct led_pattern; /* * LED Core */ @@ -88,6 +89,10 @@ struct led_classdev { unsigned long *delay_on, unsigned long *delay_off); + int (*pattern_set)(struct led_classdev *led_cdev, + struct led_pattern *pattern, u32 len, int repeat); + int (*pattern_clear)(struct led_classdev *led_cdev); + struct device *dev; const struct attribute_group **groups; @@ -472,4 +477,14 @@ static inline void led_classdev_notify_brightness_hw_changed( struct led_classdev *led_cdev, enum led_brightness brightness) { } #endif +/** + * struct led_pattern - pattern interval settings + * @delta_t: pattern interval delay, in milliseconds + * @brightness: pattern interval brightness + */ +struct led_pattern { + u32 delta_t; + int brightness; +}; + #endif /* __LINUX_LEDS_H_INCLUDED */ -- cgit v1.2.3 From ca2b497253ad01c80061a1f3ee9eb91b5d54a849 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 5 Oct 2018 13:24:36 +0100 Subject: arm64: perf: Reject stand-alone CHAIN events for PMUv3 It doesn't make sense for a perf event to be configured as a CHAIN event in isolation, so extend the arm_pmu structure with a ->filter_match() function to allow the backend PMU implementation to reject CHAIN events early. Cc: Reviewed-by: Suzuki K Poulose Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 10f92e1d8e7b..bf309ff6f244 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -99,6 +99,7 @@ struct arm_pmu { void (*stop)(struct arm_pmu *); void (*reset)(void *); int (*map_event)(struct perf_event *event); + int (*filter_match)(struct perf_event *event); int num_events; bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 -- cgit v1.2.3 From 9c2120090586d7e509faa885988d4eb2441fabc2 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 10 Oct 2018 19:09:27 +0200 Subject: PCI: Provide pci_match_id() with CONFIG_PCI=n This spares drivers from #ifdef-ing on CONFIG_PCI if the driver can be optionally built on machines without PCI bus. Consistent with acpi_driver_match_device() and similar. Acked-by: Bjorn Helgaas Signed-off-by: Lubomir Rintel Signed-off-by: Mark Brown --- include/linux/pci.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index e72ca8dd6241..d2f14eb23ea4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1702,6 +1702,10 @@ static inline int pci_irqd_intx_xlate(struct irq_domain *d, unsigned long *out_hwirq, unsigned int *out_type) { return -EINVAL; } + +static inline const struct pci_device_id *pci_match_id(const struct pci_device_id *ids, + struct pci_dev *dev) +{ return NULL; } #endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ -- cgit v1.2.3 From b0ce7b29bfcd090ddba476f45a75ec0a797b048a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 12 Oct 2018 14:54:12 +0200 Subject: regulator/gpio: Allow nonexclusive GPIO access This allows nonexclusive (simultaneous) access to a single GPIO line for the fixed regulator enable line. This happens when several regulators use the same GPIO for enabling and disabling a regulator, and all need a handle on their GPIO descriptor. This solution with a special flag is not entirely elegant and should ideally be replaced by something more careful as this makes it possible for several consumers to enable/disable the same GPIO line to the left and right without any consistency. The current use inside the regulator core should however be fine as it takes special care to handle this. For the state of the GPIO backend, this is still the lesser evil compared to going back to global GPIO numbers. Cc: Marek Szyprowski Cc: Jon Hunter Fixes: efdfeb079cc3 ("regulator: fixed: Convert to use GPIO descriptor only") Reported-by: Marek Szyprowski Tested-by: Jon Hunter Tested-by: Marek Szyprowski Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- include/linux/gpio/consumer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 21ddbe440030..33695a1d8b35 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -30,6 +30,7 @@ struct gpio_descs { #define GPIOD_FLAGS_BIT_DIR_OUT BIT(1) #define GPIOD_FLAGS_BIT_DIR_VAL BIT(2) #define GPIOD_FLAGS_BIT_OPEN_DRAIN BIT(3) +#define GPIOD_FLAGS_BIT_NONEXCLUSIVE BIT(4) /** * Optional flags that can be passed to one of gpiod_* to configure direction -- cgit v1.2.3 From 81732b26e05994552f347746eb11762e986079a0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Sep 2018 23:28:07 -0400 Subject: usb-serial: begin switching to ->[sg]et_serial() add such methods for usb_serial_driver, provide tty_operations ->[sg]et_serial() calling those. For now the lack of methods in driver means ENOIOCTLCMD from usb-serial ->[sg]et_serial(), making tty_ioctl() fall back to calling ->ioctl(). Once all drivers are converted, we'll be returning -ENOTTY instead, completing the switchover. Reviewed-by: Johan Hovold Signed-off-by: Al Viro --- include/linux/usb/serial.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 106551a5616e..1c19f77ed541 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -285,6 +285,8 @@ struct usb_serial_driver { int (*write_room)(struct tty_struct *tty); int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); + int (*get_serial)(struct tty_struct *tty, struct serial_struct *ss); + int (*set_serial)(struct tty_struct *tty, struct serial_struct *ss); void (*set_termios)(struct tty_struct *tty, struct usb_serial_port *port, struct ktermios *old); void (*break_ctl)(struct tty_struct *tty, int break_state); -- cgit v1.2.3 From f0193d3ea73b966b5dbfa272c8228d743b8856ef Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 13 Sep 2018 22:12:15 -0400 Subject: change semantics of ldisc ->compat_ioctl() First of all, make it return int. Returning long when native method had never allowed that is ridiculous and inconvenient. More importantly, change the caller; if ldisc ->compat_ioctl() is NULL or returns -ENOIOCTLCMD, tty_compat_ioctl() will try to feed cmd and compat_ptr(arg) to ldisc's native ->ioctl(). That simplifies ->compat_ioctl() instances quite a bit - they only need to deal with ioctls that are neither generic tty ones (those would get shunted off to tty_ioctl()) nor simple compat pointer ones. Note that something like TCFLSH won't reach ->compat_ioctl(), even if ldisc ->ioctl() does handle it - it will be recognized earlier and passed to tty_ioctl() (and ultimately - ldisc ->ioctl()). For many ldiscs it means that NULL ->compat_ioctl() does the right thing. Those where it won't serve (see e.g. n_r3964.c) are also easily dealt with - we need to handle the numeric-argument ioctls (calling the native instance) and, if such would exist, the ioctls that need layout conversion, etc. All in-tree ldiscs dealt with. Signed-off-by: Al Viro --- include/linux/tty_ldisc.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 840894ca3fc0..b1e6043e9917 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -54,11 +54,17 @@ * low-level driver can "grab" an ioctl request before the line * discpline has a chance to see it. * - * long (*compat_ioctl)(struct tty_struct * tty, struct file * file, + * int (*compat_ioctl)(struct tty_struct * tty, struct file * file, * unsigned int cmd, unsigned long arg); * * Process ioctl calls from 32-bit process on 64-bit system * + * NOTE: only ioctls that are neither "pointer to compatible + * structure" nor tty-generic. Something private that takes + * an integer or a pointer to wordsize-sensitive structure + * belongs here, but most of ldiscs will happily leave + * it NULL. + * * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); * * This function notifies the line discpline that a change has @@ -184,7 +190,7 @@ struct tty_ldisc_ops { const unsigned char *buf, size_t nr); int (*ioctl)(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); - long (*compat_ioctl)(struct tty_struct *tty, struct file *file, + int (*compat_ioctl)(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); void (*set_termios)(struct tty_struct *tty, struct ktermios *old); __poll_t (*poll)(struct tty_struct *, struct file *, -- cgit v1.2.3 From cc53aabcc283c36274d3f3ce9adc4b40c21d4838 Mon Sep 17 00:00:00 2001 From: Govind Singh Date: Thu, 11 Oct 2018 13:16:01 +0300 Subject: firmware: qcom: scm: Add WLAN VMID for Qualcomm SCM interface Add WLAN related VMID's to support wlan driver to set up the remote's permissions call via TrustZone. Signed-off-by: Govind Singh Reviewed-by: Bjorn Andersson Acked-by: Niklas Cassel Reviewed-by: Brian Norris Signed-off-by: Kalle Valo --- include/linux/qcom_scm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 5d65521260b3..06996ad4f2bc 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2010-2015, The Linux Foundation. All rights reserved. +/* Copyright (c) 2010-2015, 2018, The Linux Foundation. All rights reserved. * Copyright (C) 2015 Linaro Ltd. * * This program is free software; you can redistribute it and/or modify @@ -33,6 +33,8 @@ struct qcom_scm_vmperm { #define QCOM_SCM_VMID_HLOS 0x3 #define QCOM_SCM_VMID_MSS_MSA 0xF +#define QCOM_SCM_VMID_WLAN 0x18 +#define QCOM_SCM_VMID_WLAN_CE 0x19 #define QCOM_SCM_PERM_READ 0x4 #define QCOM_SCM_PERM_WRITE 0x2 #define QCOM_SCM_PERM_EXEC 0x1 -- cgit v1.2.3 From c6aed238b7a9b15a5c90a0c31f1d36577b5d2cbe Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:47 +0200 Subject: remoteproc: modify vring allocation to rely on centralized carveout allocator Current version of rproc_alloc_vring function supports only dynamic vring allocation. This patch allows to allocate vrings based on memory region declatation. Vrings are now manage like memory carveouts, to communize memory management code in rproc_alloc_registered_carveouts(). Allocated buffer is retrieved in rp_find_vq() thanks to rproc_find_carveout_by_name() functions for. This patch sets vrings names to vdev"x"vring"y" with x vdev index in resource table and y vring index in vdev. This will be updated when name will be associated to vdev in firmware resource table. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index d4cabe8da507..8bb0cf0416f1 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -454,6 +454,7 @@ struct rproc_dump_segment { * @has_iommu: flag to indicate if remote processor is behind an MMU * @auto_boot: flag to indicate if remote processor should be auto-started * @dump_segments: list of segments in the firmware + * @nb_vdev: number of vdev currently handled by rproc */ struct rproc { struct list_head node; @@ -486,6 +487,7 @@ struct rproc { bool has_iommu; bool auto_boot; struct list_head dump_segments; + int nb_vdev; }; /** @@ -513,7 +515,6 @@ struct rproc_subdev { /** * struct rproc_vring - remoteproc vring state * @va: virtual address - * @dma: dma address * @len: length, in bytes * @da: device address * @align: vring alignment @@ -523,7 +524,6 @@ struct rproc_subdev { */ struct rproc_vring { void *va; - dma_addr_t dma; int len; u32 da; u32 align; @@ -542,6 +542,7 @@ struct rproc_vring { * @vdev: the virio device * @vring: the vrings for this vdev * @rsc_offset: offset of the vdev's resource entry + * @index: vdev position versus other vdev declared in resource table */ struct rproc_vdev { struct kref refcount; @@ -554,6 +555,7 @@ struct rproc_vdev { struct virtio_device vdev; struct rproc_vring vring[RVDEV_NUM_VRINGS]; u32 rsc_offset; + u32 index; }; struct rproc *rproc_get_by_phandle(phandle phandle); -- cgit v1.2.3 From 722fb61e2ed39473297157839ec7230b77fd6940 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 10 Oct 2018 12:51:32 +0900 Subject: mmc: tmio: remove TMIO_MMC_HAVE_HIGH_REG flag TMIO_MMC_HAVE_HIGH_REG is confusing due to its counter-intuitive name. All the TMIO MMC variants (TMIO MMC, Renesas SDHI, UniPhier SD) actually have high registers. It is just that each of them implements its own registers there. The original IP from Panasonic only defines registers 0x00-0xff in the bus_shift=1 review. The register area above them is platform-dependent. In fact, TMIO_MMC_HAVE_HIGH_REG is set only by tmio-mmc.c and used to test the accessibility of CTL_SDIO_REGS. Because it is specific to the TMIO MFD variant, the right thing to do is to move such registers to tmio_mmc.c and delete the TMIO_MMC_HAVE_HIGH_REG flag. Signed-off-by: Masahiro Yamada Reviewed-by: Wolfram Sang Tested-by: Wolfram Sang Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 77866214ab51..1e70060c92ce 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -61,13 +61,6 @@ */ #define TMIO_MMC_USE_GPIO_CD BIT(5) -/* - * Some controllers doesn't have over 0x100 register. - * it is used to checking accessibility of - * CTL_SD_CARD_CLK_CTL / CTL_CLK_AND_WAIT_CTL - */ -#define TMIO_MMC_HAVE_HIGH_REG BIT(6) - /* * Some controllers have CMD12 automatically * issue/non-issue register -- cgit v1.2.3 From 18127429a854e7607b859484880b8e26cee9ddab Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 15 Oct 2018 15:43:06 +0200 Subject: bitops: protect variables in set_mask_bits() macro Unprotected naming of local variables within the set_mask_bits() can easily lead to using the wrong scope. Noticed this when "set_mask_bits(&foo->bar, 0, mask)" behaved as no-op. Signed-off-by: Miklos Szeredi Fixes: 00a1a053ebe5 ("ext4: atomically set inode->i_flags in ext4_set_inode_flags()") Cc: Theodore Ts'o --- include/linux/bitops.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 7ddb1349394d..d18ee0e63c32 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -236,17 +236,17 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, #ifdef __KERNEL__ #ifndef set_mask_bits -#define set_mask_bits(ptr, _mask, _bits) \ +#define set_mask_bits(ptr, mask, bits) \ ({ \ - const typeof(*ptr) mask = (_mask), bits = (_bits); \ - typeof(*ptr) old, new; \ + const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \ + typeof(*(ptr)) old__, new__; \ \ do { \ - old = READ_ONCE(*ptr); \ - new = (old & ~mask) | bits; \ - } while (cmpxchg(ptr, old, new) != old); \ + old__ = READ_ONCE(*(ptr)); \ + new__ = (old__ & ~mask__) | bits__; \ + } while (cmpxchg(ptr, old__, new__) != old__); \ \ - new; \ + new__; \ }) #endif -- cgit v1.2.3 From edfa87281f4fa1b78a21f6db999935a2faa2f6b8 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 15 Oct 2018 15:43:06 +0200 Subject: bitops: protect variables in bit_clear_unless() macro Unprotected naming of local variables within bit_clear_unless() can easily lead to using the wrong scope. Noticed this by code review after having hit this issue in set_mask_bits() Signed-off-by: Miklos Szeredi Fixes: 85ad1d13ee9b ("md: set MD_CHANGE_PENDING in a atomic region") Cc: Guoqing Jiang --- include/linux/bitops.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index d18ee0e63c32..705f7c442691 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -251,18 +251,18 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, #endif #ifndef bit_clear_unless -#define bit_clear_unless(ptr, _clear, _test) \ +#define bit_clear_unless(ptr, clear, test) \ ({ \ - const typeof(*ptr) clear = (_clear), test = (_test); \ - typeof(*ptr) old, new; \ + const typeof(*(ptr)) clear__ = (clear), test__ = (test);\ + typeof(*(ptr)) old__, new__; \ \ do { \ - old = READ_ONCE(*ptr); \ - new = old & ~clear; \ - } while (!(old & test) && \ - cmpxchg(ptr, old, new) != old); \ + old__ = READ_ONCE(*(ptr)); \ + new__ = old__ & ~clear__; \ + } while (!(old__ & test__) && \ + cmpxchg(ptr, old__, new__) != old__); \ \ - !(old & test); \ + !(old__ & test__); \ }) #endif -- cgit v1.2.3 From 604326b41a6fb9b4a78b6179335decee0365cd8c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 13 Oct 2018 02:45:58 +0200 Subject: bpf, sockmap: convert to generic sk_msg interface Add a generic sk_msg layer, and convert current sockmap and later kTLS over to make use of it. While sk_buff handles network packet representation from netdevice up to socket, sk_msg handles data representation from application to socket layer. This means that sk_msg framework spans across ULP users in the kernel, and enables features such as introspection or filtering of data with the help of BPF programs that operate on this data structure. Latter becomes in particular useful for kTLS where data encryption is deferred into the kernel, and as such enabling the kernel to perform L7 introspection and policy based on BPF for TLS connections where the record is being encrypted after BPF has run and came to a verdict. In order to get there, first step is to transform open coding of scatter-gather list handling into a common core framework that subsystems can use. The code itself has been split and refactored into three bigger pieces: i) the generic sk_msg API which deals with managing the scatter gather ring, providing helpers for walking and mangling, transferring application data from user space into it, and preparing it for BPF pre/post-processing, ii) the plain sock map itself where sockets can be attached to or detached from; these bits are independent of i) which can now be used also without sock map, and iii) the integration with plain TCP as one protocol to be used for processing L7 application data (later this could e.g. also be extended to other protocols like UDP). The semantics are the same with the old sock map code and therefore no change of user facing behavior or APIs. While pursuing this work it also helped finding a number of bugs in the old sockmap code that we've fixed already in earlier commits. The test_sockmap kselftest suite passes through fine as well. Joint work with John. Signed-off-by: Daniel Borkmann Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 33 ++--- include/linux/bpf_types.h | 2 +- include/linux/filter.h | 21 --- include/linux/skmsg.h | 371 ++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 383 insertions(+), 44 deletions(-) create mode 100644 include/linux/skmsg.h (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9b558713447f..e60fff48288b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -737,33 +737,18 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) } #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ -#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_INET) -struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); -struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key); -int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); -int sockmap_get_from_fd(const union bpf_attr *attr, int type, - struct bpf_prog *prog); +#if defined(CONFIG_BPF_STREAM_PARSER) +int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which); +int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); #else -static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) -{ - return NULL; -} - -static inline struct sock *__sock_hash_lookup_elem(struct bpf_map *map, - void *key) -{ - return NULL; -} - -static inline int sock_map_prog(struct bpf_map *map, - struct bpf_prog *prog, - u32 type) +static inline int sock_map_prog_update(struct bpf_map *map, + struct bpf_prog *prog, u32 which) { return -EOPNOTSUPP; } -static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type, - struct bpf_prog *prog) +static inline int sock_map_get_from_fd(const union bpf_attr *attr, + struct bpf_prog *prog) { return -EINVAL; } @@ -839,6 +824,10 @@ extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; +extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; +extern const struct bpf_func_proto bpf_msg_redirect_map_proto; +extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; +extern const struct bpf_func_proto bpf_sk_redirect_map_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 5432f4c9f50e..fa48343a5ea1 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -57,7 +57,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) -#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_INET) +#if defined(CONFIG_BPF_STREAM_PARSER) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index 6791a0ac0139..5771874bc01e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -520,24 +520,6 @@ struct bpf_skb_data_end { void *data_end; }; -struct sk_msg_buff { - void *data; - void *data_end; - __u32 apply_bytes; - __u32 cork_bytes; - int sg_copybreak; - int sg_start; - int sg_curr; - int sg_end; - struct scatterlist sg_data[MAX_SKB_FRAGS]; - bool sg_copy[MAX_SKB_FRAGS]; - __u32 flags; - struct sock *sk_redir; - struct sock *sk; - struct sk_buff *skb; - struct list_head list; -}; - struct bpf_redirect_info { u32 ifindex; u32 flags; @@ -833,9 +815,6 @@ void xdp_do_flush_map(void); void bpf_warn_invalid_xdp_action(u32 act); -struct sock *do_sk_redirect_map(struct sk_buff *skb); -struct sock *do_msg_redirect_map(struct sk_msg_buff *md); - #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h new file mode 100644 index 000000000000..95678103c4a0 --- /dev/null +++ b/include/linux/skmsg.h @@ -0,0 +1,371 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ + +#ifndef _LINUX_SKMSG_H +#define _LINUX_SKMSG_H + +#include +#include +#include +#include + +#include +#include +#include + +#define MAX_MSG_FRAGS MAX_SKB_FRAGS + +enum __sk_action { + __SK_DROP = 0, + __SK_PASS, + __SK_REDIRECT, + __SK_NONE, +}; + +struct sk_msg_sg { + u32 start; + u32 curr; + u32 end; + u32 size; + u32 copybreak; + bool copy[MAX_MSG_FRAGS]; + struct scatterlist data[MAX_MSG_FRAGS]; +}; + +struct sk_msg { + struct sk_msg_sg sg; + void *data; + void *data_end; + u32 apply_bytes; + u32 cork_bytes; + u32 flags; + struct sk_buff *skb; + struct sock *sk_redir; + struct sock *sk; + struct list_head list; +}; + +struct sk_psock_progs { + struct bpf_prog *msg_parser; + struct bpf_prog *skb_parser; + struct bpf_prog *skb_verdict; +}; + +enum sk_psock_state_bits { + SK_PSOCK_TX_ENABLED, +}; + +struct sk_psock_link { + struct list_head list; + struct bpf_map *map; + void *link_raw; +}; + +struct sk_psock_parser { + struct strparser strp; + bool enabled; + void (*saved_data_ready)(struct sock *sk); +}; + +struct sk_psock_work_state { + struct sk_buff *skb; + u32 len; + u32 off; +}; + +struct sk_psock { + struct sock *sk; + struct sock *sk_redir; + u32 apply_bytes; + u32 cork_bytes; + u32 eval; + struct sk_msg *cork; + struct sk_psock_progs progs; + struct sk_psock_parser parser; + struct sk_buff_head ingress_skb; + struct list_head ingress_msg; + unsigned long state; + struct list_head link; + spinlock_t link_lock; + refcount_t refcnt; + void (*saved_unhash)(struct sock *sk); + void (*saved_close)(struct sock *sk, long timeout); + void (*saved_write_space)(struct sock *sk); + struct proto *sk_proto; + struct sk_psock_work_state work_state; + struct work_struct work; + union { + struct rcu_head rcu; + struct work_struct gc; + }; +}; + +int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, + int elem_first_coalesce); +void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len); +int sk_msg_free(struct sock *sk, struct sk_msg *msg); +int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg); +void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes); +void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg, + u32 bytes); + +void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes); + +int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, + struct sk_msg *msg, u32 bytes); +int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, + struct sk_msg *msg, u32 bytes); + +static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes) +{ + WARN_ON(i == msg->sg.end && bytes); +} + +static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes) +{ + if (psock->apply_bytes) { + if (psock->apply_bytes < bytes) + psock->apply_bytes = 0; + else + psock->apply_bytes -= bytes; + } +} + +#define sk_msg_iter_var_prev(var) \ + do { \ + if (var == 0) \ + var = MAX_MSG_FRAGS - 1; \ + else \ + var--; \ + } while (0) + +#define sk_msg_iter_var_next(var) \ + do { \ + var++; \ + if (var == MAX_MSG_FRAGS) \ + var = 0; \ + } while (0) + +#define sk_msg_iter_prev(msg, which) \ + sk_msg_iter_var_prev(msg->sg.which) + +#define sk_msg_iter_next(msg, which) \ + sk_msg_iter_var_next(msg->sg.which) + +static inline void sk_msg_clear_meta(struct sk_msg *msg) +{ + memset(&msg->sg, 0, offsetofend(struct sk_msg_sg, copy)); +} + +static inline void sk_msg_init(struct sk_msg *msg) +{ + memset(msg, 0, sizeof(*msg)); + sg_init_marker(msg->sg.data, ARRAY_SIZE(msg->sg.data)); +} + +static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, + int which, u32 size) +{ + dst->sg.data[which] = src->sg.data[which]; + dst->sg.data[which].length = size; + src->sg.data[which].length -= size; + src->sg.data[which].offset += size; +} + +static inline u32 sk_msg_elem_used(const struct sk_msg *msg) +{ + return msg->sg.end >= msg->sg.start ? + msg->sg.end - msg->sg.start : + msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start); +} + +static inline bool sk_msg_full(const struct sk_msg *msg) +{ + return (msg->sg.end == msg->sg.start) && msg->sg.size; +} + +static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) +{ + return &msg->sg.data[which]; +} + +static inline struct page *sk_msg_page(struct sk_msg *msg, int which) +{ + return sg_page(sk_msg_elem(msg, which)); +} + +static inline bool sk_msg_to_ingress(const struct sk_msg *msg) +{ + return msg->flags & BPF_F_INGRESS; +} + +static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) +{ + struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); + + if (msg->sg.copy[msg->sg.start]) { + msg->data = NULL; + msg->data_end = NULL; + } else { + msg->data = sg_virt(sge); + msg->data_end = msg->data + sge->length; + } +} + +static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, + u32 len, u32 offset) +{ + struct scatterlist *sge; + + get_page(page); + sge = sk_msg_elem(msg, msg->sg.end); + sg_set_page(sge, page, len, offset); + sg_unmark_end(sge); + + msg->sg.copy[msg->sg.end] = true; + msg->sg.size += len; + sk_msg_iter_next(msg, end); +} + +static inline struct sk_psock *sk_psock(const struct sock *sk) +{ + return rcu_dereference_sk_user_data(sk); +} + +static inline bool sk_has_psock(struct sock *sk) +{ + return sk_psock(sk) != NULL && sk->sk_prot->recvmsg == tcp_bpf_recvmsg; +} + +static inline void sk_psock_queue_msg(struct sk_psock *psock, + struct sk_msg *msg) +{ + list_add_tail(&msg->list, &psock->ingress_msg); +} + +static inline void sk_psock_report_error(struct sk_psock *psock, int err) +{ + struct sock *sk = psock->sk; + + sk->sk_err = err; + sk->sk_error_report(sk); +} + +struct sk_psock *sk_psock_init(struct sock *sk, int node); + +int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); +void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock); +void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock); + +int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, + struct sk_msg *msg); + +static inline struct sk_psock_link *sk_psock_init_link(void) +{ + return kzalloc(sizeof(struct sk_psock_link), + GFP_ATOMIC | __GFP_NOWARN); +} + +static inline void sk_psock_free_link(struct sk_psock_link *link) +{ + kfree(link); +} + +struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock); +#if defined(CONFIG_BPF_STREAM_PARSER) +void sk_psock_unlink(struct sock *sk, struct sk_psock_link *link); +#else +static inline void sk_psock_unlink(struct sock *sk, + struct sk_psock_link *link) +{ +} +#endif + +void __sk_psock_purge_ingress_msg(struct sk_psock *psock); + +static inline void sk_psock_cork_free(struct sk_psock *psock) +{ + if (psock->cork) { + sk_msg_free(psock->sk, psock->cork); + kfree(psock->cork); + psock->cork = NULL; + } +} + +static inline void sk_psock_update_proto(struct sock *sk, + struct sk_psock *psock, + struct proto *ops) +{ + psock->saved_unhash = sk->sk_prot->unhash; + psock->saved_close = sk->sk_prot->close; + psock->saved_write_space = sk->sk_write_space; + + psock->sk_proto = sk->sk_prot; + sk->sk_prot = ops; +} + +static inline void sk_psock_restore_proto(struct sock *sk, + struct sk_psock *psock) +{ + if (psock->sk_proto) { + sk->sk_prot = psock->sk_proto; + psock->sk_proto = NULL; + } +} + +static inline void sk_psock_set_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + set_bit(bit, &psock->state); +} + +static inline void sk_psock_clear_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + clear_bit(bit, &psock->state); +} + +static inline bool sk_psock_test_state(const struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + return test_bit(bit, &psock->state); +} + +static inline struct sk_psock *sk_psock_get(struct sock *sk) +{ + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + if (psock && !refcount_inc_not_zero(&psock->refcnt)) + psock = NULL; + rcu_read_unlock(); + return psock; +} + +void sk_psock_stop(struct sock *sk, struct sk_psock *psock); +void sk_psock_destroy(struct rcu_head *rcu); +void sk_psock_drop(struct sock *sk, struct sk_psock *psock); + +static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) +{ + if (refcount_dec_and_test(&psock->refcnt)) + sk_psock_drop(sk, psock); +} + +static inline void psock_set_prog(struct bpf_prog **pprog, + struct bpf_prog *prog) +{ + prog = xchg(pprog, prog); + if (prog) + bpf_prog_put(prog); +} + +static inline void psock_progs_drop(struct sk_psock_progs *progs) +{ + psock_set_prog(&progs->msg_parser, NULL); + psock_set_prog(&progs->skb_parser, NULL); + psock_set_prog(&progs->skb_verdict, NULL); +} + +#endif /* _LINUX_SKMSG_H */ -- cgit v1.2.3 From d829e9c4112b52f4f00195900fd4c685f61365ab Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 13 Oct 2018 02:45:59 +0200 Subject: tls: convert to generic sk_msg interface Convert kTLS over to make use of sk_msg interface for plaintext and encrypted scattergather data, so it reuses all the sk_msg helpers and data structure which later on in a second step enables to glue this to BPF. This also allows to remove quite a bit of open coded helpers which are covered by the sk_msg API. Recent changes in kTLs 80ece6a03aaf ("tls: Remove redundant vars from tls record structure") and 4e6d47206c32 ("tls: Add support for inplace records encryption") changed the data path handling a bit; while we've kept the latter optimization intact, we had to undo the former change to better fit the sk_msg model, hence the sg_aead_in and sg_aead_out have been brought back and are linked into the sk_msg sgs. Now the kTLS record contains a msg_plaintext and msg_encrypted sk_msg each. In the original code, the zerocopy_from_iter() has been used out of TX but also RX path. For the strparser skb-based RX path, we've left the zerocopy_from_iter() in decrypt_internal() mostly untouched, meaning it has been moved into tls_setup_from_iter() with charging logic removed (as not used from RX). Given RX path is not based on sk_msg objects, we haven't pursued setting up a dummy sk_msg to call into sk_msg_zerocopy_from_iter(), but it could be an option to prusue in a later step. Joint work with John. Signed-off-by: Daniel Borkmann Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- include/linux/skmsg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 95678103c4a0..4e84b3c2eff8 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -102,6 +102,8 @@ struct sk_psock { int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, int elem_first_coalesce); +int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src, + u32 off, u32 len); void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len); int sk_msg_free(struct sock *sk, struct sk_msg *msg); int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg); -- cgit v1.2.3 From d3b18ad31f93d0b6bae105c679018a1ba7daa9ca Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sat, 13 Oct 2018 02:46:01 +0200 Subject: tls: add bpf support to sk_msg handling This work adds BPF sk_msg verdict program support to kTLS allowing BPF and kTLS to be combined together. Previously kTLS and sk_msg verdict programs were mutually exclusive in the ULP layer which created challenges for the orchestrator when trying to apply TCP based policy, for example. To resolve this, leveraging the work from previous patches that consolidates the use of sk_msg, we can finally enable BPF sk_msg verdict programs so they continue to run after the kTLS socket is created. No change in behavior when kTLS is not used in combination with BPF, the kselftest suite for kTLS also runs successfully. Joint work with Daniel. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- include/linux/skmsg.h | 41 +++++++++++++++++++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 4e84b3c2eff8..0b919f0bc6d6 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -29,7 +29,11 @@ struct sk_msg_sg { u32 size; u32 copybreak; bool copy[MAX_MSG_FRAGS]; - struct scatterlist data[MAX_MSG_FRAGS]; + /* The extra element is used for chaining the front and sections when + * the list becomes partitioned (e.g. end < start). The crypto APIs + * require the chaining. + */ + struct scatterlist data[MAX_MSG_FRAGS + 1]; }; struct sk_msg { @@ -112,6 +116,7 @@ void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg, u32 bytes); void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes); +void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes); int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); @@ -161,8 +166,9 @@ static inline void sk_msg_clear_meta(struct sk_msg *msg) static inline void sk_msg_init(struct sk_msg *msg) { + BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != MAX_MSG_FRAGS); memset(msg, 0, sizeof(*msg)); - sg_init_marker(msg->sg.data, ARRAY_SIZE(msg->sg.data)); + sg_init_marker(msg->sg.data, MAX_MSG_FRAGS); } static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, @@ -174,6 +180,12 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, src->sg.data[which].offset += size; } +static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) +{ + memcpy(dst, src, sizeof(*src)); + sk_msg_init(src); +} + static inline u32 sk_msg_elem_used(const struct sk_msg *msg) { return msg->sg.end >= msg->sg.start ? @@ -229,6 +241,26 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sk_msg_iter_next(msg, end); } +static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) +{ + do { + msg->sg.copy[i] = copy_state; + sk_msg_iter_var_next(i); + if (i == msg->sg.end) + break; + } while (1); +} + +static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start) +{ + sk_msg_sg_copy(msg, start, true); +} + +static inline void sk_msg_sg_copy_clear(struct sk_msg *msg, u32 start) +{ + sk_msg_sg_copy(msg, start, false); +} + static inline struct sk_psock *sk_psock(const struct sock *sk) { return rcu_dereference_sk_user_data(sk); @@ -245,6 +277,11 @@ static inline void sk_psock_queue_msg(struct sk_psock *psock, list_add_tail(&msg->list, &psock->ingress_msg); } +static inline bool sk_psock_queue_empty(const struct sk_psock *psock) +{ + return psock ? list_empty(&psock->ingress_msg) : true; +} + static inline void sk_psock_report_error(struct sk_psock *psock, int err) { struct sock *sk = psock->sk; -- cgit v1.2.3 From 9316a9ed6895c4ad2f0cde171d486f80c55d8283 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 15 Oct 2018 08:40:37 -0600 Subject: blk-mq: provide helper for setting up an SQ queue and tag set This pattern is repeated throughout all the blk-mq conversions. Provide a basic helper to get it done. Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 1da59c16f637..2286dc12c6bc 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -203,6 +203,10 @@ enum { struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); +struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, + unsigned int queue_depth, + unsigned int set_flags); int blk_mq_register_dev(struct device *, struct request_queue *); void blk_mq_unregister_dev(struct device *, struct request_queue *); -- cgit v1.2.3 From 25ab0bc334b43bbbe4eabc255006ce42a9424da2 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Wed, 10 Oct 2018 03:23:09 +0000 Subject: scsi: sched/wait: Add wait_event_lock_irq_timeout for TASK_UNINTERRUPTIBLE usage Short of reverting commit 00d909a10710 ("scsi: target: Make the session shutdown code also wait for commands that are being aborted") for v4.19, target-core needs a wait_event_t macro can be executed using TASK_UNINTERRUPTIBLE to function correctly with existing fabric drivers that expect to run with signals pending during session shutdown and active se_cmd I/O quiesce. The most notable is iscsi-target/iser-target, while ibmvscsi_tgt invokes session shutdown logic from userspace via configfs attribute that could also potentially have signals pending. So go ahead and introduce wait_event_lock_irq_timeout() to achieve this, and update + rename __wait_event_lock_irq_timeout() to make it accept 'state' as a parameter. Fixes: 00d909a10710 ("scsi: target: Make the session shutdown code also wait for commands that are being aborted") Cc: # v4.19+ Cc: Bart Van Assche Cc: Mike Christie Cc: Hannes Reinecke Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: Bryant G. Ly Cc: Peter Zijlstra (Intel) Tested-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger Reviewed-by: Bryant G. Ly Acked-by: Peter Zijlstra (Intel) Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/linux/wait.h | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index d9f131ecf708..ed7c122cb31f 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -1052,10 +1052,9 @@ do { \ __ret; \ }) -#define __wait_event_interruptible_lock_irq_timeout(wq_head, condition, \ - lock, timeout) \ +#define __wait_event_lock_irq_timeout(wq_head, condition, lock, timeout, state) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ + state, 0, timeout, \ spin_unlock_irq(&lock); \ __ret = schedule_timeout(__ret); \ spin_lock_irq(&lock)); @@ -1089,8 +1088,19 @@ do { \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_interruptible_lock_irq_timeout( \ - wq_head, condition, lock, timeout); \ + __ret = __wait_event_lock_irq_timeout( \ + wq_head, condition, lock, timeout, \ + TASK_INTERRUPTIBLE); \ + __ret; \ +}) + +#define wait_event_lock_irq_timeout(wq_head, condition, lock, timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_lock_irq_timeout( \ + wq_head, condition, lock, timeout, \ + TASK_UNINTERRUPTIBLE); \ __ret; \ }) -- cgit v1.2.3 From 9f9a742db40f95f4dc20fc7293de4ea6ddb24e47 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 9 Oct 2018 23:57:49 +0100 Subject: FDDI: defza: Support capturing outgoing SMT traffic DEC FDDIcontroller 700 (DEFZA) uses a Tx/Rx queue pair to communicate SMT frames with adapter's firmware. Any SMT frame received from the RMC via the Rx queue is queued back by the driver to the SMT Rx queue for the firmware to process. Similarly the firmware uses the SMT Tx queue to supply the driver with SMT frames which are queued back to the Tx queue for the RMC to send to the ring. When a network tap is attached to an FDDI interface handled by `defza' any incoming SMT frames captured are queued to our usual processing of network data received, which in turn delivers them to any listening taps. However the outgoing SMT frames produced by the firmware bypass our network protocol stack and are therefore not delivered to taps. This in turn means that taps are missing a part of network traffic sent by the adapter, which may make it more difficult to track down network problems or do general traffic analysis. Call `dev_queue_xmit_nit' then in the SMT Tx path, having checked that a network tap is attached, with a newly-created `dev_nit_active' helper wrapping the usual condition used in the transmit path. Signed-off-by: Maciej W. Rozycki Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 22e4ef7bb701..dc1d9ed33b31 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3645,6 +3645,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, return 0; } +bool dev_nit_active(struct net_device *dev); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern int netdev_budget; -- cgit v1.2.3 From 5f6188a8003d080e3753b8f14f4a5a2325ae1ff6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Oct 2018 09:37:52 -0700 Subject: tcp: do not change tcp_wstamp_ns in tcp_mstamp_refresh In EDT design, I made the mistake of using tcp_wstamp_ns to store the last tcp_clock_ns() sample and to store the pacing virtual timer. This causes major regressions at high speed flows. Introduce tcp_clock_cache to store last tcp_clock_ns(). This is needed because some arches have slow high-resolution kernel time service. tcp_wstamp_ns is only updated when a packet is sent. Note that we can remove tcp_mstamp in the future since tcp_mstamp is essentially tcp_clock_cache/1000, so the apparent socket size increase is temporary. Fixes: 9799ccb0e984 ("tcp: add tcp_wstamp_ns socket field") Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 848f5b25e178..8ed77bb4ed86 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -249,6 +249,7 @@ struct tcp_sock { u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ + u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ /* RTT measurement */ u64 tcp_mstamp; /* most recent packet received/sent */ -- cgit v1.2.3 From 22e6c58b8c2843337ec4e8464b1ce6e869ca5bf4 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 15 Oct 2018 18:56:41 -0700 Subject: netlink: Add answer_flags to netlink_callback With dump filtering we need a way to ensure the NLM_F_DUMP_FILTERED flag is set on a message back to the user if the data returned is influenced by some input attributes. Normally this can be done as messages are added to the skb, but if the filter results in no data being returned, the user could be confused as to why. This patch adds answer_flags to the netlink_callback allowing dump handlers to set the NLM_F_DUMP_FILTERED at a minimum in the NLMSG_DONE message ensuring the flag gets back to the user. The netlink_callback space is initialized to 0 via a memset in __netlink_dump_start, so init of the new answer_flags is covered. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 72580f1a72a2..4da90a6ab536 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -180,6 +180,7 @@ struct netlink_callback { u16 family; u16 min_dump_alloc; bool strict_check; + u16 answer_flags; unsigned int prev_seq, seq; long args[6]; }; -- cgit v1.2.3 From e1cedae1ba6b09ae8376c1486712bf91ea0dfc41 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 15 Oct 2018 18:56:46 -0700 Subject: ipmr: Refactor mr_rtm_dumproute Move per-table loops from mr_rtm_dumproute to mr_table_dump and export mr_table_dump for dumps by specific table id. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/mroute_base.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 6675b9f81979..db85373c8d15 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -283,6 +283,12 @@ void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg); int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mr_mfc *c, struct rtmsg *rtm); +int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, + struct netlink_callback *cb, + int (*fill)(struct mr_table *mrt, struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, + int cmd, int flags), + spinlock_t *lock); int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), -- cgit v1.2.3 From cb167893f41e21e6bd283d78e53489289dc0592d Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 15 Oct 2018 18:56:47 -0700 Subject: net: Plumb support for filtering ipv4 and ipv6 multicast route dumps Implement kernel side filtering of routes by egress device index and table id. If the table id is given in the filter, lookup table and call mr_table_dump directly for it. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/mroute_base.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index db85373c8d15..34de06b426ef 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -7,6 +7,7 @@ #include #include #include +#include /** * struct vif_device - interface representor for multicast routing @@ -288,7 +289,7 @@ int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), - spinlock_t *lock); + spinlock_t *lock, struct fib_dump_filter *filter); int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), @@ -296,7 +297,7 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), - spinlock_t *lock); + spinlock_t *lock, struct fib_dump_filter *filter); int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, @@ -346,7 +347,7 @@ mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), - spinlock_t *lock) + spinlock_t *lock, struct fib_dump_filter *filter) { return -EINVAL; } -- cgit v1.2.3 From a218dc82f0b5c6c8ad3d58c9870ed69e26c08b3e Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Wed, 10 Oct 2018 09:57:13 +0200 Subject: netfilter: nft_osf: Add ttl option support Add ttl option support to the nftables "osf" expression. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_osf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h index ecf7dab81e9e..c6000046c966 100644 --- a/include/linux/netfilter/nfnetlink_osf.h +++ b/include/linux/netfilter/nfnetlink_osf.h @@ -27,6 +27,7 @@ bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, const struct list_head *nf_osf_fingers); const char *nf_osf_find(const struct sk_buff *skb, - const struct list_head *nf_osf_fingers); + const struct list_head *nf_osf_fingers, + const int ttl_check); #endif /* _NFOSF_H */ -- cgit v1.2.3 From 4cf841e398503990df640f7a7c5b2ea56f11c08c Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 15 Oct 2018 16:11:31 -0700 Subject: ACPI/ADXL: Add address translation interface using an ACPI DSM Some new Intel servers provide an interface so that the OS can ask the BIOS to translate a system physical address to a memory address (socket, memory controller, channel, rank, dimm, etc.). This is useful for EDAC drivers that want to take the address of an error reported in a machine check bank and let the user know which DIMM may need to be replaced. Specification for this interface is available at: https://cdrdv2.intel.com/v1/dl/getContent/603354 [ Based on earlier code by Qiuxu Zhuo . ] [ bp: Make the first pr_info() in adxl_init() pr_debug() so that it doesn't pollute every dmesg. ] Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Acked-by: Rafael J. Wysocki Tested-by: Qiuxu Zhuo CC: Len Brown CC: linux-acpi@vger.kernel.org CC: linux-edac@vger.kernel.org Link: http://lkml.kernel.org/r/20181015202620.23610-1-tony.luck@intel.com --- include/linux/adxl.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/adxl.h (limited to 'include/linux') diff --git a/include/linux/adxl.h b/include/linux/adxl.h new file mode 100644 index 000000000000..2a629acb4c3f --- /dev/null +++ b/include/linux/adxl.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Address translation interface via ACPI DSM. + * Copyright (C) 2018 Intel Corporation + */ + +#ifndef _LINUX_ADXL_H +#define _LINUX_ADXL_H + +const char * const *adxl_get_component_names(void); +int adxl_decode(u64 addr, u64 component_values[]); + +#endif /* _LINUX_ADXL_H */ -- cgit v1.2.3 From 084181fe8cc7472695b907f0018f4cd00934cb12 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Mon, 15 Oct 2018 17:20:01 -0500 Subject: fpga: mgr: add devm_fpga_mgr_create Add devm_fpga_mgr_create() which is the managed version of fpga_mgr_create(). Change current FPGA manager drivers to use devm_fpga_mgr_create() Signed-off-by: Alan Tull Suggested-by: Federico Vaga Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 8ab5df769923..e8ca62b2cb5b 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -198,4 +198,8 @@ void fpga_mgr_free(struct fpga_manager *mgr); int fpga_mgr_register(struct fpga_manager *mgr); void fpga_mgr_unregister(struct fpga_manager *mgr); +struct fpga_manager *devm_fpga_mgr_create(struct device *dev, const char *name, + const struct fpga_manager_ops *mops, + void *priv); + #endif /*_LINUX_FPGA_MGR_H */ -- cgit v1.2.3 From 213befe049c70cfcfcbb4f6010bd5276dbc1f7b9 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Mon, 15 Oct 2018 17:20:02 -0500 Subject: fpga: bridge: add devm_fpga_bridge_create Add devm_fpga_bridge_create() which is the managed version of fpga_bridge_create(). Change current bridge drivers to use devm_fpga_bridge_create(). Signed-off-by: Alan Tull Suggested-by: Federico Vaga Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-bridge.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h index ce550fcf6360..817600a32c93 100644 --- a/include/linux/fpga/fpga-bridge.h +++ b/include/linux/fpga/fpga-bridge.h @@ -69,4 +69,8 @@ void fpga_bridge_free(struct fpga_bridge *br); int fpga_bridge_register(struct fpga_bridge *br); void fpga_bridge_unregister(struct fpga_bridge *br); +struct fpga_bridge +*devm_fpga_bridge_create(struct device *dev, const char *name, + const struct fpga_bridge_ops *br_ops, void *priv); + #endif /* _LINUX_FPGA_BRIDGE_H */ -- cgit v1.2.3 From fea82b7f6670002ff36bf1bc77d0345b0b2f2d1c Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Mon, 15 Oct 2018 17:20:03 -0500 Subject: fpga: add devm_fpga_region_create Add devm_fpga_region_create() which is the managed version of fpga_region_create(). Change current region drivers to use devm_fpga_region_create(). Signed-off-by: Alan Tull Suggested-by: Federico Vaga Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-region.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index 0521b7f577a4..27cb706275db 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -44,4 +44,8 @@ void fpga_region_free(struct fpga_region *region); int fpga_region_register(struct fpga_region *region); void fpga_region_unregister(struct fpga_region *region); +struct fpga_region +*devm_fpga_region_create(struct device *dev, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *)); + #endif /* _FPGA_REGION_H */ -- cgit v1.2.3 From 8514c470dc18e58f27dee10a787175ef8f31162f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jul 2018 15:20:32 +0200 Subject: driver core: add BUS_ATTR_WO() macro Many bus attributes are write-only, so provide a simple macro for that to be able to match the other driver core attribute macros. Cc: "Rafael J. Wysocki" Cc: Ioana Ciornei Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 8f882549edee..767cf1938b14 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -55,6 +55,8 @@ struct bus_attribute { struct bus_attribute bus_attr_##_name = __ATTR_RW(_name) #define BUS_ATTR_RO(_name) \ struct bus_attribute bus_attr_##_name = __ATTR_RO(_name) +#define BUS_ATTR_WO(_name) \ + struct bus_attribute bus_attr_##_name = __ATTR_WO(_name) extern int __must_check bus_create_file(struct bus_type *, struct bus_attribute *); -- cgit v1.2.3 From 0571967dfb5d2573c2a06871517d748932a899d1 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Sun, 14 Oct 2018 17:20:07 +0200 Subject: devres: constify p in devm_kfree() Make devm_kfree() signature uniform with that of kfree(). To avoid compiler warnings: cast p to (void *) when calling devres_destroy(). Signed-off-by: Bartosz Golaszewski Reviewed-by: Bjorn Andersson Reviewed-by: Geert Uytterhoeven Acked-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 767cf1938b14..c2022c1daef6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -694,7 +694,7 @@ static inline void *devm_kcalloc(struct device *dev, { return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); } -extern void devm_kfree(struct device *dev, void *p); +extern void devm_kfree(struct device *dev, const void *p); extern char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; extern void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp); -- cgit v1.2.3 From 09d1ea1c7309c8ca91151778bb3efe514f2e03ed Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Sun, 14 Oct 2018 17:20:09 +0200 Subject: devres: provide devm_kstrdup_const() Provide a resource managed version of kstrdup_const(). This variant internally calls devm_kstrdup() on pointers that are outside of .rodata section and returns the string as is otherwise. Make devm_kfree() check if the passed pointer doesn't point to .rodata and if so - don't actually destroy the resource. Signed-off-by: Bartosz Golaszewski Reviewed-by: Bjorn Andersson Acked-by: Mike Rapoport Acked-by: Rasmus Villemoes Reviewed-by: Geert Uytterhoeven Reviewed-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index c2022c1daef6..fecd9722400e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -696,6 +696,8 @@ static inline void *devm_kcalloc(struct device *dev, } extern void devm_kfree(struct device *dev, const void *p); extern char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; +extern const char *devm_kstrdup_const(struct device *dev, + const char *s, gfp_t gfp); extern void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp); -- cgit v1.2.3 From 891b7c5fbf619d2a314e424775b3c232eb227e90 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Oct 2018 08:09:58 -0600 Subject: mtd_blkdevs: convert to blk-mq Straight forward conversion, using an internal list to enable the driver to pull requests at will. Dynamically allocate the tag set to avoid having to pull in the block headers for blktrans.h, since various mtd drivers use block conflicting names for defines and functions. Cc: David Woodhouse Cc: linux-mtd@lists.infradead.org Tested-by: Richard Weinberger Signed-off-by: Jens Axboe --- include/linux/mtd/blktrans.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index e93837f647de..1d3ade69d39a 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -23,7 +23,6 @@ #include #include #include -#include struct hd_geometry; struct mtd_info; @@ -44,9 +43,9 @@ struct mtd_blktrans_dev { struct kref ref; struct gendisk *disk; struct attribute_group *disk_attributes; - struct workqueue_struct *wq; - struct work_struct work; struct request_queue *rq; + struct list_head rq_list; + struct blk_mq_tag_set *tag_set; spinlock_t queue_lock; void *priv; fmode_t file_mode; -- cgit v1.2.3 From c87228f16f0acdf242dee62f139013212208473f Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 11 Oct 2018 12:20:45 -0700 Subject: amiflop: fold headers into C file amifd.h and amifdreg.h are only used from amiflop.c, and they're pretty small, so move the contents to amiflop.c and get rid of the .h files. This is preparation for adding a struct blk_mq_tag_set to struct amiga_floppy_struct. Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/amifd.h | 63 ------------------------------------- include/linux/amifdreg.h | 82 ------------------------------------------------ 2 files changed, 145 deletions(-) delete mode 100644 include/linux/amifd.h delete mode 100644 include/linux/amifdreg.h (limited to 'include/linux') diff --git a/include/linux/amifd.h b/include/linux/amifd.h deleted file mode 100644 index 202a77dbe46d..000000000000 --- a/include/linux/amifd.h +++ /dev/null @@ -1,63 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _AMIFD_H -#define _AMIFD_H - -/* Definitions for the Amiga floppy driver */ - -#include - -#define FD_MAX_UNITS 4 /* Max. Number of drives */ -#define FLOPPY_MAX_SECTORS 22 /* Max. Number of sectors per track */ - -#ifndef ASSEMBLER - -struct fd_data_type { - char *name; /* description of data type */ - int sects; /* sectors per track */ -#ifdef __STDC__ - int (*read_fkt)(int); - void (*write_fkt)(int); -#else - int (*read_fkt)(); /* read whole track */ - void (*write_fkt)(); /* write whole track */ -#endif -}; - -/* -** Floppy type descriptions -*/ - -struct fd_drive_type { - unsigned long code; /* code returned from drive */ - char *name; /* description of drive */ - unsigned int tracks; /* number of tracks */ - unsigned int heads; /* number of heads */ - unsigned int read_size; /* raw read size for one track */ - unsigned int write_size; /* raw write size for one track */ - unsigned int sect_mult; /* sectors and gap multiplier (HD = 2) */ - unsigned int precomp1; /* start track for precomp 1 */ - unsigned int precomp2; /* start track for precomp 2 */ - unsigned int step_delay; /* time (in ms) for delay after step */ - unsigned int settle_time; /* time to settle after dir change */ - unsigned int side_time; /* time needed to change sides */ -}; - -struct amiga_floppy_struct { - struct fd_drive_type *type; /* type of floppy for this unit */ - struct fd_data_type *dtype; /* type of floppy for this unit */ - int track; /* current track (-1 == unknown) */ - unsigned char *trackbuf; /* current track (kmaloc()'d */ - - int blocks; /* total # blocks on disk */ - - int changed; /* true when not known */ - int disk; /* disk in drive (-1 == unknown) */ - int motor; /* true when motor is at speed */ - int busy; /* true when drive is active */ - int dirty; /* true when trackbuf is not on disk */ - int status; /* current error code for unit */ - struct gendisk *gendisk; -}; -#endif - -#endif diff --git a/include/linux/amifdreg.h b/include/linux/amifdreg.h deleted file mode 100644 index 9b514d05ec70..000000000000 --- a/include/linux/amifdreg.h +++ /dev/null @@ -1,82 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_AMIFDREG_H -#define _LINUX_AMIFDREG_H - -/* -** CIAAPRA bits (read only) -*/ - -#define DSKRDY (0x1<<5) /* disk ready when low */ -#define DSKTRACK0 (0x1<<4) /* head at track zero when low */ -#define DSKPROT (0x1<<3) /* disk protected when low */ -#define DSKCHANGE (0x1<<2) /* low when disk removed */ - -/* -** CIAAPRB bits (read/write) -*/ - -#define DSKMOTOR (0x1<<7) /* motor on when low */ -#define DSKSEL3 (0x1<<6) /* select drive 3 when low */ -#define DSKSEL2 (0x1<<5) /* select drive 2 when low */ -#define DSKSEL1 (0x1<<4) /* select drive 1 when low */ -#define DSKSEL0 (0x1<<3) /* select drive 0 when low */ -#define DSKSIDE (0x1<<2) /* side selection: 0 = upper, 1 = lower */ -#define DSKDIREC (0x1<<1) /* step direction: 0=in, 1=out (to trk 0) */ -#define DSKSTEP (0x1) /* pulse low to step head 1 track */ - -/* -** DSKBYTR bits (read only) -*/ - -#define DSKBYT (1<<15) /* register contains valid byte when set */ -#define DMAON (1<<14) /* disk DMA enabled */ -#define DISKWRITE (1<<13) /* disk write bit in DSKLEN enabled */ -#define WORDEQUAL (1<<12) /* DSKSYNC register match when true */ -/* bits 7-0 are data */ - -/* -** ADKCON/ADKCONR bits -*/ - -#ifndef SETCLR -#define ADK_SETCLR (1<<15) /* control bit */ -#endif -#define ADK_PRECOMP1 (1<<14) /* precompensation selection */ -#define ADK_PRECOMP0 (1<<13) /* 00=none, 01=140ns, 10=280ns, 11=500ns */ -#define ADK_MFMPREC (1<<12) /* 0=GCR precomp., 1=MFM precomp. */ -#define ADK_WORDSYNC (1<<10) /* enable DSKSYNC auto DMA */ -#define ADK_MSBSYNC (1<<9) /* when 1, enable sync on MSbit (for GCR) */ -#define ADK_FAST (1<<8) /* bit cell: 0=2us (GCR), 1=1us (MFM) */ - -/* -** DSKLEN bits -*/ - -#define DSKLEN_DMAEN (1<<15) -#define DSKLEN_WRITE (1<<14) - -/* -** INTENA/INTREQ bits -*/ - -#define DSKINDEX (0x1<<4) /* DSKINDEX bit */ - -/* -** Misc -*/ - -#define MFM_SYNC 0x4489 /* standard MFM sync value */ - -/* Values for FD_COMMAND */ -#define FD_RECALIBRATE 0x07 /* move to track 0 */ -#define FD_SEEK 0x0F /* seek track */ -#define FD_READ 0xE6 /* read with MT, MFM, SKip deleted */ -#define FD_WRITE 0xC5 /* write with MT, MFM */ -#define FD_SENSEI 0x08 /* Sense Interrupt Status */ -#define FD_SPECIFY 0x03 /* specify HUT etc */ -#define FD_FORMAT 0x4D /* format one track */ -#define FD_VERSION 0x10 /* get version code */ -#define FD_CONFIGURE 0x13 /* configure FIFO operation */ -#define FD_PERPENDICULAR 0x12 /* perpendicular r/w mode */ - -#endif /* _LINUX_AMIFDREG_H */ -- cgit v1.2.3 From 4354994f097d068a894aa1a0860da54571df3582 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Mon, 20 Aug 2018 19:21:43 -0700 Subject: f2fs: checkpoint disabling Note that, it requires "f2fs: return correct errno in f2fs_gc". This adds a lightweight non-persistent snapshotting scheme to f2fs. To use, mount with the option checkpoint=disable, and to return to normal operation, remount with checkpoint=enable. If the filesystem is shut down before remounting with checkpoint=enable, it will revert back to its apparent state when it was first mounted with checkpoint=disable. This is useful for situations where you wish to be able to roll back the state of the disk in case of some critical failure. Signed-off-by: Daniel Rosenberg [Jaegeuk Kim: use SB_RDONLY instead of MS_RDONLY] Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 1db13ff9a3f4..8b9c7dc0260c 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -116,6 +116,7 @@ struct f2fs_super_block { /* * For checkpoint */ +#define CP_DISABLED_FLAG 0x00001000 #define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 #define CP_NOCRC_RECOVERY_FLAG 0x00000200 #define CP_TRIMMED_FLAG 0x00000100 -- cgit v1.2.3 From c56a8be7e7aa855ebcccf0e9d9eba2216514d399 Mon Sep 17 00:00:00 2001 From: Rahul Verma Date: Tue, 16 Oct 2018 03:59:20 -0700 Subject: qed: Add supported link and advertise link to display in ethtool. Added transceiver type, speed capability and board types in HSI, are utilizing to display the accurate link information in ethtool. Signed-off-by: Rahul Verma Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index dee3c9c744f7..a47321a0d572 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -667,15 +667,35 @@ enum qed_link_mode_bits { QED_LM_Autoneg_BIT = BIT(1), QED_LM_Asym_Pause_BIT = BIT(2), QED_LM_Pause_BIT = BIT(3), - QED_LM_1000baseT_Half_BIT = BIT(4), - QED_LM_1000baseT_Full_BIT = BIT(5), + QED_LM_1000baseT_Full_BIT = BIT(4), + QED_LM_10000baseT_Full_BIT = BIT(5), QED_LM_10000baseKR_Full_BIT = BIT(6), QED_LM_20000baseKR2_Full_BIT = BIT(7), QED_LM_25000baseKR_Full_BIT = BIT(8), QED_LM_40000baseLR4_Full_BIT = BIT(9), QED_LM_50000baseKR2_Full_BIT = BIT(10), QED_LM_100000baseKR4_Full_BIT = BIT(11), - QED_LM_COUNT = 11 + QED_LM_2500baseX_Full_BIT = BIT(12), + QED_LM_Backplane_BIT = BIT(13), + QED_LM_1000baseKX_Full_BIT = BIT(14), + QED_LM_10000baseKX4_Full_BIT = BIT(15), + QED_LM_10000baseR_FEC_BIT = BIT(16), + QED_LM_40000baseKR4_Full_BIT = BIT(17), + QED_LM_40000baseCR4_Full_BIT = BIT(18), + QED_LM_40000baseSR4_Full_BIT = BIT(19), + QED_LM_25000baseCR_Full_BIT = BIT(20), + QED_LM_25000baseSR_Full_BIT = BIT(21), + QED_LM_50000baseCR2_Full_BIT = BIT(22), + QED_LM_100000baseSR4_Full_BIT = BIT(23), + QED_LM_100000baseCR4_Full_BIT = BIT(24), + QED_LM_100000baseLR4_ER4_Full_BIT = BIT(25), + QED_LM_50000baseSR2_Full_BIT = BIT(26), + QED_LM_1000baseX_Full_BIT = BIT(27), + QED_LM_10000baseCR_Full_BIT = BIT(28), + QED_LM_10000baseSR_Full_BIT = BIT(29), + QED_LM_10000baseLR_Full_BIT = BIT(30), + QED_LM_10000baseLRM_Full_BIT = BIT(31), + QED_LM_COUNT = 32 }; struct qed_link_params { -- cgit v1.2.3 From 94a04d1d3d3681adde1a3e022b25dbac7b345b7e Mon Sep 17 00:00:00 2001 From: Yonatan Cohen Date: Tue, 9 Oct 2018 12:05:12 +0300 Subject: net/mlx5: Expose DC scatter to CQE capability bit dc_req_scat_data_cqe capability bit determines if requester scatter to cqe is available for 64 bytes CQE over DC transport type. Signed-off-by: Yonatan Cohen Reviewed-by: Guy Levi Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 68f4d5f9d929..0f460fb22c31 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1005,7 +1005,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 umr_modify_atomic_disabled[0x1]; u8 umr_indirect_mkey_disabled[0x1]; u8 umr_fence[0x2]; - u8 reserved_at_20c[0x3]; + u8 dc_req_scat_data_cqe[0x1]; + u8 reserved_at_20d[0x2]; u8 drain_sigerr[0x1]; u8 cmdif_checksum[0x2]; u8 sigerr_cqe[0x1]; -- cgit v1.2.3 From 616e45df7c4aa71279c07cc803a1d51f43f89f37 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Fri, 31 Aug 2018 12:45:54 +0800 Subject: clk: add new APIs to operate on all available clocks This patch introduces of_clk_bulk_get_all and clk_bulk_x_all APIs to users who just want to handle all available clocks from device tree without need to know the detailed clock information likes clock numbers and names. This is useful in writing some generic drivers to handle clock part. Cc: Stephen Boyd Cc: Masahiro Yamada Tested-by: Thor Thayer Signed-off-by: Dong Aisheng Signed-off-by: Stephen Boyd --- include/linux/clk.h | 42 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index 4f750c481b82..e9433c76757b 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -312,7 +312,26 @@ struct clk *clk_get(struct device *dev, const char *id); */ int __must_check clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks); - +/** + * clk_bulk_get_all - lookup and obtain all available references to clock + * producer. + * @dev: device for clock "consumer" + * @clks: pointer to the clk_bulk_data table of consumer + * + * This helper function allows drivers to get all clk consumers in one + * operation. If any of the clk cannot be acquired then any clks + * that were obtained will be freed before returning to the caller. + * + * Returns a positive value for the number of clocks obtained while the + * clock references are stored in the clk_bulk_data table in @clks field. + * Returns 0 if there're none and a negative value if something failed. + * + * Drivers must assume that the clock source is not enabled. + * + * clk_bulk_get should not be called from within interrupt context. + */ +int __must_check clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks); /** * devm_clk_bulk_get - managed get multiple clk consumers * @dev: device for clock "consumer" @@ -487,6 +506,19 @@ void clk_put(struct clk *clk); */ void clk_bulk_put(int num_clks, struct clk_bulk_data *clks); +/** + * clk_bulk_put_all - "free" all the clock source + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * Note: drivers must ensure that all clk_bulk_enable calls made on this + * clock source are balanced by clk_bulk_disable calls prior to calling + * this function. + * + * clk_bulk_put_all should not be called from within interrupt context. + */ +void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks); + /** * devm_clk_put - "free" a managed clock source * @dev: device used to acquire the clock @@ -642,6 +674,12 @@ static inline int __must_check clk_bulk_get(struct device *dev, int num_clks, return 0; } +static inline int __must_check clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks) +{ + return 0; +} + static inline struct clk *devm_clk_get(struct device *dev, const char *id) { return NULL; @@ -663,6 +701,8 @@ static inline void clk_put(struct clk *clk) {} static inline void clk_bulk_put(int num_clks, struct clk_bulk_data *clks) {} +static inline void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks) {} + static inline void devm_clk_put(struct device *dev, struct clk *clk) {} -- cgit v1.2.3 From f08c2e2865f6f9b172f37d7bbf24716f9ebad553 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Fri, 31 Aug 2018 12:45:55 +0800 Subject: clk: add managed version of clk_bulk_get_all This patch introduces the managed version of clk_bulk_get_all. Cc: Michael Turquette Cc: Stephen Boyd Tested-by: Thor Thayer Signed-off-by: Dong Aisheng Signed-off-by: Stephen Boyd --- include/linux/clk.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index e9433c76757b..c705271dc1f2 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -346,6 +346,22 @@ int __must_check clk_bulk_get_all(struct device *dev, */ int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks); +/** + * devm_clk_bulk_get_all - managed get multiple clk consumers + * @dev: device for clock "consumer" + * @clks: pointer to the clk_bulk_data table of consumer + * + * Returns a positive value for the number of clocks obtained while the + * clock references are stored in the clk_bulk_data table in @clks field. + * Returns 0 if there're none and a negative value if something failed. + * + * This helper function allows drivers to get several clk + * consumers in one operation with management, the clks will + * automatically be freed when the device is unbound. + */ + +int __must_check devm_clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks); /** * devm_clk_get - lookup and obtain a managed reference to a clock producer. @@ -691,6 +707,13 @@ static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clk return 0; } +static inline int __must_check devm_clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks) +{ + + return 0; +} + static inline struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id) { -- cgit v1.2.3 From 3f4c3127d332000530349db4843deece27fe5e0c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Oct 2018 10:36:01 -0700 Subject: bpf: sockmap, fix skmsg recvmsg handler to track size correctly When converting sockmap to new skmsg generic data structures we missed that the recvmsg handler did not correctly use sg.size and instead was using individual elements length. The result is if a sock is closed with outstanding data we omit the call to sk_mem_uncharge() and can get the warning below. [ 66.728282] WARNING: CPU: 6 PID: 5783 at net/core/stream.c:206 sk_stream_kill_queues+0x1fa/0x210 To fix this correct the redirect handler to xfer the size along with the scatterlist and also decrement the size from the recvmsg handler. Now when a sock is closed the remaining 'size' will be decremented with sk_mem_uncharge(). Signed-off-by: John Fastabend Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 0b919f0bc6d6..31df0d9fa536 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -176,6 +176,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, { dst->sg.data[which] = src->sg.data[which]; dst->sg.data[which].length = size; + dst->sg.size += size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; } -- cgit v1.2.3 From 8734a162c13b1a893e7dff8de0df81fed04c51a6 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Oct 2018 11:07:59 -0700 Subject: bpf: skmsg, improve sk_msg_used_element to work in cork context Currently sk_msg_used_element is only called in zerocopy context where cork is not possible and if this case happens we fallback to copy mode. However the helper is more useful if it works in all contexts. This patch resolved the case where if end == head indicating a full or empty ring the helper always reports an empty ring. To fix this add a test for the full ring case to avoid reporting a full ring has 0 elements. This additional functionality will be used in the next patches from recvmsg context where end = head with a full ring is a valid case. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 31df0d9fa536..22347b08e1f8 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -187,18 +187,21 @@ static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) sk_msg_init(src); } +static inline bool sk_msg_full(const struct sk_msg *msg) +{ + return (msg->sg.end == msg->sg.start) && msg->sg.size; +} + static inline u32 sk_msg_elem_used(const struct sk_msg *msg) { + if (sk_msg_full(msg)) + return MAX_MSG_FRAGS; + return msg->sg.end >= msg->sg.start ? msg->sg.end - msg->sg.start : msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start); } -static inline bool sk_msg_full(const struct sk_msg *msg) -{ - return (msg->sg.end == msg->sg.start) && msg->sg.size; -} - static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) { return &msg->sg.data[which]; -- cgit v1.2.3 From a60109dc9a954ef9eddba6577e2d2e9e7952e487 Mon Sep 17 00:00:00 2001 From: Yonatan Cohen Date: Wed, 10 Oct 2018 09:25:16 +0300 Subject: IB/mlx5: Add support for extended atomic operations Extended atomic operations cmp&swp and fetch&add is a Mellanox feature extending the standard atomic operation to use, varied operand sizes, as apposed to normal atomic operation that use an 8 byte operand only. Extended atomics allows masking the results and arguments. This patch configures QP to support extended atomic operation with the maximum size possible, as exposed by HCA capabilities. Signed-off-by: Yonatan Cohen Reviewed-by: Guy Levi Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8fb072aa8671..a73c701edd16 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -97,14 +97,15 @@ enum { }; enum { - MLX5_ATOMIC_MODE_IB_COMP = 1 << 16, - MLX5_ATOMIC_MODE_CX = 2 << 16, - MLX5_ATOMIC_MODE_8B = 3 << 16, - MLX5_ATOMIC_MODE_16B = 4 << 16, - MLX5_ATOMIC_MODE_32B = 5 << 16, - MLX5_ATOMIC_MODE_64B = 6 << 16, - MLX5_ATOMIC_MODE_128B = 7 << 16, - MLX5_ATOMIC_MODE_256B = 8 << 16, + MLX5_ATOMIC_MODE_OFFSET = 16, + MLX5_ATOMIC_MODE_IB_COMP = 1, + MLX5_ATOMIC_MODE_CX = 2, + MLX5_ATOMIC_MODE_8B = 3, + MLX5_ATOMIC_MODE_16B = 4, + MLX5_ATOMIC_MODE_32B = 5, + MLX5_ATOMIC_MODE_64B = 6, + MLX5_ATOMIC_MODE_128B = 7, + MLX5_ATOMIC_MODE_256B = 8, }; enum { @@ -162,13 +163,11 @@ enum mlx5_dcbx_oper_mode { MLX5E_DCBX_PARAM_VER_OPER_AUTO = 0x3, }; -enum mlx5_dct_atomic_mode { - MLX5_ATOMIC_MODE_DCT_CX = 2, -}; - enum { MLX5_ATOMIC_OPS_CMP_SWAP = 1 << 0, MLX5_ATOMIC_OPS_FETCH_ADD = 1 << 1, + MLX5_ATOMIC_OPS_EXTENDED_CMP_SWAP = 1 << 2, + MLX5_ATOMIC_OPS_EXTENDED_FETCH_ADD = 1 << 3, }; enum mlx5_page_fault_resume_flags { -- cgit v1.2.3 From 977196b8c5b20b901acb0042579e30d7fa55790a Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:37 -0600 Subject: PCI/P2PDMA: Add PCI p2pmem DMA mappings to adjust the bus offset The DMA address used when mapping PCI P2P memory must be the PCI bus address. Thus, introduce pci_p2pmem_map_sg() to map the correct addresses when using P2P memory. Memory mapped in this way does not need to be unmapped and thus if we provided pci_p2pmem_unmap_sg() it would be empty. This breaks the expected balance between map/unmap but was left out as an empty function doesn't really provide any benefit. In the future, if this call becomes necessary it can be added without much difficulty. For this, we assume that an SGL passed to these functions contain all P2P memory or no P2P memory. Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig --- include/linux/memremap.h | 1 + include/linux/pci-p2pdma.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 9553370ebdad..0ac69ddf5fc4 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -125,6 +125,7 @@ struct dev_pagemap { struct device *dev; void *data; enum memory_type type; + u64 pci_p2pdma_bus_offset; }; #ifdef CONFIG_ZONE_DEVICE diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h index 7bdaacfd5892..b6dfb6dc2e53 100644 --- a/include/linux/pci-p2pdma.h +++ b/include/linux/pci-p2pdma.h @@ -30,6 +30,8 @@ struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, unsigned int *nents, u32 length); void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl); void pci_p2pmem_publish(struct pci_dev *pdev, bool publish); +int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir); #else /* CONFIG_PCI_P2PDMA */ static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset) @@ -75,6 +77,11 @@ static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev, static inline void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) { } +static inline int pci_p2pdma_map_sg(struct device *dev, + struct scatterlist *sg, int nents, enum dma_data_direction dir) +{ + return 0; +} #endif /* CONFIG_PCI_P2PDMA */ -- cgit v1.2.3 From 2d7bc010f450d803db9fed1a25da6144ff6140d3 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:38 -0600 Subject: PCI/P2PDMA: Introduce configfs/sysfs enable attribute helpers Users of the P2PDMA infrastructure will typically need a way for the user to tell the kernel to use P2P resources. Typically this will be a simple on/off boolean operation but sometimes it may be desirable for the user to specify the exact device to use for the P2P operation. Add new helpers for attributes which take a boolean or a PCI device. Any boolean as accepted by strtobool() turn P2P on or off (such as 'y', 'n', '1', '0', etc). Specifying a full PCI device name/BDF will select the specific device. Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig --- include/linux/pci-p2pdma.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h index b6dfb6dc2e53..bca9bc3e5be7 100644 --- a/include/linux/pci-p2pdma.h +++ b/include/linux/pci-p2pdma.h @@ -32,6 +32,10 @@ void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl); void pci_p2pmem_publish(struct pci_dev *pdev, bool publish); int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir); +int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev, + bool *use_p2pdma); +ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev, + bool use_p2pdma); #else /* CONFIG_PCI_P2PDMA */ static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset) @@ -82,6 +86,17 @@ static inline int pci_p2pdma_map_sg(struct device *dev, { return 0; } +static inline int pci_p2pdma_enable_store(const char *page, + struct pci_dev **p2p_dev, bool *use_p2pdma) +{ + *use_p2pdma = false; + return 0; +} +static inline ssize_t pci_p2pdma_enable_show(char *page, + struct pci_dev *p2p_dev, bool use_p2pdma) +{ + return sprintf(page, "none\n"); +} #endif /* CONFIG_PCI_P2PDMA */ -- cgit v1.2.3 From 49d92c0dd64ae769c2d67fe27ac260ae31259ba6 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:41 -0600 Subject: block: Add PCI P2P flag for request queue Add QUEUE_FLAG_PCI_P2P, meaning a driver's request queue supports targeting P2P memory. This will be used by P2P providers and orchestrators (in subsequent patches) to ensure block devices can support P2P memory before submitting P2P-backed pages to submit_bio(). Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig Acked-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6980014357d4..c32f7171899b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -699,6 +699,7 @@ struct request_queue { #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ #define QUEUE_FLAG_PREEMPT_ONLY 29 /* only process REQ_PREEMPT requests */ +#define QUEUE_FLAG_PCI_P2PDMA 30 /* device supports PCI p2p requests */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ @@ -731,6 +732,8 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_scsi_passthrough(q) \ test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) +#define blk_queue_pci_p2pdma(q) \ + test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ -- cgit v1.2.3 From 9c0be3f6b5d776dfe3ed249862c244a4486414dc Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Sat, 13 Oct 2018 15:10:50 -0400 Subject: tracepoint: Fix tracepoint array element size mismatch commit 46e0c9be206f ("kernel: tracepoints: add support for relative references") changes the layout of the __tracepoint_ptrs section on architectures supporting relative references. However, it does so without turning struct tracepoint * const into const int elsewhere in the tracepoint code, which has the following side-effect: Setting mod->num_tracepoints is done in by module.c: mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs", sizeof(*mod->tracepoints_ptrs), &mod->num_tracepoints); Basically, since sizeof(*mod->tracepoints_ptrs) is a pointer size (rather than sizeof(int)), num_tracepoints is erroneously set to half the size it should be on 64-bit arch. So a module with an odd number of tracepoints misses the last tracepoint due to effect of integer division. So in the module going notifier: for_each_tracepoint_range(mod->tracepoints_ptrs, mod->tracepoints_ptrs + mod->num_tracepoints, tp_module_going_check_quiescent, NULL); the expression (mod->tracepoints_ptrs + mod->num_tracepoints) actually evaluates to something within the bounds of the array, but miss the last tracepoint if the number of tracepoints is odd on 64-bit arch. Fix this by introducing a new typedef: tracepoint_ptr_t, which is either "const int" on architectures that have PREL32 relocations, or "struct tracepoint * const" on architectures that does not have this feature. Also provide a new tracepoint_ptr_defer() static inline to encapsulate deferencing this type rather than duplicate code and ugly idefs within the for_each_tracepoint_range() implementation. This issue appears in 4.19-rc kernels, and should ideally be fixed before the end of the rc cycle. Acked-by: Ard Biesheuvel Acked-by: Jessica Yu Link: http://lkml.kernel.org/r/20181013191050.22389-1-mathieu.desnoyers@efficios.com Link: http://lkml.kernel.org/r/20180704083651.24360-7-ard.biesheuvel@linaro.org Cc: Michael Ellerman Cc: Ingo Molnar Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Bjorn Helgaas Cc: Catalin Marinas Cc: James Morris Cc: James Morris Cc: Josh Poimboeuf Cc: Kees Cook Cc: Nicolas Pitre Cc: Paul Mackerras Cc: Petr Mladek Cc: Russell King Cc: "Serge E. Hallyn" Cc: Sergey Senozhatsky Cc: Thomas Garnier Cc: Thomas Gleixner Cc: Will Deacon Cc: Andrew Morton Cc: Linus Torvalds Cc: Greg Kroah-Hartman Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (VMware) --- include/linux/module.h | 3 ++- include/linux/tracepoint-defs.h | 6 ++++++ include/linux/tracepoint.h | 36 +++++++++++++++++++++++------------- 3 files changed, 31 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index f807f15bebbe..e19ae08c7fb8 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -430,7 +431,7 @@ struct module { #ifdef CONFIG_TRACEPOINTS unsigned int num_tracepoints; - struct tracepoint * const *tracepoints_ptrs; + tracepoint_ptr_t *tracepoints_ptrs; #endif #ifdef HAVE_JUMP_LABEL struct jump_entry *jump_entries; diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h index 22c5a46e9693..49ba9cde7e4b 100644 --- a/include/linux/tracepoint-defs.h +++ b/include/linux/tracepoint-defs.h @@ -35,6 +35,12 @@ struct tracepoint { struct tracepoint_func __rcu *funcs; }; +#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS +typedef const int tracepoint_ptr_t; +#else +typedef struct tracepoint * const tracepoint_ptr_t; +#endif + struct bpf_raw_event_map { struct tracepoint *tp; void *bpf_func; diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 041f7e56a289..538ba1a58f5b 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -99,6 +99,29 @@ extern void syscall_unregfunc(void); #define TRACE_DEFINE_ENUM(x) #define TRACE_DEFINE_SIZEOF(x) +#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS +static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) +{ + return offset_to_ptr(p); +} + +#define __TRACEPOINT_ENTRY(name) \ + asm(" .section \"__tracepoints_ptrs\", \"a\" \n" \ + " .balign 4 \n" \ + " .long __tracepoint_" #name " - . \n" \ + " .previous \n") +#else +static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) +{ + return *p; +} + +#define __TRACEPOINT_ENTRY(name) \ + static tracepoint_ptr_t __tracepoint_ptr_##name __used \ + __attribute__((section("__tracepoints_ptrs"))) = \ + &__tracepoint_##name +#endif + #endif /* _LINUX_TRACEPOINT_H */ /* @@ -253,19 +276,6 @@ extern void syscall_unregfunc(void); return static_key_false(&__tracepoint_##name.key); \ } -#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS -#define __TRACEPOINT_ENTRY(name) \ - asm(" .section \"__tracepoints_ptrs\", \"a\" \n" \ - " .balign 4 \n" \ - " .long __tracepoint_" #name " - . \n" \ - " .previous \n") -#else -#define __TRACEPOINT_ENTRY(name) \ - static struct tracepoint * const __tracepoint_ptr_##name __used \ - __attribute__((section("__tracepoints_ptrs"))) = \ - &__tracepoint_##name -#endif - /* * We have no guarantee that gcc and the linker won't up-align the tracepoint * structures, so we create an array of pointers that will be used for iteration -- cgit v1.2.3 From f366d322aea782cf786aa821d5accdc1609f9e10 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Sep 2018 10:19:30 +0100 Subject: UAPI: ndctl: Remove use of PAGE_SIZE The macro PAGE_SIZE isn't valid outside of the kernel, so it should not appear in UAPI headers. Furthermore, the actual machine page size could theoretically change from an application's point of view if it's running in a container that gets migrated to another machine (say 4K/ppc64 to 64K/ppc64). Fixes: f2ba5a5baecf ("libnvdimm, namespace: make min namespace size 4K") Signed-off-by: David Howells Signed-off-by: Dan Williams --- include/linux/ndctl.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 include/linux/ndctl.h (limited to 'include/linux') diff --git a/include/linux/ndctl.h b/include/linux/ndctl.h new file mode 100644 index 000000000000..cd5a293ce3ae --- /dev/null +++ b/include/linux/ndctl.h @@ -0,0 +1,22 @@ +/* + * Copyright (c) 2014-2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU Lesser General Public License, + * version 2.1, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT ANY + * WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS + * FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for + * more details. + */ +#ifndef _LINUX_NDCTL_H +#define _LINUX_NDCTL_H + +#include + +enum { + ND_MIN_NAMESPACE_SIZE = PAGE_SIZE, +}; + +#endif /* _LINUX_NDCTL_H */ -- cgit v1.2.3 From b8aee82250b7d90a32b11ba208656f52dbaca342 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 2 Oct 2018 22:57:24 +0000 Subject: net/mlx5: E-Switch, Get counters for offloaded flows from callers There's no real reason for the e-switch logic to manage the creation of counters for offloaded flows. The API already has the directive for the caller to denote they want to attach a counter to the created flow. As such, we go and move the management of flow counters to the mlx5e tc offload logic. This also lets us remove an inelegant interface where the FS layer had to provide a way to retrieve a counter from a flow rule. Signed-off-by: Mark Bloch Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index b1c026f1c8ba..74d0ea146c9a 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -186,7 +186,6 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler, struct mlx5_flow_destination *new_dest, struct mlx5_flow_destination *old_dest); -struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handler); struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, -- cgit v1.2.3 From 171c7625bef999848ee6032c6dde96e7330c4d15 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Wed, 3 Oct 2018 00:03:35 +0000 Subject: net/mlx5: Use flow counter IDs and not the wrapping cache object Currently, when a flow rule is created using the FS core layer, the caller has to pass the entire flow counter object and not just the counter HW handle (ID). This requires both the FS core and the caller to have knowledge about the inner implementation of the FS layer flow counters cache and limits the possible users. Move to use the counter ID across the place when dealing with flows. Doing this decoupling, now can we privatize the inner implementation of the flow counters. Signed-off-by: Mark Bloch Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 74d0ea146c9a..a5fc62184195 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -92,7 +92,7 @@ struct mlx5_flow_destination { u32 tir_num; u32 ft_num; struct mlx5_flow_table *ft; - struct mlx5_fc *counter; + u32 counter_id; struct { u16 num; u16 vhca_id; @@ -192,6 +192,7 @@ void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, u64 *packets, u64 *bytes); +u32 mlx5_fc_id(struct mlx5_fc *counter); int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); -- cgit v1.2.3 From b9aa0ba17af5afa13605eb6ea91f1974da97a2e2 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 31 May 2018 11:50:23 +0300 Subject: net/mlx5: Add cap bits for multi fdb encap If set, the firmware supports creating of flow tables with encap enabled while VFs are configured, if we already created one (restriction still applies on the first creation). Signed-off-by: Paul Blakey Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 15e36198f85f..963611820006 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -584,7 +584,9 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 reserved_at_0[0x1c]; u8 fdb_multi_path_to_table[0x1]; - u8 reserved_at_1d[0x1e3]; + u8 reserved_at_1d[0x1]; + u8 multi_fdb_encap[0x1]; + u8 reserved_at_1e[0x1e1]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb; -- cgit v1.2.3 From 328edb499f99126946845ece477c9c1afe8631af Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 3 Jul 2018 11:13:00 +0300 Subject: net/mlx5: Split FDB fast path prio to multiple namespaces Towards supporting multi-chains and priorities, split the FDB fast path to multiple namespaces (sub namespaces), each with multiple priorities. This patch adds a new flow steering type, FS_TYPE_PRIO_CHAINS, which is like current FS_TYPE_PRIO, but may contain only namespaces, and those will be in parallel to one another in terms of managing of the flow tables connections inside them. Meaning, while searching for the next or previous flow table to connect for a new table inside such namespace we skip the parallel namespaces in the same level under the FS_TYPE_PRIO_CHAINS prio we originated from. We use this new type for splitting the fast path prio into multiple parallel namespaces, each containing normal prios. The prios inside them (and their tables) will be connected to one another, but not from one parallel namespace to another, instead the last prio in each namespace will be connected to the next prio in the containing FDB namespace, which is the slow path prio. Signed-off-by: Paul Blakey Acked-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index a5fc62184195..f8d00872c7d3 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -101,6 +101,8 @@ struct mlx5_flow_destination { }; }; +struct mlx5_flow_namespace * +mlx5_get_fdb_sub_ns(struct mlx5_core_dev *dev, int n); struct mlx5_flow_namespace * mlx5_get_flow_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type); -- cgit v1.2.3 From d5634fee245f9e92787e3a34ef621fc12b2cbf16 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 20 Sep 2018 12:17:48 +0200 Subject: net/mlx5: Add a no-append flow insertion mode If no-append flag is set, we will add a new FTE, instead of appending the actions of the inserted rule when the same match already exists. While here, move the has_flow_tag boolean indicator to be a flag too. This patch doesn't change any functionality. Signed-off-by: Paul Blakey Reviewed-by: Or Gerlitz Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index f8d00872c7d3..5660f07d3be0 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -158,20 +158,28 @@ struct mlx5_fs_vlan { #define MLX5_FS_VLAN_DEPTH 2 +enum { + FLOW_ACT_HAS_TAG = BIT(0), + FLOW_ACT_NO_APPEND = BIT(1), +}; + struct mlx5_flow_act { u32 action; - bool has_flow_tag; u32 flow_tag; u32 reformat_id; u32 modify_id; uintptr_t esp_id; + u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; }; #define MLX5_DECLARE_FLOW_ACT(name) \ - struct mlx5_flow_act name = {MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\ - MLX5_FS_DEFAULT_FLOW_TAG, 0, 0} + struct mlx5_flow_act name = { .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\ + .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, \ + .reformat_id = 0, \ + .modify_id = 0, \ + .flags = 0, } /* Single destination per rule. * Group ID is implied by the match criteria. -- cgit v1.2.3 From 82385b0d2d2504aee51aa3fb40ebfb03603f64c3 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 17 Oct 2018 15:01:37 +0200 Subject: net: skbuff.h: Mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Acked-by: Kees Cook Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 119d092c6b13..0ba687454267 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3505,13 +3505,19 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); + /* fall through */ case 24: diffs |= __it_diff(a, b, 64); + /* fall through */ case 16: diffs |= __it_diff(a, b, 64); + /* fall through */ case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); + /* fall through */ case 20: diffs |= __it_diff(a, b, 64); + /* fall through */ case 12: diffs |= __it_diff(a, b, 64); + /* fall through */ case 4: diffs |= __it_diff(a, b, 32); break; } -- cgit v1.2.3 From eb66ae030829605d61fbef1909ce310e29f78821 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 12 Oct 2018 15:22:59 -0700 Subject: mremap: properly flush TLB before releasing the page Jann Horn points out that our TLB flushing was subtly wrong for the mremap() case. What makes mremap() special is that we don't follow the usual "add page to list of pages to be freed, then flush tlb, and then free pages". No, mremap() obviously just _moves_ the page from one page table location to another. That matters, because mremap() thus doesn't directly control the lifetime of the moved page with a freelist: instead, the lifetime of the page is controlled by the page table locking, that serializes access to the entry. As a result, we need to flush the TLB not just before releasing the lock for the source location (to avoid any concurrent accesses to the entry), but also before we release the destination page table lock (to avoid the TLB being flushed after somebody else has already done something to that page). This also makes the whole "need_flush" logic unnecessary, since we now always end up flushing the TLB for every valid entry. Reported-and-tested-by: Jann Horn Acked-by: Will Deacon Tested-by: Ingo Molnar Acked-by: Peter Zijlstra (Intel) Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/huge_mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 99c19b06d9a4..fdcb45999b26 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -43,7 +43,7 @@ extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned char *vec); extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, - pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush); + pmd_t *old_pmd, pmd_t *new_pmd); extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); -- cgit v1.2.3 From e5089c2c73a157997eb6ecca982adea9d0673075 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 3 Oct 2018 16:38:16 +0200 Subject: PM / Domains: Document flags for genpd The current documented description of the GENPD_FLAG_* flags, are too simplified, so let's extend them. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 35 ++++++++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 776c546d581a..3b5d7280e52e 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -17,11 +17,36 @@ #include #include -/* Defines used for the flags field in the struct generic_pm_domain */ -#define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ -#define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */ -#define GENPD_FLAG_ALWAYS_ON (1U << 2) /* PM domain is always powered on */ -#define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3) /* Keep devices active if wakeup */ +/* + * Flags to control the behaviour of a genpd. + * + * These flags may be set in the struct generic_pm_domain's flags field by a + * genpd backend driver. The flags must be set before it calls pm_genpd_init(), + * which initializes a genpd. + * + * GENPD_FLAG_PM_CLK: Instructs genpd to use the PM clk framework, + * while powering on/off attached devices. + * + * GENPD_FLAG_IRQ_SAFE: This informs genpd that its backend callbacks, + * ->power_on|off(), doesn't sleep. Hence, these + * can be invoked from within atomic context, which + * enables genpd to power on/off the PM domain, + * even when pm_runtime_is_irq_safe() returns true, + * for any of its attached devices. Note that, a + * genpd having this flag set, requires its + * masterdomains to also have it set. + * + * GENPD_FLAG_ALWAYS_ON: Instructs genpd to always keep the PM domain + * powered on. + * + * GENPD_FLAG_ACTIVE_WAKEUP: Instructs genpd to keep the PM domain powered + * on, in case any of its attached devices is used + * in the wakeup path to serve system wakeups. + */ +#define GENPD_FLAG_PM_CLK (1U << 0) +#define GENPD_FLAG_IRQ_SAFE (1U << 1) +#define GENPD_FLAG_ALWAYS_ON (1U << 2) +#define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3) enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ -- cgit v1.2.3 From f349b0a3e1f0d184374936f1b2a49352f8a4b1c8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Tue, 9 Oct 2018 22:13:42 +0200 Subject: dm: add dm_table_device_name() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a shortcut for dm_device_name(dm_table_get_md(t)). Signed-off-by: Michał Mirosław Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 8d937754aa0c..d7bee8669f10 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -489,6 +489,7 @@ sector_t dm_table_get_size(struct dm_table *t); unsigned int dm_table_get_num_targets(struct dm_table *t); fmode_t dm_table_get_mode(struct dm_table *t); struct mapped_device *dm_table_get_md(struct dm_table *t); +const char *dm_table_device_name(struct dm_table *t); /* * Trigger an event. -- cgit v1.2.3 From 4972e6fa3a04032830bc3d6bb343d08ab3546773 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 12 Sep 2018 15:36:41 +0300 Subject: net/mlx5: Refactor fragmented buffer struct fields and init flow Take struct mlx5_frag_buf out of mlx5_frag_buf_ctrl, as it is not needed to manage and control the datapath of the fragmented buffers API. struct mlx5_frag_buf contains control info to manage the allocation and de-allocation of the fragmented buffer. Its fields are not relevant for datapath, so here I take them out of the struct mlx5_frag_buf_ctrl, except for the fragments array itself. In addition, modified mlx5_fill_fbc to initialise the frags pointers as well. This implies that the buffer must be allocated before the function is called. A set of type-specific *_get_byte_size() functions are replaced by a generic one. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 94ffd02af7cd..e10f61a1f77d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -357,7 +357,7 @@ struct mlx5_frag_buf { }; struct mlx5_frag_buf_ctrl { - struct mlx5_frag_buf frag_buf; + struct mlx5_buf_list *frags; u32 sz_m1; u16 frag_sz_m1; u16 strides_offset; @@ -994,10 +994,12 @@ static inline u32 mlx5_base_mkey(const u32 key) return key & 0xffffff00u; } -static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, +static inline void mlx5_init_fbc_offset(struct mlx5_buf_list *frags, + u8 log_stride, u8 log_sz, u16 strides_offset, struct mlx5_frag_buf_ctrl *fbc) { + fbc->frags = frags; fbc->log_stride = log_stride; fbc->log_sz = log_sz; fbc->sz_m1 = (1 << fbc->log_sz) - 1; @@ -1006,18 +1008,11 @@ static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, fbc->strides_offset = strides_offset; } -static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, +static inline void mlx5_init_fbc(struct mlx5_buf_list *frags, + u8 log_stride, u8 log_sz, struct mlx5_frag_buf_ctrl *fbc) { - mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc); -} - -static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, - void *cqc) -{ - mlx5_fill_fbc(6 + MLX5_GET(cqc, cqc, cqe_sz), - MLX5_GET(cqc, cqc, log_cq_size), - fbc); + mlx5_init_fbc_offset(frags, log_stride, log_sz, 0, fbc); } static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, @@ -1028,8 +1023,7 @@ static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, ix += fbc->strides_offset; frag = ix >> fbc->log_frag_strides; - return fbc->frag_buf.frags[frag].buf + - ((fbc->frag_sz_m1 & ix) << fbc->log_stride); + return fbc->frags[frag].buf + ((fbc->frag_sz_m1 & ix) << fbc->log_stride); } int mlx5_cmd_init(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 4b5b9c7d972e8a7b1e7691c7c921ec0d6dec33b9 Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Tue, 9 Oct 2018 14:16:43 +0300 Subject: net/mlx5: Add FEC fields to Port Phy Link Mode (PPLM) reg Added FEC related fields to PPLM layout. These fields are needed to set and query FEC policy for different link speeds. Signed-off-by: Shay Agroskin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 39 ++++++++++++++++++++++++++++----------- 2 files changed, 29 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e10f61a1f77d..696ed3f7f894 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -133,6 +133,7 @@ enum { MLX5_REG_PVLC = 0x500f, MLX5_REG_PCMR = 0x5041, MLX5_REG_PMLP = 0x5002, + MLX5_REG_PPLM = 0x5023, MLX5_REG_PCAM = 0x507f, MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 963611820006..47b09a742ae5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -7828,20 +7828,34 @@ struct mlx5_ifc_pplr_reg_bits { struct mlx5_ifc_pplm_reg_bits { u8 reserved_at_0[0x8]; - u8 local_port[0x8]; - u8 reserved_at_10[0x10]; + u8 local_port[0x8]; + u8 reserved_at_10[0x10]; - u8 reserved_at_20[0x20]; + u8 reserved_at_20[0x20]; - u8 port_profile_mode[0x8]; - u8 static_port_profile[0x8]; - u8 active_port_profile[0x8]; - u8 reserved_at_58[0x8]; + u8 port_profile_mode[0x8]; + u8 static_port_profile[0x8]; + u8 active_port_profile[0x8]; + u8 reserved_at_58[0x8]; - u8 retransmission_active[0x8]; - u8 fec_mode_active[0x18]; + u8 retransmission_active[0x8]; + u8 fec_mode_active[0x18]; - u8 reserved_at_80[0x20]; + u8 rs_fec_correction_bypass_cap[0x4]; + u8 reserved_at_84[0x8]; + u8 fec_override_cap_56g[0x4]; + u8 fec_override_cap_100g[0x4]; + u8 fec_override_cap_50g[0x4]; + u8 fec_override_cap_25g[0x4]; + u8 fec_override_cap_10g_40g[0x4]; + + u8 rs_fec_correction_bypass_admin[0x4]; + u8 reserved_at_a4[0x8]; + u8 fec_override_admin_56g[0x4]; + u8 fec_override_admin_100g[0x4]; + u8 fec_override_admin_50g[0x4]; + u8 fec_override_admin_25g[0x4]; + u8 fec_override_admin_10g_40g[0x4]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -8137,7 +8151,10 @@ struct mlx5_ifc_pcam_enhanced_features_bits { struct mlx5_ifc_pcam_regs_5000_to_507f_bits { u8 port_access_reg_cap_mask_127_to_96[0x20]; u8 port_access_reg_cap_mask_95_to_64[0x20]; - u8 port_access_reg_cap_mask_63_to_32[0x20]; + + u8 port_access_reg_cap_mask_63_to_36[0x1c]; + u8 pplm[0x1]; + u8 port_access_reg_cap_mask_34_to_32[0x3]; u8 port_access_reg_cap_mask_31_to_13[0x13]; u8 pbmc[0x1]; -- cgit v1.2.3 From 67daf1186086ad4b2ec09b8078b835936977d06a Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Sun, 30 Sep 2018 09:58:08 +0300 Subject: net/mlx5: Added "per_lane_error_counters" cap bit to PCAM Added "Per lane raw errors" capability bit in Ports Capabilities Mask (PCAM) enhanced features layout. This bit determines if the fields "phy_raw_errors_laneX" in "Physical Layer statistical" counters group are supported. Signed-off-by: Shay Agroskin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 47b09a742ae5..dbff9ff28f2c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8140,7 +8140,8 @@ struct mlx5_ifc_pcam_enhanced_features_bits { u8 rx_icrc_encapsulated_counter[0x1]; u8 reserved_at_6e[0x8]; u8 pfcc_mask[0x1]; - u8 reserved_at_77[0x4]; + u8 reserved_at_77[0x3]; + u8 per_lane_error_counters[0x1]; u8 rx_buffer_fullness_counters[0x1]; u8 ptys_connector_type[0x1]; u8 reserved_at_7d[0x1]; -- cgit v1.2.3 From 01a14bda11add9dcd4a59200f13834d634559935 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 18 Oct 2018 21:45:18 -0400 Subject: locking/lockdep: Make global debug_locks* variables read-mostly Make the frequently used lockdep global variable debug_locks read-mostly. As debug_locks_silent is sometime used together with debug_locks, it is also made read-mostly so that they can be close together. With false cacheline sharing, cacheline contention problem can happen depending on what get put into the same cacheline as debug_locks. Signed-off-by: Waiman Long Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: http://lkml.kernel.org/r/1539913518-15598-2-git-send-email-longman@redhat.com Signed-off-by: Ingo Molnar --- include/linux/debug_locks.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 120225e9a366..257ab3c92cb8 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -8,8 +8,8 @@ struct task_struct; -extern int debug_locks; -extern int debug_locks_silent; +extern int debug_locks __read_mostly; +extern int debug_locks_silent __read_mostly; static inline int __debug_locks_off(void) -- cgit v1.2.3 From b65125c6acf38388d3342b37c18c3b6cc97eeb75 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 12 Apr 2018 14:49:23 +0200 Subject: swiotlb: mark is_swiotlb_buffer static Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy Reviewed-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 965be92c33b5..7ef541ce8f34 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -121,7 +121,6 @@ static inline unsigned int swiotlb_max_segment(void) { return 0; } #endif extern void swiotlb_print_info(void); -extern int is_swiotlb_buffer(phys_addr_t paddr); extern void swiotlb_set_max_segment(unsigned int); extern const struct dma_map_ops swiotlb_dma_ops; -- cgit v1.2.3 From dff8d6c1ed584de65aac40494d3e7468c50980c3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Aug 2018 15:30:39 +0300 Subject: swiotlb: remove the overflow buffer Like all other dma mapping drivers just return an error code instead of an actual memory buffer. The reason for the overflow buffer was that at the time swiotlb was invented there was no way to check for dma mapping errors, but this has long been fixed. Signed-off-by: Christoph Hellwig Acked-by: Catalin Marinas Reviewed-by: Robin Murphy Reviewed-by: Konrad Rzeszutek Wilk --- include/linux/dma-direct.h | 2 ++ include/linux/swiotlb.h | 3 --- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index fbca184ff5a0..bd73e7a91410 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,6 +5,8 @@ #include #include +#define DIRECT_MAPPING_ERROR 0 + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #else diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 7ef541ce8f34..f847c1b265c4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -106,9 +106,6 @@ extern void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, int nelems, enum dma_data_direction dir); -extern int -swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr); - extern int swiotlb_dma_supported(struct device *hwdev, u64 mask); -- cgit v1.2.3 From fe0640eb30b7da261ae84d252ed9ed3c7e68dfd8 Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Mon, 15 Oct 2018 10:22:21 -0700 Subject: compiler.h: update definition of unreachable() Fixes the objtool warning seen with Clang: arch/x86/mm/fault.o: warning: objtool: no_context()+0x220: unreachable instruction Fixes commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Josh noted that the fallback definition was meant to work around a pre-gcc-4.6 bug. GCC still needs to work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82365, so compiler-gcc.h defines its own version of unreachable(). Clang and ICC can use this shared definition. Link: https://github.com/ClangBuiltLinux/linux/issues/204 Suggested-by: Andy Lutomirski Suggested-by: Josh Poimboeuf Tested-by: Nathan Chancellor Signed-off-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index b5fb034fa6fa..2e0b6322588b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -124,7 +124,10 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define ASM_UNREACHABLE #endif #ifndef unreachable -# define unreachable() do { annotate_reachable(); do { } while (1); } while (0) +# define unreachable() do { \ + annotate_unreachable(); \ + __builtin_unreachable(); \ +} while (0) #endif /* -- cgit v1.2.3 From 1ff2fea5e30ca15752777441ecb64a169fe22e9e Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Mon, 15 Oct 2018 14:24:27 -0700 Subject: compiler-gcc: remove comment about gcc 4.5 from unreachable() Remove the comment about being unable to detect __builtin_unreachable. __builtin_unreachable was implemented in the GCC 4.5 timeframe. The kernel's minimum supported version of GCC is 4.6 since commit cafa0010cd51 ("Raise the minimum required gcc version to 4.6"). Commit cb984d101b30 ("compiler-gcc: integrate the various compiler-gcc[345].h files") shows that unreachable() had different guards based on GCC version. Suggested-by: Miguel Ojeda Signed-off-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler-gcc.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index cfac027e1625..2010493e1040 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -96,10 +96,6 @@ * Mark a position in code as unreachable. This can be used to * suppress control flow warnings after asm blocks that transfer * control elsewhere. - * - * Early snapshots of gcc 4.5 don't support this and we can't detect - * this in the preprocessor, but we can live with this because they're - * unreleased. Really, we need to have autoconf for the kernel. */ #define unreachable() \ do { \ -- cgit v1.2.3 From fafadcd16595c1df82df399f62421718ec9bf70a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 30 Sep 2018 16:13:33 -0700 Subject: swiotlb: don't dip into swiotlb pool for coherent allocations All architectures that support swiotlb also have a zone that backs up these less than full addressing allocations (usually ZONE_DMA32). Because of that it is rather pointless to fall back to the global swiotlb buffer if the normal dma direct allocation failed - the only thing this will do is to eat up bounce buffers that would be more useful to serve streaming mappings. Signed-off-by: Christoph Hellwig Acked-by: Catalin Marinas Acked-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index f847c1b265c4..a387b59640a4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -67,11 +67,6 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev, /* Accessory functions. */ -void *swiotlb_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_handle, - gfp_t flags, unsigned long attrs); -void swiotlb_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, unsigned long attrs); - extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, -- cgit v1.2.3 From cdf6b11daa77d4b55ddf0530842a551cc5562a93 Mon Sep 17 00:00:00 2001 From: Ben Whitten Date: Fri, 19 Oct 2018 10:33:50 +0100 Subject: regmap: Add regmap_noinc_write API The regmap API had a noinc_read function added for instances where devices supported returning data from an internal FIFO in a single read. This commit adds the noinc_write variant to allow writing to a non incrementing register, this is used in devices such as the sx1301 for loading firmware. Signed-off-by: Ben Whitten Signed-off-by: Mark Brown --- include/linux/regmap.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 379505a53722..de04dc46c7a9 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -268,6 +268,13 @@ typedef void (*regmap_unlock)(void *); * field is NULL but precious_table (see below) is not, the * check is performed on such table (a register is precious if * it belongs to one of the ranges specified by precious_table). + * @writeable_noinc_reg: Optional callback returning true if the register + * supports multiple write operations without incrementing + * the register number. If this field is NULL but + * wr_noinc_table (see below) is not, the check is + * performed on such table (a register is no increment + * writeable if it belongs to one of the ranges specified + * by wr_noinc_table). * @readable_noinc_reg: Optional callback returning true if the register * supports multiple read operations without incrementing * the register number. If this field is NULL but @@ -302,6 +309,7 @@ typedef void (*regmap_unlock)(void *); * @rd_table: As above, for read access. * @volatile_table: As above, for volatile registers. * @precious_table: As above, for precious registers. + * @wr_noinc_table: As above, for no increment writeable registers. * @rd_noinc_table: As above, for no increment readable registers. * @reg_defaults: Power on reset values for registers (for use with * register cache support). @@ -352,6 +360,7 @@ struct regmap_config { bool (*readable_reg)(struct device *dev, unsigned int reg); bool (*volatile_reg)(struct device *dev, unsigned int reg); bool (*precious_reg)(struct device *dev, unsigned int reg); + bool (*writeable_noinc_reg)(struct device *dev, unsigned int reg); bool (*readable_noinc_reg)(struct device *dev, unsigned int reg); bool disable_locking; @@ -369,6 +378,7 @@ struct regmap_config { const struct regmap_access_table *rd_table; const struct regmap_access_table *volatile_table; const struct regmap_access_table *precious_table; + const struct regmap_access_table *wr_noinc_table; const struct regmap_access_table *rd_noinc_table; const struct reg_default *reg_defaults; unsigned int num_reg_defaults; @@ -979,6 +989,8 @@ int regmap_write(struct regmap *map, unsigned int reg, unsigned int val); int regmap_write_async(struct regmap *map, unsigned int reg, unsigned int val); int regmap_raw_write(struct regmap *map, unsigned int reg, const void *val, size_t val_len); +int regmap_noinc_write(struct regmap *map, unsigned int reg, + const void *val, size_t val_len); int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, size_t val_count); int regmap_multi_reg_write(struct regmap *map, const struct reg_sequence *regs, @@ -1222,6 +1234,13 @@ static inline int regmap_raw_write_async(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_noinc_write(struct regmap *map, unsigned int reg, + const void *val, size_t val_len) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, size_t val_count) { -- cgit v1.2.3 From bcb047ebf28453da56f0265aeeb9edc52b797ea7 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Thu, 4 Oct 2018 15:25:58 +0800 Subject: regulator: bd718x7: Remove struct bd718xx_pmic All the fields in struct bd718xx_pmic are not really necessary. Remove struct bd718xx_pmic to simplify the code. Signed-off-by: Axel Lin Reviewed-by: Matti Vaittinen Signed-off-by: Mark Brown --- include/linux/mfd/rohm-bd718x7.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index 26acf9a92498..fd194bfc836f 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -321,7 +321,6 @@ enum { BD718XX_PWRBTN_LONG_PRESS_15S }; -struct bd718xx_pmic; struct bd718xx_clk; struct bd718xx { @@ -333,7 +332,6 @@ struct bd718xx { int chip_irq; struct regmap_irq_chip_data *irq_data; - struct bd718xx_pmic *pmic; struct bd718xx_clk *clk; }; -- cgit v1.2.3 From 99c228a994ec8b1580c43631866fd2c5440f5bfd Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 18 Oct 2018 14:22:55 +0300 Subject: fs: group frequently accessed fields of struct super_block together Kernel test robot reported [1] a 6% performance regression in a concurrent unlink(2) workload on commit 60f7ed8c7c4d ("fsnotify: send path type events to group with super block marks"). The performance test was run with no fsnotify marks at all on the data set, so the only extra instructions added by the offending commit are tests of the super_block fields s_fsnotify_{marks,mask} and these tests happen on almost every single inode access. When adding those fields to the super_block struct, we did not give much thought of placing them on a hot cache lines (we just placed them at the end of the struct). Re-organize struct super_block to try and keep some frequently accessed fields on the same cache line. Move the frequently accessed fields s_fsnotify_{marks,mask} near the frequently accessed fields s_fs_info,s_time_gran, while filling a 64bit alignment hole after s_time_gran. Move the seldom accessed fields s_id,s_uuid,s_max_links,s_mode near the seldom accessed fields s_vfs_rename_mutex,s_subtype. Rong Chen confirmed that this patch solved the reported problem. [1] https://lkml.org/lkml/2018/9/30/206 Reported-by: kernel test robot Tested-by: kernel test robot Fixes: 1e6cb72399 ("fsnotify: add super block object type") Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fs.h | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c14801d0aa3..6da94deb957f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1393,17 +1393,26 @@ struct super_block { struct sb_writers s_writers; + /* + * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and + * s_fsnotify_marks together for cache efficiency. They are frequently + * accessed and rarely modified. + */ + void *s_fs_info; /* Filesystem private info */ + + /* Granularity of c/m/atime in ns (cannot be worse than a second) */ + u32 s_time_gran; +#ifdef CONFIG_FSNOTIFY + __u32 s_fsnotify_mask; + struct fsnotify_mark_connector __rcu *s_fsnotify_marks; +#endif + char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ - void *s_fs_info; /* Filesystem private info */ unsigned int s_max_links; fmode_t s_mode; - /* Granularity of c/m/atime in ns. - Cannot be worse than a second */ - u32 s_time_gran; - /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. @@ -1464,11 +1473,6 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ - -#ifdef CONFIG_FSNOTIFY - __u32 s_fsnotify_mask; - struct fsnotify_mark_connector __rcu *s_fsnotify_marks; -#endif } __randomize_layout; /* Helper functions so that in most cases filesystems will -- cgit v1.2.3 From 3952105df4723abbd36b57e88c8dad42cf6c8b59 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Wed, 17 Oct 2018 19:25:23 +0530 Subject: remoteproc: Introduce custom dump function for each remoteproc segment Introduce custom dump function and private data per remoteproc dump segment. The dump function is responsible for filling the device memory segment associated with coredump Signed-off-by: Sibi Sankar Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 8bb0cf0416f1..2d036adab7ff 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -412,6 +412,9 @@ enum rproc_crash_type { * @node: list node related to the rproc segment list * @da: device address of the segment * @size: size of the segment + * @priv: private data associated with the dump_segment + * @dump: custom dump function to fill device memory segment associated + * with coredump */ struct rproc_dump_segment { struct list_head node; @@ -419,6 +422,9 @@ struct rproc_dump_segment { dma_addr_t da; size_t size; + void *priv; + void (*dump)(struct rproc *rproc, struct rproc_dump_segment *segment, + void *dest); loff_t offset; }; -- cgit v1.2.3 From ab8f873bb90da7bbe40e2f41c92a4971c4f0dc76 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Wed, 17 Oct 2018 19:25:24 +0530 Subject: remoteproc: Add mechanism for custom dump function assignment This patch adds a mechanism for assigning each rproc dump segment with a custom dump function and private data. The dump function is to be called for each rproc segment during coredump if assigned. Signed-off-by: Sibi Sankar [bjorn: reordred arguments to rproc_coredump_add_custom_segment()] Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 2d036adab7ff..507a2b524208 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -592,6 +592,12 @@ int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size); +int rproc_coredump_add_custom_segment(struct rproc *rproc, + dma_addr_t da, size_t size, + void (*dumpfn)(struct rproc *rproc, + struct rproc_dump_segment *segment, + void *dest), + void *priv); static inline struct rproc_vdev *vdev_to_rvdev(struct virtio_device *vdev) { -- cgit v1.2.3 From 144991602e6a14d667b295f1b099e609ce857772 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Thu, 18 Oct 2018 15:16:09 +0200 Subject: bpf: rename stack trace map operations In the following patches queue and stack maps (FIFO and LIFO datastructures) will be implemented. In order to avoid confusion and a possible name clash rename stack_map_ops to stack_trace_map_ops Signed-off-by: Mauricio Vasquez B Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/bpf_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index fa48343a5ea1..7bad4e1947ed 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -51,7 +51,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, htab_lru_percpu_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_LPM_TRIE, trie_map_ops) #ifdef CONFIG_PERF_EVENTS -BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) -- cgit v1.2.3 From 2ea864c58f19bf70a0e2415f9f1c53814e07f1b4 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Thu, 18 Oct 2018 15:16:20 +0200 Subject: bpf/verifier: add ARG_PTR_TO_UNINIT_MAP_VALUE ARG_PTR_TO_UNINIT_MAP_VALUE argument is a pointer to a memory zone used to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. This will be used in the following patch that implements some new helpers that receive a pointer to be filled with a map value. Signed-off-by: Mauricio Vasquez B Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e60fff48288b..0f8b863e0229 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -138,6 +138,7 @@ enum bpf_arg_type { ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ + ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack -- cgit v1.2.3 From f1a2e44a3aeccb3ff18d3ccc0b0203e70b95bd92 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Thu, 18 Oct 2018 15:16:25 +0200 Subject: bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 ++++++ include/linux/bpf_types.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0f8b863e0229..33014ae73103 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -39,6 +39,9 @@ struct bpf_map_ops { void *(*map_lookup_elem)(struct bpf_map *map, void *key); int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_map *map, void *key); + int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); + int (*map_pop_elem)(struct bpf_map *map, void *value); + int (*map_peek_elem)(struct bpf_map *map, void *value); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, @@ -811,6 +814,9 @@ static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; +extern const struct bpf_func_proto bpf_map_push_elem_proto; +extern const struct bpf_func_proto bpf_map_pop_elem_proto; +extern const struct bpf_func_proto bpf_map_peek_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 7bad4e1947ed..44d9ab4809bd 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -69,3 +69,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops) #endif #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) -- cgit v1.2.3 From b39b5f411dcfce28ff954e5d6acb2c11be3cb0ec Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 19 Oct 2018 09:57:57 -0700 Subject: bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB BPF programs of BPF_PROG_TYPE_CGROUP_SKB need to access headers in the skb. This patch enables direct access of skb for these programs. Two helper functions bpf_compute_and_save_data_end() and bpf_restore_data_end() are introduced. There are used in __cgroup_bpf_run_filter_skb(), to compute proper data_end for the BPF program, and restore original data afterwards. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 5771874bc01e..91b4c934f02e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -548,6 +548,27 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb) cb->data_end = skb->data + skb_headlen(skb); } +/* Similar to bpf_compute_data_pointers(), except that save orginal + * data in cb->data and cb->meta_data for restore. + */ +static inline void bpf_compute_and_save_data_end( + struct sk_buff *skb, void **saved_data_end) +{ + struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; + + *saved_data_end = cb->data_end; + cb->data_end = skb->data + skb_headlen(skb); +} + +/* Restore data saved by bpf_compute_data_pointers(). */ +static inline void bpf_restore_data_end( + struct sk_buff *skb, void *saved_data_end) +{ + struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; + + cb->data_end = saved_data_end; +} + static inline u8 *bpf_skb_cb(struct sk_buff *skb) { /* eBPF programs may read/write skb->cb[] area to transfer meta -- cgit v1.2.3 From 5032d079909d1ac5c2535acc32d5f01cd245d8ea Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 18 Oct 2018 13:58:35 -0700 Subject: bpf: skmsg, fix psock create on existing kcm/tls port Before using the psock returned by sk_psock_get() when adding it to a sockmap we need to ensure it is actually a sockmap based psock. Previously we were only checking this after incrementing the reference counter which was an error. This resulted in a slab-out-of-bounds error when the psock was not actually a sockmap type. This moves the check up so the reference counter is only used if it is a sockmap psock. Eric reported the following KASAN BUG, BUG: KASAN: slab-out-of-bounds in atomic_read include/asm-generic/atomic-instrumented.h:21 [inline] BUG: KASAN: slab-out-of-bounds in refcount_inc_not_zero_checked+0x97/0x2f0 lib/refcount.c:120 Read of size 4 at addr ffff88019548be58 by task syz-executor4/22387 CPU: 1 PID: 22387 Comm: syz-executor4 Not tainted 4.19.0-rc7+ #264 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c4/0x2b4 lib/dump_stack.c:113 print_address_description.cold.8+0x9/0x1ff mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.9+0x242/0x309 mm/kasan/report.c:412 check_memory_region_inline mm/kasan/kasan.c:260 [inline] check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267 kasan_check_read+0x11/0x20 mm/kasan/kasan.c:272 atomic_read include/asm-generic/atomic-instrumented.h:21 [inline] refcount_inc_not_zero_checked+0x97/0x2f0 lib/refcount.c:120 sk_psock_get include/linux/skmsg.h:379 [inline] sock_map_link.isra.6+0x41f/0xe30 net/core/sock_map.c:178 sock_hash_update_common+0x19b/0x11e0 net/core/sock_map.c:669 sock_hash_update_elem+0x306/0x470 net/core/sock_map.c:738 map_update_elem+0x819/0xdf0 kernel/bpf/syscall.c:818 Signed-off-by: John Fastabend Reported-by: Eric Dumazet Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 22347b08e1f8..84e18863f6a4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -270,11 +270,6 @@ static inline struct sk_psock *sk_psock(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } -static inline bool sk_has_psock(struct sock *sk) -{ - return sk_psock(sk) != NULL && sk->sk_prot->recvmsg == tcp_bpf_recvmsg; -} - static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { @@ -374,6 +369,26 @@ static inline bool sk_psock_test_state(const struct sk_psock *psock, return test_bit(bit, &psock->state); } +static inline struct sk_psock *sk_psock_get_checked(struct sock *sk) +{ + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + if (psock) { + if (sk->sk_prot->recvmsg != tcp_bpf_recvmsg) { + psock = ERR_PTR(-EBUSY); + goto out; + } + + if (!refcount_inc_not_zero(&psock->refcnt)) + psock = ERR_PTR(-EBUSY); + } +out: + rcu_read_unlock(); + return psock; +} + static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; -- cgit v1.2.3 From c9fbd71f73094311b31ee703a918e9e0df502cef Mon Sep 17 00:00:00 2001 From: Debabrata Banerjee Date: Thu, 18 Oct 2018 11:18:26 -0400 Subject: netpoll: allow cleanup to be synchronous This fixes a problem introduced by: commit 2cde6acd49da ("netpoll: Fix __netpoll_rcu_free so that it can hold the rtnl lock") When using netconsole on a bond, __netpoll_cleanup can asynchronously recurse multiple times, each __netpoll_free_async call can result in more __netpoll_free_async's. This means there is now a race between cleanup_work queues on multiple netpoll_info's on multiple devices and the configuration of a new netpoll. For example if a netconsole is set to enable 0, reconfigured, and enable 1 immediately, this netconsole will likely not work. Given the reason for __netpoll_free_async is it can be called when rtnl is not locked, if it is locked, we should be able to execute synchronously. It appears to be locked everywhere it's called from. Generalize the design pattern from the teaming driver for current callers of __netpoll_free_async. CC: Neil Horman CC: "David S. Miller" Signed-off-by: Debabrata Banerjee Signed-off-by: David S. Miller --- include/linux/netpoll.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 3ef82d3a78db..676f1ff161a9 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -31,8 +31,6 @@ struct netpoll { bool ipv6; u16 local_port, remote_port; u8 remote_mac[ETH_ALEN]; - - struct work_struct cleanup_work; }; struct netpoll_info { @@ -63,7 +61,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt); int __netpoll_setup(struct netpoll *np, struct net_device *ndev); int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); -void __netpoll_free_async(struct netpoll *np); +void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, struct net_device *dev); -- cgit v1.2.3 From bff5b4b3737219195ca0caef4ff7884303cb5dc1 Mon Sep 17 00:00:00 2001 From: Yuiko Oshino Date: Thu, 18 Oct 2018 15:06:01 -0400 Subject: net: phy: micrel: add Microchip KSZ9131 initial driver Add support for Microchip Technology KSZ9131 10/100/1000 Ethernet PHY Signed-off-by: Yuiko Oshino Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 472fa4d4ea62..7361cd3fddc1 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -31,6 +31,7 @@ #define PHY_ID_KSZ8081 0x00221560 #define PHY_ID_KSZ8061 0x00221570 #define PHY_ID_KSZ9031 0x00221620 +#define PHY_ID_KSZ9131 0x00221640 #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 -- cgit v1.2.3 From 6fff607e2f14bd7c63c06c464a6f93b8efbabe28 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 19 Oct 2018 19:56:49 -0700 Subject: bpf: sk_msg program helper bpf_msg_push_data This allows user to push data into a msg using sk_msg program types. The format is as follows, bpf_msg_push_data(msg, offset, len, flags) this will insert 'len' bytes at offset 'offset'. For example to prepend 10 bytes at the front of the message the user can, bpf_msg_push_data(msg, 0, 10, 0); This will invalidate data bounds so BPF user will have to then recheck data bounds after calling this. After this the msg size will have been updated and the user is free to write into the added bytes. We allow any offset/len as long as it is within the (data, data_end) range. However, a copy will be required if the ring is full and its possible for the helper to fail with ENOMEM or EINVAL errors which need to be handled by the BPF program. This can be used similar to XDP metadata to pass data between sk_msg layer and lower layers. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 84e18863f6a4..2a11e9d91dfa 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -207,6 +207,11 @@ static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) return &msg->sg.data[which]; } +static inline struct scatterlist sk_msg_elem_cpy(struct sk_msg *msg, int which) +{ + return msg->sg.data[which]; +} + static inline struct page *sk_msg_page(struct sk_msg *msg, int which) { return sg_page(sk_msg_elem(msg, which)); -- cgit v1.2.3 From b2c3fa546705944e748666b474ffdaebaec0569f Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Sat, 20 Oct 2018 14:56:11 -0400 Subject: blkcg: fix edge case for blk_get_rl() under memory pressure It is possible for blkg creation to fail when in blk_get_rl(). In this situation, the fallback logic returns the nearest created blkg. There is however special handling for the request_list for the root blkcg. This fixes the missing edge case from the earlier series changing blk_get_rl(). Fixes: e2b0989954ae ("blkcg: cleanup and make blk_get_rl use blkg_lookup_create") Signed-off-by: Dennis Zhou Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index b7fd08013de2..1e76ceebeb5d 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -597,7 +597,7 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, if (unlikely(!blkg)) blkg = __blkg_lookup_create(blkcg, q); - if (!blkg_tryget(blkg)) + if (blkg->blkcg == &blkcg_root || !blkg_tryget(blkg)) goto rl_use_root; rcu_read_unlock(); -- cgit v1.2.3 From d459d853c2edc793135e4bfa4e345c758f1cc859 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Sat, 20 Oct 2018 14:56:12 -0400 Subject: blkcg: reassociate bios when make_request() is called recursively When submitting a bio, multiple recursive calls to make_request() may occur. This causes the initial associate done in blkcg_bio_issue_check() to be incorrect and reference the prior request_queue. This introduces a helper to do reassociation when make_request() is recursively called. Fixes: a7b39b4e961c ("blkcg: always associate a bio with a blkg") Reported-by: Valdis Kletnieks Signed-off-by: Dennis Zhou Tested-by: Valdis Kletnieks Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index f447b0ebb288..b47c7f716731 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -514,6 +514,7 @@ int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); int bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); +int bio_reassociate_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ @@ -522,6 +523,8 @@ static inline int bio_associate_blkg_from_css(struct bio *bio, { return 0; } static inline int bio_associate_create_blkg(struct request_queue *q, struct bio *bio) { return 0; } +static inline int bio_reassociate_blkg(struct request_queue *q, struct bio *bio) +{ return 0; } static inline void bio_disassociate_task(struct bio *bio) { } static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } -- cgit v1.2.3 From f8d5d0cc145cc21bfc56ef807dc28102aebbf228 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 7 Nov 2017 16:30:10 -0500 Subject: xarray: Add definition of struct xarray This is a direct replacement for struct radix_tree_root. Some of the struct members have changed name; convert those, and use a #define so that radix_tree users continue to work without change. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 28 ++++++------------- include/linux/xarray.h | 70 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 78 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 60f3d8eb2cb7..0b080bd88ab7 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -30,6 +30,9 @@ #include #include +/* Keep unconverted code working */ +#define radix_tree_root xarray + /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: @@ -92,36 +95,21 @@ struct radix_tree_node { unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -/* The IDR tag is stored in the low bits of the GFP flags */ +/* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) -/* The top bits of gfp_mask are used to store the root tags */ +/* The top bits of xa_flags are used to store the root tags */ #define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT) -struct radix_tree_root { - spinlock_t xa_lock; - gfp_t gfp_mask; - struct radix_tree_node __rcu *rnode; -}; - -#define RADIX_TREE_INIT(name, mask) { \ - .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ - .gfp_mask = (mask), \ - .rnode = NULL, \ -} +#define RADIX_TREE_INIT(name, mask) XARRAY_INIT(name, mask) #define RADIX_TREE(name, mask) \ struct radix_tree_root name = RADIX_TREE_INIT(name, mask) -#define INIT_RADIX_TREE(root, mask) \ -do { \ - spin_lock_init(&(root)->xa_lock); \ - (root)->gfp_mask = (mask); \ - (root)->rnode = NULL; \ -} while (0) +#define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask) static inline bool radix_tree_empty(const struct radix_tree_root *root) { - return root->rnode == NULL; + return root->xa_head == NULL; } /** diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 4d1cd7a083e8..9122cf8bf52a 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -10,6 +10,8 @@ */ #include +#include +#include #include #include @@ -153,6 +155,74 @@ static inline bool xa_is_internal(const void *entry) return ((unsigned long)entry & 3) == 2; } +/** + * struct xarray - The anchor of the XArray. + * @xa_lock: Lock that protects the contents of the XArray. + * + * To use the xarray, define it statically or embed it in your data structure. + * It is a very small data structure, so it does not usually make sense to + * allocate it separately and keep a pointer to it in your data structure. + * + * You may use the xa_lock to protect your own data structures as well. + */ +/* + * If all of the entries in the array are NULL, @xa_head is a NULL pointer. + * If the only non-NULL entry in the array is at index 0, @xa_head is that + * entry. If any other entry in the array is non-NULL, @xa_head points + * to an @xa_node. + */ +struct xarray { + spinlock_t xa_lock; +/* private: The rest of the data structure is not to be used directly. */ + gfp_t xa_flags; + void __rcu * xa_head; +}; + +#define XARRAY_INIT(name, flags) { \ + .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ + .xa_flags = flags, \ + .xa_head = NULL, \ +} + +/** + * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags. + * @name: A string that names your XArray. + * @flags: XA_FLAG values. + * + * This is intended for file scope definitions of XArrays. It declares + * and initialises an empty XArray with the chosen name and flags. It is + * equivalent to calling xa_init_flags() on the array, but it does the + * initialisation at compiletime instead of runtime. + */ +#define DEFINE_XARRAY_FLAGS(name, flags) \ + struct xarray name = XARRAY_INIT(name, flags) + +/** + * DEFINE_XARRAY() - Define an XArray. + * @name: A string that names your XArray. + * + * This is intended for file scope definitions of XArrays. It declares + * and initialises an empty XArray with the chosen name. It is equivalent + * to calling xa_init() on the array, but it does the initialisation at + * compiletime instead of runtime. + */ +#define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) + +void xa_init_flags(struct xarray *, gfp_t flags); + +/** + * xa_init() - Initialise an empty XArray. + * @xa: XArray. + * + * An empty XArray is full of NULL entries. + * + * Context: Any context. + */ +static inline void xa_init(struct xarray *xa) +{ + xa_init_flags(xa, 0); +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) -- cgit v1.2.3 From 01959dfe771c6893365482ec78dc1d9cbbbe6de8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 9 Nov 2017 09:23:56 -0500 Subject: xarray: Define struct xa_node This is a direct replacement for struct radix_tree_node. A couple of struct members have changed name, so convert those. Use a #define so that radix tree users continue to work without change. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 29 +++-------------------------- include/linux/xarray.h | 27 +++++++++++++++++++++++++++ 2 files changed, 30 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 0b080bd88ab7..15388b7e38b9 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -32,6 +32,7 @@ /* Keep unconverted code working */ #define radix_tree_root xarray +#define radix_tree_node xa_node /* * The bottom two bits of the slot determine how the remaining bits in the @@ -60,41 +61,17 @@ static inline bool radix_tree_is_internal_node(void *ptr) /*** radix-tree API starts here ***/ -#define RADIX_TREE_MAX_TAGS 3 - #define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) -#define RADIX_TREE_TAG_LONGS \ - ((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG) +#define RADIX_TREE_MAX_TAGS XA_MAX_MARKS +#define RADIX_TREE_TAG_LONGS XA_MARK_LONGS #define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) -/* - * @count is the count of every non-NULL element in the ->slots array - * whether that is a value entry, a retry entry, a user pointer, - * a sibling entry or a pointer to the next level of the tree. - * @exceptional is the count of every element in ->slots which is - * either a value entry or a sibling of a value entry. - */ -struct radix_tree_node { - unsigned char shift; /* Bits remaining in each slot */ - unsigned char offset; /* Slot offset in parent */ - unsigned char count; /* Total entry count */ - unsigned char exceptional; /* Exceptional entry count */ - struct radix_tree_node *parent; /* Used when ascending tree */ - struct radix_tree_root *root; /* The tree we belong to */ - union { - struct list_head private_list; /* For tree user */ - struct rcu_head rcu_head; /* Used when freeing node */ - }; - void __rcu *slots[RADIX_TREE_MAP_SIZE]; - unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; -}; - /* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) /* The top bits of xa_flags are used to store the root tags */ diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 9122cf8bf52a..52141dfc5a90 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -252,6 +252,33 @@ static inline void xa_init(struct xarray *xa) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) +#define XA_MAX_MARKS 3 +#define XA_MARK_LONGS DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG) + +/* + * @count is the count of every non-NULL element in the ->slots array + * whether that is a value entry, a retry entry, a user pointer, + * a sibling entry or a pointer to the next level of the tree. + * @nr_values is the count of every element in ->slots which is + * either a value entry or a sibling of a value entry. + */ +struct xa_node { + unsigned char shift; /* Bits remaining in each slot */ + unsigned char offset; /* Slot offset in parent */ + unsigned char count; /* Total entry count */ + unsigned char nr_values; /* Value entry count */ + struct xa_node __rcu *parent; /* NULL at top of tree */ + struct xarray *array; /* The array we belong to */ + union { + struct list_head private_list; /* For tree user */ + struct rcu_head rcu_head; /* Used when freeing node */ + }; + void __rcu *slots[XA_CHUNK_SIZE]; + union { + unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; + unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; + }; +}; /* Private */ static inline bool xa_is_node(const void *entry) -- cgit v1.2.3 From ad3d6c7263e368abdc151e1cc13dc78aa39cc7a7 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 7 Nov 2017 14:57:46 -0500 Subject: xarray: Add XArray load operation The xa_load function brings with it a lot of infrastructure; xa_empty(), xa_is_err(), and large chunks of the XArray advanced API that are used to implement xa_load. As the test-suite demonstrates, it is possible to use the XArray functions on a radix tree. The radix tree functions depend on the GFP flags being stored in the root of the tree, so it's not possible to use the radix tree functions on an XArray. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 336 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 336 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 52141dfc5a90..a0df8217068c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include #include @@ -30,6 +32,10 @@ * * 0-62: Sibling entries * 256: Retry entry + * + * Errors are also represented as internal entries, but use the negative + * space (-4094 to -2). They're never stored in the slots array; only + * returned by the normal API. */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) @@ -155,6 +161,42 @@ static inline bool xa_is_internal(const void *entry) return ((unsigned long)entry & 3) == 2; } +/** + * xa_is_err() - Report whether an XArray operation returned an error + * @entry: Result from calling an XArray function + * + * If an XArray operation cannot complete an operation, it will return + * a special value indicating an error. This function tells you + * whether an error occurred; xa_err() tells you which error occurred. + * + * Context: Any context. + * Return: %true if the entry indicates an error. + */ +static inline bool xa_is_err(const void *entry) +{ + return unlikely(xa_is_internal(entry)); +} + +/** + * xa_err() - Turn an XArray result into an errno. + * @entry: Result from calling an XArray function. + * + * If an XArray operation cannot complete an operation, it will return + * a special pointer value which encodes an errno. This function extracts + * the errno from the pointer value, or returns 0 if the pointer does not + * represent an errno. + * + * Context: Any context. + * Return: A negative errno or 0. + */ +static inline int xa_err(void *entry) +{ + /* xa_to_internal() would not do sign extension. */ + if (xa_is_err(entry)) + return (long)entry >> 2; + return 0; +} + /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. @@ -209,6 +251,7 @@ struct xarray { #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) void xa_init_flags(struct xarray *, gfp_t flags); +void *xa_load(struct xarray *, unsigned long index); /** * xa_init() - Initialise an empty XArray. @@ -223,6 +266,18 @@ static inline void xa_init(struct xarray *xa) xa_init_flags(xa, 0); } +/** + * xa_empty() - Determine if an array has any present entries. + * @xa: XArray. + * + * Context: Any context. + * Return: %true if the array contains only NULL pointers. + */ +static inline bool xa_empty(const struct xarray *xa) +{ + return xa->xa_head == NULL; +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -280,6 +335,65 @@ struct xa_node { }; }; +void xa_dump(const struct xarray *); +void xa_dump_node(const struct xa_node *); + +#ifdef XA_DEBUG +#define XA_BUG_ON(xa, x) do { \ + if (x) { \ + xa_dump(xa); \ + BUG(); \ + } \ + } while (0) +#define XA_NODE_BUG_ON(node, x) do { \ + if (x) { \ + if (node) xa_dump_node(node); \ + BUG(); \ + } \ + } while (0) +#else +#define XA_BUG_ON(xa, x) do { } while (0) +#define XA_NODE_BUG_ON(node, x) do { } while (0) +#endif + +/* Private */ +static inline void *xa_head(const struct xarray *xa) +{ + return rcu_dereference_check(xa->xa_head, + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline void *xa_head_locked(const struct xarray *xa) +{ + return rcu_dereference_protected(xa->xa_head, + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline void *xa_entry(const struct xarray *xa, + const struct xa_node *node, unsigned int offset) +{ + XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); + return rcu_dereference_check(node->slots[offset], + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline void *xa_entry_locked(const struct xarray *xa, + const struct xa_node *node, unsigned int offset) +{ + XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); + return rcu_dereference_protected(node->slots[offset], + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline struct xa_node *xa_to_node(const void *entry) +{ + return (struct xa_node *)((unsigned long)entry - 2); +} + /* Private */ static inline bool xa_is_node(const void *entry) { @@ -312,4 +426,226 @@ static inline bool xa_is_sibling(const void *entry) #define XA_RETRY_ENTRY xa_mk_internal(256) +/** + * xa_is_retry() - Is the entry a retry entry? + * @entry: Entry retrieved from the XArray + * + * Return: %true if the entry is a retry entry. + */ +static inline bool xa_is_retry(const void *entry) +{ + return unlikely(entry == XA_RETRY_ENTRY); +} + +/** + * typedef xa_update_node_t - A callback function from the XArray. + * @node: The node which is being processed + * + * This function is called every time the XArray updates the count of + * present and value entries in a node. It allows advanced users to + * maintain the private_list in the node. + * + * Context: The xa_lock is held and interrupts may be disabled. + * Implementations should not drop the xa_lock, nor re-enable + * interrupts. + */ +typedef void (*xa_update_node_t)(struct xa_node *node); + +/* + * The xa_state is opaque to its users. It contains various different pieces + * of state involved in the current operation on the XArray. It should be + * declared on the stack and passed between the various internal routines. + * The various elements in it should not be accessed directly, but only + * through the provided accessor functions. The below documentation is for + * the benefit of those working on the code, not for users of the XArray. + * + * @xa_node usually points to the xa_node containing the slot we're operating + * on (and @xa_offset is the offset in the slots array). If there is a + * single entry in the array at index 0, there are no allocated xa_nodes to + * point to, and so we store %NULL in @xa_node. @xa_node is set to + * the value %XAS_RESTART if the xa_state is not walked to the correct + * position in the tree of nodes for this operation. If an error occurs + * during an operation, it is set to an %XAS_ERROR value. If we run off the + * end of the allocated nodes, it is set to %XAS_BOUNDS. + */ +struct xa_state { + struct xarray *xa; + unsigned long xa_index; + unsigned char xa_shift; + unsigned char xa_sibs; + unsigned char xa_offset; + unsigned char xa_pad; /* Helps gcc generate better code */ + struct xa_node *xa_node; + struct xa_node *xa_alloc; + xa_update_node_t xa_update; +}; + +/* + * We encode errnos in the xas->xa_node. If an error has happened, we need to + * drop the lock to fix it, and once we've done so the xa_state is invalid. + */ +#define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL)) +#define XAS_BOUNDS ((struct xa_node *)1UL) +#define XAS_RESTART ((struct xa_node *)3UL) + +#define __XA_STATE(array, index, shift, sibs) { \ + .xa = array, \ + .xa_index = index, \ + .xa_shift = shift, \ + .xa_sibs = sibs, \ + .xa_offset = 0, \ + .xa_pad = 0, \ + .xa_node = XAS_RESTART, \ + .xa_alloc = NULL, \ + .xa_update = NULL \ +} + +/** + * XA_STATE() - Declare an XArray operation state. + * @name: Name of this operation state (usually xas). + * @array: Array to operate on. + * @index: Initial index of interest. + * + * Declare and initialise an xa_state on the stack. + */ +#define XA_STATE(name, array, index) \ + struct xa_state name = __XA_STATE(array, index, 0, 0) + +/** + * XA_STATE_ORDER() - Declare an XArray operation state. + * @name: Name of this operation state (usually xas). + * @array: Array to operate on. + * @index: Initial index of interest. + * @order: Order of entry. + * + * Declare and initialise an xa_state on the stack. This variant of + * XA_STATE() allows you to specify the 'order' of the element you + * want to operate on.` + */ +#define XA_STATE_ORDER(name, array, index, order) \ + struct xa_state name = __XA_STATE(array, \ + (index >> order) << order, \ + order - (order % XA_CHUNK_SHIFT), \ + (1U << (order % XA_CHUNK_SHIFT)) - 1) + +#define xas_marked(xas, mark) xa_marked((xas)->xa, (mark)) +#define xas_trylock(xas) xa_trylock((xas)->xa) +#define xas_lock(xas) xa_lock((xas)->xa) +#define xas_unlock(xas) xa_unlock((xas)->xa) +#define xas_lock_bh(xas) xa_lock_bh((xas)->xa) +#define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa) +#define xas_lock_irq(xas) xa_lock_irq((xas)->xa) +#define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa) +#define xas_lock_irqsave(xas, flags) \ + xa_lock_irqsave((xas)->xa, flags) +#define xas_unlock_irqrestore(xas, flags) \ + xa_unlock_irqrestore((xas)->xa, flags) + +/** + * xas_error() - Return an errno stored in the xa_state. + * @xas: XArray operation state. + * + * Return: 0 if no error has been noted. A negative errno if one has. + */ +static inline int xas_error(const struct xa_state *xas) +{ + return xa_err(xas->xa_node); +} + +/** + * xas_set_err() - Note an error in the xa_state. + * @xas: XArray operation state. + * @err: Negative error number. + * + * Only call this function with a negative @err; zero or positive errors + * will probably not behave the way you think they should. If you want + * to clear the error from an xa_state, use xas_reset(). + */ +static inline void xas_set_err(struct xa_state *xas, long err) +{ + xas->xa_node = XA_ERROR(err); +} + +/** + * xas_invalid() - Is the xas in a retry or error state? + * @xas: XArray operation state. + * + * Return: %true if the xas cannot be used for operations. + */ +static inline bool xas_invalid(const struct xa_state *xas) +{ + return (unsigned long)xas->xa_node & 3; +} + +/** + * xas_valid() - Is the xas a valid cursor into the array? + * @xas: XArray operation state. + * + * Return: %true if the xas can be used for operations. + */ +static inline bool xas_valid(const struct xa_state *xas) +{ + return !xas_invalid(xas); +} + +/** + * xas_reset() - Reset an XArray operation state. + * @xas: XArray operation state. + * + * Resets the error or walk state of the @xas so future walks of the + * array will start from the root. Use this if you have dropped the + * xarray lock and want to reuse the xa_state. + * + * Context: Any context. + */ +static inline void xas_reset(struct xa_state *xas) +{ + xas->xa_node = XAS_RESTART; +} + +/** + * xas_retry() - Retry the operation if appropriate. + * @xas: XArray operation state. + * @entry: Entry from xarray. + * + * The advanced functions may sometimes return an internal entry, such as + * a retry entry or a zero entry. This function sets up the @xas to restart + * the walk from the head of the array if needed. + * + * Context: Any context. + * Return: true if the operation needs to be retried. + */ +static inline bool xas_retry(struct xa_state *xas, const void *entry) +{ + if (!xa_is_retry(entry)) + return false; + xas_reset(xas); + return true; +} + +void *xas_load(struct xa_state *); + +/** + * xas_reload() - Refetch an entry from the xarray. + * @xas: XArray operation state. + * + * Use this function to check that a previously loaded entry still has + * the same value. This is useful for the lockless pagecache lookup where + * we walk the array with only the RCU lock to protect us, lock the page, + * then check that the page hasn't moved since we looked it up. + * + * The caller guarantees that @xas is still valid. If it may be in an + * error or restart state, call xas_load() instead. + * + * Return: The entry at this location in the xarray. + */ +static inline void *xas_reload(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + + if (node) + return xa_entry(xas->xa, node, xas->xa_offset); + return xa_head(xas->xa); +} + #endif /* _LINUX_XARRAY_H */ -- cgit v1.2.3 From 9b89a0355144685a787b0dc5bcf7bdd6f2d02968 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 10 Nov 2017 09:34:31 -0500 Subject: xarray: Add XArray marks XArray marks are like the radix tree tags, only slightly more strongly typed. They are renamed in order to distinguish them from tagged pointers. This commit adds the basic get/set/clear operations. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index a0df8217068c..2de504ae9ba4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -197,6 +198,20 @@ static inline int xa_err(void *entry) return 0; } +typedef unsigned __bitwise xa_mark_t; +#define XA_MARK_0 ((__force xa_mark_t)0U) +#define XA_MARK_1 ((__force xa_mark_t)1U) +#define XA_MARK_2 ((__force xa_mark_t)2U) +#define XA_PRESENT ((__force xa_mark_t)8U) +#define XA_MARK_MAX XA_MARK_2 + +/* + * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, + * and we remain compatible with that. + */ +#define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ + (__force unsigned)(mark))) + /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. @@ -252,6 +267,9 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); +bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); +void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); +void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); /** * xa_init() - Initialise an empty XArray. @@ -278,6 +296,19 @@ static inline bool xa_empty(const struct xarray *xa) return xa->xa_head == NULL; } +/** + * xa_marked() - Inquire whether any entry in this array has a mark set + * @xa: Array + * @mark: Mark value + * + * Context: Any context. + * Return: %true if any entry has this mark set. + */ +static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) +{ + return xa->xa_flags & XA_FLAGS_MARK(mark); +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -290,6 +321,12 @@ static inline bool xa_empty(const struct xarray *xa) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) +/* + * Versions of the normal API which require the caller to hold the xa_lock. + */ +void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); +void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); + /* Everything below here is the Advanced API. Proceed with caution. */ /* @@ -388,6 +425,22 @@ static inline void *xa_entry_locked(const struct xarray *xa, lockdep_is_held(&xa->xa_lock)); } +/* Private */ +static inline struct xa_node *xa_parent(const struct xarray *xa, + const struct xa_node *node) +{ + return rcu_dereference_check(node->parent, + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline struct xa_node *xa_parent_locked(const struct xarray *xa, + const struct xa_node *node) +{ + return rcu_dereference_protected(node->parent, + lockdep_is_held(&xa->xa_lock)); +} + /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { @@ -588,6 +641,12 @@ static inline bool xas_valid(const struct xa_state *xas) return !xas_invalid(xas); } +/* True if the pointer is something other than a node */ +static inline bool xas_not_node(struct xa_node *node) +{ + return ((unsigned long)node & 3) || !node; +} + /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. @@ -625,6 +684,10 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) void *xas_load(struct xa_state *); +bool xas_get_mark(const struct xa_state *, xa_mark_t); +void xas_set_mark(const struct xa_state *, xa_mark_t); +void xas_clear_mark(const struct xa_state *, xa_mark_t); + /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. -- cgit v1.2.3 From 58d6ea3085f2e53714810a513c61629f6d2be0a6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 10 Nov 2017 15:15:08 -0500 Subject: xarray: Add XArray unconditional store operations xa_store() differs from radix_tree_insert() in that it will overwrite an existing element in the array rather than returning an error. This is the behaviour which most users want, and those that want more complex behaviour generally want to use the xas family of routines anyway. For memory allocation, xa_store() will first attempt to request memory from the slab allocator; if memory is not immediately available, it will drop the xa_lock and allocate memory, keeping a pointer in the xa_state. It does not use the per-CPU cache, although those will continue to exist until all radix tree users are converted to the xarray. This patch also includes xa_erase() and __xa_erase() for a streamlined way to store NULL. Since there is no need to allocate memory in order to store a NULL in the XArray, we do not need to trouble the user with deciding what memory allocation flags to use. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 147 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 145 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 2de504ae9ba4..15eab63286ed 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -205,10 +205,17 @@ typedef unsigned __bitwise xa_mark_t; #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 +enum xa_lock_type { + XA_LOCK_IRQ = 1, + XA_LOCK_BH = 2, +}; + /* * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, * and we remain compatible with that. */ +#define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) +#define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) @@ -267,6 +274,7 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); +void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -309,6 +317,23 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) return xa->xa_flags & XA_FLAGS_MARK(mark); } +/** + * xa_erase() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index of entry. + * + * This function is the equivalent of calling xa_store() with %NULL as + * the third argument. The XArray does not need to allocate memory, so + * the user does not need to provide GFP flags. + * + * Context: Process context. Takes and releases the xa_lock. + * Return: The entry which used to be at this index. + */ +static inline void *xa_erase(struct xarray *xa, unsigned long index) +{ + return xa_store(xa, index, NULL, 0); +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -322,11 +347,65 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) spin_unlock_irqrestore(&(xa)->xa_lock, flags) /* - * Versions of the normal API which require the caller to hold the xa_lock. - */ + * Versions of the normal API which require the caller to hold the + * xa_lock. If the GFP flags allow it, they will drop the lock to + * allocate memory, then reacquire it afterwards. These functions + * may also re-enable interrupts if the XArray flags indicate the + * locking should be interrupt safe. + */ +void *__xa_erase(struct xarray *, unsigned long index); +void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); +/** + * xa_erase_bh() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index of entry. + * + * This function is the equivalent of calling xa_store() with %NULL as + * the third argument. The XArray does not need to allocate memory, so + * the user does not need to provide GFP flags. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling softirqs. + * Return: The entry which used to be at this index. + */ +static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) +{ + void *entry; + + xa_lock_bh(xa); + entry = __xa_erase(xa, index); + xa_unlock_bh(xa); + + return entry; +} + +/** + * xa_erase_irq() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index of entry. + * + * This function is the equivalent of calling xa_store() with %NULL as + * the third argument. The XArray does not need to allocate memory, so + * the user does not need to provide GFP flags. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. + * Return: The entry which used to be at this index. + */ +static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) +{ + void *entry; + + xa_lock_irq(xa); + entry = __xa_erase(xa, index); + xa_unlock_irq(xa); + + return entry; +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* @@ -441,6 +520,12 @@ static inline struct xa_node *xa_parent_locked(const struct xarray *xa, lockdep_is_held(&xa->xa_lock)); } +/* Private */ +static inline void *xa_mk_node(const struct xa_node *node) +{ + return (void *)((unsigned long)node | 2); +} + /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { @@ -647,6 +732,12 @@ static inline bool xas_not_node(struct xa_node *node) return ((unsigned long)node & 3) || !node; } +/* True if the node represents head-of-tree, RESTART or BOUNDS */ +static inline bool xas_top(struct xa_node *node) +{ + return node <= XAS_RESTART; +} + /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. @@ -683,10 +774,14 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) } void *xas_load(struct xa_state *); +void *xas_store(struct xa_state *, void *entry); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); +void xas_init_marks(const struct xa_state *); + +bool xas_nomem(struct xa_state *, gfp_t); /** * xas_reload() - Refetch an entry from the xarray. @@ -711,4 +806,52 @@ static inline void *xas_reload(struct xa_state *xas) return xa_head(xas->xa); } +/** + * xas_set() - Set up XArray operation state for a different index. + * @xas: XArray operation state. + * @index: New index into the XArray. + * + * Move the operation state to refer to a different index. This will + * have the effect of starting a walk from the top; see xas_next() + * to move to an adjacent index. + */ +static inline void xas_set(struct xa_state *xas, unsigned long index) +{ + xas->xa_index = index; + xas->xa_node = XAS_RESTART; +} + +/** + * xas_set_order() - Set up XArray operation state for a multislot entry. + * @xas: XArray operation state. + * @index: Target of the operation. + * @order: Entry occupies 2^@order indices. + */ +static inline void xas_set_order(struct xa_state *xas, unsigned long index, + unsigned int order) +{ +#ifdef CONFIG_XARRAY_MULTI + xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0; + xas->xa_shift = order - (order % XA_CHUNK_SHIFT); + xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; + xas->xa_node = XAS_RESTART; +#else + BUG_ON(order > 0); + xas_set(xas, index); +#endif +} + +/** + * xas_set_update() - Set up XArray operation state for a callback. + * @xas: XArray operation state. + * @update: Function to call when updating a node. + * + * The XArray can notify a caller after it has updated an xa_node. + * This is advanced functionality and is only needed by the page cache. + */ +static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) +{ + xas->xa_update = update; +} + #endif /* _LINUX_XARRAY_H */ -- cgit v1.2.3 From 41aec91f55985e7f14ee75fe2f6e7bcfff0d0fae Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 10 Nov 2017 15:34:55 -0500 Subject: xarray: Add XArray conditional store operations Like cmpxchg(), xa_cmpxchg will only store to the index if the current entry matches the old entry. It returns the current entry, which is usually more useful than the errno returned by radix_tree_insert(). For the users who really only want the errno, the xa_insert() wrapper provides a more convenient calling convention. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 15eab63286ed..7f740f675b96 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -275,6 +275,8 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); +void *xa_cmpxchg(struct xarray *, unsigned long index, + void *old, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -334,6 +336,34 @@ static inline void *xa_erase(struct xarray *xa, unsigned long index) return xa_store(xa, index, NULL, 0); } +/** + * xa_insert() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * If you would rather see the existing entry in the array, use xa_cmpxchg(). + * This function is for users who don't care what the entry is, only that + * one is present. + * + * Context: Process context. Takes and releases the xa_lock. + * May sleep if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int xa_insert(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp); + if (!curr) + return 0; + if (xa_is_err(curr)) + return xa_err(curr); + return -EEXIST; +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -355,9 +385,39 @@ static inline void *xa_erase(struct xarray *xa, unsigned long index) */ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); +void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, + void *entry, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); +/** + * __xa_insert() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * If you would rather see the existing entry in the array, use __xa_cmpxchg(). + * This function is for users who don't care what the entry is, only that + * one is present. + * + * Context: Any context. Expects xa_lock to be held on entry. May + * release and reacquire xa_lock if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int __xa_insert(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr = __xa_cmpxchg(xa, index, NULL, entry, gfp); + if (!curr) + return 0; + if (xa_is_err(curr)) + return xa_err(curr); + return -EEXIST; +} + /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. -- cgit v1.2.3 From b803b42823d0d9e8b6deccf01ffc2aba5d0738df Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 14 Nov 2017 08:30:11 -0500 Subject: xarray: Add XArray iterators The xa_for_each iterator allows the user to efficiently walk a range of the array, executing the loop body once for each entry in that range that matches the filter. This commit also includes xa_find() and xa_find_after() which are helper functions for xa_for_each() but may also be useful in their own right. In the xas family of functions, we have xas_for_each(), xas_find(), xas_next_entry(), xas_for_each_tagged(), xas_find_tagged(), xas_next_tagged() and xas_pause(). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 165 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 165 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 7f740f675b96..66b10efa5a50 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -280,6 +280,10 @@ void *xa_cmpxchg(struct xarray *, unsigned long index, bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); +void *xa_find(struct xarray *xa, unsigned long *index, + unsigned long max, xa_mark_t) __attribute__((nonnull(2))); +void *xa_find_after(struct xarray *xa, unsigned long *index, + unsigned long max, xa_mark_t) __attribute__((nonnull(2))); /** * xa_init() - Initialise an empty XArray. @@ -364,6 +368,35 @@ static inline int xa_insert(struct xarray *xa, unsigned long index, return -EEXIST; } +/** + * xa_for_each() - Iterate over a portion of an XArray. + * @xa: XArray. + * @entry: Entry retrieved from array. + * @index: Index of @entry. + * @max: Maximum index to retrieve from array. + * @filter: Selection criterion. + * + * Initialise @index to the lowest index you want to retrieve from the + * array. During the iteration, @entry will have the value of the entry + * stored in @xa at @index. The iteration will skip all entries in the + * array which do not match @filter. You may modify @index during the + * iteration if you want to skip or reprocess indices. It is safe to modify + * the array during the iteration. At the end of the iteration, @entry will + * be set to NULL and @index will have a value less than or equal to max. + * + * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have + * to handle your own locking with xas_for_each(), and if you have to unlock + * after each iteration, it will also end up being O(n.log(n)). xa_for_each() + * will spin if it hits a retry entry; if you intend to see retry entries, + * you should use the xas_for_each() iterator instead. The xas_for_each() + * iterator will expand into more inline code than xa_for_each(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each(xa, entry, index, max, filter) \ + for (entry = xa_find(xa, &index, max, filter); entry; \ + entry = xa_find_after(xa, &index, max, filter)) + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -835,13 +868,16 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); +void *xas_find(struct xa_state *, unsigned long max); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); +void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); +void xas_pause(struct xa_state *); /** * xas_reload() - Refetch an entry from the xarray. @@ -914,4 +950,133 @@ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) xas->xa_update = update; } +/** + * xas_next_entry() - Advance iterator to next present entry. + * @xas: XArray operation state. + * @max: Highest index to return. + * + * xas_next_entry() is an inline function to optimise xarray traversal for + * speed. It is equivalent to calling xas_find(), and will call xas_find() + * for all the hard cases. + * + * Return: The next present entry after the one currently referred to by @xas. + */ +static inline void *xas_next_entry(struct xa_state *xas, unsigned long max) +{ + struct xa_node *node = xas->xa_node; + void *entry; + + if (unlikely(xas_not_node(node) || node->shift || + xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK))) + return xas_find(xas, max); + + do { + if (unlikely(xas->xa_index >= max)) + return xas_find(xas, max); + if (unlikely(xas->xa_offset == XA_CHUNK_MASK)) + return xas_find(xas, max); + entry = xa_entry(xas->xa, node, xas->xa_offset + 1); + if (unlikely(xa_is_internal(entry))) + return xas_find(xas, max); + xas->xa_offset++; + xas->xa_index++; + } while (!entry); + + return entry; +} + +/* Private */ +static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance, + xa_mark_t mark) +{ + unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark]; + unsigned int offset = xas->xa_offset; + + if (advance) + offset++; + if (XA_CHUNK_SIZE == BITS_PER_LONG) { + if (offset < XA_CHUNK_SIZE) { + unsigned long data = *addr & (~0UL << offset); + if (data) + return __ffs(data); + } + return XA_CHUNK_SIZE; + } + + return find_next_bit(addr, XA_CHUNK_SIZE, offset); +} + +/** + * xas_next_marked() - Advance iterator to next marked entry. + * @xas: XArray operation state. + * @max: Highest index to return. + * @mark: Mark to search for. + * + * xas_next_marked() is an inline function to optimise xarray traversal for + * speed. It is equivalent to calling xas_find_marked(), and will call + * xas_find_marked() for all the hard cases. + * + * Return: The next marked entry after the one currently referred to by @xas. + */ +static inline void *xas_next_marked(struct xa_state *xas, unsigned long max, + xa_mark_t mark) +{ + struct xa_node *node = xas->xa_node; + unsigned int offset; + + if (unlikely(xas_not_node(node) || node->shift)) + return xas_find_marked(xas, max, mark); + offset = xas_find_chunk(xas, true, mark); + xas->xa_offset = offset; + xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset; + if (xas->xa_index > max) + return NULL; + if (offset == XA_CHUNK_SIZE) + return xas_find_marked(xas, max, mark); + return xa_entry(xas->xa, node, offset); +} + +/* + * If iterating while holding a lock, drop the lock and reschedule + * every %XA_CHECK_SCHED loops. + */ +enum { + XA_CHECK_SCHED = 4096, +}; + +/** + * xas_for_each() - Iterate over a range of an XArray. + * @xas: XArray operation state. + * @entry: Entry retrieved from the array. + * @max: Maximum index to retrieve from array. + * + * The loop body will be executed for each entry present in the xarray + * between the current xas position and @max. @entry will be set to + * the entry retrieved from the xarray. It is safe to delete entries + * from the array in the loop body. You should hold either the RCU lock + * or the xa_lock while iterating. If you need to drop the lock, call + * xas_pause() first. + */ +#define xas_for_each(xas, entry, max) \ + for (entry = xas_find(xas, max); entry; \ + entry = xas_next_entry(xas, max)) + +/** + * xas_for_each_marked() - Iterate over a range of an XArray. + * @xas: XArray operation state. + * @entry: Entry retrieved from the array. + * @max: Maximum index to retrieve from array. + * @mark: Mark to search for. + * + * The loop body will be executed for each marked entry in the xarray + * between the current xas position and @max. @entry will be set to + * the entry retrieved from the xarray. It is safe to delete entries + * from the array in the loop body. You should hold either the RCU lock + * or the xa_lock while iterating. If you need to drop the lock, call + * xas_pause() first. + */ +#define xas_for_each_marked(xas, entry, max, mark) \ + for (entry = xas_find_marked(xas, max, mark); entry; \ + entry = xas_next_marked(xas, max, mark)) + #endif /* _LINUX_XARRAY_H */ -- cgit v1.2.3 From 80a0a1a9a3cde9b23851e8eb7160e2786549306a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 14 Nov 2017 16:42:22 -0500 Subject: xarray: Extract entries from an XArray The xa_extract function combines the functionality of radix_tree_gang_lookup() and radix_tree_gang_lookup_tagged(). It extracts entries matching the specified filter into a normal array. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 66b10efa5a50..82ceed981924 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -284,6 +284,8 @@ void *xa_find(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); +unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, + unsigned long max, unsigned int n, xa_mark_t); /** * xa_init() - Initialise an empty XArray. -- cgit v1.2.3 From 687149fca1f37c447e5d161e0a4a04cb2c880cb6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 17 Nov 2017 08:16:34 -0500 Subject: xarray: Destroy an XArray This function frees all the internal memory allocated to the xarray and reinitialises it to be empty. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 82ceed981924..0a758fa3ed2c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -286,6 +286,7 @@ void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); +void xa_destroy(struct xarray *); /** * xa_init() - Initialise an empty XArray. -- cgit v1.2.3 From 64d3e9a9e0cc51957d243dd2b0adc5d74ff5e128 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 1 Dec 2017 00:06:52 -0500 Subject: xarray: Step through an XArray The xas_next and xas_prev functions move the xas index by one position, and adjust the rest of the iterator state to match it. This is more efficient than calling xas_set() as it keeps the iterator at the leaves of the tree instead of walking the iterator from the root each time. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 0a758fa3ed2c..381f94a66762 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -828,6 +828,12 @@ static inline bool xas_not_node(struct xa_node *node) return ((unsigned long)node & 3) || !node; } +/* True if the node represents RESTART or an error */ +static inline bool xas_frozen(struct xa_node *node) +{ + return (unsigned long)node & 2; +} + /* True if the node represents head-of-tree, RESTART or BOUNDS */ static inline bool xas_top(struct xa_node *node) { @@ -1082,4 +1088,65 @@ enum { for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) +void *__xas_next(struct xa_state *); +void *__xas_prev(struct xa_state *); + +/** + * xas_prev() - Move iterator to previous index. + * @xas: XArray operation state. + * + * If the @xas was in an error state, it will remain in an error state + * and this function will return %NULL. If the @xas has never been walked, + * it will have the effect of calling xas_load(). Otherwise one will be + * subtracted from the index and the state will be walked to the correct + * location in the array for the next operation. + * + * If the iterator was referencing index 0, this function wraps + * around to %ULONG_MAX. + * + * Return: The entry at the new index. This may be %NULL or an internal + * entry. + */ +static inline void *xas_prev(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + + if (unlikely(xas_not_node(node) || node->shift || + xas->xa_offset == 0)) + return __xas_prev(xas); + + xas->xa_index--; + xas->xa_offset--; + return xa_entry(xas->xa, node, xas->xa_offset); +} + +/** + * xas_next() - Move state to next index. + * @xas: XArray operation state. + * + * If the @xas was in an error state, it will remain in an error state + * and this function will return %NULL. If the @xas has never been walked, + * it will have the effect of calling xas_load(). Otherwise one will be + * added to the index and the state will be walked to the correct + * location in the array for the next operation. + * + * If the iterator was referencing index %ULONG_MAX, this function wraps + * around to 0. + * + * Return: The entry at the new index. This may be %NULL or an internal + * entry. + */ +static inline void *xas_next(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + + if (unlikely(xas_not_node(node) || node->shift || + xas->xa_offset == XA_CHUNK_MASK)) + return __xas_next(xas); + + xas->xa_index++; + xas->xa_offset++; + return xa_entry(xas->xa, node, xas->xa_offset); +} + #endif /* _LINUX_XARRAY_H */ -- cgit v1.2.3 From 4e99d4e9579d3b950bf4b38d0d64eb1b9be78761 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 1 Jun 2018 22:46:02 -0400 Subject: xarray: Add xas_for_each_conflict This iterator iterates over each entry that is stored in the index or indices specified by the xa_state. This is intended for use for a conditional store of a multiindex entry, or to allow entries which are about to be removed from the xarray to be disposed of properly. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 381f94a66762..2664e718dbd3 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -878,6 +878,7 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); void *xas_find(struct xa_state *, unsigned long max); +void *xas_find_conflict(struct xa_state *); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); @@ -1088,6 +1089,22 @@ enum { for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) +/** + * xas_for_each_conflict() - Iterate over a range of an XArray. + * @xas: XArray operation state. + * @entry: Entry retrieved from the array. + * + * The loop body will be executed for each entry in the XArray that lies + * within the range specified by @xas. If the loop completes successfully, + * any entries that lie in this range will be replaced by @entry. The caller + * may break out of the loop; if they do so, the contents of the XArray will + * be unchanged. The operation may fail due to an out of memory condition. + * The caller may also call xa_set_err() to exit the loop while setting an + * error to record the reason. + */ +#define xas_for_each_conflict(xas, entry) \ + while ((entry = xas_find_conflict(xas))) + void *__xas_next(struct xa_state *); void *__xas_prev(struct xa_state *); -- cgit v1.2.3 From 2264f5132fe45571139727ebdeb78696b35d1506 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 00:11:48 -0500 Subject: xarray: Add xas_create_range This hopefully temporary function is useful for users who have not yet been converted to multi-index entries. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 2664e718dbd3..deae17aa0ed7 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -822,6 +822,17 @@ static inline bool xas_valid(const struct xa_state *xas) return !xas_invalid(xas); } +/** + * xas_is_node() - Does the xas point to a node? + * @xas: XArray operation state. + * + * Return: %true if the xas currently references a node. + */ +static inline bool xas_is_node(const struct xa_state *xas) +{ + return xas_valid(xas) && xas->xa_node; +} + /* True if the pointer is something other than a node */ static inline bool xas_not_node(struct xa_node *node) { @@ -889,6 +900,8 @@ void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); void xas_pause(struct xa_state *); +void xas_create_range(struct xa_state *); + /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. -- cgit v1.2.3 From 9f14d4f1f1045f161fd4db8a8e194b7825c2874a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 1 Oct 2018 14:54:59 -0400 Subject: xarray: Add xa_reserve and xa_release This function reserves a slot in the XArray for users which need to acquire multiple locks before storing their entry in the tree and so cannot use a plain xa_store(). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 34 ++++++++++++++++++++++++++++++++-- 1 file changed, 32 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index deae17aa0ed7..bed63d3cfea8 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -32,7 +32,8 @@ * The following internal entries have a special meaning: * * 0-62: Sibling entries - * 256: Retry entry + * 256: Zero entry + * 257: Retry entry * * Errors are also represented as internal entries, but use the negative * space (-4094 to -2). They're never stored in the slots array; only @@ -277,6 +278,7 @@ void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); +int xa_reserve(struct xarray *, unsigned long index, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -371,6 +373,20 @@ static inline int xa_insert(struct xarray *xa, unsigned long index, return -EEXIST; } +/** + * xa_release() - Release a reserved entry. + * @xa: XArray. + * @index: Index of entry. + * + * After calling xa_reserve(), you can call this function to release the + * reservation. If the entry at @index has been stored to, this function + * will do nothing. + */ +static inline void xa_release(struct xarray *xa, unsigned long index) +{ + xa_cmpxchg(xa, index, NULL, NULL, 0); +} + /** * xa_for_each() - Iterate over a portion of an XArray. * @xa: XArray. @@ -658,7 +674,19 @@ static inline bool xa_is_sibling(const void *entry) (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } -#define XA_RETRY_ENTRY xa_mk_internal(256) +#define XA_ZERO_ENTRY xa_mk_internal(256) +#define XA_RETRY_ENTRY xa_mk_internal(257) + +/** + * xa_is_zero() - Is the entry a zero entry? + * @entry: Entry retrieved from the XArray + * + * Return: %true if the entry is a zero entry. + */ +static inline bool xa_is_zero(const void *entry) +{ + return unlikely(entry == XA_ZERO_ENTRY); +} /** * xa_is_retry() - Is the entry a retry entry? @@ -880,6 +908,8 @@ static inline void xas_reset(struct xa_state *xas) */ static inline bool xas_retry(struct xa_state *xas, const void *entry) { + if (xa_is_zero(entry)) + return true; if (!xa_is_retry(entry)) return false; xas_reset(xas); -- cgit v1.2.3 From 371c752dc66948714ee3b66c3306f3ff1ff71d2e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jul 2018 10:50:12 -0400 Subject: xarray: Track free entries in an XArray Add the optional ability to track which entries in an XArray are free and provide xa_alloc() to replace most of the functionality of the IDR. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 101 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index bed63d3cfea8..e0b57af52e9b 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -205,6 +205,7 @@ typedef unsigned __bitwise xa_mark_t; #define XA_MARK_2 ((__force xa_mark_t)2U) #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 +#define XA_FREE_MARK XA_MARK_0 enum xa_lock_type { XA_LOCK_IRQ = 1, @@ -217,9 +218,12 @@ enum xa_lock_type { */ #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) +#define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) +#define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) + /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. @@ -273,6 +277,15 @@ struct xarray { */ #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) +/** + * DEFINE_XARRAY_ALLOC() - Define an XArray which can allocate IDs. + * @name: A string that names your XArray. + * + * This is intended for file scope definitions of allocating XArrays. + * See also DEFINE_XARRAY(). + */ +#define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) + void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); @@ -439,6 +452,7 @@ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); +int __xa_alloc(struct xarray *, u32 *id, u32 max, void *entry, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -518,6 +532,93 @@ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) return entry; } +/** + * xa_alloc() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @max: Maximum ID to allocate (inclusive). + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @id and @max. + * Updates the @id pointer with the index, then stores the entry at that + * index. A concurrent lookup will not see an uninitialised @id. + * + * Context: Process context. Takes and releases the xa_lock. May sleep if + * the @gfp flags permit. + * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if + * there is no more space in the XArray. + */ +static inline int xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, + gfp_t gfp) +{ + int err; + + xa_lock(xa); + err = __xa_alloc(xa, id, max, entry, gfp); + xa_unlock(xa); + + return err; +} + +/** + * xa_alloc_bh() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @max: Maximum ID to allocate (inclusive). + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @id and @max. + * Updates the @id pointer with the index, then stores the entry at that + * index. A concurrent lookup will not see an uninitialised @id. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling softirqs. May sleep if the @gfp flags permit. + * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if + * there is no more space in the XArray. + */ +static inline int xa_alloc_bh(struct xarray *xa, u32 *id, u32 max, void *entry, + gfp_t gfp) +{ + int err; + + xa_lock_bh(xa); + err = __xa_alloc(xa, id, max, entry, gfp); + xa_unlock_bh(xa); + + return err; +} + +/** + * xa_alloc_irq() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @max: Maximum ID to allocate (inclusive). + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @id and @max. + * Updates the @id pointer with the index, then stores the entry at that + * index. A concurrent lookup will not see an uninitialised @id. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. May sleep if the @gfp flags permit. + * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if + * there is no more space in the XArray. + */ +static inline int xa_alloc_irq(struct xarray *xa, u32 *id, u32 max, void *entry, + gfp_t gfp) +{ + int err; + + xa_lock_irq(xa); + err = __xa_alloc(xa, id, max, entry, gfp); + xa_unlock_irq(xa); + + return err; +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* -- cgit v1.2.3 From f32f004cddf86d63a9c42994bbce9f4e2f07c9fa Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jul 2018 15:42:46 -0400 Subject: ida: Convert to XArray Use the XA_TRACK_FREE ability to track which entries have a free bit, similarly to how it uses the radix tree's IDR_FREE tag. This eliminates the per-cpu ida_bitmap preload, and fixes the memory consumption regression I introduced when making the IDR able to store any pointer. Signed-off-by: Matthew Wilcox --- include/linux/idr.h | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 3ec8628ce17f..60daf34b625d 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -214,8 +214,7 @@ static inline void idr_preload_end(void) ++id, (entry) = idr_get_next((idr), &(id))) /* - * IDA - IDR based id allocator, use when translation from id to - * pointer isn't necessary. + * IDA - ID Allocator, use when translation from id to pointer isn't necessary. */ #define IDA_CHUNK_SIZE 128 /* 128 bytes per chunk */ #define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long)) @@ -225,14 +224,14 @@ struct ida_bitmap { unsigned long bitmap[IDA_BITMAP_LONGS]; }; -DECLARE_PER_CPU(struct ida_bitmap *, ida_bitmap); - struct ida { - struct radix_tree_root ida_rt; + struct xarray xa; }; +#define IDA_INIT_FLAGS (XA_FLAGS_LOCK_IRQ | XA_FLAGS_ALLOC) + #define IDA_INIT(name) { \ - .ida_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER | GFP_NOWAIT), \ + .xa = XARRAY_INIT(name, IDA_INIT_FLAGS) \ } #define DEFINE_IDA(name) struct ida name = IDA_INIT(name) @@ -292,7 +291,7 @@ static inline int ida_alloc_max(struct ida *ida, unsigned int max, gfp_t gfp) static inline void ida_init(struct ida *ida) { - INIT_RADIX_TREE(&ida->ida_rt, IDR_RT_MARKER | GFP_NOWAIT); + xa_init_flags(&ida->xa, IDA_INIT_FLAGS); } #define ida_simple_get(ida, start, end, gfp) \ @@ -301,9 +300,6 @@ static inline void ida_init(struct ida *ida) static inline bool ida_is_empty(const struct ida *ida) { - return radix_tree_empty(&ida->ida_rt); + return xa_empty(&ida->xa); } - -/* in lib/radix-tree.c */ -int ida_pre_get(struct ida *ida, gfp_t gfp_mask); #endif /* __IDR_H__ */ -- cgit v1.2.3 From eb797a8ee0ab4cd03df556980ce7bf167cadaa50 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 5 Mar 2018 22:46:03 -0500 Subject: page cache: Rearrange address_space Change i_pages from a radix_tree_root to an xarray, convert the documentation into kernel-doc format and change the order of the elements to pack them better on 64-bit systems. Signed-off-by: Matthew Wilcox --- include/linux/fs.h | 46 +++++++++++++++++++++++++++++++--------------- 1 file changed, 31 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c0b4a1c22ff..d126cad0f621 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -403,24 +403,40 @@ int pagecache_write_end(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); +/** + * struct address_space - Contents of a cacheable, mappable object. + * @host: Owner, either the inode or the block_device. + * @i_pages: Cached pages. + * @gfp_mask: Memory allocation flags to use for allocating pages. + * @i_mmap_writable: Number of VM_SHARED mappings. + * @i_mmap: Tree of private and shared mappings. + * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. + * @nrpages: Number of page entries, protected by the i_pages lock. + * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock. + * @writeback_index: Writeback starts here. + * @a_ops: Methods. + * @flags: Error bits and flags (AS_*). + * @wb_err: The most recent error which has occurred. + * @private_lock: For use by the owner of the address_space. + * @private_list: For use by the owner of the address_space. + * @private_data: For use by the owner of the address_space. + */ struct address_space { - struct inode *host; /* owner: inode, block_device */ - struct radix_tree_root i_pages; /* cached pages */ - atomic_t i_mmap_writable;/* count VM_SHARED mappings */ - struct rb_root_cached i_mmap; /* tree of private and shared mappings */ - struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ - /* Protected by the i_pages lock */ - unsigned long nrpages; /* number of total pages */ - /* number of shadow or DAX exceptional entries */ + struct inode *host; + struct xarray i_pages; + gfp_t gfp_mask; + atomic_t i_mmap_writable; + struct rb_root_cached i_mmap; + struct rw_semaphore i_mmap_rwsem; + unsigned long nrpages; unsigned long nrexceptional; - pgoff_t writeback_index;/* writeback starts here */ - const struct address_space_operations *a_ops; /* methods */ - unsigned long flags; /* error bits */ - spinlock_t private_lock; /* for use by the address_space */ - gfp_t gfp_mask; /* implicit gfp mask for allocations */ - struct list_head private_list; /* for use by the address_space */ - void *private_data; /* ditto */ + pgoff_t writeback_index; + const struct address_space_operations *a_ops; + unsigned long flags; errseq_t wb_err; + spinlock_t private_lock; + struct list_head private_list; + void *private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but -- cgit v1.2.3 From 0d3f92966629e536b0c5c2355c1ada8e21c245f6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 21 Nov 2017 14:07:06 -0500 Subject: page cache: Convert hole search to XArray The page cache offers the ability to search for a miss in the previous or next N locations. Rather than teach the XArray about the page cache's definition of a miss, use xas_prev() and xas_next() to search the page array. This should be more efficient as it does not have to start the lookup from the top for each index. Signed-off-by: Matthew Wilcox --- include/linux/pagemap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b1bd2186e6d2..cf9ad413eee9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -241,9 +241,9 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x) typedef int filler_t(void *, struct page *); -pgoff_t page_cache_next_hole(struct address_space *mapping, +pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); -pgoff_t page_cache_prev_hole(struct address_space *mapping, +pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); #define FGP_ACCESSED 0x00000001 -- cgit v1.2.3 From 74d609585d8bd6083bd9d75bc1fd2c0d3851bcc5 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 17 Nov 2017 10:01:45 -0500 Subject: page cache: Add and replace pages using the XArray Use the XArray APIs to add and replace pages in the page cache. This removes two uses of the radix tree preload API and is significantly shorter code. It also removes the last user of __radix_tree_create() outside radix-tree.c itself, so make it static. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 3 --- include/linux/swap.h | 8 ++++++-- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 15388b7e38b9..d55de428a589 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -231,9 +231,6 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -int __radix_tree_create(struct radix_tree_root *, unsigned long index, - unsigned order, struct radix_tree_node **nodep, - void __rcu ***slotp); int __radix_tree_insert(struct radix_tree_root *, unsigned long index, unsigned order, void *); static inline int radix_tree_insert(struct radix_tree_root *root, diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..6ea50cf41b4c 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -299,8 +299,12 @@ void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); void workingset_activation(struct page *page); -/* Do not use directly, use workingset_lookup_update */ -void workingset_update_node(struct radix_tree_node *node); +/* Only track the nodes of mappings with shadow entries */ +void workingset_update_node(struct xa_node *node); +#define mapping_set_update(xas, mapping) do { \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) \ + xas_set_update(xas, workingset_update_node); \ +} while (0) /* Returns workingset_update_node() if the mapping has shadow entries. */ #define workingset_lookup_update(mapping) \ -- cgit v1.2.3 From 3ece58a270cd1e5026282abe778bd50db7a11d08 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 18:00:33 -0400 Subject: page cache: Convert find_get_pages_contig to XArray There's no direct replacement for radix_tree_for_each_contig() in the XArray API as it's an unusual thing to do. Instead, open-code a loop using xas_next(). This removes the only user of radix_tree_for_each_contig() so delete the iterator from the API and the test suite code for it. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index d55de428a589..023e888e1163 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -522,23 +522,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, slot || (slot = radix_tree_next_chunk(root, iter, 0)) ; \ slot = radix_tree_next_slot(slot, iter, 0)) -/** - * radix_tree_for_each_contig - iterate over contiguous slots - * - * @slot: the void** variable for pointer to slot - * @root: the struct radix_tree_root pointer - * @iter: the struct radix_tree_iter pointer - * @start: iteration starting index - * - * @slot points to radix tree slot, @iter->index contains its index. - */ -#define radix_tree_for_each_contig(slot, root, iter, start) \ - for (slot = radix_tree_iter_init(iter, start) ; \ - slot || (slot = radix_tree_next_chunk(root, iter, \ - RADIX_TREE_ITER_CONTIG)) ; \ - slot = radix_tree_next_slot(slot, iter, \ - RADIX_TREE_ITER_CONTIG)) - /** * radix_tree_for_each_tagged - iterate over tagged slots * -- cgit v1.2.3 From a6906972fe67fb6f73ba04088f7897227fd1cd8f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 18:12:54 -0400 Subject: page cache; Convert find_get_pages_range_tag to XArray The 'end' parameter of the xas_for_each iterator avoids a useless iteration at the end of the range. Signed-off-by: Matthew Wilcox --- include/linux/pagemap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index cf9ad413eee9..c9bbb9a05764 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -363,10 +363,10 @@ static inline unsigned find_get_pages(struct address_space *mapping, unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, - pgoff_t end, int tag, unsigned int nr_pages, + pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages); static inline unsigned find_get_pages_tag(struct address_space *mapping, - pgoff_t *index, int tag, unsigned int nr_pages, + pgoff_t *index, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag, -- cgit v1.2.3 From c1901cd33cf407d77a181f8dd4ffff98041ef480 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 23:56:04 -0400 Subject: page cache: Convert find_get_entries_tag to XArray Slightly shorter and simpler code. Signed-off-by: Matthew Wilcox --- include/linux/pagemap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c9bbb9a05764..226f96f0dee0 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -373,7 +373,7 @@ static inline unsigned find_get_pages_tag(struct address_space *mapping, nr_pages, pages); } unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, - int tag, unsigned int nr_entries, + xa_mark_t tag, unsigned int nr_entries, struct page **entries, pgoff_t *indices); struct page *grab_cache_page_write_begin(struct address_space *mapping, -- cgit v1.2.3 From ff9c745b81ff1e482167fd73558450e66ad43a33 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 22 Nov 2017 11:41:23 -0500 Subject: mm: Convert page-writeback to XArray Includes moving mapping_tagged() to fs.h as a static inline, and changing it to return bool. Signed-off-by: Matthew Wilcox --- include/linux/fs.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d126cad0f621..e10278e4db66 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -483,15 +483,18 @@ struct block_device { struct mutex bd_fsfreeze_mutex; } __randomize_layout; +/* XArray tags, for tagging dirty and writeback pages in the pagecache. */ +#define PAGECACHE_TAG_DIRTY XA_MARK_0 +#define PAGECACHE_TAG_WRITEBACK XA_MARK_1 +#define PAGECACHE_TAG_TOWRITE XA_MARK_2 + /* - * Radix-tree tags, for tagging dirty and writeback pages within the pagecache - * radix trees + * Returns true if any of the pages in the mapping are marked with the tag. */ -#define PAGECACHE_TAG_DIRTY 0 -#define PAGECACHE_TAG_WRITEBACK 1 -#define PAGECACHE_TAG_TOWRITE 2 - -int mapping_tagged(struct address_space *mapping, int tag); +static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) +{ + return xa_marked(&mapping->i_pages, tag); +} static inline void i_mmap_lock_write(struct address_space *mapping) { -- cgit v1.2.3 From a97e7904c0806309fd77103005bb7820c3f1c5e4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 24 Nov 2017 14:24:59 -0500 Subject: mm: Convert workingset to XArray We construct an XA_STATE and use it to delete the node with xas_store() rather than adding a special function for this unique use case. Includes a test that simulates this usage for the test suite. Signed-off-by: Matthew Wilcox --- include/linux/swap.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6ea50cf41b4c..112cebcf0402 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -306,15 +306,6 @@ void workingset_update_node(struct xa_node *node); xas_set_update(xas, workingset_update_node); \ } while (0) -/* Returns workingset_update_node() if the mapping has shadow entries. */ -#define workingset_lookup_update(mapping) \ -({ \ - radix_tree_update_node_t __helper = workingset_update_node; \ - if (dax_mapping(mapping) || shmem_mapping(mapping)) \ - __helper = NULL; \ - __helper; \ -}) - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; -- cgit v1.2.3 From 4e17ec250fce0eba9b70a91c9622da2748a3ec50 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 29 Nov 2017 08:32:39 -0500 Subject: mm: Convert delete_from_swap_cache to XArray Both callers of __delete_from_swap_cache have the swp_entry_t already, so pass that in to make constructing the XA_STATE easier. Signed-off-by: Matthew Wilcox --- include/linux/swap.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 112cebcf0402..cb479bf5842e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -403,7 +403,7 @@ extern void show_swap_cache_info(void); extern int add_to_swap(struct page *page); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); extern int __add_to_swap_cache(struct page *page, swp_entry_t entry); -extern void __delete_from_swap_cache(struct page *); +extern void __delete_from_swap_cache(struct page *, swp_entry_t entry); extern void delete_from_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); @@ -557,7 +557,8 @@ static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, return -1; } -static inline void __delete_from_swap_cache(struct page *page) +static inline void __delete_from_swap_cache(struct page *page, + swp_entry_t entry) { } -- cgit v1.2.3 From 10bbd235859bf483f9a8a4ebe95463d700bae394 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 5 Dec 2017 17:30:38 -0500 Subject: pagevec: Use xa_mark_t Removes sparse warnings. Signed-off-by: Matthew Wilcox --- include/linux/pagevec.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 6dc456ac6136..081d934eda64 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -9,6 +9,8 @@ #ifndef _LINUX_PAGEVEC_H #define _LINUX_PAGEVEC_H +#include + /* 15 pointers + header align the pagevec structure to a power of two */ #define PAGEVEC_SIZE 15 @@ -40,12 +42,12 @@ static inline unsigned pagevec_lookup(struct pagevec *pvec, unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag); + xa_mark_t tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag, unsigned max_pages); + xa_mark_t tag, unsigned max_pages); static inline unsigned pagevec_lookup_tag(struct pagevec *pvec, - struct address_space *mapping, pgoff_t *index, int tag) + struct address_space *mapping, pgoff_t *index, xa_mark_t tag) { return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag); } -- cgit v1.2.3 From 7b8d046fba91d62beb8a8f78244aaa3c23a60cdd Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 1 Dec 2017 22:13:06 -0500 Subject: shmem: Convert shmem_alloc_hugepage to XArray xa_find() is a slightly easier API to use than radix_tree_gang_lookup_slot() because it contains its own RCU locking. This commit removes the last user of radix_tree_gang_lookup_slot() so remove the function too. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 023e888e1163..8a4280bc350f 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -147,12 +147,11 @@ static inline unsigned int iter_shift(const struct radix_tree_iter *iter) * radix_tree_lookup_slot * radix_tree_tag_get * radix_tree_gang_lookup - * radix_tree_gang_lookup_slot * radix_tree_gang_lookup_tag * radix_tree_gang_lookup_tag_slot * radix_tree_tagged * - * The first 8 functions are able to be called locklessly, using RCU. The + * The first 7 functions are able to be called locklessly, using RCU. The * caller must ensure calls to these functions are made within rcu_read_lock() * regions. Other readers (lock-free or otherwise) and modifications may be * running concurrently. @@ -263,9 +262,6 @@ void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *, unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); -unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *, - void __rcu ***results, unsigned long *indices, - unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); -- cgit v1.2.3 From 1cf56f9d670b88b2e947a7ccdb8ba32e6477915d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 9 Apr 2018 16:24:45 -0400 Subject: radix tree: Remove radix_tree_update_node_t The only user of this functionality was the workingset code, and it's now been converted to the XArray. Remove __radix_tree_delete_node() entirely as it was also only used by the workingset code. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 8a4280bc350f..7513d0df984b 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -242,17 +242,12 @@ void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *, unsigned long index); -typedef void (*radix_tree_update_node_t)(struct radix_tree_node *); void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *, - void __rcu **slot, void *entry, - radix_tree_update_node_t update_node); + void __rcu **slot, void *entry); void radix_tree_iter_replace(struct radix_tree_root *, const struct radix_tree_iter *, void __rcu **slot, void *entry); void radix_tree_replace_slot(struct radix_tree_root *, void __rcu **slot, void *entry); -void __radix_tree_delete_node(struct radix_tree_root *, - struct radix_tree_node *, - radix_tree_update_node_t update_node); void radix_tree_iter_delete(struct radix_tree_root *, struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); -- cgit v1.2.3 From 2956c6644bfd9aab9f6b21a12e1bd75876d9dd73 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 19 May 2018 16:47:47 -0400 Subject: radix tree: Remove split/join code radix_tree_split and radix_tree_join were never used upstream. Remove them; if they're needed in future they will be replaced by XArray equivalents. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 7513d0df984b..44f9abdcb5ab 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -284,12 +284,6 @@ static inline void radix_tree_preload_end(void) preempt_enable(); } -int radix_tree_split_preload(unsigned old_order, unsigned new_order, gfp_t); -int radix_tree_split(struct radix_tree_root *, unsigned long index, - unsigned new_order); -int radix_tree_join(struct radix_tree_root *, unsigned long index, - unsigned new_order, void *); - void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max); -- cgit v1.2.3 From 8cf2f98411e3a0865026a1061af637161b16d32b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 19 May 2018 16:47:47 -0400 Subject: radix tree: Remove radix_tree_maybe_preload_order This function was only used by the page cache which is now converted to the XArray. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 44f9abdcb5ab..664d50c5c2ff 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -259,7 +259,6 @@ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); -int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); -- cgit v1.2.3 From adb9d9c4ccb1ff0bf1d376e65f36aa5573c75c1a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 9 Apr 2018 16:52:21 -0400 Subject: radix tree: Remove radix_tree_clear_tags The page cache was the only user of this interface and it has now been converted to the XArray. Transform the test into a test of xas_init_marks(). Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 664d50c5c2ff..7b009af3bb1e 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -252,8 +252,6 @@ void radix_tree_iter_delete(struct radix_tree_root *, struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); -void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *, - void __rcu **slot); unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); -- cgit v1.2.3 From 372266ba0267803564824b1c09f1bb7f3f3fc761 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 18 Aug 2018 07:09:22 -0400 Subject: radix tree test suite: Convert tag_tagged_items to XArray The tag_tagged_items() function is supposed to test the page-writeback tagging code. Since that has been converted to the XArray, there's not much point in testing the radix tree's tagging code. This requires using the pthread mutex embedded in the xarray instead of an external lock, so remove the pthread mutexes which protect xarrays/radix trees. Also remove radix_tree_iter_tag_set() as this was the last user. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 7b009af3bb1e..9a1460488163 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -264,8 +264,6 @@ void *radix_tree_tag_clear(struct radix_tree_root *, unsigned long index, unsigned int tag); int radix_tree_tag_get(const struct radix_tree_root *, unsigned long index, unsigned int tag); -void radix_tree_iter_tag_set(struct radix_tree_root *, - const struct radix_tree_iter *iter, unsigned int tag); void radix_tree_iter_tag_clear(struct radix_tree_root *, const struct radix_tree_iter *iter, unsigned int tag); unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *, -- cgit v1.2.3 From 0e9446c35a80931044b6d8d2d74a9cabd248539f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 15 Aug 2018 14:13:29 -0400 Subject: xarray: Add range store functionality This version of xa_store_range() really only supports load and store. Our only user only needs basic load and store functionality, so there's no need to do the extra work to support marking and overlapping stores correctly yet. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index e0b57af52e9b..d9514928ddac 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -292,6 +292,8 @@ void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int xa_reserve(struct xarray *, unsigned long index, gfp_t); +void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, + void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); -- cgit v1.2.3 From 3a08cd52c37c793ffc199f6fc2ecfc368e284b2d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 22 Sep 2018 16:14:30 -0400 Subject: radix tree: Remove multiorder support All users have now been converted to the XArray. Removing the support reduces code size and ensures new users will use the XArray instead. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 40 ++++------------------------------------ 1 file changed, 4 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 9a1460488163..06c4c7a6c09c 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -96,7 +96,6 @@ static inline bool radix_tree_empty(const struct radix_tree_root *root) * @next_index: one beyond the last index for this chunk * @tags: bit-mask for tag-iterating * @node: node that contains current slot - * @shift: shift for the node that holds our slots * * This radix tree iterator works in terms of "chunks" of slots. A chunk is a * subinterval of slots contained within one radix tree leaf node. It is @@ -110,20 +109,8 @@ struct radix_tree_iter { unsigned long next_index; unsigned long tags; struct radix_tree_node *node; -#ifdef CONFIG_RADIX_TREE_MULTIORDER - unsigned int shift; -#endif }; -static inline unsigned int iter_shift(const struct radix_tree_iter *iter) -{ -#ifdef CONFIG_RADIX_TREE_MULTIORDER - return iter->shift; -#else - return 0; -#endif -} - /** * Radix-tree synchronization * @@ -230,13 +217,8 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -int __radix_tree_insert(struct radix_tree_root *, unsigned long index, - unsigned order, void *); -static inline int radix_tree_insert(struct radix_tree_root *root, - unsigned long index, void *entry) -{ - return __radix_tree_insert(root, index, 0, entry); -} +int radix_tree_insert(struct radix_tree_root *, unsigned long index, + void *); void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp); void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); @@ -384,7 +366,7 @@ void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) static inline unsigned long __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) { - return iter->index + (slots << iter_shift(iter)); + return iter->index + slots; } /** @@ -409,20 +391,8 @@ void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { - return (iter->next_index - iter->index) >> iter_shift(iter); -} - -#ifdef CONFIG_RADIX_TREE_MULTIORDER -void __rcu **__radix_tree_next_slot(void __rcu **slot, - struct radix_tree_iter *iter, unsigned flags); -#else -/* Can't happen without sibling entries, but the compiler can't tell that */ -static inline void __rcu **__radix_tree_next_slot(void __rcu **slot, - struct radix_tree_iter *iter, unsigned flags) -{ - return slot; + return iter->next_index - iter->index; } -#endif /** * radix_tree_next_slot - find next slot in chunk @@ -482,8 +452,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, return NULL; found: - if (unlikely(radix_tree_is_internal_node(rcu_dereference_raw(*slot)))) - return __radix_tree_next_slot(slot, iter, flags); return slot; } -- cgit v1.2.3 From 94e6992bb560be8bffb47f287194adf070b57695 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 26 Sep 2018 18:03:16 +0200 Subject: libceph: bump CEPH_MSG_MAX_DATA_LEN If the read is large enough, we end up spinning in the messenger: libceph: osd0 192.168.122.1:6801 io error libceph: osd0 192.168.122.1:6801 io error libceph: osd0 192.168.122.1:6801 io error This is a receive side limit, so only reads were affected. Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 49c93b9308d7..68bb09c29ce8 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -81,7 +81,13 @@ struct ceph_options { #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) -#define CEPH_MSG_MAX_DATA_LEN (16*1024*1024) + +/* + * Handle the largest possible rbd object in one message. + * There is no limit on the size of cephfs objects, but it has to obey + * rsize and wsize mount options anyway. + */ +#define CEPH_MSG_MAX_DATA_LEN (32*1024*1024) #define CEPH_AUTH_NAME_DEFAULT "guest" -- cgit v1.2.3 From 24639ce56040a8ea890ad8836068c1ad8bd177c7 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 26 Sep 2018 19:12:07 +0200 Subject: libceph: osd_req_op_cls_init() doesn't need to take opcode Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 02096da01845..f3e828460c91 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -444,9 +444,8 @@ extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages); -extern int osd_req_op_cls_init(struct ceph_osd_request *osd_req, - unsigned int which, u16 opcode, - const char *class, const char *method); +int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, + const char *class, const char *method); extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *name, const void *value, size_t size, u8 cmp_op, u8 cmp_mode); -- cgit v1.2.3 From 33165d472310262d8c79c7e4d1a17dc60cea7e35 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 28 Sep 2018 15:38:34 +0200 Subject: libceph: introduce ceph_pagelist_alloc() struct ceph_pagelist cannot be embedded into anything else because it has its own refcount. Merge allocation and initialization together. Signed-off-by: Ilya Dryomov --- include/linux/ceph/pagelist.h | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h index d0223364349f..5dead8486fd8 100644 --- a/include/linux/ceph/pagelist.h +++ b/include/linux/ceph/pagelist.h @@ -23,16 +23,7 @@ struct ceph_pagelist_cursor { size_t room; /* room remaining to reset to */ }; -static inline void ceph_pagelist_init(struct ceph_pagelist *pl) -{ - INIT_LIST_HEAD(&pl->head); - pl->mapped_tail = NULL; - pl->length = 0; - pl->room = 0; - INIT_LIST_HEAD(&pl->free_list); - pl->num_pages_free = 0; - refcount_set(&pl->refcnt, 1); -} +struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags); extern void ceph_pagelist_release(struct ceph_pagelist *pl); -- cgit v1.2.3 From 0d9c1ab3be4c0187663096a6a084421d0a1e45c6 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 15 Oct 2018 17:38:23 +0200 Subject: libceph: preallocate message data items Currently message data items are allocated with ceph_msg_data_create() in setup_request_data() inside send_request(). send_request() has never been allowed to fail, so each allocation is followed by a BUG_ON: data = ceph_msg_data_create(...); BUG_ON(!data); It's been this way since support for multiple message data items was added in commit 6644ed7b7e04 ("libceph: make message data be a pointer") in 3.10. There is no reason to delay the allocation of message data items until the last possible moment and we certainly don't need a linked list of them as they are only ever appended to the end and never erased. Make ceph_msg_new2() take max_data_items and adapt the rest of the code. Reported-by: Jerry Lee Signed-off-by: Ilya Dryomov --- include/linux/ceph/messenger.h | 24 +++++------------------- include/linux/ceph/msgpool.h | 11 ++++++----- 2 files changed, 11 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index fc2b4491ee0a..800a2128d411 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -82,22 +82,6 @@ enum ceph_msg_data_type { CEPH_MSG_DATA_BVECS, /* data source/destination is a bio_vec array */ }; -static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) -{ - switch (type) { - case CEPH_MSG_DATA_NONE: - case CEPH_MSG_DATA_PAGES: - case CEPH_MSG_DATA_PAGELIST: -#ifdef CONFIG_BLOCK - case CEPH_MSG_DATA_BIO: -#endif /* CONFIG_BLOCK */ - case CEPH_MSG_DATA_BVECS: - return true; - default: - return false; - } -} - #ifdef CONFIG_BLOCK struct ceph_bio_iter { @@ -181,7 +165,6 @@ struct ceph_bvec_iter { } while (0) struct ceph_msg_data { - struct list_head links; /* ceph_msg->data */ enum ceph_msg_data_type type; union { #ifdef CONFIG_BLOCK @@ -202,7 +185,6 @@ struct ceph_msg_data { struct ceph_msg_data_cursor { size_t total_resid; /* across all data items */ - struct list_head *data_head; /* = &ceph_msg->data */ struct ceph_msg_data *data; /* current data item */ size_t resid; /* bytes not yet consumed */ @@ -240,7 +222,9 @@ struct ceph_msg { struct ceph_buffer *middle; size_t data_length; - struct list_head data; + struct ceph_msg_data *data; + int num_data_items; + int max_data_items; struct ceph_msg_data_cursor cursor; struct ceph_connection *con; @@ -381,6 +365,8 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos, void ceph_msg_data_add_bvecs(struct ceph_msg *msg, struct ceph_bvec_iter *bvec_pos); +struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items, + gfp_t flags, bool can_fail); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); diff --git a/include/linux/ceph/msgpool.h b/include/linux/ceph/msgpool.h index 76c98a512758..729cdf700eae 100644 --- a/include/linux/ceph/msgpool.h +++ b/include/linux/ceph/msgpool.h @@ -13,14 +13,15 @@ struct ceph_msgpool { mempool_t *pool; int type; /* preallocated message type */ int front_len; /* preallocated payload size */ + int max_data_items; }; -extern int ceph_msgpool_init(struct ceph_msgpool *pool, int type, - int front_len, int size, bool blocking, - const char *name); +int ceph_msgpool_init(struct ceph_msgpool *pool, int type, + int front_len, int max_data_items, int size, + const char *name); extern void ceph_msgpool_destroy(struct ceph_msgpool *pool); -extern struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *, - int front_len); +struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len, + int max_data_items); extern void ceph_msgpool_put(struct ceph_msgpool *, struct ceph_msg *); #endif -- cgit v1.2.3 From 23ddf9bea900b4ce39e5707e1ddf66062cfe6d91 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Mon, 15 Oct 2018 16:45:58 +0100 Subject: libceph: support the RADOS copy-from operation Add support for performing remote object copies using the 'copy-from' operation. [ Add COPY_FROM to get_num_data_items(). ] Signed-off-by: Luis Henriques Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 17 +++++++++++++++++ include/linux/ceph/rados.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f3e828460c91..7a2af5034278 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -136,6 +136,13 @@ struct ceph_osd_req_op { u64 expected_object_size; u64 expected_write_size; } alloc_hint; + struct { + u64 snapid; + u64 src_version; + u8 flags; + u32 src_fadvise_flags; + struct ceph_osd_data osd_data; + } copy_from; }; }; @@ -510,6 +517,16 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct timespec64 *mtime, struct page **pages, int nr_pages); +int ceph_osdc_copy_from(struct ceph_osd_client *osdc, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + struct ceph_object_id *dst_oid, + struct ceph_object_locator *dst_oloc, + u32 dst_fadvise_flags, + u8 copy_from_flags); + /* watch/notify */ struct ceph_osd_linger_request * ceph_osdc_watch(struct ceph_osd_client *osdc, diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index f1988387c5ad..3eb0e55665b4 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -410,6 +410,14 @@ enum { enum { CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */ CEPH_OSD_OP_FLAG_FAILOK = 2, /* continue despite failure */ + CEPH_OSD_OP_FLAG_FADVISE_RANDOM = 0x4, /* the op is random */ + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL = 0x8, /* the op is sequential */ + CEPH_OSD_OP_FLAG_FADVISE_WILLNEED = 0x10,/* data will be accessed in + the near future */ + CEPH_OSD_OP_FLAG_FADVISE_DONTNEED = 0x20,/* data will not be accessed + in the near future */ + CEPH_OSD_OP_FLAG_FADVISE_NOCACHE = 0x40,/* data will be accessed only + once by this client */ }; #define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/ @@ -431,6 +439,15 @@ enum { CEPH_OSD_CMPXATTR_MODE_U64 = 2 }; +enum { + CEPH_OSD_COPY_FROM_FLAG_FLUSH = 1, /* part of a flush operation */ + CEPH_OSD_COPY_FROM_FLAG_IGNORE_OVERLAY = 2, /* ignore pool overlay */ + CEPH_OSD_COPY_FROM_FLAG_IGNORE_CACHE = 4, /* ignore osd cache logic */ + CEPH_OSD_COPY_FROM_FLAG_MAP_SNAP_CLONE = 8, /* map snap direct to + * cloneid */ + CEPH_OSD_COPY_FROM_FLAG_RWORDERED = 16, /* order with write */ +}; + enum { CEPH_OSD_WATCH_OP_UNWATCH = 0, CEPH_OSD_WATCH_OP_LEGACY_WATCH = 1, @@ -497,6 +514,17 @@ struct ceph_osd_op { __le64 expected_object_size; __le64 expected_write_size; } __attribute__ ((packed)) alloc_hint; + struct { + __le64 snapid; + __le64 src_version; + __u8 flags; /* CEPH_OSD_COPY_FROM_FLAG_* */ + /* + * CEPH_OSD_OP_FLAG_FADVISE_*: fadvise flags + * for src object, flags for dest object are in + * ceph_osd_op::flags. + */ + __le32 src_fadvise_flags; + } __attribute__ ((packed)) copy_from; }; __le32 payload_len; } __attribute__ ((packed)); -- cgit v1.2.3 From 1227daa43bce1318ff6fb54e6cd862b4f60245c7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 17 Oct 2018 17:20:35 -0700 Subject: pstore/ram: Clarify resource reservation labels When ramoops reserved a memory region in the kernel, it had an unhelpful label of "persistent_memory". When reading /proc/iomem, it would be repeated many times, did not hint that it was ramoops in particular, and didn't clarify very much about what each was used for: 400000000-407ffffff : Persistent Memory (legacy) 400000000-400000fff : persistent_memory 400001000-400001fff : persistent_memory ... 4000ff000-4000fffff : persistent_memory Instead, this adds meaningful labels for how the various regions are being used: 400000000-407ffffff : Persistent Memory (legacy) 400000000-400000fff : ramoops:dump(0/252) 400001000-400001fff : ramoops:dump(1/252) ... 4000fc000-4000fcfff : ramoops:dump(252/252) 4000fd000-4000fdfff : ramoops:console 4000fe000-4000fe3ff : ramoops:ftrace(0/3) 4000fe400-4000fe7ff : ramoops:ftrace(1/3) 4000fe800-4000febff : ramoops:ftrace(2/3) 4000fec00-4000fefff : ramoops:ftrace(3/3) 4000ff000-4000fffff : ramoops:pmsg Signed-off-by: Kees Cook Reviewed-by: Joel Fernandes (Google) Tested-by: Sai Prakash Ranjan Tested-by: Guenter Roeck --- include/linux/pstore_ram.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index e6d226464838..602d64725222 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -46,6 +46,7 @@ struct persistent_ram_zone { phys_addr_t paddr; size_t size; void *vaddr; + char *label; struct persistent_ram_buffer *buffer; size_t buffer_size; u32 flags; @@ -65,7 +66,7 @@ struct persistent_ram_zone { struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, u32 sig, struct persistent_ram_ecc_info *ecc_info, - unsigned int memtype, u32 flags); + unsigned int memtype, u32 flags, char *label); void persistent_ram_free(struct persistent_ram_zone *prz); void persistent_ram_zap(struct persistent_ram_zone *prz); -- cgit v1.2.3 From af033b2aa8a874fd5737fafe90d159136527b5b4 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 20 Sep 2018 20:05:00 +0800 Subject: f2fs: guarantee journalled quota data by checkpoint For journalled quota mode, let checkpoint to flush dquot dirty data and quota file data to guarntee persistence of all quota sysfile in last checkpoint, by this way, we can avoid corrupting quota sysfile when encountering SPO. The implementation is as below: 1. add a global state SBI_QUOTA_NEED_FLUSH to indicate that there is cached dquot metadata changes in quota subsystem, and later checkpoint should: a) flush dquot metadata into quota file. b) flush quota file to storage to keep file usage be consistent. 2. add a global state SBI_QUOTA_NEED_REPAIR to indicate that quota operation failed due to -EIO or -ENOSPC, so later, a) checkpoint will skip syncing dquot metadata. b) CP_QUOTA_NEED_FSCK_FLAG will be set in last cp pack to give a hint for fsck repairing. 3. add a global state SBI_QUOTA_SKIP_FLUSH, in checkpoint, if quota data updating is very heavy, it may cause hungtask in block_operation(). To avoid this, if our retry time exceed threshold, let's just skip flushing and retry in next checkpoint(). Signed-off-by: Weichao Guo Signed-off-by: Chao Yu [Jaegeuk Kim: avoid warnings and set fsck flag] Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 8b9c7dc0260c..d7711048ef93 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -117,6 +117,7 @@ struct f2fs_super_block { * For checkpoint */ #define CP_DISABLED_FLAG 0x00001000 +#define CP_QUOTA_NEED_FSCK_FLAG 0x00000800 #define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 #define CP_NOCRC_RECOVERY_FLAG 0x00000200 #define CP_TRIMMED_FLAG 0x00000100 -- cgit v1.2.3 From 876dcf2f3aaa0f68d437b368b93a4c4b81521191 Mon Sep 17 00:00:00 2001 From: Olivier Brunel Date: Sat, 20 Oct 2018 19:39:56 +0200 Subject: umh: Add command line to user mode helpers User mode helpers were spawned without a command line, and because an empty command line is used by many tools to identify processes as kernel threads, this could cause some issues. Notably during killing spree on shutdown, since such helper would then be skipped (i.e. not killed) which would result in the process remaining alive, and thus preventing unmouting of the rootfs (as experienced with the bpfilter umh). Fixes: 449325b52b7a ("umh: introduce fork_usermode_blob() helper") Signed-off-by: Olivier Brunel Signed-off-by: David S. Miller --- include/linux/umh.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/umh.h b/include/linux/umh.h index 5c812acbb80a..235f51b62c71 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -44,6 +44,7 @@ struct subprocess_info *call_usermodehelper_setup_file(struct file *file, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *), void *data); struct umh_info { + const char *cmdline; struct file *pipe_to_umh; struct file *pipe_from_umh; pid_t pid; -- cgit v1.2.3 From 39b27ad9c71cb72b07c9cd85191a8fe723e5b21a Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 7 Aug 2018 18:11:22 +0200 Subject: mfd: sec-core: Add SPDX license identifiers Replace GPL v2.0+ license statements with SPDX license identifiers. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/samsung/core.h | 11 ++--------- include/linux/mfd/samsung/irq.h | 10 ++-------- include/linux/mfd/samsung/rtc.h | 15 ++------------- include/linux/mfd/samsung/s2mpa01.h | 7 +------ include/linux/mfd/samsung/s2mps11.h | 9 +-------- include/linux/mfd/samsung/s2mps13.h | 14 +------------- include/linux/mfd/samsung/s2mps14.h | 14 +------------- include/linux/mfd/samsung/s2mps15.h | 11 +---------- include/linux/mfd/samsung/s2mpu02.h | 14 +------------- include/linux/mfd/samsung/s5m8763.h | 10 ++-------- include/linux/mfd/samsung/s5m8767.h | 10 ++-------- 11 files changed, 16 insertions(+), 109 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index 28f4ae76271d..3ca17eb89aa2 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -1,14 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * core.h - * - * copyright (c) 2011 Samsung Electronics Co., Ltd + * Copyright (c) 2011 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_SEC_CORE_H diff --git a/include/linux/mfd/samsung/irq.h b/include/linux/mfd/samsung/irq.h index 667aa40486dd..6cfe4201a106 100644 --- a/include/linux/mfd/samsung/irq.h +++ b/include/linux/mfd/samsung/irq.h @@ -1,13 +1,7 @@ -/* irq.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2012 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_SEC_IRQ_H diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h index 9ed2871ea335..0204decfc9aa 100644 --- a/include/linux/mfd/samsung/rtc.h +++ b/include/linux/mfd/samsung/rtc.h @@ -1,18 +1,7 @@ -/* rtc.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_SEC_RTC_H diff --git a/include/linux/mfd/samsung/s2mpa01.h b/include/linux/mfd/samsung/s2mpa01.h index 2766108bca2f..0762e9de6f2f 100644 --- a/include/linux/mfd/samsung/s2mpa01.h +++ b/include/linux/mfd/samsung/s2mpa01.h @@ -1,12 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (c) 2013 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S2MPA01_H diff --git a/include/linux/mfd/samsung/s2mps11.h b/include/linux/mfd/samsung/s2mps11.h index 2c14eeca46f0..6e7668a389a1 100644 --- a/include/linux/mfd/samsung/s2mps11.h +++ b/include/linux/mfd/samsung/s2mps11.h @@ -1,14 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mps11.h - * * Copyright (c) 2012 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S2MPS11_H diff --git a/include/linux/mfd/samsung/s2mps13.h b/include/linux/mfd/samsung/s2mps13.h index 239e977ba45d..b96d8a11dcd3 100644 --- a/include/linux/mfd/samsung/s2mps13.h +++ b/include/linux/mfd/samsung/s2mps13.h @@ -1,19 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mps13.h - * * Copyright (c) 2014 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_S2MPS13_H diff --git a/include/linux/mfd/samsung/s2mps14.h b/include/linux/mfd/samsung/s2mps14.h index c92f4782afb5..f4afa0cfc24f 100644 --- a/include/linux/mfd/samsung/s2mps14.h +++ b/include/linux/mfd/samsung/s2mps14.h @@ -1,19 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mps14.h - * * Copyright (c) 2014 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_S2MPS14_H diff --git a/include/linux/mfd/samsung/s2mps15.h b/include/linux/mfd/samsung/s2mps15.h index 36d35287c3c0..eac6bf74b72e 100644 --- a/include/linux/mfd/samsung/s2mps15.h +++ b/include/linux/mfd/samsung/s2mps15.h @@ -1,16 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (c) 2015 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __LINUX_MFD_S2MPS15_H diff --git a/include/linux/mfd/samsung/s2mpu02.h b/include/linux/mfd/samsung/s2mpu02.h index 47ae9bc583a7..76cd5380cf0f 100644 --- a/include/linux/mfd/samsung/s2mpu02.h +++ b/include/linux/mfd/samsung/s2mpu02.h @@ -1,19 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mpu02.h - * * Copyright (c) 2014 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_S2MPU02_H diff --git a/include/linux/mfd/samsung/s5m8763.h b/include/linux/mfd/samsung/s5m8763.h index e025418e5589..c534f086ca16 100644 --- a/include/linux/mfd/samsung/s5m8763.h +++ b/include/linux/mfd/samsung/s5m8763.h @@ -1,13 +1,7 @@ -/* s5m8763.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2011 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S5M8763_H diff --git a/include/linux/mfd/samsung/s5m8767.h b/include/linux/mfd/samsung/s5m8767.h index 243b58fec33d..704f8d80e96e 100644 --- a/include/linux/mfd/samsung/s5m8767.h +++ b/include/linux/mfd/samsung/s5m8767.h @@ -1,13 +1,7 @@ -/* s5m8767.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2011 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S5M8767_H -- cgit v1.2.3 From d7d8d7a2405f8b6296660648e893fc3442269d81 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 7 Aug 2018 18:11:23 +0200 Subject: mfd: maxim: Add SPDX license identifiers Replace GPL v2.0+ license statements with SPDX license identifiers. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/max14577-private.h | 11 +---------- include/linux/mfd/max14577.h | 11 +---------- include/linux/mfd/max77686-private.h | 15 +-------------- include/linux/mfd/max77686.h | 15 +-------------- include/linux/mfd/max77693-common.h | 6 +----- include/linux/mfd/max77693-private.h | 15 +-------------- include/linux/mfd/max77693.h | 15 +-------------- include/linux/mfd/max77843-private.h | 6 +----- include/linux/mfd/max8997-private.h | 15 +-------------- include/linux/mfd/max8997.h | 15 +-------------- include/linux/mfd/max8998-private.h | 15 +-------------- include/linux/mfd/max8998.h | 15 +-------------- 12 files changed, 12 insertions(+), 142 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/max14577-private.h b/include/linux/mfd/max14577-private.h index df75234f979d..a21374f8ad26 100644 --- a/include/linux/mfd/max14577-private.h +++ b/include/linux/mfd/max14577-private.h @@ -1,19 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max14577-private.h - Common API for the Maxim 14577/77836 internal sub chip * * Copyright (C) 2014 Samsung Electrnoics * Chanwoo Choi * Krzysztof Kozlowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __MAX14577_PRIVATE_H__ diff --git a/include/linux/mfd/max14577.h b/include/linux/mfd/max14577.h index d81b52bb8bee..8b3ef891ba42 100644 --- a/include/linux/mfd/max14577.h +++ b/include/linux/mfd/max14577.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max14577.h - Driver for the Maxim 14577/77836 * @@ -5,16 +6,6 @@ * Chanwoo Choi * Krzysztof Kozlowski * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * This driver is based on max8997.h * * MAX14577 has MUIC, Charger devices. diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h index 643dae777b43..833e578e051e 100644 --- a/include/linux/mfd/max77686-private.h +++ b/include/linux/mfd/max77686-private.h @@ -1,22 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77686-private.h - Voltage regulator driver for the Maxim 77686/802 * * Copyright (C) 2012 Samsung Electrnoics * Chiwoong Byun - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX77686_PRIV_H diff --git a/include/linux/mfd/max77686.h b/include/linux/mfd/max77686.h index d4b72d519115..d0fb510875e6 100644 --- a/include/linux/mfd/max77686.h +++ b/include/linux/mfd/max77686.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77686.h - Driver for the Maxim 77686/802 * * Copyright (C) 2012 Samsung Electrnoics * Chiwoong Byun * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * This driver is based on max8997.h * * MAX77686 has PMIC, RTC devices. diff --git a/include/linux/mfd/max77693-common.h b/include/linux/mfd/max77693-common.h index 095b121aa725..a5bce099f1ed 100644 --- a/include/linux/mfd/max77693-common.h +++ b/include/linux/mfd/max77693-common.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Common data shared between Maxim 77693 and 77843 drivers * * Copyright (C) 2015 Samsung Electronics - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __LINUX_MFD_MAX77693_COMMON_H diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h index 3c7a63b98ad6..e798c81aec31 100644 --- a/include/linux/mfd/max77693-private.h +++ b/include/linux/mfd/max77693-private.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77693-private.h - Voltage regulator driver for the Maxim 77693 * @@ -5,20 +6,6 @@ * SangYoung Son * * This program is not provided / owned by Maxim Integrated Products. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX77693_PRIV_H diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h index d450f687301b..c67c16ba8649 100644 --- a/include/linux/mfd/max77693.h +++ b/include/linux/mfd/max77693.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77693.h - Driver for the Maxim 77693 * @@ -6,20 +7,6 @@ * * This program is not provided / owned by Maxim Integrated Products. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * This driver is based on max8997.h * * MAX77693 has PMIC, Charger, Flash LED, Haptic, MUIC devices. diff --git a/include/linux/mfd/max77843-private.h b/include/linux/mfd/max77843-private.h index b8908bf8d315..0bc7454c4dbe 100644 --- a/include/linux/mfd/max77843-private.h +++ b/include/linux/mfd/max77843-private.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Common variables for the Maxim MAX77843 driver * * Copyright (C) 2015 Samsung Electronics * Author: Jaewon Kim * Author: Beomho Seo - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __MAX77843_PRIVATE_H_ diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h index 78c76cd4d37b..a10cd6945232 100644 --- a/include/linux/mfd/max8997-private.h +++ b/include/linux/mfd/max8997-private.h @@ -1,22 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8997-private.h - Voltage regulator driver for the Maxim 8997 * * Copyright (C) 2010 Samsung Electrnoics * MyungJoo Ham - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX8997_PRIV_H diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h index cf815577bd68..3c4e920b4727 100644 --- a/include/linux/mfd/max8997.h +++ b/include/linux/mfd/max8997.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8997.h - Driver for the Maxim 8997/8966 * * Copyright (C) 2009-2010 Samsung Electrnoics * MyungJoo Ham * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * This driver is based on max8998.h * * MAX8997 has PMIC, MUIC, HAPTIC, RTC, FLASH, and Fuel Gauge devices. diff --git a/include/linux/mfd/max8998-private.h b/include/linux/mfd/max8998-private.h index d68ada502ff3..6deb5f577602 100644 --- a/include/linux/mfd/max8998-private.h +++ b/include/linux/mfd/max8998-private.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8998-private.h - Voltage regulator driver for the Maxim 8998 * * Copyright (C) 2009-2010 Samsung Electrnoics * Kyungmin Park * Marek Szyprowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX8998_PRIV_H diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h index e3956a654cbc..061af220dcd3 100644 --- a/include/linux/mfd/max8998.h +++ b/include/linux/mfd/max8998.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8998.h - Voltage regulator driver for the Maxim 8998 * * Copyright (C) 2009-2010 Samsung Electrnoics * Kyungmin Park * Marek Szyprowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX8998_H -- cgit v1.2.3 From 3d51ec93a564a0f87d1276f067732be904816a53 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 21 Aug 2018 19:16:12 +0200 Subject: mfd: Add ingenic-tcu.h header This header contains macros for the registers that are present in the regmap shared by all the drivers related to the TCU (Timer Counter Unit) of the Ingenic JZ47xx SoCs. Signed-off-by: Paul Cercueil Signed-off-by: Lee Jones --- include/linux/mfd/ingenic-tcu.h | 56 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 include/linux/mfd/ingenic-tcu.h (limited to 'include/linux') diff --git a/include/linux/mfd/ingenic-tcu.h b/include/linux/mfd/ingenic-tcu.h new file mode 100644 index 000000000000..ab16ad283def --- /dev/null +++ b/include/linux/mfd/ingenic-tcu.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Header file for the Ingenic JZ47xx TCU driver + */ +#ifndef __LINUX_MFD_INGENIC_TCU_H_ +#define __LINUX_MFD_INGENIC_TCU_H_ + +#include + +#define TCU_REG_WDT_TDR 0x00 +#define TCU_REG_WDT_TCER 0x04 +#define TCU_REG_WDT_TCNT 0x08 +#define TCU_REG_WDT_TCSR 0x0c +#define TCU_REG_TER 0x10 +#define TCU_REG_TESR 0x14 +#define TCU_REG_TECR 0x18 +#define TCU_REG_TSR 0x1c +#define TCU_REG_TFR 0x20 +#define TCU_REG_TFSR 0x24 +#define TCU_REG_TFCR 0x28 +#define TCU_REG_TSSR 0x2c +#define TCU_REG_TMR 0x30 +#define TCU_REG_TMSR 0x34 +#define TCU_REG_TMCR 0x38 +#define TCU_REG_TSCR 0x3c +#define TCU_REG_TDFR0 0x40 +#define TCU_REG_TDHR0 0x44 +#define TCU_REG_TCNT0 0x48 +#define TCU_REG_TCSR0 0x4c +#define TCU_REG_OST_DR 0xe0 +#define TCU_REG_OST_CNTL 0xe4 +#define TCU_REG_OST_CNTH 0xe8 +#define TCU_REG_OST_TCSR 0xec +#define TCU_REG_TSTR 0xf0 +#define TCU_REG_TSTSR 0xf4 +#define TCU_REG_TSTCR 0xf8 +#define TCU_REG_OST_CNTHBUF 0xfc + +#define TCU_TCSR_RESERVED_BITS 0x3f +#define TCU_TCSR_PARENT_CLOCK_MASK 0x07 +#define TCU_TCSR_PRESCALE_LSB 3 +#define TCU_TCSR_PRESCALE_MASK 0x38 + +#define TCU_TCSR_PWM_SD BIT(9) /* 0: Shutdown abruptly 1: gracefully */ +#define TCU_TCSR_PWM_INITL_HIGH BIT(8) /* Sets the initial output level */ +#define TCU_TCSR_PWM_EN BIT(7) /* PWM pin output enable */ + +#define TCU_WDT_TCER_TCEN BIT(0) /* Watchdog timer enable */ + +#define TCU_CHANNEL_STRIDE 0x10 +#define TCU_REG_TDFRc(c) (TCU_REG_TDFR0 + ((c) * TCU_CHANNEL_STRIDE)) +#define TCU_REG_TDHRc(c) (TCU_REG_TDHR0 + ((c) * TCU_CHANNEL_STRIDE)) +#define TCU_REG_TCNTc(c) (TCU_REG_TCNT0 + ((c) * TCU_CHANNEL_STRIDE)) +#define TCU_REG_TCSRc(c) (TCU_REG_TCSR0 + ((c) * TCU_CHANNEL_STRIDE)) + +#endif /* __LINUX_MFD_INGENIC_TCU_H_ */ -- cgit v1.2.3 From 6360e40f421fba0a11bbabaa211c9c22c5cf5e61 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 28 Aug 2018 09:41:58 +0100 Subject: mfd: madera: Remove unused forward reference The madera_irqchip_pdata struct was replaced by the irq_flags member of struct madera_pdata so the forward reference is obsolete. Signed-off-by: Richard Fitzgerald Signed-off-by: Lee Jones --- include/linux/mfd/madera/pdata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/pdata.h b/include/linux/mfd/madera/pdata.h index 0b311f39c8f4..8dc852402dbb 100644 --- a/include/linux/mfd/madera/pdata.h +++ b/include/linux/mfd/madera/pdata.h @@ -24,7 +24,6 @@ struct gpio_desc; struct pinctrl_map; -struct madera_irqchip_pdata; struct madera_codec_pdata; /** -- cgit v1.2.3 From 55143439b7b501882bea9d95a54adfe00ffc79a3 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Tue, 28 Aug 2018 17:02:40 -0300 Subject: mfd: mc13xxx-core: Fix PMIC shutdown when reading ADC values When trying to read any MC13892 ADC channel on a imx51-babbage board: The MC13892 PMIC shutdowns completely. After debugging this issue and comparing the MC13892 and MC13783 initializations done in the vendor kernel, it was noticed that the CHRGRAWDIV bit of the ADC0 register was not being set. This bit is set by default after power on, but the driver was clearing it. After setting this bit it is possible to read the ADC values correctly. Signed-off-by: Fabio Estevam Tested-by: Chris Healy Signed-off-by: Lee Jones --- include/linux/mfd/mc13xxx.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h index 54a3cd808f9e..2ad9bdc0a5ec 100644 --- a/include/linux/mfd/mc13xxx.h +++ b/include/linux/mfd/mc13xxx.h @@ -249,6 +249,7 @@ struct mc13xxx_platform_data { #define MC13XXX_ADC0_TSMOD0 (1 << 12) #define MC13XXX_ADC0_TSMOD1 (1 << 13) #define MC13XXX_ADC0_TSMOD2 (1 << 14) +#define MC13XXX_ADC0_CHRGRAWDIV (1 << 15) #define MC13XXX_ADC0_ADINC1 (1 << 16) #define MC13XXX_ADC0_ADINC2 (1 << 17) -- cgit v1.2.3 From 9f8ddee1dab836ca758ca8fc555ab5a3aaa5d3fd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Aug 2018 19:52:52 +0300 Subject: mfd: intel_soc_pmic_bxtwc: Chain power button IRQs as well Power button IRQ actually has a second level of interrupts to distinguish between UI and POWER buttons. Moreover, current implementation looks awkward in approach to handle second level IRQs by first level related IRQ chip. To address above issues, split power button IRQ to be chained as well. Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg Signed-off-by: Lee Jones --- include/linux/mfd/intel_soc_pmic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 5aacdb017a9f..806a4f095312 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -25,6 +25,7 @@ struct intel_soc_pmic { int irq; struct regmap *regmap; struct regmap_irq_chip_data *irq_chip_data; + struct regmap_irq_chip_data *irq_chip_data_pwrbtn; struct regmap_irq_chip_data *irq_chip_data_tmu; struct regmap_irq_chip_data *irq_chip_data_bcu; struct regmap_irq_chip_data *irq_chip_data_adc; -- cgit v1.2.3 From 26c7e05a69d3843abb0e5389e7f538cd175c0f09 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Aug 2018 19:52:54 +0300 Subject: mfd: Convert Intel PMIC drivers to use SPDX identifier 1;5201;0c Reduce size of duplicated comments by switching to use SPDX identifier. No functional change. Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg Signed-off-by: Lee Jones --- include/linux/mfd/intel_msic.h | 7 ++----- include/linux/mfd/intel_soc_pmic.h | 12 ++---------- include/linux/mfd/intel_soc_pmic_bxtwc.h | 10 +--------- 3 files changed, 5 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/intel_msic.h b/include/linux/mfd/intel_msic.h index 439a7a617bc9..317e8608cf41 100644 --- a/include/linux/mfd/intel_msic.h +++ b/include/linux/mfd/intel_msic.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * include/linux/mfd/intel_msic.h - Core interface for Intel MSIC + * Core interface for Intel MSIC * * Copyright (C) 2011, Intel Corporation * Author: Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __LINUX_MFD_INTEL_MSIC_H__ diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 806a4f095312..ed1dfba5e5f9 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -1,17 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * intel_soc_pmic.h - Intel SoC PMIC Driver + * Intel SoC PMIC Driver * * Copyright (C) 2012-2014 Intel Corporation. All rights reserved. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Author: Yang, Bin * Author: Zhu, Lejun */ diff --git a/include/linux/mfd/intel_soc_pmic_bxtwc.h b/include/linux/mfd/intel_soc_pmic_bxtwc.h index 0c351bc85d2d..9be566cc58c6 100644 --- a/include/linux/mfd/intel_soc_pmic_bxtwc.h +++ b/include/linux/mfd/intel_soc_pmic_bxtwc.h @@ -1,16 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Header file for Intel Broxton Whiskey Cove PMIC * * Copyright (C) 2015 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #ifndef __INTEL_BXTWC_H__ -- cgit v1.2.3 From efddff27c886e729a7f84a7205bd84d7d4af7336 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 5 Sep 2018 13:54:07 +0200 Subject: mfd: max8997: Enale irq-wakeup unconditionally IRQ wake up support for MAX8997 driver was initially configured by respective property in pdata. However, after the driver conversion to device-tree, setting it was left as 'todo'. Nowadays most of other PMIC MFD drivers initialized from device-tree assume that they can be an irq wakeup source, so enable it also for MAX8997. This fixes support for wakeup from MAX8997 RTC alarm. Signed-off-by: Marek Szyprowski Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/max8997.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h index 3c4e920b4727..e955e2f0a2cc 100644 --- a/include/linux/mfd/max8997.h +++ b/include/linux/mfd/max8997.h @@ -165,7 +165,6 @@ struct max8997_led_platform_data { struct max8997_platform_data { /* IRQ */ int ono; - int wakeup; /* ---- PMIC ---- */ struct max8997_regulator_data *regulators; -- cgit v1.2.3 From 7a6a395b16c3fdcd2ede2b0ce4bf63f6dafc1fea Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Tue, 11 Sep 2018 23:01:33 +0200 Subject: mfd: ti-lmu: Switch to GPIOD Use new descriptor based API instead of the legacy one. Signed-off-by: Sebastian Reichel Signed-off-by: Pavel Machek Signed-off-by: Lee Jones --- include/linux/mfd/ti-lmu.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti-lmu.h b/include/linux/mfd/ti-lmu.h index 09d5f30384e5..1ef51ed36be5 100644 --- a/include/linux/mfd/ti-lmu.h +++ b/include/linux/mfd/ti-lmu.h @@ -16,6 +16,7 @@ #include #include #include +#include /* Notifier event */ #define LMU_EVENT_MONITOR_DONE 0x01 @@ -81,7 +82,7 @@ enum lm363x_regulator_id { struct ti_lmu { struct device *dev; struct regmap *regmap; - int en_gpio; + struct gpio_desc *en_gpio; struct blocking_notifier_head notifier; }; #endif -- cgit v1.2.3 From 07d02a67b7faae56e184f6c35f78de47f06da37f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 12 Oct 2018 13:28:26 -0400 Subject: SUNRPC: Simplify lookup code We no longer need to worry about whether or not the entry is hashed in order to figure out if the contents are valid. We only care whether or not the refcount is non-zero. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 2c97a3933ef9..a7fc8f5a2dad 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -206,11 +206,11 @@ bool rpcauth_cred_key_to_expire(struct rpc_auth *, struct rpc_cred *); char * rpcauth_stringify_acceptor(struct rpc_cred *); static inline -struct rpc_cred * get_rpccred(struct rpc_cred *cred) +struct rpc_cred *get_rpccred(struct rpc_cred *cred) { - if (cred != NULL) - atomic_inc(&cred->cr_count); - return cred; + if (cred != NULL && atomic_inc_not_zero(&cred->cr_count)) + return cred; + return NULL; } /** @@ -226,9 +226,7 @@ struct rpc_cred * get_rpccred(struct rpc_cred *cred) static inline struct rpc_cred * get_rpccred_rcu(struct rpc_cred *cred) { - if (atomic_inc_not_zero(&cred->cr_count)) - return cred; - return NULL; + return get_rpccred(cred); } #endif /* __KERNEL__ */ -- cgit v1.2.3 From 79b181810285a6b9b7a1aed25c365c9e1782e22a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 14 Oct 2018 10:34:31 -0400 Subject: SUNRPC: Convert auth creds to use refcount_t Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index a7fc8f5a2dad..a71d4bd191e7 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -67,7 +67,7 @@ struct rpc_cred { const struct rpc_credops *cr_ops; unsigned long cr_expire; /* when to gc */ unsigned long cr_flags; /* various flags */ - atomic_t cr_count; /* ref count */ + refcount_t cr_count; /* ref count */ kuid_t cr_uid; @@ -208,7 +208,7 @@ char * rpcauth_stringify_acceptor(struct rpc_cred *); static inline struct rpc_cred *get_rpccred(struct rpc_cred *cred) { - if (cred != NULL && atomic_inc_not_zero(&cred->cr_count)) + if (cred != NULL && refcount_inc_not_zero(&cred->cr_count)) return cred; return NULL; } -- cgit v1.2.3 From 331bc71cb1751d78f6807ad8e6162b07c67cdd1b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 14 Oct 2018 10:40:29 -0400 Subject: SUNRPC: Convert the auth cred cache to use refcount_t Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index a71d4bd191e7..c4db9424b63b 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -100,7 +100,7 @@ struct rpc_auth { * differ from the flavor in * au_ops->au_flavor in gss * case) */ - atomic_t au_count; /* Reference counter */ + refcount_t au_count; /* Reference counter */ struct rpc_cred_cache * au_credcache; /* per-flavor data */ -- cgit v1.2.3 From 00e23707442a75b404392cef1405ab4fd498de6b Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 22 Oct 2018 13:07:28 +0100 Subject: iov_iter: Use accessor function Use accessor functions to access an iterator's type and direction. This allows for the possibility of using some other method of determining the type of iterator than if-chains with bitwise-AND conditions. Signed-off-by: David Howells --- include/linux/uio.h | 48 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 422b1c01ee0d..fcabc959c794 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -21,7 +21,7 @@ struct kvec { size_t iov_len; }; -enum { +enum iter_type { ITER_IOVEC = 0, ITER_KVEC = 2, ITER_BVEC = 4, @@ -47,6 +47,36 @@ struct iov_iter { }; }; +static inline enum iter_type iov_iter_type(const struct iov_iter *i) +{ + return i->type & ~(READ | WRITE); +} + +static inline bool iter_is_iovec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_IOVEC; +} + +static inline bool iov_iter_is_kvec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_KVEC; +} + +static inline bool iov_iter_is_bvec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_BVEC; +} + +static inline bool iov_iter_is_pipe(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_PIPE; +} + +static inline unsigned char iov_iter_rw(const struct iov_iter *i) +{ + return i->type & (READ | WRITE); +} + /* * Total number of bytes covered by an iovec. * @@ -74,7 +104,8 @@ static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) } #define iov_for_each(iov, iter, start) \ - if (!((start).type & (ITER_BVEC | ITER_PIPE))) \ + if (iov_iter_type(start) == ITER_IOVEC || \ + iov_iter_type(start) == ITER_KVEC) \ for (iter = (start); \ (iter).count && \ ((iov = iov_iter_iovec(&(iter))), 1); \ @@ -202,19 +233,6 @@ static inline size_t iov_iter_count(const struct iov_iter *i) return i->count; } -static inline bool iter_is_iovec(const struct iov_iter *i) -{ - return !(i->type & (ITER_BVEC | ITER_KVEC | ITER_PIPE)); -} - -/* - * Get one of READ or WRITE out of iter->type without any other flags OR'd in - * with it. - * - * The ?: is just for type safety. - */ -#define iov_iter_rw(i) ((0 ? (struct iov_iter *)0 : (i))->type & (READ | WRITE)) - /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value -- cgit v1.2.3 From aa563d7bca6e882ec2bdae24603c8f016401a144 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 20 Oct 2018 00:57:56 +0100 Subject: iov_iter: Separate type from direction and use accessor functions In the iov_iter struct, separate the iterator type from the iterator direction and use accessor functions to access them in most places. Convert a bunch of places to use switch-statements to access them rather then chains of bitwise-AND statements. This makes it easier to add further iterator types. Also, this can be more efficient as to implement a switch of small contiguous integers, the compiler can use ~50% fewer compare instructions than it has to use bitwise-and instructions. Further, cease passing the iterator type into the iterator setup function. The iterator function can set that itself. Only the direction is required. Signed-off-by: David Howells --- include/linux/uio.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index fcabc959c794..3d8f1acc142c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -29,7 +29,7 @@ enum iter_type { }; struct iov_iter { - int type; + unsigned int type; size_t iov_offset; size_t count; union { @@ -212,13 +212,13 @@ size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); -void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, +void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); -void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *kvec, +void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); -void iov_iter_bvec(struct iov_iter *i, int direction, const struct bio_vec *bvec, +void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); -void iov_iter_pipe(struct iov_iter *i, int direction, struct pipe_inode_info *pipe, +void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); -- cgit v1.2.3 From 9ea9ce0427aab02a2fd88fc608267cf6952119f1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 20 Oct 2018 00:57:56 +0100 Subject: iov_iter: Add I/O discard iterator Add a new iterator, ITER_DISCARD, that can only be used in READ mode and just discards any data copied to it. This is useful in a network filesystem for discarding any unwanted data sent by a server. Signed-off-by: David Howells --- include/linux/uio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 3d8f1acc142c..55ce99ddb912 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -26,6 +26,7 @@ enum iter_type { ITER_KVEC = 2, ITER_BVEC = 4, ITER_PIPE = 8, + ITER_DISCARD = 16, }; struct iov_iter { @@ -72,6 +73,11 @@ static inline bool iov_iter_is_pipe(const struct iov_iter *i) return iov_iter_type(i) == ITER_PIPE; } +static inline bool iov_iter_is_discard(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_DISCARD; +} + static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->type & (READ | WRITE); @@ -220,6 +226,7 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_ unsigned long nr_segs, size_t count); void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); +void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, -- cgit v1.2.3 From 721fb6fbfd2132164c2e8777cc837f9b2c1794dc Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 17 Oct 2018 13:07:05 +0200 Subject: fsnotify: Fix busy inodes during unmount Detaching of mark connector from fsnotify_put_mark() can race with unmounting of the filesystem like: CPU1 CPU2 fsnotify_put_mark() spin_lock(&conn->lock); ... inode = fsnotify_detach_connector_from_object(conn) spin_unlock(&conn->lock); generic_shutdown_super() fsnotify_unmount_inodes() sees connector detached for inode -> nothing to do evict_inode() barfs on pending inode reference iput(inode); Resulting in "Busy inodes after unmount" message and possible kernel oops. Make fsnotify_unmount_inodes() properly wait for outstanding inode references from detached connectors. Note that the accounting of outstanding inode references in the superblock can cause some cacheline contention on the counter. OTOH it happens only during deletion of the last notification mark from an inode (or during unlinking of watched inode) and that is not too bad. I have measured time to create & delete inotify watch 100000 times from 64 processes in parallel (each process having its own inotify group and its own file on a shared superblock) on a 64 CPU machine. Average and standard deviation of 15 runs look like: Avg Stddev Vanilla 9.817400 0.276165 Fixed 9.710467 0.228294 So there's no statistically significant difference. Fixes: 6b3f05d24d35 ("fsnotify: Detach mark from object list when last reference is dropped") CC: stable@vger.kernel.org Signed-off-by: Jan Kara --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6da94deb957f..00b23b21e78a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1437,6 +1437,9 @@ struct super_block { /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; + /* Pending fsnotify inode refs */ + atomic_long_t s_fsnotify_inode_refs; + /* Being remounted read-only */ int s_readonly_remount; -- cgit v1.2.3 From a7fe5190c03f8137ef08db84a58dd4daf2c4785d Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 4 Oct 2018 14:04:03 +0200 Subject: cpuidle: menu: Remove get_loadavg() from the performance multiplier The function get_loadavg() returns almost always zero. To be more precise, statistically speaking for a total of 1023379 times passing in the function, the load is equal to zero 1020728 times, greater than 100, 610 times, the remaining is between 0 and 5. In 2011, the get_loadavg() was removed from the Android tree because of the above [1]. At this time, the load was: unsigned long this_cpu_load(void) { struct rq *this = this_rq(); return this->cpu_load[0]; } In 2014, the code was changed by commit 372ba8cb46b2 (cpuidle: menu: Lookup CPU runqueues less) and the load is: void get_iowait_load(unsigned long *nr_waiters, unsigned long *load) { struct rq *rq = this_rq(); *nr_waiters = atomic_read(&rq->nr_iowait); *load = rq->load.weight; } with the same result. Both measurements show using the load in this code path does no matter anymore. Removing it. [1] https://android.googlesource.com/kernel/common/+/4dedd9f124703207895777ac6e91dacde0f7cc17 Signed-off-by: Daniel Lezcano Acked-by: Mel Gorman Acked-by: Peter Zijlstra (Intel) Signed-off-by: Rafael J. Wysocki --- include/linux/sched/stat.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h index 04f1321d14c4..f30954cc059d 100644 --- a/include/linux/sched/stat.h +++ b/include/linux/sched/stat.h @@ -20,7 +20,6 @@ extern unsigned long nr_running(void); extern bool single_task_running(void); extern unsigned long nr_iowait(void); extern unsigned long nr_iowait_cpu(int cpu); -extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); static inline int sched_info_on(void) { -- cgit v1.2.3 From a91e138022bc29b5d2bbc56b41de3e0db6261e28 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:43 +0900 Subject: block: Introduce blkdev_nr_zones() helper Introduce the blkdev_nr_zones() helper function to get the total number of zones of a zoned block device. This number is always 0 for a regular block device (q->limits.zoned == BLK_ZONED_NONE case). Replace hard-coded number of zones calculation in dmz_get_zoned_device() with a call to this helper. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7d423721b327..ca5fdc1b7745 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -401,6 +401,7 @@ struct blk_zone_report_hdr { u8 padding[60]; }; +extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, unsigned int *nr_zones, gfp_t gfp_mask); @@ -414,6 +415,10 @@ extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, #else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int blkdev_nr_zones(struct block_device *bdev) +{ + return 0; +} static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) -- cgit v1.2.3 From 965b652e901886ea54f93c60027b5be76328d958 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:48 +0900 Subject: block: Expose queue nr_zones in sysfs Expose through sysfs the nr_zones field of struct request_queue. Exposing this value helps in debugging disk issues as well as facilitating scripts based use of the disk (e.g. blktests). For zoned block devices, the nr_zones field indicates the total number of zones of the device calculated using the known disk capacity and zone size. This number of zones is always 0 for regular block devices. Since nr_zones is defined conditionally with CONFIG_BLK_DEV_ZONED, introduce the blk_queue_nr_zones() function to return the correct value for any device, regardless if CONFIG_BLK_DEV_ZONED is set. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ca5fdc1b7745..6bb845f9601a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -811,6 +811,11 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) } #ifdef CONFIG_BLK_DEV_ZONED +static inline unsigned int blk_queue_nr_zones(struct request_queue *q) +{ + return blk_queue_is_zoned(q) ? q->nr_zones : 0; +} + static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { @@ -826,6 +831,11 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q, return false; return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap); } +#else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int blk_queue_nr_zones(struct request_queue *q) +{ + return 0; +} #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) -- cgit v1.2.3 From e76239a3748c90a8b0e197f8f4544a8ce52f126e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 Oct 2018 19:08:49 +0900 Subject: block: add a report_zones method Dispatching a report zones command through the request queue is a major pain due to the command reply payload rewriting necessary. Given that blkdev_report_zones() is executing everything synchronously, implement report zones as a block device file operation instead, allowing major simplification of the code in many places. sd, null-blk, dm-linear and dm-flakey being the only block device drivers supporting exposing zoned block devices, these drivers are modified to provide the device side implementation of the report_zones() block device file operation. For device mappers, a new report_zones() target type operation is defined so that the upper block layer calls blkdev_report_zones() can be propagated down to the underlying devices of the dm targets. Implementation for this new operation is added to the dm-linear and dm-flakey targets. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig [Damien] * Changed method block_device argument to gendisk * Various bug fixes and improvements * Added support for null_blk, dm-linear and dm-flakey. Reviewed-by: Martin K. Petersen Reviewed-by: Mike Snitzer Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 -- include/linux/blkdev.h | 8 +++----- include/linux/device-mapper.h | 12 ++++++++++-- 3 files changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 9578c7ab1eb6..093a818c5b68 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -283,8 +283,6 @@ enum req_opf { REQ_OP_FLUSH = 2, /* discard sectors */ REQ_OP_DISCARD = 3, - /* get zone information */ - REQ_OP_ZONE_REPORT = 4, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, /* seset a zone write pointer */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6bb845f9601a..51fe6472ce02 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -396,11 +396,6 @@ struct queue_limits { #ifdef CONFIG_BLK_DEV_ZONED -struct blk_zone_report_hdr { - unsigned int nr_zones; - u8 padding[60]; -}; - extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, @@ -1867,6 +1862,9 @@ struct block_device_operations { int (*getgeo)(struct block_device *, struct hd_geometry *); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); + int (*report_zones)(struct gendisk *, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask); struct module *owner; const struct pr_ops *pr_ops; }; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 6fb0808e87c8..a23b396a8edc 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -92,6 +92,11 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv, typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev); +typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector, + struct blk_zone *zones, + unsigned int *nr_zones, + gfp_t gfp_mask); + /* * These iteration functions are typically used to check (and combine) * properties of underlying devices. @@ -180,6 +185,9 @@ struct target_type { dm_status_fn status; dm_message_fn message; dm_prepare_ioctl_fn prepare_ioctl; +#ifdef CONFIG_BLK_DEV_ZONED + dm_report_zones_fn report_zones; +#endif dm_busy_fn busy; dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; @@ -420,8 +428,8 @@ struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); -void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, - sector_t start); +void dm_remap_zone_report(struct dm_target *ti, sector_t start, + struct blk_zone *zones, unsigned int *nr_zones); union map_info *dm_get_rq_mapinfo(struct request *rq); struct queue_limits *dm_get_queue_limits(struct mapped_device *md); -- cgit v1.2.3 From bf5054569653c491ece544cc7ee333ae53b47121 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:50 +0900 Subject: block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Mike Snitzer Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 51fe6472ce02..4293dc1cd160 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -402,6 +402,7 @@ extern int blkdev_report_zones(struct block_device *bdev, unsigned int *nr_zones, gfp_t gfp_mask); extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); +extern int blk_revalidate_disk_zones(struct gendisk *disk); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); @@ -414,6 +415,12 @@ static inline unsigned int blkdev_nr_zones(struct block_device *bdev) { return 0; } + +static inline int blk_revalidate_disk_zones(struct gendisk *disk) +{ + return 0; +} + static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) -- cgit v1.2.3 From ede95a63b5e84ddeea6b0c473b36ab8bfd8c6ce3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 23 Oct 2018 01:11:04 +0200 Subject: bpf: add bpf_jit_limit knob to restrict unpriv allocations Rick reported that the BPF JIT could potentially fill the entire module space with BPF programs from unprivileged users which would prevent later attempts to load normal kernel modules or privileged BPF programs, for example. If JIT was enabled but unsuccessful to generate the image, then before commit 290af86629b2 ("bpf: introduce BPF_JIT_ALWAYS_ON config") we would always fall back to the BPF interpreter. Nowadays in the case where the CONFIG_BPF_JIT_ALWAYS_ON could be set, then the load will abort with a failure since the BPF interpreter was compiled out. Add a global limit and enforce it for unprivileged users such that in case of BPF interpreter compiled out we fail once the limit has been reached or we fall back to BPF interpreter earlier w/o using module mem if latter was compiled in. In a next step, fair share among unprivileged users can be resolved in particular for the case where we would fail hard once limit is reached. Fixes: 290af86629b2 ("bpf: introduce BPF_JIT_ALWAYS_ON config") Fixes: 0a14842f5a3c ("net: filter: Just In Time compiler for x86-64") Co-Developed-by: Rick Edgecombe Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Cc: Eric Dumazet Cc: Jann Horn Cc: Kees Cook Cc: LKML Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 91b4c934f02e..de629b706d1d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -854,6 +854,7 @@ bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; +extern int bpf_jit_limit; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); -- cgit v1.2.3 From 70025f84e5b79627a6739533c4fe7cef5b605886 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 9 Oct 2018 17:46:51 +0100 Subject: KEYS: Provide key type operations for asymmetric key ops [ver #2] Provide five new operations in the key_type struct that can be used to provide access to asymmetric key operations. These will be implemented for the asymmetric key type in a later patch and may refer to a key retained in RAM by the kernel or a key retained in crypto hardware. int (*asym_query)(const struct kernel_pkey_params *params, struct kernel_pkey_query *info); int (*asym_eds_op)(struct kernel_pkey_params *params, const void *in, void *out); int (*asym_verify_signature)(struct kernel_pkey_params *params, const void *in, const void *in2); Since encrypt, decrypt and sign are identical in their interfaces, they're rolled together in the asym_eds_op() operation and there's an operation ID in the params argument to distinguish them. Verify is different in that we supply the data and the signature instead and get an error value (or 0) as the only result on the expectation that this may well be how a hardware crypto device may work. Signed-off-by: David Howells Tested-by: Marcel Holtmann Reviewed-by: Marcel Holtmann Reviewed-by: Denis Kenzior Tested-by: Denis Kenzior Signed-off-by: James Morris --- include/linux/key-type.h | 11 +++++++++++ include/linux/keyctl.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100644 include/linux/keyctl.h (limited to 'include/linux') diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 05d8fb5a06c4..bc9af551fc83 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -17,6 +17,9 @@ #ifdef CONFIG_KEYS +struct kernel_pkey_query; +struct kernel_pkey_params; + /* * key under-construction record * - passed to the request_key actor if supplied @@ -155,6 +158,14 @@ struct key_type { */ struct key_restriction *(*lookup_restriction)(const char *params); + /* Asymmetric key accessor functions. */ + int (*asym_query)(const struct kernel_pkey_params *params, + struct kernel_pkey_query *info); + int (*asym_eds_op)(struct kernel_pkey_params *params, + const void *in, void *out); + int (*asym_verify_signature)(struct kernel_pkey_params *params, + const void *in, const void *in2); + /* internal fields */ struct list_head link; /* link in types list */ struct lock_class_key lock_class; /* key->sem lock class */ diff --git a/include/linux/keyctl.h b/include/linux/keyctl.h new file mode 100644 index 000000000000..c7c48c79ce0e --- /dev/null +++ b/include/linux/keyctl.h @@ -0,0 +1,46 @@ +/* keyctl kernel bits + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef __LINUX_KEYCTL_H +#define __LINUX_KEYCTL_H + +#include + +struct kernel_pkey_query { + __u32 supported_ops; /* Which ops are supported */ + __u32 key_size; /* Size of the key in bits */ + __u16 max_data_size; /* Maximum size of raw data to sign in bytes */ + __u16 max_sig_size; /* Maximum size of signature in bytes */ + __u16 max_enc_size; /* Maximum size of encrypted blob in bytes */ + __u16 max_dec_size; /* Maximum size of decrypted blob in bytes */ +}; + +enum kernel_pkey_operation { + kernel_pkey_encrypt, + kernel_pkey_decrypt, + kernel_pkey_sign, + kernel_pkey_verify, +}; + +struct kernel_pkey_params { + struct key *key; + const char *encoding; /* Encoding (eg. "oaep" or "raw" for none) */ + const char *hash_algo; /* Digest algorithm used (eg. "sha1") or NULL if N/A */ + char *info; /* Modified info string to be released later */ + __u32 in_len; /* Input data size */ + union { + __u32 out_len; /* Output buffer size (enc/dec/sign) */ + __u32 in2_len; /* 2nd input data size (verify) */ + }; + enum kernel_pkey_operation op : 8; +}; + +#endif /* __LINUX_KEYCTL_H */ -- cgit v1.2.3 From 4d54954a197175c0dcb3c82af0c0740d0c5f827a Mon Sep 17 00:00:00 2001 From: Sebastien Boisvert Date: Fri, 26 Oct 2018 15:02:23 -0700 Subject: include/linux/pfn_t.h: force '~' to be parsed as an unary operator Tracing the event "fs_dax:dax_pmd_insert_mapping" with perf produces this warning: [fs_dax:dax_pmd_insert_mapping] unknown op '~' It is printed in process_op (tools/lib/traceevent/event-parse.c) because '~' is parsed as a binary operator. perf reads the format of fs_dax:dax_pmd_insert_mapping ("print fmt") from /sys/kernel/debug/tracing/events/fs_dax/dax_pmd_insert_mapping/format . The format contains: ~(((u64) ~(~(((1UL) << 12)-1))) ^ \ interpreted as a binary operator by process_op(). This part is generated in the declaration of the event class dax_pmd_insert_mapping_class in include/trace/events/fs_dax.h : __print_flags_u64(__entry->pfn_val & PFN_FLAGS_MASK, "|", PFN_FLAGS_TRACE), This patch adds a pair of parentheses in the declaration of PFN_FLAGS_MASK to make sure that '~' is parsed as a unary operator by perf. The part of the format that was problematic is now: ~(((u64) (~(~(((1UL) << 12)-1)))) Now, all the '~' are parsed as unary operators. Link: http://lkml.kernel.org/r/20181021145939.8760-1-sebhtml@videotron.qc.ca Signed-off-by: Sebastien Boisvert Acked-by: Dan Williams Cc: "Steven Rostedt (VMware)" Cc: Arnaldo Carvalho de Melo Cc: "Tzvetomir Stoyanov (VMware)" Cc: Namhyung Kim Cc: Ross Zwisler Cc: Elenie Godzaridis Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pfn_t.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 21713dc14ce2..673546ba7342 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -10,7 +10,7 @@ * PFN_DEV - pfn is not covered by system memmap by default * PFN_MAP - pfn has a dynamic page mapping established by a device driver */ -#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) +#define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1)) #define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2)) #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3)) -- cgit v1.2.3 From 74f213ea25b99fddcf34cbe07dabdb01136bcd86 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 26 Oct 2018 15:02:27 -0700 Subject: include/linux/linkage.h: align weak symbols Since WEAK() supposed to be used instead of ENTRY() to define weak symbols, but unlike ENTRY() it doesn't have ALIGN directive. It seems there is no actual reason to not have, so let's add ALIGN to WEAK() too. Link: http://lkml.kernel.org/r/20180920135631.23833-1-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Will Deacon , Catalin Marinas Cc: Kyeongdon Kim Cc: Ard Biesheuvel Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Mark Rutland Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/linkage.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index d7618c41f74c..7c47b1a471d4 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -90,6 +90,7 @@ #ifndef WEAK #define WEAK(name) \ .weak name ASM_NL \ + ALIGN ASM_NL \ name: #endif -- cgit v1.2.3 From 5780a02fd1e87641ad6a8dd6891a1e890cf45c5d Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Fri, 26 Oct 2018 15:02:59 -0700 Subject: fs/iomap.c: change return type to vm_fault_t Change iomap_page_mkwrite() return type to vm_fault_t. see commit 1c8f422059ae ("mm: change return type to vm_fault_t") for reference. Link: http://lkml.kernel.org/r/20180827172050.GA18673@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Matthew Wilcox Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/iomap.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 3555d54bf79a..9a4258154b25 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -6,6 +6,7 @@ #include #include #include +#include struct address_space; struct fiemap_extent_info; @@ -141,7 +142,8 @@ int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); -int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); +vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, + const struct iomap_ops *ops); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, const struct iomap_ops *ops); loff_t iomap_seek_hole(struct inode *inode, loff_t offset, -- cgit v1.2.3 From 9b6f7e163cd0f468d1b9696b785659d3c27c8667 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:03:19 -0700 Subject: mm: rework memcg kernel stack accounting If CONFIG_VMAP_STACK is set, kernel stacks are allocated using __vmalloc_node_range() with __GFP_ACCOUNT. So kernel stack pages are charged against corresponding memory cgroups on allocation and uncharged on releasing them. The problem is that we do cache kernel stacks in small per-cpu caches and do reuse them for new tasks, which can belong to different memory cgroups. Each stack page still holds a reference to the original cgroup, so the cgroup can't be released until the vmap area is released. To make this happen we need more than two subsequent exits without forks in between on the current cpu, which makes it very unlikely to happen. As a result, I saw a significant number of dying cgroups (in theory, up to 2 * number_of_cpu + number_of_tasks), which can't be released even by significant memory pressure. As a cgroup structure can take a significant amount of memory (first of all, per-cpu data like memcg statistics), it leads to a noticeable waste of memory. Link: http://lkml.kernel.org/r/20180827162621.30187-1-guro@fb.com Fixes: ac496bf48d97 ("fork: Optimize task creation by caching two thread stacks per CPU if CONFIG_VMAP_STACK=y") Signed-off-by: Roman Gushchin Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Andy Lutomirski Cc: Konstantin Khlebnikov Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 652f602167df..4399cc3f00e4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1268,10 +1268,11 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); void memcg_kmem_put_cache(struct kmem_cache *cachep); int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, struct mem_cgroup *memcg); + +#ifdef CONFIG_MEMCG_KMEM int memcg_kmem_charge(struct page *page, gfp_t gfp, int order); void memcg_kmem_uncharge(struct page *page, int order); -#ifdef CONFIG_MEMCG_KMEM extern struct static_key_false memcg_kmem_enabled_key; extern struct workqueue_struct *memcg_kmem_cache_wq; @@ -1307,6 +1308,16 @@ extern int memcg_expand_shrinker_maps(int new_id); extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); #else + +static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +{ + return 0; +} + +static inline void memcg_kmem_uncharge(struct page *page, int order) +{ +} + #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) -- cgit v1.2.3 From 68600f623d69da428c6163275f97ca126e1a8ec5 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:03:27 -0700 Subject: mm: don't miss the last page because of round-off error I've noticed, that dying memory cgroups are often pinned in memory by a single pagecache page. Even under moderate memory pressure they sometimes stayed in such state for a long time. That looked strange. My investigation showed that the problem is caused by applying the LRU pressure balancing math: scan = div64_u64(scan * fraction[lru], denominator), where denominator = fraction[anon] + fraction[file] + 1. Because fraction[lru] is always less than denominator, if the initial scan size is 1, the result is always 0. This means the last page is not scanned and has no chances to be reclaimed. Fix this by rounding up the result of the division. In practice this change significantly improves the speed of dying cgroups reclaim. [guro@fb.com: prevent double calculation of DIV64_U64_ROUND_UP() arguments] Link: http://lkml.kernel.org/r/20180829213311.GA13501@castle Link: http://lkml.kernel.org/r/20180827162621.30187-3-guro@fb.com Signed-off-by: Roman Gushchin Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Rik van Riel Cc: Konstantin Khlebnikov Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/math64.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 837f2f2d1d34..bb2c84afb80c 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -281,4 +281,7 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) } #endif /* mul_u64_u32_div */ +#define DIV64_U64_ROUND_UP(ll, d) \ + ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) + #endif /* _LINUX_MATH64_H */ -- cgit v1.2.3 From 33490af3f5c15757448b6c454ca93b48a333aa1b Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 26 Oct 2018 15:03:35 -0700 Subject: mm, mmu_notifier: be explicit about range invalition non-blocking mode If invalidate_range_start() is called for !blocking mode then all callbacks have to guarantee they will no block/sleep. The same obviously applies to invalidate_range_end because this operation pairs with the former and they are called from the same context. Make sure this is appropriately documented. Link: http://lkml.kernel.org/r/20180827112623.8992-3-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Jerome Glisse Cc: Boris Ostrovsky Cc: David Rientjes Cc: Juergen Gross Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 133ba78820ee..698e371aafe3 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -153,7 +153,9 @@ struct mmu_notifier_ops { * * If blockable argument is set to false then the callback cannot * sleep and has to return with -EAGAIN. 0 should be returned - * otherwise. + * otherwise. Please note that if invalidate_range_start approves + * a non-blocking behavior then the same applies to + * invalidate_range_end. * */ int (*invalidate_range_start)(struct mmu_notifier *mn, -- cgit v1.2.3 From 4e15a073a168b62311db911a55c4d4f1500c2821 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 26 Oct 2018 15:03:39 -0700 Subject: Revert "mm, mmu_notifier: annotate mmu notifiers with blockable invalidate callbacks" Revert 5ff7091f5a2ca ("mm, mmu_notifier: annotate mmu notifiers with blockable invalidate callbacks"). MMU_INVALIDATE_DOES_NOT_BLOCK flags was the only one used and it is no longer needed since 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers"). We now have a full support for per range !blocking behavior so we can drop the stop gap workaround which the per notifier flag was used for. Link: http://lkml.kernel.org/r/20180827112623.8992-4-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: David Rientjes Cc: Boris Ostrovsky Cc: Jerome Glisse Cc: Juergen Gross Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 698e371aafe3..9893a6432adf 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -2,7 +2,6 @@ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H -#include #include #include #include @@ -11,9 +10,6 @@ struct mmu_notifier; struct mmu_notifier_ops; -/* mmu_notifier_ops flags */ -#define MMU_INVALIDATE_DOES_NOT_BLOCK (0x01) - #ifdef CONFIG_MMU_NOTIFIER /* @@ -30,15 +26,6 @@ struct mmu_notifier_mm { }; struct mmu_notifier_ops { - /* - * Flags to specify behavior of callbacks for this MMU notifier. - * Used to determine which context an operation may be called. - * - * MMU_INVALIDATE_DOES_NOT_BLOCK: invalidate_range_* callbacks do not - * block - */ - int flags; - /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are @@ -183,10 +170,6 @@ struct mmu_notifier_ops { * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if * called between those functions. - * - * If this callback cannot block, and invalidate_range_{start,end} - * cannot block, mmu_notifier_ops.flags should have - * MMU_INVALIDATE_DOES_NOT_BLOCK set. */ void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end); @@ -241,7 +224,6 @@ extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, bool only_end); extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end); -extern bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm); static inline void mmu_notifier_release(struct mm_struct *mm) { @@ -495,11 +477,6 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, { } -static inline bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm) -{ - return false; -} - static inline void mmu_notifier_mm_init(struct mm_struct *mm) { } -- cgit v1.2.3 From 5d7476374564645b1a2d299e242ad7b17b1104ee Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:10 -0700 Subject: mm: remove vm_insert_mixed() All callers are now converted to vmf_insert_mixed() so convert vmf_insert_mixed() from being a compatibility wrapper into the real function. Link: http://lkml.kernel.org/r/20180828145728.11873-3-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index daa2b8f1e9a8..ecc6f9347756 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2506,7 +2506,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); -int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); @@ -2525,19 +2525,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -static inline vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, - unsigned long addr, pfn_t pfn) -{ - int err = vm_insert_mixed(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { -- cgit v1.2.3 From f5e6d1d5f8f3080aa7a51acea1f77085f45abe9c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:13 -0700 Subject: mm: introduce vmf_insert_pfn_prot() Like vm_insert_pfn_prot(), but returns a vm_fault_t instead of an errno. Also unexport vm_insert_pfn_prot as it has no modular users. Link: http://lkml.kernel.org/r/20180828145728.11873-4-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ecc6f9347756..f1293bdc6de2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2506,6 +2506,8 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); +vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, -- cgit v1.2.3 From bc12e6ad9617831727e4201e7cbf5c3b868cc8fd Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:21 -0700 Subject: mm: make vm_insert_pfn_prot() static Now this is no longer used outside mm/memory.c, make it static. Link: http://lkml.kernel.org/r/20180828145728.11873-6-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f1293bdc6de2..0f5db0455e61 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2504,8 +2504,6 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr, int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); -int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, -- cgit v1.2.3 From 67fa1666223d7c825f6651add97f0011fe155f36 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:26 -0700 Subject: mm: remove references to vm_insert_pfn() Documentation and comments. Link: http://lkml.kernel.org/r/20180828145728.11873-7-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 4c92e3ba3e16..dde947083d4e 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -107,7 +107,7 @@ enum hmm_pfn_flag_e { * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory * HMM_PFN_NONE: corresponding CPU page table entry is pte_none() * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the - * result of vm_insert_pfn() or vm_insert_page(). Therefore, it should not + * result of vmf_insert_pfn() or vm_insert_page(). Therefore, it should not * be mirrored by a device, because the entry will never have HMM_PFN_VALID * set and the pfn value is undefined. * -- cgit v1.2.3 From ae2b01f37044c10e975d22116755df56252b09d8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:29 -0700 Subject: mm: remove vm_insert_pfn() All callers are now converted to vmf_insert_pfn() so convert vmf_insert_pfn() from being a compatibility wrapper around vm_insert_pfn() to being a compatibility wrapper around vmf_insert_pfn_prot(). Link: http://lkml.kernel.org/r/20180828145728.11873-8-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0f5db0455e61..737279bb479c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2502,7 +2502,7 @@ struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); @@ -2525,19 +2525,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, - unsigned long addr, unsigned long pfn) -{ - int err = vm_insert_pfn(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) -- cgit v1.2.3 From cc252eae85e09552f9c1e7ac0c3227f835efdf2d Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:34 -0700 Subject: mm, slab: combine kmalloc_caches and kmalloc_dma_caches Patch series "kmalloc-reclaimable caches", v4. As discussed at LSF/MM [1] here's a patchset that introduces kmalloc-reclaimable caches (more details in the second patch) and uses them for dcache external names. That allows us to repurpose the NR_INDIRECTLY_RECLAIMABLE_BYTES counter later in the series. With patch 3/6, dcache external names are allocated from kmalloc-rcl-* caches, eliminating the need for manual accounting. More importantly, it also ensures the reclaimable kmalloc allocations are grouped in pages separate from the regular kmalloc allocations. The need for proper accounting of dcache external names has shown it's easy for misbehaving process to allocate lots of them, causing premature OOMs. Without the added grouping, it's likely that a similar workload can interleave the dcache external names allocations with regular kmalloc allocations (note: I haven't searched myself for an example of such regular kmalloc allocation, but I would be very surprised if there wasn't some). A pathological case would be e.g. one 64byte regular allocations with 63 external dcache names in a page (64x64=4096), which means the page is not freed even after reclaiming after all dcache names, and the process can thus "steal" the whole page with single 64byte allocation. If other kmalloc users similar to dcache external names become identified, they can also benefit from the new functionality simply by adding __GFP_RECLAIMABLE to the kmalloc calls. Side benefits of the patchset (that could be also merged separately) include removed branch for detecting __GFP_DMA kmalloc(), and shortening kmalloc cache names in /proc/slabinfo output. The latter is potentially an ABI break in case there are tools parsing the names and expecting the values to be in bytes. This is how /proc/slabinfo looks like after booting in virtme: ... kmalloc-rcl-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0 ... kmalloc-rcl-96 7 32 128 32 1 : tunables 120 60 8 : slabdata 1 1 0 kmalloc-rcl-64 25 128 64 64 1 : tunables 120 60 8 : slabdata 2 2 0 kmalloc-rcl-32 0 0 32 124 1 : tunables 120 60 8 : slabdata 0 0 0 kmalloc-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0 kmalloc-2M 0 0 2097152 1 512 : tunables 1 1 0 : slabdata 0 0 0 kmalloc-1M 0 0 1048576 1 256 : tunables 1 1 0 : slabdata 0 0 0 ... /proc/vmstat with renamed nr_indirectly_reclaimable_bytes counter: ... nr_slab_reclaimable 2817 nr_slab_unreclaimable 1781 ... nr_kernel_misc_reclaimable 0 ... /proc/meminfo with new KReclaimable counter: ... Shmem: 564 kB KReclaimable: 11260 kB Slab: 18368 kB SReclaimable: 11260 kB SUnreclaim: 7108 kB KernelStack: 1248 kB ... This patch (of 6): The kmalloc caches currently mainain separate (optional) array kmalloc_dma_caches for __GFP_DMA allocations. There are tests for __GFP_DMA in the allocation hotpaths. We can avoid the branches by combining kmalloc_caches and kmalloc_dma_caches into a single two-dimensional array where the outer dimension is cache "type". This will also allow to add kmalloc-reclaimable caches as a third type. Link: http://lkml.kernel.org/r/20180731090649.16028-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: Michal Hocko Cc: Johannes Weiner Cc: David Rientjes Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Laura Abbott Cc: Sumit Semwal Cc: Vijayanand Jitta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 42 +++++++++++++++++++++++++++++++----------- 1 file changed, 31 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index ed9cbddeb4a6..2a7137043e91 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -295,12 +295,29 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) +enum kmalloc_cache_type { + KMALLOC_NORMAL = 0, +#ifdef CONFIG_ZONE_DMA + KMALLOC_DMA, +#endif + NR_KMALLOC_TYPES +}; + #ifndef CONFIG_SLOB -extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; +extern struct kmem_cache * +kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; + +static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) +{ + int is_dma = 0; + #ifdef CONFIG_ZONE_DMA -extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; + is_dma = !!(flags & __GFP_DMA); #endif + return is_dma; +} + /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. @@ -501,18 +518,20 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { +#ifndef CONFIG_SLOB + unsigned int index; +#endif if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); #ifndef CONFIG_SLOB - if (!(flags & GFP_DMA)) { - unsigned int index = kmalloc_index(size); + index = kmalloc_index(size); - if (!index) - return ZERO_SIZE_PTR; + if (!index) + return ZERO_SIZE_PTR; - return kmem_cache_alloc_trace(kmalloc_caches[index], - flags, size); - } + return kmem_cache_alloc_trace( + kmalloc_caches[kmalloc_type(flags)][index], + flags, size); #endif } return __kmalloc(size, flags); @@ -542,13 +561,14 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) { + size <= KMALLOC_MAX_CACHE_SIZE) { unsigned int i = kmalloc_index(size); if (!i) return ZERO_SIZE_PTR; - return kmem_cache_alloc_node_trace(kmalloc_caches[i], + return kmem_cache_alloc_node_trace( + kmalloc_caches[kmalloc_type(flags)][i], flags, node, size); } #endif -- cgit v1.2.3 From 1291523f2c1d631fea34102fd241fb54a4e8f7a0 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:38 -0700 Subject: mm, slab/slub: introduce kmalloc-reclaimable caches Kmem caches can be created with a SLAB_RECLAIM_ACCOUNT flag, which indicates they contain objects which can be reclaimed under memory pressure (typically through a shrinker). This makes the slab pages accounted as NR_SLAB_RECLAIMABLE in vmstat, which is reflected also the MemAvailable meminfo counter and in overcommit decisions. The slab pages are also allocated with __GFP_RECLAIMABLE, which is good for anti-fragmentation through grouping pages by mobility. The generic kmalloc-X caches are created without this flag, but sometimes are used also for objects that can be reclaimed, which due to varying size cannot have a dedicated kmem cache with SLAB_RECLAIM_ACCOUNT flag. A prominent example are dcache external names, which prompted the creation of a new, manually managed vmstat counter NR_INDIRECTLY_RECLAIMABLE_BYTES in commit f1782c9bc547 ("dcache: account external names as indirectly reclaimable memory"). To better handle this and any other similar cases, this patch introduces SLAB_RECLAIM_ACCOUNT variants of kmalloc caches, named kmalloc-rcl-X. They are used whenever the kmalloc() call passes __GFP_RECLAIMABLE among gfp flags. They are added to the kmalloc_caches array as a new type. Allocations with both __GFP_DMA and __GFP_RECLAIMABLE will use a dma type cache. This change only applies to SLAB and SLUB, not SLOB. This is fine, since SLOB's target are tiny system and this patch does add some overhead of kmem management objects. Link: http://lkml.kernel.org/r/20180731090649.16028-3-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Laura Abbott Cc: Matthew Wilcox Cc: Michal Hocko Cc: Sumit Semwal Cc: Vijayanand Jitta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 2a7137043e91..918f374e7156 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -295,8 +295,13 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) +/* + * Whenever changing this, take care of that kmalloc_type() and + * create_kmalloc_caches() still work as intended. + */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, + KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif @@ -310,12 +315,21 @@ kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { int is_dma = 0; + int type_dma = 0; + int is_reclaimable; #ifdef CONFIG_ZONE_DMA is_dma = !!(flags & __GFP_DMA); + type_dma = is_dma * KMALLOC_DMA; #endif - return is_dma; + is_reclaimable = !!(flags & __GFP_RECLAIMABLE); + + /* + * If an allocation is both __GFP_DMA and __GFP_RECLAIMABLE, return + * KMALLOC_DMA and effectively ignore __GFP_RECLAIMABLE + */ + return type_dma + (is_reclaimable & !is_dma) * KMALLOC_RECLAIM; } /* -- cgit v1.2.3 From b29940c1abd7a4c3abeb926df0a5ec84d6902d47 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:46 -0700 Subject: mm: rename and change semantics of nr_indirectly_reclaimable_bytes The vmstat counter NR_INDIRECTLY_RECLAIMABLE_BYTES was introduced by commit eb59254608bc ("mm: introduce NR_INDIRECTLY_RECLAIMABLE_BYTES") with the goal of accounting objects that can be reclaimed, but cannot be allocated via a SLAB_RECLAIM_ACCOUNT cache. This is now possible via kmalloc() with __GFP_RECLAIMABLE flag, and the dcache external names user is converted. The counter is however still useful for accounting direct page allocations (i.e. not slab) with a shrinker, such as the ION page pool. So keep it, and: - change granularity to pages to be more like other counters; sub-page allocations should be able to use kmalloc - rename the counter to NR_KERNEL_MISC_RECLAIMABLE - expose the counter again in vmstat as "nr_kernel_misc_reclaimable"; we can again remove the check for not printing "hidden" counters Link: http://lkml.kernel.org/r/20180731090649.16028-5-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: Vijayanand Jitta Cc: Laura Abbott Cc: Sumit Semwal Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d4b0c79d2924..7bbeba21f6a3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -180,7 +180,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ - NR_INDIRECTLY_RECLAIMABLE_BYTES, /* measured in bytes */ + NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_VM_NODE_STAT_ITEMS }; -- cgit v1.2.3 From 1899ad18c6072d689896badafb81267b0a1092a4 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:04 -0700 Subject: mm: workingset: tell cache transitions from workingset thrashing Refaults happen during transitions between workingsets as well as in-place thrashing. Knowing the difference between the two has a range of applications, including measuring the impact of memory shortage on the system performance, as well as the ability to smarter balance pressure between the filesystem cache and the swap-backed workingset. During workingset transitions, inactive cache refaults and pushes out established active cache. When that active cache isn't stale, however, and also ends up refaulting, that's bonafide thrashing. Introduce a new page flag that tells on eviction whether the page has been active or not in its lifetime. This bit is then stored in the shadow entry, to classify refaults as transitioning or thrashing. How many page->flags does this leave us with on 32-bit? 20 bits are always page flags 21 if you have an MMU 23 with the zone bits for DMA, Normal, HighMem, Movable 29 with the sparsemem section bits 30 if PAE is enabled 31 with this patch. So on 32-bit PAE, that leaves 1 bit for distinguishing two NUMA nodes. If that's not enough, the system can switch to discontigmem and re-gain the 6 or 7 sparsemem section bits. Link: http://lkml.kernel.org/r/20180828172258.3185-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/linux/page-flags.h | 5 ++++- include/linux/swap.h | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7bbeba21f6a3..ba51d5bf7af1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -163,6 +163,7 @@ enum node_stat_item { NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_RESTORE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 74bee8cecf4c..4d99504f6496 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -69,13 +69,14 @@ */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ - PG_error, PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, + PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ + PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, @@ -280,6 +281,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) +PAGEFLAG(Workingset, workingset, PF_HEAD) + TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..b93740d72e78 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -296,7 +296,7 @@ struct vma_swap_readahead { /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); -bool workingset_refault(void *shadow); +void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); /* Do not use directly, use workingset_lookup_update */ -- cgit v1.2.3 From b1d29ba82cf2bc784f4c963ddd6a2cf29e229b33 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:08 -0700 Subject: delayacct: track delays from thrashing cache pages Delay accounting already measures the time a task spends in direct reclaim and waiting for swapin, but in low memory situations tasks spend can spend a significant amount of their time waiting on thrashing page cache. This isn't tracked right now. To know the full impact of memory contention on an individual task, measure the delay when waiting for a recently evicted active cache page to read back into memory. Also update tools/accounting/getdelays.c: [hannes@computer accounting]$ sudo ./getdelays -d -p 1 print delayacct stats ON PID 1 CPU count real total virtual total delay total delay average 50318 745000000 847346785 400533713 0.008ms IO count delay total delay average 435 122601218 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 19 12621439 0ms Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 31c865d1842e..577d1b25fccd 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -57,7 +57,12 @@ struct task_delay_info { u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ + + u64 thrashing_start; + u64 thrashing_delay; /* wait for thrashing page */ + u32 freepages_count; /* total count of memory reclaim */ + u32 thrashing_count; /* total count of thrash waits */ }; #endif @@ -76,6 +81,8 @@ extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); +extern void __delayacct_thrashing_start(void); +extern void __delayacct_thrashing_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { @@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void) __delayacct_freepages_end(); } +static inline void delayacct_thrashing_start(void) +{ + if (current->delays) + __delayacct_thrashing_start(); +} + +static inline void delayacct_thrashing_end(void) +{ + if (current->delays) + __delayacct_thrashing_end(); +} + #else static inline void delayacct_set_flag(int flag) {} @@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} +static inline void delayacct_thrashing_start(void) +{} +static inline void delayacct_thrashing_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ -- cgit v1.2.3 From 8508cf3ffad4defa202b303e5b6379efc4cd9054 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:11 -0700 Subject: sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD There are several definitions of those functions/macros in places that mess with fixed-point load averages. Provide an official version. [akpm@linux-foundation.org: fix missed conversion in block/blk-iolatency.c] Link: http://lkml.kernel.org/r/20180828172258.3185-5-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/loadavg.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index 80bc84ba5d2a..cc9cc62bb1f8 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -22,10 +22,23 @@ extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift); #define EXP_5 2014 /* 1/exp(5sec/5min) */ #define EXP_15 2037 /* 1/exp(5sec/15min) */ -#define CALC_LOAD(load,exp,n) \ - load *= exp; \ - load += n*(FIXED_1-exp); \ - load >>= FSHIFT; +/* + * a1 = a0 * e + a * (1 - e) + */ +static inline unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + unsigned long newload; + + newload = load * exp + active * (FIXED_1 - exp); + if (active >= load) + newload += FIXED_1-1; + + return newload / FIXED_1; +} + +#define LOAD_INT(x) ((x) >> FSHIFT) +#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) extern void calc_global_load(unsigned long ticks); -- cgit v1.2.3 From 5c54f5b9edb1aa2eabbb1091c458f1b6776a1896 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:16 -0700 Subject: sched: loadavg: make calc_load_n() public It's going to be used in a later patch. Keep the churn separate. Link: http://lkml.kernel.org/r/20180828172258.3185-6-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/loadavg.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index cc9cc62bb1f8..4859bea47a7b 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -37,6 +37,9 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) return newload / FIXED_1; } +extern unsigned long calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n); + #define LOAD_INT(x) ((x) >> FSHIFT) #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) -- cgit v1.2.3 From eb414681d5a07d28d2ff90dc05f69ec6b232ebd2 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:27 -0700 Subject: psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/psi.h | 28 +++++++++++++++ include/linux/psi_types.h | 92 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 10 ++++++ 3 files changed, 130 insertions(+) create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h (limited to 'include/linux') diff --git a/include/linux/psi.h b/include/linux/psi.h new file mode 100644 index 000000000000..b0daf050de58 --- /dev/null +++ b/include/linux/psi.h @@ -0,0 +1,28 @@ +#ifndef _LINUX_PSI_H +#define _LINUX_PSI_H + +#include +#include + +#ifdef CONFIG_PSI + +extern bool psi_disabled; + +void psi_init(void); + +void psi_task_change(struct task_struct *task, int clear, int set); + +void psi_memstall_tick(struct task_struct *task, int cpu); +void psi_memstall_enter(unsigned long *flags); +void psi_memstall_leave(unsigned long *flags); + +#else /* CONFIG_PSI */ + +static inline void psi_init(void) {} + +static inline void psi_memstall_enter(unsigned long *flags) {} +static inline void psi_memstall_leave(unsigned long *flags) {} + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_H */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h new file mode 100644 index 000000000000..2cf422db5d18 --- /dev/null +++ b/include/linux/psi_types.h @@ -0,0 +1,92 @@ +#ifndef _LINUX_PSI_TYPES_H +#define _LINUX_PSI_TYPES_H + +#include +#include + +#ifdef CONFIG_PSI + +/* Tracked task states */ +enum psi_task_count { + NR_IOWAIT, + NR_MEMSTALL, + NR_RUNNING, + NR_PSI_TASK_COUNTS, +}; + +/* Task state bitmasks */ +#define TSK_IOWAIT (1 << NR_IOWAIT) +#define TSK_MEMSTALL (1 << NR_MEMSTALL) +#define TSK_RUNNING (1 << NR_RUNNING) + +/* Resources that workloads could be stalled on */ +enum psi_res { + PSI_IO, + PSI_MEM, + PSI_CPU, + NR_PSI_RESOURCES, +}; + +/* + * Pressure states for each resource: + * + * SOME: Stalled tasks & working tasks + * FULL: Stalled tasks & no working tasks + */ +enum psi_states { + PSI_IO_SOME, + PSI_IO_FULL, + PSI_MEM_SOME, + PSI_MEM_FULL, + PSI_CPU_SOME, + /* Only per-CPU, to weigh the CPU in the global average: */ + PSI_NONIDLE, + NR_PSI_STATES, +}; + +struct psi_group_cpu { + /* 1st cacheline updated by the scheduler */ + + /* Aggregator needs to know of concurrent changes */ + seqcount_t seq ____cacheline_aligned_in_smp; + + /* States of the tasks belonging to this group */ + unsigned int tasks[NR_PSI_TASK_COUNTS]; + + /* Period time sampling buckets for each state of interest (ns) */ + u32 times[NR_PSI_STATES]; + + /* Time of last task change in this group (rq_clock) */ + u64 state_start; + + /* 2nd cacheline updated by the aggregator */ + + /* Delta detection against the sampling buckets */ + u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp; +}; + +struct psi_group { + /* Protects data updated during an aggregation */ + struct mutex stat_lock; + + /* Per-cpu task state & time tracking */ + struct psi_group_cpu __percpu *pcpu; + + /* Periodic aggregation state */ + u64 total_prev[NR_PSI_STATES - 1]; + u64 last_update; + u64 next_update; + struct delayed_work clock_work; + + /* Total stall times and sampled pressure averages */ + u64 total[NR_PSI_STATES - 1]; + unsigned long avg[NR_PSI_STATES - 1][3]; +}; + +#else /* CONFIG_PSI */ + +struct psi_group { }; + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_TYPES_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index adfb3f9a7597..b8fcc6b3080c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -706,6 +707,10 @@ struct task_struct { unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_remote_wakeup:1; +#ifdef CONFIG_PSI + unsigned sched_psi_wake_requeue:1; +#endif + /* Force alignment to the next boundary: */ unsigned :0; @@ -965,6 +970,10 @@ struct task_struct { kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; +#ifdef CONFIG_PSI + /* Pressure stall state */ + unsigned int psi_flags; +#endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; @@ -1391,6 +1400,7 @@ extern struct pid *cad_pid; #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ -- cgit v1.2.3 From 2ce7135adc9ad081aa3c49744144376ac74fea60 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:31 -0700 Subject: psi: cgroup support On a system that executes multiple cgrouped jobs and independent workloads, we don't just care about the health of the overall system, but also that of individual jobs, so that we can ensure individual job health, fairness between jobs, or prioritize some jobs over others. This patch implements pressure stall tracking for cgroups. In kernels with CONFIG_PSI=y, cgroup2 groups will have cpu.pressure, memory.pressure, and io.pressure files that track aggregate pressure stall times for only the tasks inside the cgroup. Link: http://lkml.kernel.org/r/20180828172258.3185-10-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Tejun Heo Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup-defs.h | 4 ++++ include/linux/cgroup.h | 15 +++++++++++++++ include/linux/psi.h | 25 +++++++++++++++++++++++++ 3 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 22254c1fe1c5..5e1694fe035b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -20,6 +20,7 @@ #include #include #include +#include #ifdef CONFIG_CGROUPS @@ -436,6 +437,9 @@ struct cgroup { /* used to schedule release agent */ struct work_struct release_agent_work; + /* used to track pressure stalls */ + struct psi_group psi; + /* used to store eBPF programs */ struct cgroup_bpf bpf; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b622d6608605..9968332cceed 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -650,6 +650,11 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return &cgrp->psi; +} + static inline void cgroup_init_kthreadd(void) { /* @@ -703,6 +708,16 @@ static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) return NULL; } +static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) +{ + return NULL; +} + +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return NULL; +} + static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { diff --git a/include/linux/psi.h b/include/linux/psi.h index b0daf050de58..8e0725aac0aa 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -4,6 +4,9 @@ #include #include +struct seq_file; +struct css_set; + #ifdef CONFIG_PSI extern bool psi_disabled; @@ -16,6 +19,14 @@ void psi_memstall_tick(struct task_struct *task, int cpu); void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); +int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgrp); +void psi_cgroup_free(struct cgroup *cgrp); +void cgroup_move_task(struct task_struct *p, struct css_set *to); +#endif + #else /* CONFIG_PSI */ static inline void psi_init(void) {} @@ -23,6 +34,20 @@ static inline void psi_init(void) {} static inline void psi_memstall_enter(unsigned long *flags) {} static inline void psi_memstall_leave(unsigned long *flags) {} +#ifdef CONFIG_CGROUPS +static inline int psi_cgroup_alloc(struct cgroup *cgrp) +{ + return 0; +} +static inline void psi_cgroup_free(struct cgroup *cgrp) +{ +} +static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) +{ + rcu_assign_pointer(p->cgroups, to); +} +#endif + #endif /* CONFIG_PSI */ #endif /* _LINUX_PSI_H */ -- cgit v1.2.3 From 68d48e6a2df575b935edd420396c3cb8b6aa6ad3 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:39 -0700 Subject: mm: workingset: add vmstat counter for shadow nodes Make it easier to catch bugs in the shadow node shrinker by adding a counter for the shadow nodes in circulation. [akpm@linux-foundation.org: assert that irqs are disabled, for __inc_lruvec_page_state()] [akpm@linux-foundation.org: s/WARN_ON_ONCE/VM_WARN_ON_ONCE/, per Johannes] Link: http://lkml.kernel.org/r/20181009184732.762-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ba51d5bf7af1..9f0caccd5833 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -161,6 +161,7 @@ enum node_stat_item { NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ + WORKINGSET_NODES, WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, WORKINGSET_RESTORE, -- cgit v1.2.3 From 85cfb245060e45640fa3447f8b0bad5e8bd3bdaf Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 26 Oct 2018 15:07:41 -0700 Subject: memcg: remove memcg_kmem_skip_account The flag memcg_kmem_skip_account was added during the era of opt-out kmem accounting. There is no need for such flag in the opt-in world as there aren't any __GFP_ACCOUNT allocations within memcg_create_cache_enqueue(). Link: http://lkml.kernel.org/r/20180919004501.178023-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b8fcc6b3080c..8f8a5418b627 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -724,9 +724,6 @@ struct task_struct { #endif #ifdef CONFIG_MEMCG unsigned in_user_fault:1; -#ifdef CONFIG_MEMCG_KMEM - unsigned memcg_kmem_skip_account:1; -#endif #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; -- cgit v1.2.3 From f682a97a00591def7cefbb5003dc04045028e405 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:45 -0700 Subject: mm: provide kernel parameter to allow disabling page init poisoning Patch series "Address issues slowing persistent memory initialization", v5. The main thing this patch set achieves is that it allows us to initialize each node worth of persistent memory independently. As a result we reduce page init time by about 2 minutes because instead of taking 30 to 40 seconds per node and going through each node one at a time, we process all 4 nodes in parallel in the case of a 12TB persistent memory setup spread evenly over 4 nodes. This patch (of 3): On systems with a large amount of memory it can take a significant amount of time to initialize all of the page structs with the PAGE_POISON_PATTERN value. I have seen it take over 2 minutes to initialize a system with over 12TB of RAM. In order to work around the issue I had to disable CONFIG_DEBUG_VM and then the boot time returned to something much more reasonable as the arch_add_memory call completed in milliseconds versus seconds. However in doing that I had to disable all of the other VM debugging on the system. In order to work around a kernel that might have CONFIG_DEBUG_VM enabled on a system that has a large amount of memory I have added a new kernel parameter named "vm_debug" that can be set to "-" in order to disable it. Link: http://lkml.kernel.org/r/20180925201921.3576.84239.stgit@localhost.localdomain Reviewed-by: Pavel Tatashin Signed-off-by: Alexander Duyck Cc: Dave Hansen Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4d99504f6496..934f91ef3f54 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -163,6 +163,14 @@ static inline int PagePoisoned(const struct page *page) return page->flags == PAGE_POISON_PATTERN; } +#ifdef CONFIG_DEBUG_VM +void page_init_poison(struct page *page, size_t size); +#else +static inline void page_init_poison(struct page *page, size_t size) +{ +} +#endif + /* * Page flags policies wrt compound pages * -- cgit v1.2.3 From d483da5bc78b86fe4200d2947f193a745f711713 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:48 -0700 Subject: mm: create non-atomic version of SetPageReserved for init use It doesn't make much sense to use the atomic SetPageReserved at init time when we are using memset to clear the memory and manipulating the page flags via simple "&=" and "|=" operations in __init_single_page. This patch adds a non-atomic version __SetPageReserved that can be used during page init and shows about a 10% improvement in initialization times on the systems I have available for testing. On those systems I saw initialization times drop from around 35 seconds to around 32 seconds to initialize a 3TB block of persistent memory. I believe the main advantage of this is that it allows for more compiler optimization as the __set_bit operation can be reordered whereas the atomic version cannot. I tried adding a bit of documentation based on f1dd2cd13c4 ("mm, memory_hotplug: do not associate hotadded memory to zones until online"). Ideally the reserved flag should be set earlier since there is a brief window where the page is initialization via __init_single_page and we have not set the PG_Reserved flag. I'm leaving that for a future patch set as that will require a more significant refactor. Link: http://lkml.kernel.org/r/20180925202018.3576.11607.stgit@localhost.localdomain Signed-off-by: Alexander Duyck Reviewed-by: Pavel Tatashin Acked-by: Michal Hocko Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 934f91ef3f54..50ce1bddaf56 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -303,6 +303,7 @@ PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) + __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) -- cgit v1.2.3 From 966cf44f637e6aeea7e3d01ba004bf8b5beac78f Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:52 -0700 Subject: mm: defer ZONE_DEVICE page initialization to the point where we init pgmap The ZONE_DEVICE pages were being initialized in two locations. One was with the memory_hotplug lock held and another was outside of that lock. The problem with this is that it was nearly doubling the memory initialization time. Instead of doing this twice, once while holding a global lock and once without, I am opting to defer the initialization to the one outside of the lock. This allows us to avoid serializing the overhead for memory init and we can instead focus on per-node init times. One issue I encountered is that devm_memremap_pages and hmm_devmmem_pages_create were initializing only the pgmap field the same way. One wasn't initializing hmm_data, and the other was initializing it to a poison value. Since this is something that is exposed to the driver in the case of hmm I am opting for a third option and just initializing hmm_data to 0 since this is going to be exposed to unknown third party drivers. [alexander.h.duyck@linux.intel.com: fix reference count for pgmap in devm_memremap_pages] Link: http://lkml.kernel.org/r/20181008233404.1909.37302.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/20180925202053.3576.66039.stgit@localhost.localdomain Signed-off-by: Alexander Duyck Reviewed-by: Pavel Tatashin Tested-by: Dan Williams Cc: Dave Hansen Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 737279bb479c..33228a49d7d2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -848,6 +848,8 @@ static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } +extern void memmap_init_zone_device(struct zone *, unsigned long, + unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { -- cgit v1.2.3 From 85a06835f6f1ba79f0f00838ccd5ad840dd1eafb Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:08:50 -0700 Subject: mm: mremap: downgrade mmap_sem to read when shrinking Other than munmap, mremap might be used to shrink memory mapping too. So, it may hold write mmap_sem for long time when shrinking large mapping, as what commit ("mm: mmap: zap pages with read mmap_sem in munmap") described. The mremap() will not manipulate vmas anymore after __do_munmap() call for the mapping shrink use case, so it is safe to downgrade to read mmap_sem. So, the same optimization, which downgrades mmap_sem to read for zapping pages, is also feasible and reasonable to this case. The period of holding exclusive mmap_sem for shrinking large mapping would be reduced significantly with this optimization. MREMAP_FIXED and MREMAP_MAYMOVE are more complicated to adopt this optimization since they need manipulate vmas after do_munmap(), downgrading mmap_sem may create race window. Simple mapping shrink is the low hanging fruit, and it may cover the most cases of unmap with munmap together. [akpm@linux-foundation.org: tweak comment] [yang.shi@linux.alibaba.com: fix unsigned compare against 0 issue] Link: http://lkml.kernel.org/r/1538687672-17795-2-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1538067582-60038-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Michal Hocko Cc: Matthew Wilcox Cc: Laurent Dufour Cc: Colin Ian King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 33228a49d7d2..a023c5ce71fa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2306,6 +2306,8 @@ extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); +extern int __do_munmap(struct mm_struct *, unsigned long, size_t, + struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); -- cgit v1.2.3 From cc4b8c794f476076c9ce19f43eb4d98dc4b5e155 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:08:57 -0700 Subject: mm: dax: add comment for PFN_SPECIAL The comment for PFN_SPECIAL is missed in pfn_t.h. Add comment to get consistent with other pfn flags. Link: http://lkml.kernel.org/r/1538086549-100536-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Suggested-by: Dan Williams Reviewed-by: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pfn_t.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 673546ba7342..7bb77850c65a 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -9,6 +9,8 @@ * PFN_SG_LAST - pfn references a page and is the last scatterlist entry * PFN_DEV - pfn is not covered by system memmap by default * PFN_MAP - pfn has a dynamic page mapping established by a device driver + * PFN_SPECIAL - for CONFIG_FS_DAX_LIMITED builds to allow XIP, but not + * get_user_pages */ #define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1)) -- cgit v1.2.3 From 1c2d479a119b84feacbe4de782016f1bf1ad16dc Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 26 Oct 2018 15:09:28 -0700 Subject: mm/memcontrol.c: convert mem_cgroup_id::ref to refcount_t type This will allow to use generic refcount_t interfaces to check counters overflow instead of currently existing VM_BUG_ON(). The only difference after the patch is VM_BUG_ON() may cause BUG(), while refcount_t fires with WARN(). But this seems not to be significant here, since such the problems are usually caught by syzbot with panic-on-warn enabled. Link: http://lkml.kernel.org/r/153910718919.7006.13400779039257185427.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Reviewed-by: Andrew Morton Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Andrea Parri Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 4399cc3f00e4..7ab2120155a4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -78,7 +78,7 @@ struct mem_cgroup_reclaim_cookie { struct mem_cgroup_id { int id; - atomic_t ref; + refcount_t ref; }; /* -- cgit v1.2.3 From 907ec5fca3dc38d37737de826f06f25b063aa08e Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 26 Oct 2018 15:10:15 -0700 Subject: mm: zero remaining unavailable struct pages Patch series "mm: Fix for movable_node boot option", v3. This patch series contains a fix for the movable_node boot option issue which was introduced by commit 124049decbb1 ("x86/e820: put !E820_TYPE_RAM regions into memblock.reserved"). The commit breaks the option because it changed the memory gap range to reserved memblock. So, the node is marked as Normal zone even if the SRAT has Hot pluggable affinity. First and second patch fix the original issue which the commit tried to fix, then revert the commit. This patch (of 3): There is a kernel panic that is triggered when reading /proc/kpageflags on the kernel booted with kernel parameter 'memmap=nn[KMG]!ss[KMG]': BUG: unable to handle kernel paging request at fffffffffffffffe PGD 9b20e067 P4D 9b20e067 PUD 9b210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 1728 Comm: page-types Not tainted 4.17.0-rc6-mm1-v4.17-rc6-180605-0816-00236-g2dfb086ef02c+ #160 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.fc28 04/01/2014 RIP: 0010:stable_page_flags+0x27/0x3c0 Code: 00 00 00 0f 1f 44 00 00 48 85 ff 0f 84 a0 03 00 00 41 54 55 49 89 fc 53 48 8b 57 08 48 8b 2f 48 8d 42 ff 83 e2 01 48 0f 44 c7 <48> 8b 00 f6 c4 01 0f 84 10 03 00 00 31 db 49 8b 54 24 08 4c 89 e7 RSP: 0018:ffffbbd44111fde0 EFLAGS: 00010202 RAX: fffffffffffffffe RBX: 00007fffffffeff9 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000202 RDI: ffffed1182fff5c0 RBP: ffffffffffffffff R08: 0000000000000001 R09: 0000000000000001 R10: ffffbbd44111fed8 R11: 0000000000000000 R12: ffffed1182fff5c0 R13: 00000000000bffd7 R14: 0000000002fff5c0 R15: ffffbbd44111ff10 FS: 00007efc4335a500(0000) GS:ffff93a5bfc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffffffffffffe CR3: 00000000b2a58000 CR4: 00000000001406e0 Call Trace: kpageflags_read+0xc7/0x120 proc_reg_read+0x3c/0x60 __vfs_read+0x36/0x170 vfs_read+0x89/0x130 ksys_pread64+0x71/0x90 do_syscall_64+0x5b/0x160 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7efc42e75e23 Code: 09 00 ba 9f 01 00 00 e8 ab 81 f4 ff 66 2e 0f 1f 84 00 00 00 00 00 90 83 3d 29 0a 2d 00 00 75 13 49 89 ca b8 11 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 db d3 01 00 48 89 04 24 According to kernel bisection, this problem became visible due to commit f7f99100d8d9 which changes how struct pages are initialized. Memblock layout affects the pfn ranges covered by node/zone. Consider that we have a VM with 2 NUMA nodes and each node has 4GB memory, and the default (no memmap= given) memblock layout is like below: MEMBLOCK configuration: memory size = 0x00000001fff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x4 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000100000000-0x000000013fffffff], 0x0000000040000000 bytes on node 0 flags: 0x0 memory[0x3] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... If you give memmap=1G!4G (so it just covers memory[0x2]), the range [0x100000000-0x13fffffff] is gone: MEMBLOCK configuration: memory size = 0x00000001bff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x3 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... This causes shrinking node 0's pfn range because it is calculated by the address range of memblock.memory. So some of struct pages in the gap range are left uninitialized. We have a function zero_resv_unavail() which does zeroing the struct pages outside memblock.memory, but currently it covers only the reserved unavailable range (i.e. memblock.memory && !memblock.reserved). This patch extends it to cover all unavailable range, which fixes the reported issue. Link: http://lkml.kernel.org/r/20181002143821.5112-2-msys.mizuma@gmail.com Fixes: f7f99100d8d9 ("mm: stop zeroing memory during allocation in vmemmap") Signed-off-by: Naoya Horiguchi Signed-off-by-by: Masayoshi Mizuma Tested-by: Oscar Salvador Tested-by: Masayoshi Mizuma Reviewed-by: Pavel Tatashin Cc: Ingo Molnar Cc: Michal Hocko Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 516920549378..2acdd046df2d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -265,21 +265,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ nid, flags, p_start, p_end, p_nid) -/** - * for_each_resv_unavail_range - iterate through reserved and unavailable memory - * @i: u64 used as loop variable - * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL - * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL - * - * Walks over unavailable but reserved (reserved && !memory) areas of memblock. - * Available as soon as memblock is initialized. - * Note: because this memory does not belong to any physical node, flags and - * nid arguments do not make sense and thus not exported as arguments. - */ -#define for_each_resv_unavail_range(i, p_start, p_end) \ - for_each_mem_range(i, &memblock.reserved, &memblock.memory, \ - NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL) - static inline void memblock_set_region_flags(struct memblock_region *r, enum memblock_flags flags) { -- cgit v1.2.3 From df06b37ffe5a442503b7095b77b0a970df515459 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 26 Oct 2018 15:10:28 -0700 Subject: mm/gup: cache dev_pagemap while pinning pages Getting pages from ZONE_DEVICE memory needs to check the backing device's live-ness, which is tracked in the device's dev_pagemap metadata. This metadata is stored in a radix tree and looking it up adds measurable software overhead. This patch avoids repeating this relatively costly operation when dev_pagemap is used by caching the last dev_pagemap while getting user pages. The gup_benchmark kernel self test reports this reduces time to get user pages to as low as 1/3 of the previous time. Link: http://lkml.kernel.org/r/20181012173040.15669-1-keith.busch@intel.com Signed-off-by: Keith Busch Reviewed-by: Dan Williams Acked-by: Kirill A. Shutemov Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 8 ++++---- include/linux/mm.h | 12 ++---------- 2 files changed, 6 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index fdcb45999b26..4663ee96cf59 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -213,9 +213,9 @@ static inline int hpage_nr_pages(struct page *page) } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags); + pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags); + pud_t *pud, int flags, struct dev_pagemap **pgmap); extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); @@ -344,13 +344,13 @@ static inline void mm_put_huge_zero_page(struct mm_struct *mm) } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmd, int flags) + unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, - unsigned long addr, pud_t *pud, int flags) + unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { return NULL; } diff --git a/include/linux/mm.h b/include/linux/mm.h index a023c5ce71fa..1e52b8fd1685 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2536,16 +2536,8 @@ static inline vm_fault_t vmf_error(int err) return VM_FAULT_SIGBUS; } -struct page *follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags, - unsigned int *page_mask); - -static inline struct page *follow_page(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags) -{ - unsigned int unused_page_mask; - return follow_page_mask(vma, address, foll_flags, &unused_page_mask); -} +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags); #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ -- cgit v1.2.3 From bc4ae27d817a4e92071ef67cb6368120cfabe7ec Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 26 Oct 2018 15:10:51 -0700 Subject: mm: split SWP_FILE into SWP_ACTIVATED and SWP_FS The SWP_FILE flag serves two purposes: to make swap_{read,write}page() go through the filesystem, and to make swapoff() call ->swap_deactivate(). For Btrfs, we want the latter but not the former, so split this flag into two. This makes us always call ->swap_deactivate() if ->swap_activate() succeeded, not just if it didn't add any swap extents itself. This also resolves the issue of the very misleading name of SWP_FILE, which is only used for swap files over NFS. Link: http://lkml.kernel.org/r/6d63d8668c4287a4f6d203d65696e96f80abdfc7.1536704650.git.osandov@fb.com Signed-off-by: Omar Sandoval Reviewed-by: Nikolay Borisov Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: David Sterba Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index b93740d72e78..38195f5c96b1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -167,13 +167,14 @@ enum { SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ - SWP_FILE = (1 << 7), /* set after swap_activate success */ - SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */ - SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */ - SWP_STABLE_WRITES = (1 << 10), /* no overwrite PG_writeback pages */ - SWP_SYNCHRONOUS_IO = (1 << 11), /* synchronous IO is efficient */ + SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ + SWP_FS = (1 << 8), /* swap file goes through fs */ + SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ + SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ + SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ + SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ - SWP_SCANNING = (1 << 12), /* refcount in scan_swap_map */ + SWP_SCANNING = (1 << 13), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL -- cgit v1.2.3 From ae74136b4bb64440a55117e12065b8c282ab6c1a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 3 Oct 2018 12:01:22 -0400 Subject: SUNRPC: Allow cache lookups to use RCU protection rather than the r/w spinlock Instead of the reader/writer spinlock, allow cache lookups to use RCU for looking up entries. This is more efficient since modifications can occur while other entries are being looked up. Note that for now, we keep the reader/writer spinlock until all users have been converted to use RCU-safe freeing of their cache entries. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 40d2822f0e2f..cf3e17ee2786 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -167,6 +167,9 @@ extern const struct file_operations cache_file_operations_pipefs; extern const struct file_operations content_file_operations_pipefs; extern const struct file_operations cache_flush_operations_pipefs; +extern struct cache_head * +sunrpc_cache_lookup_rcu(struct cache_detail *detail, + struct cache_head *key, int hash); extern struct cache_head * sunrpc_cache_lookup(struct cache_detail *detail, struct cache_head *key, int hash); @@ -186,6 +189,12 @@ static inline struct cache_head *cache_get(struct cache_head *h) return h; } +static inline struct cache_head *cache_get_rcu(struct cache_head *h) +{ + if (kref_get_unless_zero(&h->ref)) + return h; + return NULL; +} static inline void cache_put(struct cache_head *h, struct cache_detail *cd) { @@ -227,6 +236,9 @@ extern void sunrpc_cache_unhash(struct cache_detail *, struct cache_head *); extern void *cache_seq_start(struct seq_file *file, loff_t *pos); extern void *cache_seq_next(struct seq_file *file, void *p, loff_t *pos); extern void cache_seq_stop(struct seq_file *file, void *p); +extern void *cache_seq_start_rcu(struct seq_file *file, loff_t *pos); +extern void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos); +extern void cache_seq_stop_rcu(struct seq_file *file, void *p); extern void qword_add(char **bpp, int *lp, char *str); extern void qword_addhex(char **bpp, int *lp, char *buf, int blen); -- cgit v1.2.3 From d48cf356a13073853f19be6ca5ebbecfc2762ebe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 1 Oct 2018 10:41:51 -0400 Subject: SUNRPC: Remove non-RCU protected lookup Clean up the cache code by removing the non-RCU protected lookup. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index cf3e17ee2786..c3d67e893430 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -171,9 +171,6 @@ extern struct cache_head * sunrpc_cache_lookup_rcu(struct cache_detail *detail, struct cache_head *key, int hash); extern struct cache_head * -sunrpc_cache_lookup(struct cache_detail *detail, - struct cache_head *key, int hash); -extern struct cache_head * sunrpc_cache_update(struct cache_detail *detail, struct cache_head *new, struct cache_head *old, int hash); @@ -233,9 +230,6 @@ extern void sunrpc_cache_unregister_pipefs(struct cache_detail *); extern void sunrpc_cache_unhash(struct cache_detail *, struct cache_head *); /* Must store cache_detail in seq_file->private if using next three functions */ -extern void *cache_seq_start(struct seq_file *file, loff_t *pos); -extern void *cache_seq_next(struct seq_file *file, void *p, loff_t *pos); -extern void cache_seq_stop(struct seq_file *file, void *p); extern void *cache_seq_start_rcu(struct seq_file *file, loff_t *pos); extern void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos); extern void cache_seq_stop_rcu(struct seq_file *file, void *p); -- cgit v1.2.3 From 1863d77f15da0addcd293a1719fa5d3ef8cde3ca Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 1 Oct 2018 10:41:52 -0400 Subject: SUNRPC: Replace the cache_detail->hash_lock with a regular spinlock Now that the reader functions are all RCU protected, use a regular spinlock rather than a reader/writer lock. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index c3d67e893430..5a3e95017fc6 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -67,7 +67,7 @@ struct cache_detail { struct module * owner; int hash_size; struct hlist_head * hash_table; - rwlock_t hash_lock; + spinlock_t hash_lock; char *name; void (*cache_put)(struct kref *); -- cgit v1.2.3 From 3ae2cefb613b00d613677c05ffa384b4f660f468 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 1 Oct 2018 14:16:11 -0400 Subject: svcrdma: Increase the default connection credit limit Reduce queuing on clients by allowing more credits by default. 64 is the default NFSv4.1 slot table size on Linux clients. This size prevents the credit limit from putting RPC requests to sleep again after they have already slept waiting for a session slot. Signed-off-by: Chuck Lever Reviewed-by: Sagi Grimberg Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index fd78f78df5c6..e6e26918504c 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -113,13 +113,14 @@ struct svcxprt_rdma { /* sc_flags */ #define RDMAXPRT_CONN_PENDING 3 -#define RPCRDMA_LISTEN_BACKLOG 10 -#define RPCRDMA_MAX_REQUESTS 32 - -/* Typical ULP usage of BC requests is NFSv4.1 backchannel. Our - * current NFSv4.1 implementation supports one backchannel slot. +/* + * Default connection parameters */ -#define RPCRDMA_MAX_BC_REQUESTS 2 +enum { + RPCRDMA_LISTEN_BACKLOG = 10, + RPCRDMA_MAX_REQUESTS = 64, + RPCRDMA_MAX_BC_REQUESTS = 2, +}; #define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD -- cgit v1.2.3 From 1383a7ed67490fb00d793e36c7a4d599ff88a64d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:40:31 +1100 Subject: vfs: check file ranges before cloning files Move the file range checks from vfs_clone_file_prep into a separate generic_remap_checks function so that all the checks are collected in a central location. This forms the basis for adding more checks from generic_write_checks that will make cloning's input checking more consistent with write input checking. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 897eae8faee1..ba93a6e7dac4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, - struct inode *inode_out, loff_t pos_out, - u64 *len, bool is_dedupe); +extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *count, bool is_dedupe); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, @@ -2967,6 +2967,9 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); +extern int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + uint64_t *count, bool is_dedupe); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); -- cgit v1.2.3 From a83ab01a62e61616ebb8b97f90f568c1214dc10d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:08 +1100 Subject: vfs: rename vfs_clone_file_prep to be more descriptive The vfs_clone_file_prep is a generic function to be called by filesystem implementations only. Rename the prefix to generic_ and make it more clear that it applies to remap operations, not just clones. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ba93a6e7dac4..55729e1c2e75 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 *count, bool is_dedupe); +extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *count, bool is_dedupe); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, -- cgit v1.2.3 From 2e5dfc99f2e61c42083ba742395e7a7b353513d1 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:21 +1100 Subject: vfs: combine the clone and dedupe into a single remap_file_range Combine the clone_file_range and dedupe_file_range operations into a single remap_file_range file operation dispatch since they're fundamentally the same operation. The differences between the two can be made in the prep functions. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- include/linux/fs.h | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 55729e1c2e75..888cef35c7d7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1721,6 +1721,24 @@ struct block_device_operations; #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) +/* + * These flags control the behavior of the remap_file_range function pointer. + * If it is called with len == 0 that means "remap to end of source file". + * See Documentation/filesystems/vfs.txt for more details about this call. + * + * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) + */ +#define REMAP_FILE_DEDUP (1 << 0) + +/* + * These flags signal that the caller is ok with altering various aspects of + * the behavior of the remap operation. The changes must be made by the + * implementation; the vfs remap helper functions can take advantage of them. + * Flags in this category exist to preserve the quirky behavior of the hoisted + * btrfs clone/dedupe ioctls. + * There are no flags yet, but subsequent commits will add some. + */ +#define REMAP_FILE_ADVISORY (0) struct iov_iter; @@ -1759,10 +1777,9 @@ struct file_operations { #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, - u64); - int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, - u64); + int (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; -- cgit v1.2.3 From a91ae49bbaf43910edb09e03fedf26b23875bd52 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:28 +1100 Subject: vfs: pass remap flags to generic_remap_file_range_prep Plumb the remap flags through the filesystem from the vfs function dispatcher all the way to the prep function to prepare for behavior changes in subsequent patches. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 888cef35c7d7..631c28ce1436 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1844,7 +1844,7 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *count, bool is_dedupe); + u64 *count, unsigned int remap_flags); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, -- cgit v1.2.3 From 3d28193e1df043764deb7abdaba5e3a6660bc393 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:34 +1100 Subject: vfs: pass remap flags to generic_remap_checks Pass the same remap flags to generic_remap_checks for consistency. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 631c28ce1436..c5435ca81132 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2986,7 +2986,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *count, bool is_dedupe); + uint64_t *count, unsigned int remap_flags); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); -- cgit v1.2.3 From 42ec3d4c02187a18e27ff94b409ec27234bf2ffd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:49 +1100 Subject: vfs: make remap_file_range functions take and return bytes completed Change the remap_file_range functions to take a number of bytes to operate upon and return the number of bytes they operated on. This is a requirement for allowing fs implementations to return short clone/dedupe results to the user, which will enable us to obey resource limits in a graceful manner. A subsequent patch will enable copy_file_range to signal to the ->clone_file_range implementation that it can handle a short length, which will be returned in the function's return value. For now the short return is not implemented anywhere so the behavior won't change -- either copy_file_range manages to clone the entire range or it tries an alternative. Neither clone ioctl can take advantage of this, alas. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c5435ca81132..c72d8c3c065a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1777,9 +1777,9 @@ struct file_operations { #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*remap_file_range)(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len, unsigned int remap_flags); + loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; @@ -1844,19 +1844,22 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *count, unsigned int remap_flags); -extern int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); -extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); + loff_t *count, + unsigned int remap_flags); +extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len); +extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); -extern int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, - struct file *dst_file, loff_t dst_pos, - u64 len); +extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, + struct file *dst_file, loff_t dst_pos, + loff_t len); struct super_operations { @@ -2986,7 +2989,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *count, unsigned int remap_flags); + loff_t *count, unsigned int remap_flags); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); -- cgit v1.2.3 From 452ce65951a2f0719e4e119ecca134c06cfe22ee Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:56 +1100 Subject: vfs: plumb remap flags through the vfs clone functions Plumb a remap_flags argument through the {do,vfs}_clone_file_range functions so that clone can take advantage of it. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c72d8c3c065a..1c5e55d2a67d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1848,10 +1848,10 @@ extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, unsigned int remap_flags); extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - loff_t len); + loff_t len, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - loff_t len); + loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); -- cgit v1.2.3 From df3658361951e17364f1e1c3fa92862a990ad8bd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:03 +1100 Subject: vfs: plumb remap flags through the vfs dedupe functions Plumb a remap_flags argument through the vfs_dedupe_file_range_one functions so that dedupe can take advantage of it. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1c5e55d2a67d..544ab5083b48 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1859,7 +1859,7 @@ extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, - loff_t len); + loff_t len, unsigned int remap_flags); struct super_operations { -- cgit v1.2.3 From eca3654e3cc7d93e9734d0fa96cfb15c7f356244 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:10 +1100 Subject: vfs: enable remap callers that can handle short operations Plumb in a remap flag that enables the filesystem remap handler to shorten remapping requests for callers that can handle it. Now copy_file_range can report partial success (in case we run up against alignment problems, resource limits, etc.). We also enable CAN_SHORTEN for fideduperange to maintain existing userspace-visible behavior where xfs/btrfs shorten the dedupe range to avoid stale post-eof data exposure. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 544ab5083b48..34c22d695011 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1727,8 +1727,10 @@ struct block_device_operations; * See Documentation/filesystems/vfs.txt for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) + * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) +#define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of @@ -1736,9 +1738,8 @@ struct block_device_operations; * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. - * There are no flags yet, but subsequent commits will add some. */ -#define REMAP_FILE_ADVISORY (0) +#define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; -- cgit v1.2.3 From c32e5f39953fa6bbff35c655bdcb7b3128f1e79f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:17 +1100 Subject: vfs: hide file range comparison function There are no callers of vfs_dedupe_file_range_compare, so we might as well make it a static helper and remove the export. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 34c22d695011..346036a84f18 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1853,9 +1853,6 @@ extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); -extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, - struct inode *dest, loff_t destoff, - loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, -- cgit v1.2.3 From 966c37f2d77eb44d47af8e919267b1ba675b2eca Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 26 Oct 2018 11:30:35 +0800 Subject: ipv4/igmp: fix v1/v2 switchback timeout based on rfc3376, 8.12 Similiar with ipv6 mcast commit 89225d1ce6af3 ("net: ipv6: mld: fix v1/v2 switchback timeout to rfc3810, 9.12.") i) RFC3376 8.12. Older Version Querier Present Timeout says: The Older Version Querier Interval is the time-out for transitioning a host back to IGMPv3 mode once an older version query is heard. When an older version query is received, hosts set their Older Version Querier Present Timer to Older Version Querier Interval. This value MUST be ((the Robustness Variable) times (the Query Interval in the last Query received)) plus (one Query Response Interval). Currently we only use a hardcode value IGMP_V1/v2_ROUTER_PRESENT_TIMEOUT. Fix it by adding two new items mr_qi(Query Interval) and mr_qri(Query Response Interval) in struct in_device. Now we can calculate the switchback time via (mr_qrv * mr_qi) + mr_qri. We need update these values when receive IGMPv3 queries. Reported-by: Ying Xu Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index c759d1cbcedd..a64f21a97369 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -37,7 +37,9 @@ struct in_device { unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; - unsigned char mr_qrv; + unsigned long mr_qi; /* Query Interval */ + unsigned long mr_qri; /* Query Response Interval */ + unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; unsigned char mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ -- cgit v1.2.3 From ffb6ce7086ee2d68d8d6d987882f1c5e923fee7e Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Tue, 9 Oct 2018 14:40:55 +0800 Subject: platform/x86: asus-wmi: export function for evaluating WMI methods Export asus_wmi_evaluate_method() and related headers for use by other drivers. hid-asus is going to use this to avoid advertising that it has a keyboard backlight when the keyboard backlight is controlled via WMI. Signed-off-by: Daniel Drake Signed-off-by: Andy Shevchenko --- include/linux/platform_data/x86/asus-wmi.h | 101 +++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) create mode 100644 include/linux/platform_data/x86/asus-wmi.h (limited to 'include/linux') diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h new file mode 100644 index 000000000000..53dfc2541960 --- /dev/null +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PLATFORM_DATA_X86_ASUS_WMI_H +#define __PLATFORM_DATA_X86_ASUS_WMI_H + +#include +#include + +/* WMI Methods */ +#define ASUS_WMI_METHODID_SPEC 0x43455053 /* BIOS SPECification */ +#define ASUS_WMI_METHODID_SFBD 0x44424653 /* Set First Boot Device */ +#define ASUS_WMI_METHODID_GLCD 0x44434C47 /* Get LCD status */ +#define ASUS_WMI_METHODID_GPID 0x44495047 /* Get Panel ID?? (Resol) */ +#define ASUS_WMI_METHODID_QMOD 0x444F4D51 /* Quiet MODe */ +#define ASUS_WMI_METHODID_SPLV 0x4C425053 /* Set Panel Light Value */ +#define ASUS_WMI_METHODID_AGFN 0x4E464741 /* FaN? */ +#define ASUS_WMI_METHODID_SFUN 0x4E554653 /* FUNCtionalities */ +#define ASUS_WMI_METHODID_SDSP 0x50534453 /* Set DiSPlay output */ +#define ASUS_WMI_METHODID_GDSP 0x50534447 /* Get DiSPlay output */ +#define ASUS_WMI_METHODID_DEVP 0x50564544 /* DEVice Policy */ +#define ASUS_WMI_METHODID_OSVR 0x5256534F /* OS VeRsion */ +#define ASUS_WMI_METHODID_DSTS 0x53544344 /* Device STatuS */ +#define ASUS_WMI_METHODID_DSTS2 0x53545344 /* Device STatuS #2*/ +#define ASUS_WMI_METHODID_BSTS 0x53545342 /* Bios STatuS ? */ +#define ASUS_WMI_METHODID_DEVS 0x53564544 /* DEVice Set */ +#define ASUS_WMI_METHODID_CFVS 0x53564643 /* CPU Frequency Volt Set */ +#define ASUS_WMI_METHODID_KBFT 0x5446424B /* KeyBoard FilTer */ +#define ASUS_WMI_METHODID_INIT 0x54494E49 /* INITialize */ +#define ASUS_WMI_METHODID_HKEY 0x59454B48 /* Hot KEY ?? */ + +#define ASUS_WMI_UNSUPPORTED_METHOD 0xFFFFFFFE + +/* Wireless */ +#define ASUS_WMI_DEVID_HW_SWITCH 0x00010001 +#define ASUS_WMI_DEVID_WIRELESS_LED 0x00010002 +#define ASUS_WMI_DEVID_CWAP 0x00010003 +#define ASUS_WMI_DEVID_WLAN 0x00010011 +#define ASUS_WMI_DEVID_WLAN_LED 0x00010012 +#define ASUS_WMI_DEVID_BLUETOOTH 0x00010013 +#define ASUS_WMI_DEVID_GPS 0x00010015 +#define ASUS_WMI_DEVID_WIMAX 0x00010017 +#define ASUS_WMI_DEVID_WWAN3G 0x00010019 +#define ASUS_WMI_DEVID_UWB 0x00010021 + +/* Leds */ +/* 0x000200XX and 0x000400XX */ +#define ASUS_WMI_DEVID_LED1 0x00020011 +#define ASUS_WMI_DEVID_LED2 0x00020012 +#define ASUS_WMI_DEVID_LED3 0x00020013 +#define ASUS_WMI_DEVID_LED4 0x00020014 +#define ASUS_WMI_DEVID_LED5 0x00020015 +#define ASUS_WMI_DEVID_LED6 0x00020016 + +/* Backlight and Brightness */ +#define ASUS_WMI_DEVID_ALS_ENABLE 0x00050001 /* Ambient Light Sensor */ +#define ASUS_WMI_DEVID_BACKLIGHT 0x00050011 +#define ASUS_WMI_DEVID_BRIGHTNESS 0x00050012 +#define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021 +#define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ +#define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 + +/* Misc */ +#define ASUS_WMI_DEVID_CAMERA 0x00060013 + +/* Storage */ +#define ASUS_WMI_DEVID_CARDREADER 0x00080013 + +/* Input */ +#define ASUS_WMI_DEVID_TOUCHPAD 0x00100011 +#define ASUS_WMI_DEVID_TOUCHPAD_LED 0x00100012 + +/* Fan, Thermal */ +#define ASUS_WMI_DEVID_THERMAL_CTRL 0x00110011 +#define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 + +/* Power */ +#define ASUS_WMI_DEVID_PROCESSOR_STATE 0x00120012 + +/* Deep S3 / Resume on LID open */ +#define ASUS_WMI_DEVID_LID_RESUME 0x00120031 + +/* DSTS masks */ +#define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 +#define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 +#define ASUS_WMI_DSTS_PRESENCE_BIT 0x00010000 +#define ASUS_WMI_DSTS_USER_BIT 0x00020000 +#define ASUS_WMI_DSTS_BIOS_BIT 0x00040000 +#define ASUS_WMI_DSTS_BRIGHTNESS_MASK 0x000000FF +#define ASUS_WMI_DSTS_MAX_BRIGTH_MASK 0x0000FF00 +#define ASUS_WMI_DSTS_LIGHTBAR_MASK 0x0000000F + +#if IS_REACHABLE(CONFIG_ASUS_WMI) +int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, u32 *retval); +#else +static inline int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, + u32 *retval) +{ + return -ENODEV; +} +#endif + +#endif /* __PLATFORM_DATA_X86_ASUS_WMI_H */ -- cgit v1.2.3 From f813f21971b96f61a789dd48151f92220fdd2e0a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Tue, 30 Oct 2018 15:04:06 -0700 Subject: mm/hmm: fix utf8 ... MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "HMM updates, improvements and fixes", v2 Few fixes that only affect HMM users. Improve the synchronization call back so that we match was other mmu_notifier listener do and add proper support to the new blockable flags in the process. For curious folks here are branches to leverage HMM in various existing device drivers: https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-nouveau-v01 https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-radeon-v00 https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-intel-v00 More to come (amd gpu, Mellanox, ...) I expect more of the preparatory work for nouveau will be merge in 4.20 (like we have been doing since 4.16) and i will wait until this patchset is upstream before pushing the patches that actualy make use of HMM (to avoid complex tree inter-dependency). This patch (of 6): Somehow utf=8 must have been broken. Link: http://lkml.kernel.org/r/20181019160442.18723-2-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index dde947083d4e..42b1ae915915 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -11,7 +11,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * Authors: Jérôme Glisse + * Authors: Jérôme Glisse */ /* * Heterogeneous Memory Management (HMM) -- cgit v1.2.3 From 44532d4c591c10d6907ac5030373bc306617d92b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Tue, 30 Oct 2018 15:04:24 -0700 Subject: mm/hmm: use a structure for update callback parameters MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use a structure to gather all the parameters for the update callback. This make it easier when adding new parameters by avoiding having to update all callback function signature. The hmm_update structure is always associated with a mmu_notifier callbacks so we are not planing on grouping multiple updates together. Nor do we care about page size for the range as range will over fully cover the page being invalidated (this is a mmu_notifier property). Link: http://lkml.kernel.org/r/20181019160442.18723-6-jglisse@redhat.com Signed-off-by: Jérôme Glisse Cc: Ralph Campbell Cc: John Hubbard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 42b1ae915915..c6fb869a81c0 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -274,13 +274,28 @@ static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, struct hmm_mirror; /* - * enum hmm_update_type - type of update + * enum hmm_update_event - type of update * @HMM_UPDATE_INVALIDATE: invalidate range (no indication as to why) */ -enum hmm_update_type { +enum hmm_update_event { HMM_UPDATE_INVALIDATE, }; +/* + * struct hmm_update - HMM update informations for callback + * + * @start: virtual start address of the range to update + * @end: virtual end address of the range to update + * @event: event triggering the update (what is happening) + * @blockable: can the callback block/sleep ? + */ +struct hmm_update { + unsigned long start; + unsigned long end; + enum hmm_update_event event; + bool blockable; +}; + /* * struct hmm_mirror_ops - HMM mirror device operations callback * @@ -300,9 +315,9 @@ struct hmm_mirror_ops { /* sync_cpu_device_pagetables() - synchronize page tables * * @mirror: pointer to struct hmm_mirror - * @update_type: type of update that occurred to the CPU page table - * @start: virtual start address of the range to update - * @end: virtual end address of the range to update + * @update: update informations (see struct hmm_update) + * Returns: -EAGAIN if update.blockable false and callback need to + * block, 0 otherwise. * * This callback ultimately originates from mmu_notifiers when the CPU * page table is updated. The device driver must update its page table @@ -313,10 +328,8 @@ struct hmm_mirror_ops { * page tables are completely updated (TLBs flushed, etc); this is a * synchronous call. */ - void (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, - enum hmm_update_type update_type, - unsigned long start, - unsigned long end); + int (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, + const struct hmm_update *update); }; /* -- cgit v1.2.3 From 7275b097851a5e2e0dd4da039c7e96b59ac5314e Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:04:59 -0700 Subject: linux/bitmap.h: handle constant zero-size bitmaps correctly The static inlines in bitmap.h do not handle a compile-time constant nbits==0 correctly (they dereference the passed src or dst pointers, despite only 0 words being valid to access). I had the 0-day buildbot chew on a patch [1] that would cause build failures for such cases without complaining, suggesting that we don't have any such users currently, at least for the 70 .config/arch combinations that was built. Should any turn up, make sure they use the out-of-line versions, which do handle nbits==0 correctly. This is of course not the most efficient, but it's much less churn than teaching all the static inlines an "if (zero_const_nbits())", and since we don't have any current instances, this doesn't affect existing code at all. [1] lkml.kernel.org/r/20180815085539.27485-1-linux@rasmusvillemoes.dk Link: http://lkml.kernel.org/r/20180818131623.8755-3-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Cc: Yury Norov Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index acf5e8df3504..a9805bacbd7c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -204,8 +204,13 @@ extern int bitmap_print_to_pagebuf(bool list, char *buf, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +/* + * The static inlines below do not handle constant nbits==0 correctly, + * so make such users (should any ever turn up) call the out-of-line + * versions. + */ #define small_const_nbits(nbits) \ - (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG) + (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0) static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { -- cgit v1.2.3 From c8cebc553368209426f7279736db4f88f1853396 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:05:02 -0700 Subject: linux/bitmap.h: remove redundant uses of small_const_nbits() In the _zero, _fill and _copy functions, the small_const_nbits branch is redundant. If nbits is small and const, gcc knows full well that BITS_TO_LONGS(nbits) is 1, so len is also a compile-time constant (sizeof(long)), and calling memset or memcpy with a length argument of sizeof(long) makes gcc generate the expected code anyway: #include void a(unsigned long *x) { memset(x, 0, 8); } void b(unsigned long *x) { memset(x, 0xff, 8); } void c(unsigned long *x, const unsigned long *y) { memcpy(x, y, 8); } turns into 0000000000000000 : 0: 48 c7 07 00 00 00 00 movq $0x0,(%rdi) 7: c3 retq 8: 0f 1f 84 00 00 00 00 nopl 0x0(%rax,%rax,1) f: 00 0000000000000010 : 10: 48 c7 07 ff ff ff ff movq $0xffffffffffffffff,(%rdi) 17: c3 retq 18: 0f 1f 84 00 00 00 00 nopl 0x0(%rax,%rax,1) 1f: 00 0000000000000020 : 20: 48 8b 06 mov (%rsi),%rax 23: 48 89 07 mov %rax,(%rdi) 26: c3 retq Link: http://lkml.kernel.org/r/20180818131623.8755-4-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Cc: Yury Norov Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 24 ++++++------------------ 1 file changed, 6 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index a9805bacbd7c..004cd42a3c4d 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -214,33 +214,21 @@ extern int bitmap_print_to_pagebuf(bool list, char *buf, static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { - if (small_const_nbits(nbits)) - *dst = 0UL; - else { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0, len); - } + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memset(dst, 0, len); } static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - if (small_const_nbits(nbits)) - *dst = ~0UL; - else { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0xff, len); - } + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memset(dst, 0xff, len); } static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { - if (small_const_nbits(nbits)) - *dst = *src; - else { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memcpy(dst, src, len); - } + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memcpy(dst, src, len); } /* -- cgit v1.2.3 From d9873969fa8725dc6a5a21ab788c057fd8719751 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:05:07 -0700 Subject: linux/bitmap.h: fix type of nbits in bitmap_shift_right() Most other bitmap API, including the OOL version __bitmap_shift_right, take unsigned nbits. This was accidentally left out from 2fbad29917c98. Link: http://lkml.kernel.org/r/20180818131623.8755-5-linux@rasmusvillemoes.dk Fixes: 2fbad29917c98 ("lib: bitmap: change bitmap_shift_right to take unsigned parameters") Signed-off-by: Rasmus Villemoes Reported-by: Yury Norov Reviewed-by: Andy Shevchenko Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 004cd42a3c4d..4032680e629d 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -391,7 +391,7 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, } static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, - unsigned int shift, int nbits) + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; -- cgit v1.2.3 From 41e7b1661ffbf562d3aa2b7ce4ad283db50b711a Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:05:10 -0700 Subject: linux/bitmap.h: relax comment on compile-time constant nbits It's not clear what's so horrible about emitting a function call to handle a run-time sized bitmap. Moreover, gcc also emits a function call for a compile-time-constant-but-huge nbits, so the comment isn't even accurate. Link: http://lkml.kernel.org/r/20180818131623.8755-6-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Cc: Yury Norov Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 4032680e629d..f58e97446abc 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -28,8 +28,8 @@ * The available bitmap operations and their rough meaning in the * case that the bitmap is a single unsigned long are thus: * - * Note that nbits should be always a compile time evaluable constant. - * Otherwise many inlines will generate horrible code. + * The generated code is more efficient when nbits is known at + * compile-time and at most BITS_PER_LONG. * * :: * -- cgit v1.2.3 From 7e5ca363a5a1ec42c54dc1e0644b361a2daf984c Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Tue, 30 Oct 2018 15:05:42 -0700 Subject: lib/rbtree.c: fix typo in comment of rb_insert_augmented() The function name in the comment is not correct. Link: http://lkml.kernel.org/r/20181010021344.60433-1-richard.weiyang@gmail.com Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree_augmented.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index af8a61be2d8d..9510c677ac70 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -51,8 +51,8 @@ extern void __rb_insert_augmented(struct rb_node *node, * * On insertion, the user must update the augmented information on the path * leading to the inserted node, then call rb_link_node() as usual and - * rb_augment_inserted() instead of the usual rb_insert_color() call. - * If rb_augment_inserted() rebalances the rbtree, it will callback into + * rb_insert_augmented() instead of the usual rb_insert_color() call. + * If rb_insert_augmented() rebalances the rbtree, it will callback into * a user provided function to update the augmented information on the * affected subtrees. */ -- cgit v1.2.3 From 89976005536c47a788bdd6cef5a4e9fef3c0de32 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 30 Oct 2018 15:05:49 -0700 Subject: include/linux/compat.h: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Link: http://lkml.kernel.org/r/20181013115048.GA3262@embeddedor.com Signed-off-by: Gustavo A. R. Silva Acked-by: Kees Cook Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index d30e4dbd4be2..06e77473f175 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -488,8 +488,11 @@ put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, compat_sigset_t v; switch (_NSIG_WORDS) { case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; + /* fall through */ case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; + /* fall through */ case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; + /* fall through */ case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; } return copy_to_user(compat, &v, size) ? -EFAULT : 0; -- cgit v1.2.3 From 3819ddec1f8c8a5daf215bec4067f8fd1dc40d6d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 30 Oct 2018 15:07:10 -0700 Subject: include/linux/signal.h: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Link: http://lkml.kernel.org/r/20181013114847.GA3160@embeddedor.com Signed-off-by: Gustavo A. R. Silva Acked-by: Kees Cook Reviewed-by: Michael Ellerman Cc: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signal.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 200ed96a05af..f428e86f4800 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -129,9 +129,11 @@ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \ b3 = b->sig[3]; b2 = b->sig[2]; \ r->sig[3] = op(a3, b3); \ r->sig[2] = op(a2, b2); \ + /* fall through */ \ case 2: \ a1 = a->sig[1]; b1 = b->sig[1]; \ r->sig[1] = op(a1, b1); \ + /* fall through */ \ case 1: \ a0 = a->sig[0]; b0 = b->sig[0]; \ r->sig[0] = op(a0, b0); \ @@ -161,7 +163,9 @@ static inline void name(sigset_t *set) \ switch (_NSIG_WORDS) { \ case 4: set->sig[3] = op(set->sig[3]); \ set->sig[2] = op(set->sig[2]); \ + /* fall through */ \ case 2: set->sig[1] = op(set->sig[1]); \ + /* fall through */ \ case 1: set->sig[0] = op(set->sig[0]); \ break; \ default: \ @@ -182,6 +186,7 @@ static inline void sigemptyset(sigset_t *set) memset(set, 0, sizeof(sigset_t)); break; case 2: set->sig[1] = 0; + /* fall through */ case 1: set->sig[0] = 0; break; } @@ -194,6 +199,7 @@ static inline void sigfillset(sigset_t *set) memset(set, -1, sizeof(sigset_t)); break; case 2: set->sig[1] = -1; + /* fall through */ case 1: set->sig[0] = -1; break; } -- cgit v1.2.3 From 69a60bc75fe73511af89328ded1b33bc4a625a5c Mon Sep 17 00:00:00 2001 From: Alexander Pateenok Date: Tue, 30 Oct 2018 15:07:36 -0700 Subject: percpu: remove PER_CPU_DEF_ATTRIBUTES macro The macro is not used: $ grep -r PER_CPU_DEF_ATTRIBUTES include/linux/percpu-defs.h: __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \ include/linux/percpu-defs.h: __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES \ include/asm-generic/percpu.h:#ifndef PER_CPU_DEF_ATTRIBUTES include/asm-generic/percpu.h:#define PER_CPU_DEF_ATTRIBUTES It was added with b01e8dc34379 ("alpha: fix percpu build breakage") and removed in 2009 with b01e8dc34379..6088464cf1ae. Link: http://lkml.kernel.org/r/20180821164904.qqhcduimjznods66@K55DR.localdomain Signed-off-by: Alexander Pateenok Acked-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu-defs.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 2d2096ba1cfe..1ce8e264a269 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -91,8 +91,7 @@ extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ extern __PCPU_ATTRS(sec) __typeof__(type) name; \ - __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \ - __typeof__(type) name + __PCPU_ATTRS(sec) __weak __typeof__(type) name #else /* * Normal declaration and definition macros. @@ -101,8 +100,7 @@ extern __PCPU_ATTRS(sec) __typeof__(type) name #define DEFINE_PER_CPU_SECTION(type, name, sec) \ - __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES \ - __typeof__(type) name + __PCPU_ATTRS(sec) __typeof__(type) name #endif /* -- cgit v1.2.3 From b4a991ec584b3ce333342c431c3cc4fef8a690d7 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:40 -0700 Subject: mm: remove CONFIG_NO_BOOTMEM All achitectures select NO_BOOTMEM which essentially becomes 'Y' for any kernel configuration and therefore it can be removed. [alexander.h.duyck@linux.intel.com: remove now defunct NO_BOOTMEM from depends list for deferred init] Link: http://lkml.kernel.org/r/20180925201814.3576.15105.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/1536927045-23536-3-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Signed-off-by: Alexander Duyck Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 36 ++---------------------------------- include/linux/mmzone.h | 5 +---- 2 files changed, 3 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 42515195d7d8..1f005b5c1555 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,34 +26,6 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -#ifndef CONFIG_NO_BOOTMEM -/** - * struct bootmem_data - per-node information used by the bootmem allocator - * @node_min_pfn: the starting physical address of the node's memory - * @node_low_pfn: the end physical address of the directly addressable memory - * @node_bootmem_map: is a bitmap pointer - the bits represent all physical - * memory pages (including holes) on the node. - * @last_end_off: the offset within the page of the end of the last allocation; - * if 0, the page used is full - * @hint_idx: the PFN of the page used with the last allocation; - * together with using this with the @last_end_offset field, - * a test can be made to see if allocations can be merged - * with the page used for the last allocation rather than - * using up a full new page. - * @list: list entry in the linked list ordered by the memory addresses - */ -typedef struct bootmem_data { - unsigned long node_min_pfn; - unsigned long node_low_pfn; - void *node_bootmem_map; - unsigned long last_end_off; - unsigned long hint_idx; - struct list_head list; -} bootmem_data_t; - -extern bootmem_data_t bootmem_node_data[]; -#endif - extern unsigned long bootmem_bootmap_pages(unsigned long); extern unsigned long init_bootmem_node(pg_data_t *pgdat, @@ -125,12 +97,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long align, unsigned long goal) __malloc; -#ifdef CONFIG_NO_BOOTMEM /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 -#else -#define BOOTMEM_LOW_LIMIT __pa(MAX_DMA_ADDRESS) -#endif #ifndef ARCH_LOW_ADDRESS_LIMIT #define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL @@ -165,7 +133,7 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) -#if defined(CONFIG_HAVE_MEMBLOCK) && defined(CONFIG_NO_BOOTMEM) +#if defined(CONFIG_HAVE_MEMBLOCK) /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 @@ -373,7 +341,7 @@ static inline void __init memblock_free_late( { free_bootmem_late(base, size); } -#endif /* defined(CONFIG_HAVE_MEMBLOCK) && defined(CONFIG_NO_BOOTMEM) */ +#endif /* defined(CONFIG_HAVE_MEMBLOCK) */ extern void *alloc_large_system_hash(const char *tablename, unsigned long bucketsize, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9f0caccd5833..847705a6d0ec 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -633,9 +633,6 @@ typedef struct pglist_data { struct page_ext *node_page_ext; #endif #endif -#ifndef CONFIG_NO_BOOTMEM - struct bootmem_data *bdata; -#endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, node_present_pages @@ -869,7 +866,7 @@ static inline int is_highmem_idx(enum zone_type idx) } /** - * is_highmem - helper function to quickly check if a struct zone is a + * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone - pointer to struct zone variable -- cgit v1.2.3 From aca52c39838910605b1063a2243f553aa2a02d5c Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:44 -0700 Subject: mm: remove CONFIG_HAVE_MEMBLOCK All architecures use memblock for early memory management. There is no need for the CONFIG_HAVE_MEMBLOCK configuration option. [rppt@linux.vnet.ibm.com: of/fdt: fixup #ifdefs] Link: http://lkml.kernel.org/r/20180919103457.GA20545@rapoport-lnx [rppt@linux.vnet.ibm.com: csky: fixups after bootmem removal] Link: http://lkml.kernel.org/r/20180926112744.GC4628@rapoport-lnx [rppt@linux.vnet.ibm.com: remove stale #else and the code it protects] Link: http://lkml.kernel.org/r/1538067825-24835-1-git-send-email-rppt@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1536927045-23536-4-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Tested-by: Jonathan Cameron Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 112 ----------------------------------------------- include/linux/memblock.h | 7 --- include/linux/mm.h | 2 +- 3 files changed, 1 insertion(+), 120 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 1f005b5c1555..ee61ac355104 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -132,9 +132,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define alloc_bootmem_low_pages_node(pgdat, x) \ __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) - -#if defined(CONFIG_HAVE_MEMBLOCK) - /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) @@ -234,115 +231,6 @@ static inline void __init memblock_free_late( __memblock_free_late(base, size); } -#else - -#define BOOTMEM_ALLOC_ACCESSIBLE 0 - - -/* Fall back to all the existing bootmem APIs */ -static inline void * __init memblock_virt_alloc( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_raw( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_nopanic(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_nopanic( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_nopanic(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_low( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_low(size, align, 0); -} - -static inline void * __init memblock_virt_alloc_low_nopanic( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_low_nopanic(size, align, 0); -} - -static inline void * __init memblock_virt_alloc_from_nopanic( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return __alloc_bootmem_nopanic(size, align, min_addr); -} - -static inline void * __init memblock_virt_alloc_node( - phys_addr_t size, int nid) -{ - return __alloc_bootmem_node(NODE_DATA(nid), size, SMP_CACHE_BYTES, - BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_node_nopanic( - phys_addr_t size, int nid) -{ - return __alloc_bootmem_node_nopanic(NODE_DATA(nid), size, - SMP_CACHE_BYTES, - BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_try_nid(phys_addr_t size, - phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return __alloc_bootmem_node_high(NODE_DATA(nid), size, align, - min_addr); -} - -static inline void * __init memblock_virt_alloc_try_nid_raw( - phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, align, - min_addr, max_addr); -} - -static inline void * __init memblock_virt_alloc_try_nid_nopanic( - phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, align, - min_addr, max_addr); -} - -static inline void __init memblock_free_early( - phys_addr_t base, phys_addr_t size) -{ - free_bootmem(base, size); -} - -static inline void __init memblock_free_early_nid( - phys_addr_t base, phys_addr_t size, int nid) -{ - free_bootmem_node(NODE_DATA(nid), base, size); -} - -static inline void __init memblock_free_late( - phys_addr_t base, phys_addr_t size) -{ - free_bootmem_late(base, size); -} -#endif /* defined(CONFIG_HAVE_MEMBLOCK) */ - extern void *alloc_large_system_hash(const char *tablename, unsigned long bucketsize, unsigned long numentries, diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 2acdd046df2d..224d27363cca 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -2,7 +2,6 @@ #define _LINUX_MEMBLOCK_H #ifdef __KERNEL__ -#ifdef CONFIG_HAVE_MEMBLOCK /* * Logical memory blocks. * @@ -440,12 +439,6 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) { } #endif -#else -static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align) -{ - return 0; -} -#endif /* CONFIG_HAVE_MEMBLOCK */ #endif /* __KERNEL__ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 1e52b8fd1685..fcf9cc9d535f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2163,7 +2163,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif -#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) +#if !defined(CONFIG_FLAT_NODE_MEM_MAP) void zero_resv_unavail(void); #else static inline void zero_resv_unavail(void) {} -- cgit v1.2.3 From 355c45affca7114ab510e296a5b7012943aeea17 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:50 -0700 Subject: mm: remove bootmem allocator implementation. All architectures have been converted to use MEMBLOCK + NO_BOOTMEM. The bootmem allocator implementation can be removed. Link: http://lkml.kernel.org/r/1536927045-23536-5-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index ee61ac355104..fce6278a1724 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,14 +26,6 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -extern unsigned long bootmem_bootmap_pages(unsigned long); - -extern unsigned long init_bootmem_node(pg_data_t *pgdat, - unsigned long freepfn, - unsigned long startpfn, - unsigned long endpfn); -extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); - extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); @@ -55,14 +47,6 @@ extern void free_bootmem_late(unsigned long physaddr, unsigned long size); #define BOOTMEM_DEFAULT 0 #define BOOTMEM_EXCLUSIVE (1<<0) -extern int reserve_bootmem(unsigned long addr, - unsigned long size, - int flags); -extern int reserve_bootmem_node(pg_data_t *pgdat, - unsigned long physaddr, - unsigned long size, - int flags); - extern void *__alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal); -- cgit v1.2.3 From b146ada221c178a384fee2a8e2e5b2e8a04476b1 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:54 -0700 Subject: mm: nobootmem: remove dead code Several bootmem functions and macros are not used. Remove them. Link: http://lkml.kernel.org/r/1536927045-23536-6-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index fce6278a1724..b74bafd110b9 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -36,17 +36,6 @@ extern void free_bootmem_node(pg_data_t *pgdat, extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); -/* - * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, - * the architecture-specific code should honor this). - * - * If flags is BOOTMEM_DEFAULT, then the return value is always 0 (success). - * If flags contains BOOTMEM_EXCLUSIVE, then -EBUSY is returned if the memory - * already was reserved. - */ -#define BOOTMEM_DEFAULT 0 -#define BOOTMEM_EXCLUSIVE (1<<0) - extern void *__alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal); @@ -73,13 +62,6 @@ void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat, extern void *__alloc_bootmem_low(unsigned long size, unsigned long align, unsigned long goal) __malloc; -void *__alloc_bootmem_low_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 @@ -92,8 +74,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_align(x, align) \ __alloc_bootmem(x, align, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_nopanic(x) \ - __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages(x) \ __alloc_bootmem(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages_nopanic(x) \ @@ -104,17 +84,11 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_node_nopanic(pgdat, x) \ - __alloc_bootmem_node_nopanic(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_low(x) \ __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) -#define alloc_bootmem_low_pages_nopanic(x) \ - __alloc_bootmem_low_nopanic(x, PAGE_SIZE, 0) #define alloc_bootmem_low_pages(x) \ __alloc_bootmem_low(x, PAGE_SIZE, 0) -#define alloc_bootmem_low_pages_node(pgdat, x) \ - __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 -- cgit v1.2.3 From 9a8dd708d547268c899f1cb443c49bd4d8c84eb3 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:59 -0700 Subject: memblock: rename memblock_alloc{_nid,_try_nid} to memblock_phys_alloc* Make it explicit that the caller gets a physical address rather than a virtual one. This will also allow using meblock_alloc prefix for memblock allocations returning virtual address, which is done in the following patches. The conversion is done using the following semantic patch: @@ expression e1, e2, e3; @@ ( - memblock_alloc(e1, e2) + memblock_phys_alloc(e1, e2) | - memblock_alloc_nid(e1, e2, e3) + memblock_phys_alloc_nid(e1, e2, e3) | - memblock_alloc_try_nid(e1, e2, e3) + memblock_phys_alloc_try_nid(e1, e2, e3) ) Link: http://lkml.kernel.org/r/1536927045-23536-7-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 224d27363cca..9d46a7204975 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -300,10 +300,10 @@ static inline int memblock_get_region_node(const struct memblock_region *r) } #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); -phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); +phys_addr_t memblock_phys_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); +phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); -phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align); +phys_addr_t memblock_phys_alloc(phys_addr_t size, phys_addr_t align); /* * Set the allocation direction to bottom-up or top-down. -- cgit v1.2.3 From eb31d559f1e8390195372cd51cfb198da8bc84b9 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:08:04 -0700 Subject: memblock: remove _virt from APIs returning virtual address The conversion is done using sed -i 's@memblock_virt_alloc@memblock_alloc@g' \ $(git grep -l memblock_virt_alloc) Link: http://lkml.kernel.org/r/1536927045-23536-8-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index b74bafd110b9..7d91f0f5ee44 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -95,78 +95,78 @@ extern void *__alloc_bootmem_low(unsigned long size, #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) /* FIXME: Move to memblock.h at a point where we remove nobootmem.c */ -void *memblock_virt_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, +void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void *memblock_virt_alloc_try_nid_nopanic(phys_addr_t size, +void *memblock_alloc_try_nid_nopanic(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void *memblock_virt_alloc_try_nid(phys_addr_t size, phys_addr_t align, +void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); void __memblock_free_early(phys_addr_t base, phys_addr_t size); void __memblock_free_late(phys_addr_t base, phys_addr_t size); -static inline void * __init memblock_virt_alloc( +static inline void * __init memblock_alloc( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_raw( +static inline void * __init memblock_alloc_raw( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_nopanic( +static inline void * __init memblock_alloc_nopanic( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_nopanic(size, align, + return memblock_alloc_try_nid_nopanic(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_low( +static inline void * __init memblock_alloc_low( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid(size, align, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_low_nopanic( +static inline void * __init memblock_alloc_low_nopanic( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_nopanic(size, align, + return memblock_alloc_try_nid_nopanic(size, align, BOOTMEM_LOW_LIMIT, ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_from_nopanic( +static inline void * __init memblock_alloc_from_nopanic( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) { - return memblock_virt_alloc_try_nid_nopanic(size, align, min_addr, + return memblock_alloc_try_nid_nopanic(size, align, min_addr, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_node( +static inline void * __init memblock_alloc_node( phys_addr_t size, int nid) { - return memblock_virt_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } -static inline void * __init memblock_virt_alloc_node_nopanic( +static inline void * __init memblock_alloc_node_nopanic( phys_addr_t size, int nid) { - return memblock_virt_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } -- cgit v1.2.3 From 3913c8f9f96bb75a062ad16ea10a1cdad48bb716 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:08:36 -0700 Subject: memblock: add align parameter to memblock_alloc_node() With the align parameter memblock_alloc_node() can be used as drop in replacement for alloc_bootmem_pages_node() and __alloc_bootmem_node(), which is done in the following patches. Link: http://lkml.kernel.org/r/1536927045-23536-15-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 7d91f0f5ee44..3896af205303 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -157,9 +157,9 @@ static inline void * __init memblock_alloc_from_nopanic( } static inline void * __init memblock_alloc_node( - phys_addr_t size, int nid) + phys_addr_t size, phys_addr_t align, int nid) { - return memblock_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } -- cgit v1.2.3 From 4fc4a09e4cc1126c4e8a86c293425cffa2a2eb3c Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:03 -0700 Subject: memblock: replace __alloc_bootmem with memblock_alloc_from The functions are equivalent, just the later does not require nobootmem translation layer. The conversion is done using the following semantic patch: @@ expression size, align, goal; @@ - __alloc_bootmem(size, align, goal) + memblock_alloc_from(size, align, goal) Link: http://lkml.kernel.org/r/1536927045-23536-21-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 3896af205303..c97c105cfc67 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -122,6 +122,14 @@ static inline void * __init memblock_alloc_raw( NUMA_NO_NODE); } +static inline void * __init memblock_alloc_from( + phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) +{ + return memblock_alloc_try_nid(size, align, min_addr, + BOOTMEM_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + static inline void * __init memblock_alloc_nopanic( phys_addr_t size, phys_addr_t align) { -- cgit v1.2.3 From 6c7835f8d0d1839ca93bd3cf6faa15706f03d604 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:15 -0700 Subject: mm: nobootmem: remove bootmem allocation APIs The bootmem compatibility APIs are not used and can be removed. Link: http://lkml.kernel.org/r/1536927045-23536-23-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 47 ----------------------------------------------- 1 file changed, 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index c97c105cfc67..73f1272fce20 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -36,33 +36,6 @@ extern void free_bootmem_node(pg_data_t *pgdat, extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); -extern void *__alloc_bootmem(unsigned long size, - unsigned long align, - unsigned long goal); -extern void *__alloc_bootmem_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_node(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -void *__alloc_bootmem_node_high(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) __malloc; -extern void *__alloc_bootmem_low(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; - /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 @@ -70,26 +43,6 @@ extern void *__alloc_bootmem_low(unsigned long size, #define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL #endif -#define alloc_bootmem(x) \ - __alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_align(x, align) \ - __alloc_bootmem(x, align, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages(x) \ - __alloc_bootmem(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_nopanic(x) \ - __alloc_bootmem_nopanic(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_node(pgdat, x) \ - __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_node_nopanic(pgdat, x) \ - __alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_node(pgdat, x) \ - __alloc_bootmem_node(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) - -#define alloc_bootmem_low(x) \ - __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) -#define alloc_bootmem_low_pages(x) \ - __alloc_bootmem_low(x, PAGE_SIZE, 0) - /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) -- cgit v1.2.3 From 2013288f723887837d2f1cebef5fcf663b2319de Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:21 -0700 Subject: memblock: replace free_bootmem{_node} with memblock_free The free_bootmem and free_bootmem_node are merely wrappers for memblock_free. Replace their usage with a call to memblock_free using the following semantic patch: @@ expression e1, e2, e3; @@ ( - free_bootmem(e1, e2) + memblock_free(e1, e2) | - free_bootmem_node(e1, e2, e3) + memblock_free(e2, e3) ) Link: http://lkml.kernel.org/r/1536927045-23536-24-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 73f1272fce20..706cf8ef6678 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -30,10 +30,6 @@ extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); -extern void free_bootmem_node(pg_data_t *pgdat, - unsigned long addr, - unsigned long size); -extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); /* We are using top down, so it is safe to use 0 here */ -- cgit v1.2.3 From 53ab85ebfd27cdf16c8ddc72781c072a63bef3cb Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:25 -0700 Subject: memblock: replace free_bootmem_late with memblock_free_late The free_bootmem_late and memblock_free_late do exactly the same thing: they iterate over a range and give pages to the page allocator. Replace calls to free_bootmem_late with calls to memblock_free_late and remove the bootmem variant. Link: http://lkml.kernel.org/r/1536927045-23536-25-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 706cf8ef6678..bcc7e2fcb6a6 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -30,8 +30,6 @@ extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); -extern void free_bootmem_late(unsigned long physaddr, unsigned long size); - /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 -- cgit v1.2.3 From c6ffc5ca8fb311a89cb6de5c31b6511308ddac8d Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:30 -0700 Subject: memblock: rename free_all_bootmem to memblock_free_all The conversion is done using sed -i 's@free_all_bootmem@memblock_free_all@' \ $(git grep -l free_all_bootmem) Link: http://lkml.kernel.org/r/1536927045-23536-26-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index bcc7e2fcb6a6..b58873a567b2 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,7 +26,7 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -extern unsigned long free_all_bootmem(void); +extern unsigned long memblock_free_all(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); -- cgit v1.2.3 From 57c8a661d95dff48dd9c2f2496139082bbaf241a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:49 -0700 Subject: mm: remove include/linux/bootmem.h Move remaining definitions and declarations from include/linux/bootmem.h into include/linux/memblock.h and remove the redundant header. The includes were replaced with the semantic patch below and then semi-automated removal of duplicated '#include @@ @@ - #include + #include [sfr@canb.auug.org.au: dma-direct: fix up for the removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181002185342.133d1680@canb.auug.org.au [sfr@canb.auug.org.au: powerpc: fix up for removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181005161406.73ef8727@canb.auug.org.au [sfr@canb.auug.org.au: x86/kaslr, ACPI/NUMA: fix for linux/bootmem.h removal] Link: http://lkml.kernel.org/r/20181008190341.5e396491@canb.auug.org.au Link: http://lkml.kernel.org/r/1536927045-23536-30-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 173 ----------------------------------------------- include/linux/memblock.h | 151 +++++++++++++++++++++++++++++++++++++++-- 2 files changed, 147 insertions(+), 177 deletions(-) delete mode 100644 include/linux/bootmem.h (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h deleted file mode 100644 index b58873a567b2..000000000000 --- a/include/linux/bootmem.h +++ /dev/null @@ -1,173 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999 - */ -#ifndef _LINUX_BOOTMEM_H -#define _LINUX_BOOTMEM_H - -#include -#include -#include -#include - -/* - * simple boot-time physical memory area allocator. - */ - -extern unsigned long max_low_pfn; -extern unsigned long min_low_pfn; - -/* - * highest page - */ -extern unsigned long max_pfn; -/* - * highest possible page - */ -extern unsigned long long max_possible_pfn; - -extern unsigned long memblock_free_all(void); -extern void reset_node_managed_pages(pg_data_t *pgdat); -extern void reset_all_zones_managed_pages(void); - -/* We are using top down, so it is safe to use 0 here */ -#define BOOTMEM_LOW_LIMIT 0 - -#ifndef ARCH_LOW_ADDRESS_LIMIT -#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL -#endif - -/* FIXME: use MEMBLOCK_ALLOC_* variants here */ -#define BOOTMEM_ALLOC_ACCESSIBLE 0 -#define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) - -/* FIXME: Move to memblock.h at a point where we remove nobootmem.c */ -void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, - phys_addr_t max_addr, int nid); -void *memblock_alloc_try_nid_nopanic(phys_addr_t size, - phys_addr_t align, phys_addr_t min_addr, - phys_addr_t max_addr, int nid); -void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void __memblock_free_early(phys_addr_t base, phys_addr_t size); -void __memblock_free_late(phys_addr_t base, phys_addr_t size); - -static inline void * __init memblock_alloc( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_raw( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_from( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return memblock_alloc_try_nid(size, align, min_addr, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_nopanic( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_nopanic(size, align, - BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_low( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid(size, align, - BOOTMEM_LOW_LIMIT, - ARCH_LOW_ADDRESS_LIMIT, - NUMA_NO_NODE); -} -static inline void * __init memblock_alloc_low_nopanic( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_nopanic(size, align, - BOOTMEM_LOW_LIMIT, - ARCH_LOW_ADDRESS_LIMIT, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_from_nopanic( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return memblock_alloc_try_nid_nopanic(size, align, min_addr, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_node( - phys_addr_t size, phys_addr_t align, int nid) -{ - return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, nid); -} - -static inline void * __init memblock_alloc_node_nopanic( - phys_addr_t size, int nid) -{ - return memblock_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - nid); -} - -static inline void __init memblock_free_early( - phys_addr_t base, phys_addr_t size) -{ - __memblock_free_early(base, size); -} - -static inline void __init memblock_free_early_nid( - phys_addr_t base, phys_addr_t size, int nid) -{ - __memblock_free_early(base, size); -} - -static inline void __init memblock_free_late( - phys_addr_t base, phys_addr_t size) -{ - __memblock_free_late(base, size); -} - -extern void *alloc_large_system_hash(const char *tablename, - unsigned long bucketsize, - unsigned long numentries, - int scale, - int flags, - unsigned int *_hash_shift, - unsigned int *_hash_mask, - unsigned long low_limit, - unsigned long high_limit); - -#define HASH_EARLY 0x00000001 /* Allocating during early boot? */ -#define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min - * shift passed via *_hash_shift */ -#define HASH_ZERO 0x00000004 /* Zero allocated hash table */ - -/* Only NUMA needs hash distribution. 64bit NUMA architectures have - * sufficient vmalloc space. - */ -#ifdef CONFIG_NUMA -#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT) -extern int hashdist; /* Distribute hashes across NUMA nodes? */ -#else -#define hashdist (0) -#endif - - -#endif /* _LINUX_BOOTMEM_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 9d46a7204975..1b4d85879cbe 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -15,6 +15,19 @@ #include #include +#include + +extern unsigned long max_low_pfn; +extern unsigned long min_low_pfn; + +/* + * highest page + */ +extern unsigned long max_pfn; +/* + * highest possible page + */ +extern unsigned long long max_possible_pfn; #define INIT_MEMBLOCK_REGIONS 128 #define INIT_PHYSMEM_REGIONS 4 @@ -119,6 +132,10 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); enum memblock_flags choose_memblock_flags(void); +unsigned long memblock_free_all(void); +void reset_node_managed_pages(pg_data_t *pgdat); +void reset_all_zones_managed_pages(void); + /* Low level functions */ int memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, @@ -300,11 +317,116 @@ static inline int memblock_get_region_node(const struct memblock_region *r) } #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +/* Flags for memblock allocation APIs */ +#define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) +#define MEMBLOCK_ALLOC_ACCESSIBLE 0 + +/* We are using top down, so it is safe to use 0 here */ +#define MEMBLOCK_LOW_LIMIT 0 + +#ifndef ARCH_LOW_ADDRESS_LIMIT +#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL +#endif + phys_addr_t memblock_phys_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); phys_addr_t memblock_phys_alloc(phys_addr_t size, phys_addr_t align); +void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); +void *memblock_alloc_try_nid_nopanic(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); +void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); + +static inline void * __init memblock_alloc(phys_addr_t size, phys_addr_t align) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_raw(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_raw(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_from(phys_addr_t size, + phys_addr_t align, + phys_addr_t min_addr) +{ + return memblock_alloc_try_nid(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_nopanic(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_nopanic(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_low(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); +} +static inline void * __init memblock_alloc_low_nopanic(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_nopanic(size, align, MEMBLOCK_LOW_LIMIT, + ARCH_LOW_ADDRESS_LIMIT, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_from_nopanic(phys_addr_t size, + phys_addr_t align, + phys_addr_t min_addr) +{ + return memblock_alloc_try_nid_nopanic(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_node(phys_addr_t size, + phys_addr_t align, int nid) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, nid); +} + +static inline void * __init memblock_alloc_node_nopanic(phys_addr_t size, + int nid) +{ + return memblock_alloc_try_nid_nopanic(size, 0, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, nid); +} + +static inline void __init memblock_free_early(phys_addr_t base, + phys_addr_t size) +{ + __memblock_free_early(base, size); +} + +static inline void __init memblock_free_early_nid(phys_addr_t base, + phys_addr_t size, int nid) +{ + __memblock_free_early(base, size); +} + +static inline void __init memblock_free_late(phys_addr_t base, phys_addr_t size) +{ + __memblock_free_late(base, size); +} + /* * Set the allocation direction to bottom-up or top-down. */ @@ -323,10 +445,6 @@ static inline bool memblock_bottom_up(void) return memblock.bottom_up; } -/* Flags for memblock_alloc_base() amd __memblock_alloc_base() */ -#define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) -#define MEMBLOCK_ALLOC_ACCESSIBLE 0 - phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, enum memblock_flags flags); @@ -432,6 +550,31 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo i < memblock_type->cnt; \ i++, rgn = &memblock_type->regions[i]) +extern void *alloc_large_system_hash(const char *tablename, + unsigned long bucketsize, + unsigned long numentries, + int scale, + int flags, + unsigned int *_hash_shift, + unsigned int *_hash_mask, + unsigned long low_limit, + unsigned long high_limit); + +#define HASH_EARLY 0x00000001 /* Allocating during early boot? */ +#define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min + * shift passed via *_hash_shift */ +#define HASH_ZERO 0x00000004 /* Zero allocated hash table */ + +/* Only NUMA needs hash distribution. 64bit NUMA architectures have + * sufficient vmalloc space. + */ +#ifdef CONFIG_NUMA +#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT) +extern int hashdist; /* Distribute hashes across NUMA nodes? */ +#else +#define hashdist (0) +#endif + #ifdef CONFIG_MEMTEST extern void early_memtest(phys_addr_t start, phys_addr_t end); #else -- cgit v1.2.3 From 7e1c4e27928e5f87b9b1eaf06dc31773b2f1e7f1 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:57 -0700 Subject: memblock: stop using implicit alignment to SMP_CACHE_BYTES When a memblock allocation APIs are called with align = 0, the alignment is implicitly set to SMP_CACHE_BYTES. Implicit alignment is done deep in the memblock allocator and it can come as a surprise. Not that such an alignment would be wrong even when used incorrectly but it is better to be explicit for the sake of clarity and the prinicple of the least surprise. Replace all such uses of memblock APIs with the 'align' parameter explicitly set to SMP_CACHE_BYTES and stop implicit alignment assignment in the memblock internal allocation functions. For the case when memblock APIs are used via helper functions, e.g. like iommu_arena_new_node() in Alpha, the helper functions were detected with Coccinelle's help and then manually examined and updated where appropriate. The direct memblock APIs users were updated using the semantic patch below: @@ expression size, min_addr, max_addr, nid; @@ ( | - memblock_alloc_try_nid_raw(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_raw(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid_nopanic(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc(size, 0) + memblock_alloc(size, SMP_CACHE_BYTES) | - memblock_alloc_raw(size, 0) + memblock_alloc_raw(size, SMP_CACHE_BYTES) | - memblock_alloc_from(size, 0, min_addr) + memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_nopanic(size, 0) + memblock_alloc_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_low(size, 0) + memblock_alloc_low(size, SMP_CACHE_BYTES) | - memblock_alloc_low_nopanic(size, 0) + memblock_alloc_low_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_from_nopanic(size, 0, min_addr) + memblock_alloc_from_nopanic(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_node(size, 0, nid) + memblock_alloc_node(size, SMP_CACHE_BYTES, nid) ) [mhocko@suse.com: changelog update] [akpm@linux-foundation.org: coding-style fixes] [rppt@linux.ibm.com: fix missed uses of implicit alignment] Link: http://lkml.kernel.org/r/20181016133656.GA10925@rapoport-lnx Link: http://lkml.kernel.org/r/1538687224-17535-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Suggested-by: Michal Hocko Acked-by: Paul Burton [MIPS] Acked-by: Michael Ellerman [powerpc] Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: Geert Uytterhoeven Cc: Guan Xuetao Cc: Ingo Molnar Cc: Matt Turner Cc: Michal Simek Cc: Richard Weinberger Cc: Russell King Cc: Thomas Gleixner Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1b4d85879cbe..aee299a6aa76 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -406,7 +406,8 @@ static inline void * __init memblock_alloc_node(phys_addr_t size, static inline void * __init memblock_alloc_node_nopanic(phys_addr_t size, int nid) { - return memblock_alloc_try_nid_nopanic(size, 0, MEMBLOCK_LOW_LIMIT, + return memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, + MEMBLOCK_LOW_LIMIT, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } -- cgit v1.2.3 From d15e59260f62bd5e0f625cf5f5240f6ffac78ab6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:18 -0700 Subject: mm/memory_hotplug: make remove_memory() take the device_hotplug_lock Patch series "mm: online/offline_pages called w.o. mem_hotplug_lock", v3. Reading through the code and studying how mem_hotplug_lock is to be used, I noticed that there are two places where we can end up calling device_online()/device_offline() - online_pages()/offline_pages() without the mem_hotplug_lock. And there are other places where we call device_online()/device_offline() without the device_hotplug_lock. While e.g. echo "online" > /sys/devices/system/memory/memory9/state is fine, e.g. echo 1 > /sys/devices/system/memory/memory9/online Will not take the mem_hotplug_lock. However the device_lock() and device_hotplug_lock. E.g. via memory_probe_store(), we can end up calling add_memory()->online_pages() without the device_hotplug_lock. So we can have concurrent callers in online_pages(). We e.g. touch in online_pages() basically unprotected zone->present_pages then. Looks like there is a longer history to that (see Patch #2 for details), and fixing it to work the way it was intended is not really possible. We would e.g. have to take the mem_hotplug_lock in device/base/core.c, which sounds wrong. Summary: We had a lock inversion on mem_hotplug_lock and device_lock(). More details can be found in patch 3 and patch 6. I propose the general rules (documentation added in patch 6): 1. add_memory/add_memory_resource() must only be called with device_hotplug_lock. 2. remove_memory() must only be called with device_hotplug_lock. This is already documented and holds for all callers. 3. device_online()/device_offline() must only be called with device_hotplug_lock. This is already documented and true for now in core code. Other callers (related to memory hotplug) have to be fixed up. 4. mem_hotplug_lock is taken inside of add_memory/remove_memory/ online_pages/offline_pages. To me, this looks way cleaner than what we have right now (and easier to verify). And looking at the documentation of remove_memory, using lock_device_hotplug also for add_memory() feels natural. This patch (of 6): remove_memory() is exported right now but requires the device_hotplug_lock, which is not exported. So let's provide a variant that takes the lock and only export that one. The lock is already held in arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c arch/powerpc/platforms/powernv/memtrace.c Apart from that, there are not other users in the tree. Link: http://lkml.kernel.org/r/20180925091457.28651-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rafael J. Wysocki Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Rashmica Gupta Cc: Michael Neuling Cc: Balbir Singh Cc: Nathan Fontenot Cc: John Allen Cc: Michal Hocko Cc: Dan Williams Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Greg Kroah-Hartman Cc: YASUAKI ISHIMATSU Cc: Mathieu Malaterre Cc: Boris Ostrovsky Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jonathan Corbet Cc: Juergen Gross Cc: Kate Stewart Cc: "K. Y. Srinivasan" Cc: Martin Schwidefsky Cc: Philippe Ombredanne Cc: Stephen Hemminger Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 34a28227068d..1f096852f479 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -301,6 +301,7 @@ extern bool is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern void remove_memory(int nid, u64 start, u64 size); +extern void __remove_memory(int nid, u64 start, u64 size); #else static inline bool is_mem_section_removable(unsigned long pfn, @@ -317,6 +318,7 @@ static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) } static inline void remove_memory(int nid, u64 start, u64 size) {} +static inline void __remove_memory(int nid, u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ extern void __ref free_area_init_core_hotplug(int nid); @@ -330,7 +332,6 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); -extern void remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn, struct vmem_altmap *altmap); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, -- cgit v1.2.3 From 8df1d0e4a265f25dc1e7e7624ccdbcb4a6630c89 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:24 -0700 Subject: mm/memory_hotplug: make add_memory() take the device_hotplug_lock add_memory() currently does not take the device_hotplug_lock, however is aleady called under the lock from arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c to synchronize against CPU hot-remove and similar. In general, we should hold the device_hotplug_lock when adding memory to synchronize against online/offline request (e.g. from user space) - which already resulted in lock inversions due to device_lock() and mem_hotplug_lock - see 30467e0b3be ("mm, hotplug: fix concurrent memory hot-add deadlock"). add_memory()/add_memory_resource() will create memory block devices, so this really feels like the right thing to do. Holding the device_hotplug_lock makes sure that a memory block device can really only be accessed (e.g. via .online/.state) from user space, once the memory has been fully added to the system. The lock is not held yet in drivers/xen/balloon.c arch/powerpc/platforms/powernv/memtrace.c drivers/s390/char/sclp_cmd.c drivers/hv/hv_balloon.c So, let's either use the locked variants or take the lock. Don't export add_memory_resource(), as it once was exported to be used by XEN, which is never built as a module. If somebody requires it, we also have to export a locked variant (as device_hotplug_lock is never exported). Link: http://lkml.kernel.org/r/20180925091457.28651-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rafael J. Wysocki Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Greg Kroah-Hartman Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Nathan Fontenot Cc: John Allen Cc: Michal Hocko Cc: Dan Williams Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Mathieu Malaterre Cc: Pavel Tatashin Cc: YASUAKI ISHIMATSU Cc: Balbir Singh Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jonathan Corbet Cc: Kate Stewart Cc: "K. Y. Srinivasan" Cc: Martin Schwidefsky Cc: Michael Neuling Cc: Philippe Ombredanne Cc: Stephen Hemminger Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 1f096852f479..ffd9cd10fcf3 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -324,6 +324,7 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {} extern void __ref free_area_init_core_hotplug(int nid); extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); +extern int __add_memory(int nid, u64 start, u64 size); extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource, bool online); extern int arch_add_memory(int nid, u64 start, u64 size, -- cgit v1.2.3 From bb58fd7eeffc9bd5d6e2a16cbf0e9e259f8d09f2 Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Fri, 19 Oct 2018 14:11:03 -0700 Subject: i40e: Update status codes Add a few new status code which will be used by the ice driver, and rename a few to make them more consistent. Error code are mapped to similar values as in i40e_status.h, so as to be compatible with older VF drivers not using this status enum. Signed-off-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 2c9756bd9c4c..b2488055fd1d 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -62,13 +62,19 @@ /* Error Codes */ enum virtchnl_status_code { VIRTCHNL_STATUS_SUCCESS = 0, - VIRTCHNL_ERR_PARAM = -5, + VIRTCHNL_STATUS_ERR_PARAM = -5, + VIRTCHNL_STATUS_ERR_NO_MEMORY = -18, VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH = -38, VIRTCHNL_STATUS_ERR_CQP_COMPL_ERROR = -39, VIRTCHNL_STATUS_ERR_INVALID_VF_ID = -40, - VIRTCHNL_STATUS_NOT_SUPPORTED = -64, + VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR = -53, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED = -64, }; +/* Backward compatibility */ +#define VIRTCHNL_ERR_PARAM VIRTCHNL_STATUS_ERR_PARAM +#define VIRTCHNL_STATUS_NOT_SUPPORTED VIRTCHNL_STATUS_ERR_NOT_SUPPORTED + #define VIRTCHNL_LINK_SPEED_100MB_SHIFT 0x1 #define VIRTCHNL_LINK_SPEED_1000MB_SHIFT 0x2 #define VIRTCHNL_LINK_SPEED_10GB_SHIFT 0x3 @@ -831,7 +837,7 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: default: - return VIRTCHNL_ERR_PARAM; + return VIRTCHNL_STATUS_ERR_PARAM; } /* few more checks */ if (err_msg_format || valid_len != msglen) -- cgit v1.2.3 From a324e9396ca3d00e1101476ba067b412e0aba232 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 31 Oct 2018 19:20:20 +0100 Subject: EDAC, skx: Fix randconfig builds The driver depends on the ADXL component glue and selects it. However, ADXL itself implicitly depends on ACPI and in nonsensical randconfig builds like this: # CONFIG_ACPI is not set CONFIG_ACPI_ADXL=y where ACPI is not enabled, the build fails with: drivers/edac/skx_edac.o: In function `skx_mce_check_error': skx_edac.c:(.text+0xab): undefined reference to `adxl_decode' drivers/edac/skx_edac.o: In function `skx_init': skx_edac.c:(.init.text+0x8bf): undefined reference to `adxl_get_component_names' make: *** [vmlinux] Error 1 Add stubs for that case so that the build succeeds. CONFIG_ACPI=n doesn't make any sense for real configurations but this fix will at least silence randconfig builds. Signed-off-by: Borislav Petkov Acked-by: Tony Luck Cc: "Rafael J. Wysocki" --- include/linux/adxl.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/adxl.h b/include/linux/adxl.h index 2a629acb4c3f..2d29f55923e3 100644 --- a/include/linux/adxl.h +++ b/include/linux/adxl.h @@ -7,7 +7,12 @@ #ifndef _LINUX_ADXL_H #define _LINUX_ADXL_H +#ifdef CONFIG_ACPI_ADXL const char * const *adxl_get_component_names(void); int adxl_decode(u64 addr, u64 component_values[]); +#else +static inline const char * const *adxl_get_component_names(void) { return NULL; } +static inline int adxl_decode(u64 addr, u64 component_values[]) { return -EOPNOTSUPP; } +#endif #endif /* _LINUX_ADXL_H */ -- cgit v1.2.3 From 439cd39ea136d2c026805264d58a91f36b6b64ca Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Sat, 14 Jul 2018 21:59:43 +0200 Subject: netfilter: ipset: list:set: Decrease refcount synchronously on deletion and replace Commit 45040978c899 ("netfilter: ipset: Fix set:list type crash when flush/dump set in parallel") postponed decreasing set reference counters to the RCU callback. An 'ipset del' command can terminate before the RCU grace period is elapsed, and if sets are listed before then, the reference counter shown in userspace will be wrong: # ipset create h hash:ip; ipset create l list:set; ipset add l # ipset del l h; ipset list h Name: h Type: hash:ip Revision: 4 Header: family inet hashsize 1024 maxelem 65536 Size in memory: 88 References: 1 Number of entries: 0 Members: # sleep 1; ipset list h Name: h Type: hash:ip Revision: 4 Header: family inet hashsize 1024 maxelem 65536 Size in memory: 88 References: 0 Number of entries: 0 Members: Fix this by making the reference count update synchronous again. As a result, when sets are listed, ip_set_name_byindex() might now fetch a set whose reference count is already zero. Instead of relying on the reference count to protect against concurrent set renaming, grab ip_set_ref_lock as reader and copy the name, while holding the same lock in ip_set_rename() as writer instead. Reported-by: Li Shuang Fixes: 45040978c899 ("netfilter: ipset: Fix set:list type crash when flush/dump set in parallel") Signed-off-by: Stefano Brivio Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 34fc80f3eb90..1d100efe74ec 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -314,7 +314,7 @@ enum { extern ip_set_id_t ip_set_get_byname(struct net *net, const char *name, struct ip_set **set); extern void ip_set_put_byindex(struct net *net, ip_set_id_t index); -extern const char *ip_set_name_byindex(struct net *net, ip_set_id_t index); +extern void ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name); extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index); extern void ip_set_nfnl_put(struct net *net, ip_set_id_t index); -- cgit v1.2.3 From 0962590e553331db2cc0aef2dc35c57f6300dbbe Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 1 Nov 2018 00:05:52 +0100 Subject: bpf: fix partial copy of map_ptr when dst is scalar ALU operations on pointers such as scalar_reg += map_value_ptr are handled in adjust_ptr_min_max_vals(). Problem is however that map_ptr and range in the register state share a union, so transferring state through dst_reg->range = ptr_reg->range is just buggy as any new map_ptr in the dst_reg is then truncated (or null) for subsequent checks. Fix this by adding a raw member and use it for copying state over to dst_reg. Fixes: f1174f77b50c ("bpf/verifier: rework value tracking") Signed-off-by: Daniel Borkmann Cc: Edward Cree Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 9e8056ec20fa..d93e89761a8b 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -51,6 +51,9 @@ struct bpf_reg_state { * PTR_TO_MAP_VALUE_OR_NULL */ struct bpf_map *map_ptr; + + /* Max size from any of the above. */ + unsigned long raw; }; /* Fixed part of pointer offset, pointer types only */ s32 off; -- cgit v1.2.3 From a846446b1914d1e3d996d657754f43fde89bab51 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Fri, 12 Oct 2018 14:42:52 +0100 Subject: x86/compat: Adjust in_compat_syscall() to generic code under !COMPAT The result of in_compat_syscall() can be pictured as: x86 platform: --------------------------------------------------- | Arch\syscall | 64-bit | ia32 | x32 | |-------------------------------------------------| | x86_64 | false | true | true | |-------------------------------------------------| | i686 | | | | --------------------------------------------------- Other platforms: ------------------------------------------- | Arch\syscall | 64-bit | compat | |-----------------------------------------| | 64-bit | false | true | |-----------------------------------------| | 32-bit(?) | | | ------------------------------------------- As seen, the result of in_compat_syscall() on generic 32-bit platform differs from i686. There is no reason for in_compat_syscall() == true on native i686. It also easy to misread code if the result on native 32-bit platform differs between arches. Because of that non arch-specific code has many places with: if (IS_ENABLED(CONFIG_COMPAT) && in_compat_syscall()) in different variations. It looks-like the only non-x86 code which uses in_compat_syscall() not under CONFIG_COMPAT guard is in amd/amdkfd. But according to the commit a18069c132cb ("amdkfd: Disable support for 32-bit user processes"), it actually should be disabled on native i686. Rename in_compat_syscall() to in_32bit_syscall() for x86-specific code and make in_compat_syscall() false under !CONFIG_COMPAT. A follow on patch will clean up generic users which were forced to check IS_ENABLED(CONFIG_COMPAT) with in_compat_syscall(). Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Reviewed-by: Andy Lutomirski Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Ard Biesheuvel Cc: "David S. Miller" Cc: Herbert Xu Cc: "H. Peter Anvin" Cc: John Stultz Cc: "Kirill A. Shutemov" Cc: Oleg Nesterov Cc: Steffen Klassert Cc: Stephen Boyd Cc: Steven Rostedt Cc: linux-efi@vger.kernel.org Cc: netdev@vger.kernel.org Link: https://lkml.kernel.org/r/20181012134253.23266-2-dima@arista.com --- include/linux/compat.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index d30e4dbd4be2..f1ef24c68fcc 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -1029,9 +1029,9 @@ int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, #else /* !CONFIG_COMPAT */ #define is_compat_task() (0) -#ifndef in_compat_syscall +/* Ensure no one redefines in_compat_syscall() under !CONFIG_COMPAT */ +#define in_compat_syscall in_compat_syscall static inline bool in_compat_syscall(void) { return false; } -#endif #endif /* CONFIG_COMPAT */ -- cgit v1.2.3 From c3be6577d82a9f0163eb1e2c37a477414d12a209 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Thu, 1 Nov 2018 17:51:34 +0000 Subject: SUNRPC: Use atomic(64)_t for seq_send(64) The seq_send & seq_send64 fields in struct krb5_ctx are used as atomically incrementing counters. This is implemented using cmpxchg() & cmpxchg64() to implement what amount to custom versions of atomic_fetch_inc() & atomic64_fetch_inc(). Besides the duplication, using cmpxchg64() has another major drawback in that some 32 bit architectures don't provide it. As such commit 571ed1fd2390 ("SUNRPC: Replace krb5_seq_lock with a lockless scheme") resulted in build failures for some architectures. Change seq_send to be an atomic_t and seq_send64 to be an atomic64_t, then use atomic(64)_* functions to manipulate the values. The atomic64_t type & associated functions are provided even on architectures which lack real 64 bit atomic memory access via CONFIG_GENERIC_ATOMIC64 which uses spinlocks to serialize access. This fixes the build failures for architectures lacking cmpxchg64(). A potential alternative that was raised would be to provide cmpxchg64() on the 32 bit architectures that currently lack it, using spinlocks. However this would provide a version of cmpxchg64() with semantics a little different to the implementations on architectures with real 64 bit atomics - the spinlock-based implementation would only work if all access to the memory used with cmpxchg64() is *always* performed using cmpxchg64(). That is not currently a requirement for users of cmpxchg64(), and making it one seems questionable. As such avoiding cmpxchg64() outside of architecture-specific code seems best, particularly in cases where atomic64_t seems like a better fit anyway. The CONFIG_GENERIC_ATOMIC64 implementation of atomic64_* functions will use spinlocks & so faces the same issue, but with the key difference that the memory backing an atomic64_t ought to always be accessed via the atomic64_* functions anyway making the issue moot. Signed-off-by: Paul Burton Fixes: 571ed1fd2390 ("SUNRPC: Replace krb5_seq_lock with a lockless scheme") Cc: Trond Myklebust Cc: Anna Schumaker Cc: J. Bruce Fields Cc: Jeff Layton Cc: David S. Miller Cc: linux-nfs@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 69f749afa617..4162de72e95c 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -107,8 +107,8 @@ struct krb5_ctx { u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; s32 endtime; - u32 seq_send; - u64 seq_send64; + atomic_t seq_send; + atomic64_t seq_send64; struct xdr_netobj mech_used; u8 initiator_sign[GSS_KRB5_MAX_KEYLEN]; u8 acceptor_sign[GSS_KRB5_MAX_KEYLEN]; @@ -118,9 +118,6 @@ struct krb5_ctx { u8 acceptor_integ[GSS_KRB5_MAX_KEYLEN]; }; -extern u32 gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx); -extern u64 gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx); - /* The length of the Kerberos GSS token header */ #define GSS_KRB5_TOK_HDR_LEN (16) -- cgit v1.2.3 From b5f2954d30c77649bce9c27e7a0a94299d9cfdf8 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Thu, 1 Nov 2018 17:24:10 -0400 Subject: blkcg: revert blkcg cleanups series This reverts a series committed earlier due to null pointer exception bug report in [1]. It seems there are edge case interactions that I did not consider and will need some time to understand what causes the adverse interactions. The original series can be found in [2] with a follow up series in [3]. [1] https://www.spinics.net/lists/cgroups/msg20719.html [2] https://lore.kernel.org/lkml/20180911184137.35897-1-dennisszhou@gmail.com/ [3] https://lore.kernel.org/lkml/20181020185612.51587-1-dennis@kernel.org/ This reverts the following commits: d459d853c2ed, b2c3fa546705, 101246ec02b5, b3b9f24f5fcc, e2b0989954ae, f0fcb3ec89f3, c839e7a03f92, bdc2491708c4, 74b7c02a9bc1, 5bf9a1f3b4ef, a7b39b4e961c, 07b05bcc3213, 49f4c2dc2b50, 27e6fa996c53 Signed-off-by: Dennis Zhou Signed-off-by: Jens Axboe --- include/linux/bio.h | 26 +++----- include/linux/blk-cgroup.h | 145 ++++++++++++++------------------------------- include/linux/blk_types.h | 1 + include/linux/cgroup.h | 2 - include/linux/writeback.h | 5 +- 5 files changed, 57 insertions(+), 122 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index b47c7f716731..056fb627edb3 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -503,31 +503,23 @@ do { \ disk_devt((bio)->bi_disk) #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -int bio_associate_blkg_from_page(struct bio *bio, struct page *page); +int bio_associate_blkcg_from_page(struct bio *bio, struct page *page); #else -static inline int bio_associate_blkg_from_page(struct bio *bio, - struct page *page) { return 0; } +static inline int bio_associate_blkcg_from_page(struct bio *bio, + struct page *page) { return 0; } #endif #ifdef CONFIG_BLK_CGROUP +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); -int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css); -int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); -int bio_reassociate_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); -void bio_clone_blkg_association(struct bio *dst, struct bio *src); +void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ -static inline int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ return 0; } -static inline int bio_associate_create_blkg(struct request_queue *q, - struct bio *bio) { return 0; } -static inline int bio_reassociate_blkg(struct request_queue *q, struct bio *bio) -{ return 0; } +static inline int bio_associate_blkcg(struct bio *bio, + struct cgroup_subsys_state *blkcg_css) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } -static inline void bio_clone_blkg_association(struct bio *dst, - struct bio *src) { } +static inline void bio_clone_blkcg_association(struct bio *dst, + struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1e76ceebeb5d..6d766a19f2bb 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -126,7 +126,7 @@ struct blkcg_gq { struct request_list rl; /* reference count */ - struct percpu_ref refcnt; + atomic_t refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; @@ -184,8 +184,6 @@ extern struct cgroup_subsys_state * const blkcg_root_css; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); -struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q); struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q); int blkcg_init_queue(struct request_queue *q); @@ -232,59 +230,22 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); -/** - * blkcg_css - find the current css - * - * Find the css associated with either the kthread or the current task. - * This may return a dying css, so it is up to the caller to use tryget logic - * to confirm it is alive and well. - */ -static inline struct cgroup_subsys_state *blkcg_css(void) -{ - struct cgroup_subsys_state *css; - - css = kthread_blkcg(); - if (css) - return css; - return task_css(current, io_cgrp_id); -} static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } -/** - * __bio_blkcg - internal version of bio_blkcg for bfq and cfq - * - * DO NOT USE. - * There is a flaw using this version of the function. In particular, this was - * used in a broken paradigm where association was called on the given css. It - * is possible though that the returned css from task_css() is in the process - * of dying due to migration of the current task. So it is improper to assume - * *_get() is going to succeed. Both BFQ and CFQ rely on this logic and will - * take additional work to handle more gracefully. - */ -static inline struct blkcg *__bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return css_to_blkcg(blkcg_css()); -} - -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, NULL if not associated. - * Callers are expected to either handle NULL or know association has been - * done prior to calling this. - */ static inline struct blkcg *bio_blkcg(struct bio *bio) { - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; + struct cgroup_subsys_state *css; + + if (bio && bio->bi_css) + return css_to_blkcg(bio->bi_css); + css = kthread_blkcg(); + if (css) + return css_to_blkcg(css); + return css_to_blkcg(task_css(current, io_cgrp_id)); } static inline bool blk_cgroup_congested(void) @@ -490,35 +451,26 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) */ static inline void blkg_get(struct blkcg_gq *blkg) { - percpu_ref_get(&blkg->refcnt); + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + atomic_inc(&blkg->refcnt); } /** - * blkg_tryget - try and get a blkg reference + * blkg_try_get - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ -static inline bool blkg_tryget(struct blkcg_gq *blkg) +static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) { - return percpu_ref_tryget(&blkg->refcnt); + if (atomic_inc_not_zero(&blkg->refcnt)) + return blkg; + return NULL; } -/** - * blkg_tryget_closest - try and get a blkg ref on the closet blkg - * @blkg: blkg to get - * - * This walks up the blkg tree to find the closest non-dying blkg and returns - * the blkg that it did association with as it may not be the passed in blkg. - */ -static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) -{ - while (!percpu_ref_tryget(&blkg->refcnt)) - blkg = blkg->parent; - return blkg; -} +void __blkg_release_rcu(struct rcu_head *rcu); /** * blkg_put - put a blkg reference @@ -526,7 +478,9 @@ static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) */ static inline void blkg_put(struct blkcg_gq *blkg) { - percpu_ref_put(&blkg->refcnt); + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + if (atomic_dec_and_test(&blkg->refcnt)) + call_rcu(&blkg->rcu_head, __blkg_release_rcu); } /** @@ -579,36 +533,25 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, rcu_read_lock(); - if (bio && bio->bi_blkg) { - blkcg = bio->bi_blkg->blkcg; - if (blkcg == &blkcg_root) - goto rl_use_root; - - blkg_get(bio->bi_blkg); - rcu_read_unlock(); - return &bio->bi_blkg->rl; - } + blkcg = bio_blkcg(bio); - blkcg = css_to_blkcg(blkcg_css()); + /* bypass blkg lookup and use @q->root_rl directly for root */ if (blkcg == &blkcg_root) - goto rl_use_root; + goto root_rl; + /* + * Try to use blkg->rl. blkg lookup may fail under memory pressure + * or if either the blkcg or queue is going away. Fall back to + * root_rl in such cases. + */ blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) - blkg = __blkg_lookup_create(blkcg, q); - - if (blkg->blkcg == &blkcg_root || !blkg_tryget(blkg)) - goto rl_use_root; + goto root_rl; + blkg_get(blkg); rcu_read_unlock(); return &blkg->rl; - - /* - * Each blkg has its own request_list, however, the root blkcg - * uses the request_queue's root_rl. This is to avoid most - * overhead for the root blkcg. - */ -rl_use_root: +root_rl: rcu_read_unlock(); return &q->root_rl; } @@ -854,26 +797,32 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg struct bio *bio) { return false; } #endif - -static inline void blkcg_bio_issue_init(struct bio *bio) -{ - bio_issue_init(&bio->bi_issue, bio_sectors(bio)); -} - static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { + struct blkcg *blkcg; struct blkcg_gq *blkg; bool throtl = false; rcu_read_lock(); + blkcg = bio_blkcg(bio); + + /* associate blkcg if bio hasn't attached one */ + bio_associate_blkcg(bio, &blkcg->css); - bio_associate_create_blkg(q, bio); - blkg = bio->bi_blkg; + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + spin_unlock_irq(q->queue_lock); + } throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { + blkg = blkg ?: q->root_blkg; /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the @@ -885,8 +834,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } - blkcg_bio_issue_init(bio); - rcu_read_unlock(); return !throtl; } @@ -983,7 +930,6 @@ static inline int blkcg_activate_policy(struct request_queue *q, static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } -static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, @@ -999,7 +945,6 @@ static inline void blk_put_rl(struct request_list *rl) { } static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } -static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { return true; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 093a818c5b68..1dcf652ba0aa 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -178,6 +178,7 @@ struct bio { * release. Read comment on top of bio_associate_current(). */ struct io_context *bi_ioc; + struct cgroup_subsys_state *bi_css; struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; #endif diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b8bcbdeb2eac..32c553556bbd 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -93,8 +93,6 @@ extern struct css_set init_css_set; bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); -struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, - struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 738a0c24874f..fdfd04e348f6 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -246,8 +246,7 @@ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup - * writeback context. Must be called after the bio has been associated with - * a device. + * writeback context. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { @@ -258,7 +257,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) * regular writeback instead of writing things out itself. */ if (wbc->wb) - bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); + bio_associate_blkcg(bio, wbc->wb->blkcg_css); } #else /* CONFIG_CGROUP_WRITEBACK */ -- cgit v1.2.3 From 6d212db11947ae5464e4717536ed9faf61c01e86 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 15 Oct 2018 10:30:23 +0200 Subject: mm: add mm_pxd_folded checks to pgtable_bytes accounting functions The common mm code calls mm_dec_nr_pmds() and mm_dec_nr_puds() in free_pgtables() if the address range spans a full pud or pmd. If mm_dec_nr_puds/mm_dec_nr_pmds are non-empty due to configuration settings they blindly subtract the size of the pmd or pud table from pgtable_bytes even if the pud or pmd page table layer is folded. Add explicit mm_[pmd|pud]_folded checks to the four pgtable_bytes accounting functions mm_inc_nr_puds, mm_inc_nr_pmds, mm_dec_nr_puds and mm_dec_nr_pmds. As the check for folded page tables can be overwritten by the architecture, this allows to keep a correct pgtable_bytes value for platforms that use a dynamic number of page table levels. Acked-by: Kirill A. Shutemov Signed-off-by: Martin Schwidefsky --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index daa2b8f1e9a8..a3701e91bb57 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1742,11 +1742,15 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif @@ -1766,11 +1770,15 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif -- cgit v1.2.3 From a7ad38b0dd3c1ba8d6e5a55241e875e9db8331ab Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Sat, 3 Nov 2018 00:51:28 +0800 Subject: clocksource/drivers/c-sky: Add C-SKY SMP timer The driver is for C-SKY SMP timer. It only supports oneshot event and 32bit overflow for clocksource. Per cpu core has one timer and all timers share one clock-counter-input from the same clocksource. This use mfcr&mtcr instructions to access the regs. Signed-off-by: Guo Ren Cc: Daniel Lezcano Cc: Thomas Gleixner Signed-off-by: Daniel Lezcano --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index caf40ad0bbc6..e0cd2baa8380 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -126,6 +126,7 @@ enum cpuhp_state { CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, + CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING, -- cgit v1.2.3 From 17b8b74c0f8dbf9b9e3301f9ca5b65dd1c079951 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 19 Oct 2018 19:35:19 +0200 Subject: netfilter: ipset: Correct rcu_dereference() call in ip_set_put_comment() The function is called when rcu_read_lock() is held and not when rcu_read_lock_bh() is held. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_comment.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h index 8e2bab1e8e90..70877f8de7e9 100644 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ b/include/linux/netfilter/ipset/ip_set_comment.h @@ -43,11 +43,11 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, rcu_assign_pointer(comment->c, c); } -/* Used only when dumping a set, protected by rcu_read_lock_bh() */ +/* Used only when dumping a set, protected by rcu_read_lock() */ static inline int ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) { - struct ip_set_comment_rcu *c = rcu_dereference_bh(comment->c); + struct ip_set_comment_rcu *c = rcu_dereference(comment->c); if (!c) return 0; -- cgit v1.2.3 From 94e297c50b529f5d01cfd1dbc808d61e95180ab7 Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Fri, 2 Nov 2018 15:47:53 -0700 Subject: include/linux/notifier.h: SRCU: fix ctags ctags indexing ("make tags" command) throws this warning: ctags: Warning: include/linux/notifier.h:125: null expansion of name pattern "\1" This is the result of DEFINE_PER_CPU() macro expansion. Fix that by getting rid of line break. Similar fix was already done in commit 25528213fe9f ("tags: Fix DEFINE_PER_CPU expansions"), but this one probably wasn't noticed. Link: http://lkml.kernel.org/r/20181030202808.28027-1-semen.protsenko@linaro.org Fixes: 9c80172b902d ("kernel/SRCU: provide a static initializer") Signed-off-by: Sam Protsenko Cc: Sebastian Andrzej Siewior Cc: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/notifier.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index f35c7bf76143..0096a05395e3 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -122,8 +122,7 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #ifdef CONFIG_TREE_SRCU #define _SRCU_NOTIFIER_HEAD(name, mod) \ - static DEFINE_PER_CPU(struct srcu_data, \ - name##_head_srcu_data); \ + static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name##_head_srcu_data) -- cgit v1.2.3 From 89c83fb539f95491be80cdd5158e6f0ce329e317 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 2 Nov 2018 15:48:31 -0700 Subject: mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask THP allocation mode is quite complex and it depends on the defrag mode. This complexity is hidden in alloc_hugepage_direct_gfpmask from a large part currently. The NUMA special casing (namely __GFP_THISNODE) is however independent and placed in alloc_pages_vma currently. This both adds an unnecessary branch to all vma based page allocation requests and it makes the code more complex unnecessarily as well. Not to mention that e.g. shmem THP used to do the node reclaiming unconditionally regardless of the defrag mode until recently. This was not only unexpected behavior but it was also hardly a good default behavior and I strongly suspect it was just a side effect of the code sharing more than a deliberate decision which suggests that such a layering is wrong. Get rid of the thp special casing from alloc_pages_vma and move the logic to alloc_hugepage_direct_gfpmask. __GFP_THISNODE is applied to the resulting gfp mask only when the direct reclaim is not requested and when there is no explicit numa binding to preserve the current logic. Please note that there's also a slight difference wrt MPOL_BIND now. The previous code would avoid using __GFP_THISNODE if the local node was outside of policy_nodemask(). After this patch __GFP_THISNODE is avoided for all MPOL_BIND policies. So there's a difference that if local node is actually allowed by the bind policy's nodemask, previously __GFP_THISNODE would be added, but now it won't be. From the behavior POV this is still correct because the policy nodemask is used. Link: http://lkml.kernel.org/r/20180925120326.24392-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Alex Williamson Cc: Andrea Arcangeli Cc: David Rientjes Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: Stefan Priebe - Profihost AG Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 ++++-------- include/linux/mempolicy.h | 2 ++ 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 24bcc5eec6b4..76f8db0b0e71 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,22 +510,18 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) + int node); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ - alloc_pages(gfp_mask, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) + alloc_pages_vma(gfp_mask, 0, vma, addr, node) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5228c62af416..bac395f1d00a 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,6 +139,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); -- cgit v1.2.3 From 3e59020abf0f88182730527ee5b862e786eb485a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 31 Oct 2018 08:39:12 -0700 Subject: net: bql: add __netdev_tx_sent_queue() When qdisc_run() tries to use BQL budget to bulk-dequeue a batch of packets, GSO can later transform this list in another list of skbs, and each skb is sent to device ndo_start_xmit(), one at a time, with skb->xmit_more being set to one but for last skb. Problem is that very often, BQL limit is hit in the middle of the packet train, forcing dev_hard_start_xmit() to stop the bulk send and requeue the end of the list. BQL role is to avoid head of line blocking, making sure a qdisc can deliver high priority packets before low priority ones. But there is no way requeued packets can be bypassed by fresh packets in the qdisc. Aborting the bulk send increases TX softirqs, and hot cache lines (after skb_segment()) are wasted. Note that for TSO packets, we never split a packet in the middle because of BQL limit being hit. Drivers should be able to update BQL counters without flipping/caring about BQL status, if the current skb has xmit_more set. Upper layers are ultimately responsible to stop sending another packet train when BQL limit is hit. Code template in a driver might look like the following : send_doorbell = __netdev_tx_sent_queue(tx_queue, nr_bytes, skb->xmit_more); Note that __netdev_tx_sent_queue() use is not mandatory, since following patch will change dev_hard_start_xmit() to not care about BQL status. But it is highly recommended so that xmit_more full benefits can be reached (less doorbells sent, and less atomic operations as well) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dc1d9ed33b31..857f8abf7b91 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3190,6 +3190,26 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, #endif } +/* Variant of netdev_tx_sent_queue() for drivers that are aware + * that they should not test BQL status themselves. + * We do want to change __QUEUE_STATE_STACK_XOFF only for the last + * skb of a batch. + * Returns true if the doorbell must be used to kick the NIC. + */ +static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, + unsigned int bytes, + bool xmit_more) +{ + if (xmit_more) { +#ifdef CONFIG_BQL + dql_queued(&dev_queue->dql, bytes); +#endif + return netif_tx_queue_stopped(dev_queue); + } + netdev_tx_sent_queue(dev_queue, bytes); + return true; +} + /** * netdev_sent_queue - report the number of bytes queued to hardware * @dev: network device -- cgit v1.2.3 From 35b69a420bfb56b7b74cb635ea903db05e357bec Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 4 Nov 2018 03:48:54 +0000 Subject: clockevents/drivers/i8253: Add support for PIT shutdown quirk Add support for platforms where pit_shutdown() doesn't work because of a quirk in the PIT emulation. On these platforms setting the counter register to zero causes the PIT to start running again, negating the shutdown. Provide a global variable that controls whether the counter register is zero'ed, which platform specific code can override. Signed-off-by: Michael Kelley Signed-off-by: Thomas Gleixner Cc: "gregkh@linuxfoundation.org" Cc: "devel@linuxdriverproject.org" Cc: "daniel.lezcano@linaro.org" Cc: "virtualization@lists.linux-foundation.org" Cc: "jgross@suse.com" Cc: "akataria@vmware.com" Cc: "olaf@aepfle.de" Cc: "apw@canonical.com" Cc: vkuznets Cc: "jasowang@redhat.com" Cc: "marcelo.cerri@canonical.com" Cc: KY Srinivasan Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1541303219-11142-2-git-send-email-mikelley@microsoft.com --- include/linux/i8253.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i8253.h b/include/linux/i8253.h index e6bb36a97519..8336b2f6f834 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -21,6 +21,7 @@ #define PIT_LATCH ((PIT_TICK_RATE + HZ/2) / HZ) extern raw_spinlock_t i8253_lock; +extern bool i8253_clear_counter_on_shutdown; extern struct clock_event_device i8253_clockevent; extern void clockevent_i8253_init(bool oneshot); -- cgit v1.2.3 From d098093ba06eb032057d1aca1c2e45889e099d00 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 28 Oct 2018 12:29:55 +0100 Subject: mtd: nand: Fix nanddev_neraseblocks() nanddev_neraseblocks() currently returns the number pages per LUN instead of the total number of eraseblocks. Fixes: 9c3736a3de21 ("mtd: nand: Add core infrastructure to deal with NAND devices") Cc: Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal --- include/linux/mtd/nand.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index abe975c87b90..78b86dea2f29 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -324,9 +324,8 @@ static inline unsigned int nanddev_ntargets(const struct nand_device *nand) */ static inline unsigned int nanddev_neraseblocks(const struct nand_device *nand) { - return (u64)nand->memorg.luns_per_target * - nand->memorg.eraseblocks_per_lun * - nand->memorg.pages_per_eraseblock; + return nand->memorg.ntargets * nand->memorg.luns_per_target * + nand->memorg.eraseblocks_per_lun; } /** -- cgit v1.2.3 From 163c8d54a997153ee1a1e07fcac087492ad85b37 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 5 Nov 2018 07:36:28 +0100 Subject: compiler: remove __no_sanitize_address_or_inline again The __no_sanitize_address_or_inline and __no_kasan_or_inline defines are almost identical. The only difference is that __no_kasan_or_inline does not have the 'notrace' attribute. To be able to replace __no_sanitize_address_or_inline with the older definition, add 'notrace' to __no_kasan_or_inline and change to two users of __no_sanitize_address_or_inline in the s390 code. The 'notrace' option is necessary for e.g. the __load_psw_mask function in arch/s390/include/asm/processor.h. Without the option it is possible to trace __load_psw_mask which leads to kernel stack overflow. Signed-off-by: Martin Schwidefsky Pointed-out-by: Andrey Ryabinin Acked-by: Steven Rostedt (VMware) Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 12 ------------ include/linux/compiler.h | 2 +- 2 files changed, 1 insertion(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c0f5db3a9621..2010493e1040 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -143,18 +143,6 @@ #define KASAN_ABI_VERSION 3 #endif -/* - * Because __no_sanitize_address conflicts with inlining: - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - * we do one or the other. - */ -#ifdef CONFIG_KASAN -#define __no_sanitize_address_or_inline \ - __no_sanitize_address __maybe_unused notrace -#else -#define __no_sanitize_address_or_inline inline -#endif - #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 18c80cfa4fc4..06396c1cf127 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -189,7 +189,7 @@ void __read_once_size(const volatile void *p, void *res, int size) * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 * '__maybe_unused' allows us to avoid defined-but-not-used warnings. */ -# define __no_kasan_or_inline __no_sanitize_address __maybe_unused +# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused #else # define __no_kasan_or_inline __always_inline #endif -- cgit v1.2.3 From 4c0608f4a0e76dfb82d3accd20081f4bf47ed143 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 30 Oct 2018 09:45:55 -0400 Subject: XArray: Regularise xa_reserve The xa_reserve() function was a little unusual in that it attempted to be callable for all kinds of locking scenarios. Make it look like the other APIs with __xa_reserve, xa_reserve_bh and xa_reserve_irq variants. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 80 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 79 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index d9514928ddac..c2cb0426c60c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -291,7 +291,6 @@ void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); -int xa_reserve(struct xarray *, unsigned long index, gfp_t); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -455,6 +454,7 @@ void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int __xa_alloc(struct xarray *, u32 *id, u32 max, void *entry, gfp_t); +int __xa_reserve(struct xarray *, unsigned long index, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -621,6 +621,84 @@ static inline int xa_alloc_irq(struct xarray *xa, u32 *id, u32 max, void *entry, return err; } +/** + * xa_reserve() - Reserve this index in the XArray. + * @xa: XArray. + * @index: Index into array. + * @gfp: Memory allocation flags. + * + * Ensures there is somewhere to store an entry at @index in the array. + * If there is already something stored at @index, this function does + * nothing. If there was nothing there, the entry is marked as reserved. + * Loading from a reserved entry returns a %NULL pointer. + * + * If you do not use the entry that you have reserved, call xa_release() + * or xa_erase() to free any unnecessary memory. + * + * Context: Any context. Takes and releases the xa_lock. + * May sleep if the @gfp flags permit. + * Return: 0 if the reservation succeeded or -ENOMEM if it failed. + */ +static inline +int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + int ret; + + xa_lock(xa); + ret = __xa_reserve(xa, index, gfp); + xa_unlock(xa); + + return ret; +} + +/** + * xa_reserve_bh() - Reserve this index in the XArray. + * @xa: XArray. + * @index: Index into array. + * @gfp: Memory allocation flags. + * + * A softirq-disabling version of xa_reserve(). + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. + * Return: 0 if the reservation succeeded or -ENOMEM if it failed. + */ +static inline +int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + int ret; + + xa_lock_bh(xa); + ret = __xa_reserve(xa, index, gfp); + xa_unlock_bh(xa); + + return ret; +} + +/** + * xa_reserve_irq() - Reserve this index in the XArray. + * @xa: XArray. + * @index: Index into array. + * @gfp: Memory allocation flags. + * + * An interrupt-disabling version of xa_reserve(). + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. + * Return: 0 if the reservation succeeded or -ENOMEM if it failed. + */ +static inline +int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + int ret; + + xa_lock_irq(xa); + ret = __xa_reserve(xa, index, gfp); + xa_unlock_irq(xa); + + return ret; +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* -- cgit v1.2.3 From c5beb07e7a06b24f4f27304f6282b5dbd929543b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 31 Oct 2018 14:39:28 -0400 Subject: XArray: Unify xa_cmpxchg and __xa_cmpxchg xa_cmpxchg() was one of the largest functions in the xarray implementation. By turning it into a wrapper and having the callers take the lock (like several other functions), we save 160 bytes on a tinyconfig build and reduce the duplication in xarray.c. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 113 ++++++++++++++++++++++++++++++------------------- 1 file changed, 69 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index c2cb0426c60c..8e59d4fbd55e 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -289,8 +289,6 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); -void *xa_cmpxchg(struct xarray *, unsigned long index, - void *old, void *entry, gfp_t); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -359,48 +357,6 @@ static inline void *xa_erase(struct xarray *xa, unsigned long index) return xa_store(xa, index, NULL, 0); } -/** - * xa_insert() - Store this entry in the XArray unless another entry is - * already present. - * @xa: XArray. - * @index: Index into array. - * @entry: New entry. - * @gfp: Memory allocation flags. - * - * If you would rather see the existing entry in the array, use xa_cmpxchg(). - * This function is for users who don't care what the entry is, only that - * one is present. - * - * Context: Process context. Takes and releases the xa_lock. - * May sleep if the @gfp flags permit. - * Return: 0 if the store succeeded. -EEXIST if another entry was present. - * -ENOMEM if memory could not be allocated. - */ -static inline int xa_insert(struct xarray *xa, unsigned long index, - void *entry, gfp_t gfp) -{ - void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp); - if (!curr) - return 0; - if (xa_is_err(curr)) - return xa_err(curr); - return -EEXIST; -} - -/** - * xa_release() - Release a reserved entry. - * @xa: XArray. - * @index: Index of entry. - * - * After calling xa_reserve(), you can call this function to release the - * reservation. If the entry at @index has been stored to, this function - * will do nothing. - */ -static inline void xa_release(struct xarray *xa, unsigned long index) -{ - xa_cmpxchg(xa, index, NULL, NULL, 0); -} - /** * xa_for_each() - Iterate over a portion of an XArray. * @xa: XArray. @@ -534,6 +490,61 @@ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) return entry; } +/** + * xa_cmpxchg() - Conditionally replace an entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New value to place in array. + * @gfp: Memory allocation flags. + * + * If the entry at @index is the same as @old, replace it with @entry. + * If the return value is equal to @old, then the exchange was successful. + * + * Context: Any context. Takes and releases the xa_lock. May sleep + * if the @gfp flags permit. + * Return: The old value at this index or xa_err() if an error happened. + */ +static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock(xa); + curr = __xa_cmpxchg(xa, index, old, entry, gfp); + xa_unlock(xa); + + return curr; +} + +/** + * xa_insert() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * If you would rather see the existing entry in the array, use xa_cmpxchg(). + * This function is for users who don't care what the entry is, only that + * one is present. + * + * Context: Process context. Takes and releases the xa_lock. + * May sleep if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int xa_insert(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp); + if (!curr) + return 0; + if (xa_is_err(curr)) + return xa_err(curr); + return -EEXIST; +} + /** * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. @@ -699,6 +710,20 @@ int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) return ret; } +/** + * xa_release() - Release a reserved entry. + * @xa: XArray. + * @index: Index of entry. + * + * After calling xa_reserve(), you can call this function to release the + * reservation. If the entry at @index has been stored to, this function + * will do nothing. + */ +static inline void xa_release(struct xarray *xa, unsigned long index) +{ + xa_cmpxchg(xa, index, NULL, NULL, 0); +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* -- cgit v1.2.3 From 9c16bb88905456a9b1299338041f05fa7699971b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 5 Nov 2018 15:48:49 -0500 Subject: XArray: Turn xa_erase into an exported function Make xa_erase() take the spinlock and then call __xa_erase(), but make it out of line since it's such a common function. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 8e59d4fbd55e..4c839c17a99b 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -289,6 +289,7 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); +void *xa_erase(struct xarray *, unsigned long index); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -340,23 +341,6 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) return xa->xa_flags & XA_FLAGS_MARK(mark); } -/** - * xa_erase() - Erase this entry from the XArray. - * @xa: XArray. - * @index: Index of entry. - * - * This function is the equivalent of calling xa_store() with %NULL as - * the third argument. The XArray does not need to allocate memory, so - * the user does not need to provide GFP flags. - * - * Context: Process context. Takes and releases the xa_lock. - * Return: The entry which used to be at this index. - */ -static inline void *xa_erase(struct xarray *xa, unsigned long index) -{ - return xa_store(xa, index, NULL, 0); -} - /** * xa_for_each() - Iterate over a portion of an XArray. * @xa: XArray. -- cgit v1.2.3 From 84e5acb76dacb8ebd648a86a53907ce0dd616534 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 14:41:29 -0400 Subject: XArray: Add xa_store_bh() and xa_store_irq() These convenience wrappers disable interrupts while taking the spinlock. A number of drivers would otherwise have to open-code these functions. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 4c839c17a99b..52d9732e4ec4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -426,6 +426,58 @@ static inline int __xa_insert(struct xarray *xa, unsigned long index, return -EEXIST; } +/** + * xa_store_bh() - Store this entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_store() except it disables softirqs + * while holding the array lock. + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. + * Return: The entry which used to be at this index. + */ +static inline void *xa_store_bh(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_bh(xa); + curr = __xa_store(xa, index, entry, gfp); + xa_unlock_bh(xa); + + return curr; +} + +/** + * xa_store_irq() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_store() except it disables interrupts + * while holding the array lock. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. + * Return: The entry which used to be at this index. + */ +static inline void *xa_store_irq(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_irq(xa); + curr = __xa_store(xa, index, entry, gfp); + xa_unlock_irq(xa); + + return curr; +} + /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. -- cgit v1.2.3 From 804dfaf01bcc9daa4298c608ba9018abf616ec48 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 5 Nov 2018 16:37:15 -0500 Subject: XArray: Fix Documentation Minor fixes. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 52d9732e4ec4..564892e19f8c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -487,7 +487,7 @@ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, * the third argument. The XArray does not need to allocate memory, so * the user does not need to provide GFP flags. * - * Context: Process context. Takes and releases the xa_lock while + * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The entry which used to be at this index. */ @@ -622,7 +622,7 @@ static inline int xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, * Updates the @id pointer with the index, then stores the entry at that * index. A concurrent lookup will not see an uninitialised @id. * - * Context: Process context. Takes and releases the xa_lock while + * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if * there is no more space in the XArray. -- cgit v1.2.3 From aa9b760cec2385ad408bb2e346c7f6dc1be69a79 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 4 Nov 2018 11:32:47 +0100 Subject: HID: fix up .raw_event() documentation The documentation for the .raw_event() callback says that if the driver return 1, there will be no further processing of the event, but this is not true, the actual code in hid-core.c looks like this: if (hdrv && hdrv->raw_event && hid_match_report(hid, report)) { ret = hdrv->raw_event(hid, report, data, size); if (ret < 0) goto unlock; } ret = hid_report_raw_event(hid, type, data, size, interrupt); The only return value that has any effect on the processing is a negative error. Correct this as it seems to confuse people: I found bogus code in the Razer out-of-tree driver attempting to return 1 here. Signed-off-by: Linus Walleij Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 2827b87590d8..387c70df6f29 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -722,8 +722,8 @@ struct hid_usage_id { * input will not be passed to raw_event unless hid_device_io_start is * called. * - * raw_event and event should return 0 on no action performed, 1 when no - * further processing should be done and negative on error + * raw_event and event should return negative on error, any other value will + * pass the event on to .event() typically return 0 for success. * * input_mapping shall return a negative value to completely ignore this usage * (e.g. doubled or invalid usage), zero to continue with parsing of this -- cgit v1.2.3 From 8bd66d147c88bd441178c7b4c774ae5a185f19b8 Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Wed, 31 Oct 2018 12:39:01 -0700 Subject: include/linux/compiler*.h: define asm_volatile_goto asm_volatile_goto should also be defined for other compilers that support asm goto. Fixes commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive"). Signed-off-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3439d7d0249a..4a3f9c09c92d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -130,6 +130,10 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif +#ifndef asm_volatile_goto +#define asm_volatile_goto(x...) asm goto(x) +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) -- cgit v1.2.3 From 98ee3fc7ef8395f8b7a379e6608aee91efc66d48 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 6 Nov 2018 17:25:37 +0100 Subject: mtd: nand: Fix nanddev_pos_next_page() kernel-doc header Function name is wrong in the kernel-doc header. Fixes: 9c3736a3de21 ("mtd: nand: Add core infrastructure to deal with NAND devices") Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 78b86dea2f29..7f53ece2c039 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -568,7 +568,7 @@ static inline void nanddev_pos_next_eraseblock(struct nand_device *nand, } /** - * nanddev_pos_next_eraseblock() - Move a position to the next page + * nanddev_pos_next_page() - Move a position to the next page * @nand: NAND device * @pos: the position to update * -- cgit v1.2.3 From 81bd415c91eb966118d773dddf254aebf3022411 Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Wed, 6 Jun 2018 21:42:32 +0200 Subject: watchdog/core: Add missing prototypes for weak functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The split out of the hard lockup detector exposed two new weak functions, but no prototypes for them, which triggers the build warning: kernel/watchdog.c:109:12: warning: no previous prototype for ‘watchdog_nmi_enable’ [-Wmissing-prototypes] kernel/watchdog.c:115:13: warning: no previous prototype for ‘watchdog_nmi_disable’ [-Wmissing-prototypes] Add the prototypes. Fixes: 73ce0511c436 ("kernel/watchdog.c: move hardlockup detector to separate file") Signed-off-by: Mathieu Malaterre Signed-off-by: Thomas Gleixner Cc: Babu Moger Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180606194232.17653-1-malat@debian.org --- include/linux/nmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 08f9247e9827..9003e29cde46 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -119,6 +119,8 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } void watchdog_nmi_stop(void); void watchdog_nmi_start(void); int watchdog_nmi_probe(void); +int watchdog_nmi_enable(unsigned int cpu); +void watchdog_nmi_disable(unsigned int cpu); /** * touch_nmi_watchdog - restart NMI watchdog timeout. -- cgit v1.2.3 From 99b77fef3c6c69bb7664f1ac97a69d5b17968dae Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 31 Oct 2018 12:20:28 +0200 Subject: net/mlx5: Fix XRC SRQ umem valid bits Adapt XRC SRQ to the latest HW specification with fixed definition around umem valid bits. The previous definition relied on a bit which was taken for other purposes in legacy FW. Fixes: bd37197554eb ("net/mlx5: Update mlx5_ifc with DEVX UID bits") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dbff9ff28f2c..34e17e6f8942 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2473,14 +2473,15 @@ struct mlx5_ifc_xrc_srqc_bits { u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 dbr_umem_valid[0x1]; + u8 reserved_at_22[0x1]; u8 rlky[0x1]; u8 basic_cyclic_rcv_wqe[0x1]; u8 log_rq_stride[0x3]; u8 xrcd[0x18]; u8 page_offset[0x6]; - u8 reserved_at_46[0x2]; + u8 reserved_at_46[0x1]; + u8 dbr_umem_valid[0x1]; u8 cqn[0x18]; u8 reserved_at_60[0x20]; @@ -6689,9 +6690,12 @@ struct mlx5_ifc_create_xrc_srq_in_bits { struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_at_280[0x40]; + u8 reserved_at_280[0x60]; + u8 xrc_srq_umem_valid[0x1]; - u8 reserved_at_2c1[0x5bf]; + u8 reserved_at_2e1[0x1f]; + + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; -- cgit v1.2.3 From 781f0766cc41a9dd2e5d118ef4b1d5d89430257b Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 19 Oct 2018 16:14:50 +0800 Subject: USB: Wait for extra delay time after USB_PORT_FEAT_RESET for quirky hub Devices connected under Terminus Technology Inc. Hub (1a40:0101) may fail to work after the system resumes from suspend: [ 206.063325] usb 3-2.4: reset full-speed USB device number 4 using xhci_hcd [ 206.143691] usb 3-2.4: device descriptor read/64, error -32 [ 206.351671] usb 3-2.4: device descriptor read/64, error -32 Info for this hub: T: Bus=03 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#= 2 Spd=480 MxCh= 4 D: Ver= 2.00 Cls=09(hub ) Sub=00 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=1a40 ProdID=0101 Rev=01.11 S: Product=USB 2.0 Hub C: #Ifs= 1 Cfg#= 1 Atr=e0 MxPwr=100mA I: If#= 0 Alt= 0 #EPs= 1 Cls=09(hub ) Sub=00 Prot=00 Driver=hub Some expirements indicate that the USB devices connected to the hub are innocent, it's the hub itself is to blame. The hub needs extra delay time after it resets its port. Hence wait for extra delay, if the device is connected to this quirky hub. Signed-off-by: Kai-Heng Feng Cc: stable Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/quirks.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index b7a99ce56bc9..a1be64c9940f 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -66,4 +66,7 @@ /* Device needs a pause after every control message. */ #define USB_QUIRK_DELAY_CTRL_MSG BIT(13) +/* Hub needs extra delay after resetting its port. */ +#define USB_QUIRK_HUB_SLOW_RESET BIT(14) + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From 24efee412c75843755da0ddd7bbc2db2ce9129f5 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 6 Nov 2018 22:52:11 +0100 Subject: Compiler Attributes: improve explanation of header Explain better what "optional" attributes are, and avoid calling them so to avoid confusion. Simply retain "Optional" as a word to look for in the comments. Moreover, add a couple sentences to explain a bit more the intention and the documentation links. Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 6b28c1b7310c..f8c400ba1929 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -4,22 +4,26 @@ /* * The attributes in this file are unconditionally defined and they directly - * map to compiler attribute(s) -- except those that are optional. + * map to compiler attribute(s), unless one of the compilers does not support + * the attribute. In that case, __has_attribute is used to check for support + * and the reason is stated in its comment ("Optional: ..."). * * Any other "attributes" (i.e. those that depend on a configuration option, * on a compiler, on an architecture, on plugins, on other attributes...) * should be defined elsewhere (e.g. compiler_types.h or compiler-*.h). + * The intention is to keep this file as simple as possible, as well as + * compiler- and version-agnostic (e.g. avoiding GCC_VERSION checks). * * This file is meant to be sorted (by actual attribute name, * not by #define identifier). Use the __attribute__((__name__)) syntax * (i.e. with underscores) to avoid future collisions with other macros. - * If an attribute is optional, state the reason in the comment. + * Provide links to the documentation of each supported compiler, if it exists. */ /* - * To check for optional attributes, we use __has_attribute, which is supported - * on gcc >= 5, clang >= 2.9 and icc >= 17. In the meantime, to support - * 4.6 <= gcc < 5, we implement __has_attribute by hand. + * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. + * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute + * by hand. * * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__ * depending on the compiler used to build it; however, these attributes have -- cgit v1.2.3 From 23c625ce3065e40c933a4239efb9b11f1194a343 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 8 Nov 2018 14:55:21 +0100 Subject: libceph: assume argonaut on the server side No one is running pre-argonaut. In addition one of the argonaut features (NOSRCADDR) has been required since day one (and a half, 2.6.34 vs 2.6.35) of the kernel client. Allow for the possibility of reusing these feature bits later. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 6b92b3395fa9..65a38c4a02a1 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -213,12 +213,6 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \ CEPH_FEATURE_CEPHX_V2) -#define CEPH_FEATURES_REQUIRED_DEFAULT \ - (CEPH_FEATURE_NOSRCADDR | \ - CEPH_FEATURE_SUBSCRIBE2 | \ - CEPH_FEATURE_RECONNECT_SEQ | \ - CEPH_FEATURE_PGID64 | \ - CEPH_FEATURE_PGPOOL3 | \ - CEPH_FEATURE_OSDENC) +#define CEPH_FEATURES_REQUIRED_DEFAULT 0 #endif -- cgit v1.2.3 From a4310fa2f24687888ce80fdb0e88583561a23700 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 31 Oct 2018 10:37:46 +0100 Subject: can: dev: can_get_echo_skb(): factor out non sending code to __can_get_echo_skb() This patch factors out all non sending parts of can_get_echo_skb() into a seperate function __can_get_echo_skb(), so that it can be re-used in an upcoming patch. Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index a83e1f632eb7..f01623aef2f7 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -169,6 +169,7 @@ void can_change_state(struct net_device *dev, struct can_frame *cf, void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx); +struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr); unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); void can_free_echo_skb(struct net_device *dev, unsigned int idx); -- cgit v1.2.3 From 55059f2b7f868cd43b3ad30e28e18347e1b46ace Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 18 Sep 2018 11:40:38 +0200 Subject: can: rx-offload: introduce can_rx_offload_get_echo_skb() and can_rx_offload_queue_sorted() functions Current CAN framework can't guarantee proper/chronological order of RX and TX-ECHO messages. To make this possible, drivers should use this functions instead of can_get_echo_skb(). Signed-off-by: Oleksij Rempel Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- include/linux/can/rx-offload.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index cb31683bbe15..01a7c9e5d8d8 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -41,6 +41,10 @@ int can_rx_offload_add_timestamp(struct net_device *dev, struct can_rx_offload * int can_rx_offload_add_fifo(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight); int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 reg); int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); +int can_rx_offload_queue_sorted(struct can_rx_offload *offload, + struct sk_buff *skb, u32 timestamp); +unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, + unsigned int idx, u32 timestamp); int can_rx_offload_irq_queue_err_skb(struct can_rx_offload *offload, struct sk_buff *skb); void can_rx_offload_reset(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); -- cgit v1.2.3 From 4530ec36bb1e0d24f41c33229694adacda3d5d89 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 18 Sep 2018 11:40:40 +0200 Subject: can: rx-offload: rename can_rx_offload_irq_queue_err_skb() to can_rx_offload_queue_tail() This function has nothing todo with error. Signed-off-by: Oleksij Rempel Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- include/linux/can/rx-offload.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 01a7c9e5d8d8..8268811a697e 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -45,7 +45,8 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload, struct sk_buff *skb, u32 timestamp); unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, unsigned int idx, u32 timestamp); -int can_rx_offload_irq_queue_err_skb(struct can_rx_offload *offload, struct sk_buff *skb); +int can_rx_offload_queue_tail(struct can_rx_offload *offload, + struct sk_buff *skb); void can_rx_offload_reset(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); void can_rx_offload_enable(struct can_rx_offload *offload); -- cgit v1.2.3 From d19f9130b814d33c03118493c17454f7d90075d1 Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Sat, 10 Nov 2018 04:22:09 +0100 Subject: x86/ptrace: Fix documentation for tracehook_report_syscall_entry() tracehook_report_syscall_entry() is called not only if %TIF_SYSCALL_TRACE is set, but also if %TIF_SYSCALL_EMU is set, as appears from x86's entry code. Signed-off-by: Elvira Khabirova Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: ldv@altlinux.org Cc: oleg@redhat.com Cc: rostedt@goodmis.org Link: http://lkml.kernel.org/r/20181110042209.26333972@akathisia Signed-off-by: Ingo Molnar --- include/linux/tracehook.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 40b0b4c1bf7b..df20f8bdbfa3 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -83,8 +83,8 @@ static inline int ptrace_report_syscall(struct pt_regs *regs) * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * - * This will be called if %TIF_SYSCALL_TRACE has been set, when the - * current task has just entered the kernel for a system call. + * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set, + * when the current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. -- cgit v1.2.3 From eff896288872d687d9662000ec9ae11b6d61766f Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Nov 2018 09:55:43 -0800 Subject: efi/arm: Defer persistent reservations until after paging_init() The new memory EFI reservation feature we introduced to allow memory reservations to persist across kexec may trigger an unbounded number of calls to memblock_reserve(). The memblock subsystem can deal with this fine, but not before memblock resizing is enabled, which we can only do after paging_init(), when the memory we reallocate the array into is actually mapped. So break out the memreserve table processing into a separate routine and call it after paging_init() on arm64. On ARM, because of limited reviewing bandwidth of the maintainer, we cannot currently fix this, so instead, disable the EFI persistent memreserve entirely on ARM so we can fix it later. Tested-by: Marc Zyngier Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20181114175544.12860-5-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 845174e113ce..100ce4a4aff6 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1167,6 +1167,8 @@ static inline bool efi_enabled(int feature) extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused); extern bool efi_is_table_address(unsigned long phys_addr); + +extern int efi_apply_persistent_mem_reservations(void); #else static inline bool efi_enabled(int feature) { @@ -1185,6 +1187,11 @@ static inline bool efi_is_table_address(unsigned long phys_addr) { return false; } + +static inline int efi_apply_persistent_mem_reservations(void) +{ + return 0; +} #endif extern int efi_status_to_err(efi_status_t status); -- cgit v1.2.3 From 0145b50566e7de5637e80ecba96c7f0e6fff1aad Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 31 Oct 2018 15:20:05 +0100 Subject: iio/hid-sensors: Fix IIO_CHAN_INFO_RAW returning wrong values for signed numbers Before this commit sensor_hub_input_attr_get_raw_value() failed to take the signedness of 16 and 8 bit values into account, returning e.g. 65436 instead of -100 for the z-axis reading of an accelerometer. This commit adds a new is_signed parameter to the function and makes all callers pass the appropriate value for this. While at it, this commit also fixes up some neighboring lines where statements were needlessly split over 2 lines to improve readability. Signed-off-by: Hans de Goede Acked-by: Srinivas Pandruvada Acked-by: Benjamin Tissoires Cc: Signed-off-by: Jonathan Cameron --- include/linux/hid-sensor-hub.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 331dc377c275..dc12f5c4b076 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -177,6 +177,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev, * @attr_usage_id: Attribute usage id as per spec * @report_id: Report id to look for * @flag: Synchronous or asynchronous read +* @is_signed: If true then fields < 32 bits will be sign-extended * * Issues a synchronous or asynchronous read request for an input attribute. * Returns data upto 32 bits. @@ -190,7 +191,8 @@ enum sensor_hub_read_flags { int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, u32 usage_id, u32 attr_usage_id, u32 report_id, - enum sensor_hub_read_flags flag + enum sensor_hub_read_flags flag, + bool is_signed ); /** -- cgit v1.2.3 From b34087157dd76e8d96e5e52808134a791ac61e57 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 21 Nov 2018 16:00:50 +0000 Subject: dma-direct: Make DIRECT_MAPPING_ERROR viable for SWIOTLB With the overflow buffer removed, we no longer have a unique address which is guaranteed not to be a valid DMA target to use as an error token. The DIRECT_MAPPING_ERROR value of 0 tries to at least represent an unlikely DMA target, but unfortunately there are already SWIOTLB users with DMA-able memory at physical address 0 which now gets falsely treated as a mapping failure and leads to all manner of misbehaviour. The best we can do to mitigate that is flip DIRECT_MAPPING_ERROR to the other commonly-used error value of all-bits-set, since the last single byte of memory is by far the least-likely-valid DMA target. Fixes: dff8d6c1ed58 ("swiotlb: remove the overflow buffer") Reported-by: John Stultz Tested-by: John Stultz Acked-by: Konrad Rzeszutek Wilk Signed-off-by: Robin Murphy Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index bd73e7a91410..9e66bfe369aa 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,7 +5,7 @@ #include #include -#define DIRECT_MAPPING_ERROR 0 +#define DIRECT_MAPPING_ERROR (~(dma_addr_t)0) #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include -- cgit v1.2.3 From 86de5921a3d5dd246df661e09bdd0a6131b39ae3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Nov 2018 05:53:59 -0800 Subject: tcp: defer SACK compression after DupThresh Jean-Louis reported a TCP regression and bisected to recent SACK compression. After a loss episode (receiver not able to keep up and dropping packets because its backlog is full), linux TCP stack is sending a single SACK (DUPACK). Sender waits a full RTO timer before recovering losses. While RFC 6675 says in section 5, "Algorithm Details", (2) If DupAcks < DupThresh but IsLost (HighACK + 1) returns true -- indicating at least three segments have arrived above the current cumulative acknowledgment point, which is taken to indicate loss -- go to step (4). ... (4) Invoke fast retransmit and enter loss recovery as follows: there are old TCP stacks not implementing this strategy, and still counting the dupacks before starting fast retransmit. While these stacks probably perform poorly when receivers implement LRO/GRO, we should be a little more gentle to them. This patch makes sure we do not enable SACK compression unless 3 dupacks have been sent since last rcv_nxt update. Ideally we should even rearm the timer to send one or two more DUPACK if no more packets are coming, but that will be work aiming for linux-4.21. Many thanks to Jean-Louis for bisecting the issue, providing packet captures and testing this patch. Fixes: 5d9f4262b7ea ("tcp: add SACK compression") Reported-by: Jean-Louis Dupond Tested-by: Jean-Louis Dupond Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 8ed77bb4ed86..a9b0280687d5 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -196,6 +196,7 @@ struct tcp_sock { u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ u32 last_oow_ack_time; /* timestamp of last out-of-window ACK */ + u32 compressed_ack_rcv_nxt; u32 tsoffset; /* timestamp offset */ -- cgit v1.2.3 From f1539a0c2545d7bd82e451bd1464f2a820f55de4 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Wed, 21 Nov 2018 16:27:11 +0100 Subject: Revert "HID: input: Create a utility class for counting scroll events" This reverts commit 1ff2e1a44e02d4bdbb9be67c7d9acc240a67141f. It turns out the current API is not that compatible with some Microsoft mice, so better start again from scratch. Signed-off-by: Benjamin Tissoires Acked-by: Harry Cutts Acked-by: Dmitry Torokhov Acked-by: Jiri Kosina --- include/linux/hid.h | 28 ---------------------------- 1 file changed, 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 387c70df6f29..a355d61940f2 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1139,34 +1139,6 @@ static inline u32 hid_report_len(struct hid_report *report) int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, int interrupt); - -/** - * struct hid_scroll_counter - Utility class for processing high-resolution - * scroll events. - * @dev: the input device for which events should be reported. - * @microns_per_hi_res_unit: the amount moved by the user's finger for each - * high-resolution unit reported by the mouse, in - * microns. - * @resolution_multiplier: the wheel's resolution in high-resolution mode as a - * multiple of its lower resolution. For example, if - * moving the wheel by one "notch" would result in a - * value of 1 in low-resolution mode but 8 in - * high-resolution, the multiplier is 8. - * @remainder: counts the number of high-resolution units moved since the last - * low-resolution event (REL_WHEEL or REL_HWHEEL) was sent. Should - * only be used by class methods. - */ -struct hid_scroll_counter { - struct input_dev *dev; - int microns_per_hi_res_unit; - int resolution_multiplier; - - int remainder; -}; - -void hid_scroll_counter_handle_scroll(struct hid_scroll_counter *counter, - int hi_res_value); - /* HID quirks API */ unsigned long hid_lookup_quirk(const struct hid_device *hdev); int hid_quirks_init(char **quirks_param, __u16 bus, int count); -- cgit v1.2.3 From 0211dda68a4f6531923a2f72d8e8959207f59fba Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Wed, 21 Nov 2018 16:28:23 +0200 Subject: net/dim: Update DIM start sample after each DIM iteration On every iteration of net_dim, the algorithm may choose to check for the system state by comparing current data sample with previous data sample. After each of these comparison, regardless of the action taken, the sample used as baseline is needed to be updated. This patch fixes a bug that causes DIM to take wrong decisions, due to never updating the baseline sample for comparison between iterations. This way, DIM always compares current sample with zeros. Although this is a functional fix, it also improves and stabilizes performance as the algorithm works properly now. Performance: Tested single UDP TX stream with pktgen: samples/pktgen/pktgen_sample03_burst_single_flow.sh -i p4p2 -d 1.1.1.1 -m 24:8a:07:88:26:8b -f 3 -b 128 ConnectX-5 100GbE packet rate improved from 15-19Mpps to 19-20Mpps. Also, toggling between profiles is less frequent with the fix. Fixes: 8115b750dbcb ("net/dim: use struct net_dim_sample as arg to net_dim") Signed-off-by: Tal Gilboa Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/net_dim.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index c79e859408e6..fd458389f7d1 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -406,6 +406,8 @@ static inline void net_dim(struct net_dim *dim, } /* fall through */ case NET_DIM_START_MEASURE: + net_dim_sample(end_sample.event_ctr, end_sample.pkt_ctr, end_sample.byte_ctr, + &dim->start_sample); dim->state = NET_DIM_MEASURE_IN_PROGRESS; break; case NET_DIM_APPLY_NEW_PROFILE: -- cgit v1.2.3 From 5cd8d46ea1562be80063f53c7c6a5f40224de623 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 20 Nov 2018 13:00:18 -0500 Subject: packet: copy user buffers before orphan or clone tpacket_snd sends packets with user pages linked into skb frags. It notifies that pages can be reused when the skb is released by setting skb->destructor to tpacket_destruct_skb. This can cause data corruption if the skb is orphaned (e.g., on transmit through veth) or cloned (e.g., on mirror to another psock). Create a kernel-private copy of data in these cases, same as tun/tap zerocopy transmission. Reuse that infrastructure: mark the skb as SKBTX_ZEROCOPY_FRAG, which will trigger copy in skb_orphan_frags(_rx). Unlike other zerocopy packets, do not set shinfo destructor_arg to struct ubuf_info. tpacket_destruct_skb already uses that ptr to notify when the original skb is released and a timestamp is recorded. Do not change this timestamp behavior. The ubuf_info->callback is not needed anyway, as no zerocopy notification is expected. Mark destructor_arg as not-a-uarg by setting the lower bit to 1. The resulting value is not a valid ubuf_info pointer, nor a valid tpacket_snd frame address. Add skb_zcopy_.._nouarg helpers for this. The fix relies on features introduced in commit 52267790ef52 ("sock: add MSG_ZEROCOPY"), so can be backported as is only to 4.14. Tested with from `./in_netns.sh ./txring_overwrite` from http://github.com/wdebruij/kerneltools/tests Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap") Reported-by: Anand H. Krishnan Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0ba687454267..0d1b2c3f127b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1326,6 +1326,22 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg) } } +static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) +{ + skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); + skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; +} + +static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) +{ + return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL; +} + +static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) +{ + return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); +} + /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) { @@ -1335,7 +1351,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) if (uarg->callback == sock_zerocopy_callback) { uarg->zerocopy = uarg->zerocopy && zerocopy; sock_zerocopy_put(uarg); - } else { + } else if (!skb_zcopy_is_nouarg(skb)) { uarg->callback(uarg, zerocopy); } -- cgit v1.2.3 From 89259088c1b7fecb43e8e245dc931909132a4e03 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 17 Nov 2018 11:32:29 +0100 Subject: netfilter: nfnetlink_cttimeout: fetch timeouts for udplite and gre, too syzbot was able to trigger the WARN in cttimeout_default_get() by passing UDPLITE as l4protocol. Alias UDPLITE to UDP, both use same timeout values. Furthermore, also fetch GRE timeouts. GRE is a bit more complicated, as it still can be a module and its netns_proto_gre struct layout isn't visible outside of the gre module. Can't move timeouts around, it appears conntrack sysctl unregister assumes net_generic() returns nf_proto_net, so we get crash. Expose layout of netns_proto_gre instead. A followup nf-next patch could make gre tracker be built-in as well if needed, its not that large. Last, make the WARN() mention the missing protocol value in case anything else is missing. Reported-by: syzbot+2fae8fa157dd92618cae@syzkaller.appspotmail.com Fixes: 8866df9264a3 ("netfilter: nfnetlink_cttimeout: pass default timeout policy to obj_to_nlattr") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_proto_gre.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index b8d95564bd53..14edb795ab43 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -21,6 +21,19 @@ struct nf_ct_gre_keymap { struct nf_conntrack_tuple tuple; }; +enum grep_conntrack { + GRE_CT_UNREPLIED, + GRE_CT_REPLIED, + GRE_CT_MAX +}; + +struct netns_proto_gre { + struct nf_proto_net nf; + rwlock_t keymap_lock; + struct list_head keymap_list; + unsigned int gre_timeouts[GRE_CT_MAX]; +}; + /* add new tuple->key_reply pair to keymap */ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t); -- cgit v1.2.3 From 786a9ab1330169f2602238822b4df5d5c4c98f6c Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 21 Nov 2018 10:35:17 +0100 Subject: gpio: davinci: restore a way to manually specify the GPIO base Commit 587f7a694f01 ("gpio: davinci: Use dev name for label and automatic base selection") broke the network support in legacy boot mode for da850-evm since we can no longer request the MDIO clock GPIO. Other boards may be broken too, which I haven't tested. The problem is in the fact that most board files still use the legacy GPIO API where lines are requested by numbers rather than descriptors. While this should be fixed eventually, in order to unbreak the board for now - provide a way to manually specify the GPIO base in platform data. Fixes: 587f7a694f01 ("gpio: davinci: Use dev name for label and automatic base selection") Cc: stable@vger.kernel.org Signed-off-by: Bartosz Golaszewski Acked-by: Linus Walleij Signed-off-by: Sekhar Nori --- include/linux/platform_data/gpio-davinci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index f92a47e18034..a93841bfb9f7 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -17,6 +17,8 @@ #define __DAVINCI_GPIO_PLATFORM_H struct davinci_gpio_platform_data { + bool no_auto_base; + u32 base; u32 ngpio; u32 gpio_unbanked; }; -- cgit v1.2.3 From 8114865ff82e200b383e46821c25cb0625b842b5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sun, 18 Nov 2018 17:10:15 -0500 Subject: function_graph: Create function_graph_enter() to consolidate architecture code Currently all the architectures do basically the same thing in preparing the function graph tracer on entry to a function. This code can be pulled into a generic location and then this will allow the function graph tracer to be fixed, as well as extended. Create a new function graph helper function_graph_enter() that will call the hook function (ftrace_graph_entry) and the shadow stack operation (ftrace_push_return_trace), and remove the need of the architecture code to manage the shadow stack. This is needed to prepare for a fix of a design bug on how the curr_ret_stack is used. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a397907e8d72..5717e8f81c59 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -779,6 +779,9 @@ extern void return_to_handler(void); extern int ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, unsigned long frame_pointer, unsigned long *retp); +extern int +function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp); unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, unsigned long *retp); -- cgit v1.2.3 From e2c95a61656d29ceaac97b6a975c8a1f26e26f15 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 26 Nov 2018 14:05:38 +0100 Subject: bpf, ppc64: generalize fetching subprog into bpf_jit_get_func_addr Make fetching of the BPF call address from ppc64 JIT generic. ppc64 was using a slightly different variant rather than through the insns' imm field encoding as the target address would not fit into that space. Therefore, the target subprog number was encoded into the insns' offset and fetched through fp->aux->func[off]->bpf_func instead. Given there are other JITs with this issue and the mechanism of fetching the address is JIT-generic, move it into the core as a helper instead. On the JIT side, we get information on whether the retrieved address is a fixed one, that is, not changing through JIT passes, or a dynamic one. For the former, JITs can optimize their imm emission because this doesn't change jump offsets throughout JIT process. Signed-off-by: Daniel Borkmann Reviewed-by: Sandipan Das Tested-by: Sandipan Das Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index de629b706d1d..448dcc448f1f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -866,6 +866,10 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr); void bpf_jit_free(struct bpf_prog *fp); +int bpf_jit_get_func_addr(const struct bpf_prog *prog, + const struct bpf_insn *insn, bool extra_pass, + u64 *func_addr, bool *func_addr_fixed); + struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp); void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); -- cgit v1.2.3 From d125f3f866df88da5a85df00291f88f0baa89f7c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 19 Nov 2018 07:40:39 -0500 Subject: function_graph: Make ftrace_push_return_trace() static As all architectures now call function_graph_enter() to do the entry work, no architecture should ever call ftrace_push_return_trace(). Make it static. This is needed to prepare for a fix of a design bug on how the curr_ret_stack is used. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 5717e8f81c59..dd16e8218db3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -776,9 +776,6 @@ struct ftrace_ret_stack { */ extern void return_to_handler(void); -extern int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, - unsigned long frame_pointer, unsigned long *retp); extern int function_graph_enter(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp); -- cgit v1.2.3 From 39eb456dacb543de90d3bc6a8e0ac5cf51ac475e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 19 Nov 2018 08:07:12 -0500 Subject: function_graph: Use new curr_ret_depth to manage depth instead of curr_ret_stack Currently, the depth of the ret_stack is determined by curr_ret_stack index. The issue is that there's a race between setting of the curr_ret_stack and calling of the callback attached to the return of the function. Commit 03274a3ffb44 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") moved the calling of the callback to after the setting of the curr_ret_stack, even stating that it was safe to do so, when in fact, it was the reason there was a barrier() there (yes, I should have commented that barrier()). Not only does the curr_ret_stack keep track of the current call graph depth, it also keeps the ret_stack content from being overwritten by new data. The function profiler, uses the "subtime" variable of ret_stack structure and by moving the curr_ret_stack, it allows for interrupts to use the same structure it was using, corrupting the data, and breaking the profiler. To fix this, there needs to be two variables to handle the call stack depth and the pointer to where the ret_stack is being used, as they need to change at two different locations. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..d6183a55e8eb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1116,6 +1116,7 @@ struct task_struct { #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; + int curr_ret_depth; /* Stack of return addresses for return function tracing: */ struct ftrace_ret_stack *ret_stack; -- cgit v1.2.3 From 321a874a7ef85655e93b3206d0f36b4a6097f948 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:38 +0100 Subject: sched/smt: Expose sched_smt_present static key Make the scheduler's 'sched_smt_present' static key globaly available, so it can be used in the x86 speculation control code. Provide a query function and a stub for the CONFIG_SMP=n case. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185004.430168326@linutronix.de --- include/linux/sched/smt.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/sched/smt.h (limited to 'include/linux') diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h new file mode 100644 index 000000000000..c9e0be514110 --- /dev/null +++ b/include/linux/sched/smt.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SCHED_SMT_H +#define _LINUX_SCHED_SMT_H + +#include + +#ifdef CONFIG_SCHED_SMT +extern struct static_key_false sched_smt_present; + +static __always_inline bool sched_smt_active(void) +{ + return static_branch_likely(&sched_smt_present); +} +#else +static inline bool sched_smt_active(void) { return false; } +#endif + +#endif -- cgit v1.2.3 From a74cfffb03b73d41e08f84c2e5c87dec0ce3db9f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:39 +0100 Subject: x86/speculation: Rework SMT state change arch_smt_update() is only called when the sysfs SMT control knob is changed. This means that when SMT is enabled in the sysfs control knob the system is considered to have SMT active even if all siblings are offline. To allow finegrained control of the speculation mitigations, the actual SMT state is more interesting than the fact that siblings could be enabled. Rework the code, so arch_smt_update() is invoked from each individual CPU hotplug function, and simplify the update function while at it. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185004.521974984@linutronix.de --- include/linux/sched/smt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h index c9e0be514110..59d3736c454c 100644 --- a/include/linux/sched/smt.h +++ b/include/linux/sched/smt.h @@ -15,4 +15,6 @@ static __always_inline bool sched_smt_active(void) static inline bool sched_smt_active(void) { return false; } #endif +void arch_smt_update(void); + #endif -- cgit v1.2.3 From 46f7ecb1e7359f183f5bbd1e08b90e10e52164f9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:50 +0100 Subject: ptrace: Remove unused ptrace_may_access_sched() and MODE_IBRS The IBPB control code in x86 removed the usage. Remove the functionality which was introduced for this. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185005.559149393@linutronix.de --- include/linux/ptrace.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 6c2ffed907f5..de20ede2c5c8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -64,15 +64,12 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_NOAUDIT 0x04 #define PTRACE_MODE_FSCREDS 0x08 #define PTRACE_MODE_REALCREDS 0x10 -#define PTRACE_MODE_SCHED 0x20 -#define PTRACE_MODE_IBPB 0x40 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) -#define PTRACE_MODE_SPEC_IBPB (PTRACE_MODE_ATTACH_REALCREDS | PTRACE_MODE_IBPB) /** * ptrace_may_access - check whether the caller is permitted to access @@ -90,20 +87,6 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); -/** - * ptrace_may_access - check whether the caller is permitted to access - * a target task. - * @task: target task - * @mode: selects type of access and caller credentials - * - * Returns true on success, false on denial. - * - * Similar to ptrace_may_access(). Only to be called from context switch - * code. Does not call into audit and the regular LSM hooks due to locking - * constraints. - */ -extern bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode); - static inline int ptrace_reparented(struct task_struct *child) { return !same_thread_group(child->real_parent, child->parent); -- cgit v1.2.3 From 9137bb27e60e554dab694eafa4cca241fa3a694f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:53 +0100 Subject: x86/speculation: Add prctl() control for indirect branch speculation Add the PR_SPEC_INDIRECT_BRANCH option for the PR_GET_SPECULATION_CTRL and PR_SET_SPECULATION_CTRL prctls to allow fine grained per task control of indirect branch speculation via STIBP and IBPB. Invocations: Check indirect branch speculation status with - prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0); Enable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0); Disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0); Force disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0); See Documentation/userspace-api/spec_ctrl.rst. Signed-off-by: Tim Chen Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185005.866780996@linutronix.de --- include/linux/sched.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..d607db5fcc6a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1453,6 +1453,8 @@ static inline bool is_percpu_thread(void) #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ +#define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ +#define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1484,6 +1486,13 @@ TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) +TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) + +TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) +TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) + static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { -- cgit v1.2.3 From 3f2b7b9035107d6096ea438ea3d97dcf0481b6d2 Mon Sep 17 00:00:00 2001 From: "kiran.modukuri" Date: Mon, 26 Nov 2018 15:41:48 +0000 Subject: fscache: Fix race in fscache_op_complete() due to split atomic_sub & read The code in fscache_retrieval_complete is using atomic_sub followed by an atomic_read: atomic_sub(n_pages, &op->n_pages); if (atomic_read(&op->n_pages) <= 0) fscache_op_complete(&op->op, true); This causes two threads doing a decrement of n_pages to race with each other seeing the op->refcount 0 at same time - and they end up calling fscache_op_complete() in both the threads leading to an assertion failure. Fix this by using atomic_sub_return_relaxed() instead of two calls. Note that I'm using 'relaxed' rather than, say, 'release' as there aren't multiple variables that appear to need ordering across the release. The oops looks something like: FS-Cache: Assertion failed FS-Cache: 0 > 0 is false ... kernel BUG at /usr/src/linux-4.4.0/fs/fscache/operation.c:449! ... Workqueue: fscache_operation fscache_op_work_func [fscache] ... RIP: 0010:[] fscache_op_complete+0x10d/0x180 [fscache] ... Call Trace: [] cachefiles_read_copier+0x3a9/0x410 [cachefiles] [] fscache_op_work_func+0x22/0x50 [fscache] [] process_one_work+0x150/0x3f0 [] worker_thread+0x11a/0x470 [] ? __schedule+0x359/0x980 [] ? rescuer_thread+0x310/0x310 [] kthread+0xd6/0xf0 [] ? kthread_park+0x60/0x60 [] ret_from_fork+0x3f/0x70 [] ? kthread_park+0x60/0x60 This seen this in 4.4.x kernels and the same bug affects fscache in latest upstreams kernels. Fixes: 1bb4b7f98f36 ("FS-Cache: The retrieval remaining-pages counter needs to be atomic_t") Signed-off-by: Kiran Kumar Modukuri Signed-off-by: David Howells --- include/linux/fscache-cache.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 34cf0fdd7dc7..610815e3f1aa 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -196,8 +196,7 @@ static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op) static inline void fscache_retrieval_complete(struct fscache_retrieval *op, int n_pages) { - atomic_sub(n_pages, &op->n_pages); - if (atomic_read(&op->n_pages) <= 0) + if (atomic_sub_return_relaxed(n_pages, &op->n_pages) <= 0) fscache_op_complete(&op->op, false); } -- cgit v1.2.3 From 90230968f102acbe103fbf7c03d41addfef5f153 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Thu, 29 Nov 2018 12:00:05 +0200 Subject: net: phy: sfp: correct location of SFP standards SFP standards are now available from the SNIA (Storage Networking Industry Association) website. Cc: Andrew Lunn Cc: Florian Fainelli Signed-off-by: Baruch Siach Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/sfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index d37518e89db2..d9d9de3fcf8e 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -224,7 +224,7 @@ struct sfp_eeprom_ext { * * See the SFF-8472 specification and related documents for the definition * of these structure members. This can be obtained from - * ftp://ftp.seagate.com/sff + * https://www.snia.org/technology-communities/sff/specifications */ struct sfp_eeprom_id { struct sfp_eeprom_base base; -- cgit v1.2.3 From 89d328f637b9904b6d4c9af73c8a608b8dd4d6f8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 1 Nov 2018 16:17:22 -0700 Subject: pstore/ram: Correctly calculate usable PRZ bytes The actual number of bytes stored in a PRZ is smaller than the bytes requested by platform data, since there is a header on each PRZ. Additionally, if ECC is enabled, there are trailing bytes used as well. Normally this mismatch doesn't matter since PRZs are circular buffers and the leading "overflow" bytes are just thrown away. However, in the case of a compressed record, this rather badly corrupts the results. This corruption was visible with "ramoops.mem_size=204800 ramoops.ecc=1". Any stored crashes would not be uncompressable (producing a pstorefs "dmesg-*.enc.z" file), and triggering errors at boot: [ 2.790759] pstore: crypto_comp_decompress failed, ret = -22! Backporting this depends on commit 70ad35db3321 ("pstore: Convert console write to use ->write_buf") Reported-by: Joel Fernandes Fixes: b0aad7a99c1d ("pstore: Add compression support to pstore") Signed-off-by: Kees Cook Reviewed-by: Joel Fernandes (Google) --- include/linux/pstore.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index a15bc4d48752..30fcec375a3a 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -90,7 +90,10 @@ struct pstore_record { * * @buf_lock: spinlock to serialize access to @buf * @buf: preallocated crash dump buffer - * @bufsize: size of @buf available for crash dump writes + * @bufsize: size of @buf available for crash dump bytes (must match + * smallest number of bytes available for writing to a + * backend entry, since compressed bytes don't take kindly + * to being truncated) * * @read_mutex: serializes @open, @read, @close, and @erase callbacks * @flags: bitfield of frontends the backend can accept writes for -- cgit v1.2.3 From 0c7a52e4d4b5c4d35b31f3c3ad32af814f1bf491 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Wed, 28 Nov 2018 03:35:23 +0000 Subject: tracepoint: Use __idx instead of idx in DO_TRACE macro to make it unique After enabling KVM event tracing, almost all of trace_kvm_exit()'s printk shows "kvm_exit: IRQ: ..." even if the actual exception_type is NOT IRQ. More specifically, trace_kvm_exit() is defined in virt/kvm/arm/trace.h by TRACE_EVENT. This slight problem may have existed after commit e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU"). There are two variables in trace_kvm_exit() and __DO_TRACE() which have the same name, *idx*. Thus the actual value of *idx* will be overwritten when tracing. Fix it by adding a simple prefix. Cc: Joel Fernandes Cc: Wang Haibin Cc: linux-trace-devel@vger.kernel.org Cc: stable@vger.kernel.org Fixes: e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU") Reviewed-by: Joel Fernandes (Google) Signed-off-by: Zenghui Yu Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 538ba1a58f5b..e9de8ad0bad7 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -166,7 +166,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) struct tracepoint_func *it_func_ptr; \ void *it_func; \ void *__data; \ - int __maybe_unused idx = 0; \ + int __maybe_unused __idx = 0; \ \ if (!(cond)) \ return; \ @@ -182,7 +182,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * doesn't work from the idle path. \ */ \ if (rcuidle) { \ - idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + __idx = srcu_read_lock_notrace(&tracepoint_srcu);\ rcu_irq_enter_irqson(); \ } \ \ @@ -198,7 +198,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) \ if (rcuidle) { \ rcu_irq_exit_irqson(); \ - srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + srcu_read_unlock_notrace(&tracepoint_srcu, __idx);\ } \ \ preempt_enable_notrace(); \ -- cgit v1.2.3 From e0c274472d5d27f277af722e017525e0b33784cd Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 30 Nov 2018 14:09:58 -0800 Subject: psi: make disabling/enabling easier for vendor kernels Mel Gorman reports a hackbench regression with psi that would prohibit shipping the suse kernel with it default-enabled, but he'd still like users to be able to opt in at little to no cost to others. With the current combination of CONFIG_PSI and the psi_disabled bool set from the commandline, this is a challenge. Do the following things to make it easier: 1. Add a config option CONFIG_PSI_DEFAULT_DISABLED that allows distros to enable CONFIG_PSI in their kernel but leave the feature disabled unless a user requests it at boot-time. To avoid double negatives, rename psi_disabled= to psi=. 2. Make psi_disabled a static branch to eliminate any branch costs when the feature is disabled. In terms of numbers before and after this patch, Mel says: : The following is a comparision using CONFIG_PSI=n as a baseline against : your patch and a vanilla kernel : : 4.20.0-rc4 4.20.0-rc4 4.20.0-rc4 : kconfigdisable-v1r1 vanilla psidisable-v1r1 : Amean 1 1.3100 ( 0.00%) 1.3923 ( -6.28%) 1.3427 ( -2.49%) : Amean 3 3.8860 ( 0.00%) 4.1230 * -6.10%* 3.8860 ( -0.00%) : Amean 5 6.8847 ( 0.00%) 8.0390 * -16.77%* 6.7727 ( 1.63%) : Amean 7 9.9310 ( 0.00%) 10.8367 * -9.12%* 9.9910 ( -0.60%) : Amean 12 16.6577 ( 0.00%) 18.2363 * -9.48%* 17.1083 ( -2.71%) : Amean 18 26.5133 ( 0.00%) 27.8833 * -5.17%* 25.7663 ( 2.82%) : Amean 24 34.3003 ( 0.00%) 34.6830 ( -1.12%) 32.0450 ( 6.58%) : Amean 30 40.0063 ( 0.00%) 40.5800 ( -1.43%) 41.5087 ( -3.76%) : Amean 32 40.1407 ( 0.00%) 41.2273 ( -2.71%) 39.9417 ( 0.50%) : : It's showing that the vanilla kernel takes a hit (as the bisection : indicated it would) and that disabling PSI by default is reasonably : close in terms of performance for this particular workload on this : particular machine so; Link: http://lkml.kernel.org/r/20181127165329.GA29728@cmpxchg.org Signed-off-by: Johannes Weiner Tested-by: Mel Gorman Reported-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/psi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/psi.h b/include/linux/psi.h index 8e0725aac0aa..7006008d5b72 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -1,6 +1,7 @@ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H +#include #include #include @@ -9,7 +10,7 @@ struct css_set; #ifdef CONFIG_PSI -extern bool psi_disabled; +extern struct static_key_false psi_disabled; void psi_init(void); -- cgit v1.2.3 From b7df9ada9a7700dbcca1ba53d217c01e3d48179c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 1 Dec 2018 01:18:53 +0100 Subject: bpf: fix pointer offsets in context for 32 bit Currently, pointer offsets in three BPF context structures are broken in two scenarios: i) 32 bit compiled applications running on 64 bit kernels, and ii) LLVM compiled BPF programs running on 32 bit kernels. The latter is due to BPF target machine being strictly 64 bit. So in each of the cases the offsets will mismatch in verifier when checking / rewriting context access. Fix this by providing a helper macro __bpf_md_ptr() that will enforce padding up to 64 bit and proper alignment, and for context access a macro bpf_ctx_range_ptr() which will cover full 64 bit member range on 32 bit archs. For flow_keys, we additionally need to force the size check to sizeof(__u64) as with other pointer types. Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook") Fixes: 4f738adba30a ("bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data") Fixes: 2dbb9b9e6df6 ("bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT") Reported-by: David S. Miller Signed-off-by: Daniel Borkmann Acked-by: David S. Miller Tested-by: David S. Miller Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 448dcc448f1f..795ff0b869bb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -449,6 +449,13 @@ struct sock_reuseport; offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 +#if BITS_PER_LONG == 64 +# define bpf_ctx_range_ptr(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 +#else +# define bpf_ctx_range_ptr(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1 +#endif /* BITS_PER_LONG == 64 */ #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ -- cgit v1.2.3 From 71700bb96047f68a0aae3932466fc7c9ad5ce6c0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 30 Nov 2018 16:11:15 -0500 Subject: SUNRPC: Fix a memory leak in call_encode() If we retransmit an RPC request, we currently end up clobbering the value of req->rq_rcv_buf.bvec that was allocated by the initial call to xprt_request_prepare(req). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 43106ffa6788..2ec128060239 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -72,7 +72,6 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len) buf->head[0].iov_base = start; buf->head[0].iov_len = len; buf->tail[0].iov_len = 0; - buf->bvec = NULL; buf->pages = NULL; buf->page_len = 0; buf->flags = 0; -- cgit v1.2.3 From 37c2578c0c40e286bc0d30bdc05290b2058cf66e Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Mon, 3 Dec 2018 00:54:35 +0000 Subject: Drivers: hv: vmbus: Offload the handling of channels to two workqueues vmbus_process_offer() mustn't call channel->sc_creation_callback() directly for sub-channels, because sc_creation_callback() -> vmbus_open() may never get the host's response to the OPEN_CHANNEL message (the host may rescind a channel at any time, e.g. in the case of hot removing a NIC), and vmbus_onoffer_rescind() may not wake up the vmbus_open() as it's blocked due to a non-zero vmbus_connection.offer_in_progress, and finally we have a deadlock. The above is also true for primary channels, if the related device drivers use sync probing mode by default. And, usually the handling of primary channels and sub-channels can depend on each other, so we should offload them to different workqueues to avoid possible deadlock, e.g. in sync-probing mode, NIC1's netvsc_subchan_work() can race with NIC2's netvsc_probe() -> rtnl_lock(), and causes deadlock: the former gets the rtnl_lock and waits for all the sub-channels to appear, but the latter can't get the rtnl_lock and this blocks the handling of sub-channels. The patch can fix the multiple-NIC deadlock described above for v3.x kernels (e.g. RHEL 7.x) which don't support async-probing of devices, and v4.4, v4.9, v4.14 and v4.18 which support async-probing but don't enable async-probing for Hyper-V drivers (yet). The patch can also fix the hang issue in sub-channel's handling described above for all versions of kernels, including v4.19 and v4.20-rc4. So actually the patch should be applied to all the existing kernels, not only the kernels that have 8195b1396ec8. Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug") Cc: stable@vger.kernel.org Cc: Stephen Hemminger Cc: K. Y. Srinivasan Cc: Haiyang Zhang Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b3e24368930a..14131b6fae68 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -905,6 +905,13 @@ struct vmbus_channel { bool probe_done; + /* + * We must offload the handling of the primary/sub channels + * from the single-threaded vmbus_connection.work_queue to + * two different workqueue, otherwise we can block + * vmbus_connection.work_queue and hang: see vmbus_process_offer(). + */ + struct work_struct add_channel_work; }; static inline bool is_hvsock_channel(const struct vmbus_channel *c) -- cgit v1.2.3 From 4c05ec47384ab3627b62814e8f886e90cc38ce15 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 26 Nov 2018 20:03:30 +0900 Subject: netfilter: nf_tables: fix suspicious RCU usage in nft_chain_stats_replace() basechain->stats is rcu protected data which is updated from nft_chain_stats_replace(). This function is executed from the commit phase which holds the pernet nf_tables commit mutex - not the global nfnetlink subsystem mutex. Test commands to reproduce the problem are: %iptables-nft -I INPUT %iptables-nft -Z %iptables-nft -Z This patch uses RCU calls to handle basechain->stats updates to fix a splat that looks like: [89279.358755] ============================= [89279.363656] WARNING: suspicious RCU usage [89279.368458] 4.20.0-rc2+ #44 Tainted: G W L [89279.374661] ----------------------------- [89279.379542] net/netfilter/nf_tables_api.c:1404 suspicious rcu_dereference_protected() usage! [...] [89279.406556] 1 lock held by iptables-nft/5225: [89279.411728] #0: 00000000bf45a000 (&net->nft.commit_mutex){+.+.}, at: nf_tables_valid_genid+0x1f/0x70 [nf_tables] [89279.424022] stack backtrace: [89279.429236] CPU: 0 PID: 5225 Comm: iptables-nft Tainted: G W L 4.20.0-rc2+ #44 [89279.430135] Call Trace: [89279.430135] dump_stack+0xc9/0x16b [89279.430135] ? show_regs_print_info+0x5/0x5 [89279.430135] ? lockdep_rcu_suspicious+0x117/0x160 [89279.430135] nft_chain_commit_update+0x4ea/0x640 [nf_tables] [89279.430135] ? sched_clock_local+0xd4/0x140 [89279.430135] ? check_flags.part.35+0x440/0x440 [89279.430135] ? __rhashtable_remove_fast.constprop.67+0xec0/0xec0 [nf_tables] [89279.430135] ? sched_clock_cpu+0x126/0x170 [89279.430135] ? find_held_lock+0x39/0x1c0 [89279.430135] ? hlock_class+0x140/0x140 [89279.430135] ? is_bpf_text_address+0x5/0xf0 [89279.430135] ? check_flags.part.35+0x440/0x440 [89279.430135] ? __lock_is_held+0xb4/0x140 [89279.430135] nf_tables_commit+0x2555/0x39c0 [nf_tables] Fixes: f102d66b335a4 ("netfilter: nf_tables: use dedicated mutex to guard transactions") Signed-off-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 4a520d3304a2..cf09ab37b45b 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -62,18 +62,6 @@ static inline bool lockdep_nfnl_is_held(__u8 subsys_id) } #endif /* CONFIG_PROVE_LOCKING */ -/* - * nfnl_dereference - fetch RCU pointer when updates are prevented by subsys mutex - * - * @p: The pointer to read, prior to dereferencing - * @ss: The nfnetlink subsystem ID - * - * Return the value of the specified RCU-protected pointer, but omit - * the READ_ONCE(), because caller holds the NFNL subsystem mutex. - */ -#define nfnl_dereference(p, ss) \ - rcu_dereference_protected(p, lockdep_nfnl_is_held(ss)) - #define MODULE_ALIAS_NFNL_SUBSYS(subsys) \ MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys)) -- cgit v1.2.3 From 27359fd6e5f3c5db8fe544b63238b6170e8806d8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 30 Nov 2018 11:05:06 -0500 Subject: dax: Fix unlock mismatch with updated API Internal to dax_unlock_mapping_entry(), dax_unlock_entry() is used to store a replacement entry in the Xarray at the given xas-index with the DAX_LOCKED bit clear. When called, dax_unlock_entry() expects the unlocked value of the entry relative to the current Xarray state to be specified. In most contexts dax_unlock_entry() is operating in the same scope as the matched dax_lock_entry(). However, in the dax_unlock_mapping_entry() case the implementation needs to recall the original entry. In the case where the original entry is a 'pmd' entry it is possible that the pfn performed to do the lookup is misaligned to the value retrieved in the Xarray. Change the api to return the unlock cookie from dax_lock_page() and pass it to dax_unlock_page(). This fixes a bug where dax_unlock_page() was assuming that the page was PMD-aligned if the entry was a PMD entry with signatures like: WARNING: CPU: 38 PID: 1396 at fs/dax.c:340 dax_insert_entry+0x2b2/0x2d0 RIP: 0010:dax_insert_entry+0x2b2/0x2d0 [..] Call Trace: dax_iomap_pte_fault.isra.41+0x791/0xde0 ext4_dax_huge_fault+0x16f/0x1f0 ? up_read+0x1c/0xa0 __do_fault+0x1f/0x160 __handle_mm_fault+0x1033/0x1490 handle_mm_fault+0x18b/0x3d0 Link: https://lkml.kernel.org/r/20181130154902.GL10377@bombadil.infradead.org Fixes: 9f32d221301c ("dax: Convert dax_lock_mapping_entry to XArray") Reported-by: Dan Williams Signed-off-by: Matthew Wilcox Tested-by: Dan Williams Reviewed-by: Jan Kara Signed-off-by: Dan Williams --- include/linux/dax.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 450b28db9533..0dd316a74a29 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -7,6 +7,8 @@ #include #include +typedef unsigned long dax_entry_t; + struct iomap_ops; struct dax_device; struct dax_operations { @@ -88,8 +90,8 @@ int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); -bool dax_lock_mapping_entry(struct page *page); -void dax_unlock_mapping_entry(struct page *page); +dax_entry_t dax_lock_page(struct page *page); +void dax_unlock_page(struct page *page, dax_entry_t cookie); #else static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) @@ -122,14 +124,14 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping, return -EOPNOTSUPP; } -static inline bool dax_lock_mapping_entry(struct page *page) +static inline dax_entry_t dax_lock_page(struct page *page) { if (IS_DAX(page->mapping->host)) - return true; - return false; + return ~0UL; + return 0; } -static inline void dax_unlock_mapping_entry(struct page *page) +static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) { } #endif -- cgit v1.2.3 From f51ccf46217c28758b1f3b5bc0ccfc00eca658b2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Dec 2018 17:00:36 +0100 Subject: USB: serial: console: fix reported terminal settings The USB-serial console implementation has never reported the actual terminal settings used. Despite storing the corresponding cflags in its struct console, these were never honoured on later tty open() where the tty termios would be left initialised to the driver defaults. Unlike the serial console implementation, the USB-serial code calls subdriver open() already at console setup. While calling set_termios() and write() before open() looks like it could work for some USB-serial drivers, others definitely do not expect this, so modelling this after serial core is going to be intrusive, if at all possible. Instead, use a (renamed) tty helper to save the termios data used at console setup so that the tty termios reflects the actual terminal settings after a subsequent tty open(). Note that the calls to tty_init_termios() (tty_driver_install()) and tty_save_termios() are serialised using the disconnect mutex. This specifically fixes a regression that was triggered by a recent change adding software flow control to the pl2303 driver: a getty trying to disable flow control while leaving the baud rate unchanged would now also set the baud rate to the driver default (prior to the flow-control change this had been a noop). Fixes: 7041d9c3f01b ("USB: serial: pl2303: add support for tx xon/xoff flow control") Cc: stable # 4.18 Cc: Florian Zumbiehl Reported-by: Jarkko Nikula Tested-by: Jarkko Nikula Acked-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 414db2bce715..392138fe59b6 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -556,6 +556,7 @@ extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); extern void tty_release_struct(struct tty_struct *tty, int idx); extern int tty_release(struct inode *inode, struct file *filp); extern void tty_init_termios(struct tty_struct *tty); +extern void tty_save_termios(struct tty_struct *tty); extern int tty_standard_install(struct tty_driver *driver, struct tty_struct *tty); -- cgit v1.2.3 From 704620afc70cf47abb9d6a1a57f3825d2bca49cf Mon Sep 17 00:00:00 2001 From: Mathias Payer Date: Wed, 5 Dec 2018 21:19:59 +0100 Subject: USB: check usb_get_extra_descriptor for proper size When reading an extra descriptor, we need to properly check the minimum and maximum size allowed, to prevent from invalid data being sent by a device. Reported-by: Hui Peng Reported-by: Mathias Payer Co-developed-by: Linus Torvalds Signed-off-by: Hui Peng Signed-off-by: Mathias Payer Signed-off-by: Linus Torvalds Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 4cdd515a4385..5e49e82c4368 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -407,11 +407,11 @@ struct usb_host_bos { }; int __usb_get_extra_descriptor(char *buffer, unsigned size, - unsigned char type, void **ptr); + unsigned char type, void **ptr, size_t min); #define usb_get_extra_descriptor(ifpoint, type, ptr) \ __usb_get_extra_descriptor((ifpoint)->extra, \ (ifpoint)->extralen, \ - type, (void **)ptr) + type, (void **)ptr, sizeof(**(ptr))) /* ----------------------------------------------------------------------- */ -- cgit v1.2.3 From 2f0799a0ffc033bf3cc82d5032acc3ec633464c2 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 5 Dec 2018 15:45:54 -0800 Subject: mm, thp: restore node-local hugepage allocations This is a full revert of ac5b2c18911f ("mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings") and a partial revert of 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask"). By not setting __GFP_THISNODE, applications can allocate remote hugepages when the local node is fragmented or low on memory when either the thp defrag setting is "always" or the vma has been madvised with MADV_HUGEPAGE. Remote access to hugepages often has much higher latency than local pages of the native page size. On Haswell, ac5b2c18911f was shown to have a 13.9% access regression after this commit for binaries that remap their text segment to be backed by transparent hugepages. The intent of ac5b2c18911f is to address an issue where a local node is low on memory or fragmented such that a hugepage cannot be allocated. In every scenario where this was described as a fix, there is abundant and unfragmented remote memory available to allocate from, even with a greater access latency. If remote memory is also low or fragmented, not setting __GFP_THISNODE was also measured on Haswell to have a 40% regression in allocation latency. Restore __GFP_THISNODE for thp allocations. Fixes: ac5b2c18911f ("mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings") Fixes: 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask") Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Vlastimil Babka Cc: Michal Hocko Cc: Andrew Morton Signed-off-by: David Rientjes Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index bac395f1d00a..5228c62af416 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,8 +139,6 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); -struct mempolicy *get_vma_policy(struct vm_area_struct *vma, - unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); -- cgit v1.2.3 From 55f3f7eab75c10d9b33d122670b5935ab64db50f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 26 Nov 2018 16:08:43 -0500 Subject: XArray: Add xa_cmpxchg_irq and xa_cmpxchg_bh These convenience wrappers match the other _irq and _bh wrappers we already have. It turns out I'd already open-coded xa_cmpxchg_irq() in the shmem code, so convert that. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 564892e19f8c..f492e21c4aa2 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -553,6 +553,60 @@ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, return curr; } +/** + * xa_cmpxchg_bh() - Conditionally replace an entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New value to place in array. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_cmpxchg() except it disables softirqs + * while holding the array lock. + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. May sleep if the @gfp flags permit. + * Return: The old value at this index or xa_err() if an error happened. + */ +static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_bh(xa); + curr = __xa_cmpxchg(xa, index, old, entry, gfp); + xa_unlock_bh(xa); + + return curr; +} + +/** + * xa_cmpxchg_irq() - Conditionally replace an entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New value to place in array. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_cmpxchg() except it disables interrupts + * while holding the array lock. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. May sleep if the @gfp flags permit. + * Return: The old value at this index or xa_err() if an error happened. + */ +static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_irq(xa); + curr = __xa_cmpxchg(xa, index, old, entry, gfp); + xa_unlock_irq(xa); + + return curr; +} + /** * xa_insert() - Store this entry in the XArray unless another entry is * already present. -- cgit v1.2.3 From 60a89a3ce0cce515dc663bc1b45ac89202ad6c79 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 4 Dec 2018 20:58:33 -0500 Subject: scsi: t10-pi: Return correct ref tag when queue has no integrity profile Commit ddd0bc756983 ("block: move ref_tag calculation func to the block layer") moved ref tag calculation from SCSI to a library function. However, this change broke returning the correct ref tag for devices operating in DIF mode since these do not have an associated block integrity profile. This in turn caused read/write failures on PI-formatted disks attached to an mpt3sas controller. Fixes: ddd0bc756983 ("block: move ref_tag calculation func to the block layer") Cc: stable@vger.kernel.org # 4.19+ Reported-by: John Garry Tested-by: Xiang Chen Signed-off-by: Martin K. Petersen --- include/linux/t10-pi.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index b9626aa7e90c..3e2a80cc7b56 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -39,12 +39,13 @@ struct t10_pi_tuple { static inline u32 t10_pi_ref_tag(struct request *rq) { + unsigned int shift = ilog2(queue_logical_block_size(rq->q)); + #ifdef CONFIG_BLK_DEV_INTEGRITY - return blk_rq_pos(rq) >> - (rq->q->integrity.interval_exp - 9) & 0xffffffff; -#else - return -1U; + if (rq->q->integrity.interval_exp) + shift = rq->q->integrity.interval_exp; #endif + return blk_rq_pos(rq) >> (shift - SECTOR_SHIFT) & 0xffffffff; } extern const struct blk_integrity_profile t10_pi_type1_crc; -- cgit v1.2.3 From 356ff8a9a78fb35d6482584d260c3754dcbdf669 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Fri, 7 Dec 2018 14:50:16 -0800 Subject: Revert "mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask" This reverts commit 89c83fb539f95491be80cdd5158e6f0ce329e317. This should have been done as part of 2f0799a0ffc0 ("mm, thp: restore node-local hugepage allocations"). The movement of the thp allocation policy from alloc_pages_vma() to alloc_hugepage_direct_gfpmask() was intended to only set __GFP_THISNODE for mempolicies that are not MPOL_BIND whereas the revert could set this regardless of mempolicy. While the check for MPOL_BIND between alloc_hugepage_direct_gfpmask() and alloc_pages_vma() was racy, that has since been removed since the revert. What is left is the possibility to use __GFP_THISNODE in policy_node() when it is unexpected because the special handling for hugepages in alloc_pages_vma() was removed as part of the consolidation. Secondly, prior to 89c83fb539f9, alloc_pages_vma() implemented a somewhat different policy for hugepage allocations, which were allocated through alloc_hugepage_vma(). For hugepage allocations, if the allocating process's node is in the set of allowed nodes, allocate with __GFP_THISNODE for that node (for MPOL_PREFERRED, use that node with __GFP_THISNODE instead). This was changed for shmem_alloc_hugepage() to allow fallback to other nodes in 89c83fb539f9 as it did for new_page() in mm/mempolicy.c which is functionally different behavior and removes the requirement to only allocate hugepages locally. So this commit does a full revert of 89c83fb539f9 instead of the partial revert that was done in 2f0799a0ffc0. The result is the same thp allocation policy for 4.20 that was in 4.19. Fixes: 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask") Fixes: 2f0799a0ffc0 ("mm, thp: restore node-local hugepage allocations") Signed-off-by: David Rientjes Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Michal Hocko Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 76f8db0b0e71..0705164f928c 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,18 +510,22 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node); + int node, bool hugepage); +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ + alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ + alloc_pages(gfp_mask, order) +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node) + alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); -- cgit v1.2.3 From fdadd04931c2d7cd294dc5b2b342863f94be53a3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 11 Dec 2018 12:14:12 +0100 Subject: bpf: fix bpf_jit_limit knob for PAGE_SIZE >= 64K Michael and Sandipan report: Commit ede95a63b5 introduced a bpf_jit_limit tuneable to limit BPF JIT allocations. At compile time it defaults to PAGE_SIZE * 40000, and is adjusted again at init time if MODULES_VADDR is defined. For ppc64 kernels, MODULES_VADDR isn't defined, so we're stuck with the compile-time default at boot-time, which is 0x9c400000 when using 64K page size. This overflows the signed 32-bit bpf_jit_limit value: root@ubuntu:/tmp# cat /proc/sys/net/core/bpf_jit_limit -1673527296 and can cause various unexpected failures throughout the network stack. In one case `strace dhclient eth0` reported: setsockopt(5, SOL_SOCKET, SO_ATTACH_FILTER, {len=11, filter=0x105dd27f8}, 16) = -1 ENOTSUPP (Unknown error 524) and similar failures can be seen with tools like tcpdump. This doesn't always reproduce however, and I'm not sure why. The more consistent failure I've seen is an Ubuntu 18.04 KVM guest booted on a POWER9 host would time out on systemd/netplan configuring a virtio-net NIC with no noticeable errors in the logs. Given this and also given that in near future some architectures like arm64 will have a custom area for BPF JIT image allocations we should get rid of the BPF_JIT_LIMIT_DEFAULT fallback / default entirely. For 4.21, we have an overridable bpf_jit_alloc_exec(), bpf_jit_free_exec() so therefore add another overridable bpf_jit_alloc_exec_limit() helper function which returns the possible size of the memory area for deriving the default heuristic in bpf_jit_charge_init(). Like bpf_jit_alloc_exec() and bpf_jit_free_exec(), the new bpf_jit_alloc_exec_limit() assumes that module_alloc() is the default JIT memory provider, and therefore in case archs implement their custom module_alloc() we use MODULES_{END,_VADDR} for limits and otherwise for vmalloc_exec() cases like on ppc64 we use VMALLOC_{END,_START}. Additionally, for archs supporting large page sizes, we should change the sysctl to be handled as long to not run into sysctl restrictions in future. Fixes: ede95a63b5e8 ("bpf: add bpf_jit_limit knob to restrict unpriv allocations") Reported-by: Sandipan Das Reported-by: Michael Roth Signed-off-by: Daniel Borkmann Tested-by: Michael Roth Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 795ff0b869bb..a8b9d90a8042 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -861,7 +861,7 @@ bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; -extern int bpf_jit_limit; +extern long bpf_jit_limit; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); -- cgit v1.2.3 From 663f146f2ecfcc47934cb9f9543f664eeb6adb46 Mon Sep 17 00:00:00 2001 From: Vu Pham Date: Wed, 31 Oct 2018 16:03:21 +0200 Subject: net/mlx5: E-Switch, Fix fdb cap bits swap The cap bits locations for the fdb caps of multi path to table (used for local mirroring) and multi encap (used for prio/chains) were wrongly used in swapped locations. This went unnoted so far b/c we tested the offending patch with CX5 FW that supports both of them. On different environments where not both caps are supported, we will be messed up, fix that. Fixes: b9aa0ba17af5 ('net/mlx5: Add cap bits for multi fdb encap') Signed-off-by: Vu Pham Reviewed-by: Or Gerlitz Tested-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 34e17e6f8942..4e77bfe0b580 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -582,11 +582,13 @@ struct mlx5_ifc_flow_table_nic_cap_bits { }; struct mlx5_ifc_flow_table_eswitch_cap_bits { - u8 reserved_at_0[0x1c]; - u8 fdb_multi_path_to_table[0x1]; - u8 reserved_at_1d[0x1]; + u8 reserved_at_0[0x1a]; u8 multi_fdb_encap[0x1]; - u8 reserved_at_1e[0x1e1]; + u8 reserved_at_1b[0x1]; + u8 fdb_multi_path_to_table[0x1]; + u8 reserved_at_1d[0x3]; + + u8 reserved_at_20[0x1e0]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb; -- cgit v1.2.3 From 71391bdd2e9aab188f86bf1ecd9b232531ec7eea Mon Sep 17 00:00:00 2001 From: Xiaozhou Liu Date: Fri, 14 Dec 2018 22:14:31 +0800 Subject: include/linux/compiler_types.h: don't pollute userspace with macro definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Macros 'inline' and '__gnu_inline' used to be defined in compiler-gcc.h, which was (and is) included entirely in (__KERNEL__ && !__ASSEMBLY__). Commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") had those macros exposed to userspace, unintentionally. Then commit a3f8a30f3f00 ("Compiler Attributes: use feature checks instead of version checks") moved '__gnu_inline' back into (__KERNEL__ && !__ASSEMBLY__) and 'inline' was left behind. Since 'inline' depends on '__gnu_inline', compiling error showing "unknown type name ‘__gnu_inline’" will pop up, if userspace somehow includes . Other macros like __must_check, notrace, etc. are in a similar situation. So just move all these macros back into (__KERNEL__ && !__ASSEMBLY__). Note: 1. This patch only affects what userspace sees. 2. __must_check (when !CONFIG_ENABLE_MUST_CHECK) and noinline_for_stack were once defined in __KERNEL__ only, but we believe that they can be put into !__ASSEMBLY__ too. Acked-by: Nick Desaulniers Signed-off-by: Xiaozhou Liu Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 108 ++++++++++++++++++++--------------------- 1 file changed, 54 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 4a3f9c09c92d..ba814f18cb4c 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -104,6 +104,60 @@ struct ftrace_likely_data { unsigned long constant; }; +#ifdef CONFIG_ENABLE_MUST_CHECK +#define __must_check __attribute__((__warn_unused_result__)) +#else +#define __must_check +#endif + +#if defined(CC_USING_HOTPATCH) +#define notrace __attribute__((hotpatch(0, 0))) +#else +#define notrace __attribute__((__no_instrument_function__)) +#endif + +/* + * it doesn't make sense on ARM (currently the only user of __naked) + * to trace naked functions because then mcount is called without + * stack and frame pointer being set up and there is no chance to + * restore the lr register to the value before mcount was called. + */ +#define __naked __attribute__((__naked__)) notrace + +#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) + +/* + * Force always-inline if the user requests it so via the .config. + * GCC does not warn about unused static inline functions for + * -Wunused-function. This turns out to avoid the need for complex #ifdef + * directives. Suppress the warning in clang as well by using "unused" + * function attribute, which is redundant but not harmful for gcc. + * Prefer gnu_inline, so that extern inline functions do not emit an + * externally visible function. This makes extern inline behave as per gnu89 + * semantics rather than c99. This prevents multiple symbol definition errors + * of extern inline functions at link time. + * A lot of inline functions can cause havoc with function tracing. + * Do not use __always_inline here, since currently it expands to inline again + * (which would break users of __always_inline). + */ +#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ + !defined(CONFIG_OPTIMIZE_INLINING) +#define inline inline __attribute__((__always_inline__)) __gnu_inline \ + __maybe_unused notrace +#else +#define inline inline __gnu_inline \ + __maybe_unused notrace +#endif + +#define __inline__ inline +#define __inline inline + +/* + * Rather then using noinline to prevent stack consumption, use + * noinline_for_stack instead. For documentation reasons. + */ +#define noinline_for_stack noinline + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ @@ -161,58 +215,4 @@ struct ftrace_likely_data { #define __diag_error(compiler, version, option, comment) \ __diag_ ## compiler(version, error, option) -#ifdef CONFIG_ENABLE_MUST_CHECK -#define __must_check __attribute__((__warn_unused_result__)) -#else -#define __must_check -#endif - -#if defined(CC_USING_HOTPATCH) -#define notrace __attribute__((hotpatch(0, 0))) -#else -#define notrace __attribute__((__no_instrument_function__)) -#endif - -/* - * it doesn't make sense on ARM (currently the only user of __naked) - * to trace naked functions because then mcount is called without - * stack and frame pointer being set up and there is no chance to - * restore the lr register to the value before mcount was called. - */ -#define __naked __attribute__((__naked__)) notrace - -#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) - -/* - * Force always-inline if the user requests it so via the .config. - * GCC does not warn about unused static inline functions for - * -Wunused-function. This turns out to avoid the need for complex #ifdef - * directives. Suppress the warning in clang as well by using "unused" - * function attribute, which is redundant but not harmful for gcc. - * Prefer gnu_inline, so that extern inline functions do not emit an - * externally visible function. This makes extern inline behave as per gnu89 - * semantics rather than c99. This prevents multiple symbol definition errors - * of extern inline functions at link time. - * A lot of inline functions can cause havoc with function tracing. - * Do not use __always_inline here, since currently it expands to inline again - * (which would break users of __always_inline). - */ -#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ - !defined(CONFIG_OPTIMIZE_INLINING) -#define inline inline __attribute__((__always_inline__)) __gnu_inline \ - __maybe_unused notrace -#else -#define inline inline __gnu_inline \ - __maybe_unused notrace -#endif - -#define __inline__ inline -#define __inline inline - -/* - * Rather then using noinline to prevent stack consumption, use - * noinline_for_stack instead. For documentation reasons. - */ -#define noinline_for_stack noinline - #endif /* __LINUX_COMPILER_TYPES_H */ -- cgit v1.2.3 From d1402fc708e4c355813e49df6d15bc3466ba5114 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Fri, 14 Dec 2018 14:16:53 -0800 Subject: mm: introduce common STRUCT_PAGE_MAX_SHIFT define This define is used by arm64 to calculate the size of the vmemmap region. It is defined as the log2 of the upper bound on the size of a struct page. We move it into mm_types.h so it can be defined properly instead of set and checked with a build bug. This also allows us to use the same define for riscv. Link: http://lkml.kernel.org/r/20181107205433.3875-2-logang@deltatee.com Signed-off-by: Logan Gunthorpe Acked-by: Will Deacon Acked-by: Andrew Morton Acked-by: Ard Biesheuvel Acked-by: Catalin Marinas Cc: Arnd Bergmann Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5ed8f6292a53..2c471a2c43fa 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -206,6 +206,11 @@ struct page { #endif } _struct_page_alignment; +/* + * Used for sizing the vmemmap region on some architectures + */ +#define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) + #define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) -- cgit v1.2.3 From 9def36e0fa9a0d9c5393c039db59f1f2d3a388b3 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Fri, 14 Dec 2018 14:16:57 -0800 Subject: mm/sparse: add common helper to mark all memblocks present Presently the arches arm64, arm and sh have a function which loops through each memblock and calls memory present. riscv will require a similar function. Introduce a common memblocks_present() function that can be used by all the arches. Subsequent patches will cleanup the arches that make use of this. Link: http://lkml.kernel.org/r/20181107205433.3875-3-logang@deltatee.com Signed-off-by: Logan Gunthorpe Acked-by: Andrew Morton Cc: Michal Hocko Cc: Vlastimil Babka Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 847705a6d0ec..db023a92f3a4 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -783,6 +783,12 @@ void memory_present(int nid, unsigned long start, unsigned long end); static inline void memory_present(int nid, unsigned long start, unsigned long end) {} #endif +#if defined(CONFIG_SPARSEMEM) +void memblocks_present(void); +#else +static inline void memblocks_present(void) {} +#endif + #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else -- cgit v1.2.3 From 15c6d8e565943a904172de69cc13c53f724fa16c Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Thu, 13 Dec 2018 15:00:11 -0500 Subject: mod_devicetable.h: correct kerneldoc typo, "PHYSID2" -> "MII_PHYSID2" Signed-off-by: Robert P. J. Day Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mod_devicetable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 01797cb4587e..a0dcc9b6a723 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -565,7 +565,7 @@ struct platform_device_id { /** * struct mdio_device_id - identifies PHY devices on an MDIO/MII bus * @phy_id: The result of - * (mdio_read(&MII_PHYSID1) << 16 | mdio_read(&PHYSID2)) & @phy_id_mask + * (mdio_read(&MII_PHYSID1) << 16 | mdio_read(&MII_PHYSID2)) & @phy_id_mask * for this PHY type * @phy_id_mask: Defines the significant bits of @phy_id. A value of 0 * is used to terminate an array of struct mdio_device_id. -- cgit v1.2.3 From 96af6cd02a10b96108fc415a213441e7fb9f4f9b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 19 Dec 2018 11:23:27 +0100 Subject: Revert "x86/objtool: Use asm macros to work around GCC inlining bugs" This reverts commit c06c4d8090513f2974dfdbed2ac98634357ac475. See this commit for details about the revert: e769742d3584 ("Revert "x86/jump-labels: Macrofy inline assembly code to work around GCC inlining bugs"") Reported-by: Masahiro Yamada Reviewed-by: Borislav Petkov Reviewed-by: Thomas Gleixner Cc: Juergen Gross Cc: Richard Biener Cc: Kees Cook Cc: Segher Boessenkool Cc: Ard Biesheuvel Cc: Peter Zijlstra Cc: Josh Poimboeuf Cc: Nadav Amit Cc: Linus Torvalds Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 56 +++++++++++------------------------------------- 1 file changed, 13 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 06396c1cf127..fc5004a4b07d 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -99,13 +99,22 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, * unique, to convince GCC not to merge duplicate inline asm statements. */ #define annotate_reachable() ({ \ - asm volatile("ANNOTATE_REACHABLE counter=%c0" \ - : : "i" (__COUNTER__)); \ + asm volatile("%c0:\n\t" \ + ".pushsection .discard.reachable\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ }) #define annotate_unreachable() ({ \ - asm volatile("ANNOTATE_UNREACHABLE counter=%c0" \ - : : "i" (__COUNTER__)); \ + asm volatile("%c0:\n\t" \ + ".pushsection .discard.unreachable\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ }) +#define ASM_UNREACHABLE \ + "999:\n\t" \ + ".pushsection .discard.unreachable\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" #else #define annotate_reachable() #define annotate_unreachable() @@ -293,45 +302,6 @@ static inline void *offset_to_ptr(const int *off) return (void *)((unsigned long)off + *off); } -#else /* __ASSEMBLY__ */ - -#ifdef __KERNEL__ -#ifndef LINKER_SCRIPT - -#ifdef CONFIG_STACK_VALIDATION -.macro ANNOTATE_UNREACHABLE counter:req -\counter: - .pushsection .discard.unreachable - .long \counter\()b -. - .popsection -.endm - -.macro ANNOTATE_REACHABLE counter:req -\counter: - .pushsection .discard.reachable - .long \counter\()b -. - .popsection -.endm - -.macro ASM_UNREACHABLE -999: - .pushsection .discard.unreachable - .long 999b - . - .popsection -.endm -#else /* CONFIG_STACK_VALIDATION */ -.macro ANNOTATE_UNREACHABLE counter:req -.endm - -.macro ANNOTATE_REACHABLE counter:req -.endm - -.macro ASM_UNREACHABLE -.endm -#endif /* CONFIG_STACK_VALIDATION */ - -#endif /* LINKER_SCRIPT */ -#endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ /* Compile time object size, -1 for unknown */ -- cgit v1.2.3 From 0cd60eb1a7b5421e92a3489e1829bfb2243e21e1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 22 Dec 2018 09:21:08 +0100 Subject: dma-mapping: fix flags in dma_alloc_wc We really need the writecombine flag in dma_alloc_wc, fix a stupid oversight. Fixes: 7ed1d91a9e ("dma-mapping: translate __GFP_NOFAIL to DMA_ATTR_NO_WARN") Signed-off-by: Christoph Hellwig Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 15bd41447025..d327bdd53716 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -796,7 +796,7 @@ static inline void dmam_release_declared_memory(struct device *dev) static inline void *dma_alloc_wc(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t gfp) { - unsigned long attrs = DMA_ATTR_NO_WARN; + unsigned long attrs = DMA_ATTR_WRITE_COMBINE; if (gfp & __GFP_NOWARN) attrs |= DMA_ATTR_NO_WARN; -- cgit v1.2.3