From a29ccf6f823a84d89e1c7aaaf221cf7282022024 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Tue, 3 Jun 2008 14:59:40 +0100 Subject: Make console charset translation optional By turning off the new CONSOLE_TRANSLATIONS option and dropping the associated code and tables from the kernel, we can save about 7KiB. Taken from linux-tiny project by Tim Bird and mangled further by dwmw2. Signed-off-by: Tim Bird Signed-off-by: David Woodhouse --- include/linux/consolemap.h | 14 ++++++++++++++ include/linux/vt_kern.h | 19 +++++++++++++++++++ 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/consolemap.h b/include/linux/consolemap.h index e2bf7e5db39a..c4811da1338b 100644 --- a/include/linux/consolemap.h +++ b/include/linux/consolemap.h @@ -3,6 +3,9 @@ * * Interface between console.c, selection.c and consolemap.c */ +#ifndef __LINUX_CONSOLEMAP_H__ +#define __LINUX_CONSOLEMAP_H__ + #define LAT1_MAP 0 #define GRAF_MAP 1 #define IBMPC_MAP 2 @@ -10,6 +13,7 @@ #include +#ifdef CONFIG_CONSOLE_TRANSLATIONS struct vc_data; extern u16 inverse_translate(struct vc_data *conp, int glyph, int use_unicode); @@ -18,3 +22,13 @@ extern int conv_uni_to_pc(struct vc_data *conp, long ucs); extern u32 conv_8bit_to_uni(unsigned char c); extern int conv_uni_to_8bit(u32 uni); void console_map_init(void); +#else +#define inverse_translate(conp, glyph, uni) ((uint16_t)glyph) +#define set_translate(m, vc) ((unsigned short *)NULL) +#define conv_uni_to_pc(conp, ucs) ((int) (ucs > 0xff ? -1: ucs)) +#define conv_8bit_to_uni(c) ((uint32_t)(c)) +#define conv_uni_to_8bit(c) ((int) ((c) & 0xff)) +#define console_map_init(c) do { ; } while (0) +#endif /* CONFIG_CONSOLE_TRANSLATIONS */ + +#endif /* __LINUX_CONSOLEMAP_H__ */ diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 9448ffbdcbf6..14c0e91be9b5 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -12,6 +12,7 @@ #include #include #include +#include /* * Presently, a lot of graphics programs do not restore the contents of @@ -54,6 +55,7 @@ void redraw_screen(struct vc_data *vc, int is_switch); struct tty_struct; int tioclinux(struct tty_struct *tty, unsigned long arg); +#ifdef CONFIG_CONSOLE_TRANSLATIONS /* consolemap.c */ struct unimapinit; @@ -71,6 +73,23 @@ void con_free_unimap(struct vc_data *vc); void con_protect_unimap(struct vc_data *vc, int rdonly); int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc); +#define vc_translate(vc, c) ((vc)->vc_translate[(c) | \ + (vc)->vc_toggle_meta ? 0x80 : 0]) +#else +#define con_set_trans_old(arg) (0) +#define con_get_trans_old(arg) (-EINVAL) +#define con_set_trans_new(arg) (0) +#define con_get_trans_new(arg) (-EINVAL) +#define con_clear_unimap(vc, ui) (0) +#define con_set_unimap(vc, ct, list) (0) +#define con_set_default_unimap(vc) (0) +#define con_copy_unimap(d, s) (0) +#define con_get_unimap(vc, ct, uct, list) (-EINVAL) +#define con_free_unimap(vc) do { ; } while (0) + +#define vc_translate(vc, c) (c) +#endif + /* vt.c */ int vt_waitactive(int vt); void change_console(struct vc_data *new_vc); -- cgit v1.2.3 From 59018b6d2acabb114ab58637e6ab95ba424a89d0 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 20 May 2008 01:03:52 +0300 Subject: MTD/JFFS2: remove CVS keywords Once upon a time, the MTD repository was using CVS. This patch therefore removes all usages of the no longer updated CVS keywords from the MTD code. This also includes code that printed them to the user. Signed-off-by: Adrian Bunk Signed-off-by: David Woodhouse --- include/linux/jffs2.h | 3 --- include/linux/mtd/blktrans.h | 2 -- include/linux/mtd/cfi.h | 1 - include/linux/mtd/cfi_endian.h | 5 ----- include/linux/mtd/concat.h | 2 -- include/linux/mtd/doc2000.h | 2 -- include/linux/mtd/flashchip.h | 3 --- include/linux/mtd/ftl.h | 2 -- include/linux/mtd/gen_probe.h | 1 - include/linux/mtd/inftl.h | 4 ---- include/linux/mtd/map.h | 1 - include/linux/mtd/mtd.h | 2 -- include/linux/mtd/nand.h | 2 -- include/linux/mtd/nand_ecc.h | 2 -- include/linux/mtd/nftl.h | 2 -- include/linux/mtd/partitions.h | 2 -- include/linux/mtd/physmap.h | 2 -- include/linux/mtd/plat-ram.h | 2 -- include/linux/mtd/pmc551.h | 4 +--- include/linux/mtd/xip.h | 2 -- 20 files changed, 1 insertion(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jffs2.h b/include/linux/jffs2.h index 6b563cae23df..da720bc3eb15 100644 --- a/include/linux/jffs2.h +++ b/include/linux/jffs2.h @@ -7,9 +7,6 @@ * * For licensing information, see the file 'LICENCE' in the * jffs2 directory. - * - * $Id: jffs2.h,v 1.38 2005/09/26 11:37:23 havasi Exp $ - * */ #ifndef __LINUX_JFFS2_H__ diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index 9a6e2f953cba..310e61606415 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -1,6 +1,4 @@ /* - * $Id: blktrans.h,v 1.6 2005/11/07 11:14:54 gleixner Exp $ - * * (C) 2003 David Woodhouse * * Interface to Linux block layer for MTD 'translation layers'. diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index b0ddf4b25862..d6fb115f5a07 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -1,7 +1,6 @@ /* Common Flash Interface structures * See http://support.intel.com/design/flash/technote/index.htm - * $Id: cfi.h,v 1.57 2005/11/15 23:28:17 tpoynor Exp $ */ #ifndef __MTD_CFI_H__ diff --git a/include/linux/mtd/cfi_endian.h b/include/linux/mtd/cfi_endian.h index 25724f7d3867..d802f7736be3 100644 --- a/include/linux/mtd/cfi_endian.h +++ b/include/linux/mtd/cfi_endian.h @@ -1,8 +1,3 @@ -/* - * $Id: cfi_endian.h,v 1.11 2002/01/30 23:20:48 awozniak Exp $ - * - */ - #include #ifndef CONFIG_MTD_CFI_ADV_OPTIONS diff --git a/include/linux/mtd/concat.h b/include/linux/mtd/concat.h index ed8dc6755219..c02f3d264ecf 100644 --- a/include/linux/mtd/concat.h +++ b/include/linux/mtd/concat.h @@ -4,8 +4,6 @@ * (C) 2002 Robert Kaiser * * This code is GPL - * - * $Id: concat.h,v 1.1 2002/03/08 16:34:36 rkaiser Exp $ */ #ifndef MTD_CONCAT_H diff --git a/include/linux/mtd/doc2000.h b/include/linux/mtd/doc2000.h index 9addd073bf15..0a6d516ab71d 100644 --- a/include/linux/mtd/doc2000.h +++ b/include/linux/mtd/doc2000.h @@ -6,8 +6,6 @@ * Copyright (C) 2002-2003 Greg Ungerer * Copyright (C) 2002-2003 SnapGear Inc * - * $Id: doc2000.h,v 1.25 2005/11/07 11:14:54 gleixner Exp $ - * * Released under GPL */ diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index 39e7d2a1be9a..08dd131301c1 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -5,9 +5,6 @@ * Contains information about the location and state of a given flash device * * (C) 2000 Red Hat. GPLd. - * - * $Id: flashchip.h,v 1.18 2005/11/07 11:14:54 gleixner Exp $ - * */ #ifndef __MTD_FLASHCHIP_H__ diff --git a/include/linux/mtd/ftl.h b/include/linux/mtd/ftl.h index d99609113307..0be442f881dd 100644 --- a/include/linux/mtd/ftl.h +++ b/include/linux/mtd/ftl.h @@ -1,6 +1,4 @@ /* - * $Id: ftl.h,v 1.7 2005/11/07 11:14:54 gleixner Exp $ - * * Derived from (and probably identical to): * ftl.h 1.7 1999/10/25 20:23:17 * diff --git a/include/linux/mtd/gen_probe.h b/include/linux/mtd/gen_probe.h index 256e7342ed1e..df362ddf2949 100644 --- a/include/linux/mtd/gen_probe.h +++ b/include/linux/mtd/gen_probe.h @@ -1,7 +1,6 @@ /* * (C) 2001, 2001 Red Hat, Inc. * GPL'd - * $Id: gen_probe.h,v 1.4 2005/11/07 11:14:54 gleixner Exp $ */ #ifndef __LINUX_MTD_GEN_PROBE_H__ diff --git a/include/linux/mtd/inftl.h b/include/linux/mtd/inftl.h index 85fd041d44ad..64ee53ce95a9 100644 --- a/include/linux/mtd/inftl.h +++ b/include/linux/mtd/inftl.h @@ -2,8 +2,6 @@ * inftl.h -- defines to support the Inverse NAND Flash Translation Layer * * (C) Copyright 2002, Greg Ungerer (gerg@snapgear.com) - * - * $Id: inftl.h,v 1.7 2005/06/13 13:08:45 sean Exp $ */ #ifndef __MTD_INFTL_H__ @@ -52,8 +50,6 @@ struct INFTLrecord { int INFTL_mount(struct INFTLrecord *s); int INFTL_formatblock(struct INFTLrecord *s, int block); -extern char inftlmountrev[]; - void INFTL_dumptables(struct INFTLrecord *s); void INFTL_dumpVUchains(struct INFTLrecord *s); diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index a9fae032ba81..85e3939cf487 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -1,6 +1,5 @@ /* Overhauled routines for dealing with different mmap regions of flash */ -/* $Id: map.h,v 1.54 2005/11/07 11:14:54 gleixner Exp $ */ #ifndef __LINUX_MTD_MAP_H__ #define __LINUX_MTD_MAP_H__ diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 245f9098e171..31ed234b2a74 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -1,6 +1,4 @@ /* - * $Id: mtd.h,v 1.61 2005/11/07 11:14:54 gleixner Exp $ - * * Copyright (C) 1999-2003 David Woodhouse et al. * * Released under GPL diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index c42bc7f533a5..1288be7b7740 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -5,8 +5,6 @@ * Steven J. Hill * Thomas Gleixner * - * $Id: nand.h,v 1.74 2005/09/15 13:58:50 vwool 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. diff --git a/include/linux/mtd/nand_ecc.h b/include/linux/mtd/nand_ecc.h index 12c5bc342ead..090da505425d 100644 --- a/include/linux/mtd/nand_ecc.h +++ b/include/linux/mtd/nand_ecc.h @@ -3,8 +3,6 @@ * * Copyright (C) 2000 Steven J. Hill (sjhill@realitydiluted.com) * - * $Id: nand_ecc.h,v 1.4 2004/06/17 02:35:02 dbrown 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. diff --git a/include/linux/mtd/nftl.h b/include/linux/mtd/nftl.h index 001eec50cac6..dcaf611ed748 100644 --- a/include/linux/mtd/nftl.h +++ b/include/linux/mtd/nftl.h @@ -1,6 +1,4 @@ /* - * $Id: nftl.h,v 1.16 2004/06/30 14:49:00 dbrown Exp $ - * * (C) 1999-2003 David Woodhouse */ diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 7c37d7e55abc..5014f7a9f5df 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -4,8 +4,6 @@ * (C) 2000 Nicolas Pitre * * This code is GPL - * - * $Id: partitions.h,v 1.17 2005/11/07 11:14:55 gleixner Exp $ */ #ifndef MTD_PARTITIONS_H diff --git a/include/linux/mtd/physmap.h b/include/linux/mtd/physmap.h index 0dc07d5f3354..c8e63a5ee72e 100644 --- a/include/linux/mtd/physmap.h +++ b/include/linux/mtd/physmap.h @@ -2,8 +2,6 @@ * For boards with physically mapped flash and using * drivers/mtd/maps/physmap.c mapping driver. * - * $Id: physmap.h,v 1.4 2005/11/07 11:14:55 gleixner Exp $ - * * Copyright (C) 2003 MontaVista Software Inc. * Author: Jun Sun, jsun@mvista.com or jsun@junsun.net * diff --git a/include/linux/mtd/plat-ram.h b/include/linux/mtd/plat-ram.h index 0e37ad07bce2..e07890aff1cf 100644 --- a/include/linux/mtd/plat-ram.h +++ b/include/linux/mtd/plat-ram.h @@ -6,8 +6,6 @@ * * Generic platform device based RAM map * - * $Id: plat-ram.h,v 1.2 2005/01/24 00:37:40 bjd 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. diff --git a/include/linux/mtd/pmc551.h b/include/linux/mtd/pmc551.h index 5cc070c24d88..27ad40aed19f 100644 --- a/include/linux/mtd/pmc551.h +++ b/include/linux/mtd/pmc551.h @@ -1,6 +1,4 @@ /* - * $Id: pmc551.h,v 1.6 2005/11/07 11:14:55 gleixner Exp $ - * * PMC551 PCI Mezzanine Ram Device * * Author: @@ -17,7 +15,7 @@ #include -#define PMC551_VERSION "$Id: pmc551.h,v 1.6 2005/11/07 11:14:55 gleixner Exp $\n"\ +#define PMC551_VERSION \ "Ramix PMC551 PCI Mezzanine Ram Driver. (C) 1999,2000 Nortel Networks.\n" /* diff --git a/include/linux/mtd/xip.h b/include/linux/mtd/xip.h index e9d40bdde48c..36efcba15ecd 100644 --- a/include/linux/mtd/xip.h +++ b/include/linux/mtd/xip.h @@ -11,8 +11,6 @@ * 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. - * - * $Id: xip.h,v 1.5 2005/11/07 11:14:55 gleixner Exp $ */ #ifndef __LINUX_MTD_XIP_H__ -- cgit v1.2.3 From b8f8c3cf0a4ac0632ec3f0e15e9dc0c29de917af Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 18 Jul 2008 17:27:28 +0200 Subject: nohz: prevent tick stop outside of the idle loop Jack Ren and Eric Miao tracked down the following long standing problem in the NOHZ code: scheduler switch to idle task enable interrupts Window starts here ----> interrupt happens (does not set NEED_RESCHED) irq_exit() stops the tick ----> interrupt happens (does set NEED_RESCHED) return from schedule() cpu_idle(): preempt_disable(); Window ends here The interrupts can happen at any point inside the race window. The first interrupt stops the tick, the second one causes the scheduler to rerun and switch away from idle again and we end up with the tick disabled. The fact that it needs two interrupts where the first one does not set NEED_RESCHED and the second one does made the bug obscure and extremly hard to reproduce and analyse. Kudos to Jack and Eric. Solution: Limit the NOHZ functionality to the idle loop to make sure that we can not run into such a situation ever again. cpu_idle() { preempt_disable(); while(1) { tick_nohz_stop_sched_tick(1); <- tell NOHZ code that we are in the idle loop while (!need_resched()) halt(); tick_nohz_restart_sched_tick(); <- disables NOHZ mode preempt_enable_no_resched(); schedule(); preempt_disable(); } } In hindsight we should have done this forever, but ... /me grabs a large brown paperbag. Debugged-by: Jack Ren , Debugged-by: eric miao Signed-off-by: Thomas Gleixner --- include/linux/tick.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index a881c652f7e9..d3c02695dc5d 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -49,6 +49,7 @@ struct tick_sched { unsigned long check_clocks; enum tick_nohz_mode nohz_mode; ktime_t idle_tick; + int inidle; int tick_stopped; unsigned long idle_jiffies; unsigned long idle_calls; @@ -105,14 +106,14 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ # ifdef CONFIG_NO_HZ -extern void tick_nohz_stop_sched_tick(void); +extern void tick_nohz_stop_sched_tick(int inidle); extern void tick_nohz_restart_sched_tick(void); extern void tick_nohz_update_jiffies(void); extern ktime_t tick_nohz_get_sleep_length(void); extern void tick_nohz_stop_idle(int cpu); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); # else -static inline void tick_nohz_stop_sched_tick(void) { } +static inline void tick_nohz_stop_sched_tick(int inidle) { } static inline void tick_nohz_restart_sched_tick(void) { } static inline void tick_nohz_update_jiffies(void) { } static inline ktime_t tick_nohz_get_sleep_length(void) -- cgit v1.2.3 From 47b374752aed1c029f995473c7c463ee3ae5fbaa Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Tue, 22 Jul 2008 14:19:39 -0700 Subject: IB/mlx4: Rename struct mlx4_lso_seg to mlx4_wqe_lso_seg Make the struct name consistent with other WQE segment struct types defined in . Signed-off-by: Roland Dreier --- include/linux/mlx4/qp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 7f128b266faa..f02e9ed36cfa 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -219,7 +219,7 @@ struct mlx4_wqe_datagram_seg { __be32 reservd[2]; }; -struct mlx4_lso_seg { +struct mlx4_wqe_lso_seg { __be32 mss_hdr_size; __be32 header[0]; }; -- cgit v1.2.3 From e5899e1b7d73e67de758a32174a859cc2586c0b9 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 19 Jul 2008 14:39:24 +0200 Subject: PCI PM: make more PCI PM core functionality available to drivers Make more PCI PM core functionality available to drivers * Export pci_pme_capable() so that it can be called directly by drivers (for example, tg3 needs that). * Move the state choosing part of pci_prepare_to_sleep() to a separate function, pci_target_state(), that can be called directly by drivers (for example, tg3 needs that). Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- 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 a6a088e1a804..1d296d31abe0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -638,7 +638,9 @@ int pci_save_state(struct pci_dev *dev); int pci_restore_state(struct pci_dev *dev); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); +bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); int pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable); +pci_power_t pci_target_state(struct pci_dev *dev); int pci_prepare_to_sleep(struct pci_dev *dev); int pci_back_from_sleep(struct pci_dev *dev); -- cgit v1.2.3 From e14fa82439d33cef67eaafc1a48960bbfa610c8e Mon Sep 17 00:00:00 2001 From: Riku Voipio Date: Sat, 31 May 2008 14:43:41 +0100 Subject: leds: Add pca9532 led driver NXP pca9532 is a LED dimmer/controller attached to i2c bus. It allows attaching upto 16 leds which can either be on, off or dimmed and/or blinked with the two PWM modulators available. This driver is a "new-style" i2c driver that adheres to the driver model and implements the led framework api. Since the leds connected to the driver are platform specific, it is only useful when platform data is passed to the driver to define what leds are connected to which pins. Signed-off-by: Riku Voipio Signed-off-by: Andrew Morton Signed-off-by: Richard Purdie --- include/linux/leds-pca9532.h | 45 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 include/linux/leds-pca9532.h (limited to 'include/linux') diff --git a/include/linux/leds-pca9532.h b/include/linux/leds-pca9532.h new file mode 100644 index 000000000000..81b4207deb95 --- /dev/null +++ b/include/linux/leds-pca9532.h @@ -0,0 +1,45 @@ +/* + * pca9532.h - platform data structure for pca9532 led controller + * + * Copyright (C) 2008 Riku Voipio + * + * 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. + * + * Datasheet: http://www.nxp.com/acrobat/datasheets/PCA9532_3.pdf + * + */ + +#ifndef __LINUX_PCA9532_H +#define __LINUX_PCA9532_H + +#include + +enum pca9532_state { + PCA9532_OFF = 0x0, + PCA9532_ON = 0x1, + PCA9532_PWM0 = 0x2, + PCA9532_PWM1 = 0x3 +}; + +enum pca9532_type { PCA9532_TYPE_NONE, PCA9532_TYPE_LED, + PCA9532_TYPE_N2100_BEEP }; + +struct pca9532_led { + u8 id; + struct i2c_client *client; + char *name; + struct led_classdev ldev; + enum pca9532_type type; + enum pca9532_state state; +}; + +struct pca9532_platform_data { + struct pca9532_led leds[16]; + u8 pwm[2]; + u8 psc[2]; +}; + +#endif /* __LINUX_PCA9532_H */ + -- cgit v1.2.3 From 781a54e7664cc0089287a90d27086e9656ac68a1 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Sat, 31 May 2008 15:23:19 +0100 Subject: leds: mark led_classdev.default_trigger as const LED classdev core doesn't modify memory pointed by the default_trigger, so mark it as const and we'll able to pass const char *s without getting compiler warnings. Signed-off-by: Anton Vorontsov Signed-off-by: Richard Purdie --- include/linux/leds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 519df72e939d..e7a5e89932fe 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -48,7 +48,7 @@ struct led_classdev { struct device *dev; struct list_head node; /* LED Device list */ - char *default_trigger; /* Trigger to use */ + const char *default_trigger; /* Trigger to use */ #ifdef CONFIG_LEDS_TRIGGERS /* Protects the trigger data below */ -- cgit v1.2.3 From f46e9203d9a100bae216cc06e17f2e77351aa8d8 Mon Sep 17 00:00:00 2001 From: Nate Case Date: Wed, 16 Jul 2008 22:49:55 +0100 Subject: leds: Add support for Philips PCA955x I2C LED drivers This driver supports the PCA9550, PCA9551, PCA9552, and PCA9553 LED driver chips. Signed-off-by: Nate Case Signed-off-by: Andrew Morton Signed-off-by: Richard Purdie --- include/linux/leds.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index e7a5e89932fe..d41ccb56146a 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -118,6 +118,20 @@ extern void ledtrig_ide_activity(void); #define ledtrig_ide_activity() do {} while(0) #endif +/* + * Generic LED platform data for describing LED names and default triggers. + */ +struct led_info { + const char *name; + char *default_trigger; + int flags; +}; + +struct led_platform_data { + int num_leds; + struct led_info *leds; +}; + /* For the leds-gpio driver */ struct gpio_led { const char *name; -- cgit v1.2.3 From 95d04f0735b4fc837bff9aedcc3f3efb20ddc3d1 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Wed, 23 Jul 2008 08:12:26 -0700 Subject: IB/mlx4: Add support for memory management extensions and local DMA L_Key Add support for the following operations to mlx4 when device firmware supports them: - Send with invalidate and local invalidate send queue work requests; - Allocate/free fast register MRs; - Allocate/free fast register MR page lists; - Fast register MR send queue work requests; - Local DMA L_Key. Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 10 ++++++++++ include/linux/mlx4/qp.h | 16 ++++++++++++---- 2 files changed, 22 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 81b3dd5206e0..655ea0d1ee14 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -68,6 +68,14 @@ enum { MLX4_DEV_CAP_FLAG_UD_MCAST = 1 << 21 }; +enum { + MLX4_BMME_FLAG_LOCAL_INV = 1 << 6, + MLX4_BMME_FLAG_REMOTE_INV = 1 << 7, + MLX4_BMME_FLAG_TYPE_2_WIN = 1 << 9, + MLX4_BMME_FLAG_RESERVED_LKEY = 1 << 10, + MLX4_BMME_FLAG_FAST_REG_WR = 1 << 11, +}; + enum mlx4_event { MLX4_EVENT_TYPE_COMP = 0x00, MLX4_EVENT_TYPE_PATH_MIG = 0x01, @@ -184,6 +192,8 @@ struct mlx4_caps { u32 max_msg_sz; u32 page_size_cap; u32 flags; + u32 bmme_flags; + u32 reserved_lkey; u16 stat_rate_support; u8 port_width_cap[MLX4_MAX_PORTS + 1]; int max_gso_sz; diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index f02e9ed36cfa..e27082cd650e 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -233,6 +233,14 @@ struct mlx4_wqe_bind_seg { __be64 length; }; +enum { + MLX4_WQE_FMR_PERM_LOCAL_READ = 1 << 27, + MLX4_WQE_FMR_PERM_LOCAL_WRITE = 1 << 28, + MLX4_WQE_FMR_PERM_REMOTE_READ = 1 << 29, + MLX4_WQE_FMR_PERM_REMOTE_WRITE = 1 << 30, + MLX4_WQE_FMR_PERM_ATOMIC = 1 << 31 +}; + struct mlx4_wqe_fmr_seg { __be32 flags; __be32 mem_key; @@ -255,11 +263,11 @@ struct mlx4_wqe_fmr_ext_seg { }; struct mlx4_wqe_local_inval_seg { - u8 flags; - u8 reserved1[3]; + __be32 flags; + u32 reserved1; __be32 mem_key; - u8 reserved2[3]; - u8 guest_id; + u32 reserved2[2]; + __be32 guest_id; __be64 pa; }; -- cgit v1.2.3 From a5bf6190417cbbf80443a9f71c65b653e13e9982 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Thu, 10 Jul 2008 18:38:33 +0300 Subject: UBI: add ubi_sync() interface To flush MTD device caches. Signed-off-by: Artem Bityutskiy --- include/linux/mtd/ubi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h index f71201d0f3e7..83302bbbddb4 100644 --- a/include/linux/mtd/ubi.h +++ b/include/linux/mtd/ubi.h @@ -152,6 +152,7 @@ int ubi_leb_erase(struct ubi_volume_desc *desc, int lnum); int ubi_leb_unmap(struct ubi_volume_desc *desc, int lnum); int ubi_leb_map(struct ubi_volume_desc *desc, int lnum, int dtype); int ubi_is_mapped(struct ubi_volume_desc *desc, int lnum); +int ubi_sync(int ubi_num); /* * This function is the same as the 'ubi_leb_read()' function, but it does not -- cgit v1.2.3 From 85c6e6e28259e9b58b8984db536c45bc3161f40c Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 16 Jul 2008 10:25:56 +0300 Subject: UBI: amend commentaries Hch asked not to use "unit" for sub-systems, let it be so. Also some other commentaries modifications. Signed-off-by: Artem Bityutskiy --- include/linux/mtd/ubi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h index 83302bbbddb4..6316fafe5c2a 100644 --- a/include/linux/mtd/ubi.h +++ b/include/linux/mtd/ubi.h @@ -45,13 +45,13 @@ enum { * @size: how many physical eraseblocks are reserved for this volume * @used_bytes: how many bytes of data this volume contains * @used_ebs: how many physical eraseblocks of this volume actually contain any - * data + * data * @vol_type: volume type (%UBI_DYNAMIC_VOLUME or %UBI_STATIC_VOLUME) * @corrupted: non-zero if the volume is corrupted (static volumes only) * @upd_marker: non-zero if the volume has update marker set * @alignment: volume alignment * @usable_leb_size: how many bytes are available in logical eraseblocks of - * this volume + * this volume * @name_len: volume name length * @name: volume name * @cdev: UBI volume character device major and minor numbers -- cgit v1.2.3 From b552068999b0b05087c454e525b30b785c79dc9b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 23 Apr 2008 10:07:27 -0400 Subject: Remove __DECLARE_SEMAPHORE_GENERIC There are no users of __DECLARE_SEMAPHORE_GENERIC in the kernel Signed-off-by: Matthew Wilcox --- include/linux/semaphore.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h index 9cae64b00d6b..7415839ac890 100644 --- a/include/linux/semaphore.h +++ b/include/linux/semaphore.h @@ -26,10 +26,8 @@ struct semaphore { .wait_list = LIST_HEAD_INIT((name).wait_list), \ } -#define __DECLARE_SEMAPHORE_GENERIC(name, count) \ - struct semaphore name = __SEMAPHORE_INITIALIZER(name, count) - -#define DECLARE_MUTEX(name) __DECLARE_SEMAPHORE_GENERIC(name, 1) +#define DECLARE_MUTEX(name) \ + struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1) static inline void sema_init(struct semaphore *sem, int val) { -- cgit v1.2.3 From e108526e77aa41c89b3be96f75d97615db2b751c Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 23 Jul 2008 21:26:44 -0700 Subject: move memory_read_from_buffer() from fs.h to string.h James Bottomley warns that inclusion of linux/fs.h in a low level driver was always a danger signal. This patch moves memory_read_from_buffer() from fs.h to string.h and fixes includes in existing memory_read_from_buffer() users. Signed-off-by: Akinobu Mita Cc: James Bottomley Cc: Geert Uytterhoeven Cc: Zhang Rui Cc: Bob Moore Cc: Thomas Renninger Cc: Len Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 -- include/linux/string.h | 3 +++ 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9c2ac5c0ef5c..ff54ae4933f3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2006,8 +2006,6 @@ extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); -extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, - const void *from, size_t available); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, diff --git a/include/linux/string.h b/include/linux/string.h index efdc44593b52..810d80df0a1d 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -111,5 +111,8 @@ extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); +extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, + const void *from, size_t available); + #endif #endif /* _LINUX_STRING_H_ */ -- cgit v1.2.3 From 8b05c7e6e159d2f33c9275281b8b909a89eb7c5d Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Wed, 23 Jul 2008 21:26:53 -0700 Subject: add a helper function to test if an object is on the stack lib/debugobjects.c has a function to test if an object is on the stack. The block layer and ide needs it (they need to avoid DMA from/to stack buffers). This patch moves the function to include/linux/sched.h so that everyone can use it. lib/debugobjects.c uses current->stack but this patch uses a task_stack_page() accessor, which is a preferable way to access the stack. Signed-off-by: FUJITA Tomonori Cc: Christoph Lameter Cc: Andy Whitcroft Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index dc7e592c473a..6aca4a16e377 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1983,6 +1983,13 @@ static inline unsigned long *end_of_stack(struct task_struct *p) #endif +static inline int object_is_on_stack(void *obj) +{ + void *stack = task_stack_page(current); + + return (obj >= stack) && (obj < (stack + THREAD_SIZE)); +} + extern void thread_info_cache_init(void); /* set thread flags in other task's structures -- cgit v1.2.3 From b61bfa3c462671c48a51fb5c31af337c5a996a04 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Jul 2008 21:26:55 -0700 Subject: mm: move bootmem descriptors definition to a single place There are a lot of places that define either a single bootmem descriptor or an array of them. Use only one central array with MAX_NUMNODES items instead. Signed-off-by: Johannes Weiner Acked-by: Ralf Baechle Cc: Ingo Molnar Cc: Richard Henderson Cc: Russell King Cc: Tony Luck Cc: Hirokazu Takata Cc: Geert Uytterhoeven Cc: Kyle McMartin Cc: Paul Mackerras Cc: Paul Mundt Cc: David S. Miller Cc: Yinghai Lu Cc: Christoph Lameter Cc: Mel Gorman Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index a1d9b79078ea..2599c741405e 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -38,6 +38,8 @@ typedef struct bootmem_data { struct list_head list; } bootmem_data_t; +extern bootmem_data_t bootmem_node_data[]; + extern unsigned long bootmem_bootmap_pages(unsigned long); extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); extern void free_bootmem(unsigned long addr, unsigned long size); -- cgit v1.2.3 From ffc6421f0720f433b5b35b89ff56e998eabff93b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Jul 2008 21:26:59 -0700 Subject: mm: unexport __alloc_bootmem_core() This function has no external callers, so unexport it. Also fix its naming inconsistency. Signed-off-by: Johannes Weiner Cc: Ingo Molnar Cc: Yinghai Lu Cc: Christoph Lameter Cc: Mel Gorman Cc: Andy Whitcroft Cc: Mel Gorman Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 2599c741405e..dd8fee6c46d9 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -56,11 +56,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal); -extern void *__alloc_bootmem_core(struct bootmem_data *bdata, - unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit); /* * flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, -- cgit v1.2.3 From e4048e5dc4aecec670f48ed007a28779f09cebd6 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 23 Jul 2008 21:27:01 -0700 Subject: page allocator: inline some __alloc_pages() wrappers Two zonelist patch series rewrote __page_alloc() largely. Now, it is just a wrapper function. Inlining them will save a function call. [akpm@linux-foundation.org: export __alloc_pages_internal] Cc: Lee Schermerhorn Cc: Mel Gorman Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index b414be387180..f640ed241422 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -173,11 +173,24 @@ static inline void arch_free_page(struct page *page, int order) { } static inline void arch_alloc_page(struct page *page, int order) { } #endif -extern struct page *__alloc_pages(gfp_t, unsigned int, struct zonelist *); +struct page * +__alloc_pages_internal(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, nodemask_t *nodemask); + +static inline struct page * +__alloc_pages(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist) +{ + return __alloc_pages_internal(gfp_mask, order, zonelist, NULL); +} + +static inline struct page * +__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, nodemask_t *nodemask) +{ + return __alloc_pages_internal(gfp_mask, order, zonelist, nodemask); +} -extern struct page * -__alloc_pages_nodemask(gfp_t, unsigned int, - struct zonelist *, nodemask_t *nodemask); static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) -- cgit v1.2.3 From c748e1340e0de3fa7fed86f8bdf499be9242afff Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 23 Jul 2008 21:27:03 -0700 Subject: mm/vmstat.c: proper externs This patch adds proper extern declarations for five variables in include/linux/vmstat.h Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index e83b69346d23..58334d439516 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -44,6 +44,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, NR_VM_EVENT_ITEMS }; +extern const struct seq_operations fragmentation_op; +extern const struct seq_operations pagetypeinfo_op; +extern const struct seq_operations zoneinfo_op; +extern const struct seq_operations vmstat_op; +extern int sysctl_stat_interval; + #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. -- cgit v1.2.3 From 0d71d10a4252a3938e6b70189bc776171c02e076 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 23 Jul 2008 21:27:05 -0700 Subject: mm: remove nopfn There are no users of nopfn in the tree. Remove it. [hugh@veritas.com: fix build error] Signed-off-by: Nick Piggin Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2128ef7780c6..eb815cfc1b35 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -166,8 +166,6 @@ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); - unsigned long (*nopfn)(struct vm_area_struct *area, - unsigned long address); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ @@ -674,13 +672,6 @@ static inline int page_mapped(struct page *page) return atomic_read(&(page)->_mapcount) >= 0; } -/* - * Error return values for the *_nopfn functions - */ -#define NOPFN_SIGBUS ((unsigned long) -1) -#define NOPFN_OOM ((unsigned long) -2) -#define NOPFN_REFAULT ((unsigned long) -3) - /* * Different kinds of faults, as returned by handle_mm_fault(). * Used to decide whether a process gets delivered SIGBUS or -- cgit v1.2.3 From 28b2ee20c7cba812b6f2ccf6d722cf86d00a84dc Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 23 Jul 2008 21:27:05 -0700 Subject: access_process_vm device memory infrastructure In order to be able to debug things like the X server and programs using the PPC Cell SPUs, the debugger needs to be able to access device memory through ptrace and /proc/pid/mem. This patch: Add the generic_access_phys access function and put the hooks in place to allow access_process_vm to access device or PPC Cell SPU memory. [riel@redhat.com: Add documentation for the vm_ops->access function] Signed-off-by: Rik van Riel Signed-off-by: Benjamin Herrensmidt Cc: Dave Airlie Cc: Hugh Dickins Cc: Paul Mackerras Cc: Arnd Bergmann Acked-by: Peter Zijlstra 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 eb815cfc1b35..5c7f8f64f70e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -170,6 +170,12 @@ struct vm_operations_struct { /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page); + + /* called by access_process_vm when get_user_pages() fails, typically + * for use by special VMAs that can switch between memory and hardware + */ + int (*access)(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy @@ -771,6 +777,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) -- cgit v1.2.3 From 42b7772812d15b86543a23b82bd6070eef9a08b1 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 23 Jul 2008 21:27:10 -0700 Subject: mm: remove double indirection on tlb parameter to free_pgd_range() & Co The double indirection here is not needed anywhere and hence (at least) confusing. Signed-off-by: Jan Beulich Cc: Hugh Dickins Cc: Nick Piggin Cc: Christoph Lameter Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Luck, Tony" Cc: Paul Mundt Cc: "David S. Miller" Acked-by: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5c7f8f64f70e..f8071097302a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -769,10 +769,8 @@ struct mm_walk { int walk_page_range(unsigned long addr, unsigned long end, struct mm_walk *walk); -void free_pgd_range(struct mmu_gather **tlb, unsigned long addr, +void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); -void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma, - unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, -- cgit v1.2.3 From da3bbdd4632c0171406b2677e31494afa5bde2f8 Mon Sep 17 00:00:00 2001 From: Kentaro Makita Date: Wed, 23 Jul 2008 21:27:13 -0700 Subject: fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita Cc: Neil Brown Cc: Trond Myklebust Cc: David Chinner Cc: "J. Bruce Fields" 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 ff54ae4933f3..e5e6a244096c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1025,6 +1025,7 @@ extern int send_sigurg(struct fown_struct *fown); extern struct list_head super_blocks; extern spinlock_t sb_lock; +#define sb_entry(list) list_entry((list), struct super_block, s_list) #define S_BIAS (1<<30) struct super_block { struct list_head s_list; /* Keep this first */ @@ -1058,6 +1059,9 @@ struct super_block { struct list_head s_more_io; /* parked for more writeback */ struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */ struct list_head s_files; + /* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */ + struct list_head s_dentry_lru; /* unused dentry lru */ + int s_nr_dentry_unused; /* # of dentry on lru */ struct block_device *s_bdev; struct mtd_info *s_mtd; -- cgit v1.2.3 From 0cad47cf13bc2e9142d3a11d9f50523797d0d4ea Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 23 Jul 2008 21:27:16 -0700 Subject: page-flags: record page flag overlays explicitly With the recent page flag reorganisation we have a single enum which defines the valid page flags and their values, nice and clear. However there are a number of bits which are overloaded by different subsystems. Firstly there is PG_owner_priv_1 which is used by filesystems and by XEN. Secondly both SLOB and SLUB use a couple of extra page bits to manage internal state for pages they own; both overlay other bits. All of these "aliases" are scattered about the source making it very hard for a reader to know if the bits are safe to rely on in all contexts; confusion here is bad. As we now have a single place where the bits are clearly assigned it makes sense to clarify the reuse of bits by making the aliases explicit and visible with the original bit assignments. This patch creates explicit aliases within the enum itself for the overloaded bits, creates standard bit accessors PageFoo etc. and uses those throughout. This version pulls the bit manipulation out to standard named page bit accessors as suggested by Christoph, it retains the explicit mapping to the overlayed bits. A fusion of both ideas. This has been SLUB and SLOB have been compile tested on x86_64 only, and SLUB boot tested. If people feel this is worth doing then I can run a fuller set of testing. This patch: Some page flags are used for more than one purpose, for example PG_owner_priv_1. Currently there are individual accessors for each user, each built using the common flag name far away from the bit definitions. This makes it hard to see all possible uses of these bits. Now that we have a single enum to generate the bit orders it makes sense to express overlays in the same place. So create per use aliases for this bit in the main page-flags enum and use those in the accessors. [akpm@linux-foundation.org: fix xen] Signed-off-by: Andy Whitcroft Cc: Pekka Enberg Cc: Christoph Lameter Cc: Matt Mackall Cc: Nick Piggin Cc: KAMEZAWA Hiroyuki Reviewed-by: KOSAKI Motohiro Cc: Rik van Riel Cc: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 0d2a4e7012aa..7d8db1233e44 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -96,7 +96,14 @@ enum pageflags { #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR PG_uncached, /* Page has been mapped as uncached */ #endif - __NR_PAGEFLAGS + __NR_PAGEFLAGS, + + /* Filesystems */ + PG_checked = PG_owner_priv_1, + + /* XEN */ + PG_pinned = PG_owner_priv_1, + PG_savepinned = PG_dirty, }; #ifndef __GENERATING_BOUNDS_H @@ -155,9 +162,9 @@ PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) __PAGEFLAG(Slab, slab) -PAGEFLAG(Checked, owner_priv_1) /* Used by some filesystems */ -PAGEFLAG(Pinned, owner_priv_1) TESTSCFLAG(Pinned, owner_priv_1) /* Xen */ -PAGEFLAG(SavePinned, dirty); /* Xen */ +PAGEFLAG(Checked, checked) /* Used by some filesystems */ +PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ +PAGEFLAG(SavePinned, savepinned); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) -- cgit v1.2.3 From 8a38082d21cbc5ec961da7dda195e98a9a064dcf Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 23 Jul 2008 21:27:18 -0700 Subject: slub: record page flag overlays explicitly SLUB reuses two page bits for internal purposes, it overlays PG_active and PG_error. This is hidden away in slub.c. Document these overlays explicitly in the main page-flags enum along with all the others. Signed-off-by: Andy Whitcroft Cc: Pekka Enberg Cc: Christoph Lameter Cc: Matt Mackall Cc: Nick Piggin Tested-by: KOSAKI Motohiro Cc: KOSAKI Motohiro Cc: Rik van Riel Cc: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 7d8db1233e44..3fc586b7b90b 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -104,6 +104,10 @@ enum pageflags { /* XEN */ PG_pinned = PG_owner_priv_1, PG_savepinned = PG_dirty, + + /* SLUB */ + PG_slub_frozen = PG_active, + PG_slub_debug = PG_error, }; #ifndef __GENERATING_BOUNDS_H @@ -169,6 +173,9 @@ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) +__PAGEFLAG(SlubFrozen, slub_frozen) +__PAGEFLAG(SlubDebug, slub_debug) + /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. -- cgit v1.2.3 From 9023cb7e8564d95a1893f8cb6895a293be9a71fe Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 23 Jul 2008 21:27:19 -0700 Subject: slob: record page flag overlays explicitly SLOB reuses two page bits for internal purposes, it overlays PG_active and PG_private. This is hidden away in slob.c. Document these overlays explicitly in the main page-flags enum along with all the others. Signed-off-by: Andy Whitcroft Cc: Pekka Enberg Cc: Christoph Lameter Cc: Matt Mackall Cc: Nick Piggin Reviewed-by: KOSAKI Motohiro Cc: KOSAKI Motohiro Cc: Rik van Riel Cc: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 3fc586b7b90b..54590a9a103e 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -105,6 +105,10 @@ enum pageflags { PG_pinned = PG_owner_priv_1, PG_savepinned = PG_dirty, + /* SLOB */ + PG_slob_page = PG_active, + PG_slob_free = PG_private, + /* SLUB */ PG_slub_frozen = PG_active, PG_slub_debug = PG_error, @@ -173,6 +177,9 @@ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) +__PAGEFLAG(SlobPage, slob_page) +__PAGEFLAG(SlobFree, slob_free) + __PAGEFLAG(SlubFrozen, slub_frozen) __PAGEFLAG(SlubDebug, slub_debug) -- cgit v1.2.3 From 2185e69f680ae8c8496b6fc15e20c889d5b39b67 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 23 Jul 2008 21:27:19 -0700 Subject: mapping_set_error: add unlikely() This is called on a per-page basis and in the vast majority of cases `error' is zero. Cc: Guillaume Chazarain Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 d2fca802f809..ee1ec2c7723c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -22,7 +22,7 @@ static inline void mapping_set_error(struct address_space *mapping, int error) { - if (error) { + if (unlikely(error)) { if (error == -ENOSPC) set_bit(AS_ENOSPC, &mapping->flags); else -- cgit v1.2.3 From 9109fb7b3520de187ebc3646c209d66a233f7169 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Jul 2008 21:27:20 -0700 Subject: mm: drop unneeded pgdat argument from free_area_init_node() free_area_init_node() gets passed in the node id as well as the node descriptor. This is redundant as the function can trivially get the node descriptor itself by means of NODE_DATA() and the node's id. I checked all the users and NODE_DATA() seems to be usable everywhere from where this function is called. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f8071097302a..196924b657bc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -962,9 +962,8 @@ static inline void pgtable_page_dtor(struct page *page) NULL: pte_offset_kernel(pmd, address)) extern void free_area_init(unsigned long * zones_size); -extern void free_area_init_node(int nid, pg_data_t *pgdat, - unsigned long * zones_size, unsigned long zone_start_pfn, - unsigned long *zholes_size); +extern void free_area_init_node(int nid, unsigned long * zones_size, + unsigned long zone_start_pfn, unsigned long *zholes_size); #ifdef CONFIG_ARCH_POPULATES_NODE_MAP /* * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its -- cgit v1.2.3 From a1e78772d72b2616ed20e54896e68e0e7044854e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 23 Jul 2008 21:27:23 -0700 Subject: hugetlb: reserve huge pages for reliable MAP_PRIVATE hugetlbfs mappings until fork() This patch reserves huge pages at mmap() time for MAP_PRIVATE mappings in a similar manner to the reservations taken for MAP_SHARED mappings. The reserve count is accounted both globally and on a per-VMA basis for private mappings. This guarantees that a process that successfully calls mmap() will successfully fault all pages in the future unless fork() is called. The characteristics of private mappings of hugetlbfs files behaviour after this patch are; 1. The process calling mmap() is guaranteed to succeed all future faults until it forks(). 2. On fork(), the parent may die due to SIGKILL on writes to the private mapping if enough pages are not available for the COW. For reasonably reliable behaviour in the face of a small huge page pool, children of hugepage-aware processes should not reference the mappings; such as might occur when fork()ing to exec(). 3. On fork(), the child VMAs inherit no reserves. Reads on pages already faulted by the parent will succeed. Successful writes will depend on enough huge pages being free in the pool. 4. Quotas of the hugetlbfs mount are checked at reserve time for the mapper and at fault time otherwise. Before this patch, all reads or writes in the child potentially needs page allocations that can later lead to the death of the parent. This applies to reads and writes of uninstantiated pages as well as COW. After the patch it is only a write to an instantiated page that causes problems. Signed-off-by: Mel Gorman Acked-by: Adam Litke Cc: Andy Whitcroft Cc: William Lee Irwin III Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a79e80b689d8..185b14c9f021 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -17,6 +17,7 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) return vma->vm_flags & VM_HUGETLB; } +void reset_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); @@ -30,7 +31,8 @@ int hugetlb_report_node_meminfo(int, char *); unsigned long hugetlb_total_pages(void); int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access); -int hugetlb_reserve_pages(struct inode *inode, long from, long to); +int hugetlb_reserve_pages(struct inode *inode, long from, long to, + struct vm_area_struct *vma); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); extern unsigned long max_huge_pages; @@ -58,6 +60,11 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) { return 0; } + +static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) +{ +} + static inline unsigned long hugetlb_total_pages(void) { return 0; -- cgit v1.2.3 From 04f2cbe35699d22dbf428373682ead85ca1240f5 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 23 Jul 2008 21:27:25 -0700 Subject: hugetlb: guarantee that COW faults for a process that called mmap(MAP_PRIVATE) on hugetlbfs will succeed After patch 2 in this series, a process that successfully calls mmap() for a MAP_PRIVATE mapping will be guaranteed to successfully fault until a process calls fork(). At that point, the next write fault from the parent could fail due to COW if the child still has a reference. We only reserve pages for the parent but a copy must be made to avoid leaking data from the parent to the child after fork(). Reserves could be taken for both parent and child at fork time to guarantee faults but if the mapping is large it is highly likely we will not have sufficient pages for the reservation, and it is common to fork only to exec() immediatly after. A failure here would be very undesirable. Note that the current behaviour of mainline with MAP_PRIVATE pages is pretty bad. The following situation is allowed to occur today. 1. Process calls mmap(MAP_PRIVATE) 2. Process calls mlock() to fault all pages and makes sure it succeeds 3. Process forks() 4. Process writes to MAP_PRIVATE mapping while child still exists 5. If the COW fails at this point, the process gets SIGKILLed even though it had taken care to ensure the pages existed This patch improves the situation by guaranteeing the reliability of the process that successfully calls mmap(). When the parent performs COW, it will try to satisfy the allocation without using reserves. If that fails the parent will steal the page leaving any children without a page. Faults from the child after that point will result in failure. If the child COW happens first, an attempt will be made to allocate the page without reserves and the child will get SIGKILLed on failure. To summarise the new behaviour: 1. If the original mapper performs COW on a private mapping with multiple references, it will attempt to allocate a hugepage from the pool or the buddy allocator without using the existing reserves. On fail, VMAs mapping the same area are traversed and the page being COW'd is unmapped where found. It will then steal the original page as the last mapper in the normal way. 2. The VMAs the