From 61e84623ace35ce48975e8f90bbbac7557c43d61 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Fri, 7 Oct 2016 22:04:33 -0400 Subject: net: centralize net_device min/max MTU checking While looking into an MTU issue with sfc, I started noticing that almost every NIC driver with an ndo_change_mtu function implemented almost exactly the same range checks, and in many cases, that was the only practical thing their ndo_change_mtu function was doing. Quite a few drivers have either 68, 64, 60 or 46 as their minimum MTU value checked, and then various sizes from 1500 to 65535 for their maximum MTU value. We can remove a whole lot of redundant code here if we simple store min_mtu and max_mtu in net_device, and check against those in net/core/dev.c's dev_set_mtu(). In theory, there should be zero functional change with this patch, it just puts the infrastructure in place. Subsequent patches will attempt to start using said infrastructure, with theoretically zero change in functionality. CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- 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 136ae6bbe81e..fbdf923af4d3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1506,6 +1506,8 @@ enum netdev_priv_flags { * @if_port: Selectable AUI, TP, ... * @dma: DMA channel * @mtu: Interface MTU value + * @min_mtu: Interface Minimum MTU value + * @max_mtu: Interface Maximum MTU value * @type: Interface hardware type * @hard_header_len: Maximum hardware header length. * @@ -1726,6 +1728,8 @@ struct net_device { unsigned char dma; unsigned int mtu; + unsigned int min_mtu; + unsigned int max_mtu; unsigned short type; unsigned short hard_header_len; -- cgit v1.2.3 From cf53b1da73bdf940f1523ec5a7d375d7056c759c Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Tue, 11 Oct 2016 13:04:09 -0700 Subject: Revert "net: Add driver helper functions to determine checksum offloadability" This reverts commit 6ae23ad36253a8033c5714c52b691b84456487c5. The code has been in kernel since 4.4 but there are no in tree code that uses. Unused code is broken code, remove it. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 78 ----------------------------------------------- 1 file changed, 78 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fbdf923af4d3..bf341b65ca5e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2653,71 +2653,6 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, remcsum_unadjust((__sum16 *)ptr, grc->delta); } -struct skb_csum_offl_spec { - __u16 ipv4_okay:1, - ipv6_okay:1, - encap_okay:1, - ip_options_okay:1, - ext_hdrs_okay:1, - tcp_okay:1, - udp_okay:1, - sctp_okay:1, - vlan_okay:1, - no_encapped_ipv6:1, - no_not_encapped:1; -}; - -bool __skb_csum_offload_chk(struct sk_buff *skb, - const struct skb_csum_offl_spec *spec, - bool *csum_encapped, - bool csum_help); - -static inline bool skb_csum_offload_chk(struct sk_buff *skb, - const struct skb_csum_offl_spec *spec, - bool *csum_encapped, - bool csum_help) -{ - if (skb->ip_summed != CHECKSUM_PARTIAL) - return false; - - return __skb_csum_offload_chk(skb, spec, csum_encapped, csum_help); -} - -static inline bool skb_csum_offload_chk_help(struct sk_buff *skb, - const struct skb_csum_offl_spec *spec) -{ - bool csum_encapped; - - return skb_csum_offload_chk(skb, spec, &csum_encapped, true); -} - -static inline bool skb_csum_off_chk_help_cmn(struct sk_buff *skb) -{ - static const struct skb_csum_offl_spec csum_offl_spec = { - .ipv4_okay = 1, - .ip_options_okay = 1, - .ipv6_okay = 1, - .vlan_okay = 1, - .tcp_okay = 1, - .udp_okay = 1, - }; - - return skb_csum_offload_chk_help(skb, &csum_offl_spec); -} - -static inline bool skb_csum_off_chk_help_cmn_v4_only(struct sk_buff *skb) -{ - static const struct skb_csum_offl_spec csum_offl_spec = { - .ipv4_okay = 1, - .ip_options_okay = 1, - .tcp_okay = 1, - .udp_okay = 1, - .vlan_okay = 1, - }; - - return skb_csum_offload_chk_help(skb, &csum_offl_spec); -} - static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, @@ -3961,19 +3896,6 @@ static inline bool can_checksum_protocol(netdev_features_t features, } } -/* Map an ethertype into IP protocol if possible */ -static inline int eproto_to_ipproto(int eproto) -{ - switch (eproto) { - case htons(ETH_P_IP): - return IPPROTO_IP; - case htons(ETH_P_IPV6): - return IPPROTO_IPV6; - default: - return -1; - } -} - #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev); #else -- cgit v1.2.3 From c3aaa403840a5ccd305fb5e73f3cbfac6453b5e5 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Fri, 14 Oct 2016 05:19:17 -0400 Subject: qed: Pass MAC hints to VFs Some hypervisors can support MAC hints to their VFs. Even though we don't have such a hypervisor API in linux, we add sufficient logic for the VF to be able to receive such hints and set the mac accordingly - as long as the VF has not been set with a MAC already. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 33c24ebc9b7f..1c779486c30d 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -129,7 +129,7 @@ struct qed_tunn_params { struct qed_eth_cb_ops { struct qed_common_cb_ops common; - void (*force_mac) (void *dev, u8 *mac); + void (*force_mac) (void *dev, u8 *mac, bool forced); }; #ifdef CONFIG_DCB -- cgit v1.2.3 From 7b7e70f979e34ed84d725eab8ea42921ab6f42e3 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Fri, 14 Oct 2016 05:19:20 -0400 Subject: qed*: Allow unicast filtering Apparently qede fails to set IFF_UNICAST_FLT, and as a result is not actually performing unicast MAC filtering. While we're at it - relax a hard-coded limitation that limits each interface into using at most 15 unicast MAC addresses before turning promiscuous. Instead utilize the HW resources to their limit. Signed-off-by: Yuval Mintz 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 1c779486c30d..15130805d792 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -23,6 +23,7 @@ struct qed_dev_eth_info { u8 port_mac[ETH_ALEN]; u8 num_vlan_filters; + u16 num_mac_filters; /* Legacy VF - this affects the datapath, so qede has to know */ bool is_legacy; -- cgit v1.2.3 From 664fcf123a30edf16b47d2ce1f610d654ba917b2 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 16 Oct 2016 19:56:51 +0200 Subject: net: phy: Threaded interrupts allow some simplification The PHY interrupts are now handled in a threaded interrupt handler, which can sleep. The work queue is no longer needed, phy_change() can be called directly. phy_mac_interrupt() still needs to be safe to call in interrupt context, so keep the work queue, and use a helper to call phy_change(). Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index e25f1830fbcf..c47378c93607 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -343,7 +343,7 @@ struct phy_c45_device_ids { * giving up on the current attempt at acquiring a link * irq: IRQ number of the PHY's interrupt (-1 if none) * phy_timer: The timer for handling the state machine - * phy_queue: A work_queue for the interrupt + * phy_queue: A work_queue for the phy_mac_interrupt * attached_dev: The attached enet driver's device instance ptr * adjust_link: Callback for the enet controller to respond to * changes in the link state. @@ -802,7 +802,8 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_state_machine(struct work_struct *work); -void phy_change(struct work_struct *work); +void phy_change(struct phy_device *phydev); +void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev, int new_link); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); -- cgit v1.2.3 From 1a3f060c1a47dba4e12ac21ce62b57666b9c4e95 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 17 Oct 2016 19:15:44 -0700 Subject: net: Introduce new api for walking upper and lower devices This patch introduces netdev_walk_all_upper_dev_rcu, netdev_walk_all_lower_dev and netdev_walk_all_lower_dev_rcu. These functions recursively walk the adj_list of devices to determine all upper and lower devices. The functions take a callback function that is invoked for each device in the list. If the callback returns non-0, the walk is terminated and the functions return that code back to callers. v3 - simplified netdev_has_upper_dev_all_rcu and __netdev_has_upper_dev and removed typecast as suggested by Stephen v2 - fixed definition of netdev_next_lower_dev_rcu to mirror the upper_dev version. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bf341b65ca5e..a5902d995907 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3778,6 +3778,14 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, updev; \ updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter))) +int netdev_walk_all_upper_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *upper_dev, + void *data), + void *data); + +bool netdev_has_upper_dev_all_rcu(struct net_device *dev, + struct net_device *upper_dev); + void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter); void *netdev_lower_get_next_private_rcu(struct net_device *dev, @@ -3821,6 +3829,15 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, ldev; \ ldev = netdev_all_lower_get_next_rcu(dev, &(iter))) +int netdev_walk_all_lower_dev(struct net_device *dev, + int (*fn)(struct net_device *lower_dev, + void *data), + void *data); +int netdev_walk_all_lower_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *lower_dev, + void *data), + void *data); + void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); -- cgit v1.2.3 From f1170fd462c67c4ae2f20734566d94e0f8f62f69 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 17 Oct 2016 19:15:51 -0700 Subject: net: Remove all_adj_list and its references Only direct adjacencies are maintained. All upper or lower devices can be learned via the new walk API which recursively walks the adj_list for upper devices or lower devices. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a5902d995907..458c87631e7f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1456,7 +1456,6 @@ enum netdev_priv_flags { * @ptype_specific: Device-specific, protocol-specific packet handlers * * @adj_list: Directly linked devices, like slaves for bonding - * @all_adj_list: All linked devices, *including* neighbours * @features: Currently active device features * @hw_features: User-changeable features * @@ -1675,11 +1674,6 @@ struct net_device { struct list_head lower; } adj_list; - struct { - struct list_head upper; - struct list_head lower; - } all_adj_list; - netdev_features_t features; netdev_features_t hw_features; netdev_features_t wanted_features; @@ -3771,13 +3765,6 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, updev; \ updev = netdev_upper_get_next_dev_rcu(dev, &(iter))) -/* iterate through upper list, must be called under RCU read lock */ -#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \ - for (iter = &(dev)->all_adj_list.upper, \ - updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \ - updev; \ - updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter))) - int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *upper_dev, void *data), @@ -3817,18 +3804,6 @@ struct net_device *netdev_all_lower_get_next(struct net_device *dev, struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, struct list_head **iter); -#define netdev_for_each_all_lower_dev(dev, ldev, iter) \ - for (iter = (dev)->all_adj_list.lower.next, \ - ldev = netdev_all_lower_get_next(dev, &(iter)); \ - ldev; \ - ldev = netdev_all_lower_get_next(dev, &(iter))) - -#define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \ - for (iter = (dev)->all_adj_list.lower.next, \ - ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \ - ldev; \ - ldev = netdev_all_lower_get_next_rcu(dev, &(iter))) - int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, void *data), -- cgit v1.2.3 From 1f9127caece42514a47011326b83ad93d95cd5d7 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Mon, 17 Oct 2016 10:49:54 -0500 Subject: net: phy: Create phy_supported_speeds function which lists speeds currently supported by a phydevice phy_supported_speeds provides a means to get a list of all the speeds a phy device currently supports. Signed-off-by: Zach Brown Signed-off-by: David S. Miller --- include/linux/phy.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index c47378c93607..4b6c246c63bb 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -84,6 +84,21 @@ typedef enum { PHY_INTERFACE_MODE_MAX, } phy_interface_t; +/** + * phy_supported_speeds - return all speeds currently supported by a phy device + * @phy: The phy device to return supported speeds of. + * @speeds: buffer to store supported speeds in. + * @size: size of speeds buffer. + * + * Description: Returns the number of supported speeds, and + * fills the speeds * buffer with the supported speeds. If speeds buffer is + * too small to contain * all currently supported speeds, will return as + * many speeds as can fit. + */ +unsigned int phy_supported_speeds(struct phy_device *phy, + unsigned int *speeds, + unsigned int size); + /** * It maps 'enum phy_interface_t' found in include/linux/phy.h * into the device tree binding of 'phy-mode', so that Ethernet -- cgit v1.2.3 From 2e0bc452f4721520502575362a9cd3c1248d2337 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Mon, 17 Oct 2016 10:49:55 -0500 Subject: net: phy: leds: add support for led triggers on phy link state change Create an option CONFIG_LED_TRIGGER_PHY (default n), which will create a set of led triggers for each instantiated PHY device. There is one LED trigger per link-speed, per-phy. The triggers are registered during phy_attach and unregistered during phy_detach. This allows for a user to configure their system to allow a set of LEDs not controlled by the phy to represent link state changes on the phy. LEDS controlled by the phy are unaffected. For example, we have a board where some of the leds in the RJ45 socket are controlled by the phy, but others are not. Using the triggers provided by this patch the leds not controlled by the phy can be configured to show the current speed of the ethernet connection. The leds controlled by the phy are unaffected. Signed-off-by: Josh Cartwright Signed-off-by: Nathan Sullivan Signed-off-by: Zach Brown Signed-off-by: David S. Miller --- include/linux/phy.h | 7 ++++++ include/linux/phy_led_triggers.h | 51 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) create mode 100644 include/linux/phy_led_triggers.h (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 4b6c246c63bb..e7e1fd382564 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -25,6 +25,7 @@ #include #include #include +#include #include @@ -420,6 +421,12 @@ struct phy_device { int link_timeout; +#ifdef CONFIG_LED_TRIGGER_PHY + struct phy_led_trigger *phy_led_triggers; + unsigned int phy_num_led_triggers; + struct phy_led_trigger *last_triggered; +#endif + /* * Interrupt number for this PHY * -1 means no interrupt diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h new file mode 100644 index 000000000000..a2daea0a37d2 --- /dev/null +++ b/include/linux/phy_led_triggers.h @@ -0,0 +1,51 @@ +/* Copyright (C) 2016 National Instruments 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; 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 __PHY_LED_TRIGGERS +#define __PHY_LED_TRIGGERS + +struct phy_device; + +#ifdef CONFIG_LED_TRIGGER_PHY + +#include + +#define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 10 +#define PHY_MII_BUS_ID_SIZE (20 - 3) + +#define PHY_LINK_LED_TRIGGER_NAME_SIZE (PHY_MII_BUS_ID_SIZE + \ + FIELD_SIZEOF(struct mdio_device, addr)+\ + PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE) + +struct phy_led_trigger { + struct led_trigger trigger; + char name[PHY_LINK_LED_TRIGGER_NAME_SIZE]; + unsigned int speed; +}; + + +extern int phy_led_triggers_register(struct phy_device *phy); +extern void phy_led_triggers_unregister(struct phy_device *phy); +extern void phy_led_trigger_change_speed(struct phy_device *phy); + +#else + +static inline int phy_led_triggers_register(struct phy_device *phy) +{ + return 0; +} +static inline void phy_led_triggers_unregister(struct phy_device *phy) { } +static inline void phy_led_trigger_change_speed(struct phy_device *phy) { } + +#endif + +#endif -- cgit v1.2.3 From 9a97434215819872b054c3d0c067e5e4fa768b0e Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Mon, 17 Oct 2016 21:45:29 +0200 Subject: ARM: pxa: enhance smc91x platform data Instead of having the smc91x driver relying on machine_is_*() calls, provide this data through platform data, ie. idp, mainstone and stargate. This way, the driver doesn't need anymore machine_is_*() calls, which wouldn't work anymore with a device-tree build. Signed-off-by: Robert Jarzmik Signed-off-by: David S. Miller --- include/linux/smc91x.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/smc91x.h b/include/linux/smc91x.h index e302c447e057..129bc674dcf5 100644 --- a/include/linux/smc91x.h +++ b/include/linux/smc91x.h @@ -39,6 +39,7 @@ struct smc91x_platdata { unsigned long flags; unsigned char leda; unsigned char ledb; + bool pxa_u16_align4; /* PXA buggy u16 writes on 4*n+2 addresses */ }; #endif /* __SMC91X_H__ */ -- cgit v1.2.3 From 57a09bf0a416700676e77102c28f9cfcb48267e0 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 18 Oct 2016 19:51:19 +0200 Subject: bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers A BPF program is required to check the return register of a map_elem_lookup() call before accessing memory. The verifier keeps track of this by converting the type of the result register from PTR_TO_MAP_VALUE_OR_NULL to PTR_TO_MAP_VALUE after a conditional jump ensures safety. This check is currently exclusively performed for the result register 0. In the event the compiler reorders instructions, BPF_MOV64_REG instructions may be moved before the conditional jump which causes them to keep their type PTR_TO_MAP_VALUE_OR_NULL to which the verifier objects when the register is accessed: 0: (b7) r1 = 10 1: (7b) *(u64 *)(r10 -8) = r1 2: (bf) r2 = r10 3: (07) r2 += -8 4: (18) r1 = 0x59c00000 6: (85) call 1 7: (bf) r4 = r0 8: (15) if r0 == 0x0 goto pc+1 R0=map_value(ks=8,vs=8) R4=map_value_or_null(ks=8,vs=8) R10=fp 9: (7a) *(u64 *)(r4 +0) = 0 R4 invalid mem access 'map_value_or_null' This commit extends the verifier to keep track of all identical PTR_TO_MAP_VALUE_OR_NULL registers after a map_elem_lookup() by assigning them an ID and then marking them all when the conditional jump is observed. Signed-off-by: Thomas Graf Reviewed-by: Josef Bacik Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- 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 7035b997aaa5..ac5b393ee6b2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -23,13 +23,13 @@ struct bpf_reg_state { * result in a bad access. */ u64 min_value, max_value; + u32 id; union { /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ s64 imm; /* valid when type == PTR_TO_PACKET* */ struct { - u32 id; u16 off; u16 range; }; -- cgit v1.2.3 From 8b6b4135e4fb2b537f33b811c13f77bee25ca8d3 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Thu, 20 Oct 2016 13:55:19 -0400 Subject: net: use core MTU range checking in WAN drivers - set min/max_mtu in all hdlc drivers, remove hdlc_change_mtu - sent max_mtu in lec driver, remove lec_change_mtu - set min/max_mtu in x25_asy driver CC: netdev@vger.kernel.org CC: Krzysztof Halasa CC: Krzysztof Halasa CC: Jan "Yenya" Kasprzak CC: Francois Romieu CC: Kevin Curtis CC: Zhao Qiang Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/linux/hdlc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdlc.h b/include/linux/hdlc.h index e31bcd4c7859..97585d9679f3 100644 --- a/include/linux/hdlc.h +++ b/include/linux/hdlc.h @@ -93,8 +93,6 @@ static __inline__ void debug_frame(const struct sk_buff *skb) int hdlc_open(struct net_device *dev); /* Must be called by hardware driver when HDLC device is being closed */ void hdlc_close(struct net_device *dev); -/* May be used by hardware driver */ -int hdlc_change_mtu(struct net_device *dev, int new_mtu); /* Must be pointed to by hw driver's dev->netdev_ops->ndo_start_xmit */ netdev_tx_t hdlc_start_xmit(struct sk_buff *skb, struct net_device *dev); -- cgit v1.2.3 From b3e3893e1253692c3d2b8e8ebd5a26183ed30443 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Thu, 20 Oct 2016 13:55:22 -0400 Subject: net: use core MTU range checking in misc drivers firewire-net: - set min/max_mtu - remove fwnet_change_mtu nes: - set max_mtu - clean up nes_netdev_change_mtu xpnet: - set min/max_mtu - remove xpnet_dev_change_mtu hippi: - set min/max_mtu - remove hippi_change_mtu batman-adv: - set max_mtu - remove batadv_interface_change_mtu - initialization is a little async, not 100% certain that max_mtu is set in the optimal place, don't have hardware to test with rionet: - set min/max_mtu - remove rionet_change_mtu slip: - set min/max_mtu - streamline sl_change_mtu um/net_kern: - remove pointless ndo_change_mtu hsi/clients/ssi_protocol: - use core MTU range checking - remove now redundant ssip_pn_set_mtu ipoib: - set a default max MTU value - Note: ipoib's actual max MTU can vary, depending on if the device is in connected mode or not, so we'll just set the max_mtu value to the max possible, and let the ndo_change_mtu function continue to validate any new MTU change requests with checks for CM or not. Note that ipoib has no min_mtu set, and thus, the network core's mtu > 0 check is the only lower bounds here. mptlan: - use net core MTU range checking - remove now redundant mpt_lan_change_mtu fddi: - min_mtu = 21, max_mtu = 4470 - remove now redundant fddi_change_mtu (including export) fjes: - min_mtu = 8192, max_mtu = 65536 - The max_mtu value is actually one over IP_MAX_MTU here, but the idea is to get past the core net MTU range checks so fjes_change_mtu can validate a new MTU against what it supports (see fjes_support_mtu in fjes_hw.c) hsr: - min_mtu = 0 (calls ether_setup, max_mtu is 1500) f_phonet: - min_mtu = 6, max_mtu = 65541 u_ether: - min_mtu = 14, max_mtu = 15412 phonet/pep-gprs: - min_mtu = 576, max_mtu = 65530 - remove redundant gprs_set_mtu CC: netdev@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: Stefan Richter CC: Faisal Latif CC: linux-rdma@vger.kernel.org CC: Cliff Whickman CC: Robin Holt CC: Jes Sorensen CC: Marek Lindner CC: Simon Wunderlich CC: Antonio Quartulli CC: Sathya Prakash CC: Chaitra P B CC: Suganath Prabu Subramani CC: MPT-FusionLinux.pdl@broadcom.com CC: Sebastian Reichel CC: Felipe Balbi CC: Arvid Brodin CC: Remi Denis-Courmont Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/linux/fddidevice.h | 1 - include/linux/hippidevice.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fddidevice.h b/include/linux/fddidevice.h index 9a79f0106da1..32c22cfb238b 100644 --- a/include/linux/fddidevice.h +++ b/include/linux/fddidevice.h @@ -26,7 +26,6 @@ #ifdef __KERNEL__ __be16 fddi_type_trans(struct sk_buff *skb, struct net_device *dev); -int fddi_change_mtu(struct net_device *dev, int new_mtu); struct net_device *alloc_fddidev(int sizeof_priv); #endif diff --git a/include/linux/hippidevice.h b/include/linux/hippidevice.h index 8ec23fb0b412..402f99e328d4 100644 --- a/include/linux/hippidevice.h +++ b/include/linux/hippidevice.h @@ -32,7 +32,6 @@ struct hippi_cb { }; __be16 hippi_type_trans(struct sk_buff *skb, struct net_device *dev); -int hippi_change_mtu(struct net_device *dev, int new_mtu); int hippi_mac_addr(struct net_device *dev, void *p); int hippi_neigh_setup_dev(struct net_device *dev, struct neigh_parms *p); struct net_device *alloc_hippi_dev(int sizeof_priv); -- cgit v1.2.3 From 2d0e30c30f84d08dc16f0f2af41f1b8a85f0755e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 21 Oct 2016 12:46:33 +0200 Subject: bpf: add helper for retrieving current numa node id Use case is mainly for soreuseport to select sockets for the local numa node, but since generic, lets also add this for other networking and tracing program types. Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- 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 c201017b5730..edcd96ded8aa 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -319,6 +319,7 @@ extern const struct bpf_func_proto bpf_map_delete_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; +extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; -- cgit v1.2.3 From 3cf25904fe467aebeaa77d402b6cf3c6c5d6303b Mon Sep 17 00:00:00 2001 From: Xo Wang Date: Fri, 21 Oct 2016 10:20:12 -0700 Subject: net: phy: broadcom: Update Auxiliary Control Register macros Add the RXD-to-RXC skew (delay) time bit in the Miscellaneous Control shadow register and a mask for the shadow selector field. Remove a re-definition of MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL. Signed-off-by: Xo Wang Reviewed-by: Florian Fainelli Reviewed-by: Joel Stanley Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index e3354b74286c..22c4421c916c 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -105,11 +105,12 @@ #define MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA 0x0800 #define MII_BCM54XX_AUXCTL_MISC_WREN 0x8000 +#define MII_BCM54XX_AUXCTL_MISC_RXD_RXC_SKEW 0x0100 #define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200 #define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC 0x7000 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007 -#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000 +#define MII_BCM54XX_AUXCTL_SHDWSEL_MASK 0x0007 /* * Broadcom LED source encodings. These are used in BCM5461, BCM5481, -- cgit v1.2.3 From d92ead16be405b6d52ff7b366d1c9865ccc684bd Mon Sep 17 00:00:00 2001 From: Xo Wang Date: Fri, 21 Oct 2016 10:20:13 -0700 Subject: net: phy: broadcom: Add support for BCM54612E This PHY has internal delays enabled after reset. This clears the internal delay enables unless the interface specifically requests them. Signed-off-by: Xo Wang Reviewed-by: Florian Fainelli Reviewed-by: Joel Stanley 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 22c4421c916c..60def78c4e12 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -18,6 +18,7 @@ #define PHY_ID_BCM5421 0x002060e0 #define PHY_ID_BCM5464 0x002060b0 #define PHY_ID_BCM5461 0x002060c0 +#define PHY_ID_BCM54612E 0x03625e60 #define PHY_ID_BCM54616S 0x03625d10 #define PHY_ID_BCM57780 0x03625d90 -- cgit v1.2.3 From 3f817fe718c6cb3ddcc2ab04ba86faecc20ef8fe Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:42:01 +0300 Subject: cfg80211: Define IEEE P802.11ai (FILS) information elements Define the Element IDs and Element ID Extensions from IEEE P802.11ai/D11.0. In addition, add a new cfg80211_find_ext_ie() wrapper to make it easier to find information elements that used the Element ID Extension field. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a80516fd65c8..d428adf51446 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1960,6 +1960,26 @@ enum ieee80211_eid { WLAN_EID_VENDOR_SPECIFIC = 221, WLAN_EID_QOS_PARAMETER = 222, + WLAN_EID_CAG_NUMBER = 237, + WLAN_EID_AP_CSN = 239, + WLAN_EID_FILS_INDICATION = 240, + WLAN_EID_DILS = 241, + WLAN_EID_FRAGMENT = 242, + WLAN_EID_EXTENSION = 255 +}; + +/* Element ID Extensions for Element ID 255 */ +enum ieee80211_eid_ext { + WLAN_EID_EXT_ASSOC_DELAY_INFO = 1, + WLAN_EID_EXT_FILS_REQ_PARAMS = 2, + WLAN_EID_EXT_FILS_KEY_CONFIRM = 3, + WLAN_EID_EXT_FILS_SESSION = 4, + WLAN_EID_EXT_FILS_HLP_CONTAINER = 5, + WLAN_EID_EXT_FILS_IP_ADDR_ASSIGN = 6, + WLAN_EID_EXT_KEY_DELIVERY = 7, + WLAN_EID_EXT_FILS_WRAPPED_DATA = 8, + WLAN_EID_EXT_FILS_PUBLIC_KEY = 12, + WLAN_EID_EXT_FILS_NONCE = 13, }; /* Action category code */ -- cgit v1.2.3 From 631810603a20874554b2f17adf42b72d0f15eda5 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:42:02 +0300 Subject: cfg80211: Add Fast Initial Link Setup (FILS) auth algs This defines authentication algorithms for FILS (IEEE 802.11ai). Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d428adf51446..793a0174ba29 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1576,6 +1576,9 @@ struct ieee80211_vht_operation { #define WLAN_AUTH_SHARED_KEY 1 #define WLAN_AUTH_FT 2 #define WLAN_AUTH_SAE 3 +#define WLAN_AUTH_FILS_SK 4 +#define WLAN_AUTH_FILS_SK_PFS 5 +#define WLAN_AUTH_FILS_PK 6 #define WLAN_AUTH_LEAP 128 #define WLAN_AUTH_CHALLENGE_LEN 128 -- cgit v1.2.3 From 348bd456699801920a309c66e382380809fbdf41 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:42:03 +0300 Subject: cfg80211: Add KEK/nonces for FILS association frames The new nl80211 attributes can be used to provide KEK and nonces to allow the driver to encrypt and decrypt FILS (Re)Association Request/Response frames in station mode. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 793a0174ba29..fe849329511a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2096,6 +2096,9 @@ enum ieee80211_key_len { #define IEEE80211_GCMP_MIC_LEN 16 #define IEEE80211_GCMP_PN_LEN 6 +#define FILS_NONCE_LEN 16 +#define FILS_MAX_KEK_LEN 64 + /* Public action codes */ enum ieee80211_pub_actioncode { WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4, -- cgit v1.2.3 From a07ea4d9941af5a0c6f0be2a71b51ac9c083c5e5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 24 Oct 2016 14:40:02 +0200 Subject: genetlink: no longer support using static family IDs Static family IDs have never really been used, the only use case was the workaround I introduced for those users that assumed their family ID was also their multicast group ID. Additionally, because static family IDs would never be reserved by the generic netlink code, using a relatively low ID would only work for built-in families that can be registered immediately after generic netlink is started, which is basically only the control family (apart from the workaround code, which I also had to add code for so it would reserve those IDs) Thus, anything other than GENL_ID_GENERATE is flawed and luckily not used except in the cases I mentioned. Move those workarounds into a few lines of code, and then get rid of GENL_ID_GENERATE entirely, making it more robust. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/genl_magic_func.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 667c31101b8b..7c070c1fe457 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -260,7 +260,6 @@ static struct genl_ops ZZZ_genl_ops[] __read_mostly = { */ #define ZZZ_genl_family CONCAT_(GENL_MAGIC_FAMILY, _genl_family) static struct genl_family ZZZ_genl_family __read_mostly = { - .id = GENL_ID_GENERATE, .name = __stringify(GENL_MAGIC_FAMILY), .version = GENL_MAGIC_VERSION, #ifdef GENL_MAGIC_FAMILY_HDRSZ -- cgit v1.2.3 From 489111e5c25b93be80340c3113d71903d7c82136 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 24 Oct 2016 14:40:03 +0200 Subject: genetlink: statically initialize families Instead of providing macros/inline functions to initialize the families, make all users initialize them statically and get rid of the macros. This reduces the kernel code size by about 1.6k on x86-64 (with allyesconfig). Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/drbd_genl.h | 2 +- include/linux/genl_magic_func.h | 28 ++++++++++++++++------------ 2 files changed, 17 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h index c934d3a96b5e..2896f93808ae 100644 --- a/include/linux/drbd_genl.h +++ b/include/linux/drbd_genl.h @@ -67,7 +67,7 @@ * genl_magic_func.h * generates an entry in the static genl_ops array, * and static register/unregister functions to - * genl_register_family_with_ops(). + * genl_register_family(). * * flags and handler: * GENL_op_init( .doit = x, .dumpit = y, .flags = something) diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 7c070c1fe457..40c2e39362c8 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -259,15 +259,7 @@ static struct genl_ops ZZZ_genl_ops[] __read_mostly = { * {{{2 */ #define ZZZ_genl_family CONCAT_(GENL_MAGIC_FAMILY, _genl_family) -static struct genl_family ZZZ_genl_family __read_mostly = { - .name = __stringify(GENL_MAGIC_FAMILY), - .version = GENL_MAGIC_VERSION, -#ifdef GENL_MAGIC_FAMILY_HDRSZ - .hdrsize = NLA_ALIGN(GENL_MAGIC_FAMILY_HDRSZ), -#endif - .maxattr = ARRAY_SIZE(drbd_tla_nl_policy)-1, -}; - +static struct genl_family ZZZ_genl_family; /* * Magic: define multicast groups * Magic: define multicast group registration helper @@ -301,11 +293,23 @@ static int CONCAT_(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)( \ #undef GENL_mc_group #define GENL_mc_group(group) +static struct genl_family ZZZ_genl_family __read_mostly = { + .name = __stringify(GENL_MAGIC_FAMILY), + .version = GENL_MAGIC_VERSION, +#ifdef GENL_MAGIC_FAMILY_HDRSZ + .hdrsize = NLA_ALIGN(GENL_MAGIC_FAMILY_HDRSZ), +#endif + .maxattr = ARRAY_SIZE(drbd_tla_nl_policy)-1, + .ops = ZZZ_genl_ops, + .n_ops = ARRAY_SIZE(ZZZ_genl_ops), + .mcgrps = ZZZ_genl_mcgrps, + .n_mcgrps = ARRAY_SIZE(ZZZ_genl_mcgrps), + .module = THIS_MODULE, +}; + int CONCAT_(GENL_MAGIC_FAMILY, _genl_register)(void) { - return genl_register_family_with_ops_groups(&ZZZ_genl_family, \ - ZZZ_genl_ops, \ - ZZZ_genl_mcgrps); + return genl_register_family(&ZZZ_genl_family); } void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void) -- cgit v1.2.3 From 56989f6d8568c21257dcec0f5e644d5570ba3281 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 24 Oct 2016 14:40:05 +0200 Subject: genetlink: mark families as __ro_after_init Now genl_register_family() is the only thing (other than the users themselves, perhaps, but I didn't find any doing that) writing to the family struct. In all families that I found, genl_register_family() is only called from __init functions (some indirectly, in which case I've add __init annotations to clarifly things), so all can actually be marked __ro_after_init. This protects the data structure from accidental corruption. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/genl_magic_func.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 40c2e39362c8..377257d8f7e3 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -293,7 +293,7 @@ static int CONCAT_(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)( \ #undef GENL_mc_group #define GENL_mc_group(group) -static struct genl_family ZZZ_genl_family __read_mostly = { +static struct genl_family ZZZ_genl_family __ro_after_init = { .name = __stringify(GENL_MAGIC_FAMILY), .version = GENL_MAGIC_VERSION, #ifdef GENL_MAGIC_FAMILY_HDRSZ -- cgit v1.2.3 From b917783c7b350518f8c5d88bb5848aa8064408a6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 26 Oct 2016 18:49:46 +0200 Subject: flow_dissector: __skb_get_hash_symmetric arg can be const Signed-off-by: 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 601258f6e621..663fda2887f7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1086,7 +1086,7 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) } void __skb_get_hash(struct sk_buff *skb); -u32 __skb_get_hash_symmetric(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); -- cgit v1.2.3 From 5579e1519bad43b874922dbe87c74fdcbd97a7db Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Wed, 31 Aug 2016 05:17:54 +0000 Subject: net/mlx5: Update struct mlx5_ifc_xrqc_bits Update struct mlx5_ifc_xrqc_bits according to last specification Signed-off-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6045d4d58065..12f72e45a3f0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2844,7 +2844,7 @@ struct mlx5_ifc_xrqc_bits { struct mlx5_ifc_tag_matching_topology_context_bits tag_matching_topology_context; - u8 reserved_at_180[0x200]; + u8 reserved_at_180[0x880]; struct mlx5_ifc_wq_bits wq; }; -- cgit v1.2.3 From dd257efb1e0f8875ed7e42b88837a8dada0d0e41 Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Wed, 31 Aug 2016 05:29:58 +0000 Subject: net/mlx5: Ensure SRQ physical address structure endianness SRQ physical address structure field should be in big-endian format. Signed-off-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Leon Romanovsky --- include/linux/mlx5/srq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index 33c97dc900f8..1cde0fd53f90 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -55,7 +55,7 @@ struct mlx5_srq_attr { u32 lwm; u32 user_index; u64 db_record; - u64 *pas; + __be64 *pas; }; struct mlx5_core_dev; -- cgit v1.2.3 From 813f854053c26204e2723c498def4c7870dcc7f4 Mon Sep 17 00:00:00 2001 From: Mohamad Haj Yahia Date: Thu, 11 Aug 2016 11:21:39 +0300 Subject: net/mlx5: Introduce TSAR manipulation firmware commands TSAR (stands for Transmit Scheduling ARbiter) is a hardware component that is responsible for selecting the next entity to serve on the transmit path. The arbitration defines the QoS policy between the agents connected to the TSAR. The TSAR is a consist two main features: 1) BW Allocation between agents: The TSAR implements a defecit weighted round robin between the agents. Each agent attached to the TSAR is assigned with a weight and it is awarded transmission tokens according to this weight. 2) Rate limer per agent: Each agent attached to the TSAR is (optionally) assigned with a rate limit. TSAR will not allow scheduling for an agent exceeding its defined rate limit. In this patch we implement the API of manipulating the TSAR. Signed-off-by: Mohamad Haj Yahia Signed-off-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 199 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 195 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 12f72e45a3f0..2632cb2caf10 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -145,6 +145,12 @@ enum { MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773, MLX5_CMD_OP_SET_RATE_LIMIT = 0x780, MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781, + MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT = 0x782, + MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT = 0x783, + MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT = 0x784, + MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT = 0x785, + MLX5_CMD_OP_CREATE_QOS_PARA_VPORT = 0x786, + MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT = 0x787, MLX5_CMD_OP_ALLOC_PD = 0x800, MLX5_CMD_OP_DEALLOC_PD = 0x801, MLX5_CMD_OP_ALLOC_UAR = 0x802, @@ -537,13 +543,27 @@ struct mlx5_ifc_e_switch_cap_bits { struct mlx5_ifc_qos_cap_bits { u8 packet_pacing[0x1]; - u8 reserved_0[0x1f]; - u8 reserved_1[0x20]; + u8 esw_scheduling[0x1]; + u8 reserved_at_2[0x1e]; + + u8 reserved_at_20[0x20]; + u8 packet_pacing_max_rate[0x20]; + u8 packet_pacing_min_rate[0x20]; - u8 reserved_2[0x10]; + + u8 reserved_at_80[0x10]; u8 packet_pacing_rate_table_size[0x10]; - u8 reserved_3[0x760]; + + u8 esw_element_type[0x10]; + u8 esw_tsar_type[0x10]; + + u8 reserved_at_c0[0x10]; + u8 max_qos_para_vport[0x10]; + + u8 max_tsar_bw_share[0x20]; + + u8 reserved_at_100[0x700]; }; struct mlx5_ifc_per_protocol_networking_offload_caps_bits { @@ -2333,6 +2353,30 @@ struct mlx5_ifc_sqc_bits { struct mlx5_ifc_wq_bits wq; }; +enum { + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR = 0x0, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT = 0x1, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC = 0x2, + SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3, +}; + +struct mlx5_ifc_scheduling_context_bits { + u8 element_type[0x8]; + u8 reserved_at_8[0x18]; + + u8 element_attributes[0x20]; + + u8 parent_element_id[0x20]; + + u8 reserved_at_60[0x40]; + + u8 bw_share[0x20]; + + u8 max_average_bw[0x20]; + + u8 reserved_at_e0[0x120]; +}; + struct mlx5_ifc_rqtc_bits { u8 reserved_at_0[0xa0]; @@ -2920,6 +2964,29 @@ struct mlx5_ifc_register_loopback_control_bits { u8 reserved_at_20[0x60]; }; +struct mlx5_ifc_vport_tc_element_bits { + u8 traffic_class[0x4]; + u8 reserved_at_4[0xc]; + u8 vport_number[0x10]; +}; + +struct mlx5_ifc_vport_element_bits { + u8 reserved_at_0[0x10]; + u8 vport_number[0x10]; +}; + +enum { + TSAR_ELEMENT_TSAR_TYPE_DWRR = 0x0, + TSAR_ELEMENT_TSAR_TYPE_ROUND_ROBIN = 0x1, + TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2, +}; + +struct mlx5_ifc_tsar_element_bits { + u8 reserved_at_0[0x8]; + u8 tsar_type[0x8]; + u8 reserved_at_10[0x10]; +}; + struct mlx5_ifc_teardown_hca_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -3540,6 +3607,39 @@ struct mlx5_ifc_query_special_contexts_in_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_query_scheduling_element_out_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0xc0]; + + struct mlx5_ifc_scheduling_context_bits scheduling_context; + + u8 reserved_at_300[0x100]; +}; + +enum { + SCHEDULING_HIERARCHY_E_SWITCH = 0x2, +}; + +struct mlx5_ifc_query_scheduling_element_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 scheduling_hierarchy[0x8]; + u8 reserved_at_48[0x18]; + + u8 scheduling_element_id[0x20]; + + u8 reserved_at_80[0x180]; +}; + struct mlx5_ifc_query_rqt_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -4725,6 +4825,43 @@ struct mlx5_ifc_modify_sq_in_bits { struct mlx5_ifc_sqc_bits ctx; }; +struct mlx5_ifc_modify_scheduling_element_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x1c0]; +}; + +enum { + MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE = 0x1, + MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW = 0x2, +}; + +struct mlx5_ifc_modify_scheduling_element_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 scheduling_hierarchy[0x8]; + u8 reserved_at_48[0x18]; + + u8 scheduling_element_id[0x20]; + + u8 reserved_at_80[0x20]; + + u8 modify_bitmask[0x20]; + + u8 reserved_at_c0[0x40]; + + struct mlx5_ifc_scheduling_context_bits scheduling_context; + + u8 reserved_at_300[0x100]; +}; + struct mlx5_ifc_modify_rqt_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -5390,6 +5527,30 @@ struct mlx5_ifc_destroy_sq_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_destroy_scheduling_element_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x1c0]; +}; + +struct mlx5_ifc_destroy_scheduling_element_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 scheduling_hierarchy[0x8]; + u8 reserved_at_48[0x18]; + + u8 scheduling_element_id[0x20]; + + u8 reserved_at_80[0x180]; +}; + struct mlx5_ifc_destroy_rqt_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -6017,6 +6178,36 @@ struct mlx5_ifc_create_sq_in_bits { struct mlx5_ifc_sqc_bits ctx; }; +struct mlx5_ifc_create_scheduling_element_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + u8 scheduling_element_id[0x20]; + + u8 reserved_at_a0[0x160]; +}; + +struct mlx5_ifc_create_scheduling_element_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 scheduling_hierarchy[0x8]; + u8 reserved_at_48[0x18]; + + u8 reserved_at_60[0xa0]; + + struct mlx5_ifc_scheduling_context_bits scheduling_context; + + u8 reserved_at_300[0x100]; +}; + struct mlx5_ifc_create_rqt_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; -- cgit v1.2.3 From 74491de937125d0c98c9b9c9208b4105717a3caa Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Wed, 31 Aug 2016 11:24:25 +0000 Subject: net/mlx5: Add multi dest support Currently when calling mlx5_add_flow_rule we accept only one flow destination, this commit allows to pass multiple destinations. This change forces us to change the return structure to a more flexible one. We introduce a flow handle (struct mlx5_flow_handle), it holds internally the number for rules created and holds an array where each cell points the to a flow rule. From the consumers (of mlx5_add_flow_rule) point of view this change is only cosmetic and requires only to change the type of the returned value they store. From the core point of view, we now need to use a loop when allocating and deleting rules (e.g given to us a flow handler). Signed-off-by: Mark Bloch Signed-off-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 93ebc5e21334..0dcd287f4bd0 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -69,8 +69,8 @@ enum mlx5_flow_namespace_type { struct mlx5_flow_table; struct mlx5_flow_group; -struct mlx5_flow_rule; struct mlx5_flow_namespace; +struct mlx5_flow_handle; struct mlx5_flow_spec { u8 match_criteria_enable; @@ -127,18 +127,20 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); /* Single destination per rule. * Group ID is implied by the match criteria. */ -struct mlx5_flow_rule * -mlx5_add_flow_rule(struct mlx5_flow_table *ft, - struct mlx5_flow_spec *spec, - u32 action, - u32 flow_tag, - struct mlx5_flow_destination *dest); -void mlx5_del_flow_rule(struct mlx5_flow_rule *fr); - -int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, - struct mlx5_flow_destination *dest); - -struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_rule *rule); +struct mlx5_flow_handle * +mlx5_add_flow_rules(struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec, + u32 action, + u32 flow_tag, + struct mlx5_flow_destination *dest, + int dest_num); +void mlx5_del_flow_rules(struct mlx5_flow_handle *fr); + +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 c62cce2caee558e18aa05c01c2fd3b40f07174f2 Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Mon, 24 Oct 2016 18:29:13 -0700 Subject: net: add an ioctl to get a socket network namespace Each socket operates in a network namespace where it has been created, so if we want to dump and restore a socket, we have to know its network namespace. We have a socket_diag to get information about sockets, it doesn't report sockets which are not bound or connected. This patch introduces a new socket ioctl, which is called SIOCGSKNS and used to get a file descriptor for a socket network namespace. A task must have CAP_NET_ADMIN in a target network namespace to use this ioctl. Cc: "David S. Miller" Cc: Eric W. Biederman Signed-off-by: Andrei Vagin Signed-off-by: David S. Miller --- include/linux/proc_fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index b97bf2ef996e..368c7ad06ae5 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -82,4 +82,8 @@ static inline struct proc_dir_entry *proc_net_mkdir( return proc_mkdir_data(name, 0, parent, net); } +struct ns_common; +int open_related_ns(struct ns_common *ns, + struct ns_common *(*get_ns)(struct ns_common *ns)); + #endif /* _LINUX_PROC_FS_H */ -- cgit v1.2.3 From 9cf1f6a8c4cbb7836b838b51b3b02ddf32c6c6a0 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 28 Oct 2016 11:43:20 -0400 Subject: net: Move functions for configuring traffic classes out of inline headers The functions for configuring the traffic class to queue mappings have other effects that need to be addressed. Instead of trying to export a bunch of new functions just relocate the functions so that we can instrument them directly with the functionality they will need. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 31 +++---------------------------- 1 file changed, 3 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 20ce8df115ac..e05ab3bd48d2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1920,34 +1920,9 @@ int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) return 0; } -static inline -void netdev_reset_tc(struct net_device *dev) -{ - dev->num_tc = 0; - memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); - memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); -} - -static inline -int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) -{ - if (tc >= dev->num_tc) - return -EINVAL; - - dev->tc_to_txq[tc].count = count; - dev->tc_to_txq[tc].offset = offset; - return 0; -} - -static inline -int netdev_set_num_tc(struct net_device *dev, u8 num_tc) -{ - if (num_tc > TC_MAX_QUEUE) - return -EINVAL; - - dev->num_tc = num_tc; - return 0; -} +void netdev_reset_tc(struct net_device *dev); +int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset); +int netdev_set_num_tc(struct net_device *dev, u8 num_tc); static inline int netdev_get_num_tc(struct net_device *dev) -- cgit v1.2.3 From 8d059b0f6f5b1d3acf829454e1087818ad660058 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 28 Oct 2016 11:43:49 -0400 Subject: net: Add sysfs value to determine queue traffic class Add a sysfs attribute for a Tx queue that allows us to determine the traffic class for a given queue. This will allow us to more easily determine this in the future. It is needed as XPS will take the traffic class for a group of queues into account in order to avoid pulling traffic from one traffic class into another. Signed-off-by: Alexander Duyck 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 e05ab3bd48d2..d91a41860614 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1920,6 +1920,7 @@ int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) return 0; } +int netdev_txq_to_tc(struct net_device *dev, unsigned int txq); void netdev_reset_tc(struct net_device *dev); int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset); int netdev_set_num_tc(struct net_device *dev, u8 num_tc); -- cgit v1.2.3 From 184c449f91fef521042970cca46bd5cdfc0e3a37 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 28 Oct 2016 11:50:13 -0400 Subject: net: Add support for XPS with QoS via traffic classes This patch adds support for setting and using XPS when QoS via traffic classes is enabled. With this change we will factor in the priority and traffic class mapping of the packet and use that information to correctly select the queue. This allows us to define a set of queues for a given traffic class via mqprio and then configure the XPS mapping for those queues so that the traffic flows can avoid head-of-line blocking between the individual CPUs if so desired. Signed-off-by: Alexander Duyck 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 d91a41860614..66fd61c681d9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -732,8 +732,8 @@ struct xps_dev_maps { struct rcu_head rcu; struct xps_map __rcu *cpu_map[0]; }; -#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ - (nr_cpu_ids * sizeof(struct xps_map *))) +#define XPS_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ + (nr_cpu_ids * (_tcs) * sizeof(struct xps_map *))) #endif /* CONFIG_XPS */ #define TC_MAX_QUEUE 16 -- cgit v1.2.3 From 0fefbfbaad298162737d5418eb85065879f99b3e Mon Sep 17 00:00:00 2001 From: Sudarsana Kalluru Date: Mon, 31 Oct 2016 07:14:21 +0200 Subject: qed*: Management firmware - notifications and defaults Management firmware is interested in various tidbits about the driver - including the driver state & several configuration related fields [MTU, primtary MAC, etc.]. This adds the necessray logic to update MFW with such configurations, some of which are passed directly via qed while for others APIs are provide so that qede would be able to later configure if needed. This also introduces a new default configuration for MTU which would replace the default inherited by being an ethernet device. Signed-off-by: Sudarsana Kalluru Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8978a60371f4..5c909cd02764 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -267,6 +267,7 @@ struct qed_dev_info { u8 mf_mode; bool tx_switching; bool rdma_supported; + u16 mtu; }; enum qed_sb_type { @@ -554,6 +555,33 @@ struct qed_common_ops { */ int (*set_led)(struct qed_dev *cdev, enum qed_led_mode mode); + +/** + * @brief update_drv_state - API to inform the change in the driver state. + * + * @param cdev + * @param active + * + */ + int (*update_drv_state)(struct qed_dev *cdev, bool active); + +/** + * @brief update_mac - API to inform the change in the mac address + * + * @param cdev + * @param mac + * + */ + int (*update_mac)(struct qed_dev *cdev, u8 *mac); + +/** + * @brief update_mtu - API to inform the change in the mtu + * + * @param cdev + * @param mtu + * + */ + int (*update_mtu)(struct qed_dev *cdev, u16 mtu); }; #define MASK_FIELD(_name, _value) \ -- cgit v1.2.3 From 7a4b21b7d1f0644456501e33d3917c9aaee76a75 Mon Sep 17 00:00:00 2001 From: "Mintz, Yuval" Date: Mon, 31 Oct 2016 07:14:22 +0200 Subject: qed: Add nvram selftest Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 5c909cd02764..ffc2d2f5e88f 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -402,6 +402,15 @@ struct qed_selftest_ops { * @return 0 on success, error otherwise. */ int (*selftest_clock)(struct qed_dev *cdev); + +/** + * @brief selftest_nvram - Perform nvram test + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*selftest_nvram) (struct qed_dev *cdev); }; struct qed_common_ops { -- cgit v1.2.3 From 14d39648cbfc6289e3f873d30f282b9517ebe860 Mon Sep