From b01a60be7a4a161ac0a11df30569d21a20795aef Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 5 Jul 2013 17:43:56 +0200 Subject: ssb: fix alignment of struct bcma_device_id The ARM OABI and EABI disagree on the alignment of structures with small members, so module init tools may interpret the ssb device table incorrectly, as shown by this warning when building the b43 device driver in an OABI kernel: FATAL: drivers/net/wireless/b43/b43: sizeof(struct ssb_device_id)=6 is not a modulo of the size of section __mod_ssb_device_table=88. Forcing the default (EABI) alignment on the structure makes this problem go away. Since the ssb_device_id may have the same problem, better fix both structures. Signed-off-by: Arnd Bergmann Cc: Russell King Cc: John W. Linville Cc: Michael Buesch Cc: Larry Finger Signed-off-by: John W. Linville --- include/linux/mod_devicetable.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index b62d4af6c667..45e921401b06 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -361,7 +361,8 @@ struct ssb_device_id { __u16 vendor; __u16 coreid; __u8 revision; -}; + __u8 __pad; +} __attribute__((packed, aligned(2))); #define SSB_DEVICE(_vendor, _coreid, _revision) \ { .vendor = _vendor, .coreid = _coreid, .revision = _revision, } #define SSB_DEVTABLE_END \ @@ -377,7 +378,7 @@ struct bcma_device_id { __u16 id; __u8 rev; __u8 class; -}; +} __attribute__((packed,aligned(2))); #define BCMA_CORE(_manuf, _id, _rev, _class) \ { .manuf = _manuf, .id = _id, .rev = _rev, .class = _class, } #define BCMA_CORETABLE_END \ -- cgit v1.2.2 From 0699a73af3811b66b1ab5650575acee5eea841ab Mon Sep 17 00:00:00 2001 From: Clemens Ladisch Date: Mon, 22 Jul 2013 21:32:09 +0200 Subject: firewire: fix libdc1394/FlyCap2 iso event regression Commit 18d627113b83 (firewire: prevent dropping of completed iso packet header data) was intended to be an obvious bug fix, but libdc1394 and FlyCap2 depend on the old behaviour by ignoring all returned information and thus not noticing that not all packets have been received yet. The result was that the video frame buffers would be saved before they contained the correct data. Reintroduce the old behaviour for old clients. Tested-by: Stepan Salenikovich Tested-by: Josep Bosch Cc: # 3.4+ Signed-off-by: Clemens Ladisch Signed-off-by: Stefan Richter --- include/linux/firewire.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 3b0e820375ab..5d7782e42b8f 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -436,6 +436,7 @@ struct fw_iso_context { int type; int channel; int speed; + bool drop_overflow_headers; size_t header_size; union { fw_iso_callback_t sc; -- cgit v1.2.2 From 148519120c6d1f19ad53349683aeae9f228b0b8d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 27 Jul 2013 01:41:34 +0200 Subject: Revert "cpuidle: Quickly notice prediction failure for repeat mode" Revert commit 69a37bea (cpuidle: Quickly notice prediction failure for repeat mode), because it has been identified as the source of a significant performance regression in v3.8 and later as explained by Jeremy Eder: We believe we've identified a particular commit to the cpuidle code that seems to be impacting performance of variety of workloads. The simplest way to reproduce is using netperf TCP_RR test, so we're using that, on a pair of Sandy Bridge based servers. We also have data from a large database setup where performance is also measurably/positively impacted, though that test data isn't easily share-able. Included below are test results from 3 test kernels: kernel reverts ----------------------------------------------------------- 1) vanilla upstream (no reverts) 2) perfteam2 reverts e11538d1f03914eb92af5a1a378375c05ae8520c 3) test reverts 69a37beabf1f0a6705c08e879bdd5d82ff6486c4 e11538d1f03914eb92af5a1a378375c05ae8520c In summary, netperf TCP_RR numbers improve by approximately 4% after reverting 69a37beabf1f0a6705c08e879bdd5d82ff6486c4. When 69a37beabf1f0a6705c08e879bdd5d82ff6486c4 is included, C0 residency never seems to get above 40%. Taking that patch out gets C0 near 100% quite often, and performance increases. The below data are histograms representing the %c0 residency @ 1-second sample rates (using turbostat), while under netperf test. - If you look at the first 4 histograms, you can see %c0 residency almost entirely in the 30,40% bin. - The last pair, which reverts 69a37beabf1f0a6705c08e879bdd5d82ff6486c4, shows %c0 in the 80,90,100% bins. Below each kernel name are netperf TCP_RR trans/s numbers for the particular kernel that can be disclosed publicly, comparing the 3 test kernels. We ran a 4th test with the vanilla kernel where we've also set /dev/cpu_dma_latency=0 to show overall impact boosting single-threaded TCP_RR performance over 11% above baseline. 3.10-rc2 vanilla RX + c0 lock (/dev/cpu_dma_latency=0): TCP_RR trans/s 54323.78 ----------------------------------------------------------- 3.10-rc2 vanilla RX (no reverts) TCP_RR trans/s 48192.47 Receiver %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 59]: *********************************************************** 40.0000 - 50.0000 [ 1]: * 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: Sender %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 11]: *********** 40.0000 - 50.0000 [ 49]: ************************************************* 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: ----------------------------------------------------------- 3.10-rc2 perfteam2 RX (reverts commit e11538d1f03914eb92af5a1a378375c05ae8520c) TCP_RR trans/s 49698.69 Receiver %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 1]: * 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 59]: *********************************************************** 40.0000 - 50.0000 [ 0]: 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: Sender %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 2]: ** 40.0000 - 50.0000 [ 58]: ********************************************************** 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: ----------------------------------------------------------- 3.10-rc2 test RX (reverts 69a37beabf1f0a6705c08e879bdd5d82ff6486c4 and e11538d1f03914eb92af5a1a378375c05ae8520c) TCP_RR trans/s 47766.95 Receiver %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 1]: * 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 27]: *************************** 40.0000 - 50.0000 [ 2]: ** 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 2]: ** 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 28]: **************************** Sender: 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 11]: *********** 40.0000 - 50.0000 [ 0]: 50.0000 - 60.0000 [ 1]: * 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 3]: *** 80.0000 - 90.0000 [ 7]: ******* 90.0000 - 100.0000 [ 38]: ************************************** These results demonstrate gaining back the tendency of the CPU to stay in more responsive, performant C-states (and thus yield measurably better performance), by reverting commit 69a37beabf1f0a6705c08e879bdd5d82ff6486c4. Requested-by: Jeremy Eder Tested-by: Len Brown Cc: 3.8+ Signed-off-by: Rafael J. Wysocki --- include/linux/tick.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 9180f4b85e6d..62bd8b72873c 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -174,10 +174,4 @@ static inline void tick_nohz_task_switch(struct task_struct *tsk) { } #endif -# ifdef CONFIG_CPU_IDLE_GOV_MENU -extern void menu_hrtimer_cancel(void); -# else -static inline void menu_hrtimer_cancel(void) {} -# endif /* CONFIG_CPU_IDLE_GOV_MENU */ - #endif -- cgit v1.2.2 From 2b44c4db2e2f1765d35163a861d301038e0c8a75 Mon Sep 17 00:00:00 2001 From: Colin Cross Date: Wed, 24 Jul 2013 17:41:33 -0700 Subject: freezer: set PF_SUSPEND_TASK flag on tasks that call freeze_processes Calling freeze_processes sets a global flag that will cause any process that calls try_to_freeze to enter the refrigerator. It skips sending a signal to the current task, but if the current task ever hits try_to_freeze, all threads will be frozen and the system will deadlock. Set a new flag, PF_SUSPEND_TASK, on the task that calls freeze_processes. The flag notifies the freezer that the thread is involved in suspend and should not be frozen. Also add a WARN_ON in thaw_processes if the caller does not have the PF_SUSPEND_TASK flag set to catch if a different task calls thaw_processes than the one that called freeze_processes, leaving a task with PF_SUSPEND_TASK permanently set on it. Threads that spawn off a task with PF_SUSPEND_TASK set (which swsusp does) will also have PF_SUSPEND_TASK set, preventing them from freezing while they are helping with suspend, but they need to be dead by the time suspend is triggered, otherwise they may run when userspace is expected to be frozen. Add a WARN_ON in thaw_processes if more than one thread has the PF_SUSPEND_TASK flag set. Reported-and-tested-by: Michael Leun Signed-off-by: Colin Cross Signed-off-by: Rafael J. Wysocki --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 50d04b92ceda..d722490da030 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1628,6 +1628,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ +#define PF_SUSPEND_TASK 0x80000000 /* this thread called freeze_processes and should not be frozen */ /* * Only the _current_ task can read/write to tsk->flags, but other -- cgit v1.2.2 From cd23b14b654769db83c9684ae1ba32c0e066670f Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 18 Jul 2013 15:31:08 +0300 Subject: mlx5_core: Implement new initialization sequence Introduce enbale_hca and disable_hca commands to signify when the driver starts or ceases to operate on the device. In addition the driver will use boot and init pages count; boot pages is required to allow firmware to complete boot commands and the other to complete init hca. Command interface revision is bumped to 4 to enforce using supported firmware. This patch breaks compatibility with old versions of firmware (< 4); however, the first GA firmware we will publish will support version 4 so this should not be a problem. Signed-off-by: Eli Cohen Signed-off-by: Roland Dreier --- include/linux/mlx5/device.h | 20 ++++++++++++++++++++ include/linux/mlx5/driver.h | 4 +++- 2 files changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8de8d8f22384..737685e9e852 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -690,6 +690,26 @@ struct mlx5_query_cq_mbox_out { __be64 pas[0]; }; +struct mlx5_enable_hca_mbox_in { + struct mlx5_inbox_hdr hdr; + u8 rsvd[8]; +}; + +struct mlx5_enable_hca_mbox_out { + struct mlx5_outbox_hdr hdr; + u8 rsvd[8]; +}; + +struct mlx5_disable_hca_mbox_in { + struct mlx5_inbox_hdr hdr; + u8 rsvd[8]; +}; + +struct mlx5_disable_hca_mbox_out { + struct mlx5_outbox_hdr hdr; + u8 rsvd[8]; +}; + struct mlx5_eq_context { u8 status; u8 ec_oi; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f22e4419839b..2aa258b0ced1 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -101,6 +101,8 @@ enum { MLX5_CMD_OP_QUERY_ADAPTER = 0x101, MLX5_CMD_OP_INIT_HCA = 0x102, MLX5_CMD_OP_TEARDOWN_HCA = 0x103, + MLX5_CMD_OP_ENABLE_HCA = 0x104, + MLX5_CMD_OP_DISABLE_HCA = 0x105, MLX5_CMD_OP_QUERY_PAGES = 0x107, MLX5_CMD_OP_MANAGE_PAGES = 0x108, MLX5_CMD_OP_SET_HCA_CAP = 0x109, @@ -690,7 +692,7 @@ int mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, s16 npages); -int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev); +int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev); void mlx5_register_debugfs(void); void mlx5_unregister_debugfs(void); -- cgit v1.2.2 From 22f2020f84c6da2dd0acb2dce12e39e59ff7c8be Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 31 Jul 2013 13:53:48 -0700 Subject: vmpressure: change vmpressure::sr_lock to spinlock There is nothing that can sleep inside critical sections protected by this lock and those sections are really small so there doesn't make much sense to use mutex for them. Change the log to a spinlock Signed-off-by: Michal Hocko Reported-by: Tejun Heo Cc: Anton Vorontsov Cc: Johannes Weiner Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Li Zefan Reviewed-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmpressure.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h index 76be077340ea..2081680e015d 100644 --- a/include/linux/vmpressure.h +++ b/include/linux/vmpressure.h @@ -12,7 +12,7 @@ struct vmpressure { unsigned long scanned; unsigned long reclaimed; /* The lock is used to keep the scanned/reclaimed above in sync. */ - struct mutex sr_lock; + struct spinlock sr_lock; /* The list of vmpressure_event structs. */ struct list_head events; -- cgit v1.2.2 From 33cb876e947b9ddda8dca3fb99234b743a597ef9 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 31 Jul 2013 13:53:51 -0700 Subject: vmpressure: make sure there are no events queued after memcg is offlined vmpressure is called synchronously from reclaim where the target_memcg is guaranteed to be alive but the eventfd is signaled from the work queue context. This means that memcg (along with vmpressure structure which is embedded into it) might go away while the work item is pending which would result in use-after-release bug. We have two possible ways how to fix this. Either vmpressure pins memcg before it schedules vmpr->work and unpin it in vmpressure_work_fn or explicitely flush the work item from the css_offline context (as suggested by Tejun). This patch implements the later one and it introduces vmpressure_cleanup which flushes the vmpressure work queue item item. It hooks into mem_cgroup_css_offline after the memcg itself is cleaned up. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Michal Hocko Reported-by: Tejun Heo Cc: Anton Vorontsov Cc: Johannes Weiner Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Li Zefan Acked-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmpressure.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h index 2081680e015d..7dc17e2456de 100644 --- a/include/linux/vmpressure.h +++ b/include/linux/vmpressure.h @@ -30,6 +30,7 @@ extern void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, extern void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio); extern void vmpressure_init(struct vmpressure *vmpr); +extern void vmpressure_cleanup(struct vmpressure *vmpr); extern struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg); extern struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr); extern struct vmpressure *css_to_vmpressure(struct cgroup_subsys_state *css); -- cgit v1.2.2 From e0d1095ae3405404d247afb00233ef837d58da83 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 1 Aug 2013 11:10:25 +0800 Subject: net: rename CONFIG_NET_LL_RX_POLL to CONFIG_NET_RX_BUSY_POLL Eliezer renames several *ll_poll to *busy_poll, but forgets CONFIG_NET_LL_RX_POLL, so in case of confusion, rename it too. Cc: Eliezer Tamir Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- include/linux/skbuff.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0741a1e919a5..9a4156845e93 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -973,7 +973,7 @@ struct net_device_ops { gfp_t gfp); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL int (*ndo_busy_poll)(struct napi_struct *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5afefa01a13c..3b71a4e83642 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -501,7 +501,7 @@ struct sk_buff { /* 7/9 bit hole (depending on ndisc_nodetype presence) */ kmemcheck_bitfield_end(flags2); -#if defined CONFIG_NET_DMA || defined CONFIG_NET_LL_RX_POLL +#if defined CONFIG_NET_DMA || defined CONFIG_NET_RX_BUSY_POLL union { unsigned int napi_id; dma_cookie_t dma_cookie; -- cgit v1.2.2