From b31041042a8cdece67f925e4bae55b5f5fd754ca Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 19 Feb 2013 12:17:02 -0800 Subject: workqueue: better define synchronization rule around rescuer->pool updates Rescuers visit different worker_pools to process work items from pools under pressure. Currently, rescuer->pool is updated outside any locking and when an outsider looks at a rescuer, there's no way to tell when and whether rescuer->pool is gonna change. While this doesn't currently cause any problem, it is nasty. With recent worker_maybe_bind_and_lock() changes, we can move rescuer->pool updates inside pool locks such that if rescuer->pool equals a locked pool, it's guaranteed to stay that way until the pool is unlocked. Move rescuer->pool inside pool->lock. This patch doesn't introduce any visible behavior difference. tj: Updated the description. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo --- kernel/workqueue_internal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/workqueue_internal.h') diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 07650264ec15..f9c887731e2b 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -32,6 +32,7 @@ struct worker { struct list_head scheduled; /* L: scheduled works */ struct task_struct *task; /* I: worker task */ struct worker_pool *pool; /* I: the associated pool */ + /* L: for rescuers */ /* 64 bytes boundary on 64bit, 32 on 32bit */ unsigned long last_active; /* L: last active timestamp */ unsigned int flags; /* X: flags */ -- cgit v1.2.3 From d84ff0512f1bfc0d8c864efadb4523fce68919cc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:29:59 -0700 Subject: workqueue: consistently use int for @cpu variables Workqueue is mixing unsigned int and int for @cpu variables. There's no point in using unsigned int for cpus - many of cpu related APIs take int anyway. Consistently use int for @cpu variables so that we can use negative values to mark special ones. This patch doesn't introduce any visible behavior changes. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- kernel/workqueue_internal.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel/workqueue_internal.h') diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index f9c887731e2b..f116f071d919 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -59,8 +59,7 @@ static inline struct worker *current_wq_worker(void) * Scheduler hooks for concurrency managed workqueue. Only to be used from * sched.c and workqueue.c. */ -void wq_worker_waking_up(struct task_struct *task, unsigned int cpu); -struct task_struct *wq_worker_sleeping(struct task_struct *task, - unsigned int cpu); +void wq_worker_waking_up(struct task_struct *task, int cpu); +struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ -- cgit v1.2.3 From a9ab775bcadf122d91e1a201eb66ae2eec90365a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 19 Mar 2013 13:45:21 -0700 Subject: workqueue: directly restore CPU affinity of workers from CPU_ONLINE Rebinding workers of a per-cpu pool after a CPU comes online involves a lot of back-and-forth mostly because only the task itself could adjust CPU affinity if PF_THREAD_BOUND was set. As CPU_ONLINE itself couldn't adjust affinity, it had to somehow coerce the workers themselves to perform set_cpus_allowed_ptr(). Due to the various states a worker can be in, this led to three different paths a worker may be rebound. worker->rebind_work is queued to busy workers. Idle ones are signaled by unlinking worker->entry and call idle_worker_rebind(). The manager isn't covered by either and implements its own mechanism. PF_THREAD_BOUND has been relaced with PF_NO_SETAFFINITY and CPU_ONLINE itself now can manipulate CPU affinity of workers. This patch replaces the existing rebind mechanism with direct one where CPU_ONLINE iterates over all workers using for_each_pool_worker(), restores CPU affinity, and clears WORKER_UNBOUND. There are a couple subtleties. All bound idle workers should have their runqueues set to that of the bound CPU; however, if the target task isn't running, set_cpus_allowed_ptr() just updates the cpus_allowed mask deferring the actual migration to when the task wakes up. This is worked around by waking up idle workers after restoring CPU affinity before any workers can become bound. Another subtlety is stems from matching @pool->nr_running with the number of running unbound workers. While DISASSOCIATED, all workers are unbound and nr_running is zero. As workers become bound again, nr_running needs to be adjusted accordingly; however, there is no good way to tell whether a given worker is running without poking into scheduler internals. Instead of clearing UNBOUND directly, rebind_workers() replaces UNBOUND with another new NOT_RUNNING flag - REBOUND, which will later be cleared by the workers themselves while preparing for the next round of work item execution. The only change needed for the workers is clearing REBOUND along with PREP. * This patch leaves for_each_busy_worker() without any user. Removed. * idle_worker_rebind(), busy_worker_rebind_fn(), worker->rebind_work and rebind logic in manager_workers() removed. * worker_thread() now looks at WORKER_DIE instead of testing whether @worker->entry is empty to determine whether it needs to do something special as dying is the only special thing now. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- kernel/workqueue_internal.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel/workqueue_internal.h') diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index f116f071d919..84ab6e1dc6fb 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -38,9 +38,6 @@ struct worker { unsigned int flags; /* X: flags */ int id; /* I: worker id */ - /* for rebinding worker to CPU */ - struct work_struct rebind_work; /* L: for busy worker */ - /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ }; -- cgit v1.2.3 From 3d1cb2059d9374e58da481b783332cf191cb6620 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 30 Apr 2013 15:27:22 -0700 Subject: workqueue: include workqueue info when printing debug dump of a worker task One of the problems that arise when converting dedicated custom threadpool to workqueue is that the shared worker pool used by workqueue anonimizes each worker making it more difficult to identify what the worker was doing on which target from the output of sysrq-t or debug dump from oops, BUG() and friends. This patch implements set_worker_desc() which can be called from any workqueue work function to set its description. When the worker task is dumped for whatever reason - sysrq-t, WARN, BUG, oops, lockdep assertion and so on - the description will be printed out together with the workqueue name and the worker function pointer. The printing side is implemented by print_worker_info() which is called from functions in task dump paths - sched_show_task() and dump_stack_print_info(). print_worker_info() can be safely called on any task in any state as long as the task struct itself is accessible. It uses probe_*() functions to access worker fields. It may print garbage if something went very wrong, but it wouldn't cause (another) oops. The description is currently limited to 24bytes including the terminating \0. worker->desc_valid and workder->desc[] are added and the 64 bytes marker which was already incorrect before adding the new fields is moved to the correct position. Here's an example dump with writeback updated to set the bdi name as worker desc. Hardware name: Bochs Modules linked in: Pid: 7, comm: kworker/u9:0 Not tainted 3.9.0-rc1-work+ #1 Workqueue: writeback bdi_writeback_workfn (flush-8:0) ffffffff820a3ab0 ffff88000f6e9cb8 ffffffff81c61845 ffff88000f6e9cf8 ffffffff8108f50f 0000000000000000 0000000000000000 ffff88000cde16b0 ffff88000cde1aa8 ffff88001ee19240 ffff88000f6e9fd8 ffff88000f6e9d08 Call Trace: [] dump_stack+0x19/0x1b [] warn_slowpath_common+0x7f/0xc0 [] warn_slowpath_null+0x1a/0x20 [] bdi_writeback_workfn+0x2a0/0x3b0 ... Signed-off-by: Tejun Heo Cc: Peter Zijlstra Cc: Ingo Molnar Acked-by: Jan Kara Cc: Oleg Nesterov Cc: Jens Axboe Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/workqueue_internal.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'kernel/workqueue_internal.h') diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 84ab6e1dc6fb..ad83c96b2ece 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -29,15 +29,25 @@ struct worker { struct work_struct *current_work; /* L: work being processed */ work_func_t current_func; /* L: current_work's fn */ struct pool_workqueue *current_pwq; /* L: current_work's pwq */ + bool desc_valid; /* ->desc is valid */ struct list_head scheduled; /* L: scheduled works */ + + /* 64 bytes boundary on 64bit, 32 on 32bit */ + struct task_struct *task; /* I: worker task */ struct worker_pool *pool; /* I: the associated pool */ /* L: for rescuers */ - /* 64 bytes boundary on 64bit, 32 on 32bit */ + unsigned long last_active; /* L: last active timestamp */ unsigned int flags; /* X: flags */ int id; /* I: worker id */ + /* + * Opaque string set with work_set_desc(). Printed out with task + * dump for debugging - WARN, BUG, panic or sysrq. + */ + char desc[WORKER_DESC_LEN]; + /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ }; -- cgit v1.2.3