From 81dcaf6516d8bbd75b894862c8ae7bba04380cfe Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Sep 2010 10:17:35 +0200 Subject: workqueue: implement alloc_ordered_workqueue() alloc_ordered_workqueue() creates a workqueue which processes each work itemp one by one in the queued order. This will be used to replace create_freezeable_workqueue() and create_singlethread_workqueue(). Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 25e02c941bac..07c48925a8fc 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -306,6 +306,24 @@ __alloc_workqueue_key(const char *name, unsigned int flags, int max_active, __alloc_workqueue_key((name), (flags), (max_active), NULL, NULL) #endif +/** + * alloc_ordered_workqueue - allocate an ordered workqueue + * @name: name of the workqueue + * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_RESCUER are meaningful) + * + * Allocate an ordered workqueue. An ordered workqueue executes at + * most one work item at any given time in the queued order. They are + * implemented as unbound workqueues with @max_active of one. + * + * RETURNS: + * Pointer to the allocated workqueue on success, %NULL on failure. + */ +static inline struct workqueue_struct * +alloc_ordered_workqueue(const char *name, unsigned int flags) +{ + return alloc_workqueue(name, WQ_UNBOUND | flags, 1); +} + #define create_workqueue(name) \ alloc_workqueue((name), WQ_RESCUER, 1) #define create_freezeable_workqueue(name) \ -- cgit v1.2.3-58-ga151 From 401a8d048eadfbe1b1c1bf53d3b614fcc894c61a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Sep 2010 10:36:00 +0200 Subject: workqueue: cleanup flush/cancel functions Make the following cleanup changes. * Relocate flush/cancel function prototypes and definitions. * Relocate wait_on_cpu_work() and wait_on_work() before try_to_grab_pending(). These will be used to implement flush_work_sync(). * Make all flush/cancel functions return bool instead of int. * Update wait_on_cpu_work() and wait_on_work() to return %true if they actually waited. * Add / update comments. This patch doesn't cause any functional changes. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 18 ++--- kernel/workqueue.c | 175 +++++++++++++++++++++++++--------------------- 2 files changed, 103 insertions(+), 90 deletions(-) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 07c48925a8fc..bb9b683ea6fa 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -343,7 +343,6 @@ extern int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, extern void flush_workqueue(struct workqueue_struct *wq); extern void flush_scheduled_work(void); -extern void flush_delayed_work(struct delayed_work *work); extern int schedule_work(struct work_struct *work); extern int schedule_work_on(int cpu, struct work_struct *work); @@ -355,8 +354,11 @@ extern int keventd_up(void); int execute_in_process_context(work_func_t fn, struct execute_work *); -extern int flush_work(struct work_struct *work); -extern int cancel_work_sync(struct work_struct *work); +extern bool flush_work(struct work_struct *work); +extern bool cancel_work_sync(struct work_struct *work); + +extern bool flush_delayed_work(struct delayed_work *dwork); +extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); @@ -370,9 +372,9 @@ extern unsigned int work_busy(struct work_struct *work); * it returns 1 and the work doesn't re-arm itself. Run flush_workqueue() or * cancel_work_sync() to wait on it. */ -static inline int cancel_delayed_work(struct delayed_work *work) +static inline bool cancel_delayed_work(struct delayed_work *work) { - int ret; + bool ret; ret = del_timer_sync(&work->timer); if (ret) @@ -385,9 +387,9 @@ static inline int cancel_delayed_work(struct delayed_work *work) * if it returns 0 the timer function may be running and the queueing is in * progress. */ -static inline int __cancel_delayed_work(struct delayed_work *work) +static inline bool __cancel_delayed_work(struct delayed_work *work) { - int ret; + bool ret; ret = del_timer(&work->timer); if (ret) @@ -395,8 +397,6 @@ static inline int __cancel_delayed_work(struct delayed_work *work) return ret; } -extern int cancel_delayed_work_sync(struct delayed_work *work); - /* Obsolete. use cancel_delayed_work_sync() */ static inline void cancel_rearming_delayed_workqueue(struct workqueue_struct *wq, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f77afd939229..1240b9d94b03 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2327,16 +2327,24 @@ out_unlock: EXPORT_SYMBOL_GPL(flush_workqueue); /** - * flush_work - block until a work_struct's callback has terminated - * @work: the work which is to be flushed + * flush_work - wait for a work to finish executing the last queueing instance + * @work: the work to flush * - * Returns false if @work has already terminated. + * Wait until @work has finished execution. This function considers + * only the last queueing instance of @work. If @work has been + * enqueued across different CPUs on a non-reentrant workqueue or on + * multiple workqueues, @work might still be executing on return on + * some of the CPUs from earlier queueing. * - * It is expected that, prior to calling flush_work(), the caller has - * arranged for the work to not be requeued, otherwise it doesn't make - * sense to use this function. + * If @work was queued only on a non-reentrant, ordered or unbound + * workqueue, @work is guaranteed to be idle on return if it hasn't + * been requeued since flush started. + * + * RETURNS: + * %true if flush_work() waited for the work to finish execution, + * %false if it was already idle. */ -int flush_work(struct work_struct *work) +bool flush_work(struct work_struct *work) { struct worker *worker = NULL; struct global_cwq *gcwq; @@ -2374,13 +2382,49 @@ int flush_work(struct work_struct *work) wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); - return 1; + return true; already_gone: spin_unlock_irq(&gcwq->lock); - return 0; + return false; } EXPORT_SYMBOL_GPL(flush_work); +static bool wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work) +{ + struct wq_barrier barr; + struct worker *worker; + + spin_lock_irq(&gcwq->lock); + + worker = find_worker_executing_work(gcwq, work); + if (unlikely(worker)) + insert_wq_barrier(worker->current_cwq, &barr, work, worker); + + spin_unlock_irq(&gcwq->lock); + + if (unlikely(worker)) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + return true; + } else + return false; +} + +static bool wait_on_work(struct work_struct *work) +{ + bool ret = false; + int cpu; + + might_sleep(); + + lock_map_acquire(&work->lockdep_map); + lock_map_release(&work->lockdep_map); + + for_each_gcwq_cpu(cpu) + ret |= wait_on_cpu_work(get_gcwq(cpu), work); + return ret; +} + /* * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit, * so this work can't be re-armed in any way. @@ -2423,39 +2467,7 @@ static int try_to_grab_pending(struct work_struct *work) return ret; } -static void wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work) -{ - struct wq_barrier barr; - struct worker *worker; - - spin_lock_irq(&gcwq->lock); - - worker = find_worker_executing_work(gcwq, work); - if (unlikely(worker)) - insert_wq_barrier(worker->current_cwq, &barr, work, worker); - - spin_unlock_irq(&gcwq->lock); - - if (unlikely(worker)) { - wait_for_completion(&barr.done); - destroy_work_on_stack(&barr.work); - } -} - -static void wait_on_work(struct work_struct *work) -{ - int cpu; - - might_sleep(); - - lock_map_acquire(&work->lockdep_map); - lock_map_release(&work->lockdep_map); - - for_each_gcwq_cpu(cpu) - wait_on_cpu_work(get_gcwq(cpu), work); -} - -static int __cancel_work_timer(struct work_struct *work, +static bool __cancel_work_timer(struct work_struct *work, struct timer_list* timer) { int ret; @@ -2472,42 +2484,60 @@ static int __cancel_work_timer(struct work_struct *work, } /** - * cancel_work_sync - block until a work_struct's callback has terminated - * @work: the work which is to be flushed - * - * Returns true if @work was pending. + * cancel_work_sync - cancel a work and wait for it to finish + * @work: the work to cancel * - * cancel_work_sync() will cancel the work if it is queued. If the work's - * callback appears to be running, cancel_work_sync() will block until it - * has completed. + * Cancel @work and wait for its execution to finish. This function + * can be used even if the work re-queues itself or migrates to + * another workqueue. On return from this function, @work is + * guaranteed to be not pending or executing on any CPU. * - * It is possible to use this function if the work re-queues itself. It can - * cancel the work even if it migrates to another workqueue, however in that - * case it only guarantees that work->func() has completed on the last queued - * workqueue. - * - * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not - * pending, otherwise it goes into a busy-wait loop until the timer expires. + * cancel_work_sync(&delayed_work->work) must not be used for + * delayed_work's. Use cancel_delayed_work_sync() instead. * - * The caller must ensure that workqueue_struct on which this work was last + * The caller must ensure that the workqueue on which @work was last * queued can't be destroyed before this function returns. + * + * RETURNS: + * %true if @work was pending, %false otherwise. */ -int cancel_work_sync(struct work_struct *work) +bool cancel_work_sync(struct work_struct *work) { return __cancel_work_timer(work, NULL); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** - * cancel_delayed_work_sync - reliably kill off a delayed work. - * @dwork: the delayed work struct + * flush_delayed_work - wait for a dwork to finish executing the last queueing + * @dwork: the delayed work to flush + * + * Delayed timer is cancelled and the pending work is queued for + * immediate execution. Like flush_work(), this function only + * considers the last queueing instance of @dwork. + * + * RETURNS: + * %true if flush_work() waited for the work to finish execution, + * %false if it was already idle. + */ +bool flush_delayed_work(struct delayed_work *dwork) +{ + if (del_timer_sync(&dwork->timer)) + __queue_work(raw_smp_processor_id(), + get_work_cwq(&dwork->work)->wq, &dwork->work); + return flush_work(&dwork->work); +} +EXPORT_SYMBOL(flush_delayed_work); + +/** + * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish + * @dwork: the delayed work cancel * - * Returns true if @dwork was pending. + * This is cancel_work_sync() for delayed works. * - * It is possible to use this function if @dwork rearms itself via queue_work() - * or queue_delayed_work(). See also the comment for cancel_work_sync(). + * RETURNS: + * %true if @dwork was pending, %false otherwise. */ -int cancel_delayed_work_sync(struct delayed_work *dwork) +bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_timer(&dwork->work, &dwork->timer); } @@ -2558,23 +2588,6 @@ int schedule_delayed_work(struct delayed_work *dwork, } EXPORT_SYMBOL(schedule_delayed_work); -/** - * flush_delayed_work - block until a dwork_struct's callback has terminated - * @dwork: the delayed work which is to be flushed - * - * Any timeout is cancelled, and any pending work is run immediately. - */ -void flush_delayed_work(struct delayed_work *dwork) -{ - if (del_timer_sync(&dwork->timer)) { - __queue_work(get_cpu(), get_work_cwq(&dwork->work)->wq, - &dwork->work); - put_cpu(); - } - flush_work(&dwork->work); -} -EXPORT_SYMBOL(flush_delayed_work); - /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use -- cgit v1.2.3-58-ga151 From 09383498c5d35262e643bfdbae84826177a3c624 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Sep 2010 10:48:29 +0200 Subject: workqueue: implement flush[_delayed]_work_sync() Implement flush[_delayed]_work_sync(). These are flush functions which also make sure no CPU is still executing the target work from earlier queueing instances. These are similar to cancel[_delayed]_work_sync() except that the target work item is flushed instead of cancelled. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 ++ kernel/workqueue.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index bb9b683ea6fa..e33ff4a91703 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -355,9 +355,11 @@ extern int keventd_up(void); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); +extern bool flush_work_sync(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); +extern bool flush_delayed_work_sync(struct delayed_work *work); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 33d31d768706..19e4bc15ee99 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2435,6 +2435,41 @@ static bool wait_on_work(struct work_struct *work) return ret; } +/** + * flush_work_sync - wait until a work has finished execution + * @work: the work to flush + * + * Wait until @work has finished execution. On return, it's + * guaranteed that all queueing instances of @work which happened + * before this function is called are finished. In other words, if + * @work hasn't been requeued since this function was called, @work is + * guaranteed to be idle on return. + * + * RETURNS: + * %true if flush_work_sync() waited for the work to finish execution, + * %false if it was already idle. + */ +bool flush_work_sync(struct work_struct *work) +{ + struct wq_barrier barr; + bool pending, waited; + + /* we'll wait for executions separately, queue barr only if pending */ + pending = start_flush_work(work, &barr, false); + + /* wait for executions to finish */ + waited = wait_on_work(work); + + /* wait for the pending one */ + if (pending) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + } + + return pending || waited; +} +EXPORT_SYMBOL_GPL(flush_work_sync); + /* * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit, * so this work can't be re-armed in any way. @@ -2538,6 +2573,27 @@ bool flush_delayed_work(struct delayed_work *dwork) } EXPORT_SYMBOL(flush_delayed_work); +/** + * flush_delayed_work_sync - wait for a dwork to finish + * @dwork: the delayed work to flush + * + * Delayed timer is cancelled and the pending work is queued for + * execution immediately. Other than timer handling, its behavior + * is identical to flush_work_sync(). + * + * RETURNS: + * %true if flush_work_sync() waited for the work to finish execution, + * %false if it was already idle. + */ +bool flush_delayed_work_sync(struct delayed_work *dwork) +{ + if (del_timer_sync(&dwork->timer)) + __queue_work(raw_smp_processor_id(), + get_work_cwq(&dwork->work)->wq, &dwork->work); + return flush_work_sync(&dwork->work); +} +EXPORT_SYMBOL(flush_delayed_work_sync); + /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel -- cgit v1.2.3-58-ga151 From 97bd234701b2b39a0e749c1fe0e44f1d14c94292 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 5 Oct 2010 10:41:14 +0200 Subject: workqueue: prepare for more tracepoints Define workqueue_work event class and use it for workqueue_execute_end trace point. Also, move trace/events/workqueue.h include downwards such that all struct definitions are visible to it. This is to prepare for more tracepoints and doesn't cause any functional change. Signed-off-by: Tejun Heo Cc: Frederic Weisbecker --- include/trace/events/workqueue.h | 32 +++++++++++++++++++------------- kernel/workqueue.c | 6 +++--- 2 files changed, 22 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index 49682d7e9d60..ec9d7244eb9f 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -7,13 +7,7 @@ #include #include -/** - * workqueue_execute_start - called immediately before the workqueue callback - * @work: pointer to struct work_struct - * - * Allows to track workqueue execution. - */ -TRACE_EVENT(workqueue_execute_start, +DECLARE_EVENT_CLASS(workqueue_work, TP_PROTO(struct work_struct *work), @@ -21,24 +15,22 @@ TRACE_EVENT(workqueue_execute_start, TP_STRUCT__entry( __field( void *, work ) - __field( void *, function) ), TP_fast_assign( __entry->work = work; - __entry->function = work->func; ), - TP_printk("work struct %p: function %pf", __entry->work, __entry->function) + TP_printk("work struct %p", __entry->work) ); /** - * workqueue_execute_end - called immediately before the workqueue callback + * workqueue_execute_start - called immediately before the workqueue callback * @work: pointer to struct work_struct * * Allows to track workqueue execution. */ -TRACE_EVENT(workqueue_execute_end, +TRACE_EVENT(workqueue_execute_start, TP_PROTO(struct work_struct *work), @@ -46,15 +38,29 @@ TRACE_EVENT(workqueue_execute_end, TP_STRUCT__entry( __field( void *, work ) + __field( void *, function) ), TP_fast_assign( __entry->work = work; + __entry->function = work->func; ), - TP_printk("work struct %p", __entry->work) + TP_printk("work struct %p: function %pf", __entry->work, __entry->function) ); +/** + * workqueue_execute_end - called immediately before the workqueue callback + * @work: pointer to struct work_struct + * + * Allows to track workqueue execution. + */ +DEFINE_EVENT(workqueue_work, workqueue_execute_end, + + TP_PROTO(struct work_struct *work), + + TP_ARGS(work) +); #endif /* _TRACE_WORKQUEUE_H */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 19e4bc15ee99..026f778e879b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -42,9 +42,6 @@ #include #include -#define CREATE_TRACE_POINTS -#include - #include "workqueue_sched.h" enum { @@ -257,6 +254,9 @@ EXPORT_SYMBOL_GPL(system_long_wq); EXPORT_SYMBOL_GPL(system_nrt_wq); EXPORT_SYMBOL_GPL(system_unbound_wq); +#define CREATE_TRACE_POINTS +#include + #define for_each_busy_worker(worker, i, pos, gcwq) \ for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) \ hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry) -- cgit v1.2.3-58-ga151 From cdadf0097cdca06c497ffaeb5982e028c6e4ed38 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 5 Oct 2010 10:49:55 +0200 Subject: workqueue: add queue_work and activate_work trace points These two tracepoints allow tracking when and how a work is queued and activated. This patch is based on Frederic's patch to add queue_work trace point. Signed-off-by: Tejun Heo Cc: Frederic Weisbecker --- include/trace/events/workqueue.h | 53 ++++++++++++++++++++++++++++++++++++++++ kernel/workqueue.c | 3 +++ 2 files changed, 56 insertions(+) (limited to 'include') diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index ec9d7244eb9f..7d497291c85d 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -24,6 +24,59 @@ DECLARE_EVENT_CLASS(workqueue_work, TP_printk("work struct %p", __entry->work) ); +/** + * workqueue_queue_work - called when a work gets queued + * @req_cpu: the requested cpu + * @cwq: pointer to struct cpu_workqueue_struct + * @work: pointer to struct work_struct + * + * This event occurs when a work is queued immediately or once a + * delayed work is actually queued on a workqueue (ie: once the delay + * has been reached). + */ +TRACE_EVENT(workqueue_queue_work, + + TP_PROTO(unsigned int req_cpu, struct cpu_workqueue_struct *cwq, + struct work_struct *work), + + TP_ARGS(req_cpu, cwq, work), + + TP_STRUCT__entry( + __field( void *, work ) + __field( void *, function) + __field( void *, workqueue) + __field( unsigned int, req_cpu ) + __field( unsigned int, cpu ) + ), + + TP_fast_assign( + __entry->work = work; + __entry->function = work->func; + __entry->workqueue = cwq->wq; + __entry->req_cpu = req_cpu; + __entry->cpu = cwq->gcwq->cpu; + ), + + TP_printk("work struct=%p function=%pf workqueue=%p req_cpu=%u cpu=%u", + __entry->work, __entry->function, __entry->workqueue, + __entry->req_cpu, __entry->cpu) +); + +/** + * workqueue_activate_work - called when a work gets activated + * @work: pointer to struct work_struct + * + * This event occurs when a queued work is put on the active queue, + * which happens immediately after queueing unless @max_active limit + * is reached. + */ +DEFINE_EVENT(workqueue_work, workqueue_activate_work, + + TP_PROTO(struct work_struct *work), + + TP_ARGS(work) +); + /** * workqueue_execute_start - called immediately before the workqueue callback * @work: pointer to struct work_struct diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 026f778e879b..cb2ccfbed0c6 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -997,6 +997,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, /* gcwq determined, get cwq and queue */ cwq = get_cwq(gcwq->cpu, wq); + trace_workqueue_queue_work(cpu, cwq, work); BUG_ON(!list_empty(&work->entry)); @@ -1004,6 +1005,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, work_flags = work_color_to_flags(cwq->work_color); if (likely(cwq->nr_active < cwq->max_active)) { + trace_workqueue_activate_work(work); cwq->nr_active++; worklist = gcwq_determine_ins_pos(gcwq, cwq); } else { @@ -1679,6 +1681,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) struct work_struct, entry); struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq); + trace_workqueue_activate_work(work); move_linked_works(work, pos, NULL); __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); cwq->nr_active++; -- cgit v1.2.3-58-ga151 From 6370a6ad3b53df90b4700977f7718118a2cd524a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 11 Oct 2010 15:12:27 +0200 Subject: workqueue: add and use WQ_MEM_RECLAIM flag Add WQ_MEM_RECLAIM flag which currently maps to WQ_RESCUER, mark WQ_RESCUER as internal and replace all external WQ_RESCUER usages to WQ_MEM_RECLAIM. This makes the API users express the intent of the workqueue instead of indicating the internal mechanism used to guarantee forward progress. This is also to make it cleaner to add more semantics to WQ_MEM_RECLAIM. For example, if deemed necessary, memory reclaim workqueues can be made highpri. This patch doesn't introduce any functional change. Signed-off-by: Tejun Heo Cc: Jeff Garzik Cc: Dave Chinner Cc: Steven Whitehouse --- Documentation/workqueue.txt | 29 +++++++++++++++-------------- drivers/ata/libata-sff.c | 2 +- fs/gfs2/main.c | 2 +- fs/xfs/linux-2.6/xfs_buf.c | 2 +- include/linux/workqueue.h | 11 ++++++----- kernel/workqueue.c | 7 +++++++ 6 files changed, 31 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt index e4498a2872c3..996a27d9b8db 100644 --- a/Documentation/workqueue.txt +++ b/Documentation/workqueue.txt @@ -196,11 +196,11 @@ resources, scheduled and executed. suspend operations. Work items on the wq are drained and no new work item starts execution until thawed. - WQ_RESCUER + WQ_MEM_RECLAIM All wq which might be used in the memory reclaim paths _MUST_ - have this flag set. This reserves one worker exclusively for - the execution of this wq under memory pressure. + have this flag set. The wq is guaranteed to have at least one + execution context regardless of memory pressure. WQ_HIGHPRI @@ -356,11 +356,11 @@ If q1 has WQ_CPU_INTENSIVE set, 6. Guidelines -* Do not forget to use WQ_RESCUER if a wq may process work items which - are used during memory reclaim. Each wq with WQ_RESCUER set has one - rescuer thread reserved for it. If there is dependency among - multiple work items used during memory reclaim, they should be - queued to separate wq each with WQ_RESCUER. +* Do not forget to use WQ_MEM_RECLAIM if a wq may process work items + which are used during memory reclaim. Each wq with WQ_MEM_RECLAIM + set has an execution context reserved for it. If there is + dependency among multiple work items used during memory reclaim, + they should be queued to separate wq each with WQ_MEM_RECLAIM. * Unless strict ordering is required, there is no need to use ST wq. @@ -368,12 +368,13 @@ If q1 has WQ_CPU_INTENSIVE set, recommended. In most use cases, concurrency level usually stays well under the default limit. -* A wq serves as a domain for forward progress guarantee (WQ_RESCUER), - flush and work item attributes. Work items which are not involved - in memory reclaim and don't need to be flushed as a part of a group - of work items, and don't require any special attribute, can use one - of the system wq. There is no difference in execution - characteristics between using a dedicated wq and a system wq. +* A wq serves as a domain for forward progress guarantee + (WQ_MEM_RECLAIM, flush and work item attributes. Work items which + are not involved in memory reclaim and don't need to be flushed as a + part of a group of work items, and don't require any special + attribute, can use one of the system wq. There is no difference in + execution characteristics between using a dedicated wq and a system + wq. * Unless work items are expected to consume a huge amount of CPU cycles, using a bound wq is usually beneficial due to the increased diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index e30c537cce32..f5296bb19ec0 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -3335,7 +3335,7 @@ void ata_sff_port_init(struct ata_port *ap) int __init ata_sff_init(void) { - ata_sff_wq = alloc_workqueue("ata_sff", WQ_RESCUER, WQ_MAX_ACTIVE); + ata_sff_wq = alloc_workqueue("ata_sff", WQ_MEM_RECLAIM, WQ_MAX_ACTIVE); if (!ata_sff_wq) return -ENOMEM; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index b1e9630eb46a..1c5f46075d52 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -140,7 +140,7 @@ static int __init init_gfs2_fs(void) error = -ENOMEM; gfs_recovery_wq = alloc_workqueue("gfs_recovery", - WQ_NON_REENTRANT | WQ_RESCUER, 0); + WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0); if (!gfs_recovery_wq) goto fail_wq; diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 286e36e21dae..6838aefca71f 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -1933,7 +1933,7 @@ xfs_buf_init(void) goto out; xfslogd_workqueue = alloc_workqueue("xfslogd", - WQ_RESCUER | WQ_HIGHPRI, 1); + WQ_MEM_RECLAIM | WQ_HIGHPRI, 1); if (!xfslogd_workqueue) goto out_free_buf_zone; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index e33ff4a91703..03bbe903e5ce 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -243,11 +243,12 @@ enum { WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZEABLE = 1 << 2, /* freeze during suspend */ - WQ_RESCUER = 1 << 3, /* has an rescue worker */ + WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ WQ_DYING = 1 << 6, /* internal: workqueue is dying */ + WQ_RESCUER = 1 << 7, /* internal: workqueue has rescuer */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ @@ -309,7 +310,7 @@ __alloc_workqueue_key(const char *name, unsigned int flags, int max_active, /** * alloc_ordered_workqueue - allocate an ordered workqueue * @name: name of the workqueue - * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_RESCUER are meaningful) + * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_MEM_RECLAIM are meaningful) * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are @@ -325,11 +326,11 @@ alloc_ordered_workqueue(const char *name, unsigned int flags) } #define create_workqueue(name) \ - alloc_workqueue((name), WQ_RESCUER, 1) + alloc_workqueue((name), WQ_MEM_RECLAIM, 1) #define create_freezeable_workqueue(name) \ - alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1) #define create_singlethread_workqueue(name) \ - alloc_workqueue((name), WQ_UNBOUND | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_UNBOUND | WQ_MEM_RECLAIM, 1) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b57a8babdec3..2c6871cbcbee 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2847,6 +2847,13 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, struct workqueue_struct *wq; unsigned int cpu; + /* + * Workqueues which may be used during memory reclaim should + * have a rescuer to guarantee forward progress. + */ + if (flags & WQ_MEM_RECLAIM) + flags |= WQ_RESCUER; + /* * Unbound workqueues aren't concurrency managed and should be * dispatched to workers immediately. -- cgit v1.2.3-58-ga151 From daaae6b010ac0f60c9c35e481589966f9f1fcc22 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 19 Oct 2010 11:28:15 +0200 Subject: workqueue: remove in_workqueue_context() Commit a25909a4 (lockdep: Add an in_workqueue_context() lockdep-based test function) added in_workqueue_context() but there hasn't been any in-kernel user and the lockdep annotation in workqueue is scheduled to change. Remove the unused function. Signed-off-by: Tejun Heo Cc: Paul E. McKenney --- include/linux/workqueue.h | 4 ---- kernel/workqueue.c | 15 --------------- 2 files changed, 19 deletions(-) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 03bbe903e5ce..070bb7a88936 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -430,8 +430,4 @@ extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ -#ifdef CONFIG_LOCKDEP -int in_workqueue_context(struct workqueue_struct *wq); -#endif - #endif diff --git a/kernel/workqueue.c b/kernel/workqueue.c index eb5c1972443a..30acdb74cc23 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -310,21 +310,6 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask, (cpu) < WORK_CPU_NONE; \ (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq))) -#ifdef CONFIG_LOCKDEP -/** - * in_workqueue_context() - in context of specified workqueue? - * @wq: the workqueue of interest - * - * Checks lockdep state to see if the current task is executing from - * within a workqueue item. This function exists only if lockdep is - * enabled. - */ -int in_workqueue_context(struct workqueue_struct *wq) -{ - return lock_is_held(&wq->lockdep_map); -} -#endif - #ifdef CONFIG_DEBUG_OBJECTS_WORK static struct debug_obj_descr work_debug_descr; -- cgit v1.2.3-58-ga151