From a25909a4d4a29e272f953e12595bf2f04a292dbd Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 13 May 2010 12:32:28 -0700 Subject: lockdep: Add an in_workqueue_context() lockdep-based test function Some recent uses of RCU make use of workqueues. In these uses, execution within the context of a specific workqueue takes the place of the usual RCU read-side primitives such as rcu_read_lock(), and flushing of workqueues takes the place of the usual RCU grace-period primitives. Checking for correct use of rcu_dereference() in such cases requires a test of whether the code is executing in the context of a particular workqueue. This commit adds an in_workqueue_context() function that provides this test. This new function is only defined when lockdep is enabled, which allows it to be used as the second argument of rcu_dereference_check(). Signed-off-by: Paul E. McKenney --- include/linux/workqueue.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 9466e860d8c2..d0f7c8178498 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -297,4 +297,8 @@ static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) #else long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ + +#ifdef CONFIG_LOCKDEP +int in_workqueue_context(struct workqueue_struct *wq); +#endif #endif -- cgit From c790bce0481857412c964c5e9d46d56e41c4b051 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:09 +0200 Subject: workqueue: kill RT workqueue With stop_machine() converted to use cpu_stop, RT workqueue doesn't have any user left. Kill RT workqueue support. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 20 +++++++++----------- kernel/workqueue.c | 6 ------ 2 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 9466e860d8c2..0697946c66a1 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -181,12 +181,11 @@ static inline void destroy_work_on_stack(struct work_struct *work) { } extern struct workqueue_struct * -__create_workqueue_key(const char *name, int singlethread, - int freezeable, int rt, struct lock_class_key *key, - const char *lock_name); +__create_workqueue_key(const char *name, int singlethread, int freezeable, + struct lock_class_key *key, const char *lock_name); #ifdef CONFIG_LOCKDEP -#define __create_workqueue(name, singlethread, freezeable, rt) \ +#define __create_workqueue(name, singlethread, freezeable) \ ({ \ static struct lock_class_key __key; \ const char *__lock_name; \ @@ -197,19 +196,18 @@ __create_workqueue_key(const char *name, int singlethread, __lock_name = #name; \ \ __create_workqueue_key((name), (singlethread), \ - (freezeable), (rt), &__key, \ + (freezeable), &__key, \ __lock_name); \ }) #else -#define __create_workqueue(name, singlethread, freezeable, rt) \ - __create_workqueue_key((name), (singlethread), (freezeable), (rt), \ +#define __create_workqueue(name, singlethread, freezeable) \ + __create_workqueue_key((name), (singlethread), (freezeable), \ NULL, NULL) #endif -#define create_workqueue(name) __create_workqueue((name), 0, 0, 0) -#define create_rt_workqueue(name) __create_workqueue((name), 0, 0, 1) -#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1, 0) -#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0, 0) +#define create_workqueue(name) __create_workqueue((name), 0, 0) +#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1) +#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 327d2deb4451..1a47fbf92fae 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -62,7 +62,6 @@ struct workqueue_struct { const char *name; int singlethread; int freezeable; /* Freeze threads during suspend */ - int rt; #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif @@ -947,7 +946,6 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu) static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) { - struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; struct workqueue_struct *wq = cwq->wq; const char *fmt = is_wq_single_threaded(wq) ? "%s" : "%s/%d"; struct task_struct *p; @@ -963,8 +961,6 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) */ if (IS_ERR(p)) return PTR_ERR(p); - if (cwq->wq->rt) - sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); cwq->thread = p; trace_workqueue_creation(cwq->thread, cpu); @@ -986,7 +982,6 @@ static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) struct workqueue_struct *__create_workqueue_key(const char *name, int singlethread, int freezeable, - int rt, struct lock_class_key *key, const char *lock_name) { @@ -1008,7 +1003,6 @@ struct workqueue_struct *__create_workqueue_key(const char *name, lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); wq->singlethread = singlethread; wq->freezeable = freezeable; - wq->rt = rt; INIT_LIST_HEAD(&wq->list); if (singlethread) { -- cgit From 4690c4ab56c71919893ca25252f2dd65b58188c7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:10 +0200 Subject: workqueue: misc/cosmetic updates Make the following updates in preparation of concurrency managed workqueue. None of these changes causes any visible behavior difference. * Add comments and adjust indentations to data structures and several functions. * Rename wq_per_cpu() to get_cwq() and swap the position of two parameters for consistency. Convert a direct per_cpu_ptr() access to wq->cpu_wq to get_cwq(). * Add work_static() and Update set_wq_data() such that it sets the flags part to WORK_STRUCT_PENDING | WORK_STRUCT_STATIC if static | @extra_flags. * Move santiy check on work->entry emptiness from queue_work_on() to __queue_work() which all queueing paths share. * Make __queue_work() take @cpu and @wq instead of @cwq. * Restructure flush_work() and __create_workqueue_key() to make them easier to modify. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 5 ++ kernel/workqueue.c | 131 +++++++++++++++++++++++++++++----------------- 2 files changed, 89 insertions(+), 47 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 0697946c66a1..e724dafc9e6d 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -96,9 +96,14 @@ struct execute_work { #ifdef CONFIG_DEBUG_OBJECTS_WORK extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); +static inline unsigned int work_static(struct work_struct *work) +{ + return *work_data_bits(work) & (1 << WORK_STRUCT_STATIC); +} #else static inline void __init_work(struct work_struct *work, int onstack) { } static inline void destroy_work_on_stack(struct work_struct *work) { } +static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif /* diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1a47fbf92fae..c56146a755e5 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -36,6 +36,16 @@ #define CREATE_TRACE_POINTS #include +/* + * Structure fields follow one of the following exclusion rules. + * + * I: Set during initialization and read-only afterwards. + * + * L: cwq->lock protected. Access with cwq->lock held. + * + * W: workqueue_lock protected. + */ + /* * The per-CPU workqueue (if single thread, we always use the first * possible cpu). @@ -48,8 +58,8 @@ struct cpu_workqueue_struct { wait_queue_head_t more_work; struct work_struct *current_work; - struct workqueue_struct *wq; - struct task_struct *thread; + struct workqueue_struct *wq; /* I: the owning workqueue */ + struct task_struct *thread; } ____cacheline_aligned; /* @@ -57,13 +67,13 @@ struct cpu_workqueue_struct { * per-CPU workqueues: */ struct workqueue_struct { - struct cpu_workqueue_struct *cpu_wq; - struct list_head list; - const char *name; + struct cpu_workqueue_struct *cpu_wq; /* I: cwq's */ + struct list_head list; /* W: list of all workqueues */ + const char *name; /* I: workqueue name */ int singlethread; int freezeable; /* Freeze threads during suspend */ #ifdef CONFIG_LOCKDEP - struct lockdep_map lockdep_map; + struct lockdep_map lockdep_map; #endif }; @@ -204,8 +214,8 @@ static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq) ? cpu_singlethread_map : cpu_populated_map; } -static -struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu) +static struct cpu_workqueue_struct *get_cwq(unsigned int cpu, + struct workqueue_struct *wq) { if (unlikely(is_wq_single_threaded(wq))) cpu = singlethread_cpu; @@ -217,15 +227,13 @@ struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu) * - Must *only* be called if the pending flag is set */ static inline void set_wq_data(struct work_struct *work, - struct cpu_workqueue_struct *cwq) + struct cpu_workqueue_struct *cwq, + unsigned long extra_flags) { - unsigned long new; - BUG_ON(!work_pending(work)); - new = (unsigned long) cwq | (1UL << WORK_STRUCT_PENDING); - new |= WORK_STRUCT_FLAG_MASK & *work_data_bits(work); - atomic_long_set(&work->data, new); + atomic_long_set(&work->data, (unsigned long)cwq | work_static(work) | + (1UL << WORK_STRUCT_PENDING) | extra_flags); } /* @@ -233,9 +241,7 @@ static inline void set_wq_data(struct work_struct *work, */ static inline void clear_wq_data(struct work_struct *work) { - unsigned long flags = *work_data_bits(work) & - (1UL << WORK_STRUCT_STATIC); - atomic_long_set(&work->data, flags); + atomic_long_set(&work->data, work_static(work)); } static inline @@ -244,29 +250,47 @@ struct cpu_workqueue_struct *get_wq_data(struct work_struct *work) return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK); } +/** + * insert_work - insert a work into cwq + * @cwq: cwq @work belongs to + * @work: work to insert + * @head: insertion point + * @extra_flags: extra WORK_STRUCT_* flags to set + * + * Insert @work into @cwq after @head. + * + * CONTEXT: + * spin_lock_irq(cwq->lock). + */ static void insert_work(struct cpu_workqueue_struct *cwq, - struct work_struct *work, struct list_head *head) + struct work_struct *work, struct list_head *head, + unsigned int extra_flags) { trace_workqueue_insertion(cwq->thread, work); - set_wq_data(work, cwq); + /* we own @work, set data and link */ + set_wq_data(work, cwq, extra_flags); + /* * Ensure that we get the right work->data if we see the * result of list_add() below, see try_to_grab_pending(). */ smp_wmb(); + list_add_tail(&work->entry, head); wake_up(&cwq->more_work); } -static void __queue_work(struct cpu_workqueue_struct *cwq, +static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, struct work_struct *work) { + struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); unsigned long flags; debug_work_activate(work); spin_lock_irqsave(&cwq->lock, flags); - insert_work(cwq, work, &cwq->worklist); + BUG_ON(!list_empty(&work->entry)); + insert_work(cwq, work, &cwq->worklist, 0); spin_unlock_irqrestore(&cwq->lock, flags); } @@ -308,8 +332,7 @@ queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) int ret = 0; if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) { - BUG_ON(!list_empty(&work->entry)); - __queue_work(wq_per_cpu(wq, cpu), work); + __queue_work(cpu, wq, work); ret = 1; } return ret; @@ -320,9 +343,8 @@ static void delayed_work_timer_fn(unsigned long __data) { struct delayed_work *dwork = (struct delayed_work *)__data; struct cpu_workqueue_struct *cwq = get_wq_data(&dwork->work); - struct workqueue_struct *wq = cwq->wq; - __queue_work(wq_per_cpu(wq, smp_processor_id()), &dwork->work); + __queue_work(smp_processor_id(), cwq->wq, &dwork->work); } /** @@ -366,7 +388,7 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, timer_stats_timer_set_start_info(&dwork->timer); /* This stores cwq for the moment, for the timer_fn */ - set_wq_data(work, wq_per_cpu(wq, raw_smp_processor_id())); + set_wq_data(work, get_cwq(raw_smp_processor_id(), wq), 0); timer->expires = jiffies + delay; timer->data = (unsigned long)dwork; timer->function = delayed_work_timer_fn; @@ -430,6 +452,12 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) spin_unlock_irq(&cwq->lock); } +/** + * worker_thread - the worker thread function + * @__cwq: cwq to serve + * + * The cwq worker thread function. + */ static int worker_thread(void *__cwq) { struct cpu_workqueue_struct *cwq = __cwq; @@ -468,6 +496,17 @@ static void wq_barrier_func(struct work_struct *work) complete(&barr->done); } +/** + * insert_wq_barrier - insert a barrier work + * @cwq: cwq to insert barrier into + * @barr: wq_barrier to insert + * @head: insertion point + * + * Insert barrier @barr into @cwq before @head. + * + * CONTEXT: + * spin_lock_irq(cwq->lock). + */ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, struct wq_barrier *barr, struct list_head *head) { @@ -479,11 +518,10 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, */ INIT_WORK_ON_STACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work)); - init_completion(&barr->done); debug_work_activate(&barr->work); - insert_work(cwq, &barr->work, head); + insert_work(cwq, &barr->work, head, 0); } static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) @@ -517,9 +555,6 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) * * We sleep until all works which were queued on entry have been handled, * but we are not livelocked by new incoming ones. - * - * This function used to run the workqueues itself. Now we just wait for the - * helper threads to do it. */ void flush_workqueue(struct workqueue_struct *wq) { @@ -558,7 +593,6 @@ int flush_work(struct work_struct *work) lock_map_acquire(&cwq->wq->lockdep_map); lock_map_release(&cwq->wq->lockdep_map); - prev = NULL; spin_lock_irq(&cwq->lock); if (!list_empty(&work->entry)) { /* @@ -567,22 +601,22 @@ int flush_work(struct work_struct *work) */ smp_rmb(); if (unlikely(cwq != get_wq_data(work))) - goto out; + goto already_gone; prev = &work->entry; } else { if (cwq->current_work != work) - goto out; + goto already_gone; prev = &cwq->worklist; } insert_wq_barrier(cwq, &barr, prev->next); -out: - spin_unlock_irq(&cwq->lock); - if (!prev) - return 0; + spin_unlock_irq(&cwq->lock); wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); return 1; +already_gone: + spin_unlock_irq(&cwq->lock); + return 0; } EXPORT_SYMBOL_GPL(flush_work); @@ -665,7 +699,7 @@ static void wait_on_work(struct work_struct *work) cpu_map = wq_cpu_map(wq); for_each_cpu(cpu, cpu_map) - wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), work); + wait_on_cpu_work(get_cwq(cpu, wq), work); } static int __cancel_work_timer(struct work_struct *work, @@ -782,9 +816,8 @@ EXPORT_SYMBOL(schedule_delayed_work); void flush_delayed_work(struct delayed_work *dwork) { if (del_timer_sync(&dwork->timer)) { - struct cpu_workqueue_struct *cwq; - cwq = wq_per_cpu(get_wq_data(&dwork->work)->wq, get_cpu()); - __queue_work(cwq, &dwork->work); + __queue_work(get_cpu(), get_wq_data(&dwork->work)->wq, + &dwork->work); put_cpu(); } flush_work(&dwork->work); @@ -991,13 +1024,11 @@ struct workqueue_struct *__create_workqueue_key(const char *name, wq = kzalloc(sizeof(*wq), GFP_KERNEL); if (!wq) - return NULL; + goto err; wq->cpu_wq = alloc_percpu(struct cpu_workqueue_struct); - if (!wq->cpu_wq) { - kfree(wq); - return NULL; - } + if (!wq->cpu_wq) + goto err; wq->name = name; lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); @@ -1041,6 +1072,12 @@ struct workqueue_struct *__create_workqueue_key(const char *name, wq = NULL; } return wq; +err: + if (wq) { + free_percpu(wq->cpu_wq); + kfree(wq); + } + return NULL; } EXPORT_SYMBOL_GPL(__create_workqueue_key); -- cgit From 97e37d7b9e65a6ac939f796f91081135b7a08acc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:10 +0200 Subject: workqueue: merge feature parameters into flags Currently, __create_workqueue_key() takes @singlethread and @freezeable paramters and store them separately in workqueue_struct. Merge them into a single flags parameter and field and use WQ_FREEZEABLE and WQ_SINGLE_THREAD. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 25 +++++++++++++++---------- kernel/workqueue.c | 17 +++++++---------- 2 files changed, 22 insertions(+), 20 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index e724dafc9e6d..d89cfc143b1a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -184,13 +184,17 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } #define work_clear_pending(work) \ clear_bit(WORK_STRUCT_PENDING, work_data_bits(work)) +enum { + WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ + WQ_SINGLE_THREAD = 1 << 1, /* no per-cpu worker */ +}; extern struct workqueue_struct * -__create_workqueue_key(const char *name, int singlethread, int freezeable, +__create_workqueue_key(const char *name, unsigned int flags, struct lock_class_key *key, const char *lock_name); #ifdef CONFIG_LOCKDEP -#define __create_workqueue(name, singlethread, freezeable) \ +#define __create_workqueue(name, flags) \ ({ \ static struct lock_class_key __key; \ const char *__lock_name; \ @@ -200,19 +204,20 @@ __create_workqueue_key(const char *name, int singlethread, int freezeable, else \ __lock_name = #name; \ \ - __create_workqueue_key((name), (singlethread), \ - (freezeable), &__key, \ + __create_workqueue_key((name), (flags), &__key, \ __lock_name); \ }) #else -#define __create_workqueue(name, singlethread, freezeable) \ - __create_workqueue_key((name), (singlethread), (freezeable), \ - NULL, NULL) +#define __create_workqueue(name, flags) \ + __create_workqueue_key((name), (flags), NULL, NULL) #endif -#define create_workqueue(name) __create_workqueue((name), 0, 0) -#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1) -#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0) +#define create_workqueue(name) \ + __create_workqueue((name), 0) +#define create_freezeable_workqueue(name) \ + __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_THREAD) +#define create_singlethread_workqueue(name) \ + __create_workqueue((name), WQ_SINGLE_THREAD) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c56146a755e5..68e4dd808ec0 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -67,11 +67,10 @@ struct cpu_workqueue_struct { * per-CPU workqueues: */ struct workqueue_struct { + unsigned int flags; /* I: WQ_* flags */ struct cpu_workqueue_struct *cpu_wq; /* I: cwq's */ struct list_head list; /* W: list of all workqueues */ const char *name; /* I: workqueue name */ - int singlethread; - int freezeable; /* Freeze threads during suspend */ #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif @@ -203,9 +202,9 @@ static const struct cpumask *cpu_singlethread_map __read_mostly; static cpumask_var_t cpu_populated_map __read_mostly; /* If it's single threaded, it isn't in the list of workqueues. */ -static inline int is_wq_single_threaded(struct workqueue_struct *wq) +static inline bool is_wq_single_threaded(struct workqueue_struct *wq) { - return wq->singlethread; + return wq->flags & WQ_SINGLE_THREAD; } static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq) @@ -463,7 +462,7 @@ static int worker_thread(void *__cwq) struct cpu_workqueue_struct *cwq = __cwq; DEFINE_WAIT(wait); - if (cwq->wq->freezeable) + if (cwq->wq->flags & WQ_FREEZEABLE) set_freezable(); for (;;) { @@ -1013,8 +1012,7 @@ static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) } struct workqueue_struct *__create_workqueue_key(const char *name, - int singlethread, - int freezeable, + unsigned int flags, struct lock_class_key *key, const char *lock_name) { @@ -1030,13 +1028,12 @@ struct workqueue_struct *__create_workqueue_key(const char *name, if (!wq->cpu_wq) goto err; + wq->flags = flags; wq->name = name; lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); - wq->singlethread = singlethread; - wq->freezeable = freezeable; INIT_LIST_HEAD(&wq->list); - if (singlethread) { + if (flags & WQ_SINGLE_THREAD) { cwq = init_cpu_workqueue(wq, singlethread_cpu); err = create_workqueue_thread(cwq, singlethread_cpu); start_workqueue_thread(cwq, -1); -- cgit From 22df02bb3fab24af97bff4c69cc6fd8529fc66fe Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:10 +0200 Subject: workqueue: define masks for work flags and conditionalize STATIC flags Work flags are about to see more traditional mask handling. Define WORK_STRUCT_*_BIT as the bit position constant and redefine WORK_STRUCT_* as bit masks. Also, make WORK_STRUCT_STATIC_* flags conditional While at it, re-define these constants as enums and use WORK_STRUCT_STATIC instead of hard-coding 2 in WORK_DATA_STATIC_INIT(). Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 29 +++++++++++++++++++++-------- kernel/workqueue.c | 12 ++++++------ 2 files changed, 27 insertions(+), 14 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index d89cfc143b1a..d60c5701ab45 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -22,12 +22,25 @@ typedef void (*work_func_t)(struct work_struct *work); */ #define work_data_bits(work) ((unsigned long *)(&(work)->data)) +enum { + WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ +#ifdef CONFIG_DEBUG_OBJECTS_WORK + WORK_STRUCT_STATIC_BIT = 1, /* static initializer (debugobjects) */ +#endif + + WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, +#ifdef CONFIG_DEBUG_OBJECTS_WORK + WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, +#else + WORK_STRUCT_STATIC = 0, +#endif + + WORK_STRUCT_FLAG_MASK = 3UL, + WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, +}; + struct work_struct { atomic_long_t data; -#define WORK_STRUCT_PENDING 0 /* T if work item pending execution */ -#define WORK_STRUCT_STATIC 1 /* static initializer (debugobjects) */ -#define WORK_STRUCT_FLAG_MASK (3UL) -#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) struct list_head entry; work_func_t func; #ifdef CONFIG_LOCKDEP @@ -36,7 +49,7 @@ struct work_struct { }; #define WORK_DATA_INIT() ATOMIC_LONG_INIT(0) -#define WORK_DATA_STATIC_INIT() ATOMIC_LONG_INIT(2) +#define WORK_DATA_STATIC_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_STATIC) struct delayed_work { struct work_struct work; @@ -98,7 +111,7 @@ extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); static inline unsigned int work_static(struct work_struct *work) { - return *work_data_bits(work) & (1 << WORK_STRUCT_STATIC); + return *work_data_bits(work) & WORK_STRUCT_STATIC; } #else static inline void __init_work(struct work_struct *work, int onstack) { } @@ -167,7 +180,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } * @work: The work item in question */ #define work_pending(work) \ - test_bit(WORK_STRUCT_PENDING, work_data_bits(work)) + test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) /** * delayed_work_pending - Find out whether a delayable work item is currently @@ -182,7 +195,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } * @work: The work item in question */ #define work_clear_pending(work) \ - clear_bit(WORK_STRUCT_PENDING, work_data_bits(work)) + clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) enum { WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 68e4dd808ec0..5c49d762293b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -115,7 +115,7 @@ static int work_fixup_activate(void *addr, enum debug_obj_state state) * statically initialized. We just make sure that it * is tracked in the object tracker. */ - if (test_bit(WORK_STRUCT_STATIC, work_data_bits(work))) { + if (test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work))) { debug_object_init(work, &work_debug_descr); debug_object_activate(work, &work_debug_descr); return 0; @@ -232,7 +232,7 @@ static inline void set_wq_data(struct work_struct *work, BUG_ON(!work_pending(work)); atomic_long_set(&work->data, (unsigned long)cwq | work_static(work) | - (1UL << WORK_STRUCT_PENDING) | extra_flags); + WORK_STRUCT_PENDING | extra_flags); } /* @@ -330,7 +330,7 @@ queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { int ret = 0; - if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) { + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_work(cpu, wq, work); ret = 1; } @@ -380,7 +380,7 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; - if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) { + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { BUG_ON(timer_pending(timer)); BUG_ON(!list_empty(&work->entry)); @@ -516,7 +516,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, * might deadlock. */ INIT_WORK_ON_STACK(&barr->work, wq_barrier_func); - __set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work)); + __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion(&barr->done); debug_work_activate(&barr->work); @@ -628,7 +628,7 @@ static int try_to_grab_pending(struct work_struct *work) struct cpu_workqueue_struct *cwq; int ret = -1; - if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; /* -- cgit From 0f900049cbe2767d47c2a62b54f0e822e1d66840 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:11 +0200 Subject: workqueue: update cwq alignement work->data field is used for two purposes. It points to cwq it's queued on and the lower bits are used for flags. Currently, two bits are reserved which is always safe as 4 byte alignment is guaranteed on every architecture. However, future changes will need more flag bits. On SMP, the percpu allocator is capable of honoring larger alignment (there are other users which depend on it) and larger alignment works just fine. On UP, percpu allocator is a thin wrapper around kzalloc/kfree() and don't honor alignment request. This patch introduces WORK_STRUCT_FLAG_BITS and implements alloc/free_cwqs() which guarantees max(1 << WORK_STRUCT_FLAG_BITS, __alignof__(unsigned long long) alignment both on SMP and UP. On SMP, simply wrapping percpu allocator is enough. On UP, extra space is allocated so that cwq can be aligned and the original pointer can be stored after it which is used in the free path. * Alignment problem on UP is reported by Michal Simek. Signed-off-by: Tejun Heo Cc: Christoph Lameter Cc: Ingo Molnar Cc: Frederic Weisbecker Reported-by: Michal Simek --- include/linux/workqueue.h | 5 +++- kernel/workqueue.c | 60 +++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 59 insertions(+), 6 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index d60c5701ab45..b90958a037dc 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -26,6 +26,9 @@ enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT = 1, /* static initializer (debugobjects) */ + WORK_STRUCT_FLAG_BITS = 2, +#else + WORK_STRUCT_FLAG_BITS = 1, #endif WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, @@ -35,7 +38,7 @@ enum { WORK_STRUCT_STATIC = 0, #endif - WORK_STRUCT_FLAG_MASK = 3UL, + WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, }; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index dc78956ccf03..74a38499b19a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -46,7 +46,9 @@ /* * The per-CPU workqueue (if single thread, we always use the first - * possible cpu). + * possible cpu). The lower WORK_STRUCT_FLAG_BITS of + * work_struct->data are used for flags and thus cwqs need to be + * aligned at two's power of the number of flag bits. */ struct cpu_workqueue_struct { @@ -59,7 +61,7 @@ struct cpu_workqueue_struct { struct workqueue_struct *wq; /* I: the owning workqueue */ struct task_struct *thread; -} ____cacheline_aligned; +}; /* * The externally visible workqueue abstraction is an array of @@ -967,6 +969,53 @@ int current_is_keventd(void) } +static struct cpu_workqueue_struct *alloc_cwqs(void) +{ + /* + * cwqs are forced aligned according to WORK_STRUCT_FLAG_BITS. + * Make sure that the alignment isn't lower than that of + * unsigned long long. + */ + const size_t size = sizeof(struct cpu_workqueue_struct); + const size_t align = max_t(size_t, 1 << WORK_STRUCT_FLAG_BITS, + __alignof__(unsigned long long)); + struct cpu_workqueue_struct *cwqs; +#ifndef CONFIG_SMP + void *ptr; + + /* + * On UP, percpu allocator doesn't honor alignment parameter + * and simply uses arch-dependent default. Allocate enough + * room to align cwq and put an extra pointer at the end + * pointing back to the originally allocated pointer which + * will be used for free. + * + * FIXME: This really belongs to UP percpu code. Update UP + * percpu code to honor alignment and remove this ugliness. + */ + ptr = __alloc_percpu(size + align + sizeof(void *), 1); + cwqs = PTR_ALIGN(ptr, align); + *(void **)per_cpu_ptr(cwqs + 1, 0) = ptr; +#else + /* On SMP, percpu allocator can do it itself */ + cwqs = __alloc_percpu(size, align); +#endif + /* just in case, make sure it's actually aligned */ + BUG_ON(!IS_ALIGNED((unsigned long)cwqs, align)); + return cwqs; +} + +static void free_cwqs(struct cpu_workqueue_struct *cwqs) +{ +#ifndef CONFIG_SMP + /* on UP, the pointer to free is stored right after the cwq */ + if (cwqs) + free_percpu(*(void **)per_cpu_ptr(cwqs + 1, 0)); +#else + free_percpu(cwqs); +#endif +} + static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) { struct workqueue_struct *wq = cwq->wq; @@ -1012,7 +1061,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name, if (!wq) goto err; - wq->cpu_wq = alloc_percpu(struct cpu_workqueue_struct); + wq->cpu_wq = alloc_cwqs(); if (!wq->cpu_wq) goto err; @@ -1031,6 +1080,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name, for_each_possible_cpu(cpu) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + BUG_ON((unsigned long)cwq & WORK_STRUCT_FLAG_MASK); cwq->wq = wq; cwq->cpu = cpu; spin_lock_init(&cwq->lock); @@ -1059,7 +1109,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name, return wq; err: if (wq) { - free_percpu(wq->cpu_wq); + free_cwqs(wq->cpu_wq); kfree(wq); } return NULL; @@ -1112,7 +1162,7 @@ void destroy_workqueue(struct workqueue_struct *wq) for_each_possible_cpu(cpu) cleanup_workqueue_thread(get_cwq(cpu, wq)); - free_percpu(wq->cpu_wq); + free_cwqs(wq->cpu_wq); kfree(wq); } EXPORT_SYMBOL_GPL(destroy_workqueue); -- cgit From 73f53c4aa732eced5fcb1844d3d452c30905f20f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:11 +0200 Subject: workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 21 ++- kernel/workqueue.c | 355 +++++++++++++++++++++++++++++++++++++++------- 2 files changed, 322 insertions(+), 54 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index b90958a037dc..8762f62103d8 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -26,11 +26,13 @@ enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT = 1, /* static initializer (debugobjects) */ - WORK_STRUCT_FLAG_BITS = 2, + WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ #else - WORK_STRUCT_FLAG_BITS = 1, + WORK_STRUCT_COLOR_SHIFT = 2, /* color for workqueue flushing */ #endif + WORK_STRUCT_COLOR_BITS = 4, + WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, @@ -38,6 +40,21 @@ enum { WORK_STRUCT_STATIC = 0, #endif + /* + * The last color is no color used for works which don't + * participate in workqueue flushing. + */ + WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS) - 1, + WORK_NO_COLOR = WORK_NR_COLORS, + + /* + * Reserve 6 bits off of cwq pointer w/ debugobjects turned + * off. This makes cwqs aligned to 64 bytes which isn't too + * excessive while allowing 15 workqueue flush colors. + */ + WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + + WORK_STRUCT_COLOR_BITS, + WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, }; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 74a38499b19a..56e47c59d73b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -41,6 +41,8 @@ * * L: cwq->lock protected. Access with cwq->lock held. * + * F: wq->flush_mutex protected. + * * W: workqueue_lock protected. */ @@ -60,9 +62,22 @@ struct cpu_workqueue_struct { unsigned int cpu; struct workqueue_struct *wq; /* I: the owning workqueue */ + int work_color; /* L: current color */ + int flush_color; /* L: flushing color */ + int nr_in_flight[WORK_NR_COLORS]; + /* L: nr of in_flight works */ struct task_struct *thread; }; +/* + * Structure used to wait for workqueue flush. + */ +struct wq_flusher { + struct list_head list; /* F: list of flushers */ + int flush_color; /* F: flush color waiting for */ + struct completion done; /* flush completion */ +}; + /* * The externally visible workqueue abstraction is an array of * per-CPU workqueues: @@ -71,6 +86,15 @@ struct workqueue_struct { unsigned int flags; /* I: WQ_* flags */ struct cpu_workqueue_struct *cpu_wq; /* I: cwq's */ struct list_head list; /* W: list of all workqueues */ + + struct mutex flush_mutex; /* protects wq flushing */ + int work_color; /* F: current work color */ + int flush_color; /* F: current flush color */ + atomic_t nr_cwqs_to_flush; /* flush in progress */ + struct wq_flusher *first_flusher; /* F: first flusher */ + struct list_head flusher_queue; /* F: flush waiters */ + struct list_head flusher_overflow; /* F: flush overflow list */ + const char *name; /* I: workqueue name */ #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; @@ -207,6 +231,22 @@ static struct cpu_workqueue_struct *target_cwq(unsigned int cpu, return get_cwq(cpu, wq); } +static unsigned int work_color_to_flags(int color) +{ + return color << WORK_STRUCT_COLOR_SHIFT; +} + +static int get_work_color(struct work_struct *work) +{ + return (*work_data_bits(work) >> WORK_STRUCT_COLOR_SHIFT) & + ((1 << WORK_STRUCT_COLOR_BITS) - 1); +} + +static int work_next_color(int color) +{ + return (color + 1) % WORK_NR_COLORS; +} + /* * Set the workqueue on which a work item is to be run * - Must *only* be called if the pending flag is set @@ -273,7 +313,9 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, debug_work_activate(work); spin_lock_irqsave(&cwq->lock, flags); BUG_ON(!list_empty(&work->entry)); - insert_work(cwq, work, &cwq->worklist, 0); + cwq->nr_in_flight[cwq->work_color]++; + insert_work(cwq, work, &cwq->worklist, + work_color_to_flags(cwq->work_color)); spin_unlock_irqrestore(&cwq->lock, flags); } @@ -386,6 +428,44 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL_GPL(queue_delayed_work_on); +/** + * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight + * @cwq: cwq of interest + * @color: color of work which left the queue + * + * A work either has completed or is removed from pending queue, + * decrement nr_in_flight of its cwq and handle workqueue flushing. + * + * CONTEXT: + * spin_lock_irq(cwq->lock). + */ +static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) +{ + /* ignore uncolored works */ + if (color == WORK_NO_COLOR) + return; + + cwq->nr_in_flight[color]--; + + /* is flush in progress and are we at the flushing tip? */ + if (likely(cwq->flush_color != color)) + return; + + /* are there still in-flight works? */ + if (cwq->nr_in_flight[color]) + return; + + /* this cwq is done, clear flush_color */ + cwq->flush_color = -1; + + /* + * If this was the last cwq, wake up the first flusher. It + * will handle the rest. + */ + if (atomic_dec_and_test(&cwq->wq->nr_cwqs_to_flush)) + complete(&cwq->wq->first_flusher->done); +} + /** * process_one_work - process single work * @cwq: cwq to process work for @@ -404,6 +484,7 @@ static void process_one_work(struct cpu_workqueue_struct *cwq, struct work_struct *work) { work_func_t f = work->func; + int work_color; #ifdef CONFIG_LOCKDEP /* * It is permissible to free the struct work_struct from @@ -417,6 +498,7 @@ static void process_one_work(struct cpu_workqueue_struct *cwq, /* claim and process */ debug_work_deactivate(work); cwq->current_work = work; + work_color = get_work_color(work); list_del_init(&work->entry); spin_unlock_irq(&cwq->lock); @@ -443,6 +525,7 @@ static void process_one_work(struct cpu_workqueue_struct *cwq, /* we're done with it, release */ cwq->current_work = NULL; + cwq_dec_nr_in_flight(cwq, work_color); } static void run_workqueue(struct cpu_workqueue_struct *cwq) @@ -529,29 +612,78 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, init_completion(&barr->done); debug_work_activate(&barr->work); - insert_work(cwq, &barr->work, head, 0); + insert_work(cwq, &barr->work, head, work_color_to_flags(WORK_NO_COLOR)); } -static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) +/** + * flush_workqueue_prep_cwqs - prepare cwqs for workqueue flushing + * @wq: workqueue being flushed + * @flush_color: new flush color, < 0 for no-op + * @work_color: new work color, < 0 for no-op + * + * Prepare cwqs for workqueue flushing. + * + * If @flush_color is non-negative, flush_color on all cwqs should be + * -1. If no cwq has in-flight commands at the specified color, all + * cwq->flush_color's stay at -1 and %false is returned. If any cwq + * has in flight commands, its cwq->flush_color is set to + * @flush_color, @wq->nr_cwqs_to_flush is updated accordingly, cwq + * wakeup logic is armed and %true is returned. + * + * The caller should have initialized @wq->first_flusher prior to + * calling this function with non-negative @flush_color. If + * @flush_color is negative, no flush color update is done and %false + * is returned. + * + * If @work_color is non-negative, all cwqs should have the same + * work_color which is previous to @work_color and all will be + * advanced to @work_color. + * + * CONTEXT: + * mutex_lock(wq->flush_mutex). + * + * RETURNS: + * %true if @flush_color >= 0 and there's something to flush. %false + * otherwise. + */ +static bool flush_workqueue_prep_cwqs(struct workqueue_struct *wq, + int flush_color, int work_color) { - int active = 0; - struct wq_barrier barr; + bool wait = false; + unsigned int cpu; - WARN_ON(cwq->thread == current); - - spin_lock_irq(&cwq->lock); - if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) { - insert_wq_barrier(cwq, &barr, &cwq->worklist); - active = 1; + if (flush_color >= 0) { + BUG_ON(atomic_read(&wq->nr_cwqs_to_flush)); + atomic_set(&wq->nr_cwqs_to_flush, 1); } - spin_unlock_irq(&cwq->lock); - if (active) { - wait_for_completion(&barr.done); - destroy_work_on_stack(&barr.work); + for_each_possible_cpu(cpu) { + struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + + spin_lock_irq(&cwq->lock); + + if (flush_color >= 0) { + BUG_ON(cwq->flush_color != -1); + + if (cwq->nr_in_flight[flush_color]) { + cwq->flush_color = flush_color; + atomic_inc(&wq->nr_cwqs_to_flush); + wait = true; + } + } + + if (work_color >= 0) { + BUG_ON(work_color != work_next_color(cwq->work_color)); + cwq->work_color = work_color; + } + + spin_unlock_irq(&cwq->lock); } - return active; + if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_cwqs_to_flush)) + complete(&wq->first_flusher->done); + + return wait; } /** @@ -566,13 +698,143 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) */ void flush_workqueue(struct workqueue_struct *wq) { - int cpu; + struct wq_flusher this_flusher = { + .list = LIST_HEAD_INIT(this_flusher.list), + .flush_color = -1, + .done = COMPLETION_INITIALIZER_ONSTACK(this_flusher.done), + }; + int next_color; - might_sleep(); lock_map_acquire(&wq->lockdep_map); lock_map_release(&wq->lockdep_map); - for_each_possible_cpu(cpu) - flush_cpu_workqueue(get_cwq(cpu, wq)); + + mutex_lock(&wq->flush_mutex); + + /* + * Start-to-wait phase + */ + next_color = work_next_color(wq->work_color); + + if (next_color != wq->flush_color) { + /* + * Color space is not full. The current work_color + * becomes our flush_color and work_color is advanced + * by one. + */ + BUG_ON(!list_empty(&wq->flusher_overflow)); + this_flusher.flush_color = wq->work_color; + wq->work_color = next_color; + + if (!wq->first_flusher) { + /* no flush in progress, become the first flusher */ + BUG_ON(wq->flush_color != this_flusher.flush_color); + + wq->first_flusher = &this_flusher; + + if (!flush_workqueue_prep_cwqs(wq, wq->flush_color, + wq->work_color)) { + /* nothing to flush, done */ + wq->flush_color = next_color; + wq->first_flusher = NULL; + goto out_unlock; + } + } else { + /* wait in queue */ + BUG_ON(wq->flush_color == this_flusher.flush_color); + list_add_tail(&this_flusher.list, &wq->flusher_queue); + flush_workqueue_prep_cwqs(wq, -1, wq->work_color); + } + } else { + /* + * Oops, color space is full, wait on overflow queue. + * The next flush completion will assign us + * flush_color and transfer to flusher_queue. + */ + list_add_tail(&this_flusher.list, &wq->flusher_overflow); + } + + mutex_unlock(&wq->flush_mutex); + + wait_for_completion(&this_flusher.done); + + /* + * Wake-up-and-cascade phase + * + * First flushers are responsible for cascading flushes and + * handling overflow. Non-first flushers can simply return. + */ + if (wq->first_flusher != &this_flusher) + return; + + mutex_lock(&wq->flush_mutex); + + wq->first_flusher = NULL; + + BUG_ON(!list_empty(&this_flusher.list)); + BUG_ON(wq->flush_color != this_flusher.flush_color); + + while (true) { + struct wq_flusher *next, *tmp; + + /* complete all the flushers sharing the current flush color */ + list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) { + if (next->flush_color != wq->flush_color) + break; + list_del_init(&next->list); + complete(&next->done); + } + + BUG_ON(!list_empty(&wq->flusher_overflow) && + wq->flush_color != work_next_color(wq->work_color)); + + /* this flush_color is finished, advance by one */ + wq->flush_color = work_next_color(wq->flush_color); + + /* one color has been freed, handle overflow queue */ + if (!list_empty(&wq->flusher_overflow)) { + /* + * Assign the same color to all overflowed + * flushers, advance work_color and append to + * flusher_queue. This is the start-to-wait + * phase for these overflowed flushers. + */ + list_for_each_entry(tmp, &wq->flusher_overflow, list) + tmp->flush_color = wq->work_color; + + wq->work_color = work_next_color(wq->work_color); + + list_splice_tail_init(&wq->flusher_overflow, + &wq->flusher_queue); + flush_workqueue_prep_cwqs(wq, -1, wq->work_color); + } + + if (list_empty(&wq->flusher_queue)) { + BUG_ON(wq->flush_color != wq->work_color); + break; + } + + /* + * Need to flush more colors. Make the next flusher + * the new first flusher and arm cwqs. + */ + BUG_ON(wq->flush_color == wq->work_color); + BUG_ON(wq->flush_color != next->flush_color); + + list_del_init(&next->list); + wq->first_flusher = next; + + if (flush_workqueue_prep_cwqs(wq, wq->flush_color, -1)) + break; + + /* + * Meh... this color is already done, clear first + * flusher and repeat cascading. + */ + wq->first_flusher = NULL; + } + +out_unlock: + mutex_unlock(&wq->flush_mutex); } EXPORT_SYMBOL_GPL(flush_workqueue); @@ -659,6 +921,7 @@ static int try_to_grab_pending(struct work_struct *work) if (cwq == get_wq_data(work)) { debug_work_deactivate(work); list_del_init(&work->entry); + cwq_dec_nr_in_flight(cwq, get_work_color(work)); ret = 1; } } @@ -1066,6 +1329,10 @@ struct workqueue_struct *__create_workqueue_key(const char *name, goto err; wq->flags = flags; + mutex_init(&wq->flush_mutex); + atomic_set(&wq->nr_cwqs_to_flush, 0); + INIT_LIST_HEAD(&wq->flusher_queue); + INIT_LIST_HEAD(&wq->flusher_overflow); wq->name = name; lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); INIT_LIST_HEAD(&wq->list); @@ -1083,6 +1350,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name, BUG_ON((unsigned long)cwq & WORK_STRUCT_FLAG_MASK); cwq->wq = wq; cwq->cpu = cpu; + cwq->flush_color = -1; spin_lock_init(&cwq->lock); INIT_LIST_HEAD(&cwq->worklist); init_waitqueue_head(&cwq->more_work); @@ -1116,33 +1384,6 @@ err: } EXPORT_SYMBOL_GPL(__create_workqueue_key); -static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) -{ - /* - * Our caller is either destroy_workqueue() or CPU_POST_DEAD, - * cpu_add_remove_lock protects cwq->thread. - */ - if (cwq->thread == NULL) - return; - - lock_map_acquire(&cwq->wq->lockdep_map); - lock_map_release(&cwq->wq->lockdep_map); - - flush_cpu_workqueue(cwq); - /* - * If the caller is CPU_POST_DEAD and cwq->worklist was not empty, - * a concurrent flush_workqueue() can insert a barrier after us. - * However, in that case run_workqueue() won't return and check - * kthread_should_stop() until it flushes all work_struct's. - * When ->worklist becomes empty it is safe to exit because no - * more work_structs can be queued on this cwq: flush_workqueue - * checks list_empty(), and a "normal" queue_work() can't use - * a dead CPU. - */ - kthread_stop(cwq->thread); - cwq->thread = NULL; -} - /** * destroy_workqueue - safely terminate a workqueue * @wq: target workqueue @@ -1159,8 +1400,20 @@ void destroy_workqueue(struct workqueue_struct *wq) spin_unlock(&workqueue_lock); cpu_maps_update_done(); - for_each_possible_cpu(cpu) - cleanup_workqueue_thread(get_cwq(cpu, wq)); + flush_workqueue(wq); + + for_each_possible_cpu(cpu) { + struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + int i; + + if (cwq->thread) { + kthread_stop(cwq->thread); + cwq->thread = NULL; + } + + for (i = 0; i < WORK_NR_COLORS; i++) + BUG_ON(cwq->nr_in_flight[i]); + } free_cwqs(wq->cpu_wq); kfree(wq); @@ -1185,9 +1438,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, switch (action) { case CPU_POST_DEAD: - lock_map_acquire(&cwq->wq->lockdep_map); - lock_map_release(&cwq->wq->lockdep_map); - flush_cpu_workqueue(cwq); + flush_workqueue(wq); break; } } -- cgit From affee4b294a0fc97d67c8a77dc080c4dd262a79e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:12 +0200 Subject: workqueue: reimplement work flushing using linked works A work is linked to the next one by having WORK_STRUCT_LINKED bit set and these links can be chained. When a linked work is dispatched to a worker, all linked works are dispatched to the worker's newly added ->scheduled queue and processed back-to-back. Currently, as there's only single worker per cwq, having linked works doesn't make any visible behavior difference. This change is to prepare for multiple shared workers per cpu. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 4 +- kernel/workqueue.c | 152 +++++++++++++++++++++++++++++++++++++++------- 2 files changed, 134 insertions(+), 22 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 8762f62103d8..4f4fdba722c3 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -24,8 +24,9 @@ typedef void (*work_func_t)(struct work_struct *work); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ + WORK_STRUCT_LINKED_BIT = 1, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK - WORK_STRUCT_STATIC_BIT = 1, /* static initializer (debugobjects) */ + WORK_STRUCT_STATIC_BIT = 2, /* static initializer (debugobjects) */ WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ #else WORK_STRUCT_COLOR_SHIFT = 2, /* color for workqueue flushing */ @@ -34,6 +35,7 @@ enum { WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, + WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, #else diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 600db10a4dbf..9953d3c7bd10 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -51,6 +51,7 @@ struct cpu_workqueue_struct; struct worker { struct work_struct *current_work; /* L: work being processed */ + struct list_head scheduled; /* L: scheduled works */ struct task_struct *task; /* I: worker task */ struct cpu_workqueue_struct *cwq; /* I: the associated cwq */ int id; /* I: worker id */ @@ -445,6 +446,8 @@ static struct worker *alloc_worker(void) struct worker *worker; worker = kzalloc(sizeof(*worker), GFP_KERNEL); + if (worker) + INIT_LIST_HEAD(&worker->scheduled); return worker; } @@ -530,6 +533,7 @@ static void destroy_worker(struct worker *worker) /* sanity check frenzy */ BUG_ON(worker->current_work); + BUG_ON(!list_empty(&worker->scheduled)); kthread_stop(worker->task); kfree(worker); @@ -539,6 +543,47 @@ static void destroy_worker(struct worker *worker) spin_unlock(&workqueue_lock); } +/** + * move_linked_works - move linked works to a list + * @work: start of series of works to be scheduled + * @head: target list to append @work to + * @nextp: out paramter for nested worklist walking + * + * Schedule linked works starting from @work to @head. Work series to + * be scheduled starts at @work and includes any consecutive work with + * WORK_STRUCT_LINKED set in its predecessor. + * + * If @nextp is not NULL, it's updated to point to the next work of + * the last scheduled work. This allows move_linked_works() to be + * nested inside outer list_for_each_entry_safe(). + * + * CONTEXT: + * spin_lock_irq(cwq->lock). + */ +static void move_linked_works(struct work_struct *work, struct list_head *head, + struct work_struct **nextp) +{ + struct work_struct *n; + + /* + * Linked worklist will always end before the end of the list, + * use NULL for list head. + */ + list_for_each_entry_safe_from(work, n, NULL, entry) { + list_move_tail(&work->entry, head); + if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) + break; + } + + /* + * If we're already inside safe list traversal and have moved + * multiple works to the scheduled queue, the next position + * needs to be updated. + */ + if (nextp) + *nextp = n; +} + /** * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight * @cwq: cwq of interest @@ -639,17 +684,25 @@ static void process_one_work(struct worker *worker, struct work_struct *work) cwq_dec_nr_in_flight(cwq, work_color); } -static void run_workqueue(struct worker *worker) +/** + * process_scheduled_works - process scheduled works + * @worker: self + * + * Process all scheduled works. Please note that the scheduled list + * may change while processing a work, so this function repeatedly + * fetches a work from the top and executes it. + * + * CONTEXT: + * spin_lock_irq(cwq->lock) which may be released and regrabbed + * multiple times. + */ +static void process_scheduled_works(struct worker *worker) { - struct cpu_workqueue_struct *cwq = worker->cwq; - - spin_lock_irq(&cwq->lock); - while (!list_empty(&cwq->worklist)) { - struct work_struct *work = list_entry(cwq->worklist.next, + while (!list_empty(&worker->scheduled)) { + struct work_struct *work = list_first_entry(&worker->scheduled, struct work_struct, entry); process_one_work(worker, work); } - spin_unlock_irq(&cwq->lock); } /** @@ -684,7 +737,28 @@ static int worker_thread(void *__worker) get_cpu_mask(cwq->cpu)))) set_cpus_allowed_ptr(worker->task, get_cpu_mask(cwq->cpu)); - run_workqueue(worker); + + spin_lock_irq(&cwq->lock); + + while (!list_empty(&cwq->worklist)) { + struct work_struct *work = + list_first_entry(&cwq->worklist, + struct work_struct, entry); + + if (likely(!(*work_data_bits(work) & + WORK_STRUCT_LINKED))) { + /* optimization path, not strictly necessary */ + process_one_work(worker, work); + if (unlikely(!list_empty(&worker->scheduled))) + process_scheduled_works(worker); + } else { + move_linked_works(work, &worker->scheduled, + NULL); + process_scheduled_works(worker); + } + } + + spin_unlock_irq(&cwq->lock); } return 0; @@ -705,16 +779,33 @@ static void wq_barrier_func(struct work_struct *work) * insert_wq_barrier - insert a barrier work * @cwq: cwq to insert barrier into * @barr: wq_barrier to insert - * @head: insertion point + * @target: target work to attach @barr to + * @worker: worker currently executing @target, NULL if @target is not executing * - * Insert barrier @barr into @cwq before @head. + * @barr is linked to @target such that @barr is completed only after + * @target finishes execution. Please note that the ordering + * guarantee is observed only with respect to @target and on the local + * cpu. + * + * Currently, a queued barrier can't be canceled. This is because + * try_to_grab_pending() can't determine whether the work to be + * grabbed is at the head of the queue and thus can't clear LINKED + * flag of the previous work while there must be a valid next work + * after a work with LINKED flag set. + * + * Note that when @worker is non-NULL, @target may be modified + * underneath us, so we can't reliably determine cwq from @target. * * CONTEXT: * spin_lock_irq(cwq->lock). */ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, - struct wq_barrier *barr, struct list_head *head) + struct wq_barrier *barr, + struct work_struct *target, struct worker *worker) { + struct list_head *head; + unsigned int linked = 0; + /* * debugobject calls are safe here even with cwq->lock locked * as we know for sure that this will not trigger any of the @@ -725,8 +816,24 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion(&barr->done); + /* + * If @target is currently being executed, schedule the + * barrier to the worker; otherwise, put it after @target. + */ + if (worker) + head = worker->scheduled.next; + else { + unsigned long *bits = work_data_bits(target); + + head = target->entry.next; + /* there can already be other linked works, inherit and set */ + linked = *bits & WORK_STRUCT_LINKED; + __set_bit(WORK_STRUCT_LINKED_BIT, bits); + } + debug_work_activate(&barr->work); - insert_work(cwq, &barr->work, head, work_color_to_flags(WORK_NO_COLOR)); + insert_work(cwq, &barr->work, head, + work_color_to_flags(WORK_NO_COLOR) | linked); } /** @@ -964,8 +1071,8 @@ EXPORT_SYMBOL_GPL(flush_workqueue); */ int flush_work(struct work_struct *work) { + struct worker *worker = NULL; struct cpu_workqueue_struct *cwq; - struct list_head *prev; struct wq_barrier barr; might_sleep(); @@ -985,14 +1092,14 @@ int flush_work(struct work_struct *work) smp_rmb(); if (unlikely(cwq != get_wq_data(work))) goto already_gone; - prev = &work->entry; } else { - if (!cwq->worker || cwq->worker->current_work != work) + if (cwq->worker && cwq->worker->current_work == work) + worker = cwq->worker; + if (!worker) goto already_gone; - prev = &cwq->worklist; } - insert_wq_barrier(cwq, &barr, prev->next); + insert_wq_barrier(cwq, &barr, work, worker); spin_unlock_irq(&cwq->lock); wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); @@ -1048,16 +1155,19 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq, struct work_struct *work) { struct wq_barrier barr; - int running = 0; + struct worker *worker; spin_lock_irq(&cwq->lock); + + worker = NULL; if (unlikely(cwq->worker && cwq->worker->current_work == work)) { - insert_wq_barrier(cwq, &barr, cwq->worklist.next); - running = 1; + worker = cwq->worker; + insert_wq_barrier(cwq, &barr, work, worker); } + spin_unlock_irq(&cwq->lock); - if (unlikely(running)) { + if (unlikely(worker)) { wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); } -- cgit From 1e19ffc63dbbaea7a7d1c63d99c38d3e5a4c7edf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:12 +0200 Subject: workqueue: implement per-cwq active work limit Add cwq->nr_active, cwq->max_active and cwq->delayed_work. nr_active counts the number of active works per cwq. A work is active if it's flushable (colored) and is on cwq's worklist. If nr_active reaches max_active, new works are queued on cwq->delayed_work and activated later as works on the cwq complete and decrement nr_active. cwq->max_active can be specified via the new @max_active parameter to __create_workqueue() and is set to 1 for all workqueues for now. As each cwq has only single worker now, this double queueing doesn't cause any behavior difference visible to its users. This will be used to reimplement freeze/thaw and implement shared worker pool. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 18 +++++++++--------- kernel/workqueue.c | 39 +++++++++++++++++++++++++++++++++++++-- 2 files changed, 46 insertions(+), 11 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4f4fdba722c3..eb753b7790e5 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -225,11 +225,11 @@ enum { }; extern struct workqueue_struct * -__create_workqueue_key(const char *name, unsigned int flags, +__create_workqueue_key(const char *name, unsigned int flags, int max_active, struct lock_class_key *key, const char *lock_name); #ifdef CONFIG_LOCKDEP -#define __create_workqueue(name, flags) \ +#define __create_workqueue(name, flags, max_active) \ ({ \ static struct lock_class_key __key; \ const char *__lock_name; \ @@ -239,20 +239,20 @@ __create_workqueue_key(const char *name, unsigned int flags, else \ __lock_name = #name; \ \ - __create_workqueue_key((name), (flags), &__key, \ - __lock_name); \ + __create_workqueue_key((name), (flags), (max_active), \ + &__key, __lock_name); \ }) #else -#define __create_workqueue(name, flags) \ - __create_workqueue_key((name), (flags), NULL, NULL) +#define __create_workqueue(name, flags, max_active) \ + __create_workqueue_key((name), (flags), (max_active), NULL, NULL) #endif #define create_workqueue(name) \ - __create_workqueue((name), 0) + __create_workqueue((name), 0, 1) #define create_freezeable_workqueue(name) \ - __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_THREAD) + __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_THREAD, 1) #define create_singlethread_workqueue(name) \ - __create_workqueue((name), WQ_SINGLE_THREAD) + __create_workqueue((name), WQ_SINGLE_THREAD, 1) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 9953d3c7bd10..e541b5db67dd 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -77,6 +77,9 @@ struct cpu_workqueue_struct { int flush_color; /* L: flushing color */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ + int nr_active; /* L: nr of active works */ + int max_active; /* I: max active works */ + struct list_head delayed_works; /* L: delayed works */ }; /* @@ -321,14 +324,24 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, struct work_struct *work) { struct cpu_workqueue_struct *cwq = target_cwq(cpu, wq); + struct list_head *worklist; unsigned long flags; debug_work_activate(work); + spin_lock_irqsave(&cwq->lock, flags); BUG_ON(!list_empty(&work->entry)); + cwq->nr_in_flight[cwq->work_color]++; - insert_work(cwq, work, &cwq->worklist, - work_color_to_flags(cwq->work_color)); + + if (likely(cwq->nr_active < cwq->max_active)) { + cwq->nr_active++; + worklist = &cwq->worklist; + } else + worklist = &cwq->delayed_works; + + insert_work(cwq, work, worklist, work_color_to_flags(cwq->work_color)); + spin_unlock_irqrestore(&cwq->lock, flags); } @@ -584,6 +597,15 @@ static void move_linked_works(struct work_struct *work, struct list_head *head, *nextp = n; } +static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) +{ + struct work_struct *work = list_first_entry(&cwq->delayed_works, + struct work_struct, entry); + + move_linked_works(work, &cwq->worklist, NULL); + cwq->nr_active++; +} + /** * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight * @cwq: cwq of interest @@ -602,6 +624,12 @@ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) return; cwq->nr_in_flight[color]--; + cwq->nr_active--; + + /* one down, submit a delayed one */ + if (!list_empty(&cwq->delayed_works) && + cwq->nr_active < cwq->max_active) + cwq_activate_first_delayed(cwq); /* is flush in progress and are we at the flushing tip? */ if (likely(cwq->flush_color != color)) @@ -1505,6 +1533,7 @@ static void free_cwqs(struct cpu_workqueue_struct *cwqs) struct workqueue_struct *__create_workqueue_key(const char *name, unsigned int flags, + int max_active, struct lock_class_key *key, const char *lock_name) { @@ -1513,6 +1542,8 @@ struct workqueue_struct *__create_workqueue_key(const char *name, bool failed = false; unsigned int cpu; + max_active = clamp_val(max_active, 1, INT_MAX); + wq = kzalloc(sizeof(*wq), GFP_KERNEL); if (!wq) goto err; @@ -1544,8 +1575,10 @@ struct workqueue_struct *__create_workqueue_key(const char *name, cwq->cpu = cpu; cwq->wq = wq; cwq->flush_color = -1; + cwq->max_active = max_active; spin_lock_init(&cwq->lock); INIT_LIST_HEAD(&cwq->worklist); + INIT_LIST_HEAD(&cwq->delayed_works); init_waitqueue_head(&cwq->more_work); if (failed) @@ -1607,6 +1640,8 @@ void destroy_workqueue(struct workqueue_struct *wq) for (i = 0; i < WORK_NR_COLORS; i++) BUG_ON(cwq->nr_in_flight[i]); + BUG_ON(cwq->nr_active); + BUG_ON(!list_empty(&cwq->delayed_works)); } free_cwqs(wq->cpu_wq); -- cgit From a0a1a5fd4fb15ec61117c759fe9f5c16c53d9e9c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:12 +0200 Subject: workqueue: reimplement workqueue freeze using max_active Currently, workqueue freezing is implemented by marking the worker freezeable and calling try_to_freeze() from dispatch loop. Reimplement it using cwq->limit so that the workqueue is frozen instead of the worker. * workqueue_struct->saved_max_active is added which stores the specified max_active on initialization. * On freeze, all cwq->max_active's are quenched to zero. Freezing is complete when nr_active on all cwqs reach zero. * On thaw, all cwq->max_active's are restored to wq->saved_max_active and the worklist is repopulated. This new implementation allows having single shared pool of workers per cpu. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 7 ++ kernel/power/process.c | 21 +++++- kernel/workqueue.c | 163 +++++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 179 insertions(+), 12 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index eb753b7790e5..ab0b7fb99bc2 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -340,4 +340,11 @@ static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) #else long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ + +#ifdef CONFIG_FREEZER +extern void freeze_workqueues_begin(void); +extern bool freeze_workqueues_busy(void); +extern void thaw_workqueues(void); +#endif /* CONFIG_FREEZER */ + #endif diff --git a/kernel/power/process.c b/kernel/power/process.c index 71ae29052ab6..028a99598f49 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -15,6 +15,7 @@ #include #include #include +#include /* * Timeout for stopping processes @@ -35,6 +36,7 @@ static int try_to_freeze_tasks(bool sig_only) struct task_struct *g, *p; unsigned long end_time; unsigned int todo; + bool wq_busy = false; struct timeval start, end; u64 elapsed_csecs64; unsigned int elapsed_csecs; @@ -42,6 +44,10 @@ static int try_to_freeze_tasks(bool sig_only) do_gettimeofday(&start); end_time = jiffies + TIMEOUT; + + if (!sig_only) + freeze_workqueues_begin(); + while (true) { todo = 0; read_lock(&tasklist_lock); @@ -63,6 +69,12 @@ static int try_to_freeze_tasks(bool sig_only) todo++; } while_each_thread(g, p); read_unlock(&tasklist_lock); + + if (!sig_only) { + wq_busy = freeze_workqueues_busy(); + todo += wq_busy; + } + if (!todo || time_after(jiffies, end_time)) break; @@ -86,8 +98,12 @@ static int try_to_freeze_tasks(bool sig_only) */ printk("\n"); printk(KERN_ERR "Freezing of tasks failed after %d.%02d seconds " - "(%d tasks refusing to freeze):\n", - elapsed_csecs / 100, elapsed_csecs % 100, todo); + "(%d tasks refusing to freeze, wq_busy=%d):\n", + elapsed_csecs / 100, elapsed_csecs % 100, + todo - wq_busy, wq_busy); + + thaw_workqueues(); + read_lock(&tasklist_lock); do_each_thread(g, p) { task_lock(p); @@ -157,6 +173,7 @@ void thaw_processes(void) oom_killer_enable(); printk("Restarting tasks ... "); + thaw_workqueues(); thaw_tasks(true); thaw_tasks(false); schedule(); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index e541b5db67dd..4d059c532792 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -78,7 +78,7 @@ struct cpu_workqueue_struct { int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ int nr_active; /* L: nr of active works */ - int max_active; /* I: max active works */ + int max_active; /* L: max active works */ struct list_head delayed_works; /* L: delayed works */ }; @@ -108,6 +108,7 @@ struct workqueue_struct { struct list_head flusher_queue; /* F: flush waiters */ struct list_head flusher_overflow; /* F: flush overflow list */ + int saved_max_active; /* I: saved cwq max_active */ const char *name; /* I: workqueue name */ #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; @@ -228,6 +229,7 @@ static inline void debug_work_deactivate(struct work_struct *work) { } static DEFINE_SPINLOCK(workqueue_lock); static LIST_HEAD(workqueues); static DEFINE_PER_CPU(struct ida, worker_ida); +static bool workqueue_freezing; /* W: have wqs started freezing? */ static int worker_thread(void *__worker); @@ -745,19 +747,13 @@ static int worker_thread(void *__worker) struct cpu_workqueue_struct *cwq = worker->cwq; DEFINE_WAIT(wait); - if (cwq->wq->flags & WQ_FREEZEABLE) - set_freezable(); - for (;;) { prepare_to_wait(&cwq->more_work, &wait, TASK_INTERRUPTIBLE); - if (!freezing(current) && - !kthread_should_stop() && + if (!kthread_should_stop() && list_empty(&cwq->worklist)) schedule(); finish_wait(&cwq->more_work, &wait); - try_to_freeze(); - if (kthread_should_stop()) break; @@ -1553,6 +1549,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name, goto err; wq->flags = flags; + wq->saved_max_active = max_active; mutex_init(&wq->flush_mutex); atomic_set(&wq->nr_cwqs_to_flush, 0); INIT_LIST_HEAD(&wq->flusher_queue); @@ -1591,8 +1588,19 @@ struct workqueue_struct *__create_workqueue_key(const char *name, failed = true; } + /* + * workqueue_lock protects global freeze state and workqueues + * list. Grab it, set max_active accordingly and add the new + * workqueue to workqueues list. + */ spin_lock(&workqueue_lock); + + if (workqueue_freezing && wq->flags & WQ_FREEZEABLE) + for_each_possible_cpu(cpu) + get_cwq(cpu, wq)->max_active = 0; + list_add(&wq->list, &workqueues); + spin_unlock(&workqueue_lock); cpu_maps_update_done(); @@ -1621,14 +1629,18 @@ void destroy_workqueue(struct workqueue_struct *wq) { int cpu; + flush_workqueue(wq); + + /* + * wq list is used to freeze wq, remove from list after + * flushing is complete in case freeze races us. + */ cpu_maps_update_begin(); spin_lock(&workqueue_lock); list_del(&wq->list); spin_unlock(&workqueue_lock); cpu_maps_update_done(); - flush_workqueue(wq); - for_each_possible_cpu(cpu) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); int i; @@ -1722,6 +1734,137 @@ long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) EXPORT_SYMBOL_GPL(work_on_cpu); #endif /* CONFIG_SMP */ +#ifdef CONFIG_FREEZER + +/** + * freeze_workqueues_begin - begin freezing workqueues + * + * Start freezing workqueues. After this function returns, all + * freezeable workqueues will queue new works to their frozen_works + * list instead of the cwq ones. + * + * CONTEXT: + * Grabs and releases workqueue_lock and cwq->lock's. + */ +void freeze_workqueues_begin(void) +{ + struct workqueue_struct *wq; + unsigned int cpu; + + spin_lock(&workqueue_lock); + + BUG_ON(workqueue_freezing); + workqueue_freezing = true; + + for_each_possible_cpu(cpu) { + list_for_each_entry(wq, &workqueues, list) { + struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + + spin_lock_irq(&cwq->lock); + + if (wq->flags & WQ_FREEZEABLE) + cwq->max_active = 0; + + spin_unlock_irq(&cwq->lock); + } + } + + spin_unlock(&workqueue_lock); +} + +/** + * freeze_workqueues_busy - are freezeable workqueues still busy? + * + * Check whether freezing is complete. This function must be called + * between freeze_workqueues_begin() and thaw_workqueues(). + * + * CONTEXT: + * Grabs and releases workqueue_lock. + * + * RETURNS: + * %true if some freezeable workqueues are still busy. %false if + * freezing is complete. + */ +bool freeze_workqueues_busy(void) +{ + struct workqueue_struct *wq; + unsigned int cpu; + bool busy = false; + + spin_lock(&workqueue_lock); + + BUG_ON(!workqueue_freezing); + + for_each_possible_cpu(cpu) { + /* + * nr_active is monotonically decreasing. It's safe + * to peek without lock. + */ + list_for_each_entry(wq, &workqueues, list) { + struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + + if (!(wq->flags & WQ_FREEZEABLE)) + continue; + + BUG_ON(cwq->nr_active < 0); + if (cwq->nr_active) { + busy = true; + goto out_unlock; + } + } + } +out_unlock: + spin_unlock(&workqueue_lock); + return busy; +} + +/** + * thaw_workqueues - thaw workqueues + * + * Thaw workqueues. Normal queueing is restored and all collected + * frozen works are transferred to their respective cwq worklists. + * + * CONTEXT: + * Grabs and releases workqueue_lock and cwq->lock's. + */ +void thaw_workqueues(void) +{ + struct workqueue_struct *wq; + unsigned int cpu; + + spin_lock(&workqueue_lock); + + if (!workqueue_freezing) + goto out_unlock; + + for_each_possible_cpu(cpu) { + list_for_each_entry(wq, &workqueues, list) { + struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + + if (!(wq->flags & WQ_FREEZEABLE)) + continue; + + spin_lock_irq(&cwq->lock); + + /* restore max_active and repopulate worklist */ + cwq->max_active = wq->saved_max_active; + + while (!list_empty(&cwq->delayed_works) && + cwq->nr_active < cwq->max_active) + cwq_activate_first_delayed(cwq); + + wake_up(&cwq->more_work); + + spin_unlock_irq(&cwq->lock); + } + } + + workqueue_freezing = false; +out_unlock: + spin_unlock(&workqueue_lock); +} +#endif /* CONFIG_FREEZER */ + void __init init_workqueues(void) { unsigned int cpu; -- cgit From 502ca9d819792e7d79b6e002afe9094c641fe410 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:13 +0200 Subject: workqueue: make single thread workqueue shared worker pool friendly Reimplement st (single thread) workqueue so that it's friendly to shared worker pool. It was originally implemented by confining st workqueues to use cwq of a fixed cpu and always having a worker for the cpu. This implementation isn't very friendly to shared worker pool and suboptimal in that it ends up crossing cpu boundaries often. Reimplement st workqueue using dynamic single cpu binding and cwq->limit. WQ_SINGLE_THREAD is replaced with WQ_SINGLE_CPU. In a single cpu workqueue, at most single cwq is bound to the wq at any given time. Arbitration is done using atomic accesses to wq->single_cpu when queueing a work. Once bound, the binding stays till the workqueue is drained. Note that the binding is never broken while a workqueue is frozen. This is because idle cwqs may have works waiting in delayed_works queue while frozen. On thaw, the cwq is restarted if there are any delayed works or unbound otherwise. When combined with max_active limit of 1, single cpu workqueue has exactly the same execution properties as the original single thread workqueue while allowing sharing of per-cpu workers. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 6 +-- kernel/workqueue.c | 135 ++++++++++++++++++++++++++++++++++------------ 2 files changed, 103 insertions(+), 38 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ab0b7fb99bc2..10611f7fc809 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -221,7 +221,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } enum { WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ - WQ_SINGLE_THREAD = 1 << 1, /* no per-cpu worker */ + WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ }; extern struct workqueue_struct * @@ -250,9 +250,9 @@ __create_workqueue_key(const char *name, unsigned int flags, int max_active, #define create_workqueue(name) \ __create_workqueue((name), 0, 1) #define create_freezeable_workqueue(name) \ - __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_THREAD, 1) + __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_CPU, 1) #define create_singlethread_workqueue(name) \ - __create_workqueue((name), WQ_SINGLE_THREAD, 1) + __create_workqueue((name), WQ_SINGLE_CPU, 1) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f57855f718d7..cfb8aa567e17 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -114,8 +114,7 @@ struct global_cwq { } ____cacheline_aligned_in_smp; /* - * The per-CPU workqueue (if single thread, we always use the first - * possible cpu). The lower WORK_STRUCT_FLAG_BITS of + * The per-CPU workqueue. The lower WORK_STRUCT_FLAG_BITS of * work_struct->data are used for flags and thus cwqs need to be * aligned at two's power of the number of flag bits. */ @@ -159,6 +158,8 @@ struct workqueue_struct { struct list_head flusher_queue; /* F: flush waiters */ struct list_head flusher_overflow; /* F: flush overflow list */ + unsigned long single_cpu; /* cpu for single cpu wq */ + int saved_max_active; /* I: saved cwq max_active */ const char *name; /* I: workqueue name */ #ifdef CONFIG_LOCKDEP @@ -289,8 +290,6 @@ static DEFINE_PER_CPU(struct global_cwq, global_cwq); static int worker_thread(void *__worker); -static int singlethread_cpu __read_mostly; - static struct global_cwq *get_gcwq(unsigned int cpu) { return &per_cpu(global_cwq, cpu); @@ -302,14 +301,6 @@ static struct cpu_workqueue_struct *get_cwq(unsigned int cpu, return per_cpu_ptr(wq->cpu_wq, cpu); } -static struct cpu_workqueue_struct *target_cwq(unsigned int cpu, - struct workqueue_struct *wq) -{ - if (unlikely(wq->flags & WQ_SINGLE_THREAD)) - cpu = singlethread_cpu; - return get_cwq(cpu, wq); -} - static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; @@ -410,17 +401,87 @@ static void insert_work(struct cpu_workqueue_struct *cwq, wake_up_process(cwq->worker->task); } +/** + * cwq_unbind_single_cpu - unbind cwq from single cpu workqueue processing + * @cwq: cwq to unbind + * + * Try to unbind @cwq from single cpu workqueue processing. If + * @cwq->wq is frozen, unbind is delayed till the workqueue is thawed. + * + * CONTEXT: + * spin_lock_irq(gcwq->lock). + */ +static void cwq_unbind_single_cpu(struct cpu_workqueue_struct *cwq) +{ + struct workqueue_struct *wq = cwq->wq; + struct global_cwq *gcwq = cwq->gcwq; + + BUG_ON(wq->single_cpu != gcwq->cpu); + /* + * Unbind from workqueue if @cwq is not frozen. If frozen, + * thaw_workqueues() will either restart processing on this + * cpu or unbind if empty. This keeps works queued while + * frozen fully ordered and flushable. + */ + if (likely(!(gcwq->flags & GCWQ_FREEZING))) { + smp_wmb(); /* paired with cmpxchg() in __queue_work() */ + wq->single_cpu = NR_CPUS; + } +} + static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, struct work_struct *work) { - struct cpu_workqueue_struct *cwq = target_cwq(cpu, wq); - struct global_cwq *gcwq = cwq->gcwq; + struct global_cwq *gcwq; + struct cpu_workqueue_struct *cwq; struct list_head *worklist; unsigned long flags; + bool arbitrate; debug_work_activate(work); - spin_lock_irqsave(&gcwq->lock, flags); + /* determine gcwq to use */ + if (!(wq->flags & WQ_SINGLE_CPU)) { + /* just use the requested cpu for multicpu workqueues */ + gcwq = get_gcwq(cpu); + spin_lock_irqsave(&gcwq->lock, flags); + } else { + unsigned int req_cpu = cpu; + + /* + * It's a bit more complex for single cpu workqueues. + * We first need to determine which cpu is going to be + * used. If no cpu is currently serving this + * workqueue, arbitrate using atomic accesses to + * wq->single_cpu; otherwise, use the current one. + */ + retry: + cpu = wq->single_cpu; + arbitrate = cpu == NR_CPUS; + if (arbitrate) + cpu = req_cpu; + + gcwq = get_gcwq(cpu); + spin_lock_irqsave(&gcwq->lock, flags); + + /* + * The following cmpxchg() is a full barrier paired + * with smp_wmb() in cwq_unbind_single_cpu() and + * guarantees that all changes to wq->st_* fields are + * visible on the new cpu after this point. + */ + if (arbitrate) + cmpxchg(&wq->single_cpu, NR_CPUS, cpu); + + if (unlikely(wq->single_cpu != cpu)) { + spin_unlock_irqrestore(&gcwq->lock, flags); + goto retry; + } + } + + /* gcwq determined, get cwq and queue */ + cwq = get_cwq(gcwq->cpu, wq); + BUG_ON(!list_empty(&work->entry)); cwq->nr_in_flight[cwq->work_color]++; @@ -530,7 +591,7 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, timer_stats_timer_set_start_info(&dwork->timer); /* This stores cwq for the moment, for the timer_fn */ - set_wq_data(work, target_cwq(raw_smp_processor_id(), wq), 0); + set_wq_data(work, get_cwq(raw_smp_processor_id(), wq), 0); timer->expires = jiffies + delay; timer->data = (unsigned long)dwork; timer->function = delayed_work_timer_fn; @@ -790,10 +851,14 @@ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) cwq->nr_in_flight[color]--; cwq->nr_active--; - /* one down, submit a delayed one */ - if (!list_empty(&cwq->delayed_works) && - cwq->nr_active < cwq->max_active) - cwq_activate_first_delayed(cwq); + if (!list_empty(&cwq->delayed_works)) { + /* one down, submit a delayed one */ + if (cwq->nr_active < cwq->max_active) + cwq_activate_first_delayed(cwq); + } else if (!cwq->nr_active && cwq->wq->flags & WQ_SINGLE_CPU) { + /* this was the last work, unbind from single cpu */ + cwq_unbind_single_cpu(cwq); + } /* is flush in progress and are we at the flushing tip? */ if (likely(cwq->flush_color != color)) @@ -1727,7 +1792,6 @@ struct workqueue_struct *__create_workqueue_key(const char *name, struct lock_class_key *key, const char *lock_name) { - bool singlethread = flags & WQ_SINGLE_THREAD; struct workqueue_struct *wq; bool failed = false; unsigned int cpu; @@ -1748,6 +1812,8 @@ struct workqueue_struct *__create_workqueue_key(const char *name, atomic_set(&wq->nr_cwqs_to_flush, 0); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); + wq->single_cpu = NR_CPUS; + wq->name = name; lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); INIT_LIST_HEAD(&wq->list); @@ -1773,8 +1839,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name, if (failed) continue; - cwq->worker = create_worker(cwq, - cpu_online(cpu) && !singlethread); + cwq->worker = create_worker(cwq, cpu_online(cpu)); if (cwq->worker) start_worker(cwq->worker); else @@ -1958,18 +2023,16 @@ static int __cpuinit trustee_thread(void *__gcwq) spin_lock_irq(&gcwq->lock); /* - * Make all multithread workers rogue. Trustee must be bound - * to the target cpu and can't be cancelled. + * Make all workers rogue. Trustee must be bound to the + * target cpu and can't be cancelled. */ BUG_ON(gcwq->cpu != smp_processor_id()); list_for_each_entry(worker, &gcwq->idle_list, entry) - if (!(worker->cwq->wq->flags & WQ_SINGLE_THREAD)) - worker->flags |= WORKER_ROGUE; + worker->flags |= WORKER_ROGUE; for_each_busy_worker(worker, i, pos, gcwq) - if (!(worker->cwq->wq->flags & WQ_SINGLE_THREAD)) - worker->flags |= WORKER_ROGUE; + worker->flags |= WORKER_ROGUE; /* * We're now in charge. Notify and proceed to drain. We need @@ -2074,14 +2137,12 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, wait_trustee_state(gcwq, TRUSTEE_DONE); } - /* clear ROGUE from all multithread workers */ + /* clear ROGUE from all workers */ list_for_each_entry(worker, &gcwq->idle_list, entry) - if (!(worker->cwq->wq->flags & WQ_SINGLE_THREAD)) - worker->flags &= ~WORKER_ROGUE; + worker->flags &= ~WORKER_ROGUE; for_each_busy_worker(worker, i, pos, gcwq) - if (!(worker->cwq->wq->flags & WQ_SINGLE_THREAD)) - worker->flags &= ~WORKER_ROGUE; + worker->flags &= ~WORKER_ROGUE; break; } @@ -2266,6 +2327,11 @@ void thaw_workqueues(void) cwq->nr_active < cwq->max_active) cwq_activate_first_delayed(cwq); + /* perform delayed unbind from single cpu if empty */ + if (wq->single_cpu == gcwq->cpu && + !cwq->nr_active && list_empty(&cwq->delayed_works)) + cwq_unbind_single_cpu(cwq); + wake_up_process(cwq->worker->task); } @@ -2283,7 +2349,6 @@ void __init init_workqueues(void) unsigned int cpu; int i; - singlethread_cpu = cpumask_first(cpu_possible_mask); hotcpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE); /* initialize gcwqs */ -- cgit From 7a22ad757ec75186ad43a5b4670fa7423ee8f480 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:13 +0200 Subject: workqueue: carry cpu number in work data once execution starts To implement non-reentrant workqueue, the last gcwq a work was executed on must be reliably obtainable as long as the work structure is valid even if the previous workqueue has been destroyed. To achieve this, work->data will be overloaded to carry the last cpu number once execution starts so that the previous gcwq can be located reliably. This means that cwq can't be obtained from work after execution starts but only gcwq. Implement set_work_{cwq|cpu}(), get_work_[g]cwq() and clear_work_data() to set work data to the cpu number when starting execution, access the overloaded work data and clear it after cancellation. queue_delayed_work_on() is updated to preserve the last cpu while in-flight in timer and other callers which depended on getting cwq from work after execution starts are converted to depend on gcwq instead. * Anton Blanchard fixed compile error on powerpc due to missing linux/threads.h include. Signed-off-by: Tejun Heo Cc: Anton Blanchard --- include/linux/workqueue.h | 7 +- kernel/workqueue.c | 163 +++++++++++++++++++++++++++++----------------- 2 files changed, 109 insertions(+), 61 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 10611f7fc809..0a7814131e66 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -9,6 +9,7 @@ #include #include #include +#include #include struct workqueue_struct; @@ -59,6 +60,7 @@ enum { WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, + WORK_STRUCT_NO_CPU = NR_CPUS << WORK_STRUCT_FLAG_BITS, }; struct work_struct { @@ -70,8 +72,9 @@ struct work_struct { #endif }; -#define WORK_DATA_INIT() ATOMIC_LONG_INIT(0) -#define WORK_DATA_STATIC_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_STATIC) +#define WORK_DATA_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU) +#define WORK_DATA_STATIC_INIT() \ + ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU | WORK_STRUCT_STATIC) struct delayed_work { struct work_struct work; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c276dec75ea4..c68277c204ab 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -319,31 +319,71 @@ static int work_next_color(int color) } /* - * Set the workqueue on which a work item is to be run - * - Must *only* be called if the pending flag is set + * Work data points to the cwq while a work is on queue. Once + * execution starts, it points to the cpu the work was last on. This + * can be distinguished by comparing the data value against + * PAGE_OFFSET. + * + * set_work_{cwq|cpu}() and clear_work_data() can be used to set the + * cwq, cpu or clear work->data. These functions should only be + * called while the work is owned - ie. while the PENDING bit is set. + * + * get_work_[g]cwq() can be used to obtain the gcwq or cwq + * corresponding to a work. gcwq is available once the work has been + * queued anywhere after initialization. cwq is available only from + * queueing until execution starts. */ -static inline void set_wq_data(struct work_struct *work, - struct cpu_workqueue_struct *cwq, - unsigned long extra_flags) +static inline void set_work_data(struct work_struct *work, unsigned long data, + unsigned long flags) { BUG_ON(!work_pending(work)); + atomic_long_set(&work->data, data | flags | work_static(work)); +} - atomic_long_set(&work->data, (unsigned long)cwq | work_static(work) | - WORK_STRUCT_PENDING | extra_flags); +static void set_work_cwq(struct work_struct *work, + struct cpu_workqueue_struct *cwq, + unsigned long extra_flags) +{ + set_work_data(work, (unsigned long)cwq, + WORK_STRUCT_PENDING | extra_flags); } -/* - * Clear WORK_STRUCT_PENDING and the workqueue on which it was queued. - */ -static inline void clear_wq_data(struct work_struct *work) +static void set_work_cpu(struct work_struct *work, unsigned int cpu) +{ + set_work_data(work, cpu << WORK_STRUCT_FLAG_BITS, WORK_STRUCT_PENDING); +} + +static void clear_work_data(struct work_struct *work) +{ + set_work_data(work, WORK_STRUCT_NO_CPU, 0); +} + +static inline unsigned long get_work_data(struct work_struct *work) +{ + return atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK; +} + +static struct cpu_workqueue_struct *get_work_cwq(struct work_struct *work) { - atomic_long_set(&work->data, work_static(work)); + unsigned long data = get_work_data(work); + + return data >= PAGE_OFFSET ? (void *)data : NULL; } -static inline struct cpu_workqueue_struct *get_wq_data(struct work_struct *work) +static struct global_cwq *get_work_gcwq(struct work_struct *work) { - return (void *)(atomic_long_read(&work->data) & - WORK_STRUCT_WQ_DATA_MASK); + unsigned long data = get_work_data(work); + unsigned int cpu; + + if (data >= PAGE_OFFSET) + return ((struct cpu_workqueue_struct *)data)->gcwq; + + cpu = data >> WORK_STRUCT_FLAG_BITS; + if (cpu == NR_CPUS) + return NULL; + + BUG_ON(cpu >= num_possible_cpus()); + return get_gcwq(cpu); } /** @@ -443,7 +483,7 @@ static void insert_work(struct cpu_workqueue_struct *cwq, unsigned int extra_flags) { /* we own @work, set data and link */ - set_wq_data(work, cwq, extra_flags); + set_work_cwq(work, cwq, extra_flags); /* * Ensure that we get the right work->data if we see the @@ -599,7 +639,7 @@ EXPORT_SYMBOL_GPL(queue_work_on); static void delayed_work_timer_fn(unsigned long __data) { struct delayed_work *dwork = (struct delayed_work *)__data; - struct cpu_workqueue_struct *cwq = get_wq_data(&dwork->work); + struct cpu_workqueue_struct *cwq = get_work_cwq(&dwork->work); __queue_work(smp_processor_id(), cwq->wq, &dwork->work); } @@ -639,13 +679,19 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work = &dwork->work; if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + struct global_cwq *gcwq = get_work_gcwq(work); + unsigned int lcpu = gcwq ? gcwq->cpu : raw_smp_processor_id(); + BUG_ON(timer_pending(timer)); BUG_ON(!list_empty(&work->entry)); timer_stats_timer_set_start_info(&dwork->timer); - - /* This stores cwq for the moment, for the timer_fn */ - set_wq_data(work, get_cwq(raw_smp_processor_id(), wq), 0); + /* + * This stores cwq for the moment, for the timer_fn. + * Note that the work's gcwq is preserved to allow + * reentrance detection for delayed works. + */ + set_work_cwq(work, get_cwq(lcpu, wq), 0); timer->expires = jiffies + delay; timer->data = (unsigned long)dwork; timer->function = delayed_work_timer_fn; @@ -970,11 +1016,14 @@ static void process_one_work(struct worker *worker, struct work_struct *work) worker->current_work = work; worker->current_cwq = cwq; work_color = get_work_color(work); + + BUG_ON(get_work_cwq(work) != cwq); + /* record the current cpu number in the work data and dequeue */ + set_work_cpu(work, gcwq->cpu); list_del_init(&work->entry); spin_unlock_irq(&gcwq->lock); - BUG_ON(get_wq_data(work) != cwq); work_clear_pending(work); lock_map_acquire(&cwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); @@ -1406,37 +1455,39 @@ EXPORT_SYMBOL_GPL(flush_workqueue); int flush_work(struct work_struct *work) { struct worker *worker = NULL; - struct cpu_workqueue_struct *cwq; struct global_cwq *gcwq; + struct cpu_workqueue_struct *cwq; struct wq_barrier barr; might_sleep(); - cwq = get_wq_data(work); - if (!cwq) + gcwq = get_work_gcwq(work); + if (!gcwq) return 0; - gcwq = cwq->gcwq; - - lock_map_acquire(&cwq->wq->lockdep_map); - lock_map_release(&cwq->wq->lockdep_map); spin_lock_irq(&gcwq->lock); if (!list_empty(&work->entry)) { /* * See the comment near try_to_grab_pending()->smp_rmb(). - * If it was re-queued under us we are not going to wait. + * If it was re-queued to a different gcwq under us, we + * are not going to wait. */ smp_rmb(); - if (unlikely(cwq != get_wq_data(work))) + cwq = get_work_cwq(work); + if (unlikely(!cwq || gcwq != cwq->gcwq)) goto already_gone; } else { - if (cwq->worker && cwq->worker->current_work == work) - worker = cwq->worker; + worker = find_worker_executing_work(gcwq, work); if (!worker) goto already_gone; + cwq = worker->current_cwq; } insert_wq_barrier(cwq, &barr, work, worker); spin_unlock_irq(&gcwq->lock); + + lock_map_acquire(&cwq->wq->lockdep_map); + lock_map_release(&cwq->wq->lockdep_map); + wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); return 1; @@ -1453,7 +1504,6 @@ EXPORT_SYMBOL_GPL(flush_work); static int try_to_grab_pending(struct work_struct *work) { struct global_cwq *gcwq; - struct cpu_workqueue_struct *cwq; int ret = -1; if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) @@ -1463,24 +1513,23 @@ static int try_to_grab_pending(struct work_struct *work) * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ - - cwq = get_wq_data(work); - if (!cwq) + gcwq = get_work_gcwq(work); + if (!gcwq) return ret; - gcwq = cwq->gcwq; spin_lock_irq(&gcwq->lock); if (!list_empty(&work->entry)) { /* - * This work is queued, but perhaps we locked the wrong cwq. + * This work is queued, but perhaps we locked the wrong gcwq. * In that case we must see the new value after rmb(), see * insert_work()->wmb(). */ smp_rmb(); - if (cwq == get_wq_data(work)) { + if (gcwq == get_work_gcwq(work)) { debug_work_deactivate(work); list_del_init(&work->entry); - cwq_dec_nr_in_flight(cwq, get_work_color(work)); + cwq_dec_nr_in_flight(get_work_cwq(work), + get_work_color(work)); ret = 1; } } @@ -1489,20 +1538,16 @@ static int try_to_grab_pending(struct work_struct *work) return ret; } -static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq, - struct work_struct *work) +static void wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work) { - struct global_cwq *gcwq = cwq->gcwq; struct wq_barrier barr; struct worker *worker; spin_lock_irq(&gcwq->lock); - worker = NULL; - if (unlikely(cwq->worker && cwq->worker->current_work == work)) { - worker = cwq->worker; - insert_wq_barrier(cwq, &barr, work, worker); - } + worker = find_worker_executing_work(gcwq, work); + if (unlikely(worker)) + insert_wq_barrier(worker->current_cwq, &barr, work, worker); spin_unlock_irq(&gcwq->lock); @@ -1514,8 +1559,6 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq, static void wait_on_work(struct work_struct *work) { - struct cpu_workqueue_struct *cwq; - struct workqueue_struct *wq; int cpu; might_sleep(); @@ -1523,14 +1566,8 @@ static void wait_on_work(struct work_struct *work) lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); - cwq = get_wq_data(work); - if (!cwq) - return; - - wq = cwq->wq; - for_each_possible_cpu(cpu) - wait_on_cpu_work(get_cwq(cpu, wq), work); + wait_on_cpu_work(get_gcwq(cpu), work); } static int __cancel_work_timer(struct work_struct *work, @@ -1545,7 +1582,7 @@ static int __cancel_work_timer(struct work_struct *work, wait_on_work(work); } while (unlikely(ret < 0)); - clear_wq_data(work); + clear_work_data(work); return ret; } @@ -1647,7 +1684,7 @@ EXPORT_SYMBOL(schedule_delayed_work); void flush_delayed_work(struct delayed_work *dwork) { if (del_timer_sync(&dwork->timer)) { - __queue_work(get_cpu(), get_wq_data(&dwork->work)->wq, + __queue_work(get_cpu(), get_work_cwq(&dwork->work)->wq, &dwork->work); put_cpu(); } @@ -2405,6 +2442,14 @@ void __init init_workqueues(void) unsigned int cpu; int i; + /* + * The pointer part of work->data is either pointing to the + * cwq or contains the cpu number the work ran last on. Make + * sure cpu number won't overflow into kernel pointer area so + * that they can be distinguished. + */ + BUILD_BUG_ON(NR_CPUS << WORK_STRUCT_FLAG_BITS >= PAGE_OFFSET); + hotcpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE); /* initialize gcwqs */ -- cgit From 18aa9effad4adb2c1efe123af4eb24fec9f59b30 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:13 +0200 Subject: workqueue: implement WQ_NON_REENTRANT With gcwq managing all the workers and work->data pointing to the last gcwq it was on, non-reentrance can be easily implemented by checking whether the work is still running on the previous gcwq on queueing. Implement it. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 1 + kernel/workqueue.c | 32 +++++++++++++++++++++++++++++--- 2 files changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 0a7814131e66..07cf5e5f91cb 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -225,6 +225,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } enum { WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ + WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ }; extern struct workqueue_struct * diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c68277c204ab..bce1074bdec1 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -534,11 +534,37 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, debug_work_activate(work); - /* determine gcwq to use */ + /* + * Determine gcwq to use. SINGLE_CPU is inherently + * NON_REENTRANT, so test it first. + */ if (!(wq->flags & WQ_SINGLE_CPU)) { - /* just use the requested cpu for multicpu workqueues */ + struct global_cwq *last_gcwq; + + /* + * It's multi cpu. If @wq is non-reentrant and @work + * was previously on a different cpu, it might still + * be running there, in which case the work needs to + * be queued on that cpu to guarantee non-reentrance. + */ gcwq = get_gcwq(cpu); - spin_lock_irqsave(&gcwq->lock, flags); + if (wq->flags & WQ_NON_REENTRANT && + (last_gcwq = get_work_gcwq(work)) && last_gcwq != gcwq) { + struct worker *worker; + + spin_lock_irqsave(&last_gcwq->lock, flags); + + worker = find_worker_executing_work(last_gcwq, work); + + if (worker && worker->current_cwq->wq == wq) + gcwq = last_gcwq; + else { + /* meh... not running there, queue here */ + spin_unlock_irqrestore(&last_gcwq->lock, flags); + spin_lock_irqsave(&gcwq->lock, flags); + } + } else + spin_lock_irqsave(&gcwq->lock, flags); } else { unsigned int req_cpu = cpu; -- cgit From e22bee782b3b00bd4534ae9b1c5fb2e8e6573c5c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:14 +0200 Subject: workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 8 +- kernel/workqueue.c | 936 +++++++++++++++++++++++++++++++++++++++++----- kernel/workqueue_sched.h | 13 +- 3 files changed, 841 insertions(+), 116 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 07cf5e5f91cb..b8f4ec45c40a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -226,6 +226,7 @@ enum { WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ + WQ_RESCUER = 1 << 3, /* has an rescue worker */ }; extern struct workqueue_struct * @@ -252,11 +253,12 @@ __create_workqueue_key(const char *name, unsigned int flags, int max_active, #endif #define create_workqueue(name) \ - __create_workqueue((name), 0, 1) + __create_workqueue((name), WQ_RESCUER, 1) #define create_freezeable_workqueue(name) \ - __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_CPU, 1) + __create_workqueue((name), \ + WQ_FREEZEABLE | WQ_SINGLE_CPU | WQ_RESCUER, 1) #define create_singlethread_workqueue(name) \ - __create_workqueue((name), WQ_SINGLE_CPU, 1) + __create_workqueue((name), WQ_SINGLE_CPU | WQ_RESCUER, 1) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4c31fde092c6..0ad46523b423 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -34,17 +34,25 @@ #include #include #include -#include + +#include "workqueue_sched.h" enum { /* global_cwq flags */ + GCWQ_MANAGE_WORKERS = 1 << 0, /* need to manage workers */ + GCWQ_MANAGING_WORKERS = 1 << 1, /* managing workers */ + GCWQ_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ GCWQ_FREEZING = 1 << 3, /* freeze in progress */ /* worker flags */ WORKER_STARTED = 1 << 0, /* started */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ + WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_ROGUE = 1 << 4, /* not bound to any cpu */ + WORKER_REBIND = 1 << 5, /* mom is home, come back */ + + WORKER_NOT_RUNNING = WORKER_PREP | WORKER_ROGUE | WORKER_REBIND, /* gcwq->trustee_state */ TRUSTEE_START = 0, /* start */ @@ -57,7 +65,19 @@ enum { BUSY_WORKER_HASH_SIZE = 1 << BUSY_WORKER_HASH_ORDER, BUSY_WORKER_HASH_MASK = BUSY_WORKER_HASH_SIZE - 1, + MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ + IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ + + MAYDAY_INITIAL_TIMEOUT = HZ / 100, /* call for help after 10ms */ + MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ + CREATE_COOLDOWN = HZ, /* time to breath after fail */ TRUSTEE_COOLDOWN = HZ / 10, /* for trustee draining */ + + /* + * Rescue workers are used only on emergencies and shared by + * all cpus. Give -20. + */ + RESCUER_NICE_LEVEL = -20, }; /* @@ -65,8 +85,16 @@ enum { * * I: Set during initialization and read-only afterwards. * + * P: Preemption protected. Disabling preemption is enough and should + * only be modified and accessed from the local cpu. + * * L: gcwq->lock protected. Access with gcwq->lock held. * + * X: During normal operation, modification requires gcwq->lock and + * should be done only from local cpu. Either disabling preemption + * on local cpu or grabbing gcwq->lock is enough for read access. + * While trustee is in charge, it's identical to L. + * * F: wq->flush_mutex protected. * * W: workqueue_lock protected. @@ -74,6 +102,10 @@ enum { struct global_cwq; +/* + * The poor guys doing the actual heavy lifting. All on-duty workers + * are either serving the manager role, on idle list or on busy hash. + */ struct worker { /* on idle list while idle, on busy hash table while busy */ union { @@ -86,12 +118,17 @@ struct worker { struct list_head scheduled; /* L: scheduled works */ struct task_struct *task; /* I: worker task */ struct global_cwq *gcwq; /* I: the associated gcwq */ - unsigned int flags; /* L: flags */ + /* 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 */ + struct work_struct rebind_work; /* L: rebind worker to cpu */ }; /* - * Global per-cpu workqueue. + * Global per-cpu workqueue. There's one and only one for each cpu + * and all works are queued and processed here regardless of their + * target workqueues. */ struct global_cwq { spinlock_t lock; /* the gcwq lock */ @@ -103,15 +140,19 @@ struct global_cwq { int nr_idle; /* L: currently idle ones */ /* workers are chained either in the idle_list or busy_hash */ - struct list_head idle_list; /* L: list of idle workers */ + struct list_head idle_list; /* X: list of idle workers */ struct hlist_head busy_hash[BUSY_WORKER_HASH_SIZE]; /* L: hash of busy workers */ + struct timer_list idle_timer; /* L: worker idle timeout */ + struct timer_list mayday_timer; /* L: SOS timer for dworkers */ + struct ida worker_ida; /* L: for worker IDs */ struct task_struct *trustee; /* L: for gcwq shutdown */ unsigned int trustee_state; /* L: trustee state */ wait_queue_head_t trustee_wait; /* trustee wait */ + struct worker *first_idle; /* L: first idle worker */ } ____cacheline_aligned_in_smp; /* @@ -121,7 +162,6 @@ struct global_cwq { */ struct cpu_workqueue_struct { struct global_cwq *gcwq; /* I: the associated gcwq */ - struct worker *worker; struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ @@ -160,6 +200,9 @@ struct workqueue_struct { unsigned long single_cpu; /* cpu for single cpu wq */ + cpumask_var_t mayday_mask; /* cpus requesting rescue */ + struct worker *rescuer; /* I: rescue worker */ + int saved_max_active; /* I: saved cwq max_active */ const char *name; /* I: workqueue name */ #ifdef CONFIG_LOCKDEP @@ -286,7 +329,13 @@ static DEFINE_SPINLOCK(workqueue_lock); static LIST_HEAD(workqueues); static bool workqueue_freezing; /* W: have wqs started freezing? */ +/* + * The almighty global cpu workqueues. nr_running is the only field + * which is expected to be used frequently by other cpus via + * try_to_wake_up(). Put it in a separate cacheline. + */ static DEFINE_PER_CPU(struct global_cwq, global_cwq); +static DEFINE_PER_CPU_SHARED_ALIGNED(atomic_t, gcwq_nr_running); static int worker_thread(void *__worker); @@ -295,6 +344,11 @@ static struct global_cwq *get_gcwq(unsigned int cpu) return &per_cpu(global_cwq, cpu); } +static atomic_t *get_gcwq_nr_running(unsigned int cpu) +{ + return &per_cpu(gcwq_nr_running, cpu); +} + static struct cpu_workqueue_struct *get_cwq(unsigned int cpu, struct workqueue_struct *wq) { @@ -385,6 +439,63 @@ static struct global_cwq *get_work_gcwq(struct work_struct *work) return get_gcwq(cpu); } +/* + * Policy functions. These define the policies on how the global + * worker pool is managed. Unless noted otherwise, these functions + * assume that they're being called with gcwq->lock held. + */ + +/* + * Need to wake up a worker? Called from anything but currently + * running workers. + */ +static bool need_more_worker(struct global_cwq *gcwq) +{ + atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu); + + return !list_empty(&gcwq->worklist) && !atomic_read(nr_running); +} + +/* Can I start working? Called from busy but !running workers. */ +static bool may_start_working(struct global_cwq *gcwq) +{ + return gcwq->nr_idle; +} + +/* Do I need to keep working? Called from currently running workers. */ +static bool keep_working(struct global_cwq *gcwq) +{ + atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu); + + return !list_empty(&gcwq->worklist) && atomic_read(nr_running) <= 1; +} + +/* Do we need a new worker? Called from manager. */ +static bool need_to_create_worker(struct global_cwq *gcwq) +{ + return need_more_worker(gcwq) && !may_start_working(gcwq); +} + +/* Do I need to be the manager? */ +static bool need_to_manage_workers(struct global_cwq *gcwq) +{ + return need_to_create_worker(gcwq) || gcwq->flags & GCWQ_MANAGE_WORKERS; +} + +/* Do we have too many workers and should some go away? */ +static bool too_many_workers(struct global_cwq *gcwq) +{ + bool managing = gcwq->flags & GCWQ_MANAGING_WORKERS; + int nr_idle = gcwq->nr_idle + managing; /* manager is considered idle */ + int nr_busy = gcwq->nr_workers - nr_idle; + + return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; +} + +/* + * Wake up functions. + */ + /* Return the first worker. Safe with preemption disabled */ static struct worker *first_worker(struct global_cwq *gcwq) { @@ -412,12 +523,77 @@ static void wake_up_worker(struct global_cwq *gcwq) } /** - * worker_set_flags - set worker flags + * wq_worker_waking_up - a worker is waking up + * @task: task waking up + * @cpu: CPU @task is waking up to + * + * This function is called during try_to_wake_up() when a worker is + * being awoken. + * + * CONTEXT: + * spin_lock_irq(rq->lock) + */ +void wq_worker_waking_up(struct task_struct *task, unsigned int cpu) +{ + struct worker *worker = kthread_data(task); + + if (likely(!(worker->flags & WORKER_NOT_RUNNING))) + atomic_inc(get_gcwq_nr_running(cpu)); +} + +/** + * wq_worker_sleeping - a worker is going to sleep + * @task: task going to sleep + * @cpu: CPU in question, must be the current CPU number + * + * This function is called during schedule() when a busy worker is + * going to sleep. Worker on the same cpu can be woken up by + * returning pointer to its task. + * + * CONTEXT: + * spin_lock_irq(rq->lock) + * + * RETURNS: + * Worker task on @cpu to wake up, %NULL if none. + */ +struct task_struct *wq_worker_sleeping(struct task_struct *task, + unsigned int cpu) +{ + struct worker *worker = kthread_data(task), *to_wakeup = NULL; + struct global_cwq *gcwq = get_gcwq(cpu); + atomic_t *nr_running = get_gcwq_nr_running(cpu); + + if (unlikely(worker->flags & WORKER_NOT_RUNNING)) + return NULL; + + /* this can only happen on the local cpu */ + BUG_ON(cpu != raw_smp_processor_id()); + + /* + * The counterpart of the following dec_and_test, implied mb, + * worklist not empty test sequence is in insert_work(). + * Please read comment there. + * + * NOT_RUNNING is clear. This means that trustee is not in + * charge and we're running on the local cpu w/ rq lock held + * and preemption disabled, which in turn means that none else + * could be manipulating idle_list, so dereferencing idle_list + * without gcwq lock is safe. + */ + if (atomic_dec_and_test(nr_running) && !list_empty(&gcwq->worklist)) + to_wakeup = first_worker(gcwq); + return to_wakeup ? to_wakeup->task : NULL; +} + +/** + * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: worker to set flags for * @flags: flags to set * @wakeup: wakeup an idle worker if necessary * - * Set @flags in @worker->flags. + * Set @flags in @worker->flags and adjust nr_running accordingly. If + * nr_running becomes zero and @wakeup is %true, an idle worker is + * woken up. * * LOCKING: * spin_lock_irq(gcwq->lock). @@ -425,22 +601,49 @@ static void wake_up_worker(struct global_cwq *gcwq) static inline void worker_set_flags(struct worker *worker, unsigned int flags, bool wakeup) { + struct global_cwq *gcwq = worker->gcwq; + + /* + * If transitioning into NOT_RUNNING, adjust nr_running and + * wake up an idle worker as necessary if requested by + * @wakeup. + */ + if ((flags & WORKER_NOT_RUNNING) && + !(worker->flags & WORKER_NOT_RUNNING)) { + atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu); + + if (wakeup) { + if (atomic_dec_and_test(nr_running) && + !list_empty(&gcwq->worklist)) + wake_up_worker(gcwq); + } else + atomic_dec(nr_running); + } + worker->flags |= flags; } /** - * worker_clr_flags - clear worker flags + * worker_clr_flags - clear worker flags and adjust nr_running accordingly * @worker: worker to set flags for * @flags: flags to clear * - * Clear @flags in @worker->flags. + * Clear @flags in @worker->flags and adjust nr_running accordingly. * * LOCKING: * spin_lock_irq(gcwq->lock). */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { + struct global_cwq *gcwq = worker->gcwq; + unsigned int oflags = worker->flags; + worker->flags &= ~flags; + + /* if transitioning out of NOT_RUNNING, increment nr_running */ + if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) + if (!(worker->flags & WORKER_NOT_RUNNING)) + atomic_inc(get_gcwq_nr_running(gcwq->cpu)); } /** @@ -540,6 +743,8 @@ static void insert_work(struct cpu_workqueue_struct *cwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { + struct global_cwq *gcwq = cwq->gcwq; + /* we own @work, set data and link */ set_work_cwq(work, cwq, extra_flags); @@ -550,7 +755,16 @@ static void insert_work(struct cpu_workqueue_struct *cwq, smp_wmb(); list_add_tail(&work->entry, head); - wake_up_worker(cwq->gcwq); + + /* + * Ensure either worker_sched_deactivated() sees the above + * list_add_tail() or we see zero nr_running to avoid workers + * lying around lazily while there are works to be processed. + */ + smp_mb(); + + if (!atomic_read(get_gcwq_nr_running(gcwq->cpu))) + wake_up_worker(gcwq); } /** @@ -810,11 +1024,16 @@ static void worker_enter_idle(struct worker *worker) worker_set_flags(worker, WORKER_IDLE, false); gcwq->nr_idle++; + worker->last_active = jiffies; /* idle_list is LIFO */ list_add(&worker->entry, &gcwq->idle_list); - if (unlikely(worker->flags & WORKER_ROGUE)) + if (likely(!(worker->flags & WORKER_ROGUE))) { + if (too_many_workers(gcwq) && !timer_pending(&gcwq->idle_timer)) + mod_timer(&gcwq->idle_timer, + jiffies + IDLE_WORKER_TIMEOUT); + } else wake_up_all(&gcwq->trustee_wait); } @@ -837,6 +1056,81 @@ static void worker_leave_idle(struct worker *worker) list_del_init(&worker->entry); } +/** + * worker_maybe_bind_and_lock - bind worker to its cpu if possible and lock gcwq + * @worker: self + * + * Works which are scheduled while the cpu is online must at least be + * scheduled to a worker which is bound to the cpu so that if they are + * flushed from cpu callbacks while cpu is going down, they are + * guaranteed to execute on the cpu. + * + * This function is to be used by rogue workers and rescuers to bind + * themselves to the target cpu and may race with cpu going down or + * coming online. kthread_bind() can't be used because it may put the + * worker to already dead cpu and set_cpus_allowed_ptr() can't be used + * verbatim as it's best effort and blocking and gcwq may be + * [dis]associated in the meantime. + * + * This function tries set_cpus_allowed() and locks gcwq and verifies + * the binding against GCWQ_DISASSOCIATED which is set during + * CPU_DYING and cleared during CPU_ONLINE, so if the worker enters + * idle state or fetches works without dropping lock, it can guarantee + * the scheduling requirement described in the first paragraph. + * + * CONTEXT: + * Might sleep. Called without any lock but returns with gcwq->lock + * held. + * + * RETURNS: + * %true if the associated gcwq is online (@worker is successfully + * bound), %false if offline. + */ +static bool worker_maybe_bind_and_lock(struct worker *worker) +{ + struct global_cwq *gcwq = worker->gcwq; + struct task_struct *task = worker->task; + + while (true) { + /* + * The following call may fail, succeed or succeed + * without actually migrating the task to the cpu if + * it races with cpu hotunplug operation. Verify + * against GCWQ_DISASSOCIATED. + */ + set_cpus_allowed_ptr(task, get_cpu_mask(gcwq->cpu)); + + spin_lock_irq(&gcwq->lock); + if (gcwq->flags & GCWQ_DISASSOCIATED) + return false; + if (task_cpu(task) == gcwq->cpu && + cpumask_equal(¤t->cpus_allowed, + get_cpu_mask(gcwq->cpu))) + return true; + spin_unlock_irq(&gcwq->lock); + + /* CPU has come up inbetween, retry migration */ + cpu_relax(); + } +} + +/* + * Function for worker->rebind_work used to rebind rogue busy workers + * to the associated cpu which is coming back online. This is + * scheduled by cpu up but can race with other cpu hotplug operations + * and may be executed twice without intervening cpu down. + */ +static void worker_rebind_fn(struct work_struct *work) +{ + struct worker *worker = container_of(work, struct worker, rebind_work); + struct global_cwq *gcwq = worker->gcwq; + + if (worker_maybe_bind_and_lock(worker)) + worker_clr_flags(worker, WORKER_REBIND); + + spin_unlock_irq(&gcwq->lock); +} + static struct worker *alloc_worker(void) { struct worker *worker; @@ -845,6 +1139,9 @@ static struct worker *alloc_worker(void) if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); + INIT_WORK(&worker->rebind_work, worker_rebind_fn); + /* on creation a worker is in !idle && prep state */ + worker->flags = WORKER_PREP; } return worker; } @@ -963,6 +1260,220 @@ static void destroy_worker(struct worker *worker) ida_remove(&gcwq->worker_ida, id); } +static void idle_worker_timeout(unsigned long __gcwq) +{ + struct global_cwq *gcwq = (void *)__gcwq; + + spin_lock_irq(&gcwq->lock); + + if (too_many_workers(gcwq)) { + struct worker *worker; + unsigned long expires; + + /* idle_list is kept in LIFO order, check the last one */ + worker = list_entry(gcwq->idle_list.prev, struct worker, entry); + expires = worker->last_active + IDLE_WORKER_TIMEOUT; + + if (time_before(jiffies, expires)) + mod_timer(&gcwq->idle_timer, expires); + else { + /* it's been idle for too long, wake up manager */ + gcwq->flags |= GCWQ_MANAGE_WORKERS; + wake_up_worker(gcwq); + } + } + + spin_unlock_irq(&gcwq->lock); +} + +static bool send_mayday(struct work_struct *work) +{ + struct cpu_workqueue_struct *cwq = get_work_cwq(work); + struct workqueue_struct *wq = cwq->wq; + + if (!(wq->flags & WQ_RESCUER)) + return false; + + /* mayday mayday mayday */ + if (!cpumask_test_and_set_cpu(cwq->gcwq->cpu, wq->mayday_mask)) + wake_up_process(wq->rescuer->task); + return true; +} + +static void gcwq_mayday_timeout(unsigned long __gcwq) +{ + struct global_cwq *gcwq = (void *)__gcwq; + struct work_struct *work; + + spin_lock_irq(&gcwq->lock); + + if (need_to_create_worker(gcwq)) { + /* + * We've been trying to create a new worker but + * haven't been successful. We might be hitting an + * allocation deadlock. Send distress signals to + * rescuers. + */ + list_for_each_entry(work, &gcwq->worklist, entry) + send_mayday(work); + } + + spin_unlock_irq(&gcwq->lock); + + mod_timer(&gcwq->mayday_timer, jiffies + MAYDAY_INTERVAL); +} + +/** + * maybe_create_worker - create a new worker if necessary + * @gcwq: gcwq to create a new worker for + * + * Create a new worker for @gcwq if necessary. @gcwq is guaranteed to + * have at least one idle worker on return from this function. If + * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is + * sent to all rescuers with works scheduled on @gcwq to resolve + * possible allocation deadlock. + * + * On return, need_to_create_worker() is guaranteed to be false and + * may_start_working() true. + * + * LOCKING: + * spin_lock_irq(gcwq->lock) which may be released and regrabbed + * multiple times. Does GFP_KERNEL allocations. Called only from + * manager. + * + * RETURNS: + * false if no action was taken and gcwq->lock stayed locked, true + * otherwise. + */ +static bool maybe_create_worker(struct global_cwq *gcwq) +{ + if (!need_to_create_worker(gcwq)) + return false; +restart: + /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ + mod_timer(&gcwq->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); + + while (true) { + struct worker *worker; + + spin_unlock_irq(&gcwq->lock); + + worker = create_worker(gcwq, true); + if (worker) { + del_timer_sync(&gcwq->mayday_timer); + spin_lock_irq(&gcwq->lock); + start_worker(worker); + BUG_ON(need_to_create_worker(gcwq)); + return true; + } + + if (!need_to_create_worker(gcwq)) + break; + + spin_unlock_irq(&gcwq->lock); + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(CREATE_COOLDOWN); + spin_lock_irq(&gcwq->lock); + if (!need_to_create_worker(gcwq)) + break; + } + + spin_unlock_irq(&gcwq->lock); + del_timer_sync(&gcwq->mayday_timer); + spin_lock_irq(&gcwq->lock); + if (need_to_create_worker(gcwq)) + goto restart; + return true; +} + +/** + * maybe_destroy_worker - destroy workers which have been idle for a while + * @gcwq: gcwq to destroy workers for + * + * Destroy @gcwq workers which have been idle for longer than + * IDLE_WORKER_TIMEOUT. + * + * LOCKING: + * spin_lock_irq(gcwq->lock) which may be released and regrabbed + * multiple times. Called only from manager. + * + * RETURNS: + * false if no action was taken and gcwq->lock stayed locked, true + * otherwise. + */ +static bool maybe_destroy_workers(struct global_cwq *gcwq) +{ + bool ret = false; + + while (too_many_workers(gcwq)) { + struct worker *worker; + unsigned long expires; + + worker = list_entry(gcwq->idle_list.prev, struct worker, entry); + expires = worker->last_active + IDLE_WORKER_TIMEOUT; + + if (time_before(jiffies, expires)) { + mod_timer(&gcwq->idle_timer, expires); + break; + } + + destroy_worker(worker); + ret = true; + } + + return ret; +} + +/** + * manage_workers - manage worker pool + * @worker: self + * + * Assume the manager role and manage gcwq worker pool @worker belongs + * to. At any given time, there can be only zero or one manager per + * gcwq. The exclusion is handled automatically by this function. + * + * The caller can safely start processing works on false return. On + * true return, it's guaranteed that need_to_create_worker() is false + * and may_start_working() is true. + * + * CONTEXT: + * spin_lock_irq(gcwq->lock) which may be released and regrabbed + * multiple times. Does GFP_KERNEL allocations. + * + * RETURNS: + * false if no action was taken and gcwq->lock stayed locked, true if + * some action was taken. + */ +static bool manage_workers(struct worker *worker) +{ + struct global_cwq *gcwq = worker->gcwq; + bool ret = false; + + if (gcwq->flags & GCWQ_MANAGING_WORKERS) + return ret; + + gcwq->flags &= ~GCWQ_MANAGE_WORKERS; + gcwq->flags |= GCWQ_MANAGING_WORKERS; + + /* + * Destroy and then create so that may_start_working() is true + * on return. + */ + ret |= maybe_destroy_workers(gcwq); + ret |= maybe_create_worker(gcwq); + + gcwq->flags &= ~GCWQ_MANAGING_WORKERS; + + /* + * The trustee might be waiting to take over the manager + * position, tell it we're done. + */ + if (unlikely(gcwq->trustee)) + wake_up_all(&gcwq->trustee_wait); + + return ret; +} + /** * move_linked_works - move linked works to a list * @work: start of series of works to be scheduled @@ -1169,24 +1680,39 @@ static void process_scheduled_works(struct worker *worker) * worker_thread - the worker thread function * @__worker: self * - * The cwq worker thread function. + * The gcwq worker thread function. There's a single dynamic pool of + * these per each cpu. These workers process all works regardless of + * their specific target workqueue. The only exception is works which + * belong to workqueues with a rescuer which will be explained in + * rescuer_thread(). */ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct global_cwq *gcwq = worker->gcwq; + /* tell the scheduler that this is a workqueue worker */ + worker->task->flags |= PF_WQ_WORKER; woke_up: spin_lock_irq(&gcwq->lock); /* DIE can be set only while we're idle, checking here is enough */ if (worker->flags & WORKER_DIE) { spin_unlock_irq(&gcwq->lock); + worker->task->flags &= ~PF_WQ_WORKER; return 0; } worker_leave_idle(worker); recheck: + /* no more worker necessary? */ + if (!need_more_worker(gcwq)) + goto sleep; + + /* do we need to manage? */ + if (unlikely(!may_start_working(gcwq)) && manage_workers(worker)) + goto recheck; + /* * ->scheduled list can only be filled while a worker is * preparing to process a work or actually processing it. @@ -1194,27 +1720,18 @@ recheck: */ BUG_ON(!list_empty(&worker->scheduled)); - while (!list_empty(&gcwq->worklist)) { + /* + * When control reaches this point, we're guaranteed to have + * at least one idle worker or that someone else has already + * assumed the manager role. + */ + worker_clr_flags(worker, WORKER_PREP); + + do { struct work_struct *work = list_first_entry(&gcwq->worklist, struct work_struct, entry); - /* - * The following is a rather inefficient way to close - * race window against cpu hotplug operations. Will - * be replaced soon. - */ - if (unlikely(!(worker->flags & WORKER_ROGUE) && - !cpumask_equal(&worker->task->cpus_allowed, - get_cpu_mask(gcwq->cpu)))) { - spin_unlock_irq(&gcwq->lock); - set_cpus_allowed_ptr(worker->task, - get_cpu_mask(gcwq->cpu)); - cpu_relax(); - spin_lock_irq(&gcwq->lock); - goto recheck; - } - if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) { /* optimization path, not strictly necessary */ process_one_work(worker, work); @@ -1224,13 +1741,19 @@ recheck: move_linked_works(work, &worker->scheduled, NULL); process_scheduled_works(worker); } - } + } while (keep_working(gcwq)); + + worker_set_flags(worker, WORKER_PREP, false); + if (unlikely(need_to_manage_workers(gcwq)) && manage_workers(worker)) + goto recheck; +sleep: /* - * gcwq->lock is held and there's no work to process, sleep. - * Workers are woken up only while holding gcwq->lock, so - * setting the current state before releasing gcwq->lock is - * enough to prevent losing any event. + * gcwq->lock is held and there's no work to process and no + * need to manage, sleep. Workers are woken up only while + * holding gcwq->lock or from local cpu, so setting the + * current state before releasing gcwq->lock is enough to + * prevent losing any event. */ worker_enter_idle(worker); __set_current_state(TASK_INTERRUPTIBLE); @@ -1239,6 +1762,68 @@ recheck: goto woke_up; } +/** + * rescuer_thread - the rescuer thread function + * @__wq: the associated workqueue + * + * Workqueue rescuer thread function. There's one rescuer for each + * workqueue which has WQ_RESCUER set. + * + * Regular work processing on a gcwq may block trying to create a new + * worker which uses GFP_KERNEL allocation which has slight chance of + * developing into deadlock if some works currently on the same queue + * need to be processed to satisfy the GFP_KERNEL allocation. This is + * the problem rescuer solves. + * + * When such condition is possible, the gcwq summons rescuers of all + * workqueues which have works queued on the gcwq and let them process + * those works so that forward progress can be guaranteed. + * + * This should happen rarely. + */ +static int rescuer_thread(void *__wq) +{ + struct workqueue_struct *wq = __wq; + struct worker *rescuer = wq->rescuer; + struct list_head *scheduled = &rescuer->scheduled; + unsigned int cpu; + + set_user_nice(current, RESCUER_NICE_LEVEL); +repeat: + set_current_state(TASK_INTERRUPTIBLE); + + if (kthread_should_stop()) + return 0; + + for_each_cpu(cpu, wq->mayday_mask) { + struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + struct global_cwq *gcwq = cwq->gcwq; + struct work_struct *work, *n; + + __set_current_state(TASK_RUNNING); + cpumask_clear_cpu(cpu, wq->mayday_mask); + + /* migrate to the target cpu if possible */ + rescuer->gcwq = gcwq; + worker_maybe_bind_and_lock(rescuer); + + /* + * Slurp in all works issued via this workqueue and + * process'em. + */ + BUG_ON(!list_empty(&rescuer->scheduled)); + list_for_each_entry_safe(work, n, &gcwq->worklist, entry) + if (get_work_cwq(work) == cwq) + move_linked_works(work, scheduled, &n); + + process_scheduled_works(rescuer); + spin_unlock_irq(&gcwq->lock); + } + + schedule(); + goto repeat; +} + struct wq_barrier { struct work_struct work; struct completion done; @@ -1998,7 +2583,6 @@ struct workqueue_struct *__create_workqueue_key(const char *name, const char *lock_name) { struct workqueue_struct *wq; - bool failed = false; unsigned int cpu; max_active = clamp_val(max_active, 1, INT_MAX); @@ -2023,13 +2607,6 @@ struct workqueue_struct *__create_workqueue_key(const char *name, lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); INIT_LIST_HEAD(&wq->list); - cpu_maps_update_begin(); - /* - * We must initialize cwqs for each possible cpu even if we - * are going to call destroy_workqueue() finally. Otherwise - * cpu_up() can hit the uninitialized cwq once we drop the - * lock. - */ for_each_possible_cpu(cpu) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); struct global_cwq *gcwq = get_gcwq(cpu); @@ -2040,14 +2617,25 @@ struct workqueue_struct *__create_workqueue_key(const char *name, cwq->flush_color = -1; cwq->max_active = max_active; INIT_LIST_HEAD(&cwq->delayed_works); + } - if (failed) - continue; - cwq->worker = create_worker(gcwq, cpu_online(cpu)); - if (cwq->worker) - start_worker(cwq->worker); - else - failed = true; + if (flags & WQ_RESCUER) { + struct worker *rescuer; + + if (!alloc_cpumask_var(&wq->mayday_mask, GFP_KERNEL)) + goto err; + + wq->rescuer = rescuer = alloc_worker(); + if (!rescuer) + goto err; + + rescuer->task = kthread_create(rescuer_thread, wq, "%s", name); + if (IS_ERR(rescuer->task)) + goto err; + + wq->rescuer = rescuer; + rescuer->task->flags |= PF_THREAD_BOUND; + wake_up_process(rescuer->task); } /* @@ -2065,16 +2653,12 @@ struct workqueue_struct *__create_workqueue_key(const char *name, spin_unlock(&workqueue_lock); - cpu_maps_update_done(); - - if (failed) { - destroy_workqueue(wq); - wq = NULL; - } return wq; err: if (wq) { free_cwqs(wq->cpu_wq); + free_cpumask_var(wq->mayday_mask); + kfree(wq->rescuer); kfree(wq); } return NULL; @@ -2097,42 +2681,26 @@ void destroy_workqueue(struct workqueue_struct *wq) * wq list is used to freeze wq, remove from list after * flushing is complete in case freeze races us. */ - cpu_maps_update_begin(); spin_lock(&workqueue_lock); list_del(&wq->list); spin_unlock(&workqueue_lock); - cpu_maps_update_done(); + /* sanity check */ for_each_possible_cpu(cpu) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - struct global_cwq *gcwq = cwq->gcwq; int i; - if (cwq->worker) { - retry: - spin_lock_irq(&gcwq->lock); - /* - * Worker can only be destroyed while idle. - * Wait till it becomes idle. This is ugly - * and prone to starvation. It will go away - * once dynamic worker pool is implemented. - */ - if (!(cwq->worker->flags & WORKER_IDLE)) { - spin_unlock_irq(&gcwq->lock); - msleep(100); - goto retry; - } - destroy_worker(cwq->worker); - cwq->worker = NULL; - spin_unlock_irq(&gcwq->lock); - } - for (i = 0; i < WORK_NR_COLORS; i++) BUG_ON(cwq->nr_in_flight[i]); BUG_ON(cwq->nr_active); BUG_ON(!list_empty(&cwq->delayed_works)); } + if (wq->flags & WQ_RESCUER) { + kthread_stop(wq->rescuer->task); + free_cpumask_var(wq->mayday_mask); + } + free_cwqs(wq->cpu_wq); kfree(wq); } @@ -2141,10 +2709,18 @@ EXPORT_SYMBOL_GPL(destroy_workqueue); /* * CPU hotplug. * - * CPU hotplug is implemented by allowing cwqs to be detached from - * CPU, running with unbound workers and allowing them to be - * reattached later if the cpu comes back online. A separate thread - * is created to govern cwqs in such state and is called the trustee. + * There are two challenges in supporting CPU hotplug. Firstly, there + * are a lot of assumptions on strong associations among work, cwq and + * gcwq which make migrating pending and scheduled works very + * difficult to implement without impacting hot paths. Secondly, + * gcwqs serve mix of short, long and very long running works making + * blocked draining impractical. + * + * This is solved by allowing a gcwq to be detached from CPU, running + * it with unbound (rogue) workers and allowing it to be reattached + * later if the cpu comes back online. A separate thread is created + * to govern a gcwq in such state and is called the trustee of the + * gcwq. * * Trustee states and their descriptions. * @@ -2152,11 +2728,12 @@ EXPORT_SYMBOL_GPL(destroy_workqueue); * new trustee is started with this state. * * IN_CHARGE Once started, trustee will enter this state after - * making all existing workers rogue. DOWN_PREPARE waits - * for trustee to enter this state. After reaching - * IN_CHARGE, trustee tries to execute the pending - * worklist until it's empty and the state is set to - * BUTCHER, or the state is set to RELEASE. + * assuming the manager role and making all existing + * workers rogue. DOWN_PREPARE waits for trustee to + * enter this state. After reaching IN_CHARGE, trustee + * tries to execute the pending worklist until it's empty + * and the state is set to BUTCHER, or the state is set + * to RELEASE. * * BUTCHER Command state which is set by the cpu callback after * the cpu has went down. Once this state is set trustee @@ -2167,7 +2744,9 @@ EXPORT_SYMBOL_GPL(destroy_workqueue); * RELEASE Command state which is set by the cpu callback if the * cpu down has been canceled or it has come online * again. After recognizing this state, trustee stops - * trying to drain or butcher and transits to DONE. + * trying to drain or butcher and clears ROGUE, rebinds + * all remaining workers back to the cpu and releases + * manager role. * * DONE Trustee will enter this state after BUTCHER or RELEASE * is complete. @@ -2233,17 +2812,24 @@ static int __cpuinit trustee_thread(void *__gcwq) { struct global_cwq *gcwq = __gcwq; struct worker *worker; + struct work_struct *work; struct hlist_node *pos; + long rc; int i; BUG_ON(gcwq->cpu != smp_processor_id()); spin_lock_irq(&gcwq->lock); /* - * Make all workers rogue. Trustee must be bound to the - * target cpu and can't be cancelled. + * Claim the manager position and make all workers rogue. + * Trustee must be bound to the target cpu and can't be + * cancelled. */ BUG_ON(gcwq->cpu != smp_processor_id()); + rc = trustee_wait_event(!(gcwq->flags & GCWQ_MANAGING_WORKERS)); + BUG_ON(rc < 0); + + gcwq->flags |= GCWQ_MANAGING_WORKERS; list_for_each_entry(worker, &gcwq->idle_list, entry) worker_set_flags(worker, WORKER_ROGUE, false); @@ -2251,6 +2837,28 @@ static int __cpuinit trustee_thread(void *__gcwq) for_each_busy_worker(worker, i, pos, gcwq) worker_set_flags(worker, WORKER_ROGUE, false); + /* + * Call schedule() so that we cross rq->lock and thus can + * guarantee sched callbacks see the rogue flag. This is + * necessary as scheduler callbacks may be invoked from other + * cpus. + */ + spin_unlock_irq(&gcwq->lock); + schedule(); + spin_lock_irq(&gcwq->lock); + + /* + * Sched callbacks are disabled now. gcwq->nr_running should + * be zero and will stay that way, making need_more_worker() + * and keep_working() always return true as long as the + * worklist is not empty. + */ + WARN_ON_ONCE(atomic_read(get_gcwq_nr_running(gcwq->cpu)) != 0); + + spin_unlock_irq(&gcwq->lock); + del_timer_sync(&gcwq->idle_timer); + spin_lock_irq(&gcwq->lock); + /* * We're now in charge. Notify and proceed to drain. We need * to keep the gcwq running during the whole CPU down @@ -2263,18 +2871,90 @@ static int __cpuinit trustee_thread(void *__gcwq) /* * The original cpu is in the process of dying and may go away * anytime now. When that happens, we and all workers would - * be migrated to other cpus. Try draining any left work. - * Note that if the gcwq is frozen, there may be frozen works - * in freezeable cwqs. Don't declare completion while frozen. + * be migrated to other cpus. Try draining any left work. We + * want to get it over with ASAP - spam rescuers, wake up as + * many idlers as necessary and create new ones till the + * worklist is empty. Note that if the gcwq is frozen, there + * may be frozen works in freezeable cwqs. Don't declare + * completion while frozen. */ while (gcwq->nr_workers != gcwq->nr_idle || gcwq->flags & GCWQ_FREEZING || gcwq->trustee_state == TRUSTEE_IN_CHARGE) { + int nr_works = 0; + + list_for_each_entry(work, &gcwq->worklist, entry) { + send_mayday(work); + nr_works++; + } + + list_for_each_entry(worker, &gcwq->idle_list, entry) { + if (!nr_works--) + break; + wake_up_process(worker->task); + } + + if (need_to_create_worker(gcwq)) { + spin_unlock_irq(&gcwq->lock); + worker = create_worker(gcwq, false); + spin_lock_irq(&gcwq->lock); + if (worker) { + worker_set_flags(worker, WORKER_ROGUE, false); + start_worker(worker); + } + } + /* give a breather */ if (trustee_wait_event_timeout(false, TRUSTEE_COOLDOWN) < 0) break; } + /* + * Either all works have been scheduled and cpu is down, or + * cpu down has already been canceled. Wait for and butcher + * all workers till we're canceled. + */ + do { + rc = trustee_wait_event(!list_empty(&gcwq->idle_list)); + while (!list_empty(&gcwq->idle_list)) + destroy_worker(list_first_entry(&gcwq->idle_list, + struct worker, entry)); + } while (gcwq->nr_workers && rc >= 0); + + /* + * At this point, either draining has completed and no worker + * is left, or cpu down has been canceled or the cpu is being + * brought back up. There shouldn't be any idle one left. + * Tell the remaining busy ones to rebind once it finishes the + * currently scheduled works by scheduling the rebind_work. + */ + WARN_ON(!list_empty(&gcwq->idle_list)); + + for_each_busy_worker(worker, i, pos, gcwq) { + struct work_struct *rebind_work = &worker->rebind_work; + + /* + * Rebind_work may race with future cpu hotplug + * operations. Use a separate flag to mark that + * rebinding is scheduled. + */ + worker_set_flags(worker, WORKER_REBIND, false); + worker_clr_flags(worker, WORKER_ROGUE); + + /* queue rebind_work, wq doesn't matter, use the default one */ + if (test_and_set_bit(WORK_STRUCT_PENDING_BIT, + work_data_bits(rebind_work))) + continue; + + debug_work_activate(rebind_work); + insert_work(get_cwq(gcwq->cpu, keventd_wq), rebind_work, + worker->scheduled.next, + work_color_to_flags(WORK_NO_COLOR)); + } + + /* relinquish manager role */ + gcwq->flags &= ~GCWQ_MANAGING_WORKERS; + /* notify completion */ gcwq->trustee = NULL; gcwq->trustee_state = TRUSTEE_DONE; @@ -2313,10 +2993,8 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, unsigned int cpu = (unsigned long)hcpu; struct global_cwq *gcwq = get_gcwq(cpu); struct task_struct *new_trustee = NULL; - struct worker *worker; - struct hlist_node *pos; + struct worker *uninitialized_var(new_worker); unsigned long flags; - int i; action &= ~CPU_TASKS_FROZEN; @@ -2327,6 +3005,15 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, if (IS_ERR(new_trustee)) return notifier_from_errno(PTR_ERR(new_trustee)); kthread_bind(new_trustee, cpu); + /* fall through */ + case CPU_UP_PREPARE: + BUG_ON(gcwq->first_idle); + new_worker = create_worker(gcwq, false); + if (!new_worker) { + if (new_trustee) + kthread_stop(new_trustee); + return NOTIFY_BAD; + } } /* some are called w/ irq disabled, don't disturb irq status */ @@ -2340,26 +3027,50 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, gcwq->trustee_state = TRUSTEE_START; wake_up_process(gcwq->trustee); wait_trustee_state(gcwq, TRUSTEE_IN_CHARGE); + /* fall through */ + case CPU_UP_PREPARE: + BUG_ON(gcwq->first_idle); + gcwq->first_idle = new_worker; + break; + + case CPU_DYING: + /* + * Before this, the trustee and all workers except for + * the ones which are still executing works from + * before the last CPU down must be on the cpu. After + * this, they'll all be diasporas. + */ + gcwq->flags |= GCWQ_DISASSOCIATED; break; case CPU_POST_DEAD: gcwq->trustee_state = TRUSTEE_BUTCHER; + /* fall through */ + case CPU_UP_CANCELED: + destroy_worker(gcwq->first_idle); + gcwq->first_idle = NULL; break; case CPU_DOWN_FAILED: case CPU_ONLINE: + gcwq->flags &= ~GCWQ_DISASSOCIATED; if (gcwq->trustee_state != TRUSTEE_DONE) { gcwq->trustee_state = TRUSTEE_RELEASE; wake_up_process(gcwq->trustee); wait_trustee_state(gcwq, TRUSTEE_DONE); } - /* clear ROGUE from all workers */ - list_for_each_entry(worker, &gcwq->idle_list, entry) - worker_clr_flags(worker, WORKER_ROGUE); - - for_each_busy_worker(worker, i, pos, gcwq) - worker_clr_flags(worker, WORKER_ROGUE); + /* + * Trustee is done and there might be no worker left. + * Put the first_idle in and request a real manager to + * take a look. + */ + spin_unlock_irq(&gcwq->lock); + kthread_bind(gcwq->first_idle->task, cpu); + spin_lock_irq(&gcwq->lock); + gcwq->flags |= GCWQ_MANAGE_WORKERS; + start_worker(gcwq->first_idle); + gcwq->first_idle = NULL; break; } @@ -2548,10 +3259,10 @@ void thaw_workqueues(void) if (wq->single_cpu == gcwq->cpu && !cwq->nr_active && list_empty(&cwq->delayed_works)) cwq_unbind_single_cpu(cwq); - - wake_up_process(cwq->worker->task); } + wake_up_worker(gcwq); + spin_unlock_irq(&gcwq->lock); } @@ -2588,12 +3299,31 @@ void __init init_workqueues(void) for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) INIT_HLIST_HEAD(&gcwq->busy_hash[i]); + init_timer_deferrable(&gcwq->idle_timer); + gcwq->idle_timer.function = idle_worker_timeout; + gcwq->idle_timer.data = (unsigned long)gcwq; + + setup_timer(&gcwq->mayday_timer, gcwq_mayday_timeout, + (unsigned long)gcwq); + ida_init(&gcwq->worker_ida); gcwq->trustee_state = TRUSTEE_DONE; init_waitqueue_head(&gcwq->trustee_wait); } + /* create the initial worker */ + for_each_online_cpu(cpu) { + struct global_cwq *gcwq = get_gcwq(cpu); + struct worker *worker; + + worker = create_worker(gcwq, true); + BUG_ON(!worker); + spin_lock_irq(&gcwq->lock); + start_worker(worker); + spin_unlock_irq(&gcwq->lock); + } + keventd_wq = create_workqueue("events"); BUG_ON(!keventd_wq); } diff --git a/kernel/workqueue_sched.h b/kernel/workqueue_sched.h index af040babb742..2d10fc98dc79 100644 --- a/kernel/workqueue_sched.h +++ b/kernel/workqueue_sched.h @@ -4,13 +4,6 @@ * Scheduler hooks for concurrency managed workqueue. Only to be * included from sched.c and workqueue.c. */ -static inline void wq_worker_waking_up(struct task_struct *task, - unsigned int cpu) -{ -} - -static inline struct task_struct *wq_worker_sleeping(struct task_struct *task, - unsigned int cpu) -{ - return NULL; -} +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); -- cgit From b71ab8c2025caef8db719aa41af0ed735dc543cd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:14 +0200 Subject: workqueue: increase max_active of keventd and kill current_is_keventd() Define WQ_MAX_ACTIVE and create keventd with max_active set to half of it which means that keventd now can process upto WQ_MAX_ACTIVE / 2 - 1 works concurrently. Unless some combination can result in dependency loop longer than max_active, deadlock won't happen and thus it's unnecessary to check whether current_is_keventd() before trying to schedule a work. Kill current_is_keventd(). (Lockdep annotations are broken. We need lock_map_acquire_read_norecurse()) Signed-off-by: Tejun Heo Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Christoph Lameter Cc: Tony Luck Cc: Andi Kleen Cc: Oleg Nesterov --- arch/ia64/kernel/smpboot.c | 2 +- arch/x86/kernel/smpboot.c | 2 +- include/linux/workqueue.h | 4 ++- kernel/workqueue.c | 63 ++++++++++------------------------------------ 4 files changed, 18 insertions(+), 53 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 6a1380e90f87..99dcc85193c9 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -519,7 +519,7 @@ do_boot_cpu (int sapicid, int cpu) /* * We can't use kernel_thread since we must avoid to reschedule the child. */ - if (!keventd_up() || current_is_keventd()) + if (!keventd_up()) c_idle.work.func(&c_idle.work); else { schedule_work(&c_idle.work); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c4f33b2e77d6..4d90f376e985 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -735,7 +735,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) goto do_rest; } - if (!keventd_up() || current_is_keventd()) + if (!keventd_up()) c_idle.work.func(&c_idle.work); else { schedule_work(&c_idle.work); diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index b8f4ec45c40a..33e24e734d50 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -227,6 +227,9 @@ enum { WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ WQ_RESCUER = 1 << 3, /* has an rescue worker */ + + WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ + WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, }; extern struct workqueue_struct * @@ -280,7 +283,6 @@ extern int schedule_delayed_work(struct delayed_work *work, unsigned long delay) extern int schedule_delayed_work_on(int cpu, struct delayed_work *work, unsigned long delay); extern int schedule_on_each_cpu(work_func_t func); -extern int current_is_keventd(void); extern int keventd_up(void); extern void init_workqueues(void); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 0ad46523b423..4190e84cf995 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2398,7 +2398,6 @@ EXPORT_SYMBOL(schedule_delayed_work_on); int schedule_on_each_cpu(work_func_t func) { int cpu; - int orig = -1; struct work_struct *works; works = alloc_percpu(struct work_struct); @@ -2407,23 +2406,12 @@ int schedule_on_each_cpu(work_func_t func) get_online_cpus(); - /* - * When running in keventd don't schedule a work item on - * itself. Can just call directly because the work queue is - * already bound. This also is faster. - */ - if (current_is_keventd()) - orig = raw_smp_processor_id(); - for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, func); - if (cpu != orig) - schedule_work_on(cpu, work); + schedule_work_on(cpu, work); } - if (orig >= 0) - func(per_cpu_ptr(works, orig)); for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); @@ -2494,41 +2482,6 @@ int keventd_up(void) return keventd_wq != NULL; } -int current_is_keventd(void) -{ - bool found = false; - unsigned int cpu; - - /* - * There no longer is one-to-one relation between worker and - * work queue and a worker task might be unbound from its cpu - * if the cpu was offlined. Match all busy workers. This - * function will go away once dynamic pool is implemented. - */ - for_each_possible_cpu(cpu) { - struct global_cwq *gcwq = get_gcwq(cpu); - struct worker *worker; - struct hlist_node *pos; - unsigned long flags; - int i; - - spin_lock_irqsave(&gcwq->lock, flags); - - for_each_busy_worker(worker, i, pos, gcwq) { - if (worker->task == current) { - found = true; - break; - } - } - - spin_unlock_irqrestore(&gcwq->lock, flags); - if (found) - break; - } - - return found; -} - static struct cpu_workqueue_struct *alloc_cwqs(void) { /* @@ -2576,6 +2529,16 @@ static void free_cwqs(struct cpu_workqueue_struct *cwqs) #endif } +static int wq_clamp_max_active(int max_active, const char *name) +{ + if (max_active < 1 || max_active > WQ_MAX_ACTIVE) + printk(KERN_WARNING "workqueue: max_active %d requested for %s " + "is out of range, clamping between %d and %d\n", + max_active, name, 1, WQ_MAX_ACTIVE); + + return clamp_val(max_active, 1, WQ_MAX_ACTIVE); +} + struct workqueue_struct *__create_workqueue_key(const char *name, unsigned int flags, int max_active, @@ -2585,7 +2548,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name, struct workqueue_struct *wq; unsigned int cpu; - max_active = clamp_val(max_active, 1, INT_MAX); + max_active = wq_clamp_max_active(max_active, name); wq = kzalloc(sizeof(*wq), GFP_KERNEL); if (!wq) @@ -3324,6 +3287,6 @@ void __init init_workqueues(void) spin_unlock_irq(&gcwq->lock); } - keventd_wq = create_workqueue("events"); + keventd_wq = __create_workqueue("events", 0, WQ_DFL_ACTIVE); BUG_ON(!keventd_wq); } -- cgit From d320c03830b17af64e4547075003b1eeb274bc6c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:14 +0200 Subject: workqueue: s/__create_workqueue()/alloc_workqueue()/, and add system workqueues This patch makes changes to make new workqueue features available to its users. * Now that workqueue is more featureful, there should be a public workqueue creation function which takes paramters to control them. Rename __create_workqueue() to alloc_workqueue() and make 0 max_active mean WQ_DFL_ACTIVE. In the long run, all create_workqueue_*() will be converted over to alloc_workqueue(). * To further unify access interface, rename keventd_wq to system_wq and export it. * Add system_long_wq and system_nrt_wq. The former is to host long running works separately (so that flush_scheduled_work() dosen't take so long) and the latter guarantees any queued work item is never executed in parallel by multiple CPUs. These will be used by future patches to update workqueue users. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 40 +++++++++++++++++++++++++++++----------- kernel/workqueue.c | 42 +++++++++++++++++++++++++----------------- 2 files changed, 54 insertions(+), 28 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 33e24e734d50..48b7422f25ae 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -232,12 +232,31 @@ enum { WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, }; +/* + * System-wide workqueues which are always present. + * + * system_wq is the one used by schedule[_delayed]_work[_on](). + * Multi-CPU multi-threaded. There are users which expect relatively + * short queue flush time. Don't queue works which can run for too + * long. + * + * system_long_wq is similar to system_wq but may host long running + * works. Queue flushing might take relatively long. + * + * system_nrt_wq is non-reentrant and guarantees that any given work + * item is never executed in parallel by multiple CPUs. Queue + * flushing might take relatively long. + */ +extern struct workqueue_struct *system_wq; +extern struct workqueue_struct *system_long_wq; +extern struct workqueue_struct *system_nrt_wq; + extern struct workqueue_struct * -__create_workqueue_key(const char *name, unsigned int flags, int max_active, - struct lock_class_key *key, const char *lock_name); +__alloc_workqueue_key(const char *name, unsigned int flags, int max_active, + struct lock_class_key *key, const char *lock_name); #ifdef CONFIG_LOCKDEP -#define __create_workqueue(name, flags, max_active) \ +#define alloc_workqueue(name, flags, max_active) \ ({ \ static struct lock_class_key __key; \ const char *__lock_name; \ @@ -247,21 +266,20 @@ __create_workqueue_key(const char *name, unsigned int flags, int max_active, else \ __lock_name = #name; \ \ - __create_workqueue_key((name), (flags), (max_active), \ - &__key, __lock_name); \ + __alloc_workqueue_key((name), (flags), (max_active), \ + &__key, __lock_name); \ }) #else -#define __create_workqueue(name, flags, max_active) \ - __create_workqueue_key((name), (flags), (max_active), NULL, NULL) +#define alloc_workqueue(name, flags, max_active) \ + __alloc_workqueue_key((name), (flags), (max_active), NULL, NULL) #endif #define create_workqueue(name) \ - __create_workqueue((name), WQ_RESCUER, 1) + alloc_workqueue((name), WQ_RESCUER, 1) #define create_freezeable_workqueue(name) \ - __create_workqueue((name), \ - WQ_FREEZEABLE | WQ_SINGLE_CPU | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_CPU | WQ_RESCUER, 1) #define create_singlethread_workqueue(name) \ - __create_workqueue((name), WQ_SINGLE_CPU | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_SINGLE_CPU | WQ_RESCUER, 1) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4190e84cf995..16ce617974d2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -210,6 +210,13 @@ struct workqueue_struct { #endif }; +struct workqueue_struct *system_wq __read_mostly; +struct workqueue_struct *system_long_wq __read_mostly; +struct workqueue_struct *system_nrt_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_wq); +EXPORT_SYMBOL_GPL(system_long_wq); +EXPORT_SYMBOL_GPL(system_nrt_wq); + #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) @@ -2306,8 +2313,6 @@ int cancel_delayed_work_sync(struct delayed_work *dwork) } EXPORT_SYMBOL(cancel_delayed_work_sync); -static struct workqueue_struct *keventd_wq __read_mostly; - /** * schedule_work - put work task in global workqueue * @work: job to be done @@ -2321,7 +2326,7 @@ static struct workqueue_struct *keventd_wq __read_mostly; */ int schedule_work(struct work_struct *work) { - return queue_work(keventd_wq, work); + return queue_work(system_wq, work); } EXPORT_SYMBOL(schedule_work); @@ -2334,7 +2339,7 @@ EXPORT_SYMBOL(schedule_work); */ int schedule_work_on(int cpu, struct work_struct *work) { - return queue_work_on(cpu, keventd_wq, work); + return queue_work_on(cpu, system_wq, work); } EXPORT_SYMBOL(schedule_work_on); @@ -2349,7 +2354,7 @@ EXPORT_SYMBOL(schedule_work_on); int schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) { - return queue_delayed_work(keventd_wq, dwork, delay); + return queue_delayed_work(system_wq, dwork, delay); } EXPORT_SYMBOL(schedule_delayed_work); @@ -2382,7 +2387,7 @@ EXPORT_SYMBOL(flush_delayed_work); int schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { - return queue_delayed_work_on(cpu, keventd_wq, dwork, delay); + return queue_delayed_work_on(cpu, system_wq, dwork, delay); } EXPORT_SYMBOL(schedule_delayed_work_on); @@ -2447,7 +2452,7 @@ int schedule_on_each_cpu(work_func_t func) */ void flush_scheduled_work(void) { - flush_workqueue(keventd_wq); + flush_workqueue(system_wq); } EXPORT_SYMBOL(flush_scheduled_work); @@ -2479,7 +2484,7 @@ EXPORT_SYMBOL_GPL(execute_in_process_context); int keventd_up(void) { - return keventd_wq != NULL; + return system_wq != NULL; } static struct cpu_workqueue_struct *alloc_cwqs(void) @@ -2539,15 +2544,16 @@ static int wq_clamp_max_active(int max_active, const char *name) return clamp_val(max_active, 1, WQ_MAX_ACTIVE); } -struct workqueue_struct *__create_workqueue_key(const char *name, - unsigned int flags, - int max_active, - struct lock_class_key *key, - const char *lock_name) +struct workqueue_struct *__alloc_workqueue_key(const char *name, + unsigned int flags, + int max_active, + struct lock_class_key *key, + const char *lock_name) { struct workqueue_struct *wq; unsigned int cpu; + max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, name); wq = kzalloc(sizeof(*wq), GFP_KERNEL); @@ -2626,7 +2632,7 @@ err: } return NULL; } -EXPORT_SYMBOL_GPL(__create_workqueue_key); +EXPORT_SYMBOL_GPL(__alloc_workqueue_key); /** * destroy_workqueue - safely terminate a workqueue @@ -2910,7 +2916,7 @@ static int __cpuinit trustee_thread(void *__gcwq) continue; debug_work_activate(rebind_work); - insert_work(get_cwq(gcwq->cpu, keventd_wq), rebind_work, + insert_work(get_cwq(gcwq->cpu, system_wq), rebind_work, worker->scheduled.next, work_color_to_flags(WORK_NO_COLOR)); } @@ -3287,6 +3293,8 @@ void __init init_workqueues(void) spin_unlock_irq(&gcwq->lock); } - keventd_wq = __create_workqueue("events", 0, WQ_DFL_ACTIVE); - BUG_ON(!keventd_wq); + system_wq = alloc_workqueue("events", 0, 0); + system_long_wq = alloc_workqueue("events_long", 0, 0); + system_nrt_wq = alloc_workqueue("events_nrt", WQ_NON_REENTRANT, 0); + BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq); } -- cgit From dcd989cb73ab0f7b722d64ab6516f101d9f43f88 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:14 +0200 Subject: workqueue: implement several utility APIs Implement the following utility APIs. workqueue_set_max_active() : adjust max_active of a wq workqueue_congested() : test whether a wq is contested work_cpu() : determine the last / current cpu of a work work_busy() : query whether a work is busy * Anton Blanchard fixed missing ret initialization in work_busy(). Signed-off-by: Tejun Heo Cc: Anton Blanchard --- include/linux/workqueue.h | 11 ++++- kernel/workqueue.c | 108 +++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 117 insertions(+), 2 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 48b7422f25ae..0a7f79729380 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -61,6 +61,10 @@ enum { WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, WORK_STRUCT_NO_CPU = NR_CPUS << WORK_STRUCT_FLAG_BITS, + + /* bit mask for work_busy() return values */ + WORK_BUSY_PENDING = 1 << 0, + WORK_BUSY_RUNNING = 1 << 1, }; struct work_struct { @@ -307,9 +311,14 @@ extern void init_workqueues(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 void workqueue_set_max_active(struct workqueue_struct *wq, + int max_active); +extern bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq); +extern unsigned int work_cpu(struct work_struct *work); +extern unsigned int work_busy(struct work_struct *work); + /* * Kill off a pending schedule_delayed_work(). Note that the work callback * function may still be running on return from cancel_delayed_work(), unless diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 16ce617974d2..c1aa65c2ff38 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -203,7 +203,7 @@ struct workqueue_struct { cpumask_var_t mayday_mask; /* cpus requesting rescue */ struct worker *rescuer; /* I: rescue worker */ - int saved_max_active; /* I: saved cwq max_active */ + int saved_max_active; /* W: saved cwq max_active */ const char *name; /* I: workqueue name */ #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; @@ -2675,6 +2675,112 @@ void destroy_workqueue(struct workqueue_struct *wq) } EXPORT_SYMBOL_GPL(destroy_workqueue); +/** + * workqueue_set_max_active - adjust max_active of a workqueue + * @wq: target workqueue + * @max_active: new max_active value. + * + * Set max_active of @wq to @max_active. + * + * CONTEXT: + * Don't call from IRQ context. + */ +void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) +{ + unsigned int cpu; + + max_active = wq_clamp_max_active(max_active, wq->name); + + spin_lock(&workqueue_lock); + + wq->saved_max_active = max_active; + + for_each_possible_cpu(cpu) { + struct global_cwq *gcwq = get_gcwq(cpu); + + spin_lock_irq(&gcwq->lock); + + if (!(wq->flags & WQ_FREEZEABLE) || + !(gcwq->flags & GCWQ_FREEZING)) + get_cwq(gcwq->cpu, wq)->max_active = max_active; + + spin_unlock_irq(&gcwq->lock); + } + + spin_unlock(&workqueue_lock); +} +EXPORT_SYMBOL_GPL(workqueue_set_max_active); + +/** + * workqueue_congested - test whether a workqueue is congested + * @cpu: CPU in question + * @wq: target workqueue + * + * Test whether @wq's cpu workqueue for @cpu is congested. There is + * no synchronization around this function and the test result is + * unreliable and only useful as advisory hints or for debugging. + * + * RETURNS: + * %true if congested, %false otherwise. + */ +bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq) +{ + struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + + return !list_empty(&cwq->delayed_works); +} +EXPORT_SYMBOL_GPL(workqueue_congested); + +/** + * work_cpu - return the last known associated cpu for @work + * @work: the work of interest + * + * RETURNS: + * CPU number if @work was ever queued. NR_CPUS otherwise. + */ +unsigned int work_cpu(struct work_struct *work) +{ + struct global_cwq *gcwq = get_work_gcwq(work); + + return gcwq ? gcwq->cpu : NR_CPUS; +} +EXPORT_SYMBOL_GPL(work_cpu); + +/** + * work_busy - test whether a work is currently pending or running + * @work: the work to be tested + * + * Test whether @work is currently pending or running. There is no + * synchronization around this function and the test result is + * unreliable and only useful as advisory hints or for debugging. + * Especially for reentrant wqs, the pending state might hide the + * running state. + * + * RETURNS: + * OR'd bitmask of WORK_BUSY_* bits. + */ +unsigned int work_busy(struct work_struct *work) +{ + struct global_cwq *gcwq = get_work_gcwq(work); + unsigned long flags; + unsigned int ret = 0; + + if (!gcwq) + return false; + + spin_lock_irqsave(&gcwq->lock, flags); + + if (work_pending(work)) + ret |= WORK_BUSY_PENDING; + if (find_worker_executing_work(gcwq, work)) + ret |= WORK_BUSY_RUNNING; + + spin_unlock_irqrestore(&gcwq->lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(work_busy); + /* * CPU hotplug. * -- cgit From 649027d73a6309ac34dc2886362e662bd73456dc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:14 +0200 Subject: workqueue: implement high priority workqueue This patch implements high priority workqueue which can be specified with WQ_HIGHPRI flag on creation. A high priority workqueue has the following properties. * A work queued to it is queued at the head of the worklist of the respective gcwq after other highpri works, while normal works are always appended at the end. * As long as there are highpri works on gcwq->worklist, [__]need_more_worker() remains %true and process_one_work() wakes up another worker before it start executing a work. The above two properties guarantee that works queued to high priority workqueues are dispatched to workers and start execution as soon as possible regardless of the state of other works. Signed-off-by: Tejun Heo Cc: Andi Kleen Cc: Andrew Morton --- include/linux/workqueue.h | 1 + kernel/workqueue.c | 70 +++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 65 insertions(+), 6 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 0a7f79729380..006dcf7e808a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -231,6 +231,7 @@ enum { WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ WQ_RESCUER = 1 << 3, /* has an rescue worker */ + WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c1aa65c2ff38..5775717288d5 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -43,6 +43,7 @@ enum { GCWQ_MANAGING_WORKERS = 1 << 1, /* managing workers */ GCWQ_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ GCWQ_FREEZING = 1 << 3, /* freeze in progress */ + GCWQ_HIGHPRI_PENDING = 1 << 4, /* highpri works on queue */ /* worker flags */ WORKER_STARTED = 1 << 0, /* started */ @@ -452,15 +453,19 @@ static struct global_cwq *get_work_gcwq(struct work_struct *work) * assume that they're being called with gcwq->lock held. */ +static bool __need_more_worker(struct global_cwq *gcwq) +{ + return !atomic_read(get_gcwq_nr_running(gcwq->cpu)) || + gcwq->flags & GCWQ_HIGHPRI_PENDING; +} + /* * Need to wake up a worker? Called from anything but currently * running workers. */ static bool need_more_worker(struct global_cwq *gcwq) { - atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu); - - return !list_empty(&gcwq->worklist) && !atomic_read(nr_running); + return !list_empty(&gcwq->worklist) && __need_more_worker(gcwq); } /* Can I start working? Called from busy but !running workers. */ @@ -733,6 +738,43 @@ static struct worker *find_worker_executing_work(struct global_cwq *gcwq, work); } +/** + * gcwq_determine_ins_pos - find insertion position + * @gcwq: gcwq of interest + * @cwq: cwq a work is being queued for + * + * A work for @cwq is about to be queued on @gcwq, determine insertion + * position for the work. If @cwq is for HIGHPRI wq, the work is + * queued at the head of the queue but in FIFO order with respect to + * other HIGHPRI works; otherwise, at the end of the queue. This + * function also sets GCWQ_HIGHPRI_PENDING flag to hint @gcwq that + * there are HIGHPRI works pending. + * + * CONTEXT: + * spin_lock_irq(gcwq->lock). + * + * RETURNS: + * Pointer to inserstion position. + */ +static inline struct list_head *gcwq_determine_ins_pos(struct global_cwq *gcwq, + struct cpu_workqueue_struct *cwq) +{ + struct work_struct *twork; + + if (likely(!(cwq->wq->flags & WQ_HIGHPRI))) + return &gcwq->worklist; + + list_for_each_entry(twork, &gcwq->worklist, entry) { + struct cpu_workqueue_struct *tcwq = get_work_cwq(twork); + + if (!(tcwq->wq->flags & WQ_HIGHPRI)) + break; + } + + gcwq->flags |= GCWQ_HIGHPRI_PENDING; + return &twork->entry; +} + /** * insert_work - insert a work into gcwq * @cwq: cwq @work belongs to @@ -770,7 +812,7 @@ static void insert_work(struct cpu_workqueue_struct *cwq, */ smp_mb(); - if (!atomic_read(get_gcwq_nr_running(gcwq->cpu))) + if (__need_more_worker(gcwq)) wake_up_worker(gcwq); } @@ -887,7 +929,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, if (likely(cwq->nr_active < cwq->max_active)) { cwq->nr_active++; - worklist = &gcwq->worklist; + worklist = gcwq_determine_ins_pos(gcwq, cwq); } else worklist = &cwq->delayed_works; @@ -1526,8 +1568,9 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) { struct work_struct *work = list_first_entry(&cwq->delayed_works, struct work_struct, entry); + struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq); - move_linked_works(work, &cwq->gcwq->worklist, NULL); + move_linked_works(work, pos, NULL); cwq->nr_active++; } @@ -1634,6 +1677,21 @@ static void process_one_work(struct worker *worker, struct work_struct *work) set_work_cpu(work, gcwq->cpu); list_del_init(&work->entry); + /* + * If HIGHPRI_PENDING, check the next work, and, if HIGHPRI, + * wake up another worker; otherwise, clear HIGHPRI_PENDING. + */ + if (unlikely(gcwq->flags & GCWQ_HIGHPRI_PENDING)) { + struct work_struct *nwork = list_first_entry(&gcwq->worklist, + struct work_struct, entry); + + if (!list_empty(&gcwq->worklist) && + get_work_cwq(nwork)->wq->flags & WQ_HIGHPRI) + wake_up_worker(gcwq); + else + gcwq->flags &= ~GCWQ_HIGHPRI_PENDING; + } + spin_unlock_irq(&gcwq->lock); work_clear_pending(work); -- cgit From fb0e7beb5c1b6fb4da786ba709d7138373d5fb22 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:15 +0200 Subject: workqueue: implement cpu intensive workqueue This patch implements cpu intensive workqueue which can be specified with WQ_CPU_INTENSIVE flag on creation. Works queued to a cpu intensive workqueue don't participate in concurrency management. IOW, it doesn't contribute to gcwq->nr_running and thus doesn't delay excution of other works. Note that although cpu intensive works won't delay other works, they can be delayed by other works. Combine with WQ_HIGHPRI to avoid being delayed by other works too. As the name suggests this is useful when using workqueue for cpu intensive works. Workers executing cpu intensive works are not considered for workqueue concurrency management and left for the scheduler to manage. Signed-off-by: Tejun Heo Cc: Andrew Morton --- include/linux/workqueue.h | 1 + kernel/workqueue.c | 16 +++++++++++++++- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 006dcf7e808a..3f36d37ac5ba 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -232,6 +232,7 @@ enum { WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ WQ_RESCUER = 1 << 3, /* has an rescue worker */ WQ_HIGHPRI = 1 << 4, /* high priority */ + WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 5775717288d5..6fa847c5c5e9 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -52,8 +52,10 @@ enum { WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_ROGUE = 1 << 4, /* not bound to any cpu */ WORKER_REBIND = 1 << 5, /* mom is home, come back */ + WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ - WORKER_NOT_RUNNING = WORKER_PREP | WORKER_ROGUE | WORKER_REBIND, + WORKER_NOT_RUNNING = WORKER_PREP | WORKER_ROGUE | WORKER_REBIND | + WORKER_CPU_INTENSIVE, /* gcwq->trustee_state */ TRUSTEE_START = 0, /* start */ @@ -1641,6 +1643,7 @@ static void process_one_work(struct worker *worker, struct work_struct *work) struct cpu_workqueue_struct *cwq = get_work_cwq(work); struct global_cwq *gcwq = cwq->gcwq; struct hlist_head *bwh = busy_worker_head(gcwq, work); + bool cpu_intensive = cwq->wq->flags & WQ_CPU_INTENSIVE; work_func_t f = work->func; int work_color; struct worker *collision; @@ -1692,6 +1695,13 @@ static void process_one_work(struct worker *worker, struct work_struct *work) gcwq->flags &= ~GCWQ_HIGHPRI_PENDING; } + /* + * CPU intensive works don't participate in concurrency + * management. They're the scheduler's responsibility. + */ + if (unlikely(cpu_intensive)) + worker_set_flags(worker, WORKER_CPU_INTENSIVE, true); + spin_unlock_irq(&gcwq->lock); work_clear_pending(work); @@ -1713,6 +1723,10 @@ static void process_one_work(struct worker *worker, struct work_struct *work) spin_lock_irq(&gcwq->lock); + /* clear cpu intensive status */ + if (unlikely(cpu_intensive)) + worker_clr_flags(worker, WORKER_CPU_INTENSIVE); + /* we're done with it, release */ hlist_del_init(&worker->hentry); worker->current_work = NULL; -- cgit From bdbc5dd7de5d07d6c9d3536e598956165a031d4c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 2 Jul 2010 10:03:51 +0200 Subject: workqueue: prepare for WQ_UNBOUND implementation In preparation of WQ_UNBOUND addition, make the following changes. * Add WORK_CPU_* constants for pseudo cpu id numbers used (currently only WORK_CPU_NONE) and use them instead of NR_CPUS. This is to allow another pseudo cpu id for unbound cpu. * Reorder WQ_* flags. * Make workqueue_struct->cpu_wq a union which contains a percpu pointer, regular pointer and an unsigned long value and use kzalloc/kfree() in UP allocation path. This will be used to implement unbound workqueues which will use only one cwq on SMPs. * Move alloc_cwqs() allocation after initialization of wq fields, so that alloc_cwqs() has access to wq->flags. * Trivial relocation of wq local variables in freeze functions. These changes don't cause any functional change. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 10 ++++-- kernel/workqueue.c | 83 ++++++++++++++++++++++++----------------------- 2 files changed, 50 insertions(+), 43 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 3f36d37ac5ba..139069a6286c 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -50,6 +50,10 @@ enum { WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS) - 1, WORK_NO_COLOR = WORK_NR_COLORS, + /* special cpu IDs */ + WORK_CPU_NONE = NR_CPUS, + WORK_CPU_LAST = WORK_CPU_NONE, + /* * Reserve 6 bits off of cwq pointer w/ debugobjects turned * off. This makes cwqs aligned to 64 bytes which isn't too @@ -60,7 +64,7 @@ enum { WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, - WORK_STRUCT_NO_CPU = NR_CPUS << WORK_STRUCT_FLAG_BITS, + WORK_STRUCT_NO_CPU = WORK_CPU_NONE << WORK_STRUCT_FLAG_BITS, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, @@ -227,9 +231,9 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) enum { - WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ + WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ - WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ + WQ_FREEZEABLE = 1 << 2, /* freeze during suspend */ WQ_RESCUER = 1 << 3, /* has an rescue worker */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2eb9fbddf5c6..a105ddf55f79 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -190,7 +190,11 @@ struct wq_flusher { */ struct workqueue_struct { unsigned int flags; /* I: WQ_* flags */ - struct cpu_workqueue_struct *cpu_wq; /* I: cwq's */ + union { + struct cpu_workqueue_struct __percpu *pcpu; + struct cpu_workqueue_struct *single; + unsigned long v; + } cpu_wq; /* I: cwq's */ struct list_head list; /* W: list of all workqueues */ struct mutex flush_mutex; /* protects wq flushing */ @@ -362,7 +366,11 @@ static atomic_t *get_gcwq_nr_running(unsigned int cpu) static struct cpu_workqueue_struct *get_cwq(unsigned int cpu, struct workqueue_struct *wq) { - return per_cpu_ptr(wq->cpu_wq, cpu); +#ifndef CONFIG_SMP + return wq->cpu_wq.single; +#else + return per_cpu_ptr(wq->cpu_wq.pcpu, cpu); +#endif } static unsigned int work_color_to_flags(int color) @@ -442,7 +450,7 @@ static struct global_cwq *get_work_gcwq(struct work_struct *work) return ((struct cpu_workqueue_struct *)data)->gcwq; cpu = data >> WORK_STRUCT_FLAG_BITS; - if (cpu == NR_CPUS) + if (cpu == WORK_CPU_NONE) return NULL; BUG_ON(cpu >= nr_cpu_ids); @@ -846,7 +854,7 @@ static void cwq_unbind_single_cpu(struct cpu_workqueue_struct *cwq) */ if (likely(!(gcwq->flags & GCWQ_FREEZING))) { smp_wmb(); /* paired with cmpxchg() in __queue_work() */ - wq->single_cpu = NR_CPUS; + wq->single_cpu = WORK_CPU_NONE; } } @@ -904,7 +912,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, */ retry: cpu = wq->single_cpu; - arbitrate = cpu == NR_CPUS; + arbitrate = cpu == WORK_CPU_NONE; if (arbitrate) cpu = req_cpu; @@ -918,7 +926,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, * visible on the new cpu after this point. */ if (arbitrate) - cmpxchg(&wq->single_cpu, NR_CPUS, cpu); + cmpxchg(&wq->single_cpu, WORK_CPU_NONE, cpu); if (unlikely(wq->single_cpu != cpu)) { spin_unlock_irqrestore(&gcwq->lock, flags); @@ -2572,7 +2580,7 @@ int keventd_up(void) return system_wq != NULL; } -static struct cpu_workqueue_struct *alloc_cwqs(void) +static int alloc_cwqs(struct workqueue_struct *wq) { /* * cwqs are forced aligned according to WORK_STRUCT_FLAG_BITS. @@ -2582,40 +2590,36 @@ static struct cpu_workqueue_struct *alloc_cwqs(void) const size_t size = sizeof(struct cpu_workqueue_struct); const size_t align = max_t(size_t, 1 << WORK_STRUCT_FLAG_BITS, __alignof__(unsigned long long)); - struct cpu_workqueue_struct *cwqs; #ifndef CONFIG_SMP void *ptr; /* - * On UP, percpu allocator doesn't honor alignment parameter - * and simply uses arch-dependent default. Allocate enough - * room to align cwq and put an extra pointer at the end - * pointing back to the originally allocated pointer which - * will be used for free. - * - * FIXME: This really belongs to UP percpu code. Update UP - * percpu code to honor alignment and remove this ugliness. + * Allocate enough room to align cwq and put an extra pointer + * at the end pointing back to the originally allocated + * pointer which will be used for free. */ - ptr = __alloc_percpu(size + align + sizeof(void *), 1); - cwqs = PTR_ALIGN(ptr, align); - *(void **)per_cpu_ptr(cwqs + 1, 0) = ptr; + ptr = kzalloc(size + align + sizeof(void *), GFP_KERNEL); + if (ptr) { + wq->cpu_wq.single = PTR_ALIGN(ptr, align); + *(void **)(wq->cpu_wq.single + 1) = ptr; + } #else - /* On SMP, percpu allocator can do it itself */ - cwqs = __alloc_percpu(size, align); + /* On SMP, percpu allocator can align itself */ + wq->cpu_wq.pcpu = __alloc_percpu(size, align); #endif /* just in case, make sure it's actually aligned */ - BUG_ON(!IS_ALIGNED((unsigned long)cwqs, align)); - return cwqs; + BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align)); + return wq->cpu_wq.v ? 0 : -ENOMEM; } -static void free_cwqs(struct cpu_workqueue_struct *cwqs) +static void free_cwqs(struct workqueue_struct *wq) { #ifndef CONFIG_SMP /* on UP, the pointer to free is stored right after the cwq */ - if (cwqs) - free_percpu(*(void **)per_cpu_ptr(cwqs + 1, 0)); + if (wq->cpu_wq.single) + kfree(*(void **)(wq->cpu_wq.single + 1)); #else - free_percpu(cwqs); + free_percpu(wq->cpu_wq.pcpu); #endif } @@ -2645,22 +2649,21 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, if (!wq) goto err; - wq->cpu_wq = alloc_cwqs(); - if (!wq->cpu_wq) - goto err; - wq->flags = flags; wq->saved_max_active = max_active; mutex_init(&wq->flush_mutex); atomic_set(&wq->nr_cwqs_to_flush, 0); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); - wq->single_cpu = NR_CPUS; + wq->single_cpu = WORK_CPU_NONE; wq->name = name; lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); INIT_LIST_HEAD(&wq->list); + if (alloc_cwqs(wq) < 0) + goto err; + for_each_possible_cpu(cpu) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); struct global_cwq *gcwq = get_gcwq(cpu); @@ -2710,7 +2713,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, return wq; err: if (wq) { - free_cwqs(wq->cpu_wq); + free_cwqs(wq); free_cpumask_var(wq->mayday_mask); kfree(wq->rescuer); kfree(wq); @@ -2755,7 +2758,7 @@ void destroy_workqueue(struct workqueue_struct *wq) free_cpumask_var(wq->mayday_mask); } - free_cwqs(wq->cpu_wq); + free_cwqs(wq); kfree(wq); } EXPORT_SYMBOL_GPL(destroy_workqueue); @@ -2821,13 +2824,13 @@ EXPORT_SYMBOL_GPL(workqueue_congested); * @work: the work of interest * * RETURNS: - * CPU number if @work was ever queued. NR_CPUS otherwise. + * CPU number if @work was ever queued. WORK_CPU_NONE otherwise. */ unsigned int work_cpu(struct work_struct *work) { struct global_cwq *gcwq = get_work_gcwq(work); - return gcwq ? gcwq->cpu : NR_CPUS; + return gcwq ? gcwq->cpu : WORK_CPU_NONE; } EXPORT_SYMBOL_GPL(work_cpu); @@ -3300,7 +3303,6 @@ EXPORT_SYMBOL_GPL(work_on_cpu); */ void freeze_workqueues_begin(void) { - struct workqueue_struct *wq; unsigned int cpu; spin_lock(&workqueue_lock); @@ -3310,6 +3312,7 @@ void freeze_workqueues_begin(void) for_each_possible_cpu(cpu) { struct global_cwq *gcwq = get_gcwq(cpu); + struct workqueue_struct *wq; spin_lock_irq(&gcwq->lock); @@ -3344,7 +3347,6 @@ void freeze_workqueues_begin(void) */ bool freeze_workqueues_busy(void) { - struct workqueue_struct *wq; unsigned int cpu; bool busy = false; @@ -3353,6 +3355,7 @@ bool freeze_workqueues_busy(void) BUG_ON(!workqueue_freezing); for_each_possible_cpu(cpu) { + struct workqueue_struct *wq; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. @@ -3386,7 +3389,6 @@ out_unlock: */ void thaw_workqueues(void) { - struct workqueue_struct *wq; unsigned int cpu; spin_lock(&workqueue_lock); @@ -3396,6 +3398,7 @@ void thaw_workqueues(void) for_each_possible_cpu(cpu) { struct global_cwq *gcwq = get_gcwq(cpu); + struct workqueue_struct *wq; spin_lock_irq(&gcwq->lock); @@ -3443,7 +3446,7 @@ void __init init_workqueues(void) * sure cpu number won't overflow into kernel pointer area so * that they can be distinguished. */ - BUILD_BUG_ON(NR_CPUS << WORK_STRUCT_FLAG_BITS >= PAGE_OFFSET); + BUILD_BUG_ON(WORK_CPU_LAST << WORK_STRUCT_FLAG_BITS >= PAGE_OFFSET); hotcpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE); -- cgit From f34217977d717385a3e9fd7018ac39fade3964c0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 2 Jul 2010 10:03:51 +0200 Subject: workqueue: implement unbound workqueue This patch implements unbound workqueue which can be specified with WQ_UNBOUND flag on creation. An unbound workqueue has the following properties. * It uses a dedicated gcwq with a pseudo CPU number WORK_CPU_UNBOUND. This gcwq is always online and disassociated. * Workers are not bound to any CPU and not concurrency managed. Works are dispatched to workers as soon as possible and the only applied limitation is @max_active. IOW, all unbound workqeueues are implicitly high priority. Unbound workqueues can be used as simple execution context provider. Contexts unbound to any cpu are served as soon as possible. Signed-off-by: Tejun Heo Cc: Arjan van de Ven Cc: David Howells --- include/linux/workqueue.h | 15 +++- kernel/workqueue.c | 218 +++++++++++++++++++++++++++++++++------------- 2 files changed, 173 insertions(+), 60 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 139069a6286c..67ce734747f6 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -51,7 +51,8 @@ enum { WORK_NO_COLOR = WORK_NR_COLORS, /* special cpu IDs */ - WORK_CPU_NONE = NR_CPUS, + WORK_CPU_UNBOUND = NR_CPUS, + WORK_CPU_NONE = NR_CPUS + 1, WORK_CPU_LAST = WORK_CPU_NONE, /* @@ -237,11 +238,17 @@ enum { WQ_RESCUER = 1 << 3, /* has an rescue worker */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ + WQ_UNBOUND = 1 << 6, /* not bound to any cpu */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ + WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, }; +/* unbound wq's aren't per-cpu, scale max_active according to #cpus */ +#define WQ_UNBOUND_MAX_ACTIVE \ + max_t(int, WQ_MAX_ACTIVE, num_possible_cpus() * WQ_MAX_UNBOUND_PER_CPU) + /* * System-wide workqueues which are always present. * @@ -256,10 +263,16 @@ enum { * system_nrt_wq is non-reentrant and guarantees that any given work * item is never executed in parallel by multiple CPUs. Queue * flushing might take relatively long. + * + * system_unbound_wq is unbound workqueue. Workers are not bound to + * any specific CPU, not concurrency managed, and all queued works are + * executed immediately as long as max_active limit is not reached and + * resources are available. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_nrt_wq; +extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct * __alloc_workqueue_key(const char *name, unsigned int flags, int max_active, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index a105ddf55f79..4608563cdd63 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -53,9 +53,10 @@ enum { WORKER_ROGUE = 1 << 4, /* not bound to any cpu */ WORKER_REBIND = 1 << 5, /* mom is home, come back */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ + WORKER_UNBOUND = 1 << 7, /* worker is unbound */ WORKER_NOT_RUNNING = WORKER_PREP | WORKER_ROGUE | WORKER_REBIND | - WORKER_CPU_INTENSIVE, + WORKER_CPU_INTENSIVE | WORKER_UNBOUND, /* gcwq->trustee_state */ TRUSTEE_START = 0, /* start */ @@ -96,7 +97,7 @@ enum { * X: During normal operation, modification requires gcwq->lock and * should be done only from local cpu. Either disabling preemption * on local cpu or grabbing gcwq->lock is enough for read access. - * While trustee is in charge, it's identical to L. + * If GCWQ_DISASSOCIATED is set, it's identical to L. * * F: wq->flush_mutex protected. * @@ -220,14 +221,52 @@ struct workqueue_struct { struct workqueue_struct *system_wq __read_mostly; struct workqueue_struct *system_long_wq __read_mostly; struct workqueue_struct *system_nrt_wq __read_mostly; +struct workqueue_struct *system_unbound_wq __read_mostly; EXPORT_SYMBOL_GPL(system_wq); EXPORT_SYMBOL_GPL(system_long_wq); EXPORT_SYMBOL_GPL(system_nrt_wq); +EXPORT_SYMBOL_GPL(system_unbound_wq); #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) +static inline int __next_gcwq_cpu(int cpu, const struct cpumask *mask, + unsigned int sw) +{ + if (cpu < nr_cpu_ids) { + if (sw & 1) { + cpu = cpumask_next(cpu, mask); + if (cpu < nr_cpu_ids) + return cpu; + } + if (sw & 2) + return WORK_CPU_UNBOUND; + } + return WORK_CPU_NONE; +} + +static inline int __next_wq_cpu(int cpu, const struct cpumask *mask, + struct workqueue_struct *wq) +{ + return __next_gcwq_cpu(cpu, mask, !(wq->flags & WQ_UNBOUND) ? 1 : 2); +} + +#define for_each_gcwq_cpu(cpu) \ + for ((cpu) = __next_gcwq_cpu(-1, cpu_possible_mask, 3); \ + (cpu) < WORK_CPU_NONE; \ + (cpu) = __next_gcwq_cpu((cpu), cpu_possible_mask, 3)) + +#define for_each_online_gcwq_cpu(cpu) \ + for ((cpu) = __next_gcwq_cpu(-1, cpu_online_mask, 3); \ + (cpu) < WORK_CPU_NONE; \ + (cpu) = __next_gcwq_cpu((cpu), cpu_online_mask, 3)) + +#define for_each_cwq_cpu(cpu, wq) \ + for ((cpu) = __next_wq_cpu(-1, cpu_possible_mask, (wq)); \ + (cpu) < WORK_CPU_NONE; \ + (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq))) + #ifdef CONFIG_DEBUG_OBJECTS_WORK static struct debug_obj_descr work_debug_descr; @@ -351,26 +390,46 @@ static bool workqueue_freezing; /* W: have wqs started freezing? */ static DEFINE_PER_CPU(struct global_cwq, global_cwq); static DEFINE_PER_CPU_SHARED_ALIGNED(atomic_t, gcwq_nr_running); +/* + * Global cpu workqueue and nr_running counter for unbound gcwq. The + * gcwq is always online, has GCWQ_DISASSOCIATED set, and all its + * workers have WORKER_UNBOUND set. + */ +static struct global_cwq unbound_global_cwq; +static atomic_t unbound_gcwq_nr_running = ATOMIC_INIT(0); /* always 0 */ + static int worker_thread(void *__worker); static struct global_cwq *get_gcwq(unsigned int cpu) { - return &per_cpu(global_cwq, cpu); + if (cpu != WORK_CPU_UNBOUND) + return &per_cpu(global_cwq, cpu); + else + return &unbound_global_cwq; } static atomic_t *get_gcwq_nr_running(unsigned int cpu) { - return &per_cpu(gcwq_nr_running, cpu); + if (cpu != WORK_CPU_UNBOUND) + return &per_cpu(gcwq_nr_running, cpu); + else + return &unbound_gcwq_nr_running; } static struct cpu_workqueue_struct *get_cwq(unsigned int cpu, struct workqueue_struct *wq) { -#ifndef CONFIG_SMP - return wq->cpu_wq.single; + if (!(wq->flags & WQ_UNBOUND)) { + if (likely(cpu < nr_cpu_ids)) { +#ifdef CONFIG_SMP + return per_cpu_ptr(wq->cpu_wq.pcpu, cpu); #else - return per_cpu_ptr(wq->cpu_wq.pcpu, cpu); + return wq->cpu_wq.single; #endif + } + } else if (likely(cpu == WORK_CPU_UNBOUND)) + return wq->cpu_wq.single; + return NULL; } static unsigned int work_color_to_flags(int color) @@ -453,7 +512,7 @@ static struct global_cwq *get_work_gcwq(struct work_struct *work) if (cpu == WORK_CPU_NONE) return NULL; - BUG_ON(cpu >= nr_cpu_ids); + BUG_ON(cpu >= nr_cpu_ids && cpu != WORK_CPU_UNBOUND); return get_gcwq(cpu); } @@ -869,11 +928,14 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, debug_work_activate(work); + if (unlikely(cpu == WORK_CPU_UNBOUND)) + cpu = raw_smp_processor_id(); + /* * Determine gcwq to use. SINGLE_CPU is inherently * NON_REENTRANT, so test it first. */ - if (!(wq->flags & WQ_SINGLE_CPU)) { + if (!(wq->flags & (WQ_SINGLE_CPU | WQ_UNBOUND))) { struct global_cwq *last_gcwq; /* @@ -900,7 +962,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, } } else spin_lock_irqsave(&gcwq->lock, flags); - } else { + } else if (!(wq->flags & WQ_UNBOUND)) { unsigned int req_cpu = cpu; /* @@ -932,6 +994,9 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, spin_unlock_irqrestore(&gcwq->lock, flags); goto retry; } + } else { + gcwq = get_gcwq(WORK_CPU_UNBOUND); + spin_lock_irqsave(&gcwq->lock, flags); } /* gcwq determined, get cwq and queue */ @@ -1166,7 +1231,8 @@ static bool worker_maybe_bind_and_lock(struct worker *worker) * it races with cpu hotunplug operation. Verify * against GCWQ_DISASSOCIATED. */ - set_cpus_allowed_ptr(task, get_cpu_mask(gcwq->cpu)); + if (!(gcwq->flags & GCWQ_DISASSOCIATED)) + set_cpus_allowed_ptr(task, get_cpu_mask(gcwq->cpu)); spin_lock_irq(&gcwq->lock); if (gcwq->flags & GCWQ_DISASSOCIATED) @@ -1231,8 +1297,9 @@ static struct worker *alloc_worker(void) */ static struct worker *create_worker(struct global_cwq *gcwq, bool bind) { - int id = -1; + bool on_unbound_cpu = gcwq->cpu == WORK_CPU_UNBOUND; struct worker *worker = NULL; + int id = -1; spin_lock_irq(&gcwq->lock); while (ida_get_new(&gcwq->worker_ida, &id)) { @@ -1250,8 +1317,12 @@ static struct worker *create_worker(struct global_cwq *gcwq, bool bind) worker->gcwq = gcwq; worker->id = id; - worker->task = kthread_create(worker_thread, worker, "kworker/%u:%d", - gcwq->cpu, id); + if (!on_unbound_cpu) + worker->task = kthread_create(worker_thread, worker, + "kworker/%u:%d", gcwq->cpu, id); + else + worker->task = kthread_create(worker_thread, worker, + "kworker/u:%d", id); if (IS_ERR(worker->task)) goto fail; @@ -1260,10 +1331,13 @@ static struct worker *create_worker(struct global_cwq *gcwq, bool bind) * online later on. Make sure every worker has * PF_THREAD_BOUND set. */ - if (bind) + if (bind && !on_unbound_cpu) kthread_bind(worker->task, gcwq->cpu); - else + else { worker->task->flags |= PF_THREAD_BOUND; + if (on_unbound_cpu) + worker->flags |= WORKER_UNBOUND; + } return worker; fail: @@ -1358,12 +1432,17 @@ static bool send_mayday(struct work_struct *work) { struct cpu_workqueue_struct *cwq = get_work_cwq(work); struct workqueue_struct *wq = cwq->wq; + unsigned int cpu; if (!(wq->flags & WQ_RESCUER)) return false; /* mayday mayday mayday */ - if (!cpumask_test_and_set_cpu(cwq->gcwq->cpu, wq->mayday_mask)) + cpu = cwq->gcwq->cpu; + /* WORK_CPU_UNBOUND can't be set in cpumask, use cpu 0 instead */ + if (cpu == WORK_CPU_UNBOUND) + cpu = 0; + if (!cpumask_test_and_set_cpu(cpu, wq->mayday_mask)) wake_up_process(wq->rescuer->task); return true; } @@ -1882,6 +1961,7 @@ static int rescuer_thread(void *__wq) struct workqueue_struct *wq = __wq; struct worker *rescuer = wq->rescuer; struct list_head *scheduled = &rescuer->scheduled; + bool is_unbound = wq->flags & WQ_UNBOUND; unsigned int cpu; set_user_nice(current, RESCUER_NICE_LEVEL); @@ -1891,8 +1971,13 @@ repeat: if (kthread_should_stop()) return 0; + /* + * See whether any cpu is asking for help. Unbounded + * workqueues use cpu 0 in mayday_mask for CPU_UNBOUND. + */ for_each_cpu(cpu, wq->mayday_mask) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + unsigned int tcpu = is_unbound ? WORK_CPU_UNBOUND : cpu; + struct cpu_workqueue_struct *cwq = get_cwq(tcpu, wq); struct global_cwq *gcwq = cwq->gcwq; struct work_struct *work, *n; @@ -2034,7 +2119,7 @@ static bool flush_workqueue_prep_cwqs(struct workqueue_struct *wq, atomic_set(&wq->nr_cwqs_to_flush, 1); } - for_each_possible_cpu(cpu) { + for_each_cwq_cpu(cpu, wq) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); struct global_cwq *gcwq = cwq->gcwq; @@ -2344,7 +2429,7 @@ static void wait_on_work(struct work_struct *work) lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); - for_each_possible_cpu(cpu) + for_each_gcwq_cpu(cpu) wait_on_cpu_work(get_gcwq(cpu), work); } @@ -2590,23 +2675,25 @@ static int alloc_cwqs(struct workqueue_struct *wq) const size_t size = sizeof(struct cpu_workqueue_struct); const size_t align = max_t(size_t, 1 << WORK_STRUCT_FLAG_BITS, __alignof__(unsigned long long)); -#ifndef CONFIG_SMP - void *ptr; - /* - * Allocate enough room to align cwq and put an extra pointer - * at the end pointing back to the originally allocated - * pointer which will be used for free. - */ - ptr = kzalloc(size + align + sizeof(void *), GFP_KERNEL); - if (ptr) { - wq->cpu_wq.single = PTR_ALIGN(ptr, align); - *(void **)(wq->cpu_wq.single + 1) = ptr; + if (CONFIG_SMP && !(wq->flags & WQ_UNBOUND)) { + /* on SMP, percpu allocator can align itself */ + wq->cpu_wq.pcpu = __alloc_percpu(size, align); + } else { + void *ptr; + + /* + * Allocate enough room to align cwq and put an extra + * pointer at the end pointing back to the originally + * allocated pointer which will be used for free. + */ + ptr = kzalloc(size + align + sizeof(void *), GFP_KERNEL); + if (ptr) { + wq->cpu_wq.single = PTR_ALIGN(ptr, align); + *(void **)(wq->cpu_wq.single + 1) = ptr; + } } -#else - /* On SMP, percpu allocator can align itself */ - wq->cpu_wq.pcpu = __alloc_percpu(size, align); -#endif + /* just in case, make sure it's actually aligned */ BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align)); return wq->cpu_wq.v ? 0 : -ENOMEM; @@ -2614,23 +2701,25 @@ static int alloc_cwqs(struct workqueue_struct *wq) static void free_cwqs(struct workqueue_struct *wq) { -#ifndef CONFIG_SMP - /* on UP, the pointer to free is stored right after the cwq */ - if (wq->cpu_wq.single) + if (CONFIG_SMP && !(wq->flags & WQ_UNBOUND)) + free_percpu(wq->cpu_wq.pcpu); + else if (wq->cpu_wq.single) { + /* the pointer to free is stored right after the cwq */ kfree(*(void **)(wq->cpu_wq.single + 1)); -#else - free_percpu(wq->cpu_wq.pcpu); -#endif + } } -static int wq_clamp_max_active(int max_active, const char *name) +static int wq_clamp_max_active(int max_active, unsigned int flags, + const char *name) { - if (max_active < 1 || max_active > WQ_MAX_ACTIVE) + int lim = flags & WQ_UNBOUND ? WQ_UNBOUND_MAX_ACTIVE : WQ_MAX_ACTIVE; + + if (max_active < 1 || max_active > lim) printk(KERN_WARNING "workqueue: max_active %d requested for %s " "is out of range, clamping between %d and %d\n", - max_active, name, 1, WQ_MAX_ACTIVE); + max_active, name, 1, lim); - return clamp_val(max_active, 1, WQ_MAX_ACTIVE); + return clamp_val(max_active, 1, lim); } struct workqueue_struct *__alloc_workqueue_key(const char *name, @@ -2642,8 +2731,15 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, struct workqueue_struct *wq; unsigned int cpu; + /* + * Unbound workqueues aren't concurrency managed and should be + * dispatched to workers immediately. + */ + if (flags & WQ_UNBOUND) + flags |= WQ_HIGHPRI; + max_active = max_active ?: WQ_DFL_ACTIVE; - max_active = wq_clamp_max_active(max_active, name); + max_active = wq_clamp_max_active(max_active, flags, name); wq = kzalloc(sizeof(*wq), GFP_KERNEL); if (!wq) @@ -2664,7 +2760,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, if (alloc_cwqs(wq) < 0) goto err; - for_each_possible_cpu(cpu) { + for_each_cwq_cpu(cpu, wq) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); struct global_cwq *gcwq = get_gcwq(cpu); @@ -2703,7 +2799,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, spin_lock(&workqueue_lock); if (workqueue_freezing && wq->flags & WQ_FREEZEABLE) - for_each_possible_cpu(cpu) + for_each_cwq_cpu(cpu, wq) get_cwq(cpu, wq)->max_active = 0; list_add(&wq->list, &workqueues); @@ -2743,7 +2839,7 @@ void destroy_workqueue(struct workqueue_struct *wq) spin_unlock(&workqueue_lock); /* sanity check */ - for_each_possible_cpu(cpu) { + for_each_cwq_cpu(cpu, wq) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); int i; @@ -2777,13 +2873,13 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { unsigned int cpu; - max_active = wq_clamp_max_active(max_active, wq->name); + max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); spin_lock(&workqueue_lock); wq->saved_max_active = max_active; - for_each_possible_cpu(cpu) { + for_each_cwq_cpu(cpu, wq) { struct global_cwq *gcwq = get_gcwq(cpu); spin_lock_irq(&gcwq->lock); @@ -3310,7 +3406,7 @@ void freeze_workqueues_begin(void) BUG_ON(workqueue_freezing); workqueue_freezing = true; - for_each_possible_cpu(cpu) { + for_each_gcwq_cpu(cpu) { struct global_cwq *gcwq = get_gcwq(cpu); struct workqueue_struct *wq; @@ -3322,7 +3418,7 @@ void freeze_workqueues_begin(void) list_for_each_entry(wq, &workqueues, list) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - if (wq->flags & WQ_FREEZEABLE) + if (cwq && wq->flags & WQ_FREEZEABLE) cwq->max_active = 0; } @@ -3354,7 +3450,7 @@ bool freeze_workqueues_busy(void) BUG_ON(!workqueue_freezing); - for_each_possible_cpu(cpu) { + for_each_gcwq_cpu(cpu) { struct workqueue_struct *wq; /* * nr_active is monotonically decreasing. It's safe @@ -3363,7 +3459,7 @@ bool freeze_workqueues_busy(void) list_for_each_entry(wq, &workqueues, list) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - if (!(wq->flags & WQ_FREEZEABLE)) + if (!cwq || !(wq->flags & WQ_FREEZEABLE)) continue; BUG_ON(cwq->nr_active < 0); @@ -3396,7 +3492,7 @@ void thaw_workqueues(void) if (!workqueue_freezing) goto out_unlock; - for_each_possible_cpu(cpu) { + for_each_gcwq_cpu(cpu) { struct global_cwq *gcwq = get_gcwq(cpu); struct workqueue_struct *wq; @@ -3408,7 +3504,7 @@ void thaw_workqueues(void) list_for_each_entry(wq, &workqueues, list) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - if (!(wq->flags & WQ_FREEZEABLE)) + if (!cwq || !(wq->flags & WQ_FREEZEABLE)) continue; /* restore max_active and repopulate worklist */ @@ -3451,12 +3547,14 @@ void __init init_workqueues(void) hotcpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE); /* initialize gcwqs */ - for_each_possible_cpu(cpu) { + for_each_gcwq_cpu(cpu) { struct global_cwq *gcwq = get_gcwq(cpu); spin_lock_init(&gcwq->lock); INIT_LIST_HEAD(&gcwq->worklist); gcwq->cpu = cpu; + if (cpu == WORK_CPU_UNBOUND) + gcwq->flags |= GCWQ_DISASSOCIATED; INIT_LIST_HEAD(&gcwq->idle_list); for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) @@ -3476,7 +3574,7 @@ void __init init_workqueues(void) } /* create the initial worker */ - for_each_online_cpu(cpu) { + for_each_online_gcwq_cpu(cpu) { struct global_cwq *gcwq = get_gcwq(cpu); struct worker *worker; @@ -3490,5 +3588,7 @@ void __init init_workqueues(void) system_wq = alloc_workqueue("events", 0, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); system_nrt_wq = alloc_workqueue("events_nrt", WQ_NON_REENTRANT, 0); + system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, + WQ_UNBOUND_MAX_ACTIVE); BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq); } -- cgit From c7fc77f78f16d138ca997ce096a62f46e2e9420a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 2 Jul 2010 10:03:51 +0200 Subject: workqueue: remove WQ_SINGLE_CPU and use WQ_UNBOUND instead WQ_SINGLE_CPU combined with @max_active of 1 is used to achieve full ordering among works queued to a workqueue. The same can be achieved using WQ_UNBOUND as unbound workqueues always use the gcwq for WORK_CPU_UNBOUND. As @max_active is always one and benefits from cpu locality isn't accessible anyway, serving them with unbound workqueues should be fine. Drop WQ_SINGLE_CPU support and use WQ_UNBOUND instead. Note that most single thread workqueue users will be converted to use multithread or non-reentrant instead and only the ones which require strict ordering will keep using WQ_UNBOUND + @max_active of 1. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 7 ++-- kernel/workqueue.c | 100 +++++++++------------------------------------- 2 files changed, 21 insertions(+), 86 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 67ce734747f6..d74a529ed13e 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -233,12 +233,11 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } enum { WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ - WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ + 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_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ - WQ_UNBOUND = 1 << 6, /* not bound to any cpu */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ @@ -300,9 +299,9 @@ __alloc_workqueue_key(const char *name, unsigned int flags, int max_active, #define create_workqueue(name) \ alloc_workqueue((name), WQ_RESCUER, 1) #define create_freezeable_workqueue(name) \ - alloc_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_CPU | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_RESCUER, 1) #define create_singlethread_workqueue(name) \ - alloc_workqueue((name), WQ_SINGLE_CPU | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_UNBOUND | WQ_RESCUER, 1) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4608563cdd63..20d6237d7498 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -206,8 +206,6 @@ struct workqueue_struct { struct list_head flusher_queue; /* F: flush waiters */ struct list_head flusher_overflow; /* F: flush overflow list */ - unsigned long single_cpu; /* cpu for single cpu wq */ - cpumask_var_t mayday_mask; /* cpus requesting rescue */ struct worker *rescuer; /* I: rescue worker */ @@ -889,34 +887,6 @@ static void insert_work(struct cpu_workqueue_struct *cwq, wake_up_worker(gcwq); } -/** - * cwq_unbind_single_cpu - unbind cwq from single cpu workqueue processing - * @cwq: cwq to unbind - * - * Try to unbind @cwq from single cpu workqueue processing. If - * @cwq->wq is frozen, unbind is delayed till the workqueue is thawed. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock). - */ -static void cwq_unbind_single_cpu(struct cpu_workqueue_struct *cwq) -{ - struct workqueue_struct *wq = cwq->wq; - struct global_cwq *gcwq = cwq->gcwq; - - BUG_ON(wq->single_cpu != gcwq->cpu); - /* - * Unbind from workqueue if @cwq is not frozen. If frozen, - * thaw_workqueues() will either restart processing on this - * cpu or unbind if empty. This keeps works queued while - * frozen fully ordered and flushable. - */ - if (likely(!(gcwq->flags & GCWQ_FREEZING))) { - smp_wmb(); /* paired with cmpxchg() in __queue_work() */ - wq->single_cpu = WORK_CPU_NONE; - } -} - static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, struct work_struct *work) { @@ -924,20 +894,16 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, struct cpu_workqueue_struct *cwq; struct list_head *worklist; unsigned long flags; - bool arbitrate; debug_work_activate(work); - if (unlikely(cpu == WORK_CPU_UNBOUND)) - cpu = raw_smp_processor_id(); - - /* - * Determine gcwq to use. SINGLE_CPU is inherently - * NON_REENTRANT, so test it first. - */ - if (!(wq->flags & (WQ_SINGLE_CPU | WQ_UNBOUND))) { + /* determine gcwq to use */ + if (!(wq->flags & WQ_UNBOUND)) { struct global_cwq *last_gcwq; + if (unlikely(cpu == WORK_CPU_UNBOUND)) + cpu = raw_smp_processor_id(); + /* * It's multi cpu. If @wq is non-reentrant and @work * was previously on a different cpu, it might still @@ -962,38 +928,6 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, } } else spin_lock_irqsave(&gcwq->lock, flags); - } else if (!(wq->flags & WQ_UNBOUND)) { - unsigned int req_cpu = cpu; - - /* - * It's a bit more complex for single cpu workqueues. - * We first need to determine which cpu is going to be - * used. If no cpu is currently serving this - * workqueue, arbitrate using atomic accesses to - * wq->single_cpu; otherwise, use the current one. - */ - retry: - cpu = wq->single_cpu; - arbitrate = cpu == WORK_CPU_NONE; - if (arbitrate) - cpu = req_cpu; - - gcwq = get_gcwq(cpu); - spin_lock_irqsave(&gcwq->lock, flags); - - /* - * The following cmpxchg() is a full barrier paired - * with smp_wmb() in cwq_unbind_single_cpu() and - * guarantees that all changes to wq->st_* fields are - * visible on the new cpu after this point. - */ - if (arbitrate) - cmpxchg(&wq->single_cpu, WORK_CPU_NONE, cpu); - - if (unlikely(wq->single_cpu != cpu)) { - spin_unlock_irqrestore(&gcwq->lock, flags); - goto retry; - } } else { gcwq = get_gcwq(WORK_CPU_UNBOUND); spin_lock_irqsave(&gcwq->lock, flags); @@ -1105,19 +1039,30 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work = &dwork->work; if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { - struct global_cwq *gcwq = get_work_gcwq(work); - unsigned int lcpu = gcwq ? gcwq->cpu : raw_smp_processor_id(); + unsigned int lcpu; BUG_ON(timer_pending(timer)); BUG_ON(!list_empty(&work->entry)); timer_stats_timer_set_start_info(&dwork->timer); + /* * This stores cwq for the moment, for the timer_fn. * Note that the work's gcwq is preserved to allow * reentrance detection for delayed works. */ + if (!(wq->flags & WQ_UNBOUND)) { + struct global_cwq *gcwq = get_work_gcwq(work); + + if (gcwq && gcwq->cpu != WORK_CPU_UNBOUND) + lcpu = gcwq->cpu; + else + lcpu = raw_smp_processor_id(); + } else + lcpu = WORK_CPU_UNBOUND; + set_work_cwq(work, get_cwq(lcpu, wq), 0); + timer->expires = jiffies + delay; timer->data = (unsigned long)dwork; timer->function = delayed_work_timer_fn; @@ -1696,9 +1641,6 @@ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) /* one down, submit a delayed one */ if (cwq->nr_active < cwq->max_active) cwq_activate_first_delayed(cwq); - } else if (!cwq->nr_active && cwq->wq->flags & WQ_SINGLE_CPU) { - /* this was the last work, unbind from single cpu */ - cwq_unbind_single_cpu(cwq); } /* is flush in progress and are we at the flushing tip? */ @@ -2751,7 +2693,6 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, atomic_set(&wq->nr_cwqs_to_flush, 0); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); - wq->single_cpu = WORK_CPU_NONE; wq->name = name; lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); @@ -3513,11 +3454,6 @@ void thaw_workqueues(void) while (!list_empty(&cwq->delayed_works) && cwq->nr_active < cwq->max_active) cwq_activate_first_delayed(cwq); - - /* perform delayed unbind from single cpu if empty */ - if (wq->single_cpu == gcwq->cpu && - !cwq->nr_active && list_empty(&cwq->delayed_works)) - cwq_unbind_single_cpu(cwq); } wake_up_worker(gcwq); -- cgit From e120153ddf8620fd0a194d301e9c5a8b28483bb5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 22 Jul 2010 14:14:25 +0200 Subject: workqueue: fix how cpu number is stored in work->data Once a work starts execution, its data contains the cpu number it was on instead of pointing to cwq. This is added by commit 7a22ad75 (workqueue: carry cpu number in work data once execution starts) to reliably determine the work was last on even if the workqueue itself was destroyed inbetween. Whether data points to a cwq or contains a cpu number was distinguished by comparing the value against PAGE_OFFSET. The assumption was that a cpu number should be below PAGE_OFFSET while a pointer to cwq should be above it. However, on architectures which use separate address spaces for user and kernel spaces, this doesn't hold as PAGE_OFFSET is zero. Fix it by using an explicit flag, WORK_STRUCT_CWQ, to mark what the data field contains. If the flag is set, it's pointing to a cwq; otherwise, it contains a cpu number. Reported on s390 and microblaze during linux-next testing. Signed-off-by: Tejun Heo Reported-by: Sachin Sant Reported-by: Michal Simek Reported-by: Martin Schwidefsky Tested-by: Martin Schwidefsky Tested-by: Michal Simek --- include/linux/workqueue.h | 14 ++++++++------ kernel/workqueue.c | 36 +++++++++++++----------------------- 2 files changed, 21 insertions(+), 29 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index d74a529ed13e..5f76001c4e6d 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -25,17 +25,19 @@ typedef void (*work_func_t)(struct work_struct *work); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ - WORK_STRUCT_LINKED_BIT = 1, /* next work is linked to this one */ + WORK_STRUCT_CWQ_BIT = 1, /* data points to cwq */ + WORK_STRUCT_LINKED_BIT = 2, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK - WORK_STRUCT_STATIC_BIT = 2, /* static initializer (debugobjects) */ - WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ + WORK_STRUCT_STATIC_BIT = 3, /* static initializer (debugobjects) */ + WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ #else - WORK_STRUCT_COLOR_SHIFT = 2, /* color for workqueue flushing */ + WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ #endif WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, + WORK_STRUCT_CWQ = 1 << WORK_STRUCT_CWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, @@ -56,8 +58,8 @@ enum { WORK_CPU_LAST = WORK_CPU_NONE, /* - * Reserve 6 bits off of cwq pointer w/ debugobjects turned - * off. This makes cwqs aligned to 64 bytes which isn't too + * Reserve 7 bits off of cwq pointer w/ debugobjects turned + * off. This makes cwqs aligned to 128 bytes which isn't too * excessive while allowing 15 workqueue flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c11edc9c9365..e5cb7faac58e 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -468,10 +468,9 @@ static int work_next_color(int color) } /* - * Work data points to the cwq while a work is on queue. Once - * execution starts, it points to the cpu the work was last on. This - * can be distinguished by comparing the data value against - * PAGE_OFFSET. + * A work's data points to the cwq with WORK_STRUCT_CWQ set while the + * work is on queue. Once execution starts, WORK_STRUCT_CWQ is + * cleared and the work data contains the cpu number it was last on. * * set_work_{cwq|cpu}() and clear_work_data() can be used to set the * cwq, cpu or clear work->data. These functions should only be @@ -494,7 +493,7 @@ static void set_work_cwq(struct work_struct *work, unsigned long extra_flags) { set_work_data(work, (unsigned long)cwq, - WORK_STRUCT_PENDING | extra_flags); + WORK_STRUCT_PENDING | WORK_STRUCT_CWQ | extra_flags); } static void set_work_cpu(struct work_struct *work, unsigned int cpu) @@ -507,25 +506,24 @@ static void clear_work_data(struct work_struct *work) set_work_data(work, WORK_STRUCT_NO_CPU, 0); } -static inline unsigned long get_work_data(struct work_struct *work) -{ - return atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK; -} - static struct cpu_workqueue_struct *get_work_cwq(struct work_struct *work) { - unsigned long data = get_work_data(work); + unsigned long data = atomic_long_read(&work->data); - return data >= PAGE_OFFSET ? (void *)data : NULL; + if (data & WORK_STRUCT_CWQ) + return (void *)(data & WORK_STRUCT_WQ_DATA_MASK); + else + return NULL; } static struct global_cwq *get_work_gcwq(struct work_struct *work) { - unsigned long data = get_work_data(work); + unsigned long data = atomic_long_read(&work->data); unsigned int cpu; - if (data >= PAGE_OFFSET) - return ((struct cpu_workqueue_struct *)data)->gcwq; + if (data & WORK_STRUCT_CWQ) + return ((struct cpu_workqueue_struct *) + (data & WORK_STRUCT_WQ_DATA_MASK))->gcwq; cpu = data >> WORK_STRUCT_FLAG_BITS; if (cpu == WORK_CPU_NONE) @@ -3501,14 +3499,6 @@ void __init init_workqueues(void) unsigned int cpu; int i; - /* - * The pointer part of work->data is either pointing to the - * cwq or contains the cpu number the work ran last on. Make - * sure cpu number won't overflow into kernel pointer area so - * that they can be distinguished. - */ - BUILD_BUG_ON(WORK_CPU_LAST << WORK_STRUCT_FLAG_BITS >= PAGE_OFFSET); - hotcpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE); /* initialize gcwqs */ -- cgit From 6ee0578b4daaea01c96b172c6aacca43fd9807a6 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Fri, 30 Jul 2010 14:57:37 -0700 Subject: workqueue: mark init_workqueues() as early_initcall() Mark init_workqueues() as early_initcall() and thus it will be initialized before smp bringup. init_workqueues() registers for the hotcpu notifier and thus it should cope with the processors that are brought online after the workqueues are initialized. x86 smp bringup code uses workqueues and uses a workaround for the cold boot process (as the workqueues are initialized post smp_init()). Marking init_workqueues() as early_initcall() will pave the way for cleaning up this code. Signed-off-by: Suresh Siddha Signed-off-by: Tejun Heo Cc: Oleg Nesterov Cc: Andrew Morton --- include/linux/workqueue.h | 1 - init/main.c | 2 -- kernel/workqueue.c | 4 +++- 3 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 5f76001c4e6d..51dc9a727e5e 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -327,7 +327,6 @@ extern int schedule_delayed_work_on(int cpu, struct delayed_work *work, extern int schedule_on_each_cpu(work_func_t func); extern int keventd_up(void); -extern void init_workqueues(void); int execute_in_process_context(work_func_t fn, struct execute_work *); extern int flush_work(struct work_struct *work); diff --git a/init/main.c b/init/main.c index 3bdb152f412f..5f2ec2cdd900 100644 --- a/init/main.c +++ b/init/main.c @@ -32,7 +32,6 @@ #include #include #include -#include #include #include #include @@ -786,7 +785,6 @@ static void __init do_initcalls(void) */ static void __init do_basic_setup(void) { - init_workqueues(); cpuset_init_smp(); usermodehelper_init(); init_tmpfs(); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1105c474073a..e2eb351d9152 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3507,7 +3507,7 @@ out_unlock: } #endif /* CONFIG_FREEZER */ -void __init init_workqueues(void) +static int __init init_workqueues(void) { unsigned int cpu; int i; @@ -3559,4 +3559,6 @@ void __init init_workqueues(void) system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq); + return 0; } +early_initcall(init_workqueues); -- cgit From e41e704bc4f49057fc68b643108366e6e6781aa3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Aug 2010 14:22:47 +0200 Subject: workqueue: improve destroy_workqueue() debuggability Now that the worklist is global, having works pending after wq destruction can easily lead to oops and destroy_workqueue() have several BUG_ON()s to catch these cases. Unfortunately, BUG_ON() doesn't tell much about how the work became pending after the final flush_workqueue(). This patch adds WQ_DYING which is set before the final flush begins. If a work is requested to be queued on a dying workqueue, WARN_ON_ONCE() is triggered and the request is ignored. This clearly indicates which caller is trying to queue a work on a dying workqueue and keeps the system working in most cases. Locking rule comment is updated such that the 'I' rule includes modifying the field from destruction path. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 ++ kernel/workqueue.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4f9d277bcd9a..c959666eafca 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -241,6 +241,8 @@ enum { WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ + WQ_DYING = 1 << 6, /* internal: workqueue is dying */ + WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index cc3456f96c56..362b50d092e2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -87,7 +87,8 @@ enum { /* * Structure fields follow one of the following exclusion rules. * - * I: Set during initialization and read-only afterwards. + * I: Modifiable by initialization/destruction paths and read-only for + * everyone else. * * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. @@ -944,6 +945,9 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, debug_work_activate(work); + if (WARN_ON_ONCE(wq->flags & WQ_DYING)) + return; + /* determine gcwq to use */ if (!(wq->flags & WQ_UNBOUND)) { struct global_cwq *last_gcwq; @@ -2828,6 +2832,7 @@ void destroy_workqueue(struct workqueue_struct *wq) { unsigned int cpu; + wq->flags |= WQ_DYING; flush_workqueue(wq); /* -- cgit From 8a2e8e5dec7e29c56a46ba176c664ab6a3d04118 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 25 Aug 2010 10:33:56 +0200 Subject: workqueue: fix cwq->nr_active underflow cwq->nr_active is used to keep track of how many work items are active for the cpu workqueue, where 'active' is defined as either pending on global worklist or executing. This is used to implement the max_active limit and workqueue freezing. If a work item is queued after nr_active has already reached max_active, the work item doesn't increment nr_active and is put on the delayed queue and gets activated later as previous active work items retire. try_to_grab_pending() which is used in the cancellation path unconditionally decremented nr_active whether the work item being cancelled is currently active or delayed, so cancelling a delayed work item makes nr_active underflow. This breaks max_active enforcement and triggers BUG_ON() in destroy_workqueue() later on. This patch fixes this bug by adding a flag WORK_STRUCT_DELAYED, which is set while a work item in on the delayed list and making try_to_grab_pending() decrement nr_active iff the work item is currently active. The addition of the flag enlarges cwq alignment to 256 bytes which is getting a bit too large. It's scheduled to be reduced back to 128 bytes by merging WORK_STRUCT_PENDING and WORK_STRUCT_CWQ in the next devel cycle. Signed-off-by: Tejun Heo Reported-by: Johannes Berg --- include/linux/workqueue.h | 16 +++++++++------- kernel/workqueue.c | 30 ++++++++++++++++++++---------- 2 files changed, 29 insertions(+), 17 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index c959666eafca..f11100f96482 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -25,18 +25,20 @@ typedef void (*work_func_t)(struct work_struct *work); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ - WORK_STRUCT_CWQ_BIT = 1, /* data points to cwq */ - WORK_STRUCT_LINKED_BIT = 2, /* next work is linked to this one */ + WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */ + WORK_STRUCT_CWQ_BIT = 2, /* data points to cwq */ + WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK - WORK_STRUCT_STATIC_BIT = 3, /* static initializer (debugobjects) */ - WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ + WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */ + WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */ #else - WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ + WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ #endif WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, + WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT, WORK_STRUCT_CWQ = 1 << WORK_STRUCT_CWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK @@ -59,8 +61,8 @@ enum { /* * Reserve 7 bits off of cwq pointer w/ debugobjects turned - * off. This makes cwqs aligned to 128 bytes which isn't too - * excessive while allowing 15 workqueue flush colors. + * off. This makes cwqs aligned to 256 bytes and allows 15 + * workqueue flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 362b50d092e2..a2dccfca03ba 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -941,6 +941,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, struct global_cwq *gcwq; struct cpu_workqueue_struct *cwq; struct list_head *worklist; + unsigned int work_flags; unsigned long flags; debug_work_activate(work); @@ -990,14 +991,17 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, BUG_ON(!list_empty(&work->entry)); cwq->nr_in_flight[cwq->work_color]++; + work_flags = work_color_to_flags(cwq->work_color); if (likely(cwq->nr_active < cwq->max_active)) { cwq->nr_active++; worklist = gcwq_determine_ins_pos(gcwq, cwq); - } else + } else { + work_flags |= WORK_STRUCT_DELAYED; worklist = &cwq->delayed_works; + } - insert_work(cwq, work, worklist, work_color_to_flags(cwq->work_color)); + insert_work(cwq, work, worklist, work_flags); spin_unlock_irqrestore(&gcwq->lock, flags); } @@ -1666,6 +1670,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq); move_linked_works(work, pos, NULL); + __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); cwq->nr_active++; } @@ -1673,6 +1678,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight * @cwq: cwq of interest * @color: color of work which left the queue + * @delayed: for a delayed work * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its cwq and handle workqueue flushing. @@ -1680,19 +1686,22 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) * CONTEXT: * spin_lock_irq(gcwq->lock). */ -static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) +static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color, + bool delayed) { /* ignore uncolored works */ if (color == WORK_NO_COLOR) return; cwq->nr_in_flight[color]--; - cwq->nr_active--; - if (!list_empty(&cwq->delayed_works)) { - /* one down, submit a delayed one */ - if (cwq->nr_active < cwq->max_active) - cwq_activate_first_delayed(cwq); + if (!delayed) { + cwq->nr_active--; + if (!list_empty(&cwq->delayed_works)) { + /* one down, submit a delayed one */ + if (cwq->nr_active < cwq->max_active) + cwq_activate_first_delayed(cwq); + } } /* is flush in progress and are we at the flushing tip? */ @@ -1823,7 +1832,7 @@ __acquires(&gcwq->lock) hlist_del_init(&worker->hentry); worker->current_work = NULL; worker->current_cwq = NULL; - cwq_dec_nr_in_flight(cwq, work_color); + cwq_dec_nr_in_flight(cwq, work_color, false); } /** @@ -2388,7 +2397,8 @@ static int try_to_grab_pending(struct work_struct *work) debug_work_deactivate(work); list_del_init(&work->entry); cwq_dec_nr_in_flight(get_work_cwq(work), - get_work_color(work)); + get_work_color(work), + *work_data_bits(work) & WORK_STRUCT_DELAYED); ret = 1; } } -- cgit From c54fce6eff197d9c57c97afbf6c9722ce434fc8f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 10 Sep 2010 16:51:36 +0200 Subject: workqueue: add documentation Update copyright notice and add Documentation/workqueue.txt. Randy Dunlap, Dave Chinner: misc fixes. Signed-off-by: Tejun Heo Reviewed-By: Florian Mickler Cc: Ingo Molnar Cc: Christoph Lameter Cc: Randy Dunlap Cc: Dave Chinner --- Documentation/workqueue.txt | 380 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/workqueue.h | 4 + kernel/workqueue.c | 27 ++-- 3 files changed, 401 insertions(+), 10 deletions(-) create mode 100644 Documentation/workqueue.txt (limited to 'include/linux/workqueue.h') diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt new file mode 100644 index 000000000000..e4498a2872c3 --- /dev/null +++ b/Documentation/workqueue.txt @@ -0,0 +1,380 @@ + +Concurrency Managed Workqueue (cmwq) + +September, 2010 Tejun Heo + Florian Mickler + +CONTENTS + +1. Introduction +2. Why cmwq? +3. The Design +4. Application Programming Interface (API) +5. Example Execution Scenarios +6. Guidelines + + +1. Introduction + +There are many cases where an asynchronous process execution context +is needed and the workqueue (wq) API is the most commonly used +mechanism for such cases. + +When such an asynchronous execution context is needed, a work item +describing which function to execute is put on a queue. An +independent thread serves as the asynchronous execution context. The +queue is called workqueue and the thread is called worker. + +While there are work items on the workqueue the worker executes the +functions associated with the work items one after the other. When +there is no work item left on the workqueue the worker becomes idle. +When a new work item gets queued, the worker begins executing again. + + +2. Why cmwq? + +In the original wq implementation, a multi threaded (MT) wq had one +worker thread per CPU and a single threaded (ST) wq had one worker +thread system-wide. A single MT wq needed to keep around the same +number of workers as the number of CPUs. The kernel grew a lot of MT +wq users over the years and with the number of CPU cores continuously +rising, some systems saturated the default 32k PID space just booting +up. + +Although MT wq wasted a lot of resource, the level of concurrency +provided was unsatisfactory. The limitation was common to both ST and +MT wq albeit less severe on MT. Each wq maintained its own separate +worker pool. A MT wq could provide only one execution context per CPU +while a ST wq one for the whole system. Work items had to compete for +those very limited execution contexts leading to various problems +including proneness to deadlocks around the single execution context. + +The tension between the provided level of concurrency and resource +usage also forced its users to make unnecessary tradeoffs like libata +choosing to use ST wq for polling PIOs and accepting an unnecessary +limitation that no two polling PIOs can progress at the same time. As +MT wq don't provide much better concurrency, users which require +higher level of concurrency, like async or fscache, had to implement +their own thread pool. + +Concurrency Managed Workqueue (cmwq) is a reimplementation of wq with +focus on the following goals. + +* Maintain compatibility with the original workqueue API. + +* Use per-CPU unified worker pools shared by all wq to provide + flexible level of concurrency on demand without wasting a lot of + resource. + +* Automatically regulate worker pool and level of concurrency so that + the API users don't need to worry about such details. + + +3. The Design + +In order to ease the asynchronous execution of functions a new +abstraction, the work item, is introduced. + +A work item is a simple struct that holds a pointer to the function +that is to be executed asynchronously. Whenever a driver or subsystem +wants a function to be executed asynchronously it has to set up a work +item pointing to that function and queue that work item on a +workqueue. + +Special purpose threads, called worker threads, execute the functions +off of the queue, one after the other. If no work is queued, the +worker threads become idle. These worker threads are managed in so +called thread-pools. + +The cmwq design differentiates between the user-facing workqueues that +subsystems and drivers queue work items on and the backend mechanism +which manages thread-pool and processes the queued work items. + +The backend is called gcwq. There is one gcwq for each possible CPU +and one gcwq to serve work items queued on unbound workqueues. + +Subsystems and drivers can create and queue work items through special +workqueue API functions as they see fit. They can influence some +aspects of the way the work items are executed by setting flags on the +workqueue they are putting the work item on. These flags include +things like CPU locality, reentrancy, concurrency limits and more. To +get a detailed overview refer to the API description of +alloc_workqueue() below. + +When a work item is queued to a workqueue, the target gcwq is +determined according to the queue parameters and workqueue attributes +and appended on the shared worklist of the gcwq. For example, unless +specifically overridden, a work item of a bound workqueue will be +queued on the worklist of exactly that gcwq that is associated to the +CPU the issuer is running on. + +For any worker pool implementation, managing the concurrency level +(how many execution contexts are active) is an important issue. cmwq +tries to keep the concurrency at a minimal but sufficient level. +Minimal to save resources and sufficient in that the system is used at +its full capacity. + +Each gcwq bound to an actual CPU implements concurrency management by +hooking into the scheduler. The gcwq is notified whenever an active +worker wakes up or sleeps and keeps track of the number of the +currently runnable workers. Generally, work items are not expected to +hog a CPU and consume many cycles. That means maintaining just enough +concurrency to prevent work processing from stalling should be +optimal. As long as there are one or more runnable workers on the +CPU, the gcwq doesn't start execution of a new work, but, when the +last running worker goes to sleep, it immediately schedules a new +worker so that the CPU doesn't sit idle while there are pending work +items. This allows using a minimal number of workers without losing +execution bandwidth. + +Keeping idle workers around doesn't cost other than the memory space +for kthreads, so cmwq holds onto idle ones for a while before killing +them. + +For an unbound wq, the above concurrency management doesn't apply and +the gcwq for the pseudo unbound CPU tries to start executing all work +items as soon as possible. The responsibility of regulating +concurrency level is on the users. There is also a flag to mark a +bound wq to ignore the concurrency management. Please refer to the +API section for details. + +Forward progress guarantee relies on that workers can be created when +more execution contexts are necessary, which in turn is guaranteed +through the use of rescue workers. All work items which might be used +on code paths that handle memory reclaim are required to be queued on +wq's that have a rescue-worker reserved for execution under memory +pressure. Else it is possible that the thread-pool deadlocks waiting +for execution contexts to free up. + + +4. Application Programming Interface (API) + +alloc_workqueue() allocates a wq. The original create_*workqueue() +functions are deprecated and scheduled for removal. alloc_workqueue() +takes three arguments - @name, @flags and @max_active. @name is the +name of the wq and also used as the name of the rescuer thread if +there is one. + +A wq no longer manages execution resources but serves as a domain for +forward progress guarantee, flush and work item attributes. @flags +and @max_active control how work items are assigned execution +resources, scheduled and executed. + +@flags: + + WQ_NON_REENTRANT + + By default, a wq guarantees non-reentrance only on the same + CPU. A work item may not be executed concurrently on the same + CPU by multiple workers but is allowed to be executed + concurrently on multiple CPUs. This flag makes sure + non-reentrance is enforced across all CPUs. Work items queued + to a non-reentrant wq are guaranteed to be executed by at most + one worker system-wide at any given time. + + WQ_UNBOUND + + Work items queued to an unbound wq are served by a special + gcwq which hosts workers which are not bound to any specific + CPU. This makes the wq behave as a simple execution context + provider without concurrency management. The unbound gcwq + tries to start execution of work items as soon as possible. + Unbound wq sacrifices locality but is useful for the following + cases. + + * Wide fluctuation in the concurrency level requirement is + expected and using bound wq may end up creating large number + of mostly unused workers across different CPUs as the issuer + hops through different CPUs. + + * Long running CPU intensive workloads which can be better + managed by the system scheduler. + + WQ_FREEZEABLE + + A freezeable wq participates in the freeze phase of the system + suspend operations. Work items on the wq are drained and no + new work item starts execution until thawed. + + WQ_RESCUER + + 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. + + WQ_HIGHPRI + + Work items of a highpri wq are queued at the head of the + worklist of the target gcwq and start execution regardless of + the current concurrency level. In other words, highpri work + items will always start execution as soon as execution + resource is available. + + Ordering among highpri work items is preserved - a highpri + work item queued after another highpri work item will start + execution after the earlier highpri work item starts. + + Although highpri work items are not held back by other + runnable work items, they still contribute to the concurrency + level. Highpri work items in runnable state will prevent + non-highpri work items from starting execution. + + This flag is meaningless for unbound wq. + + WQ_CPU_INTENSIVE + + Work items of a CPU intensive wq do not contribute to the + concurrency level. In other words, runnable CPU intensive + work items will not prevent other work items from starting + execution. This is useful for bound work items which are + expected to hog CPU cycles so that their execution is + regulated by the system scheduler. + + Although CPU intensive work items don't contribute to the + concurrency level, start of their executions is still + regulated by the concurrency management and runnable + non-CPU-intensive work items can delay execution of CPU + intensive work items. + + This flag is meaningless for unbound wq. + + WQ_HIGHPRI | WQ_CPU_INTENSIVE + + This combination makes the wq avoid interaction with + concurrency management completely and behave as a simple + per-CPU execution context provider. Work items queued on a + highpri CPU-intensive wq start execution as soon as resources + are available and don't affect execution of other work items. + +@max_active: + +@max_active determines the maximum number of execution contexts per +CPU which can be assigned to the work items of a wq. For example, +with @max_active of 16, at most 16 work items of the wq can be +executing at the same time per CPU. + +Currently, for a bound wq, the maximum limit for @max_active is 512 +and the default value used when 0 is specified is 256. For an unbound +wq, the limit is higher of 512 and 4 * num_possible_cpus(). These +values are chosen sufficiently high such that they are not the +limiting factor while providing protection in runaway cases. + +The number of active work items of a wq is usually regulated by the +users of the wq, more specifically, by how many work items the users +may queue at the same time. Unless there is a specific need for +throttling the number of active work items, specifying '0' is +recommended. + +Some users depend on the strict execution ordering of ST wq. The +combination of @max_active of 1 and WQ_UNBOUND is used to achieve this +behavior. Work items on such wq are always queued to the unbound gcwq +and only one work item can be active at any given time thus achieving +the same ordering property as ST wq. + + +5. Example Execution Scenarios + +The following example execution scenarios try to illustrate how cmwq +behave under different configurations. + + Work items w0, w1, w2 are queued to a bound wq q0 on the same CPU. + w0 burns CPU for 5ms then sleeps for 10ms then burns CPU for 5ms + again before finishing. w1 and w2 burn CPU for 5ms then sleep for + 10ms. + +Ignoring all other tasks, works and processing overhead, and assuming +simple FIFO scheduling, the following is one highly simplified version +of possible sequences of events with the original wq. + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 starts and burns CPU + 25 w1 sleeps + 35 w1 wakes up and finishes + 35 w2 starts and burns CPU + 40 w2 sleeps + 50 w2 wakes up and finishes + +And with cmwq with @max_active >= 3, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 starts and burns CPU + 10 w1 sleeps + 10 w2 starts and burns CPU + 15 w2 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 25 w2 wakes up and finishes + +If @max_active == 2, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 starts and burns CPU + 10 w1 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 20 w2 starts and burns CPU + 25 w2 sleeps + 35 w2 wakes up and finishes + +Now, let's assume w1 and w2 are queued to a different wq q1 which has +WQ_HIGHPRI set, + + TIME IN MSECS EVENT + 0 w1 and w2 start and burn CPU + 5 w1 sleeps + 10 w2 sleeps + 10 w0 starts and burns CPU + 15 w0 sleeps + 15 w1 wakes up and finishes + 20 w2 wakes up and finishes + 25 w0 wakes up and burns CPU + 30 w0 finishes + +If q1 has WQ_CPU_INTENSIVE set, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 and w2 start and burn CPU + 10 w1 sleeps + 15 w2 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 25 w2 wakes up and finishes + + +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. + +* Unless strict ordering is required, there is no need to use ST wq. + +* Unless there is a specific need, using 0 for @max_active is + 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. + +* Unless work items are expected to consume a huge amount of CPU + cycles, using a bound wq is usually beneficial due to the increased + level of locality in wq operations and work item execution. diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index f11100f96482..25e02c941bac 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -235,6 +235,10 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } #define work_clear_pending(work) \ clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) +/* + * Workqueue flags and constants. For details, please refer to + * Documentation/workqueue.txt. + */ enum { WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 727f24e563ae..f77afd939229 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1,19 +1,26 @@ /* - * linux/kernel/workqueue.c + * kernel/workqueue.c - generic async execution with shared worker pool * - * Generic mechanism for defining kernel helper threads for running - * arbitrary tasks in process context. + * Copyright (C) 2002 Ingo Molnar * - * Started by Ingo Molnar, Copyright (C) 2002 + * Derived from the taskqueue/keventd code by: + * David Woodhouse + * Andrew Morton + * Kai Petzke + * Theodore Ts'o * - * Derived from the taskqueue/keventd code by: + * Made to use alloc_percpu by Christoph Lameter. * - * David Woodhouse - * Andrew Morton - * Kai Petzke - * Theodore Ts'o + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo * - * Made to use alloc_percpu by Christoph Lameter. + * This is the generic async execution mechanism. Work items as are + * executed in process context. The worker pool is shared and + * automatically managed. There is one worker pool for each CPU and + * one extra for works which are better served by workers which are + * not bound to any specific CPU. + * + * Please read Documentation/workqueue.txt for details. */ #include -- cgit 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/linux/workqueue.h') 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 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/linux/workqueue.h') 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 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/linux/workqueue.h') 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 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/linux/workqueue.h') 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 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/linux/workqueue.h') 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 From ca1cab37d91cbe8a8333732540d43cabb54cfa85 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 26 Oct 2010 14:22:34 -0700 Subject: workqueues: s/ON_STACK/ONSTACK/ Silly though it is, completions and wait_queue_heads use foo_ONSTACK (COMPLETION_INITIALIZER_ONSTACK, DECLARE_COMPLETION_ONSTACK, __WAIT_QUEUE_HEAD_INIT_ONSTACK and DECLARE_WAIT_QUEUE_HEAD_ONSTACK) so I guess workqueues should do the same thing. s/INIT_WORK_ON_STACK/INIT_WORK_ONSTACK/ s/INIT_DELAYED_WORK_ON_STACK/INIT_DELAYED_WORK_ONSTACK/ Cc: Peter Zijlstra Acked-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/hpet.c | 2 +- arch/x86/kernel/smpboot.c | 2 +- drivers/md/dm-snap-persistent.c | 2 +- include/linux/workqueue.h | 6 +++--- kernel/workqueue.c | 2 +- 5 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index aff0b3c27509..ae03cab4352e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -713,7 +713,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n, switch (action & 0xf) { case CPU_ONLINE: - INIT_DELAYED_WORK_ON_STACK(&work.work, hpet_work); + INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work); init_completion(&work.complete); /* FIXME: add schedule_work_on() */ schedule_delayed_work_on(cpu, &work.work, 0); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6af118511b4a..6c7faecd9e4a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -747,7 +747,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), }; - INIT_WORK_ON_STACK(&c_idle.work, do_fork_idle); + INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle); alternatives_smp_switch(1); diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 0b61792a2780..2129cdb115dc 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -254,7 +254,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw, * Issue the synchronous I/O from a different thread * to avoid generic_make_request recursion. */ - INIT_WORK_ON_STACK(&req.work, do_metadata); + INIT_WORK_ONSTACK(&req.work, do_metadata); queue_work(ps->metadata_wq, &req.work); flush_workqueue(ps->metadata_wq); diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 070bb7a88936..0c0771f06bfa 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -190,7 +190,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } __INIT_WORK((_work), (_func), 0); \ } while (0) -#define INIT_WORK_ON_STACK(_work, _func) \ +#define INIT_WORK_ONSTACK(_work, _func) \ do { \ __INIT_WORK((_work), (_func), 1); \ } while (0) @@ -201,9 +201,9 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } init_timer(&(_work)->timer); \ } while (0) -#define INIT_DELAYED_WORK_ON_STACK(_work, _func) \ +#define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ do { \ - INIT_WORK_ON_STACK(&(_work)->work, (_func)); \ + INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ init_timer_on_stack(&(_work)->timer); \ } while (0) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index e5ff2cbaadc2..90db1bd1a978 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2064,7 +2064,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, * checks and call back into the fixup functions where we * might deadlock. */ - INIT_WORK_ON_STACK(&barr->work, wq_barrier_func); + INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion(&barr->done); -- cgit