From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752118AbZLRM5o (ORCPT ); Fri, 18 Dec 2009 07:57:44 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1750844AbZLRM5g (ORCPT ); Fri, 18 Dec 2009 07:57:36 -0500 Received: from hera.kernel.org ([140.211.167.34]:45246 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752081AbZLRM5T (ORCPT ); Fri, 18 Dec 2009 07:57:19 -0500 From: Tejun Heo To: torvalds@linux-foundation.org, awalls@radix.net, linux-kernel@vger.kernel.org, jeff@garzik.org, mingo@elte.hu, akpm@linux-foundation.org, jens.axboe@oracle.com, rusty@rustcorp.com.au, cl@linux-foundation.org, dhowells@redhat.com, arjan@linux.intel.com, avi@redhat.com, peterz@infradead.org, johannes@sipsolutions.net, andi@firstfloor.org Cc: Tejun Heo Subject: [PATCH 21/27] workqueue: introduce global cwq and unify cwq locks Date: Fri, 18 Dec 2009 21:58:02 +0900 Message-Id: <1261141088-2014-22-git-send-email-tj@kernel.org> X-Mailer: git-send-email 1.6.4.2 In-Reply-To: <1261141088-2014-1-git-send-email-tj@kernel.org> References: <1261141088-2014-1-git-send-email-tj@kernel.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org There is one gcwq (global cwq) per each cpu and all cwqs on an cpu point to it. A gcwq contains a lock to be used by all cwqs on the cpu and an ida to give IDs to workers belonging to the cpu. This patch introduces gcwq, moves worker_ida into gcwq and make all cwqs on the same cpu use the cpu's gcwq->lock instead of separate locks. gcwq->ida is now protected by gcwq->lock too. Signed-off-by: Tejun Heo --- kernel/workqueue.c | 156 ++++++++++++++++++++++++++++++++-------------------- 1 files changed, 96 insertions(+), 60 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index eca3925..91c924c 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -40,38 +40,45 @@ * * I: Set during initialization and read-only afterwards. * - * L: cwq->lock protected. Access with cwq->lock held. + * L: gcwq->lock protected. Access with gcwq->lock held. * * F: wq->flush_mutex protected. * * W: workqueue_lock protected. */ +struct global_cwq; 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 global_cwq *gcwq; /* I: the associated gcwq */ struct cpu_workqueue_struct *cwq; /* I: the associated cwq */ int id; /* I: worker id */ }; /* + * Global per-cpu workqueue. + */ +struct global_cwq { + spinlock_t lock; /* the gcwq lock */ + unsigned int cpu; /* I: the associated cpu */ + struct ida worker_ida; /* L: for worker IDs */ +} ____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 * 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 { - - spinlock_t lock; - + struct global_cwq *gcwq; /* I: the associated gcwq */ struct list_head worklist; wait_queue_head_t more_work; - unsigned int cpu; struct worker *worker; - struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ @@ -228,13 +235,19 @@ static inline void debug_work_deactivate(struct work_struct *work) { } /* Serializes the accesses to the list of workqueues. */ 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 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); +} + static struct cpu_workqueue_struct *get_cwq(unsigned int cpu, struct workqueue_struct *wq) { @@ -296,7 +309,7 @@ static inline struct cpu_workqueue_struct *get_wq_data(struct work_struct *work) * Insert @work into @cwq after @head. * * CONTEXT: - * spin_lock_irq(cwq->lock). + * spin_lock_irq(gcwq->lock). */ static void insert_work(struct cpu_workqueue_struct *cwq, struct work_struct *work, struct list_head *head, @@ -319,12 +332,13 @@ 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 list_head *worklist; unsigned long flags; debug_work_activate(work); - spin_lock_irqsave(&cwq->lock, flags); + spin_lock_irqsave(&gcwq->lock, flags); BUG_ON(!list_empty(&work->entry)); cwq->nr_in_flight[cwq->work_color]++; @@ -337,7 +351,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, insert_work(cwq, work, worklist, work_color_to_flags(cwq->work_color)); - spin_unlock_irqrestore(&cwq->lock, flags); + spin_unlock_irqrestore(&gcwq->lock, flags); } /** @@ -476,39 +490,41 @@ static struct worker *alloc_worker(void) */ static struct worker *create_worker(struct cpu_workqueue_struct *cwq, bool bind) { + struct global_cwq *gcwq = cwq->gcwq; int id = -1; struct worker *worker = NULL; - spin_lock(&workqueue_lock); - while (ida_get_new(&per_cpu(worker_ida, cwq->cpu), &id)) { - spin_unlock(&workqueue_lock); - if (!ida_pre_get(&per_cpu(worker_ida, cwq->cpu), GFP_KERNEL)) + spin_lock_irq(&gcwq->lock); + while (ida_get_new(&gcwq->worker_ida, &id)) { + spin_unlock_irq(&gcwq->lock); + if (!ida_pre_get(&gcwq->worker_ida, GFP_KERNEL)) goto fail; - spin_lock(&workqueue_lock); + spin_lock_irq(&gcwq->lock); } - spin_unlock(&workqueue_lock); + spin_unlock_irq(&gcwq->lock); worker = alloc_worker(); if (!worker) goto fail; + worker->gcwq = gcwq; worker->cwq = cwq; worker->id = id; worker->task = kthread_create(worker_thread, worker, "kworker/%u:%d", - cwq->cpu, id); + gcwq->cpu, id); if (IS_ERR(worker->task)) goto fail; if (bind) - kthread_bind(worker->task, cwq->cpu); + kthread_bind(worker->task, gcwq->cpu); return worker; fail: if (id >= 0) { - spin_lock(&workqueue_lock); - ida_remove(&per_cpu(worker_ida, cwq->cpu), id); - spin_unlock(&workqueue_lock); + spin_lock_irq(&gcwq->lock); + ida_remove(&gcwq->worker_ida, id); + spin_unlock_irq(&gcwq->lock); } kfree(worker); return NULL; @@ -521,7 +537,7 @@ fail: * Start @worker. * * CONTEXT: - * spin_lock_irq(cwq->lock). + * spin_lock_irq(gcwq->lock). */ static void start_worker(struct worker *worker) { @@ -536,7 +552,7 @@ static void start_worker(struct worker *worker) */ static void destroy_worker(struct worker *worker) { - int cpu = worker->cwq->cpu; + struct global_cwq *gcwq = worker->gcwq; int id = worker->id; /* sanity check frenzy */ @@ -546,9 +562,9 @@ static void destroy_worker(struct worker *worker) kthread_stop(worker->task); kfree(worker); - spin_lock(&workqueue_lock); - ida_remove(&per_cpu(worker_ida, cpu), id); - spin_unlock(&workqueue_lock); + spin_lock_irq(&gcwq->lock); + ida_remove(&gcwq->worker_ida, id); + spin_unlock_irq(&gcwq->lock); } /** @@ -566,7 +582,7 @@ static void destroy_worker(struct worker *worker) * nested inside outer list_for_each_entry_safe(). * * CONTEXT: - * spin_lock_irq(cwq->lock). + * spin_lock_irq(gcwq->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) @@ -611,7 +627,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) * decrement nr_in_flight of its cwq and handle workqueue flushing. * * CONTEXT: - * spin_lock_irq(cwq->lock). + * spin_lock_irq(gcwq->lock). */ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) { @@ -658,11 +674,12 @@ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) * call this function to process a work. * * CONTEXT: - * spin_lock_irq(cwq->lock) which is released and regrabbed. + * spin_lock_irq(gcwq->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) { struct cpu_workqueue_struct *cwq = worker->cwq; + struct global_cwq *gcwq = cwq->gcwq; work_func_t f = work->func; int work_color; #ifdef CONFIG_LOCKDEP @@ -681,7 +698,7 @@ static void process_one_work(struct worker *worker, struct work_struct *work) work_color = work_flags_to_color(*work_data_bits(work)); list_del_init(&work->entry); - spin_unlock_irq(&cwq->lock); + spin_unlock_irq(&gcwq->lock); BUG_ON(get_wq_data(work) != cwq); work_clear_pending(work); @@ -701,7 +718,7 @@ static void process_one_work(struct worker *worker, struct work_struct *work) dump_stack(); } - spin_lock_irq(&cwq->lock); + spin_lock_irq(&gcwq->lock); /* we're done with it, release */ worker->current_work = NULL; @@ -717,7 +734,7 @@ static void process_one_work(struct worker *worker, struct work_struct *work) * fetches a work from the top and executes it. * * CONTEXT: - * spin_lock_irq(cwq->lock) which may be released and regrabbed + * spin_lock_irq(gcwq->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) @@ -738,6 +755,7 @@ static void process_scheduled_works(struct worker *worker) static int worker_thread(void *__worker) { struct worker *worker = __worker; + struct global_cwq *gcwq = worker->gcwq; struct cpu_workqueue_struct *cwq = worker->cwq; DEFINE_WAIT(wait); @@ -751,7 +769,7 @@ static int worker_thread(void *__worker) if (kthread_should_stop()) break; - spin_lock_irq(&cwq->lock); + spin_lock_irq(&gcwq->lock); while (!list_empty(&cwq->worklist)) { struct work_struct *work = @@ -771,7 +789,7 @@ static int worker_thread(void *__worker) } } - spin_unlock_irq(&cwq->lock); + spin_unlock_irq(&gcwq->lock); } return 0; @@ -810,7 +828,7 @@ static void wq_barrier_func(struct work_struct *work) * underneath us, so we can't reliably determine cwq from @target. * * CONTEXT: - * spin_lock_irq(cwq->lock). + * spin_lock_irq(gcwq->lock). */ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, struct wq_barrier *barr, @@ -820,7 +838,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, unsigned int linked = 0; /* - * debugobject calls are safe here even with cwq->lock locked + * debugobject calls are safe here even with gcwq->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. @@ -890,8 +908,9 @@ static bool flush_workqueue_prep_cwqs(struct workqueue_struct *wq, for_each_possible_cpu(cpu) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + struct global_cwq *gcwq = cwq->gcwq; - spin_lock_irq(&cwq->lock); + spin_lock_irq(&gcwq->lock); if (flush_color >= 0) { BUG_ON(cwq->flush_color != -1); @@ -908,7 +927,7 @@ static bool flush_workqueue_prep_cwqs(struct workqueue_struct *wq, cwq->work_color = work_color; } - spin_unlock_irq(&cwq->lock); + spin_unlock_irq(&gcwq->lock); } return wait; @@ -1081,17 +1100,19 @@ int flush_work(struct work_struct *work) { struct worker *worker = NULL; struct cpu_workqueue_struct *cwq; + struct global_cwq *gcwq; struct wq_barrier barr; might_sleep(); cwq = get_wq_data(work); if (!cwq) return 0; + gcwq = cwq->gcwq; lock_map_acquire(&cwq->wq->lockdep_map); lock_map_release(&cwq->wq->lockdep_map); - spin_lock_irq(&cwq->lock); + spin_lock_irq(&gcwq->lock); if (!list_empty(&work->entry)) { /* * See the comment near try_to_grab_pending()->smp_rmb(). @@ -1108,12 +1129,12 @@ int flush_work(struct work_struct *work) } insert_wq_barrier(cwq, &barr, work, worker); - spin_unlock_irq(&cwq->lock); + spin_unlock_irq(&gcwq->lock); wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); return 1; already_gone: - spin_unlock_irq(&cwq->lock); + spin_unlock_irq(&gcwq->lock); return 0; } EXPORT_SYMBOL_GPL(flush_work); @@ -1124,6 +1145,7 @@ 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; @@ -1138,8 +1160,9 @@ static int try_to_grab_pending(struct work_struct *work) cwq = get_wq_data(work); if (!cwq) return ret; + gcwq = cwq->gcwq; - spin_lock_irq(&cwq->lock); + spin_lock_irq(&gcwq->lock); if (!list_empty(&work->entry)) { /* * This work is queued, but perhaps we locked the wrong cwq. @@ -1155,7 +1178,7 @@ static int try_to_grab_pending(struct work_struct *work) ret = 1; } } - spin_unlock_irq(&cwq->lock); + spin_unlock_irq(&gcwq->lock); return ret; } @@ -1163,10 +1186,11 @@ static int try_to_grab_pending(struct work_struct *work) static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq, struct work_struct *work) { + struct global_cwq *gcwq = cwq->gcwq; struct wq_barrier barr; struct worker *worker; - spin_lock_irq(&cwq->lock); + spin_lock_irq(&gcwq->lock); worker = NULL; if (unlikely(cwq->worker && cwq->worker->current_work == work)) { @@ -1174,7 +1198,7 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq, insert_wq_barrier(cwq, &barr, work, worker); } - spin_unlock_irq(&cwq->lock); + spin_unlock_irq(&gcwq->lock); if (unlikely(worker)) { wait_for_completion(&barr.done); @@ -1518,13 +1542,13 @@ struct workqueue_struct *__create_workqueue_key(const char *name, */ for_each_possible_cpu(cpu) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + struct global_cwq *gcwq = get_gcwq(cpu); BUG_ON((unsigned long)cwq & WORK_STRUCT_FLAG_MASK); - cwq->cpu = cpu; + cwq->gcwq = gcwq; 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); @@ -1698,7 +1722,7 @@ EXPORT_SYMBOL_GPL(work_on_cpu); * list instead of the cwq ones. * * CONTEXT: - * Grabs and releases workqueue_lock and cwq->lock's. + * Grabs and releases workqueue_lock and gcwq->lock's. */ void freeze_workqueues_begin(void) { @@ -1711,16 +1735,18 @@ void freeze_workqueues_begin(void) workqueue_freezing = true; for_each_possible_cpu(cpu) { + struct global_cwq *gcwq = get_gcwq(cpu); + + spin_lock_irq(&gcwq->lock); + 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_irq(&gcwq->lock); } spin_unlock(&workqueue_lock); @@ -1779,7 +1805,7 @@ out_unlock: * frozen works are transferred to their respective cwq worklists. * * CONTEXT: - * Grabs and releases workqueue_lock and cwq->lock's. + * Grabs and releases workqueue_lock and gcwq->lock's. */ void thaw_workqueues(void) { @@ -1792,14 +1818,16 @@ void thaw_workqueues(void) goto out_unlock; for_each_possible_cpu(cpu) { + struct global_cwq *gcwq = get_gcwq(cpu); + + spin_lock_irq(&gcwq->lock); + 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; @@ -1808,9 +1836,9 @@ void thaw_workqueues(void) cwq_activate_first_delayed(cwq); wake_up(&cwq->more_work); - - spin_unlock_irq(&cwq->lock); } + + spin_unlock_irq(&gcwq->lock); } workqueue_freezing = false; @@ -1831,11 +1859,19 @@ void __init init_workqueues(void) BUILD_BUG_ON(__alignof__(struct cpu_workqueue_struct) < __alignof__(unsigned long long)); - for_each_possible_cpu(cpu) - ida_init(&per_cpu(worker_ida, cpu)); - singlethread_cpu = cpumask_first(cpu_possible_mask); hotcpu_notifier(workqueue_cpu_callback, 0); + + /* initialize gcwqs */ + for_each_possible_cpu(cpu) { + struct global_cwq *gcwq = get_gcwq(cpu); + + spin_lock_init(&gcwq->lock); + gcwq->cpu = cpu; + + ida_init(&gcwq->worker_ida); + } + keventd_wq = create_workqueue("events"); BUG_ON(!keventd_wq); } -- 1.6.4.2