From 45d9550a0e7e9230606ca3c4c6f4dc6297848b2f Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 19 Feb 2013 12:17:01 -0800 Subject: workqueue: allow more off-queue flag space When a work item is off-queue, its work->data contains WORK_STRUCT_* and WORK_OFFQ_* flags. As WORK_OFFQ_* flags are used only while a work item is off-queue, it can occupy bits of work->data which aren't used while off-queue. WORK_OFFQ_* currently only use bits used by on-queue CWQ pointer. As color bits aren't used while off-queue, there's no reason to not use them. Lower WORK_OFFQ_FLAG_BASE from WORK_STRUCT_FLAG_BITS to WORK_STRUCT_COLOR_SHIFT thus giving 4 more bits to off-queue flag space which is also used to record worker_pool ID while off-queue. This doesn't introduce any visible behavior difference. tj: Rewrote the description. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 8afab27cdbc..5bd030f630a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -68,7 +68,7 @@ enum { WORK_STRUCT_COLOR_BITS, /* data contains off-queue information when !WORK_STRUCT_PWQ */ - WORK_OFFQ_FLAG_BASE = WORK_STRUCT_FLAG_BITS, + WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, WORK_OFFQ_CANCELING = (1 << WORK_OFFQ_FLAG_BASE), -- cgit v1.2.3-70-g09d2 From d84ff0512f1bfc0d8c864efadb4523fce68919cc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:29:59 -0700 Subject: workqueue: consistently use int for @cpu variables Workqueue is mixing unsigned int and int for @cpu variables. There's no point in using unsigned int for cpus - many of cpu related APIs take int anyway. Consistently use int for @cpu variables so that we can use negative values to mark special ones. This patch doesn't introduce any visible behavior changes. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 6 +++--- kernel/workqueue.c | 24 +++++++++++------------- kernel/workqueue_internal.h | 5 ++--- 3 files changed, 16 insertions(+), 19 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 5bd030f630a..899be6636d2 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -435,7 +435,7 @@ extern bool cancel_delayed_work_sync(struct delayed_work *dwork); 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 bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); /* @@ -466,12 +466,12 @@ static inline bool __deprecated flush_delayed_work_sync(struct delayed_work *dwo } #ifndef CONFIG_SMP -static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) +static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } #else -long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg); +long work_on_cpu(int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 26c67c76b6c..73c5f68065b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -124,7 +124,7 @@ enum { struct worker_pool { spinlock_t lock; /* the pool lock */ - unsigned int cpu; /* I: the associated cpu */ + int cpu; /* I: the associated cpu */ int id; /* I: pool ID */ unsigned int flags; /* X: flags */ @@ -467,8 +467,7 @@ static struct worker_pool *get_std_worker_pool(int cpu, bool highpri) return &pools[highpri]; } -static struct pool_workqueue *get_pwq(unsigned int cpu, - struct workqueue_struct *wq) +static struct pool_workqueue *get_pwq(int cpu, struct workqueue_struct *wq) { if (!(wq->flags & WQ_UNBOUND)) { if (likely(cpu < nr_cpu_ids)) @@ -730,7 +729,7 @@ static void wake_up_worker(struct worker_pool *pool) * CONTEXT: * spin_lock_irq(rq->lock) */ -void wq_worker_waking_up(struct task_struct *task, unsigned int cpu) +void wq_worker_waking_up(struct task_struct *task, int cpu) { struct worker *worker = kthread_data(task); @@ -755,8 +754,7 @@ void wq_worker_waking_up(struct task_struct *task, unsigned int cpu) * 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 task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) { struct worker *worker = kthread_data(task), *to_wakeup = NULL; struct worker_pool *pool; @@ -1159,7 +1157,7 @@ static bool is_chained_work(struct workqueue_struct *wq) return worker && worker->current_pwq->wq == wq; } -static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, +static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { struct pool_workqueue *pwq; @@ -1714,7 +1712,7 @@ static struct worker *create_worker(struct worker_pool *pool) if (pool->cpu != WORK_CPU_UNBOUND) worker->task = kthread_create_on_node(worker_thread, worker, cpu_to_node(pool->cpu), - "kworker/%u:%d%s", pool->cpu, id, pri); + "kworker/%d:%d%s", pool->cpu, id, pri); else worker->task = kthread_create(worker_thread, worker, "kworker/u:%d%s", id, pri); @@ -3345,7 +3343,7 @@ EXPORT_SYMBOL_GPL(workqueue_set_max_active); * RETURNS: * %true if congested, %false otherwise. */ -bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq) +bool workqueue_congested(int cpu, struct workqueue_struct *wq) { struct pool_workqueue *pwq = get_pwq(cpu, wq); @@ -3461,7 +3459,7 @@ static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { - unsigned int cpu = (unsigned long)hcpu; + int cpu = (unsigned long)hcpu; struct worker_pool *pool; switch (action & ~CPU_TASKS_FROZEN) { @@ -3507,7 +3505,7 @@ static int __cpuinit workqueue_cpu_down_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { - unsigned int cpu = (unsigned long)hcpu; + int cpu = (unsigned long)hcpu; struct work_struct unbind_work; switch (action & ~CPU_TASKS_FROZEN) { @@ -3547,7 +3545,7 @@ static void work_for_cpu_fn(struct work_struct *work) * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. */ -long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) +long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; @@ -3705,7 +3703,7 @@ out_unlock: static int __init init_workqueues(void) { - unsigned int cpu; + int cpu; /* make sure we have enough bits for OFFQ pool ID */ BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT)) < diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index f9c887731e2..f116f071d91 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -59,8 +59,7 @@ static inline struct worker *current_wq_worker(void) * Scheduler hooks for concurrency managed workqueue. Only to be used from * sched.c and workqueue.c. */ -void wq_worker_waking_up(struct task_struct *task, unsigned int cpu); -struct task_struct *wq_worker_sleeping(struct task_struct *task, - unsigned int cpu); +void wq_worker_waking_up(struct task_struct *task, int cpu); +struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ -- cgit v1.2.3-70-g09d2 From 7a4e344c5675eefbde93ed9a98ef45e0e4957bc2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:00 -0700 Subject: workqueue: introduce workqueue_attrs Introduce struct workqueue_attrs which carries worker attributes - currently the nice level and allowed cpumask along with helper routines alloc_workqueue_attrs() and free_workqueue_attrs(). Each worker_pool now carries ->attrs describing the attributes of its workers. All functions dealing with cpumask and nice level of workers are updated to follow worker_pool->attrs instead of determining them from other characteristics of the worker_pool, and init_workqueues() is updated to set worker_pool->attrs appropriately for all standard pools. Note that create_worker() is updated to always perform set_user_nice() and use set_cpus_allowed_ptr() combined with manual assertion of PF_THREAD_BOUND instead of kthread_bind(). This simplifies handling random attributes without affecting the outcome. This patch doesn't introduce any behavior changes. v2: Missing cpumask_var_t definition caused build failure on some archs. linux/cpumask.h included. Signed-off-by: Tejun Heo Reported-by: kbuild test robot Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 13 ++++++ kernel/workqueue.c | 103 ++++++++++++++++++++++++++++++++++++---------- 2 files changed, 94 insertions(+), 22 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 899be6636d2..00c1b9ba825 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -11,6 +11,7 @@ #include #include #include +#include struct workqueue_struct; @@ -115,6 +116,15 @@ struct delayed_work { int cpu; }; +/* + * A struct for workqueue attributes. This can be used to change + * attributes of an unbound workqueue. + */ +struct workqueue_attrs { + int nice; /* nice level */ + cpumask_var_t cpumask; /* allowed CPUs */ +}; + static inline struct delayed_work *to_delayed_work(struct work_struct *work) { return container_of(work, struct delayed_work, work); @@ -399,6 +409,9 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, extern void destroy_workqueue(struct workqueue_struct *wq); +struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask); +void free_workqueue_attrs(struct workqueue_attrs *attrs); + extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_work(struct workqueue_struct *wq, struct work_struct *work); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 094f16668e1..b0d3cbb83f6 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -148,6 +148,8 @@ struct worker_pool { struct mutex assoc_mutex; /* protect POOL_DISASSOCIATED */ struct ida worker_ida; /* L: for worker IDs */ + struct workqueue_attrs *attrs; /* I: worker attributes */ + /* * The current concurrency level. As it's likely to be accessed * from other CPUs during try_to_wake_up(), put it in a separate @@ -1566,14 +1568,13 @@ __acquires(&pool->lock) * against POOL_DISASSOCIATED. */ if (!(pool->flags & POOL_DISASSOCIATED)) - set_cpus_allowed_ptr(current, get_cpu_mask(pool->cpu)); + set_cpus_allowed_ptr(current, pool->attrs->cpumask); spin_lock_irq(&pool->lock); if (pool->flags & POOL_DISASSOCIATED) return false; if (task_cpu(current) == pool->cpu && - cpumask_equal(¤t->cpus_allowed, - get_cpu_mask(pool->cpu))) + cpumask_equal(¤t->cpus_allowed, pool->attrs->cpumask)) return true; spin_unlock_irq(&pool->lock); @@ -1679,7 +1680,7 @@ static void rebind_workers(struct worker_pool *pool) * wq doesn't really matter but let's keep @worker->pool * and @pwq->pool consistent for sanity. */ - if (std_worker_pool_pri(worker->pool)) + if (worker->pool->attrs->nice < 0) wq = system_highpri_wq; else wq = system_wq; @@ -1721,7 +1722,7 @@ static struct worker *alloc_worker(void) */ static struct worker *create_worker(struct worker_pool *pool) { - const char *pri = std_worker_pool_pri(pool) ? "H" : ""; + const char *pri = pool->attrs->nice < 0 ? "H" : ""; struct worker *worker = NULL; int id = -1; @@ -1751,24 +1752,23 @@ static struct worker *create_worker(struct worker_pool *pool) if (IS_ERR(worker->task)) goto fail; - if (std_worker_pool_pri(pool)) - set_user_nice(worker->task, HIGHPRI_NICE_LEVEL); + set_user_nice(worker->task, pool->attrs->nice); + set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); /* - * Determine CPU binding of the new worker depending on - * %POOL_DISASSOCIATED. The caller is responsible for ensuring the - * flag remains stable across this function. See the comments - * above the flag definition for details. - * - * As an unbound worker may later become a regular one if CPU comes - * online, make sure every worker has %PF_THREAD_BOUND set. + * %PF_THREAD_BOUND is used to prevent userland from meddling with + * cpumask of workqueue workers. This is an abuse. We need + * %PF_NO_SETAFFINITY. */ - if (!(pool->flags & POOL_DISASSOCIATED)) { - kthread_bind(worker->task, pool->cpu); - } else { - worker->task->flags |= PF_THREAD_BOUND; + worker->task->flags |= PF_THREAD_BOUND; + + /* + * The caller is responsible for ensuring %POOL_DISASSOCIATED + * remains stable across this function. See the comments above the + * flag definition for details. + */ + if (pool->flags & POOL_DISASSOCIATED) worker->flags |= WORKER_UNBOUND; - } return worker; fail: @@ -3123,7 +3123,52 @@ int keventd_up(void) return system_wq != NULL; } -static void init_worker_pool(struct worker_pool *pool) +/** + * free_workqueue_attrs - free a workqueue_attrs + * @attrs: workqueue_attrs to free + * + * Undo alloc_workqueue_attrs(). + */ +void free_workqueue_attrs(struct workqueue_attrs *attrs) +{ + if (attrs) { + free_cpumask_var(attrs->cpumask); + kfree(attrs); + } +} + +/** + * alloc_workqueue_attrs - allocate a workqueue_attrs + * @gfp_mask: allocation mask to use + * + * Allocate a new workqueue_attrs, initialize with default settings and + * return it. Returns NULL on failure. + */ +struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask) +{ + struct workqueue_attrs *attrs; + + attrs = kzalloc(sizeof(*attrs), gfp_mask); + if (!attrs) + goto fail; + if (!alloc_cpumask_var(&attrs->cpumask, gfp_mask)) + goto fail; + + cpumask_setall(attrs->cpumask); + return attrs; +fail: + free_workqueue_attrs(attrs); + return NULL; +} + +/** + * init_worker_pool - initialize a newly zalloc'd worker_pool + * @pool: worker_pool to initialize + * + * Initiailize a newly zalloc'd @pool. It also allocates @pool->attrs. + * Returns 0 on success, -errno on failure. + */ +static int init_worker_pool(struct worker_pool *pool) { spin_lock_init(&pool->lock); pool->flags |= POOL_DISASSOCIATED; @@ -3141,6 +3186,11 @@ static void init_worker_pool(struct worker_pool *pool) mutex_init(&pool->manager_arb); mutex_init(&pool->assoc_mutex); ida_init(&pool->worker_ida); + + pool->attrs = alloc_workqueue_attrs(GFP_KERNEL); + if (!pool->attrs) + return -ENOMEM; + return 0; } static int alloc_and_link_pwqs(struct workqueue_struct *wq) @@ -3792,7 +3842,8 @@ out_unlock: static int __init init_workqueues(void) { - int cpu; + int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; + int i, cpu; /* make sure we have enough bits for OFFQ pool ID */ BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT)) < @@ -3809,10 +3860,18 @@ static int __init init_workqueues(void) for_each_wq_cpu(cpu) { struct worker_pool *pool; + i = 0; for_each_std_worker_pool(pool, cpu) { - init_worker_pool(pool); + BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; + if (cpu != WORK_CPU_UNBOUND) + cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); + else + cpumask_setall(pool->attrs->cpumask); + + pool->attrs->nice = std_nice[i++]; + /* alloc pool ID */ BUG_ON(worker_pool_assign_id(pool)); } -- cgit v1.2.3-70-g09d2 From 493008a8e475771a2126e0ce95a73e35b371d277 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:03 -0700 Subject: workqueue: drop WQ_RESCUER and test workqueue->rescuer for NULL instead WQ_RESCUER is superflous. WQ_MEM_RECLAIM indicates that the user wants a rescuer and testing wq->rescuer for NULL can answer whether a given workqueue has a rescuer or not. Drop WQ_RESCUER and test wq->rescuer directly. This will help simplifying __alloc_workqueue_key() failure path by allowing it to use destroy_workqueue() on a partially constructed workqueue, which in turn will help implementing dynamic management of pool_workqueues. While at it, clear wq->rescuer after freeing it in destroy_workqueue(). This is a precaution as scheduled changes will make destruction more complex. This patch doesn't introduce any functional changes. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 1 - kernel/workqueue.c | 22 ++++++++++------------ 2 files changed, 10 insertions(+), 13 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 00c1b9ba825..c270b4eedf1 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -295,7 +295,6 @@ enum { WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ WQ_DRAINING = 1 << 6, /* internal: workqueue is draining */ - 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 */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index a8b86f7b6e3..7ff2b9c5cc3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1827,7 +1827,7 @@ static void send_mayday(struct work_struct *work) lockdep_assert_held(&workqueue_lock); - if (!(wq->flags & WQ_RESCUER)) + if (!wq->rescuer) return; /* mayday mayday mayday */ @@ -2285,7 +2285,7 @@ sleep: * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each - * workqueue which has WQ_RESCUER set. + * workqueue which has WQ_MEM_RECLAIM set. * * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of @@ -2769,7 +2769,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr) * flusher is not running on the same workqueue by verifying write * access. */ - if (pwq->wq->saved_max_active == 1 || pwq->wq->flags & WQ_RESCUER) + if (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer) lock_map_acquire(&pwq->wq->lockdep_map); else lock_map_acquire_read(&pwq->wq->lockdep_map); @@ -3412,13 +3412,6 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, va_end(args); va_end(args1); - /* - * Workqueues which may be used during memory reclaim should - * have a rescuer to guarantee forward progress. - */ - if (flags & WQ_MEM_RECLAIM) - flags |= WQ_RESCUER; - max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); @@ -3449,7 +3442,11 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, } local_irq_enable(); - if (flags & WQ_RESCUER) { + /* + * Workqueues which may be used during memory reclaim should + * have a rescuer to guarantee forward progress. + */ + if (flags & WQ_MEM_RECLAIM) { struct worker *rescuer; wq->rescuer = rescuer = alloc_worker(); @@ -3533,9 +3530,10 @@ void destroy_workqueue(struct workqueue_struct *wq) spin_unlock_irq(&workqueue_lock); - if (wq->flags & WQ_RESCUER) { + if (wq->rescuer) { kthread_stop(wq->rescuer->task); kfree(wq->rescuer); + wq->rescuer = NULL; } /* -- cgit v1.2.3-70-g09d2 From 9e8cd2f5898ab6710ad81f4583fada08bf8049a4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:04 -0700 Subject: workqueue: implement apply_workqueue_attrs() Implement apply_workqueue_attrs() which applies workqueue_attrs to the specified unbound workqueue by creating a new pwq (pool_workqueue) linked to worker_pool with the specified attributes. A new pwq is linked at the head of wq->pwqs instead of tail and __queue_work() verifies that the first unbound pwq has positive refcnt before choosing it for the actual queueing. This is to cover the case where creation of a new pwq races with queueing. As base ref on a pwq won't be dropped without making another pwq the first one, __queue_work() is guaranteed to make progress and not add work item to a dead pwq. init_and_link_pwq() is updated to return the last first pwq the new pwq replaced, which is put by apply_workqueue_attrs(). Note that apply_workqueue_attrs() is almost identical to unbound pwq part of alloc_and_link_pwqs(). The only difference is that there is no previous first pwq. apply_workqueue_attrs() is implemented to handle such cases and replaces unbound pwq handling in alloc_and_link_pwqs(). Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 2 ++ kernel/workqueue.c | 91 ++++++++++++++++++++++++++++++++++++----------- 2 files changed, 73 insertions(+), 20 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index c270b4eedf1..e152394fa7e 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -410,6 +410,8 @@ extern void destroy_workqueue(struct workqueue_struct *wq); struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask); void free_workqueue_attrs(struct workqueue_attrs *attrs); +int apply_workqueue_attrs(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 16fb6747276..2a67fbbd192 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1228,7 +1228,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, if (unlikely(wq->flags & WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; - +retry: /* pwq which will be used unless @work is executing elsewhere */ if (!(wq->flags & WQ_UNBOUND)) { if (cpu == WORK_CPU_UNBOUND) @@ -1262,6 +1262,25 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, spin_lock(&pwq->pool->lock); } + /* + * pwq is determined and locked. For unbound pools, we could have + * raced with pwq release and it could already be dead. If its + * refcnt is zero, repeat pwq selection. Note that pwqs never die + * without another pwq replacing it as the first pwq or while a + * work item is executing on it, so the retying is guaranteed to + * make forward-progress. + */ + if (unlikely(!pwq->refcnt)) { + if (wq->flags & WQ_UNBOUND) { + spin_unlock(&pwq->pool->lock); + cpu_relax(); + goto retry; + } + /* oops */ + WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", + wq->name, cpu); + } + /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); @@ -3425,7 +3444,8 @@ static void pwq_unbound_release_workfn(struct work_struct *work) static void init_and_link_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, - struct worker_pool *pool) + struct worker_pool *pool, + struct pool_workqueue **p_last_pwq) { BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK); @@ -3445,13 +3465,58 @@ static void init_and_link_pwq(struct pool_workqueue *pwq, mutex_lock(&wq->flush_mutex); spin_lock_irq(&workqueue_lock); + if (p_last_pwq) + *p_last_pwq = first_pwq(wq); pwq->work_color = wq->work_color; - list_add_tail_rcu(&pwq->pwqs_node, &wq->pwqs); + list_add_rcu(&pwq->pwqs_node, &wq->pwqs); spin_unlock_irq(&workqueue_lock); mutex_unlock(&wq->flush_mutex); } +/** + * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue + * @wq: the target workqueue + * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() + * + * Apply @attrs to an unbound workqueue @wq. If @attrs doesn't match the + * current attributes, a new pwq is created and made the first pwq which + * will serve all new work items. Older pwqs are released as in-flight + * work items finish. Note that a work item which repeatedly requeues + * itself back-to-back will stay on its current pwq. + * + * Performs GFP_KERNEL allocations. Returns 0 on success and -errno on + * failure. + */ +int apply_workqueue_attrs(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs) +{ + struct pool_workqueue *pwq, *last_pwq; + struct worker_pool *pool; + + if (WARN_ON(!(wq->flags & WQ_UNBOUND))) + return -EINVAL; + + pwq = kmem_cache_zalloc(pwq_cache, GFP_KERNEL); + if (!pwq) + return -ENOMEM; + + pool = get_unbound_pool(attrs); + if (!pool) { + kmem_cache_free(pwq_cache, pwq); + return -ENOMEM; + } + + init_and_link_pwq(pwq, wq, pool, &last_pwq); + if (last_pwq) { + spin_lock_irq(&last_pwq->pool->lock); + put_pwq(last_pwq); + spin_unlock_irq(&last_pwq->pool->lock); + } + + return 0; +} + static int alloc_and_link_pwqs(struct workqueue_struct *wq) { bool highpri = wq->flags & WQ_HIGHPRI; @@ -3468,26 +3533,12 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) struct worker_pool *cpu_pools = per_cpu(cpu_worker_pools, cpu); - init_and_link_pwq(pwq, wq, &cpu_pools[highpri]); + init_and_link_pwq(pwq, wq, &cpu_pools[highpri], NULL); } + return 0; } else { - struct pool_workqueue *pwq; - struct worker_pool *pool; - - pwq = kmem_cache_zalloc(pwq_cache, GFP_KERNEL); - if (!pwq) - return -ENOMEM; - - pool = get_unbound_pool(unbound_std_wq_attrs[highpri]); - if (!pool) { - kmem_cache_free(pwq_cache, pwq); - return -ENOMEM; - } - - init_and_link_pwq(pwq, wq, pool); + return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } - - return 0; } static int wq_clamp_max_active(int max_active, unsigned int flags, -- cgit v1.2.3-70-g09d2 From 618b01eb426dd2d73a4b5e5ebc6379e4eee3b123 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:04 -0700 Subject: workqueue: make it clear that WQ_DRAINING is an internal flag We're gonna add another internal WQ flag. Let's make the distinction clear. Prefix WQ_DRAINING with __ and move it to bit 16. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 2 +- kernel/workqueue.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index e152394fa7e..1751ec4c47c 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -294,7 +294,7 @@ enum { WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ - WQ_DRAINING = 1 << 6, /* internal: workqueue is draining */ + __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2a67fbbd192..590f4d048ec 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1225,7 +1225,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, debug_work_activate(work); /* if dying, only works from the same workqueue are allowed */ - if (unlikely(wq->flags & WQ_DRAINING) && + if (unlikely(wq->flags & __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; retry: @@ -2763,11 +2763,11 @@ void drain_workqueue(struct workqueue_struct *wq) /* * __queue_work() needs to test whether there are drainers, is much * hotter than drain_workqueue() and already looks at @wq->flags. - * Use WQ_DRAINING so that queue doesn't have to check nr_drainers. + * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. */ spin_lock_irq(&workqueue_lock); if (!wq->nr_drainers++) - wq->flags |= WQ_DRAINING; + wq->flags |= __WQ_DRAINING; spin_unlock_irq(&workqueue_lock); reflush: flush_workqueue(wq); @@ -2795,7 +2795,7 @@ reflush: spin_lock(&workqueue_lock); if (!--wq->nr_drainers) - wq->flags &= ~WQ_DRAINING; + wq->flags &= ~__WQ_DRAINING; spin_unlock(&workqueue_lock); local_irq_enable(); -- cgit v1.2.3-70-g09d2 From 8719dceae2f98a578507c0f6b49c93f320bd729c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:04 -0700 Subject: workqueue: reject adjusting max_active or applying attrs to ordered workqueues Adjusting max_active of or applying new workqueue_attrs to an ordered workqueue breaks its ordering guarantee. The former is obvious. The latter is because applying attrs creates a new pwq (pool_workqueue) and there is no ordering constraint between the old and new pwqs. Make apply_workqueue_attrs() and workqueue_set_max_active() trigger WARN_ON() if those operations are requested on an ordered workqueue and fail / ignore respectively. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 3 ++- kernel/workqueue.c | 9 +++++++++ 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 1751ec4c47c..5668ab249af 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -295,6 +295,7 @@ enum { WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ + __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ @@ -397,7 +398,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ - alloc_workqueue(fmt, WQ_UNBOUND | (flags), 1, ##args) + alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue((name), WQ_MEM_RECLAIM, 1) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 590f4d048ec..cecd4ffe2c4 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3494,9 +3494,14 @@ int apply_workqueue_attrs(struct workqueue_struct *wq, struct pool_workqueue *pwq, *last_pwq; struct worker_pool *pool; + /* only unbound workqueues can change attributes */ if (WARN_ON(!(wq->flags & WQ_UNBOUND))) return -EINVAL; + /* creating multiple pwqs breaks ordering guarantee */ + if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs))) + return -EINVAL; + pwq = kmem_cache_zalloc(pwq_cache, GFP_KERNEL); if (!pwq) return -ENOMEM; @@ -3752,6 +3757,10 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { struct pool_workqueue *pwq; + /* disallow meddling with max_active for ordered workqueues */ + if (WARN_ON(wq->flags & __WQ_ORDERED)) + return; + max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); spin_lock_irq(&workqueue_lock); -- cgit v1.2.3-70-g09d2 From 226223ab3c4118ddd10688cc2c131135848371ab Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:05 -0700 Subject: workqueue: implement sysfs interface for workqueues There are cases where workqueue users want to expose control knobs to userland. e.g. Unbound workqueues with custom attributes are scheduled to be used for writeback workers and depending on configuration it can be useful to allow admins to tinker with the priority or allowed CPUs. This patch implements workqueue_sysfs_register(), which makes the workqueue visible under /sys/bus/workqueue/devices/WQ_NAME. There currently are two attributes common to both per-cpu and unbound pools and extra attributes for unbound pools including nice level and cpumask. If alloc_workqueue*() is called with WQ_SYSFS, workqueue_sysfs_register() is called automatically as part of workqueue creation. This is the preferred method unless the workqueue user wants to apply workqueue_attrs before making the workqueue visible to userland. v2: Disallow exposing ordered workqueues as ordered workqueues can't be tuned in any way. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 8 ++ kernel/workqueue.c | 288 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 296 insertions(+) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 5668ab249af..7f6d29a417c 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -293,6 +293,7 @@ enum { 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_SYSFS = 1 << 6, /* visible in sysfs, see wq_sysfs_register() */ __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ @@ -495,4 +496,11 @@ extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ +#ifdef CONFIG_SYSFS +int workqueue_sysfs_register(struct workqueue_struct *wq); +#else /* CONFIG_SYSFS */ +static inline int workqueue_sysfs_register(struct workqueue_struct *wq) +{ return 0; } +#endif /* CONFIG_SYSFS */ + #endif diff --git a/kernel/workqueue.c b/kernel/workqueue.c index cecd4ffe2c4..c82feac0a87 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -210,6 +210,8 @@ struct wq_flusher { struct completion done; /* flush completion */ }; +struct wq_device; + /* * The externally visible workqueue abstraction is an array of * per-CPU workqueues: @@ -233,6 +235,10 @@ struct workqueue_struct { int nr_drainers; /* W: drain in progress */ int saved_max_active; /* W: saved pwq max_active */ + +#ifdef CONFIG_SYSFS + struct wq_device *wq_dev; /* I: for sysfs interface */ +#endif #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif @@ -442,6 +448,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], static DEFINE_IDR(worker_pool_idr); static int worker_thread(void *__worker); +static void copy_workqueue_attrs(struct workqueue_attrs *to, + const struct workqueue_attrs *from); /* allocate ID and assign it to @pool */ static int worker_pool_assign_id(struct worker_pool *pool) @@ -3153,6 +3161,281 @@ int keventd_up(void) return system_wq != NULL; } +#ifdef CONFIG_SYSFS +/* + * Workqueues with WQ_SYSFS flag set is visible to userland via + * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the + * following attributes. + * + * per_cpu RO bool : whether the workqueue is per-cpu or unbound + * max_active RW int : maximum number of in-flight work items + * + * Unbound workqueues have the following extra attributes. + * + * id RO int : the associated pool ID + * nice RW int : nice value of the workers + * cpumask RW mask : bitmask of allowed CPUs for the workers + */ +struct wq_device { + struct workqueue_struct *wq; + struct device dev; +}; + +static struct workqueue_struct *dev_to_wq(struct device *dev) +{ + struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); + + return wq_dev->wq; +} + +static ssize_t wq_per_cpu_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + + return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); +} + +static ssize_t wq_max_active_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + + return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); +} + +static ssize_t wq_max_active_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int val; + + if (sscanf(buf, "%d", &val) != 1 || val <= 0) + return -EINVAL; + + workqueue_set_max_active(wq, val); + return count; +} + +static struct device_attribute wq_sysfs_attrs[] = { + __ATTR(per_cpu, 0444, wq_per_cpu_show, NULL), + __ATTR(max_active, 0644, wq_max_active_show, wq_max_active_store), + __ATTR_NULL, +}; + +static ssize_t wq_pool_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct worker_pool *pool; + int written; + + rcu_read_lock_sched(); + pool = first_pwq(wq)->pool; + written = scnprintf(buf, PAGE_SIZE, "%d\n", pool->id); + rcu_read_unlock_sched(); + + return written; +} + +static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int written; + + rcu_read_lock_sched(); + written = scnprintf(buf, PAGE_SIZE, "%d\n", + first_pwq(wq)->pool->attrs->nice); + rcu_read_unlock_sched(); + + return written; +} + +/* prepare workqueue_attrs for sysfs store operations */ +static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) +{ + struct workqueue_attrs *attrs; + + attrs = alloc_workqueue_attrs(GFP_KERNEL); + if (!attrs) + return NULL; + + rcu_read_lock_sched(); + copy_workqueue_attrs(attrs, first_pwq(wq)->pool->attrs); + rcu_read_unlock_sched(); + return attrs; +} + +static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct workqueue_attrs *attrs; + int ret; + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + return -ENOMEM; + + if (sscanf(buf, "%d", &attrs->nice) == 1 && + attrs->nice >= -20 && attrs->nice <= 19) + ret = apply_workqueue_attrs(wq, attrs); + else + ret = -EINVAL; + + free_workqueue_attrs(attrs); + return ret ?: count; +} + +static ssize_t wq_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int written; + + rcu_read_lock_sched(); + written = cpumask_scnprintf(buf, PAGE_SIZE, + first_pwq(wq)->pool->attrs->cpumask); + rcu_read_unlock_sched(); + + written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); + return written; +} + +static ssize_t wq_cpumask_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct workqueue_attrs *attrs; + int ret; + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + return -ENOMEM; + + ret = cpumask_parse(buf, attrs->cpumask); + if (!ret) + ret = apply_workqueue_attrs(wq, attrs); + + free_workqueue_attrs(attrs); + return ret ?: count; +} + +static struct device_attribute wq_sysfs_unbound_attrs[] = { + __ATTR(pool_id, 0444, wq_pool_id_show, NULL), + __ATTR(nice, 0644, wq_nice_show, wq_nice_store), + __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), + __ATTR_NULL, +}; + +static struct bus_type wq_subsys = { + .name = "workqueue", + .dev_attrs = wq_sysfs_attrs, +}; + +static int __init wq_sysfs_init(void) +{ + return subsys_virtual_register(&wq_subsys, NULL); +} +core_initcall(wq_sysfs_init); + +static void wq_device_release(struct device *dev) +{ + struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); + + kfree(wq_dev); +} + +/** + * workqueue_sysfs_register - make a workqueue visible in sysfs + * @wq: the workqueue to register + * + * Expose @wq in sysfs under /sys/bus/workqueue/devices. + * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set + * which is the preferred method. + * + * Workqueue user should use this function directly iff it wants to apply + * workqueue_attrs before making the workqueue visible in sysfs; otherwise, + * apply_workqueue_attrs() may race against userland updating the + * attributes. + * + * Returns 0 on success, -errno on failure. + */ +int workqueue_sysfs_register(struct workqueue_struct *wq) +{ + struct wq_device *wq_dev; + int ret; + + /* + * Adjusting max_active or creating new pwqs by applyting + * attributes breaks ordering guarantee. Disallow exposing ordered + * workqueues. + */ + if (WARN_ON(wq->flags & __WQ_ORDERED)) + return -EINVAL; + + wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); + if (!wq_dev) + return -ENOMEM; + + wq_dev->wq = wq; + wq_dev->dev.bus = &wq_subsys; + wq_dev->dev.init_name = wq->name; + wq_dev->dev.release = wq_device_release; + + /* + * unbound_attrs are created separately. Suppress uevent until + * everything is ready. + */ + dev_set_uevent_suppress(&wq_dev->dev, true); + + ret = device_register(&wq_dev->dev); + if (ret) { + kfree(wq_dev); + wq->wq_dev = NULL; + return ret; + } + + if (wq->flags & WQ_UNBOUND) { + struct device_attribute *attr; + + for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { + ret = device_create_file(&wq_dev->dev, attr); + if (ret) { + device_unregister(&wq_dev->dev); + wq->wq_dev = NULL; + return ret; + } + } + } + + kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); + return 0; +} + +/** + * workqueue_sysfs_unregister - undo workqueue_sysfs_register() + * @wq: the workqueue to unregister + * + * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. + */ +static void workqueue_sysfs_unregister(struct workqueue_struct *wq) +{ + struct wq_device *wq_dev = wq->wq_dev; + + if (!wq->wq_dev) + return; + + wq->wq_dev = NULL; + device_unregister(&wq_dev->dev); +} +#else /* CONFIG_SYSFS */ +static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } +#endif /* CONFIG_SYSFS */ + /** * free_workqueue_attrs - free a workqueue_attrs * @attrs: workqueue_attrs to free @@ -3625,6 +3908,9 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, wake_up_process(rescuer->task); } + if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) + goto err_destroy; + /* * workqueue_lock protects global freeze state and workqueues * list. Grab it, set max_active accordingly and add the new @@ -3693,6 +3979,8 @@ void destroy_workqueue(struct workqueue_struct *wq) spin_unlock_irq(&workqueue_lock); + workqueue_sysfs_unregister(wq); + if (wq->rescuer) { kthread_stop(wq->rescuer->task); kfree(wq->rescuer); -- cgit v1.2.3-70-g09d2 From e62676169118bc2d42e5008b3f8872646313f077 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 17:41:37 -0700 Subject: workqueue: implement current_is_workqueue_rescuer() Implement a function which queries whether it currently is running off a workqueue rescuer. This will be used to convert writeback to workqueue. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 1 + kernel/workqueue.c | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 7f6d29a417c..df30763c868 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -451,6 +451,7 @@ extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); +extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c82feac0a87..f5c8bbb9ada 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4071,6 +4071,19 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) } EXPORT_SYMBOL_GPL(workqueue_set_max_active); +/** + * current_is_workqueue_rescuer - is %current workqueue rescuer? + * + * Determine whether %current is a workqueue rescuer. Can be used from + * work functions to determine whether it's being run off the rescuer task. + */ +bool current_is_workqueue_rescuer(void) +{ + struct worker *worker = current_wq_worker(); + + return worker && worker == worker->current_pwq->wq->rescuer; +} + /** * workqueue_congested - test whether a workqueue is congested * @cpu: CPU in question -- cgit v1.2.3-70-g09d2 From 8425e3d5bdbe8e741d2c73cf3189ed59b4038b84 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 13 Mar 2013 16:51:36 -0700 Subject: workqueue: inline trivial wrappers There's no reason to make these trivial wrappers full (exported) functions. Inline the followings. queue_work() queue_delayed_work() mod_delayed_work() schedule_work_on() schedule_work() schedule_delayed_work_on() schedule_delayed_work() keventd_up() Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 123 +++++++++++++++++++++++++++++++++++++++++----- kernel/workqueue.c | 111 ----------------------------------------- 2 files changed, 111 insertions(+), 123 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index df30763c868..835d12b7696 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -417,28 +417,16 @@ int apply_workqueue_attrs(struct workqueue_struct *wq, extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); -extern bool queue_work(struct workqueue_struct *wq, struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); -extern bool queue_delayed_work(struct workqueue_struct *wq, - struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); -extern bool mod_delayed_work(struct workqueue_struct *wq, - struct delayed_work *dwork, unsigned long delay); extern void flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern void flush_scheduled_work(void); -extern bool schedule_work_on(int cpu, struct work_struct *work); -extern bool schedule_work(struct work_struct *work); -extern bool schedule_delayed_work_on(int cpu, struct delayed_work *work, - unsigned long delay); -extern bool schedule_delayed_work(struct delayed_work *work, - unsigned long delay); extern int schedule_on_each_cpu(work_func_t func); -extern int keventd_up(void); int execute_in_process_context(work_func_t fn, struct execute_work *); @@ -455,6 +443,117 @@ extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); +/** + * queue_work - queue work on a workqueue + * @wq: workqueue to use + * @work: work to queue + * + * Returns %false if @work was already on a queue, %true otherwise. + * + * We queue the work to the CPU on which it was submitted, but if the CPU dies + * it can be processed by another CPU. + */ +static inline bool queue_work(struct workqueue_struct *wq, + struct work_struct *work) +{ + return queue_work_on(WORK_CPU_UNBOUND, wq, work); +} + +/** + * queue_delayed_work - queue work on a workqueue after delay + * @wq: workqueue to use + * @dwork: delayable work to queue + * @delay: number of jiffies to wait before queueing + * + * Equivalent to queue_delayed_work_on() but tries to use the local CPU. + */ +static inline bool queue_delayed_work(struct workqueue_struct *wq, + struct delayed_work *dwork, + unsigned long delay) +{ + return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); +} + +/** + * mod_delayed_work - modify delay of or queue a delayed work + * @wq: workqueue to use + * @dwork: work to queue + * @delay: number of jiffies to wait before queueing + * + * mod_delayed_work_on() on local CPU. + */ +static inline bool mod_delayed_work(struct workqueue_struct *wq, + struct delayed_work *dwork, + unsigned long delay) +{ + return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); +} + +/** + * schedule_work_on - put work task on a specific cpu + * @cpu: cpu to put the work task on + * @work: job to be done + * + * This puts a job on a specific cpu + */ +static inline bool schedule_work_on(int cpu, struct work_struct *work) +{ + return queue_work_on(cpu, system_wq, work); +} + +/** + * schedule_work - put work task in global workqueue + * @work: job to be done + * + * Returns %false if @work was already on the kernel-global workqueue and + * %true otherwise. + * + * This puts a job in the kernel-global workqueue if it was not already + * queued and leaves it in the same position on the kernel-global + * workqueue otherwise. + */ +static inline bool schedule_work(struct work_struct *work) +{ + return queue_work(system_wq, work); +} + +/** + * schedule_delayed_work_on - queue work in global workqueue on CPU after delay + * @cpu: cpu to use + * @dwork: job to be done + * @delay: number of jiffies to wait + * + * After waiting for a given time this puts a job in the kernel-global + * workqueue on the specified CPU. + */ +static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, + unsigned long delay) +{ + return queue_delayed_work_on(cpu, system_wq, dwork, delay); +} + +/** + * schedule_delayed_work - put work task in global workqueue after delay + * @dwork: job to be done + * @delay: number of jiffies to wait or 0 for immediate execution + * + * After waiting for a given time this puts a job in the kernel-global + * workqueue. + */ +static inline bool schedule_delayed_work(struct delayed_work *dwork, + unsigned long delay) +{ + return queue_delayed_work(system_wq, dwork, delay); +} + +/** + * keventd_up - is workqueue initialized yet? + */ +static inline bool keventd_up(void) +{ + return system_wq != NULL; +} + /* * Like above, but uses del_timer() instead of del_timer_sync(). This means, * if it returns 0 the timer function may be running and the queueing is in diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 147fc5a784f..f37421fb4f3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1340,22 +1340,6 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL_GPL(queue_work_on); -/** - * queue_work - queue work on a workqueue - * @wq: workqueue to use - * @work: work to queue - * - * Returns %false if @work was already on a queue, %true otherwise. - * - * We queue the work to the CPU on which it was submitted, but if the CPU dies - * it can be processed by another CPU. - */ -bool queue_work(struct workqueue_struct *wq, struct work_struct *work) -{ - return queue_work_on(WORK_CPU_UNBOUND, wq, work); -} -EXPORT_SYMBOL_GPL(queue_work); - void delayed_work_timer_fn(unsigned long __data) { struct delayed_work *dwork = (struct delayed_work *)__data; @@ -1430,21 +1414,6 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL_GPL(queue_delayed_work_on); -/** - * queue_delayed_work - queue work on a workqueue after delay - * @wq: workqueue to use - * @dwork: delayable work to queue - * @delay: number of jiffies to wait before queueing - * - * Equivalent to queue_delayed_work_on() but tries to use the local CPU. - */ -bool queue_delayed_work(struct workqueue_struct *wq, - struct delayed_work *dwork, unsigned long delay) -{ - return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); -} -EXPORT_SYMBOL_GPL(queue_delayed_work); - /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU * @cpu: CPU number to execute work on @@ -1483,21 +1452,6 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL_GPL(mod_delayed_work_on); -/** - * mod_delayed_work - modify delay of or queue a delayed work - * @wq: workqueue to use - * @dwork: work to queue - * @delay: number of jiffies to wait before queueing - * - * mod_delayed_work_on() on local CPU. - */ -bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, - unsigned long delay) -{ - return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); -} -EXPORT_SYMBOL_GPL(mod_delayed_work); - /** * worker_enter_idle - enter idle state * @worker: worker which is entering idle state @@ -3001,66 +2955,6 @@ bool cancel_delayed_work_sync(struct delayed_work *dwork) } EXPORT_SYMBOL(cancel_delayed_work_sync); -/** - * schedule_work_on - put work task on a specific cpu - * @cpu: cpu to put the work task on - * @work: job to be done - * - * This puts a job on a specific cpu - */ -bool schedule_work_on(int cpu, struct work_struct *work) -{ - return queue_work_on(cpu, system_wq, work); -} -EXPORT_SYMBOL(schedule_work_on); - -/** - * schedule_work - put work task in global workqueue - * @work: job to be done - * - * Returns %false if @work was already on the kernel-global workqueue and - * %true otherwise. - * - * This puts a job in the kernel-global workqueue if it was not already - * queued and leaves it in the same position on the kernel-global - * workqueue otherwise. - */ -bool schedule_work(struct work_struct *work) -{ - return queue_work(system_wq, work); -} -EXPORT_SYMBOL(schedule_work); - -/** - * schedule_delayed_work_on - queue work in global workqueue on CPU after delay - * @cpu: cpu to use - * @dwork: job to be done - * @delay: number of jiffies to wait - * - * After waiting for a given time this puts a job in the kernel-global - * workqueue on the specified CPU. - */ -bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, - unsigned long delay) -{ - return queue_delayed_work_on(cpu, system_wq, dwork, delay); -} -EXPORT_SYMBOL(schedule_delayed_work_on); - -/** - * schedule_delayed_work - put work task in global workqueue after delay - * @dwork: job to be done - * @delay: number of jiffies to wait or 0 for immediate execution - * - * After waiting for a given time this puts a job in the kernel-global - * workqueue. - */ -bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) -{ - return queue_delayed_work(system_wq, dwork, delay); -} -EXPORT_SYMBOL(schedule_delayed_work); - /** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call @@ -3154,11 +3048,6 @@ int execute_in_process_context(work_func_t fn, struct execute_work *ew) } EXPORT_SYMBOL_GPL(execute_in_process_context); -int keventd_up(void) -{ - return system_wq != NULL; -} - #ifdef CONFIG_SYSFS /* * Workqueues with WQ_SYSFS flag set is visible to userland via -- cgit v1.2.3-70-g09d2 From d55262c4d164759a8debe772da6c9b16059dec47 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 1 Apr 2013 11:23:38 -0700 Subject: workqueue: update sysfs interface to reflect NUMA awareness and a kernel param to disable NUMA affinity Unbound workqueues are now NUMA aware. Let's add some control knobs and update sysfs interface accordingly. * Add kernel param workqueue.numa_disable which disables NUMA affinity globally. * Replace sysfs file "pool_id" with "pool_ids" which contain node:pool_id pairs. This change is userland-visible but "pool_id" hasn't seen a release yet, so this is okay. * Add a new sysf files "numa" which can toggle NUMA affinity on individual workqueues. This is implemented as attrs->no_numa whichn is special in that it isn't part of a pool's attributes. It only affects how apply_workqueue_attrs() picks which pools to use. After "pool_ids" change, first_pwq() doesn't have any user left. Removed. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- Documentation/kernel-parameters.txt | 9 ++++ include/linux/workqueue.h | 5 +++ kernel/workqueue.c | 82 ++++++++++++++++++++++++++----------- 3 files changed, 73 insertions(+), 23 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 4609e81dbc3..c75ea0b8ec5 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3222,6 +3222,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted. or other driver-specific files in the Documentation/watchdog/ directory. + workqueue.disable_numa + By default, all work items queued to unbound + workqueues are affine to the NUMA nodes they're + issued on, which results in better behavior in + general. If NUMA affinity needs to be disabled for + whatever reason, this option can be used. Note + that this also can be controlled per-workqueue for + workqueues visible under /sys/bus/workqueue/. + x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of default x2apic cluster mode on platforms supporting x2apic. diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 835d12b7696..71797563937 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -119,10 +119,15 @@ struct delayed_work { /* * A struct for workqueue attributes. This can be used to change * attributes of an unbound workqueue. + * + * Unlike other fields, ->no_numa isn't a property of a worker_pool. It + * only modifies how apply_workqueue_attrs() select pools and thus doesn't + * participate in pool hash calculations or equality comparisons. */ struct workqueue_attrs { int nice; /* nice level */ cpumask_var_t cpumask; /* allowed CPUs */ + bool no_numa; /* disable NUMA affinity */ }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 57cd77de4a4..729ac6a4486 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -268,6 +268,9 @@ static int wq_numa_tbl_len; /* highest possible NUMA node id + 1 */ static cpumask_var_t *wq_numa_possible_cpumask; /* possible CPUs of each node */ +static bool wq_disable_numa; +module_param_named(disable_numa, wq_disable_numa, bool, 0444); + static bool wq_numa_enabled; /* unbound NUMA affinity enabled */ /* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */ @@ -516,21 +519,6 @@ static int worker_pool_assign_id(struct worker_pool *pool) return ret; } -/** - * first_pwq - return the first pool_workqueue of the specified workqueue - * @wq: the target workqueue - * - * This must be called either with wq->mutex held or sched RCU read locked. - * If the pwq needs to be used beyond the locking in effect, the caller is - * responsible for guaranteeing that the pwq stays online. - */ -static struct pool_workqueue *first_pwq(struct workqueue_struct *wq) -{ - assert_rcu_or_wq_mutex(wq); - return list_first_or_null_rcu(&wq->pwqs, struct pool_workqueue, - pwqs_node); -} - /** * unbound_pwq_by_node - return the unbound pool_workqueue for the given node * @wq: the target workqueue @@ -3114,16 +3102,21 @@ static struct device_attribute wq_sysfs_attrs[] = { __ATTR_NULL, }; -static ssize_t wq_pool_id_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t wq_pool_ids_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); - struct worker_pool *pool; - int written; + const char *delim = ""; + int node, written = 0; rcu_read_lock_sched(); - pool = first_pwq(wq)->pool; - written = scnprintf(buf, PAGE_SIZE, "%d\n", pool->id); + for_each_node(node) { + written += scnprintf(buf + written, PAGE_SIZE - written, + "%s%d:%d", delim, node, + unbound_pwq_by_node(wq, node)->pool->id); + delim = " "; + } + written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); rcu_read_unlock_sched(); return written; @@ -3212,10 +3205,46 @@ static ssize_t wq_cpumask_store(struct device *dev, return ret ?: count; } +static ssize_t wq_numa_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int written; + + mutex_lock(&wq->mutex); + written = scnprintf(buf, PAGE_SIZE, "%d\n", + !wq->unbound_attrs->no_numa); + mutex_unlock(&wq->mutex); + + return written; +} + +static ssize_t wq_numa_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct workqueue_attrs *attrs; + int v, ret; + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + return -ENOMEM; + + ret = -EINVAL; + if (sscanf(buf, "%d", &v) == 1) { + attrs->no_numa = !v; + ret = apply_workqueue_attrs(wq, attrs); + } + + free_workqueue_attrs(attrs); + return ret ?: count; +} + static struct device_attribute wq_sysfs_unbound_attrs[] = { - __ATTR(pool_id, 0444, wq_pool_id_show, NULL), + __ATTR(pool_ids, 0444, wq_pool_ids_show, NULL), __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), + __ATTR(numa, 0644, wq_numa_show, wq_numa_store), __ATTR_NULL, }; @@ -3750,7 +3779,7 @@ static void free_unbound_pwq(struct pool_workqueue *pwq) static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node, int cpu_going_down, cpumask_t *cpumask) { - if (!wq_numa_enabled) + if (!wq_numa_enabled || attrs->no_numa) goto use_dfl; /* does @node have any online CPUs @attrs wants? */ @@ -3951,6 +3980,8 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, cpumask = target_attrs->cpumask; mutex_lock(&wq->mutex); + if (wq->unbound_attrs->no_numa) + goto out_unlock; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); pwq = unbound_pwq_by_node(wq, node); @@ -4763,6 +4794,11 @@ static void __init wq_numa_init(void) if (num_possible_nodes() <= 1) return; + if (wq_disable_numa) { + pr_info("workqueue: NUMA affinity support disabled\n"); + return; + } + wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(GFP_KERNEL); BUG_ON(!wq_update_unbound_numa_attrs_buf); -- cgit v1.2.3-70-g09d2 From 3d1cb2059d9374e58da481b783332cf191cb6620 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 30 Apr 2013 15:27:22 -0700 Subject: workqueue: include workqueue info when printing debug dump of a worker task One of the problems that arise when converting dedicated custom threadpool to workqueue is that the shared worker pool used by workqueue anonimizes each worker making it more difficult to identify what the worker was doing on which target from the output of sysrq-t or debug dump from oops, BUG() and friends. This patch implements set_worker_desc() which can be called from any workqueue work function to set its description. When the worker task is dumped for whatever reason - sysrq-t, WARN, BUG, oops, lockdep assertion and so on - the description will be printed out together with the workqueue name and the worker function pointer. The printing side is implemented by print_worker_info() which is called from functions in task dump paths - sched_show_task() and dump_stack_print_info(). print_worker_info() can be safely called on any task in any state as long as the task struct itself is accessible. It uses probe_*() functions to access worker fields. It may print garbage if something went very wrong, but it wouldn't cause (another) oops. The description is currently limited to 24bytes including the terminating \0. worker->desc_valid and workder->desc[] are added and the 64 bytes marker which was already incorrect before adding the new fields is moved to the correct position. Here's an example dump with writeback updated to set the bdi name as worker desc. Hardware name: Bochs Modules linked in: Pid: 7, comm: kworker/u9:0 Not tainted 3.9.0-rc1-work+ #1 Workqueue: writeback bdi_writeback_workfn (flush-8:0) ffffffff820a3ab0 ffff88000f6e9cb8 ffffffff81c61845 ffff88000f6e9cf8 ffffffff8108f50f 0000000000000000 0000000000000000 ffff88000cde16b0 ffff88000cde1aa8 ffff88001ee19240 ffff88000f6e9fd8 ffff88000f6e9d08 Call Trace: [] dump_stack+0x19/0x1b [] warn_slowpath_common+0x7f/0xc0 [] warn_slowpath_null+0x1a/0x20 [] bdi_writeback_workfn+0x2a0/0x3b0 ... Signed-off-by: Tejun Heo Cc: Peter Zijlstra Cc: Ingo Molnar Acked-by: Jan Kara Cc: Oleg Nesterov Cc: Jens Axboe Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/workqueue.h | 5 +++ kernel/printk.c | 2 ++ kernel/sched/core.c | 1 + kernel/workqueue.c | 79 +++++++++++++++++++++++++++++++++++++++++++++ kernel/workqueue_internal.h | 12 ++++++- 5 files changed, 98 insertions(+), 1 deletion(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 71797563937..623488fdc1f 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -92,6 +92,9 @@ enum { /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, + + /* maximum string length for set_worker_desc() */ + WORKER_DESC_LEN = 24, }; struct work_struct { @@ -447,6 +450,8 @@ extern void workqueue_set_max_active(struct workqueue_struct *wq, extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); +extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); +extern void print_worker_info(const char *log_lvl, struct task_struct *task); /** * queue_work - queue work on a workqueue diff --git a/kernel/printk.c b/kernel/printk.c index e10ad515901..96dcfcd9a2d 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -2891,6 +2891,8 @@ void dump_stack_print_info(const char *log_lvl) if (dump_stack_arch_desc_str[0] != '\0') printk("%sHardware name: %s\n", log_lvl, dump_stack_arch_desc_str); + + print_worker_info(log_lvl, current); } /** diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c70a8814a76..5662f58f0b6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4586,6 +4586,7 @@ void sched_show_task(struct task_struct *p) task_pid_nr(p), ppid, (unsigned long)task_thread_info(p)->flags); + print_worker_info(KERN_INFO, p); show_stack(p, NULL); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 154aa12af48..4aa9f5bc6b2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -46,6 +46,7 @@ #include #include #include +#include #include "workqueue_internal.h" @@ -2197,6 +2198,7 @@ __acquires(&pool->lock) worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; + worker->desc_valid = false; pwq_dec_nr_in_flight(pwq, work_color); } @@ -4365,6 +4367,83 @@ unsigned int work_busy(struct work_struct *work) } EXPORT_SYMBOL_GPL(work_busy); +/** + * set_worker_desc - set description for the current work item + * @fmt: printf-style format string + * @...: arguments for the format string + * + * This function can be called by a running work function to describe what + * the work item is about. If the worker task gets dumped, this + * information will be printed out together to help debugging. The + * description can be at most WORKER_DESC_LEN including the trailing '\0'. + */ +void set_worker_desc(const char *fmt, ...) +{ + struct worker *worker = current_wq_worker(); + va_list args; + + if (worker) { + va_start(args, fmt); + vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); + va_end(args); + worker->desc_valid = true; + } +} + +/** + * print_worker_info - print out worker information and description + * @log_lvl: the log level to use when printing + * @task: target task + * + * If @task is a worker and currently executing a work item, print out the + * name of the workqueue being serviced and worker description set with + * set_worker_desc() by the currently executing work item. + * + * This function can be safely called on any task as long as the + * task_struct itself is accessible. While safe, this function isn't + * synchronized and may print out mixups or garbages of limited length. + */ +void print_worker_info(const char *log_lvl, struct task_struct *task) +{ + work_func_t *fn = NULL; + char name[WQ_NAME_LEN] = { }; + char desc[WORKER_DESC_LEN] = { }; + struct pool_workqueue *pwq = NULL; + struct workqueue_struct *wq = NULL; + bool desc_valid = false; + struct worker *worker; + + if (!(task->flags & PF_WQ_WORKER)) + return; + + /* + * This function is called without any synchronization and @task + * could be in any state. Be careful with dereferences. + */ + worker = probe_kthread_data(task); + + /* + * Carefully copy the associated workqueue's workfn and name. Keep + * the original last '\0' in case the original contains garbage. + */ + probe_kernel_read(&fn, &worker->current_func, sizeof(fn)); + probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq)); + probe_kernel_read(&wq, &pwq->wq, sizeof(wq)); + probe_kernel_read(name, wq->name, sizeof(name) - 1); + + /* copy worker description */ + probe_kernel_read(&desc_valid, &worker->desc_valid, sizeof(desc_valid)); + if (desc_valid) + probe_kernel_read(desc, worker->desc, sizeof(desc) - 1); + + if (fn || name[0] || desc[0]) { + printk("%sWorkqueue: %s %pf", log_lvl, name, fn); + if (desc[0]) + pr_cont(" (%s)", desc); + pr_cont("\n"); + } +} + /* * CPU hotplug. * diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 84ab6e1dc6f..ad83c96b2ec 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -29,15 +29,25 @@ struct worker { struct work_struct *current_work; /* L: work being processed */ work_func_t current_func; /* L: current_work's fn */ struct pool_workqueue *current_pwq; /* L: current_work's pwq */ + bool desc_valid; /* ->desc is valid */ struct list_head scheduled; /* L: scheduled works */ + + /* 64 bytes boundary on 64bit, 32 on 32bit */ + struct task_struct *task; /* I: worker task */ struct worker_pool *pool; /* I: the associated pool */ /* L: for rescuers */ - /* 64 bytes boundary on 64bit, 32 on 32bit */ + unsigned long last_active; /* L: last active timestamp */ unsigned int flags; /* X: flags */ int id; /* I: worker id */ + /* + * Opaque string set with work_set_desc(). Printed out with task + * dump for debugging - WARN, BUG, panic or sysrq. + */ + char desc[WORKER_DESC_LEN]; + /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ }; -- cgit v1.2.3-70-g09d2