--- zzzz-none-000/linux-3.10.107/kernel/workqueue.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/kernel/workqueue.c 2021-02-04 17:41:59.000000000 +0000 @@ -16,9 +16,10 @@ * * 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. + * automatically managed. There are two worker pools for each CPU (one for + * normal work items and the other for high priority ones) and some extra + * pools for workqueues which are not bound to any specific CPU - the + * number of these backing pools is dynamic. * * Please read Documentation/workqueue.txt for details. */ @@ -47,6 +48,9 @@ #include #include #include +#if defined(CONFIG_AVM_SIMPLE_PROFILING) +#include +#endif /*--- #if defined(CONFIG_AVM_SIMPLE_PROFILING) ---*/ #include "workqueue_internal.h" @@ -64,15 +68,12 @@ * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED should be flipped only while holding - * manager_mutex to avoid changing binding state while - * create_worker() is in progress. + * attach_mutex to avoid changing binding state while + * worker_attach_to_pool() is in progress. */ - POOL_MANAGE_WORKERS = 1 << 0, /* need to manage workers */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ - POOL_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 */ @@ -99,10 +100,10 @@ /* * Rescue workers are used only on emergencies and shared by - * all cpus. Give -20. + * all cpus. Give MIN_NICE. */ - RESCUER_NICE_LEVEL = -20, - HIGHPRI_NICE_LEVEL = -20, + RESCUER_NICE_LEVEL = MIN_NICE, + HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 24, }; @@ -123,13 +124,17 @@ * cpu or grabbing pool->lock is enough for read access. If * POOL_DISASSOCIATED is set, it's identical to L. * - * MG: pool->manager_mutex and pool->lock protected. Writes require both - * locks. Reads can happen under either lock. + * A: pool->attach_mutex protected. * * PL: wq_pool_mutex protected. * * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. * + * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. + * + * PWR: wq_pool_mutex and wq->mutex protected for writes. Either or + * sched-RCU for reads. + * * WQ: wq->mutex protected. * * WR: wq->mutex protected for writes. Sched-RCU protected for reads. @@ -162,8 +167,12 @@ /* see manage_workers() for details on the two manager mutexes */ struct mutex manager_arb; /* manager arbitration */ - struct mutex manager_mutex; /* manager exclusion */ - struct idr worker_idr; /* MG: worker IDs and iteration */ + struct worker *manager; /* L: purely informational */ + struct mutex attach_mutex; /* attach/detach exclusion */ + struct list_head workers; /* A: attached workers */ + struct completion *detach_completion; /* all workers detached */ + + struct ida worker_ida; /* worker IDs for task name */ struct workqueue_attrs *attrs; /* I: worker attributes */ struct hlist_node hash_node; /* PL: unbound_pool_hash node */ @@ -230,7 +239,7 @@ */ struct workqueue_struct { struct list_head pwqs; /* WR: all pwqs of this wq */ - struct list_head list; /* PL: list of all workqueues */ + struct list_head list; /* PR: list of all workqueues */ struct mutex mutex; /* protects this wq */ int work_color; /* WQ: current work color */ @@ -246,8 +255,8 @@ int nr_drainers; /* WQ: drain in progress */ int saved_max_active; /* WQ: saved pwq max_active */ - struct workqueue_attrs *unbound_attrs; /* WQ: only for unbound wqs */ - struct pool_workqueue *dfl_pwq; /* WQ: only for unbound wqs */ + struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ + struct pool_workqueue *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ @@ -257,21 +266,31 @@ #endif char name[WQ_NAME_LEN]; /* I: workqueue name */ + /* + * Destruction of workqueue_struct is sched-RCU protected to allow + * walking the workqueues list without grabbing wq_pool_mutex. + * This is used to dump all workqueues from sysrq. + */ + struct rcu_head rcu; + /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __percpu *cpu_pwqs; /* I: per-cpu pwqs */ - struct pool_workqueue __rcu *numa_pwq_tbl[]; /* FR: unbound pwqs indexed by node */ + struct pool_workqueue __rcu *numa_pwq_tbl[]; /* PWR: unbound pwqs indexed by node */ }; static struct kmem_cache *pwq_cache; -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); +/* see the comment above the definition of WQ_POWER_EFFICIENT */ +static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); +module_param_named(power_efficient, wq_power_efficient, bool, 0444); + static bool wq_numa_enabled; /* unbound NUMA affinity enabled */ /* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */ @@ -280,9 +299,11 @@ static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ -static LIST_HEAD(workqueues); /* PL: list of all workqueues */ +static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ +static cpumask_var_t wq_unbound_cpumask; /* PL: low level cpumask for all unbound wqs */ + /* the per-cpu worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); @@ -308,33 +329,32 @@ EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_freezable_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_wq); +struct workqueue_struct *system_power_efficient_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_power_efficient_wq); +struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); static int worker_thread(void *__worker); -static void copy_workqueue_attrs(struct workqueue_attrs *to, - const struct workqueue_attrs *from); +static void workqueue_sysfs_unregister(struct workqueue_struct *wq); #define CREATE_TRACE_POINTS #include #define assert_rcu_or_pool_mutex() \ - rcu_lockdep_assert(rcu_read_lock_sched_held() || \ - lockdep_is_held(&wq_pool_mutex), \ - "sched RCU or wq_pool_mutex should be held") + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + !lockdep_is_held(&wq_pool_mutex), \ + "sched RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex(wq) \ - rcu_lockdep_assert(rcu_read_lock_sched_held() || \ - lockdep_is_held(&wq->mutex), \ - "sched RCU or wq->mutex should be held") - -#ifdef CONFIG_LOCKDEP -#define assert_manager_or_pool_lock(pool) \ - WARN_ONCE(debug_locks && \ - !lockdep_is_held(&(pool)->manager_mutex) && \ - !lockdep_is_held(&(pool)->lock), \ - "pool->manager_mutex or ->lock should be held") -#else -#define assert_manager_or_pool_lock(pool) do { } while (0) -#endif + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + !lockdep_is_held(&wq->mutex), \ + "sched RCU or wq->mutex should be held") + +#define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + !lockdep_is_held(&wq->mutex) && \ + !lockdep_is_held(&wq_pool_mutex), \ + "sched RCU, wq->mutex or wq_pool_mutex should be held") #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ @@ -361,17 +381,16 @@ /** * for_each_pool_worker - iterate through all workers of a worker_pool * @worker: iteration cursor - * @wi: integer used for iteration * @pool: worker_pool to iterate workers of * - * This must be called with either @pool->manager_mutex or ->lock held. + * This must be called with @pool->attach_mutex. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ -#define for_each_pool_worker(worker, wi, pool) \ - idr_for_each_entry(&(pool)->worker_idr, (worker), (wi)) \ - if (({ assert_manager_or_pool_lock((pool)); false; })) { } \ +#define for_each_pool_worker(worker, pool) \ + list_for_each_entry((worker), &(pool)->workers, node) \ + if (({ lockdep_assert_held(&pool->attach_mutex); false; })) { } \ else /** @@ -502,19 +521,33 @@ } EXPORT_SYMBOL_GPL(destroy_work_on_stack); +void destroy_delayed_work_on_stack(struct delayed_work *work) +{ + destroy_timer_on_stack(&work->timer); + debug_object_free(&work->work, &work_debug_descr); +} +EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); + #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif -/* allocate ID and assign it to @pool */ +/** + * worker_pool_assign_id - allocate ID and assing it to @pool + * @pool: the pool pointer of interest + * + * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned + * successfully, -errno on failure. + */ static int worker_pool_assign_id(struct worker_pool *pool) { int ret; lockdep_assert_held(&wq_pool_mutex); - ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL); + ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, + GFP_KERNEL); if (ret >= 0) { pool->id = ret; return 0; @@ -527,14 +560,27 @@ * @wq: the target workqueue * @node: the node ID * - * This must be called either with pwq_lock held or sched RCU read locked. + * This must be called with any of wq_pool_mutex, wq->mutex 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. + * + * Return: The unbound pool_workqueue for @node. */ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq, int node) { - assert_rcu_or_wq_mutex(wq); + assert_rcu_or_wq_mutex_or_pool_mutex(wq); + + /* + * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a + * delayed item is pending. The plan is to keep CPU -> NODE + * mapping valid and stable across CPU on/offlines. Once that + * happens, this workaround can be removed. + */ + if (unlikely(node == NUMA_NO_NODE)) + return wq->dfl_pwq; + return rcu_dereference_raw(wq->numa_pwq_tbl[node]); } @@ -657,8 +703,6 @@ * get_work_pool - return the worker_pool a given work was associated with * @work: the work item of interest * - * Return the worker_pool @work was last associated with. %NULL if none. - * * Pools are created and destroyed under wq_pool_mutex, and allows read * access under sched-RCU read lock. As such, this function should be * called under wq_pool_mutex or with preemption disabled. @@ -667,6 +711,8 @@ * mentioned locking is in effect. If the returned pool needs to be used * beyond the critical section, the caller is responsible for ensuring the * returned pool is and stays online. + * + * Return: The worker_pool @work was last associated with. %NULL if none. */ static struct worker_pool *get_work_pool(struct work_struct *work) { @@ -690,7 +736,7 @@ * get_work_pool_id - return the worker pool ID a given work is associated with * @work: the work item of interest * - * Return the worker_pool ID @work was last associated with. + * Return: The worker_pool ID @work was last associated with. * %WORK_OFFQ_POOL_NONE if none. */ static int get_work_pool_id(struct work_struct *work) @@ -762,13 +808,6 @@ return need_more_worker(pool) && !may_start_working(pool); } -/* Do I need to be the manager? */ -static bool need_to_manage_workers(struct worker_pool *pool) -{ - return need_to_create_worker(pool) || - (pool->flags & POOL_MANAGE_WORKERS); -} - /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { @@ -776,13 +815,6 @@ int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; - /* - * nr_idle and idle_list may disagree if idle rebinding is in - * progress. Never return %true if idle_list is empty. - */ - if (list_empty(&pool->idle_list)) - return false; - return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } @@ -790,8 +822,8 @@ * Wake up functions. */ -/* Return the first worker. Safe with preemption disabled */ -static struct worker *first_worker(struct worker_pool *pool) +/* Return the first idle worker. Safe with preemption disabled */ +static struct worker *first_idle_worker(struct worker_pool *pool) { if (unlikely(list_empty(&pool->idle_list))) return NULL; @@ -810,7 +842,7 @@ */ static void wake_up_worker(struct worker_pool *pool) { - struct worker *worker = first_worker(pool); + struct worker *worker = first_idle_worker(pool); if (likely(worker)) wake_up_process(worker->task); @@ -849,7 +881,7 @@ * CONTEXT: * spin_lock_irq(rq->lock) * - * RETURNS: + * Return: * Worker task on @cpu to wake up, %NULL if none. */ struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) @@ -868,7 +900,7 @@ pool = worker->pool; /* this can only happen on the local cpu */ - if (WARN_ON_ONCE(cpu != raw_smp_processor_id())) + if (WARN_ON_ONCE(cpu != raw_smp_processor_id() || pool->cpu != cpu)) return NULL; /* @@ -884,7 +916,7 @@ */ if (atomic_dec_and_test(&pool->nr_running) && !list_empty(&pool->worklist)) - to_wakeup = first_worker(pool); + to_wakeup = first_idle_worker(pool); return to_wakeup ? to_wakeup->task : NULL; } @@ -892,35 +924,22 @@ * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set - * @wakeup: wakeup an idle worker if necessary * - * 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. + * Set @flags in @worker->flags and adjust nr_running accordingly. * * CONTEXT: * spin_lock_irq(pool->lock) */ -static inline void worker_set_flags(struct worker *worker, unsigned int flags, - bool wakeup) +static inline void worker_set_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; WARN_ON_ONCE(worker->task != current); - /* - * If transitioning into NOT_RUNNING, adjust nr_running and - * wake up an idle worker as necessary if requested by - * @wakeup. - */ + /* If transitioning into NOT_RUNNING, adjust nr_running. */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { - if (wakeup) { - if (atomic_dec_and_test(&pool->nr_running) && - !list_empty(&pool->worklist)) - wake_up_worker(pool); - } else - atomic_dec(&pool->nr_running); + atomic_dec(&pool->nr_running); } worker->flags |= flags; @@ -984,8 +1003,8 @@ * CONTEXT: * spin_lock_irq(pool->lock). * - * RETURNS: - * Pointer to worker which is executing @work if found, NULL + * Return: + * Pointer to worker which is executing @work if found, %NULL * otherwise. */ static struct worker *find_worker_executing_work(struct worker_pool *pool, @@ -1006,7 +1025,7 @@ * 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 + * @nextp: out parameter 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 @@ -1173,14 +1192,16 @@ * @flags: place to store irq state * * Try to grab PENDING bit of @work. This function can handle @work in any - * stable state - idle, on timer or on worklist. Return values are + * stable state - idle, on timer or on worklist. * + * Return: * 1 if @work was pending and we successfully stole PENDING * 0 if @work was idle and we claimed PENDING * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry * -ENOENT if someone else is canceling @work, this state may persist * for arbitrarily long * + * Note: * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting * interrupted while holding PENDING and @work off queue, irq must be * disabled on entry. This, combined with delayed_work->timer being @@ -1248,7 +1269,7 @@ pwq_activate_delayed_work(work); list_del_init(&work->entry); - pwq_dec_nr_in_flight(get_work_pwq(work), get_work_color(work)); + pwq_dec_nr_in_flight(pwq, get_work_color(work)); /* work->data points to pwq iff queued, point to pool */ set_work_pool_and_keep_pending(work, pool->id); @@ -1334,7 +1355,7 @@ debug_work_activate(work); - /* if dying, only works from the same workqueue are allowed */ + /* if draining, only works from the same workqueue are allowed */ if (unlikely(wq->flags & __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; @@ -1422,10 +1443,10 @@ * @wq: workqueue to use * @work: work to queue * - * Returns %false if @work was already on a queue, %true otherwise. - * * We queue the work to a specific CPU, the caller must ensure it * can't go away. + * + * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) @@ -1495,7 +1516,7 @@ * @dwork: work to queue * @delay: number of jiffies to wait before queueing * - * Returns %false if @work was already on a queue, %true otherwise. If + * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. */ @@ -1531,7 +1552,7 @@ * zero, @work is guaranteed to be scheduled immediately regardless of its * current state. * - * Returns %false if @dwork was idle and queued, %true if @dwork was + * Return: %false if @dwork was idle and queued, %true if @dwork was * pending and its timer was modified. * * This function is safe to call from any context including IRQ handler. @@ -1576,7 +1597,7 @@ (worker->hentry.next || worker->hentry.pprev))) return; - /* can't use worker_set_flags(), also called from start_worker() */ + /* can't use worker_set_flags(), also called from create_worker() */ worker->flags |= WORKER_IDLE; pool->nr_idle++; worker->last_active = jiffies; @@ -1618,78 +1639,15 @@ list_del_init(&worker->entry); } -/** - * worker_maybe_bind_and_lock - try to bind %current to worker_pool and lock it - * @pool: target worker_pool - * - * Bind %current to the cpu of @pool if it is associated and lock @pool. - * - * 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 unbound 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 pool may be - * [dis]associated in the meantime. - * - * This function tries set_cpus_allowed() and locks pool and verifies the - * binding against %POOL_DISASSOCIATED which is set during - * %CPU_DOWN_PREPARE 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 pool->lock - * held. - * - * RETURNS: - * %true if the associated pool is online (@worker is successfully - * bound), %false if offline. - */ -static bool worker_maybe_bind_and_lock(struct worker_pool *pool) -__acquires(&pool->lock) -{ - 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 POOL_DISASSOCIATED. - */ - if (!(pool->flags & POOL_DISASSOCIATED)) - 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, pool->attrs->cpumask)) - return true; - spin_unlock_irq(&pool->lock); - - /* - * We've raced with CPU hot[un]plug. Give it a breather - * and retry migration. cond_resched() is required here; - * otherwise, we might deadlock against cpu_stop trying to - * bring down the CPU on non-preemptive kernel. - */ - cpu_relax(); - cond_resched(); - } -} - -static struct worker *alloc_worker(void) +static struct worker *alloc_worker(int node) { struct worker *worker; - worker = kzalloc(sizeof(*worker), GFP_KERNEL); + worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node); if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); + INIT_LIST_HEAD(&worker->node); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } @@ -1697,17 +1655,75 @@ } /** + * worker_attach_to_pool() - attach a worker to a pool + * @worker: worker to be attached + * @pool: the target pool + * + * Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and + * cpu-binding of @worker are kept coordinated with the pool across + * cpu-[un]hotplugs. + */ +static void worker_attach_to_pool(struct worker *worker, + struct worker_pool *pool) +{ + mutex_lock(&pool->attach_mutex); + + /* + * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any + * online CPUs. It'll be re-applied when any of the CPUs come up. + */ + set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); + + /* + * The pool->attach_mutex ensures %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; + + list_add_tail(&worker->node, &pool->workers); + + mutex_unlock(&pool->attach_mutex); +} + +/** + * worker_detach_from_pool() - detach a worker from its pool + * @worker: worker which is attached to its pool + * @pool: the pool @worker is attached to + * + * Undo the attaching which had been done in worker_attach_to_pool(). The + * caller worker shouldn't access to the pool after detached except it has + * other reference to the pool. + */ +static void worker_detach_from_pool(struct worker *worker, + struct worker_pool *pool) +{ + struct completion *detach_completion = NULL; + + mutex_lock(&pool->attach_mutex); + list_del(&worker->node); + if (list_empty(&pool->workers)) + detach_completion = pool->detach_completion; + mutex_unlock(&pool->attach_mutex); + + /* clear leftover flags without pool->lock after it is detached */ + worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); + + if (detach_completion) + complete(detach_completion); +} + +/** * create_worker - create a new workqueue worker * @pool: pool the new worker will belong to * - * Create a new worker which is bound to @pool. The returned worker - * can be started by calling start_worker() or destroyed using - * destroy_worker(). + * Create and start a new worker which is attached to @pool. * * CONTEXT: * Might sleep. Does GFP_KERNEL allocations. * - * RETURNS: + * Return: * Pointer to the newly created worker. */ static struct worker *create_worker(struct worker_pool *pool) @@ -1716,23 +1732,12 @@ int id = -1; char id_buf[16]; - lockdep_assert_held(&pool->manager_mutex); - - /* - * ID is needed to determine kthread name. Allocate ID first - * without installing the pointer. - */ - idr_preload(GFP_KERNEL); - spin_lock_irq(&pool->lock); - - id = idr_alloc(&pool->worker_idr, NULL, 0, 0, GFP_NOWAIT); - - spin_unlock_irq(&pool->lock); - idr_preload_end(); + /* ID is needed to determine kthread name */ + id = ida_simple_get(&pool->worker_ida, 0, 0, GFP_KERNEL); if (id < 0) goto fail; - worker = alloc_worker(); + worker = alloc_worker(pool->node); if (!worker) goto fail; @@ -1750,126 +1755,56 @@ if (IS_ERR(worker->task)) goto fail; - /* - * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any - * online CPUs. It'll be re-applied when any of the CPUs come up. - */ set_user_nice(worker->task, pool->attrs->nice); - set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); - - /* prevent userland from meddling with cpumask of workqueue workers */ - worker->task->flags |= PF_NO_SETAFFINITY; + kthread_bind_mask(worker->task, pool->attrs->cpumask); - /* - * 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; + /* successful, attach the worker to the pool */ + worker_attach_to_pool(worker, pool); - /* successful, commit the pointer to idr */ + /* start the newly created worker */ spin_lock_irq(&pool->lock); - idr_replace(&pool->worker_idr, worker, worker->id); + worker->pool->nr_workers++; + worker_enter_idle(worker); + wake_up_process(worker->task); spin_unlock_irq(&pool->lock); return worker; fail: - if (id >= 0) { - spin_lock_irq(&pool->lock); - idr_remove(&pool->worker_idr, id); - spin_unlock_irq(&pool->lock); - } + if (id >= 0) + ida_simple_remove(&pool->worker_ida, id); kfree(worker); return NULL; } /** - * start_worker - start a newly created worker - * @worker: worker to start - * - * Make the pool aware of @worker and start it. - * - * CONTEXT: - * spin_lock_irq(pool->lock). - */ -static void start_worker(struct worker *worker) -{ - worker->flags |= WORKER_STARTED; - worker->pool->nr_workers++; - worker_enter_idle(worker); - wake_up_process(worker->task); -} - -/** - * create_and_start_worker - create and start a worker for a pool - * @pool: the target pool - * - * Grab the managership of @pool and create and start a new worker for it. - */ -static int create_and_start_worker(struct worker_pool *pool) -{ - struct worker *worker; - - mutex_lock(&pool->manager_mutex); - - worker = create_worker(pool); - if (worker) { - spin_lock_irq(&pool->lock); - start_worker(worker); - spin_unlock_irq(&pool->lock); - } - - mutex_unlock(&pool->manager_mutex); - - return worker ? 0 : -ENOMEM; -} - -/** * destroy_worker - destroy a workqueue worker * @worker: worker to be destroyed * - * Destroy @worker and adjust @pool stats accordingly. + * Destroy @worker and adjust @pool stats accordingly. The worker should + * be idle. * * CONTEXT: - * spin_lock_irq(pool->lock) which is released and regrabbed. + * spin_lock_irq(pool->lock). */ static void destroy_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; - lockdep_assert_held(&pool->manager_mutex); lockdep_assert_held(&pool->lock); /* sanity check frenzy */ if (WARN_ON(worker->current_work) || - WARN_ON(!list_empty(&worker->scheduled))) + WARN_ON(!list_empty(&worker->scheduled)) || + WARN_ON(!(worker->flags & WORKER_IDLE))) return; - if (worker->flags & WORKER_STARTED) - pool->nr_workers--; - if (worker->flags & WORKER_IDLE) - pool->nr_idle--; - - /* - * Once WORKER_DIE is set, the kworker may destroy itself at any - * point. Pin to ensure the task stays until we're done with it. - */ - get_task_struct(worker->task); + pool->nr_workers--; + pool->nr_idle--; list_del_init(&worker->entry); worker->flags |= WORKER_DIE; - - idr_remove(&pool->worker_idr, worker->id); - - spin_unlock_irq(&pool->lock); - - kthread_stop(worker->task); - put_task_struct(worker->task); - kfree(worker); - - spin_lock_irq(&pool->lock); + wake_up_process(worker->task); } static void idle_worker_timeout(unsigned long __pool) @@ -1878,7 +1813,7 @@ spin_lock_irq(&pool->lock); - if (too_many_workers(pool)) { + while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; @@ -1886,13 +1821,12 @@ worker = list_entry(pool->idle_list.prev, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; - if (time_before(jiffies, expires)) + if (time_before(jiffies, expires)) { mod_timer(&pool->idle_timer, expires); - else { - /* it's been idle for too long, wake up manager */ - pool->flags |= POOL_MANAGE_WORKERS; - wake_up_worker(pool); + break; } + + destroy_worker(worker); } spin_unlock_irq(&pool->lock); @@ -1926,8 +1860,8 @@ struct worker_pool *pool = (void *)__pool; struct work_struct *work; - spin_lock_irq(&wq_mayday_lock); /* for wq->maydays */ - spin_lock(&pool->lock); + spin_lock_irq(&pool->lock); + spin_lock(&wq_mayday_lock); /* for wq->maydays */ if (need_to_create_worker(pool)) { /* @@ -1940,8 +1874,8 @@ send_mayday(work); } - spin_unlock(&pool->lock); - spin_unlock_irq(&wq_mayday_lock); + spin_unlock(&wq_mayday_lock); + spin_unlock_irq(&pool->lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } @@ -1968,8 +1902,6 @@ __releases(&pool->lock) __acquires(&pool->lock) { - if (!need_to_create_worker(pool)) - return; restart: spin_unlock_irq(&pool->lock); @@ -1977,23 +1909,10 @@ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); while (true) { - struct worker *worker; - - worker = create_worker(pool); - if (worker) { - del_timer_sync(&pool->mayday_timer); - spin_lock_irq(&pool->lock); - start_worker(worker); - if (WARN_ON_ONCE(need_to_create_worker(pool))) - goto restart; - return; - } - - if (!need_to_create_worker(pool)) + if (create_worker(pool) || !need_to_create_worker(pool)) break; - __set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(CREATE_COOLDOWN); + schedule_timeout_interruptible(CREATE_COOLDOWN); if (!need_to_create_worker(pool)) break; @@ -2001,38 +1920,13 @@ del_timer_sync(&pool->mayday_timer); spin_lock_irq(&pool->lock); + /* + * This is necessary even after a new worker was just successfully + * created as @pool->lock was dropped and the new worker might have + * already become busy. + */ if (need_to_create_worker(pool)) goto restart; - return; -} - -/** - * maybe_destroy_worker - destroy workers which have been idle for a while - * @pool: pool to destroy workers for - * - * Destroy @pool workers which have been idle for longer than - * IDLE_WORKER_TIMEOUT. - * - * LOCKING: - * spin_lock_irq(pool->lock) which may be released and regrabbed - * multiple times. Called only from manager. - */ -static void maybe_destroy_workers(struct worker_pool *pool) -{ - while (too_many_workers(pool)) { - struct worker *worker; - unsigned long expires; - - worker = list_entry(pool->idle_list.prev, struct worker, entry); - expires = worker->last_active + IDLE_WORKER_TIMEOUT; - - if (time_before(jiffies, expires)) { - mod_timer(&pool->idle_timer, expires); - break; - } - - destroy_worker(worker); - } } /** @@ -2051,7 +1945,7 @@ * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * - * RETURNS: + * Return: * %false if the pool doesn't need management and the caller can safely * start processing works, %true if management function was performed and * the conditions that the caller verified before calling the function may @@ -2062,8 +1956,6 @@ struct worker_pool *pool = worker->pool; /* - * Managership is governed by two mutexes - manager_arb and - * manager_mutex. manager_arb handles arbitration of manager role. * Anyone who successfully grabs manager_arb wins the arbitration * and becomes the manager. mutex_trylock() on pool->manager_arb * failure while holding pool->lock reliably indicates that someone @@ -2072,39 +1964,14 @@ * grabbing manager_arb is responsible for actually performing * manager duties. If manager_arb is grabbed and released without * actual management, the pool may stall indefinitely. - * - * manager_mutex is used for exclusion of actual management - * operations. The holder of manager_mutex can be sure that none - * of management operations, including creation and destruction of - * workers, won't take place until the mutex is released. Because - * manager_mutex doesn't interfere with manager role arbitration, - * it is guaranteed that the pool's management, while may be - * delayed, won't be disturbed by someone else grabbing - * manager_mutex. */ if (!mutex_trylock(&pool->manager_arb)) return false; + pool->manager = worker; - /* - * With manager arbitration won, manager_mutex would be free in - * most cases. trylock first without dropping @pool->lock. - */ - if (unlikely(!mutex_trylock(&pool->manager_mutex))) { - spin_unlock_irq(&pool->lock); - mutex_lock(&pool->manager_mutex); - spin_lock_irq(&pool->lock); - } - - pool->flags &= ~POOL_MANAGE_WORKERS; - - /* - * Destroy and then create so that may_start_working() is true - * on return. - */ - maybe_destroy_workers(pool); maybe_create_worker(pool); - mutex_unlock(&pool->manager_mutex); + pool->manager = NULL; mutex_unlock(&pool->manager_arb); return true; } @@ -2144,13 +2011,8 @@ lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif - /* - * Ensure we're on the correct CPU. DISASSOCIATED test is - * necessary to avoid spurious warnings from rescuers servicing the - * unbound or a disassociated pool. - */ - WARN_ON_ONCE(!(worker->flags & WORKER_UNBOUND) && - !(pool->flags & POOL_DISASSOCIATED) && + /* ensure we're on the correct CPU */ + WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && raw_smp_processor_id() != pool->cpu); /* @@ -2176,17 +2038,22 @@ list_del_init(&work->entry); /* - * CPU intensive works don't participate in concurrency - * management. They're the scheduler's responsibility. + * CPU intensive works don't participate in concurrency management. + * They're the scheduler's responsibility. This takes @worker out + * of concurrency management and the next code block will chain + * execution of the pending work items. */ if (unlikely(cpu_intensive)) - worker_set_flags(worker, WORKER_CPU_INTENSIVE, true); + worker_set_flags(worker, WORKER_CPU_INTENSIVE); /* - * Unbound pool isn't concurrency managed and work items should be - * executed ASAP. Wake up another worker if necessary. + * Wake up another worker if necessary. The condition is always + * false for normal per-cpu workers since nr_running would always + * be >= 1 at this point. This is used to chain execution of the + * pending work items for WORKER_NOT_RUNNING workers such as the + * UNBOUND and CPU_INTENSIVE ones. */ - if ((worker->flags & WORKER_UNBOUND) && need_more_worker(pool)) + if (need_more_worker(pool)) wake_up_worker(pool); /* @@ -2202,7 +2069,13 @@ lock_map_acquire_read(&pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); trace_workqueue_execute_start(work); +#if defined(CONFIG_AVM_SIMPLE_PROFILING) + avm_simple_profiling_log(avm_profile_data_type_workitem_begin, (unsigned int)worker->current_func, (unsigned int)work); +#endif /*--- #if defined(CONFIG_AVM_SIMPLE_PROFILING) ---*/ worker->current_func(work); +#if defined(CONFIG_AVM_SIMPLE_PROFILING) + avm_simple_profiling_log(avm_profile_data_type_workitem_end, (unsigned int)worker->current_func, (unsigned int)work); +#endif /*--- #if defined(CONFIG_AVM_SIMPLE_PROFILING) ---*/ /* * While we must be careful to not use "work" after this, the trace * point will only record its address. @@ -2225,9 +2098,10 @@ * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in - * stop_machine. + * stop_machine. At the same time, report a quiescent RCU state so + * the same condition doesn't freeze RCU. */ - cond_resched(); + cond_resched_rcu_qs(); spin_lock_irq(&pool->lock); @@ -2274,6 +2148,8 @@ * work items regardless of their specific target workqueue. The only * exception is work items which belong to workqueues with a rescuer which * will be explained in rescuer_thread(). + * + * Return: 0 */ static int worker_thread(void *__worker) { @@ -2290,6 +2166,11 @@ spin_unlock_irq(&pool->lock); WARN_ON_ONCE(!list_empty(&worker->entry)); worker->task->flags &= ~PF_WQ_WORKER; + + set_task_comm(worker->task, "kworker/dying"); + ida_simple_remove(&pool->worker_ida, worker->id); + worker_detach_from_pool(worker, pool); + kfree(worker); return 0; } @@ -2335,11 +2216,8 @@ } } while (keep_working(pool)); - worker_set_flags(worker, WORKER_PREP, false); + worker_set_flags(worker, WORKER_PREP); sleep: - if (unlikely(need_to_manage_workers(pool)) && manage_workers(worker)) - goto recheck; - /* * pool->lock is held and there's no work to process and no need to * manage, sleep. Workers are woken up only while holding @@ -2372,6 +2250,8 @@ * those works so that forward progress can be guaranteed. * * This should happen rarely. + * + * Return: 0 */ static int rescuer_thread(void *__rescuer) { @@ -2414,38 +2294,60 @@ spin_unlock_irq(&wq_mayday_lock); - /* migrate to the target cpu if possible */ - worker_maybe_bind_and_lock(pool); + worker_attach_to_pool(rescuer, pool); + + spin_lock_irq(&pool->lock); rescuer->pool = pool; /* * Slurp in all works issued via this workqueue and * process'em. */ - WARN_ON_ONCE(!list_empty(&rescuer->scheduled)); + WARN_ON_ONCE(!list_empty(scheduled)); list_for_each_entry_safe(work, n, &pool->worklist, entry) if (get_work_pwq(work) == pwq) move_linked_works(work, scheduled, &n); - process_scheduled_works(rescuer); + if (!list_empty(scheduled)) { + process_scheduled_works(rescuer); + + /* + * The above execution of rescued work items could + * have created more to rescue through + * pwq_activate_first_delayed() or chained + * queueing. Let's put @pwq back on mayday list so + * that such back-to-back work items, which may be + * being used to relieve memory pressure, don't + * incur MAYDAY_INTERVAL delay inbetween. + */ + if (need_to_create_worker(pool)) { + spin_lock(&wq_mayday_lock); + get_pwq(pwq); + list_move_tail(&pwq->mayday_node, &wq->maydays); + spin_unlock(&wq_mayday_lock); + } + } /* * Put the reference grabbed by send_mayday(). @pool won't - * go away while we're holding its lock. + * go away while we're still attached to it. */ put_pwq(pwq); /* - * Leave this pool. If keep_working() is %true, notify a + * Leave this pool. If need_more_worker() is %true, notify a * regular worker; otherwise, we end up with 0 concurrency * and stalling the execution. */ - if (keep_working(pool)) + if (need_more_worker(pool)) wake_up_worker(pool); rescuer->pool = NULL; - spin_unlock(&pool->lock); - spin_lock(&wq_mayday_lock); + spin_unlock_irq(&pool->lock); + + worker_detach_from_pool(rescuer, pool); + + spin_lock_irq(&wq_mayday_lock); } spin_unlock_irq(&wq_mayday_lock); @@ -2465,6 +2367,7 @@ struct wq_barrier { struct work_struct work; struct completion done; + struct task_struct *task; /* purely informational */ }; static void wq_barrier_func(struct work_struct *work) @@ -2513,6 +2416,7 @@ INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion(&barr->done); + barr->task = current; /* * If @target is currently being executed, schedule the @@ -2561,7 +2465,7 @@ * CONTEXT: * mutex_lock(wq->mutex). * - * RETURNS: + * Return: * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ @@ -2756,7 +2660,7 @@ out_unlock: mutex_unlock(&wq->mutex); } -EXPORT_SYMBOL_GPL(flush_workqueue); +EXPORT_SYMBOL(flush_workqueue); /** * drain_workqueue - drain a workqueue @@ -2765,7 +2669,7 @@ * Wait until the workqueue becomes empty. While draining is in progress, * only chain queueing is allowed. IOW, only currently pending or running * work items on @wq can queue further work items on it. @wq is flushed - * repeatedly until it becomes empty. The number of flushing is detemined + * repeatedly until it becomes empty. The number of flushing is determined * by the depth of chaining and should be relatively short. Whine if it * takes too long. */ @@ -2869,7 +2773,7 @@ * Wait until @work has finished execution. @work is guaranteed to be idle * on return if it hasn't been requeued since flush started. * - * RETURNS: + * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ @@ -2977,7 +2881,7 @@ * The caller must ensure that the workqueue on which @work was last * queued can't be destroyed before this function returns. * - * RETURNS: + * Return: * %true if @work was pending, %false otherwise. */ bool cancel_work_sync(struct work_struct *work) @@ -2994,7 +2898,7 @@ * immediate execution. Like flush_work(), this function only * considers the last queueing instance of @dwork. * - * RETURNS: + * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ @@ -3012,11 +2916,15 @@ * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel * - * Kill off a pending delayed_work. Returns %true if @dwork was pending - * and canceled; %false if wasn't pending. Note that the work callback - * function may still be running on return, unless it returns %true and the - * work doesn't re-arm itself. Explicitly flush or use - * cancel_delayed_work_sync() to wait on it. + * Kill off a pending delayed_work. + * + * Return: %true if @dwork was pending and canceled; %false if it wasn't + * pending. + * + * Note: + * The work callback function may still be running on return, unless + * it returns %true and the work doesn't re-arm itself. Explicitly flush or + * use cancel_delayed_work_sync() to wait on it. * * This function is safe to call from any context including IRQ handler. */ @@ -3045,7 +2953,7 @@ * * This is cancel_work_sync() for delayed works. * - * RETURNS: + * Return: * %true if @dwork was pending, %false otherwise. */ bool cancel_delayed_work_sync(struct delayed_work *dwork) @@ -3062,7 +2970,7 @@ * system workqueue and blocks until all CPUs have completed. * schedule_on_each_cpu() is very slow. * - * RETURNS: + * Return: * 0 on success, -errno on failure. */ int schedule_on_each_cpu(work_func_t func) @@ -3092,36 +3000,6 @@ } /** - * flush_scheduled_work - ensure that any scheduled work has run to completion. - * - * Forces execution of the kernel-global workqueue and blocks until its - * completion. - * - * Think twice before calling this function! It's very easy to get into - * trouble if you don't take great care. Either of the following situations - * will lead to deadlock: - * - * One of the work items currently on the workqueue needs to acquire - * a lock held by your code or its caller. - * - * Your code is running in the context of a work routine. - * - * They will be detected by lockdep when they occur, but the first might not - * occur very often. It depends on what work items are on the workqueue and - * what locks they need, which you have no control over. - * - * In most situations flushing the entire workqueue is overkill; you merely - * need to know that a particular work item isn't queued and isn't running. - * In such cases you should use cancel_delayed_work_sync() or - * cancel_work_sync() instead. - */ -void flush_scheduled_work(void) -{ - flush_workqueue(system_wq); -} -EXPORT_SYMBOL(flush_scheduled_work); - -/** * execute_in_process_context - reliably execute the routine with user context * @fn: the function to execute * @ew: guaranteed storage for the execute work structure (must @@ -3130,7 +3008,7 @@ * Executes the function immediately if process context is available, * otherwise schedules the function for delayed execution. * - * Returns: 0 - function was executed + * Return: 0 - function was executed * 1 - function was scheduled for execution */ int execute_in_process_context(work_func_t fn, struct execute_work *ew) @@ -3147,321 +3025,6 @@ } EXPORT_SYMBOL_GPL(execute_in_process_context); -#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_ids_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct workqueue_struct *wq = dev_to_wq(dev); - const char *delim = ""; - int node, written = 0; - - rcu_read_lock_sched(); - 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; -} - -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; - - mutex_lock(&wq->mutex); - written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); - mutex_unlock(&wq->mutex); - - 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; - - mutex_lock(&wq->mutex); - copy_workqueue_attrs(attrs, wq->unbound_attrs); - mutex_unlock(&wq->mutex); - 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; - - mutex_lock(&wq->mutex); - written = cpumask_scnprintf(buf, PAGE_SIZE, wq->unbound_attrs->cpumask); - mutex_unlock(&wq->mutex); - - 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 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_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, -}; - -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; - } - } - } - - dev_set_uevent_suppress(&wq_dev->dev, false); - 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 @@ -3481,7 +3044,9 @@ * @gfp_mask: allocation mask to use * * Allocate a new workqueue_attrs, initialize with default settings and - * return it. Returns NULL on failure. + * return it. + * + * Return: The allocated new workqueue_attr on success. %NULL on failure. */ struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask) { @@ -3539,8 +3104,9 @@ * 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. Even on failure, all fields + * Initialize a newly zalloc'd @pool. It also allocates @pool->attrs. + * + * Return: 0 on success, -errno on failure. Even on failure, all fields * inside @pool proper are initialized and put_unbound_pool() can be called * on @pool safely to release it. */ @@ -3563,9 +3129,10 @@ (unsigned long)pool); mutex_init(&pool->manager_arb); - mutex_init(&pool->manager_mutex); - idr_init(&pool->worker_idr); + mutex_init(&pool->attach_mutex); + INIT_LIST_HEAD(&pool->workers); + ida_init(&pool->worker_ida); INIT_HLIST_NODE(&pool->hash_node); pool->refcnt = 1; @@ -3576,11 +3143,25 @@ return 0; } +static void rcu_free_wq(struct rcu_head *rcu) +{ + struct workqueue_struct *wq = + container_of(rcu, struct workqueue_struct, rcu); + + if (!(wq->flags & WQ_UNBOUND)) + free_percpu(wq->cpu_pwqs); + else + free_workqueue_attrs(wq->unbound_attrs); + + kfree(wq->rescuer); + kfree(wq); +} + static void rcu_free_pool(struct rcu_head *rcu) { struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); - idr_destroy(&pool->worker_idr); + ida_destroy(&pool->worker_ida); free_workqueue_attrs(pool->attrs); kfree(pool); } @@ -3598,6 +3179,7 @@ */ static void put_unbound_pool(struct worker_pool *pool) { + DECLARE_COMPLETION_ONSTACK(detach_completion); struct worker *worker; lockdep_assert_held(&wq_pool_mutex); @@ -3606,7 +3188,7 @@ return; /* sanity checks */ - if (WARN_ON(!(pool->flags & POOL_DISASSOCIATED)) || + if (WARN_ON(!(pool->cpu < 0)) || WARN_ON(!list_empty(&pool->worklist))) return; @@ -3618,18 +3200,24 @@ /* * Become the manager and destroy all workers. Grabbing * manager_arb prevents @pool's workers from blocking on - * manager_mutex. + * attach_mutex. */ mutex_lock(&pool->manager_arb); - mutex_lock(&pool->manager_mutex); - spin_lock_irq(&pool->lock); - while ((worker = first_worker(pool))) + spin_lock_irq(&pool->lock); + while ((worker = first_idle_worker(pool))) destroy_worker(worker); WARN_ON(pool->nr_workers || pool->nr_idle); - spin_unlock_irq(&pool->lock); - mutex_unlock(&pool->manager_mutex); + + mutex_lock(&pool->attach_mutex); + if (!list_empty(&pool->workers)) + pool->detach_completion = &detach_completion; + mutex_unlock(&pool->attach_mutex); + + if (pool->detach_completion) + wait_for_completion(pool->detach_completion); + mutex_unlock(&pool->manager_arb); /* shut down the timers */ @@ -3647,15 +3235,19 @@ * Obtain a worker_pool which has the same attributes as @attrs, bump the * reference count and return it. If there already is a matching * worker_pool, it will be used; otherwise, this function attempts to - * create a new one. On failure, returns NULL. + * create a new one. * * Should be called with wq_pool_mutex held. + * + * Return: On success, a worker_pool with the same attributes as @attrs. + * On failure, %NULL. */ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) { u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; int node; + int target_node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); @@ -3663,20 +3255,29 @@ hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { if (wqattrs_equal(pool->attrs, attrs)) { pool->refcnt++; - goto out_unlock; + return pool; + } + } + + /* if cpumask is contained inside a NUMA node, we belong to that node */ + if (wq_numa_enabled) { + for_each_node(node) { + if (cpumask_subset(attrs->cpumask, + wq_numa_possible_cpumask[node])) { + target_node = node; + break; + } } } /* nope, create a new one */ - pool = kzalloc(sizeof(*pool), GFP_KERNEL); + pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, target_node); if (!pool || init_worker_pool(pool) < 0) goto fail; - if (workqueue_freezing) - pool->flags |= POOL_FREEZING; - lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */ copy_workqueue_attrs(pool->attrs, attrs); + pool->node = target_node; /* * no_numa isn't a worker_pool attribute, always clear it. See @@ -3684,27 +3285,16 @@ */ pool->attrs->no_numa = false; - /* if cpumask is contained inside a NUMA node, we belong to that node */ - if (wq_numa_enabled) { - for_each_node(node) { - if (cpumask_subset(pool->attrs->cpumask, - wq_numa_possible_cpumask[node])) { - pool->node = node; - break; - } - } - } - if (worker_pool_assign_id(pool) < 0) goto fail; /* create and start the initial worker */ - if (create_and_start_worker(pool) < 0) + if (!create_worker(pool)) goto fail; /* install */ hash_add(unbound_pool_hash, &pool->hash_node, hash); -out_unlock: + return pool; fail: if (pool) @@ -3733,11 +3323,6 @@ if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) return; - /* - * Unlink @pwq. Synchronization against wq->mutex isn't strictly - * necessary on release but do it anyway. It's easier to verify - * and consistent with the linking path. - */ mutex_lock(&wq->mutex); list_del_rcu(&pwq->pwqs_node); is_last = list_empty(&wq->pwqs); @@ -3751,12 +3336,10 @@ /* * If we're the last pwq going away, @wq is already dead and no one - * is gonna access it anymore. Free it. + * is gonna access it anymore. Schedule RCU free. */ - if (is_last) { - free_workqueue_attrs(wq->unbound_attrs); - kfree(wq); - } + if (is_last) + call_rcu_sched(&wq->rcu, rcu_free_wq); } /** @@ -3781,7 +3364,12 @@ spin_lock_irq(&pwq->pool->lock); - if (!freezable || !(pwq->pool->flags & POOL_FREEZING)) { + /* + * During [un]freezing, the caller is responsible for ensuring that + * this function is called at least once after @workqueue_freezing + * is updated and visible. + */ + if (!freezable || !workqueue_freezing) { pwq->max_active = wq->saved_max_active; while (!list_empty(&pwq->delayed_works) && @@ -3829,10 +3417,7 @@ if (!list_empty(&pwq->pwqs_node)) return; - /* - * Set the matching work_color. This is synchronized with - * wq->mutex to avoid confusing flush_workqueue(). - */ + /* set the matching work_color */ pwq->work_color = wq->work_color; /* sync max_active to the current setting */ @@ -3865,29 +3450,16 @@ return pwq; } -/* undo alloc_unbound_pwq(), used only in the error path */ -static void free_unbound_pwq(struct pool_workqueue *pwq) -{ - lockdep_assert_held(&wq_pool_mutex); - - if (pwq) { - put_unbound_pool(pwq->pool); - kmem_cache_free(pwq_cache, pwq); - } -} - /** - * wq_calc_node_mask - calculate a wq_attrs' cpumask for the specified node - * @attrs: the wq_attrs of interest + * wq_calc_node_cpumask - calculate a wq_attrs' cpumask for the specified node + * @attrs: the wq_attrs of the default pwq of the target workqueue * @node: the target NUMA node * @cpu_going_down: if >= 0, the CPU to consider as offline * @cpumask: outarg, the resulting cpumask * * Calculate the cpumask a workqueue with @attrs should use on @node. If * @cpu_going_down is >= 0, that cpu is considered offline during - * calculation. The result is stored in @cpumask. This function returns - * %true if the resulting @cpumask is different from @attrs->cpumask, - * %false if equal. + * calculation. The result is stored in @cpumask. * * If NUMA affinity is not enabled, @attrs->cpumask is always used. If * enabled and @node has online CPUs requested by @attrs, the returned @@ -3896,6 +3468,9 @@ * * The caller is responsible for ensuring that the cpumask of @node stays * stable. + * + * Return: %true if the resulting @cpumask is different from @attrs->cpumask, + * %false if equal. */ static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node, int cpu_going_down, cpumask_t *cpumask) @@ -3927,6 +3502,7 @@ { struct pool_workqueue *old_pwq; + lockdep_assert_held(&wq_pool_mutex); lockdep_assert_held(&wq->mutex); /* link_pwq() can handle duplicate calls */ @@ -3937,45 +3513,59 @@ return old_pwq; } -/** - * 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. Unless disabled, on NUMA - * machines, this function maps a separate pwq to each NUMA node with - * possibles CPUs in @attrs->cpumask so that work items are affine to the - * NUMA node it was issued on. 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) +/* context to store the prepared attrs & pwqs before applying */ +struct apply_wqattrs_ctx { + struct workqueue_struct *wq; /* target workqueue */ + struct workqueue_attrs *attrs; /* attrs to apply */ + struct list_head list; /* queued for batching commit */ + struct pool_workqueue *dfl_pwq; + struct pool_workqueue *pwq_tbl[]; +}; + +/* free the resources after success or abort */ +static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { + if (ctx) { + int node; + + for_each_node(node) + put_pwq_unlocked(ctx->pwq_tbl[node]); + put_pwq_unlocked(ctx->dfl_pwq); + + free_workqueue_attrs(ctx->attrs); + + kfree(ctx); + } +} + +/* allocate the attrs and pwqs for later installation */ +static struct apply_wqattrs_ctx * +apply_wqattrs_prepare(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs) +{ + struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs, *tmp_attrs; - struct pool_workqueue **pwq_tbl, *dfl_pwq; - int node, ret; + int node; - /* only unbound workqueues can change attributes */ - if (WARN_ON(!(wq->flags & WQ_UNBOUND))) - return -EINVAL; + lockdep_assert_held(&wq_pool_mutex); - /* creating multiple pwqs breaks ordering guarantee */ - if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs))) - return -EINVAL; + ctx = kzalloc(sizeof(*ctx) + nr_node_ids * sizeof(ctx->pwq_tbl[0]), + GFP_KERNEL); - pwq_tbl = kzalloc(wq_numa_tbl_len * sizeof(pwq_tbl[0]), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(GFP_KERNEL); tmp_attrs = alloc_workqueue_attrs(GFP_KERNEL); - if (!pwq_tbl || !new_attrs || !tmp_attrs) - goto enomem; + if (!ctx || !new_attrs || !tmp_attrs) + goto out_free; - /* make a copy of @attrs and sanitize it */ + /* + * Calculate the attrs of the default pwq. + * If the user configured cpumask doesn't overlap with the + * wq_unbound_cpumask, we fallback to the wq_unbound_cpumask. + */ copy_workqueue_attrs(new_attrs, attrs); - cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); + cpumask_and(new_attrs->cpumask, new_attrs->cpumask, wq_unbound_cpumask); + if (unlikely(cpumask_empty(new_attrs->cpumask))) + cpumask_copy(new_attrs->cpumask, wq_unbound_cpumask); /* * We may create multiple pwqs with differing cpumasks. Make a @@ -3985,75 +3575,129 @@ copy_workqueue_attrs(tmp_attrs, new_attrs); /* - * CPUs should stay stable across pwq creations and installations. - * Pin CPUs, determine the target cpumask for each node and create - * pwqs accordingly. - */ - get_online_cpus(); - - mutex_lock(&wq_pool_mutex); - - /* * If something goes wrong during CPU up/down, we'll fall back to * the default pwq covering whole @attrs->cpumask. Always create * it even if we don't use it immediately. */ - dfl_pwq = alloc_unbound_pwq(wq, new_attrs); - if (!dfl_pwq) - goto enomem_pwq; + ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); + if (!ctx->dfl_pwq) + goto out_free; for_each_node(node) { - if (wq_calc_node_cpumask(attrs, node, -1, tmp_attrs->cpumask)) { - pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs); - if (!pwq_tbl[node]) - goto enomem_pwq; + if (wq_calc_node_cpumask(new_attrs, node, -1, tmp_attrs->cpumask)) { + ctx->pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs); + if (!ctx->pwq_tbl[node]) + goto out_free; } else { - dfl_pwq->refcnt++; - pwq_tbl[node] = dfl_pwq; + ctx->dfl_pwq->refcnt++; + ctx->pwq_tbl[node] = ctx->dfl_pwq; } } - mutex_unlock(&wq_pool_mutex); + /* save the user configured attrs and sanitize it. */ + copy_workqueue_attrs(new_attrs, attrs); + cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); + ctx->attrs = new_attrs; + + ctx->wq = wq; + free_workqueue_attrs(tmp_attrs); + return ctx; + +out_free: + free_workqueue_attrs(tmp_attrs); + free_workqueue_attrs(new_attrs); + apply_wqattrs_cleanup(ctx); + return NULL; +} + +/* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ +static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) +{ + int node; /* all pwqs have been created successfully, let's install'em */ - mutex_lock(&wq->mutex); + mutex_lock(&ctx->wq->mutex); - copy_workqueue_attrs(wq->unbound_attrs, new_attrs); + copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwq and install the new one */ for_each_node(node) - pwq_tbl[node] = numa_pwq_tbl_install(wq, node, pwq_tbl[node]); + ctx->pwq_tbl[node] = numa_pwq_tbl_install(ctx->wq, node, + ctx->pwq_tbl[node]); /* @dfl_pwq might not have been used, ensure it's linked */ - link_pwq(dfl_pwq); - swap(wq->dfl_pwq, dfl_pwq); + link_pwq(ctx->dfl_pwq); + swap(ctx->wq->dfl_pwq, ctx->dfl_pwq); - mutex_unlock(&wq->mutex); + mutex_unlock(&ctx->wq->mutex); +} - /* put the old pwqs */ - for_each_node(node) - put_pwq_unlocked(pwq_tbl[node]); - put_pwq_unlocked(dfl_pwq); +static void apply_wqattrs_lock(void) +{ + /* CPUs should stay stable across pwq creations and installations */ + get_online_cpus(); + mutex_lock(&wq_pool_mutex); +} +static void apply_wqattrs_unlock(void) +{ + mutex_unlock(&wq_pool_mutex); put_online_cpus(); - ret = 0; - /* fall through */ -out_free: - free_workqueue_attrs(tmp_attrs); - free_workqueue_attrs(new_attrs); - kfree(pwq_tbl); +} + +static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs) +{ + struct apply_wqattrs_ctx *ctx; + int ret = -ENOMEM; + + /* 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; + + ctx = apply_wqattrs_prepare(wq, attrs); + + /* the ctx has been prepared successfully, let's commit it */ + if (ctx) { + apply_wqattrs_commit(ctx); + ret = 0; + } + + apply_wqattrs_cleanup(ctx); + return ret; +} -enomem_pwq: - free_unbound_pwq(dfl_pwq); - for_each_node(node) - if (pwq_tbl && pwq_tbl[node] != dfl_pwq) - free_unbound_pwq(pwq_tbl[node]); - mutex_unlock(&wq_pool_mutex); - put_online_cpus(); -enomem: - ret = -ENOMEM; - goto out_free; +/** + * 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. Unless disabled, on NUMA + * machines, this function maps a separate pwq to each NUMA node with + * possibles CPUs in @attrs->cpumask so that work items are affine to the + * NUMA node it was issued on. 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. + * + * Return: 0 on success and -errno on failure. + */ +int apply_workqueue_attrs(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs) +{ + int ret; + + apply_wqattrs_lock(); + ret = apply_workqueue_attrs_locked(wq, attrs); + apply_wqattrs_unlock(); + + return ret; } /** @@ -4089,7 +3733,8 @@ lockdep_assert_held(&wq_pool_mutex); - if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND)) + if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND) || + wq->unbound_attrs->no_numa) return; /* @@ -4100,52 +3745,37 @@ target_attrs = wq_update_unbound_numa_attrs_buf; 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); /* * Let's determine what needs to be done. If the target cpumask is - * different from wq's, we need to compare it to @pwq's and create - * a new one if they don't match. If the target cpumask equals - * wq's, the default pwq should be used. If @pwq is already the - * default one, nothing to do; otherwise, install the default one. + * different from the default pwq's, we need to compare it to @pwq's + * and create a new one if they don't match. If the target cpumask + * equals the default pwq's, the default pwq should be used. */ - if (wq_calc_node_cpumask(wq->unbound_attrs, node, cpu_off, cpumask)) { + if (wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, cpu_off, cpumask)) { if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask)) - goto out_unlock; + return; } else { - if (pwq == wq->dfl_pwq) - goto out_unlock; - else - goto use_dfl_pwq; + goto use_dfl_pwq; } - mutex_unlock(&wq->mutex); - /* create a new pwq */ pwq = alloc_unbound_pwq(wq, target_attrs); if (!pwq) { - pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n", - wq->name); - mutex_lock(&wq->mutex); + pr_warn("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n", + wq->name); goto use_dfl_pwq; } - /* - * Install the new pwq. As this function is called only from CPU - * hotplug callbacks and applying a new attrs is wrapped with - * get/put_online_cpus(), @wq->unbound_attrs couldn't have changed - * inbetween. - */ + /* Install the new pwq. */ mutex_lock(&wq->mutex); old_pwq = numa_pwq_tbl_install(wq, node, pwq); goto out_unlock; use_dfl_pwq: + mutex_lock(&wq->mutex); spin_lock_irq(&wq->dfl_pwq->pool->lock); get_pwq(wq->dfl_pwq); spin_unlock_irq(&wq->dfl_pwq->pool->lock); @@ -4213,9 +3843,13 @@ struct workqueue_struct *wq; struct pool_workqueue *pwq; + /* see the comment above the definition of WQ_POWER_EFFICIENT */ + if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) + flags |= WQ_UNBOUND; + /* allocate wq and format name */ if (flags & WQ_UNBOUND) - tbl_size = wq_numa_tbl_len * sizeof(wq->numa_pwq_tbl[0]); + tbl_size = nr_node_ids * sizeof(wq->numa_pwq_tbl[0]); wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL); if (!wq) @@ -4257,7 +3891,7 @@ if (flags & WQ_MEM_RECLAIM) { struct worker *rescuer; - rescuer = alloc_worker(); + rescuer = alloc_worker(NUMA_NO_NODE); if (!rescuer) goto err_destroy; @@ -4270,7 +3904,7 @@ } wq->rescuer = rescuer; - rescuer->task->flags |= PF_NO_SETAFFINITY; + kthread_bind_mask(rescuer->task, cpu_possible_mask); wake_up_process(rescuer->task); } @@ -4289,7 +3923,7 @@ pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); - list_add(&wq->list, &workqueues); + list_add_tail_rcu(&wq->list, &workqueues); mutex_unlock(&wq_pool_mutex); @@ -4345,24 +3979,20 @@ * flushing is complete in case freeze races us. */ mutex_lock(&wq_pool_mutex); - list_del_init(&wq->list); + list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); workqueue_sysfs_unregister(wq); - if (wq->rescuer) { + if (wq->rescuer) kthread_stop(wq->rescuer->task); - kfree(wq->rescuer); - wq->rescuer = NULL; - } if (!(wq->flags & WQ_UNBOUND)) { /* * The base ref is never dropped on per-cpu pwqs. Directly - * free the pwqs and wq. + * schedule RCU free. */ - free_percpu(wq->cpu_pwqs); - kfree(wq); + call_rcu_sched(&wq->rcu, rcu_free_wq); } else { /* * We're the sole accessor of @wq at this point. Directly @@ -4422,6 +4052,8 @@ * * Determine whether %current is a workqueue rescuer. Can be used from * work functions to determine whether it's being run off the rescuer task. + * + * Return: %true if %current is a workqueue rescuer. %false otherwise. */ bool current_is_workqueue_rescuer(void) { @@ -4445,7 +4077,7 @@ * workqueue being congested on one CPU doesn't mean the workqueue is also * contested on other CPUs / NUMA nodes. * - * RETURNS: + * Return: * %true if congested, %false otherwise. */ bool workqueue_congested(int cpu, struct workqueue_struct *wq) @@ -4478,7 +4110,7 @@ * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * - * RETURNS: + * Return: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) @@ -4581,6 +4213,166 @@ } } +static void pr_cont_pool_info(struct worker_pool *pool) +{ + pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); + if (pool->node != NUMA_NO_NODE) + pr_cont(" node=%d", pool->node); + pr_cont(" flags=0x%x nice=%d", pool->flags, pool->attrs->nice); +} + +static void pr_cont_work(bool comma, struct work_struct *work) +{ + if (work->func == wq_barrier_func) { + struct wq_barrier *barr; + + barr = container_of(work, struct wq_barrier, work); + + pr_cont("%s BAR(%d)", comma ? "," : "", + task_pid_nr(barr->task)); + } else { + pr_cont("%s %pf", comma ? "," : "", work->func); + } +} + +static void show_pwq(struct pool_workqueue *pwq) +{ + struct worker_pool *pool = pwq->pool; + struct work_struct *work; + struct worker *worker; + bool has_in_flight = false, has_pending = false; + int bkt; + + pr_info(" pwq %d:", pool->id); + pr_cont_pool_info(pool); + + pr_cont(" active=%d/%d%s\n", pwq->nr_active, pwq->max_active, + !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); + + hash_for_each(pool->busy_hash, bkt, worker, hentry) { + if (worker->current_pwq == pwq) { + has_in_flight = true; + break; + } + } + if (has_in_flight) { + bool comma = false; + + pr_info(" in-flight:"); + hash_for_each(pool->busy_hash, bkt, worker, hentry) { + if (worker->current_pwq != pwq) + continue; + + pr_cont("%s %d%s:%pf", comma ? "," : "", + task_pid_nr(worker->task), + worker == pwq->wq->rescuer ? "(RESCUER)" : "", + worker->current_func); + list_for_each_entry(work, &worker->scheduled, entry) + pr_cont_work(false, work); + comma = true; + } + pr_cont("\n"); + } + + list_for_each_entry(work, &pool->worklist, entry) { + if (get_work_pwq(work) == pwq) { + has_pending = true; + break; + } + } + if (has_pending) { + bool comma = false; + + pr_info(" pending:"); + list_for_each_entry(work, &pool->worklist, entry) { + if (get_work_pwq(work) != pwq) + continue; + + pr_cont_work(comma, work); + comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); + } + pr_cont("\n"); + } + + if (!list_empty(&pwq->delayed_works)) { + bool comma = false; + + pr_info(" delayed:"); + list_for_each_entry(work, &pwq->delayed_works, entry) { + pr_cont_work(comma, work); + comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); + } + pr_cont("\n"); + } +} + +/** + * show_workqueue_state - dump workqueue state + * + * Called from a sysrq handler and prints out all busy workqueues and + * pools. + */ +void show_workqueue_state(void) +{ + struct workqueue_struct *wq; + struct worker_pool *pool; + unsigned long flags; + int pi; + + rcu_read_lock_sched(); + + pr_info("Showing busy workqueues and worker pools:\n"); + + list_for_each_entry_rcu(wq, &workqueues, list) { + struct pool_workqueue *pwq; + bool idle = true; + + for_each_pwq(pwq, wq) { + if (pwq->nr_active || !list_empty(&pwq->delayed_works)) { + idle = false; + break; + } + } + if (idle) + continue; + + pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); + + for_each_pwq(pwq, wq) { + spin_lock_irqsave(&pwq->pool->lock, flags); + if (pwq->nr_active || !list_empty(&pwq->delayed_works)) + show_pwq(pwq); + spin_unlock_irqrestore(&pwq->pool->lock, flags); + } + } + + for_each_pool(pool, pi) { + struct worker *worker; + bool first = true; + + spin_lock_irqsave(&pool->lock, flags); + if (pool->nr_workers == pool->nr_idle) + goto next_pool; + + pr_info("pool %d:", pool->id); + pr_cont_pool_info(pool); + pr_cont(" workers=%d", pool->nr_workers); + if (pool->manager) + pr_cont(" manager: %d", + task_pid_nr(pool->manager->task)); + list_for_each_entry(worker, &pool->idle_list, entry) { + pr_cont(" %s%d", first ? "idle: " : "", + task_pid_nr(worker->task)); + first = false; + } + pr_cont("\n"); + next_pool: + spin_unlock_irqrestore(&pool->lock, flags); + } + + rcu_read_unlock_sched(); +} + /* * CPU hotplug. * @@ -4601,28 +4393,25 @@ int cpu = smp_processor_id(); struct worker_pool *pool; struct worker *worker; - int wi; for_each_cpu_worker_pool(pool, cpu) { - WARN_ON_ONCE(cpu != smp_processor_id()); - - mutex_lock(&pool->manager_mutex); + mutex_lock(&pool->attach_mutex); spin_lock_irq(&pool->lock); /* - * We've blocked all manager operations. Make all workers + * We've blocked all attach/detach operations. Make all workers * unbound and set DISASSOCIATED. Before this, 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 may become diasporas. */ - for_each_pool_worker(worker, wi, pool) + for_each_pool_worker(worker, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; spin_unlock_irq(&pool->lock); - mutex_unlock(&pool->manager_mutex); + mutex_unlock(&pool->attach_mutex); /* * Call schedule() so that we cross rq->lock and thus can @@ -4662,24 +4451,35 @@ static void rebind_workers(struct worker_pool *pool) { struct worker *worker; - int wi; - lockdep_assert_held(&pool->manager_mutex); + lockdep_assert_held(&pool->attach_mutex); /* * Restore CPU affinity of all workers. As all idle workers should * be on the run-queue of the associated CPU before any local - * wake-ups for concurrency management happen, restore CPU affinty + * wake-ups for concurrency management happen, restore CPU affinity * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ - for_each_pool_worker(worker, wi, pool) + for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask) < 0); spin_lock_irq(&pool->lock); - for_each_pool_worker(worker, wi, pool) { + /* + * XXX: CPU hotplug notifiers are weird and can call DOWN_FAILED + * w/o preceding DOWN_PREPARE. Work around it. CPU hotplug is + * being reworked and this can go away in time. + */ + if (!(pool->flags & POOL_DISASSOCIATED)) { + spin_unlock_irq(&pool->lock); + return; + } + + pool->flags &= ~POOL_DISASSOCIATED; + + for_each_pool_worker(worker, pool) { unsigned int worker_flags = worker->flags; /* @@ -4731,9 +4531,8 @@ { static cpumask_t cpumask; struct worker *worker; - int wi; - lockdep_assert_held(&pool->manager_mutex); + lockdep_assert_held(&pool->attach_mutex); /* is @cpu allowed for @pool? */ if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) @@ -4745,7 +4544,7 @@ return; /* as we're called from CPU_ONLINE, the following shouldn't fail */ - for_each_pool_worker(worker, wi, pool) + for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask) < 0); } @@ -4754,7 +4553,7 @@ * Workqueues should be brought up before normal priority CPU notifiers. * This will be registered high priority CPU notifier. */ -static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb, +static int workqueue_cpu_up_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -4768,7 +4567,7 @@ for_each_cpu_worker_pool(pool, cpu) { if (pool->nr_workers) continue; - if (create_and_start_worker(pool) < 0) + if (!create_worker(pool)) return NOTIFY_BAD; } break; @@ -4778,19 +4577,14 @@ mutex_lock(&wq_pool_mutex); for_each_pool(pool, pi) { - mutex_lock(&pool->manager_mutex); - - if (pool->cpu == cpu) { - spin_lock_irq(&pool->lock); - pool->flags &= ~POOL_DISASSOCIATED; - spin_unlock_irq(&pool->lock); + mutex_lock(&pool->attach_mutex); + if (pool->cpu == cpu) rebind_workers(pool); - } else if (pool->cpu < 0) { + else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); - } - mutex_unlock(&pool->manager_mutex); + mutex_unlock(&pool->attach_mutex); } /* update NUMA affinity of unbound workqueues */ @@ -4807,7 +4601,7 @@ * Workqueues should be brought down after normal priority CPU notifiers. * This will be registered as low priority CPU notifier. */ -static int __cpuinit workqueue_cpu_down_callback(struct notifier_block *nfb, +static int workqueue_cpu_down_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -4829,6 +4623,7 @@ /* wait for per-cpu unbinding to finish */ flush_work(&unbind_work); + destroy_work_on_stack(&unbind_work); break; } return NOTIFY_OK; @@ -4856,9 +4651,10 @@ * @fn: the function to run * @arg: the function arg * - * This will return the value @fn returns. * 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. + * + * Return: The value @fn returns. */ long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { @@ -4867,6 +4663,7 @@ INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn); schedule_work_on(cpu, &wfc.work); flush_work(&wfc.work); + destroy_work_on_stack(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu); @@ -4886,24 +4683,14 @@ */ void freeze_workqueues_begin(void) { - struct worker_pool *pool; struct workqueue_struct *wq; struct pool_workqueue *pwq; - int pi; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(workqueue_freezing); workqueue_freezing = true; - /* set FREEZING */ - for_each_pool(pool, pi) { - spin_lock_irq(&pool->lock); - WARN_ON_ONCE(pool->flags & POOL_FREEZING); - pool->flags |= POOL_FREEZING; - spin_unlock_irq(&pool->lock); - } - list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) @@ -4923,7 +4710,7 @@ * CONTEXT: * Grabs and releases wq_pool_mutex. * - * RETURNS: + * Return: * %true if some freezable workqueues are still busy. %false if freezing * is complete. */ @@ -4973,21 +4760,13 @@ { struct workqueue_struct *wq; struct pool_workqueue *pwq; - struct worker_pool *pool; - int pi; mutex_lock(&wq_pool_mutex); if (!workqueue_freezing) goto out_unlock; - /* clear FREEZING */ - for_each_pool(pool, pi) { - spin_lock_irq(&pool->lock); - WARN_ON_ONCE(!(pool->flags & POOL_FREEZING)); - pool->flags &= ~POOL_FREEZING; - spin_unlock_irq(&pool->lock); - } + workqueue_freezing = false; /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { @@ -4997,21 +4776,461 @@ mutex_unlock(&wq->mutex); } - workqueue_freezing = false; out_unlock: mutex_unlock(&wq_pool_mutex); } #endif /* CONFIG_FREEZER */ +static int workqueue_apply_unbound_cpumask(void) +{ + LIST_HEAD(ctxs); + int ret = 0; + struct workqueue_struct *wq; + struct apply_wqattrs_ctx *ctx, *n; + + lockdep_assert_held(&wq_pool_mutex); + + list_for_each_entry(wq, &workqueues, list) { + if (!(wq->flags & WQ_UNBOUND)) + continue; + /* creating multiple pwqs breaks ordering guarantee */ + if (wq->flags & __WQ_ORDERED) + continue; + + ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs); + if (!ctx) { + ret = -ENOMEM; + break; + } + + list_add_tail(&ctx->list, &ctxs); + } + + list_for_each_entry_safe(ctx, n, &ctxs, list) { + if (!ret) + apply_wqattrs_commit(ctx); + apply_wqattrs_cleanup(ctx); + } + + return ret; +} + +/** + * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask + * @cpumask: the cpumask to set + * + * The low-level workqueues cpumask is a global cpumask that limits + * the affinity of all unbound workqueues. This function check the @cpumask + * and apply it to all unbound workqueues and updates all pwqs of them. + * + * Retun: 0 - Success + * -EINVAL - Invalid @cpumask + * -ENOMEM - Failed to allocate memory for attrs or pwqs. + */ +int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) +{ + int ret = -EINVAL; + cpumask_var_t saved_cpumask; + + if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_and(cpumask, cpumask, cpu_possible_mask); + if (!cpumask_empty(cpumask)) { + apply_wqattrs_lock(); + + /* save the old wq_unbound_cpumask. */ + cpumask_copy(saved_cpumask, wq_unbound_cpumask); + + /* update wq_unbound_cpumask at first and apply it to wqs. */ + cpumask_copy(wq_unbound_cpumask, cpumask); + ret = workqueue_apply_unbound_cpumask(); + + /* restore the wq_unbound_cpumask when failed. */ + if (ret < 0) + cpumask_copy(wq_unbound_cpumask, saved_cpumask); + + apply_wqattrs_unlock(); + } + + free_cpumask_var(saved_cpumask); + return ret; +} + +#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 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 DEVICE_ATTR_RO(per_cpu); + +static ssize_t 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 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 DEVICE_ATTR_RW(max_active); + +static struct attribute *wq_sysfs_attrs[] = { + &dev_attr_per_cpu.attr, + &dev_attr_max_active.attr, + NULL, +}; +ATTRIBUTE_GROUPS(wq_sysfs); + +static ssize_t wq_pool_ids_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + const char *delim = ""; + int node, written = 0; + + rcu_read_lock_sched(); + 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; +} + +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; + + mutex_lock(&wq->mutex); + written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); + mutex_unlock(&wq->mutex); + + 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; + + lockdep_assert_held(&wq_pool_mutex); + + attrs = alloc_workqueue_attrs(GFP_KERNEL); + if (!attrs) + return NULL; + + copy_workqueue_attrs(attrs, wq->unbound_attrs); + 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 = -ENOMEM; + + apply_wqattrs_lock(); + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + goto out_unlock; + + if (sscanf(buf, "%d", &attrs->nice) == 1 && + attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) + ret = apply_workqueue_attrs_locked(wq, attrs); + else + ret = -EINVAL; + +out_unlock: + apply_wqattrs_unlock(); + 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; + + mutex_lock(&wq->mutex); + written = scnprintf(buf, PAGE_SIZE, "%*pb\n", + cpumask_pr_args(wq->unbound_attrs->cpumask)); + mutex_unlock(&wq->mutex); + 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 = -ENOMEM; + + apply_wqattrs_lock(); + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + goto out_unlock; + + ret = cpumask_parse(buf, attrs->cpumask); + if (!ret) + ret = apply_workqueue_attrs_locked(wq, attrs); + +out_unlock: + apply_wqattrs_unlock(); + free_workqueue_attrs(attrs); + 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 = -ENOMEM; + + apply_wqattrs_lock(); + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + goto out_unlock; + + ret = -EINVAL; + if (sscanf(buf, "%d", &v) == 1) { + attrs->no_numa = !v; + ret = apply_workqueue_attrs_locked(wq, attrs); + } + +out_unlock: + apply_wqattrs_unlock(); + free_workqueue_attrs(attrs); + return ret ?: count; +} + +static struct device_attribute wq_sysfs_unbound_attrs[] = { + __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, +}; + +static struct bus_type wq_subsys = { + .name = "workqueue", + .dev_groups = wq_sysfs_groups, +}; + +static ssize_t wq_unbound_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int written; + + mutex_lock(&wq_pool_mutex); + written = scnprintf(buf, PAGE_SIZE, "%*pb\n", + cpumask_pr_args(wq_unbound_cpumask)); + mutex_unlock(&wq_pool_mutex); + + return written; +} + +static ssize_t wq_unbound_cpumask_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + cpumask_var_t cpumask; + int ret; + + if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; + + ret = cpumask_parse(buf, cpumask); + if (!ret) + ret = workqueue_set_unbound_cpumask(cpumask); + + free_cpumask_var(cpumask); + return ret ? ret : count; +} + +static struct device_attribute wq_sysfs_cpumask_attr = + __ATTR(cpumask, 0644, wq_unbound_cpumask_show, + wq_unbound_cpumask_store); + +static int __init wq_sysfs_init(void) +{ + int err; + + err = subsys_virtual_register(&wq_subsys, NULL); + if (err) + return err; + + return device_create_file(wq_subsys.dev_root, &wq_sysfs_cpumask_attr); +} +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. + * + * Return: 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 applying + * 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; + } + } + } + + dev_set_uevent_suppress(&wq_dev->dev, false); + 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 */ + static void __init wq_numa_init(void) { cpumask_var_t *tbl; int node, cpu; - /* determine NUMA pwq table len - highest node id + 1 */ - for_each_node(node) - wq_numa_tbl_len = max(wq_numa_tbl_len, node + 1); - if (num_possible_nodes() <= 1) return; @@ -5028,7 +5247,7 @@ * available. Build one from cpu_to_node() which should have been * fully initialized by now. */ - tbl = kzalloc(wq_numa_tbl_len * sizeof(tbl[0]), GFP_KERNEL); + tbl = kzalloc(nr_node_ids * sizeof(tbl[0]), GFP_KERNEL); BUG_ON(!tbl); for_each_node(node) @@ -5054,12 +5273,11 @@ 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)) < - WORK_CPU_END * NR_STD_WORKER_POOLS); - WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); + BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); + cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); + pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP); @@ -5092,7 +5310,7 @@ for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; - BUG_ON(create_and_start_worker(pool) < 0); + BUG_ON(!create_worker(pool)); } } @@ -5122,8 +5340,15 @@ WQ_UNBOUND_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); + system_power_efficient_wq = alloc_workqueue("events_power_efficient", + WQ_POWER_EFFICIENT, 0); + system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient", + WQ_FREEZABLE | WQ_POWER_EFFICIENT, + 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || - !system_unbound_wq || !system_freezable_wq); + !system_unbound_wq || !system_freezable_wq || + !system_power_efficient_wq || + !system_freezable_power_efficient_wq); return 0; } early_initcall(init_workqueues);