diff options
Diffstat (limited to 'kernel/workqueue.c')
| -rw-r--r-- | kernel/workqueue.c | 3895 |
1 files changed, 2487 insertions, 1408 deletions
diff --git a/kernel/workqueue.c b/kernel/workqueue.c index fbc6576a83c3..4aa9f5bc6b2d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -41,32 +41,35 @@ #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> +#include <linux/jhash.h> +#include <linux/hashtable.h> +#include <linux/rculist.h> +#include <linux/nodemask.h> +#include <linux/moduleparam.h> +#include <linux/uaccess.h> -#include "workqueue_sched.h" +#include "workqueue_internal.h" enum { /* - * global_cwq flags + * worker_pool flags * - * A bound gcwq is either associated or disassociated with its CPU. + * A bound pool is either associated or disassociated with its CPU. * While associated (!DISASSOCIATED), all workers are bound to the * CPU and none has %WORKER_UNBOUND set and concurrency management * is in effect. * * While DISASSOCIATED, the cpu may be offline and all workers have * %WORKER_UNBOUND set and concurrency management disabled, and may - * be executing on any CPU. The gcwq behaves as an unbound one. + * be executing on any CPU. The pool behaves as an unbound one. * - * Note that DISASSOCIATED can be flipped only while holding - * assoc_mutex of all pools on the gcwq to avoid changing binding - * state while create_worker() is in progress. + * Note that DISASSOCIATED should be flipped only while holding + * manager_mutex to avoid changing binding state while + * create_worker() is in progress. */ - GCWQ_DISASSOCIATED = 1 << 0, /* cpu can't serve workers */ - GCWQ_FREEZING = 1 << 1, /* freeze in progress */ - - /* pool flags */ POOL_MANAGE_WORKERS = 1 << 0, /* need to manage workers */ - POOL_MANAGING_WORKERS = 1 << 1, /* managing workers */ + POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ + POOL_FREEZING = 1 << 3, /* freeze in progress */ /* worker flags */ WORKER_STARTED = 1 << 0, /* started */ @@ -75,15 +78,15 @@ enum { WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ + WORKER_REBOUND = 1 << 8, /* worker was rebound */ - WORKER_NOT_RUNNING = WORKER_PREP | WORKER_UNBOUND | - WORKER_CPU_INTENSIVE, + WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | + WORKER_UNBOUND | WORKER_REBOUND, - NR_WORKER_POOLS = 2, /* # worker pools per gcwq */ + NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ + UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ - BUSY_WORKER_HASH_SIZE = 1 << BUSY_WORKER_HASH_ORDER, - BUSY_WORKER_HASH_MASK = BUSY_WORKER_HASH_SIZE - 1, MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ @@ -100,6 +103,8 @@ enum { */ RESCUER_NICE_LEVEL = -20, HIGHPRI_NICE_LEVEL = -20, + + WQ_NAME_LEN = 24, }; /* @@ -111,48 +116,34 @@ enum { * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. * - * L: gcwq->lock protected. Access with gcwq->lock held. + * L: pool->lock protected. Access with pool->lock held. + * + * X: During normal operation, modification requires pool->lock and should + * be done only from local cpu. Either disabling preemption on local + * 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. * - * X: During normal operation, modification requires gcwq->lock and - * should be done only from local cpu. Either disabling preemption - * on local cpu or grabbing gcwq->lock is enough for read access. - * If GCWQ_DISASSOCIATED is set, it's identical to L. + * PL: wq_pool_mutex protected. * - * F: wq->flush_mutex protected. + * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. * - * W: workqueue_lock protected. + * WQ: wq->mutex protected. + * + * WR: wq->mutex protected for writes. Sched-RCU protected for reads. + * + * MD: wq_mayday_lock protected. */ -struct global_cwq; -struct worker_pool; - -/* - * The poor guys doing the actual heavy lifting. All on-duty workers - * are either serving the manager role, on idle list or on busy hash. - */ -struct worker { - /* on idle list while idle, on busy hash table while busy */ - union { - struct list_head entry; /* L: while idle */ - struct hlist_node hentry; /* L: while busy */ - }; - - struct work_struct *current_work; /* L: work being processed */ - struct cpu_workqueue_struct *current_cwq; /* L: current_work's cwq */ - struct list_head scheduled; /* L: scheduled works */ - struct task_struct *task; /* I: worker task */ - struct worker_pool *pool; /* I: the associated pool */ - /* 64 bytes boundary on 64bit, 32 on 32bit */ - unsigned long last_active; /* L: last active timestamp */ - unsigned int flags; /* X: flags */ - int id; /* I: worker id */ - - /* for rebinding worker to CPU */ - struct work_struct rebind_work; /* L: for busy worker */ -}; +/* struct worker is defined in workqueue_internal.h */ struct worker_pool { - struct global_cwq *gcwq; /* I: the owning gcwq */ + spinlock_t lock; /* the pool lock */ + int cpu; /* I: the associated cpu */ + int node; /* I: the associated node ID */ + int id; /* I: pool ID */ unsigned int flags; /* X: flags */ struct list_head worklist; /* L: list of pending works */ @@ -165,107 +156,145 @@ struct worker_pool { struct timer_list idle_timer; /* L: worker idle timeout */ struct timer_list mayday_timer; /* L: SOS timer for workers */ - struct mutex assoc_mutex; /* protect GCWQ_DISASSOCIATED */ - struct ida worker_ida; /* L: for worker IDs */ -}; + /* a workers is either on busy_hash or idle_list, or the manager */ + DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); + /* L: hash of busy workers */ -/* - * Global per-cpu workqueue. There's one and only one for each cpu - * and all works are queued and processed here regardless of their - * target workqueues. - */ -struct global_cwq { - spinlock_t lock; /* the gcwq lock */ - unsigned int cpu; /* I: the associated cpu */ - unsigned int flags; /* L: GCWQ_* flags */ + /* 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 */ - /* workers are chained either in busy_hash or pool idle_list */ - struct hlist_head busy_hash[BUSY_WORKER_HASH_SIZE]; - /* L: hash of busy workers */ + struct workqueue_attrs *attrs; /* I: worker attributes */ + struct hlist_node hash_node; /* PL: unbound_pool_hash node */ + int refcnt; /* PL: refcnt for unbound pools */ + + /* + * The current concurrency level. As it's likely to be accessed + * from other CPUs during try_to_wake_up(), put it in a separate + * cacheline. + */ + atomic_t nr_running ____cacheline_aligned_in_smp; - struct worker_pool pools[NR_WORKER_POOLS]; - /* normal and highpri pools */ + /* + * Destruction of pool is sched-RCU protected to allow dereferences + * from get_work_pool(). + */ + struct rcu_head rcu; } ____cacheline_aligned_in_smp; /* - * The per-CPU workqueue. The lower WORK_STRUCT_FLAG_BITS of - * work_struct->data are used for flags and thus cwqs need to be - * aligned at two's power of the number of flag bits. + * The per-pool workqueue. While queued, the lower WORK_STRUCT_FLAG_BITS + * of work_struct->data are used for flags and the remaining high bits + * point to the pwq; thus, pwqs need to be aligned at two's power of the + * number of flag bits. */ -struct cpu_workqueue_struct { +struct pool_workqueue { struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ + int refcnt; /* L: reference count */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ int nr_active; /* L: nr of active works */ int max_active; /* L: max active works */ struct list_head delayed_works; /* L: delayed works */ -}; + struct list_head pwqs_node; /* WR: node on wq->pwqs */ + struct list_head mayday_node; /* MD: node on wq->maydays */ + + /* + * Release of unbound pwq is punted to system_wq. See put_pwq() + * and pwq_unbound_release_workfn() for details. pool_workqueue + * itself is also sched-RCU protected so that the first pwq can be + * determined without grabbing wq->mutex. + */ + struct work_struct unbound_release_work; + struct rcu_head rcu; +} __aligned(1 << WORK_STRUCT_FLAG_BITS); /* * Structure used to wait for workqueue flush. */ struct wq_flusher { - struct list_head list; /* F: list of flushers */ - int flush_color; /* F: flush color waiting for */ + struct list_head list; /* WQ: list of flushers */ + int flush_color; /* WQ: flush color waiting for */ struct completion done; /* flush completion */ }; -/* - * All cpumasks are assumed to be always set on UP and thus can't be - * used to determine whether there's something to be done. - */ -#ifdef CONFIG_SMP -typedef cpumask_var_t mayday_mask_t; -#define mayday_test_and_set_cpu(cpu, mask) \ - cpumask_test_and_set_cpu((cpu), (mask)) -#define mayday_clear_cpu(cpu, mask) cpumask_clear_cpu((cpu), (mask)) -#define for_each_mayday_cpu(cpu, mask) for_each_cpu((cpu), (mask)) -#define alloc_mayday_mask(maskp, gfp) zalloc_cpumask_var((maskp), (gfp)) -#define free_mayday_mask(mask) free_cpumask_var((mask)) -#else -typedef unsigned long mayday_mask_t; -#define mayday_test_and_set_cpu(cpu, mask) test_and_set_bit(0, &(mask)) -#define mayday_clear_cpu(cpu, mask) clear_bit(0, &(mask)) -#define for_each_mayday_cpu(cpu, mask) if ((cpu) = 0, (mask)) -#define alloc_mayday_mask(maskp, gfp) true -#define free_mayday_mask(mask) do { } while (0) -#endif +struct wq_device; /* - * The externally visible workqueue abstraction is an array of - * per-CPU workqueues: + * The externally visible workqueue. It relays the issued work items to + * the appropriate worker_pool through its pool_workqueues. */ struct workqueue_struct { - unsigned int flags; /* W: WQ_* flags */ - union { - struct cpu_workqueue_struct __percpu *pcpu; - struct cpu_workqueue_struct *single; - unsigned long v; - } cpu_wq; /* I: cwq's */ - struct list_head list; /* W: list of all workqueues */ - - struct mutex flush_mutex; /* protects wq flushing */ - int work_color; /* F: current work color */ - int flush_color; /* F: current flush color */ - atomic_t nr_cwqs_to_flush; /* flush in progress */ - struct wq_flusher *first_flusher; /* F: first flusher */ - struct list_head flusher_queue; /* F: flush waiters */ - struct list_head flusher_overflow; /* F: flush overflow list */ - - mayday_mask_t mayday_mask; /* cpus requesting rescue */ + struct list_head pwqs; /* WR: all pwqs of this wq */ + struct list_head list; /* PL: list of all workqueues */ + + struct mutex mutex; /* protects this wq */ + int work_color; /* WQ: current work color */ + int flush_color; /* WQ: current flush color */ + atomic_t nr_pwqs_to_flush; /* flush in progress */ + struct wq_flusher *first_flusher; /* WQ: first flusher */ + struct list_head flusher_queue; /* WQ: flush waiters */ + struct list_head flusher_overflow; /* WQ: flush overflow list */ + + struct list_head maydays; /* MD: pwqs requesting rescue */ struct worker *rescuer; /* I: rescue worker */ - int nr_drainers; /* W: drain in progress */ - int saved_max_active; /* W: saved cwq max_active */ + 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 */ + +#ifdef CONFIG_SYSFS + struct wq_device *wq_dev; /* I: for sysfs interface */ +#endif #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif - char name[]; /* I: workqueue name */ + char name[WQ_NAME_LEN]; /* I: workqueue name */ + + /* 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 */ }; +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); + +static bool wq_numa_enabled; /* unbound NUMA affinity enabled */ + +/* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */ +static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; + +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 bool workqueue_freezing; /* PL: have wqs started freezing? */ + +/* the per-cpu worker pools */ +static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], + cpu_worker_pools); + +static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ + +/* PL: hash of all unbound pools keyed by pool->attrs */ +static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); + +/* I: attributes used when instantiating standard unbound pools on demand */ +static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; + struct workqueue_struct *system_wq __read_mostly; EXPORT_SYMBOL_GPL(system_wq); struct workqueue_struct *system_highpri_wq __read_mostly; @@ -277,65 +306,87 @@ EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_freezable_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_wq); +static int worker_thread(void *__worker); +static void copy_workqueue_attrs(struct workqueue_attrs *to, + const struct workqueue_attrs *from); + #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> -#define for_each_worker_pool(pool, gcwq) \ - for ((pool) = &(gcwq)->pools[0]; \ - (pool) < &(gcwq)->pools[NR_WORKER_POOLS]; (pool)++) +#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") -#define for_each_busy_worker(worker, i, pos, gcwq) \ - for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) \ - hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry) +#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") -static inline int __next_gcwq_cpu(int cpu, const struct cpumask *mask, - unsigned int sw) -{ - if (cpu < nr_cpu_ids) { - if (sw & 1) { - cpu = cpumask_next(cpu, mask); - if (cpu < nr_cpu_ids) - return cpu; - } - if (sw & 2) - return WORK_CPU_UNBOUND; - } - return WORK_CPU_NONE; -} +#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 -static inline int __next_wq_cpu(int cpu, const struct cpumask *mask, - struct workqueue_struct *wq) -{ - return __next_gcwq_cpu(cpu, mask, !(wq->flags & WQ_UNBOUND) ? 1 : 2); -} +#define for_each_cpu_worker_pool(pool, cpu) \ + for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ + (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ + (pool)++) -/* - * CPU iterators +/** + * for_each_pool - iterate through all worker_pools in the system + * @pool: iteration cursor + * @pi: integer used for iteration * - * An extra gcwq is defined for an invalid cpu number - * (WORK_CPU_UNBOUND) to host workqueues which are not bound to any - * specific CPU. The following iterators are similar to - * for_each_*_cpu() iterators but also considers the unbound gcwq. + * This must be called either with wq_pool_mutex held or sched RCU read + * locked. If the pool needs to be used beyond the locking in effect, the + * caller is responsible for guaranteeing that the pool stays online. * - * for_each_gcwq_cpu() : possible CPUs + WORK_CPU_UNBOUND - * for_each_online_gcwq_cpu() : online CPUs + WORK_CPU_UNBOUND - * for_each_cwq_cpu() : possible CPUs for bound workqueues, - * WORK_CPU_UNBOUND for unbound workqueues + * The if/else clause exists only for the lockdep assertion and can be + * ignored. */ -#define for_each_gcwq_cpu(cpu) \ - for ((cpu) = __next_gcwq_cpu(-1, cpu_possible_mask, 3); \ - (cpu) < WORK_CPU_NONE; \ - (cpu) = __next_gcwq_cpu((cpu), cpu_possible_mask, 3)) +#define for_each_pool(pool, pi) \ + idr_for_each_entry(&worker_pool_idr, pool, pi) \ + if (({ assert_rcu_or_pool_mutex(); false; })) { } \ + else -#define for_each_online_gcwq_cpu(cpu) \ - for ((cpu) = __next_gcwq_cpu(-1, cpu_online_mask, 3); \ - (cpu) < WORK_CPU_NONE; \ - (cpu) = __next_gcwq_cpu((cpu), cpu_online_mask, 3)) +/** + * 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. + * + * 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; })) { } \ + else -#define for_each_cwq_cpu(cpu, wq) \ - for ((cpu) = __next_wq_cpu(-1, cpu_possible_mask, (wq)); \ - (cpu) < WORK_CPU_NONE; \ - (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq))) +/** + * for_each_pwq - iterate through all pool_workqueues of the specified workqueue + * @pwq: iteration cursor + * @wq: the target workqueue + * + * This must be called either with wq->mutex held or sched RCU read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. + * + * The if/else clause exists only for the lockdep assertion and can be + * ignored. + */ +#define for_each_pwq(pwq, wq) \ + list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node) \ + if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \ + else #ifdef CONFIG_DEBUG_OBJECTS_WORK @@ -453,64 +504,35 @@ static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif -/* Serializes the accesses to the list of workqueues. */ -static DEFINE_SPINLOCK(workqueue_lock); -static LIST_HEAD(workqueues); -static bool workqueue_freezing; /* W: have wqs started freezing? */ - -/* - * The almighty global cpu workqueues. nr_running is the only field - * which is expected to be used frequently by other cpus via - * try_to_wake_up(). Put it in a separate cacheline. - */ -static DEFINE_PER_CPU(struct global_cwq, global_cwq); -static DEFINE_PER_CPU_SHARED_ALIGNED(atomic_t, pool_nr_running[NR_WORKER_POOLS]); - -/* - * Global cpu workqueue and nr_running counter for unbound gcwq. The - * gcwq is always online, has GCWQ_DISASSOCIATED set, and all its - * workers have WORKER_UNBOUND set. - */ -static struct global_cwq unbound_global_cwq; -static atomic_t unbound_pool_nr_running[NR_WORKER_POOLS] = { - [0 ... NR_WORKER_POOLS - 1] = ATOMIC_INIT(0), /* always 0 */ -}; - -static int worker_thread(void *__worker); - -static int worker_pool_pri(struct worker_pool *pool) -{ - return pool - pool->gcwq->pools; -} - -static struct global_cwq *get_gcwq(unsigned int cpu) +/* allocate ID and assign it to @pool */ +static int worker_pool_assign_id(struct worker_pool *pool) { - if (cpu != WORK_CPU_UNBOUND) - return &per_cpu(global_cwq, cpu); - else - return &unbound_global_cwq; -} + int ret; -static atomic_t *get_pool_nr_running(struct worker_pool *pool) -{ - int cpu = pool->gcwq->cpu; - int idx = worker_pool_pri(pool); + lockdep_assert_held(&wq_pool_mutex); - if (cpu != WORK_CPU_UNBOUND) - return &per_cpu(pool_nr_running, cpu)[idx]; - else - return &unbound_pool_nr_running[idx]; + ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL); + if (ret >= 0) { + pool->id = ret; + return 0; + } + return ret; } -static struct cpu_workqueue_struct *get_cwq(unsigned int cpu, - struct workqueue_struct *wq) +/** + * unbound_pwq_by_node - return the unbound pool_workqueue for the given node + * @wq: the target workqueue + * @node: the node ID + * + * This must be called either with pwq_lock held or sched RCU read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. + */ +static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq, + int node) { - if (!(wq->flags & WQ_UNBOUND)) { - if (likely(cpu < nr_cpu_ids)) - return per_cpu_ptr(wq->cpu_wq.pcpu, cpu); - } else if (likely(cpu == WORK_CPU_UNBOUND)) - return wq->cpu_wq.single; - return NULL; + assert_rcu_or_wq_mutex(wq); + return rcu_dereference_raw(wq->numa_pwq_tbl[node]); } static unsigned int work_color_to_flags(int color) @@ -530,19 +552,19 @@ static int work_next_color(int color) } /* - * While queued, %WORK_STRUCT_CWQ is set and non flag bits of a work's data - * contain the pointer to the queued cwq. Once execution starts, the flag - * is cleared and the high bits contain OFFQ flags and CPU number. + * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data + * contain the pointer to the queued pwq. Once execution starts, the flag + * is cleared and the high bits contain OFFQ flags and pool ID. * - * set_work_cwq(), set_work_cpu_and_clear_pending(), mark_work_canceling() - * and clear_work_data() can be used to set the cwq, cpu or clear + * set_work_pwq(), set_work_pool_and_clear_pending(), mark_work_canceling() + * and clear_work_data() can be used to set the pwq, pool or clear * work->data. These functions should only be called while the work is * owned - ie. while the PENDING bit is set. * - * get_work_[g]cwq() can be used to obtain the gcwq or cwq corresponding to - * a work. gcwq is available once the work has been queued anywhere after - * initialization until it is sync canceled. cwq is available only while - * the work item is queued. + * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq + * corresponding to a work. Pool is available once the work has been + * queued anywhere after initialization until it is sync canceled. pwq is + * available only while the work item is queued. * * %WORK_OFFQ_CANCELING is used to mark a work item which is being * canceled. While being canceled, a work item may have its PENDING set @@ -552,20 +574,26 @@ static int work_next_color(int color) static inline void set_work_data(struct work_struct *work, unsigned long data, unsigned long flags) { - BUG_ON(!work_pending(work)); + WARN_ON_ONCE(!work_pending(work)); atomic_long_set(&work->data, data | flags | work_static(work)); } -static void set_work_cwq(struct work_struct *work, - struct cpu_workqueue_struct *cwq, +static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, unsigned long extra_flags) { - set_work_data(work, (unsigned long)cwq, - WORK_STRUCT_PENDING | WORK_STRUCT_CWQ | extra_flags); + set_work_data(work, (unsigned long)pwq, + WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags); +} + +static void set_work_pool_and_keep_pending(struct work_struct *work, + int pool_id) +{ + set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, + WORK_STRUCT_PENDING); } -static void set_work_cpu_and_clear_pending(struct work_struct *work, - unsigned int cpu) +static void set_work_pool_and_clear_pending(struct work_struct *work, + int pool_id) { /* * The following wmb is paired with the implied mb in @@ -574,67 +602,100 @@ static void set_work_cpu_and_clear_pending(struct work_struct *work, * owner. */ smp_wmb(); - set_work_data(work, (unsigned long)cpu << WORK_OFFQ_CPU_SHIFT, 0); + set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0); } static void clear_work_data(struct work_struct *work) { - smp_wmb(); /* see set_work_cpu_and_clear_pending() */ - set_work_data(work, WORK_STRUCT_NO_CPU, 0); + smp_wmb(); /* see set_work_pool_and_clear_pending() */ + set_work_data(work, WORK_STRUCT_NO_POOL, 0); } -static struct cpu_workqueue_struct *get_work_cwq(struct work_struct *work) +static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); - if (data & WORK_STRUCT_CWQ) + if (data & WORK_STRUCT_PWQ) return (void *)(data & WORK_STRUCT_WQ_DATA_MASK); else return NULL; } -static struct global_cwq *get_work_gcwq(struct work_struct *work) +/** + * 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. + * + * All fields of the returned pool are accessible as long as the above + * 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. + */ +static struct worker_pool *get_work_pool(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); - unsigned int cpu; + int pool_id; - if (data & WORK_STRUCT_CWQ) - return ((struct cpu_workqueue_struct *) - (data & WORK_STRUCT_WQ_DATA_MASK))->pool->gcwq; + assert_rcu_or_pool_mutex(); - cpu = data >> WORK_OFFQ_CPU_SHIFT; - if (cpu == WORK_CPU_NONE) + if (data & WORK_STRUCT_PWQ) + return ((struct pool_workqueue *) + (data & WORK_STRUCT_WQ_DATA_MASK))->pool; + + pool_id = data >> WORK_OFFQ_POOL_SHIFT; + if (pool_id == WORK_OFFQ_POOL_NONE) return NULL; - BUG_ON(cpu >= nr_cpu_ids && cpu != WORK_CPU_UNBOUND); - return get_gcwq(cpu); + return idr_find(&worker_pool_idr, pool_id); +} + +/** + * 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. + * %WORK_OFFQ_POOL_NONE if none. + */ +static int get_work_pool_id(struct work_struct *work) +{ + unsigned long data = atomic_long_read(&work->data); + + if (data & WORK_STRUCT_PWQ) + return ((struct pool_workqueue *) + (data & WORK_STRUCT_WQ_DATA_MASK))->pool->id; + + return data >> WORK_OFFQ_POOL_SHIFT; } static void mark_work_canceling(struct work_struct *work) { - struct global_cwq *gcwq = get_work_gcwq(work); - unsigned long cpu = gcwq ? gcwq->cpu : WORK_CPU_NONE; + unsigned long pool_id = get_work_pool_id(work); - set_work_data(work, (cpu << WORK_OFFQ_CPU_SHIFT) | WORK_OFFQ_CANCELING, - WORK_STRUCT_PENDING); + pool_id <<= WORK_OFFQ_POOL_SHIFT; + set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING); } static bool work_is_canceling(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); - return !(data & WORK_STRUCT_CWQ) && (data & WORK_OFFQ_CANCELING); + return !(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_CANCELING); } /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that - * they're being called with gcwq->lock held. + * they're being called with pool->lock held. */ static bool __need_more_worker(struct worker_pool *pool) { - return !atomic_read(get_pool_nr_running(pool)); + return !atomic_read(&pool->nr_running); } /* @@ -642,7 +703,7 @@ static bool __need_more_worker(struct worker_pool *pool) * running workers. * * Note that, because unbound workers never contribute to nr_running, this - * function will always return %true for unbound gcwq as long as the + * function will always return %true for unbound pools as long as the * worklist isn't empty. */ static bool need_more_worker(struct worker_pool *pool) @@ -659,9 +720,8 @@ static bool may_start_working(struct worker_pool *pool) /* Do I need to keep working? Called from currently running workers. */ static bool keep_working(struct worker_pool *pool) { - atomic_t *nr_running = get_pool_nr_running(pool); - - return !list_empty(&pool->worklist) && atomic_read(nr_running) <= 1; + return !list_empty(&pool->worklist) && + atomic_read(&pool->nr_running) <= 1; } /* Do we need a new worker? Called from manager. */ @@ -680,7 +740,7 @@ static bool need_to_manage_workers(struct worker_pool *pool) /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { - bool managing = pool->flags & POOL_MANAGING_WORKERS; + bool managing = mutex_is_locked(&pool->manager_arb); int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; @@ -714,7 +774,7 @@ static struct worker *first_worker(struct worker_pool *pool) * Wake up the first idle worker of @pool. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ static void wake_up_worker(struct worker_pool *pool) { @@ -735,13 +795,13 @@ static void wake_up_worker(struct worker_pool *pool) * CONTEXT: * spin_lock_irq(rq->lock) */ -void wq_worker_waking_up(struct task_struct *task, unsigned int cpu) +void wq_worker_waking_up(struct task_struct *task, int cpu) { struct worker *worker = kthread_data(task); if (!(worker->flags & WORKER_NOT_RUNNING)) { - WARN_ON_ONCE(worker->pool->gcwq->cpu != cpu); - atomic_inc(get_pool_nr_running(worker->pool)); + WARN_ON_ONCE(worker->pool->cpu != cpu); + atomic_inc(&worker->pool->nr_running); } } @@ -760,18 +820,24 @@ void wq_worker_waking_up(struct task_struct *task, unsigned int cpu) * RETURNS: * Worker task on @cpu to wake up, %NULL if none. */ -struct task_struct *wq_worker_sleeping(struct task_struct *task, - unsigned int cpu) +struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) { struct worker *worker = kthread_data(task), *to_wakeup = NULL; - struct worker_pool *pool = worker->pool; - atomic_t *nr_running = get_pool_nr_running(pool); + struct worker_pool *pool; + /* + * Rescuers, which may not have all the fields set up like normal + * workers, also reach here, let's not access anything before + * checking NOT_RUNNING. + */ if (worker->flags & WORKER_NOT_RUNNING) return NULL; + pool = worker->pool; + /* this can only happen on the local cpu */ - BUG_ON(cpu != raw_smp_processor_id()); + if (WARN_ON_ONCE(cpu != raw_smp_processor_id())) + return NULL; /* * The counterpart of the following dec_and_test, implied mb, @@ -781,10 +847,11 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, * NOT_RUNNING is clear. This means that we're bound to and * running on the local cpu w/ rq lock held and preemption * disabled, which in turn means that none else could be - * manipulating idle_list, so dereferencing idle_list without gcwq + * manipulating idle_list, so dereferencing idle_list without pool * lock is safe. */ - if (atomic_dec_and_test(nr_running) && !list_empty(&pool->worklist)) + if (atomic_dec_and_test(&pool->nr_running) && + !list_empty(&pool->worklist)) to_wakeup = first_worker(pool); return to_wakeup ? to_wakeup->task : NULL; } @@ -800,7 +867,7 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, * woken up. * * CONTEXT: - * spin_lock_irq(gcwq->lock) + * spin_lock_irq(pool->lock) */ static inline void worker_set_flags(struct worker *worker, unsigned int flags, bool wakeup) @@ -816,14 +883,12 @@ static inline void worker_set_flags(struct worker *worker, unsigned int flags, */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { - atomic_t *nr_running = get_pool_nr_running(pool); - if (wakeup) { - if (atomic_dec_and_test(nr_running) && + if (atomic_dec_and_test(&pool->nr_running) && !list_empty(&pool->worklist)) wake_up_worker(pool); } else - atomic_dec(nr_running); + atomic_dec(&pool->nr_running); } worker->flags |= flags; @@ -837,7 +902,7 @@ static inline void worker_set_flags(struct worker *worker, unsigned int flags, * Clear @flags in @worker->flags and adjust nr_running accordingly. * * CONTEXT: - * spin_lock_irq(gcwq->lock) + * spin_lock_irq(pool->lock) */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { @@ -855,87 +920,54 @@ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) - atomic_inc(get_pool_nr_running(pool)); + atomic_inc(&pool->nr_running); } /** - * busy_worker_head - return the busy hash head for a work - * @gcwq: gcwq of interest - * @work: work to be hashed - * - * Return hash head of @gcwq for @work. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock). - * - * RETURNS: - * Pointer to the hash head. - */ -static struct hlist_head *busy_worker_head(struct global_cwq *gcwq, - struct work_struct *work) -{ - const int base_shift = ilog2(sizeof(struct work_struct)); - unsigned long v = (unsigned long)work; - - /* simple shift and fold hash, do we need something better? */ - v >>= base_shift; - v += v >> BUSY_WORKER_HASH_ORDER; - v &= BUSY_WORKER_HASH_MASK; - - return &gcwq->busy_hash[v]; -} - -/** - * __find_worker_executing_work - find worker which is executing a work - * @gcwq: gcwq of interest - * @bwh: hash head as returned by busy_worker_head() + * find_worker_executing_work - find worker which is executing a work + * @pool: pool of interest * @work: work to find worker for * - * Find a worker which is executing @work on @gcwq. @bwh should be - * the hash head obtained by calling busy_worker_head() with the same - * work. + * Find a worker which is executing @work on @pool by searching + * @pool->busy_hash which is keyed by the address of @work. For a worker + * to match, its current execution should match the address of @work and + * its work function. This is to avoid unwanted dependency between + * unrelated work executions through a work item being recycled while still + * being executed. + * + * This is a bit tricky. A work item may be freed once its execution + * starts and nothing prevents the freed area from being recycled for + * another work item. If the same work item address ends up being reused + * before the original execution finishes, workqueue will identify the + * recycled work item as currently executing and make it wait until the + * current execution finishes, introducing an unwanted dependency. + * + * This function checks the work item address and work function to avoid + * false positives. Note that this isn't complete as one may construct a + * work function which can introduce dependency onto itself through a + * recycled work item. Well, if somebody wants to shoot oneself in the + * foot that badly, there's only so much we can do, and if such deadlock + * actually occurs, it should be easy to locate the culprit work function. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). * * RETURNS: * Pointer to worker which is executing @work if found, NULL * otherwise. */ -static struct worker *__find_worker_executing_work(struct global_cwq *gcwq, - struct hlist_head *bwh, - struct work_struct *work) +static struct worker *find_worker_executing_work(struct worker_pool *pool, + struct work_struct *work) { struct worker *worker; - struct hlist_node *tmp; - hlist_for_each_entry(worker, tmp, bwh, hentry) - if (worker->current_work == work) + hash_for_each_possible(pool->busy_hash, worker, hentry, + (unsigned long)work) + if (worker->current_work == work && + worker->current_func == work->func) return worker; - return NULL; -} -/** - * find_worker_executing_work - find worker which is executing a work - * @gcwq: gcwq of interest - * @work: work to find worker for - * - * Find a worker which is executing @work on @gcwq. This function is - * identical to __find_worker_executing_work() except that this - * function calculates @bwh itself. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock). - * - * RETURNS: - * Pointer to worker which is executing @work if found, NULL - * otherwise. - */ -static struct worker *find_worker_executing_work(struct global_cwq *gcwq, - struct work_struct *work) -{ - return __find_worker_executing_work(gcwq, busy_worker_head(gcwq, work), - work); + return NULL; } /** @@ -953,7 +985,7 @@ static struct worker *find_worker_executing_work(struct global_cwq *gcwq, * nested inside outer list_for_each_entry_safe(). * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) @@ -979,67 +1011,127 @@ static void move_linked_works(struct work_struct *work, struct list_head *head, *nextp = n; } -static void cwq_activate_delayed_work(struct work_struct *work) +/** + * get_pwq - get an extra reference on the specified pool_workqueue + * @pwq: pool_workqueue to get + * + * Obtain an extra reference on @pwq. The caller should guarantee that + * @pwq has positive refcnt and be holding the matching pool->lock. + */ +static void get_pwq(struct pool_workqueue *pwq) +{ + lockdep_assert_held(&pwq->pool->lock); + WARN_ON_ONCE(pwq->refcnt <= 0); + pwq->refcnt++; +} + +/** + * put_pwq - put a pool_workqueue reference + * @pwq: pool_workqueue to put + * + * Drop a reference of @pwq. If its refcnt reaches zero, schedule its + * destruction. The caller should be holding the matching pool->lock. + */ +static void put_pwq(struct pool_workqueue *pwq) { - struct cpu_workqueue_struct *cwq = get_work_cwq(work); + lockdep_assert_held(&pwq->pool->lock); + if (likely(--pwq->refcnt)) + return; + if (WARN_ON_ONCE(!(pwq->wq->flags & WQ_UNBOUND))) + return; + /* + * @pwq can't be released under pool->lock, bounce to + * pwq_unbound_release_workfn(). This never recurses on the same + * pool->lock as this path is taken only for unbound workqueues and + * the release work item is scheduled on a per-cpu workqueue. To + * avoid lockdep warning, unbound pool->locks are given lockdep + * subclass of 1 in get_unbound_pool(). + */ + schedule_work(&pwq->unbound_release_work); +} + +/** + * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock + * @pwq: pool_workqueue to put (can be %NULL) + * + * put_pwq() with locking. This function also allows %NULL @pwq. + */ +static void put_pwq_unlocked(struct pool_workqueue *pwq) +{ + if (pwq) { + /* + * As both pwqs and pools are sched-RCU protected, the + * following lock operations are safe. + */ + spin_lock_irq(&pwq->pool->lock); + put_pwq(pwq); + spin_unlock_irq(&pwq->pool->lock); + } +} + +static void pwq_activate_delayed_work(struct work_struct *work) +{ + struct pool_workqueue *pwq = get_work_pwq(work); trace_workqueue_activate_work(work); - move_linked_works(work, &cwq->pool->worklist, NULL); + move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); - cwq->nr_active++; + pwq->nr_active++; } -static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) +static void pwq_activate_first_delayed(struct pool_workqueue *pwq) { - struct work_struct *work = list_first_entry(&cwq->delayed_works, + struct work_struct *work = list_first_entry(&pwq->delayed_works, struct work_struct, entry); - cwq_activate_delayed_work(work); + pwq_activate_delayed_work(work); } /** - * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight - * @cwq: cwq of interest + * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight + * @pwq: pwq of interest * @color: color of work which left the queue * * A work either has completed or is removed from pending queue, - * decrement nr_in_flight of its cwq and handle workqueue flushing. + * decrement nr_in_flight of its pwq and handle workqueue flushing. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ -static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) +static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color) { - /* ignore uncolored works */ + /* uncolored work items don't participate in flushing or nr_active */ if (color == WORK_NO_COLOR) - return; + goto out_put; - cwq->nr_in_flight[color]--; + pwq->nr_in_flight[color]--; - cwq->nr_active--; - if (!list_empty(&cwq->delayed_works)) { + pwq->nr_active--; + if (!list_empty(&pwq->delayed_works)) { /* one down, submit a delayed one */ - if (cwq->nr_active < cwq->max_active) - cwq_activate_first_delayed(cwq); + if (pwq->nr_active < pwq->max_active) + pwq_activate_first_delayed(pwq); } /* is flush in progress and are we at the flushing tip? */ - if (likely(cwq->flush_color != color)) - return; + if (likely(pwq->flush_color != color)) + goto out_put; /* are there still in-flight works? */ - if (cwq->nr_in_flight[color]) - return; + if (pwq->nr_in_flight[color]) + goto out_put; - /* this cwq is done, clear flush_color */ - cwq->flush_color = -1; + /* this pwq is done, clear flush_color */ + pwq->flush_color = -1; /* - * If this was the last cwq, wake up the first flusher. It + * If this was the last pwq, wake up the first flusher. It * will handle the rest. */ - if (atomic_dec_and_test(&cwq->wq->nr_cwqs_to_flush)) - complete(&cwq->wq->first_flusher->done); + if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) + complete(&pwq->wq->first_flusher->done); +out_put: + put_pwq(pwq); } /** @@ -1070,7 +1162,8 @@ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) static int try_to_grab_pending(struct work_struct *work, bool is_dwork, unsigned long *flags) { - struct global_cwq *gcwq; + struct worker_pool *pool; + struct pool_workqueue *pwq; local_irq_save(*flags); @@ -1095,41 +1188,43 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ - gcwq = get_work_gcwq(work); - if (!gcwq) + pool = get_work_pool(work); + if (!pool) goto fail; - spin_lock(&gcwq->lock); - if (!list_empty(&work->entry)) { + spin_lock(&pool->lock); + /* + * work->data is guaranteed to point to pwq only while the work + * item is queued on pwq->wq, and both updating work->data to point + * to pwq on queueing and to pool on dequeueing are done under + * pwq->pool->lock. This in turn guarantees that, if work->data + * points to pwq which is associated with a locked pool, the work + * item is currently queued on that pool. + */ + pwq = get_work_pwq(work); + if (pwq && pwq->pool == pool) { + debug_work_deactivate(work); + /* - * This work is queued, but perhaps we locked the wrong gcwq. - * In that case we must see the new value after rmb(), see - * insert_work()->wmb(). + * A delayed work item cannot be grabbed directly because + * it might have linked NO_COLOR work items which, if left + * on the delayed_list, will confuse pwq->nr_active + * management later on and cause stall. Make sure the work + * item is activated before grabbing. */ - smp_rmb(); - if (gcwq == get_work_gcwq(work)) { - debug_work_deactivate(work); + if (*work_data_bits(work) & WORK_STRUCT_DELAYED) + pwq_activate_delayed_work(work); - /* - * A delayed work item cannot be grabbed directly - * because it might have linked NO_COLOR work items - * which, if left on the delayed_list, will confuse - * cwq->nr_active management later on and cause - * stall. Make sure the work item is activated - * before grabbing. - */ - if (*work_data_bits(work) & WORK_STRUCT_DELAYED) - cwq_activate_delayed_work(work); + list_del_init(&work->entry); + pwq_dec_nr_in_flight(get_work_pwq(work), get_work_color(work)); - list_del_init(&work->entry); - cwq_dec_nr_in_flight(get_work_cwq(work), - get_work_color(work)); + /* work->data points to pwq iff queued, point to pool */ + set_work_pool_and_keep_pending(work, pool->id); - spin_unlock(&gcwq->lock); - return 1; - } + spin_unlock(&pool->lock); + return 1; } - spin_unlock(&gcwq->lock); + spin_unlock(&pool->lock); fail: local_irq_restore(*flags); if (work_is_canceling(work)) @@ -1139,39 +1234,32 @@ fail: } /** - * insert_work - insert a work into gcwq - * @cwq: cwq @work belongs to + * insert_work - insert a work into a pool + * @pwq: pwq @work belongs to * @work: work to insert * @head: insertion point * @extra_flags: extra WORK_STRUCT_* flags to set * - * Insert @work which belongs to @cwq into @gcwq after @head. - * @extra_flags is or'd to work_struct flags. + * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to + * work_struct flags. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ -static void insert_work(struct cpu_workqueue_struct *cwq, - struct work_struct *work, struct list_head *head, - unsigned int extra_flags) +static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, + struct list_head *head, unsigned int extra_flags) { - struct worker_pool *pool = cwq->pool; + struct worker_pool *pool = pwq->pool; /* we own @work, set data and link */ - set_work_cwq(work, cwq, extra_flags); - - /* - * Ensure that we get the right work->data if we see the - * result of list_add() below, see try_to_grab_pending(). - */ - smp_wmb(); - + set_work_pwq(work, pwq, extra_flags); list_add_tail(&work->entry, head); + get_pwq(pwq); /* - * Ensure either worker_sched_deactivated() sees the above - * list_add_tail() or we see zero nr_running to avoid workers - * lying around lazily while there are works to be processed. + * Ensure either wq_worker_sleeping() sees the above + * list_add_tail() or we see zero nr_running to avoid workers lying + * around lazily while there are works to be processed. */ smp_mb(); @@ -1181,41 +1269,25 @@ static void insert_work(struct cpu_workqueue_struct *cwq, /* * Test whether @work is being queued from another work executing on the - * same workqueue. This is rather expensive and should only be used from - * cold paths. + * same workqueue. */ static bool is_chained_work(struct workqueue_struct *wq) { - unsigned long flags; - unsigned int cpu; - - for_each_gcwq_cpu(cpu) { - struct global_cwq *gcwq = get_gcwq(cpu); - struct worker *worker; - struct hlist_node *pos; - int i; + struct worker *worker; - spin_lock_irqsave(&gcwq->lock, flags); - for_each_busy_worker(worker, i, pos, gcwq) { - if (worker->task != current) - continue; - spin_unlock_irqrestore(&gcwq->lock, flags); - /* - * I'm @worker, no locking necessary. See if @work - * is headed to the same workqueue. - */ - return worker->current_cwq->wq == wq; - } - spin_unlock_irqrestore(&gcwq->lock, flags); - } - return false; + worker = current_wq_worker(); + /* + * Return %true iff I'm a worker execuing a work item on @wq. If + * I'm @worker, it's safe to dereference it without locking. + */ + return worker && worker->current_pwq->wq == wq; } -static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, +static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { - struct global_cwq *gcwq; - struct cpu_workqueue_struct *cwq; + struct pool_workqueue *pwq; + struct worker_pool *last_pool; struct list_head *worklist; unsigned int work_flags; unsigned int req_cpu = cpu; @@ -1231,72 +1303,85 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, debug_work_activate(work); /* if dying, only works from the same workqueue are allowed */ - if (unlikely(wq->flags & WQ_DRAINING) && + if (unlikely(wq->flags & __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; +retry: + if (req_cpu == WORK_CPU_UNBOUND) + cpu = raw_smp_processor_id(); - /* determine gcwq to use */ - if (!(wq->flags & WQ_UNBOUND)) { - struct global_cwq *last_gcwq; - - if (cpu == WORK_CPU_UNBOUND) - cpu = raw_smp_processor_id(); - - /* - * It's multi cpu. If @work was previously on a different - * cpu, it might still be running there, in which case the - * work needs to be queued on that cpu to guarantee - * non-reentrancy. - */ - gcwq = get_gcwq(cpu); - last_gcwq = get_work_gcwq(work); + /* pwq which will be used unless @work is executing elsewhere */ + if (!(wq->flags & WQ_UNBOUND)) + pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); + else + pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); - if (last_gcwq && last_gcwq != gcwq) { - struct worker *worker; + /* + * If @work was previously on a different pool, it might still be + * running there, in which case the work needs to be queued on that + * pool to guarantee non-reentrancy. + */ + last_pool = get_work_pool(work); + if (last_pool && last_pool != pwq->pool) { + struct worker *worker; - spin_lock(&last_gcwq->lock); + spin_lock(&last_pool->lock); - worker = find_worker_executing_work(last_gcwq, work); + worker = find_worker_executing_work(last_pool, work); - if (worker && worker->current_cwq->wq == wq) - gcwq = last_gcwq; - else { - /* meh... not running there, queue here */ - spin_unlock(&last_gcwq->lock); - spin_lock(&gcwq->lock); - } + if (worker && worker->current_pwq->wq == wq) { + pwq = worker->current_pwq; } else { - spin_lock(&gcwq->lock); + /* meh... not running there, queue here */ + spin_unlock(&last_pool->lock); + spin_lock(&pwq->pool->lock); } } else { - gcwq = get_gcwq(WORK_CPU_UNBOUND); - spin_lock(&gcwq->lock); + spin_lock(&pwq->pool->lock); + } + + /* + * pwq is determined and locked. For unbound pools, we could have + * raced with pwq release and it could already be dead. If its + * refcnt is zero, repeat pwq selection. Note that pwqs never die + * without another pwq replacing it in the numa_pwq_tbl or while + * work items are executing on it, so the retrying is guaranteed to + * make forward-progress. + */ + if (unlikely(!pwq->refcnt)) { + if (wq->flags & WQ_UNBOUND) { + spin_unlock(&pwq->pool->lock); + cpu_relax(); + goto retry; + } + /* oops */ + WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", + wq->name, cpu); } - /* gcwq determined, get cwq and queue */ - cwq = get_cwq(gcwq->cpu, wq); - trace_workqueue_queue_work(req_cpu, cwq, work); + /* pwq determined, queue */ + trace_workqueue_queue_work(req_cpu, pwq, work); if (WARN_ON(!list_empty(&work->entry))) { - spin_unlock(&gcwq->lock); + spin_unlock(&pwq->pool->lock); return; } - cwq->nr_in_flight[cwq->work_color]++; - work_flags = work_color_to_flags(cwq->work_color); + pwq->nr_in_flight[pwq->work_color]++; + work_flags = work_color_to_flags(pwq->work_color); - if (likely(cwq->nr_active < cwq->max_active)) { + if (likely(pwq->nr_active < pwq->max_active)) { trace_workqueue_activate_work(work); - cwq->nr_active++; - worklist = &cwq->pool->worklist; + pwq->nr_active++; + worklist = &pwq->pool->worklist; } else { work_flags |= WORK_STRUCT_DELAYED; - worklist = &cwq->delayed_works; + worklist = &pwq->delayed_works; } - insert_work(cwq, work, worklist, work_flags); + insert_work(pwq, work, worklist, work_flags); - spin_unlock(&gcwq->lock); + spin_unlock(&pwq->pool->lock); } /** @@ -1328,38 +1413,20 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL_GPL(queue_work_on); -/** - * queue_work - queue work on a workqueue - * @wq: workqueue to use - * @work: work to queue - * - * Returns %false if @work was already on a queue, %true otherwise. - * - * We queue the work to the CPU on which it was submitted, but if the CPU dies - * it can be processed by another CPU. - */ -bool queue_work(struct workqueue_struct *wq, struct work_struct *work) -{ - return queue_work_on(WORK_CPU_UNBOUND, wq, work); -} -EXPORT_SYMBOL_GPL(queue_work); - void delayed_work_timer_fn(unsigned long __data) { struct delayed_work *dwork = (struct delayed_work *)__data; - struct cpu_workqueue_struct *cwq = get_work_cwq(&dwork->work); /* should have been called from irqsafe timer with irq already off */ - __queue_work(dwork->cpu, cwq->wq, &dwork->work); + __queue_work(dwork->cpu, dwork->wq, &dwork->work); } -EXPORT_SYMBOL_GPL(delayed_work_timer_fn); +EXPORT_SYMBOL(delayed_work_timer_fn); static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; - unsigned int lcpu; WARN_ON_ONCE(timer->function != delayed_work_timer_fn || timer->data != (unsigned long)dwork); @@ -1379,30 +1446,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, timer_stats_timer_set_start_info(&dwork->timer); - /* - * This stores cwq for the moment, for the timer_fn. Note that the - * work's gcwq is preserved to allow reentrance detection for - * delayed works. - */ - if (!(wq->flags & WQ_UNBOUND)) { - struct global_cwq *gcwq = get_work_gcwq(work); - - /* - * If we cannot get the last gcwq from @work directly, - * select the last CPU such that it avoids unnecessarily - * triggering non-reentrancy check in __queue_work(). - */ - lcpu = cpu; - if (gcwq) - lcpu = gcwq->cpu; - if (lcpu == WORK_CPU_UNBOUND) - lcpu = raw_smp_processor_id(); - } else { - lcpu = WORK_CPU_UNBOUND; - } - - set_work_cwq(work, get_cwq(lcpu, wq), 0); - + dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; @@ -1444,21 +1488,6 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, EXPORT_SYMBOL_GPL(queue_delayed_work_on); /** - * queue_delayed_work - queue work on a workqueue after delay - * @wq: workqueue to use - * @dwork: delayable work to queue - * @delay: number of jiffies to wait before queueing - * - * Equivalent to queue_delayed_work_on() but tries to use the local CPU. - */ -bool queue_delayed_work(struct workqueue_struct *wq, - struct delayed_work *dwork, unsigned long delay) -{ - return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); -} -EXPORT_SYMBOL_GPL(queue_delayed_work); - -/** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU * @cpu: CPU number to execute work on * @wq: workqueue to use @@ -1497,21 +1526,6 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, EXPORT_SYMBOL_GPL(mod_delayed_work_on); /** - * mod_delayed_work - modify delay of or queue a delayed work - * @wq: workqueue to use - * @dwork: work to queue - * @delay: number of jiffies to wait before queueing - * - * mod_delayed_work_on() on local CPU. - */ -bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, - unsigned long delay) -{ - return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); -} -EXPORT_SYMBOL_GPL(mod_delayed_work); - -/** * worker_enter_idle - enter idle state * @worker: worker which is entering idle state * @@ -1519,16 +1533,16 @@ EXPORT_SYMBOL_GPL(mod_delayed_work); * necessary. * * LOCKING: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ static void worker_enter_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; - struct global_cwq *gcwq = pool->gcwq; - BUG_ON(worker->flags & WORKER_IDLE); - BUG_ON(!list_empty(&worker->entry) && - (worker->hentry.next || worker->hentry.pprev)); + if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) || + WARN_ON_ONCE(!list_empty(&worker->entry) && + (worker->hentry.next || worker->hentry.pprev))) + return; /* can't use worker_set_flags(), also called from start_worker() */ worker->flags |= WORKER_IDLE; @@ -1542,14 +1556,14 @@ static void worker_enter_idle(struct worker *worker) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* - * Sanity check nr_running. Because gcwq_unbind_fn() releases - * gcwq->lock between setting %WORKER_UNBOUND and zapping + * Sanity check nr_running. Because wq_unbind_fn() releases + * pool->lock between setting %WORKER_UNBOUND and zapping * nr_running, the warning may trigger spuriously. Check iff * unbind is not in progress. */ - WARN_ON_ONCE(!(gcwq->flags & GCWQ_DISASSOCIATED) && + WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && pool->nr_workers == pool->nr_idle && - atomic_read(get_pool_nr_running(pool))); + atomic_read(&pool->nr_running)); } /** @@ -1559,72 +1573,71 @@ static void worker_enter_idle(struct worker *worker) * @worker is leaving idle state. Update stats. * * LOCKING: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ static void worker_leave_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; - BUG_ON(!(worker->flags & WORKER_IDLE)); + if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE))) + return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; list_del_init(&worker->entry); } /** - * worker_maybe_bind_and_lock - bind worker to its cpu if possible and lock gcwq - * @worker: self + * 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 rogue workers and rescuers to bind + * 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 gcwq may be + * 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 gcwq and verifies the - * binding against %GCWQ_DISASSOCIATED which is set during + * 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 gcwq->lock + * Might sleep. Called without any lock but returns with pool->lock * held. * * RETURNS: - * %true if the associated gcwq is online (@worker is successfully + * %true if the associated pool is online (@worker is successfully * bound), %false if offline. */ -static bool worker_maybe_bind_and_lock(struct worker *worker) -__acquires(&gcwq->lock) +static bool worker_maybe_bind_and_lock(struct worker_pool *pool) +__acquires(&pool->lock) { - struct global_cwq *gcwq = worker->pool->gcwq; - struct task_struct *task = worker->task; - while (true) { /* * The following call may fail, succeed or succeed * without actually migrating the task to the cpu if * it races with cpu hotunplug operation. Verify - * against GCWQ_DISASSOCIATED. + * against POOL_DISASSOCIATED. */ - if (!(gcwq->flags & GCWQ_DISASSOCIATED)) - set_cpus_allowed_ptr(task, get_cpu_mask(gcwq->cpu)); + if (!(pool->flags & POOL_DISASSOCIATED)) + set_cpus_allowed_ptr(current, pool->attrs->cpumask); - spin_lock_irq(&gcwq->lock); - if (gcwq->flags & GCWQ_DISASSOCIATED) + spin_lock_irq(&pool->lock); + if (pool->flags & POOL_DISASSOCIATED) return false; - if (task_cpu(task) == gcwq->cpu && - cpumask_equal(¤t->cpus_allowed, - get_cpu_mask(gcwq->cpu))) + if (task_cpu(current) == pool->cpu && + cpumask_equal(¤t->cpus_allowed, pool->attrs->cpumask)) return true; - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); /* * We've raced with CPU hot[un]plug. Give it a breather @@ -1637,118 +1650,6 @@ __acquires(&gcwq->lock) } } -/* - * Rebind an idle @worker to its CPU. worker_thread() will test - * list_empty(@worker->entry) before leaving idle and call this function. - */ -static void idle_worker_rebind(struct worker *worker) -{ - struct global_cwq *gcwq = worker->pool->gcwq; - - /* CPU may go down again inbetween, clear UNBOUND only on success */ - if (worker_maybe_bind_and_lock(worker)) - worker_clr_flags(worker, WORKER_UNBOUND); - - /* rebind complete, become available again */ - list_add(&worker->entry, &worker->pool->idle_list); - spin_unlock_irq(&gcwq->lock); -} - -/* - * Function for @worker->rebind.work used to rebind unbound busy workers to - * the associated cpu which is coming back online. This is scheduled by - * cpu up but can race with other cpu hotplug operations and may be - * executed twice without intervening cpu down. - */ -static void busy_worker_rebind_fn(struct work_struct *work) -{ - struct worker *worker = container_of(work, struct worker, rebind_work); - struct global_cwq *gcwq = worker->pool->gcwq; - - if (worker_maybe_bind_and_lock(worker)) - worker_clr_flags(worker, WORKER_UNBOUND); - - spin_unlock_irq(&gcwq->lock); -} - -/** - * rebind_workers - rebind all workers of a gcwq to the associated CPU - * @gcwq: gcwq of interest - * - * @gcwq->cpu is coming online. Rebind all workers to the CPU. Rebinding - * is different for idle and busy ones. - * - * Idle ones will be removed from the idle_list and woken up. They will - * add themselves back after completing rebind. This ensures that the - * idle_list doesn't contain any unbound workers when re-bound busy workers - * try to perform local wake-ups for concurrency management. - * - * Busy workers can rebind after they finish their current work items. - * Queueing the rebind work item at the head of the scheduled list is - * enough. Note that nr_running will be properly bumped as busy workers - * rebind. - * - * On return, all non-manager workers are scheduled for rebind - see - * manage_workers() for the manager special case. Any idle worker - * including the manager will not appear on @idle_list until rebind is - * complete, making local wake-ups safe. - */ -static void rebind_workers(struct global_cwq *gcwq) -{ - struct worker_pool *pool; - struct worker *worker, *n; - struct hlist_node *pos; - int i; - - lockdep_assert_held(&gcwq->lock); - - for_each_worker_pool(pool, gcwq) - lockdep_assert_held(&pool->assoc_mutex); - - /* dequeue and kick idle ones */ - for_each_worker_pool(pool, gcwq) { - list_for_each_entry_safe(worker, n, &pool->idle_list, entry) { - /* - * idle workers should be off @pool->idle_list - * until rebind is complete to avoid receiving - * premature local wake-ups. - */ - list_del_init(&worker->entry); - - /* - * worker_thread() will see the above dequeuing - * and call idle_worker_rebind(). - */ - wake_up_process(worker->task); - } - } - - /* rebind busy workers */ - for_each_busy_worker(worker, i, pos, gcwq) { - struct work_struct *rebind_work = &worker->rebind_work; - struct workqueue_struct *wq; - - if (test_and_set_bit(WORK_STRUCT_PENDING_BIT, - work_data_bits(rebind_work))) - continue; - - debug_work_activate(rebind_work); - - /* - * wq doesn't really matter but let's keep @worker->pool - * and @cwq->pool consistent for sanity. - */ - if (worker_pool_pri(worker->pool)) - wq = system_highpri_wq; - else - wq = system_wq; - - insert_work(get_cwq(gcwq->cpu, wq), rebind_work, - worker->scheduled.next, - work_color_to_flags(WORK_NO_COLOR)); - } -} - static struct worker *alloc_worker(void) { struct worker *worker; @@ -1757,7 +1658,6 @@ static struct worker *alloc_worker(void) if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); - INIT_WORK(&worker->rebind_work, busy_worker_rebind_fn); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } @@ -1780,19 +1680,25 @@ static struct worker *alloc_worker(void) */ static struct worker *create_worker(struct worker_pool *pool) { - struct global_cwq *gcwq = pool->gcwq; - const char *pri = worker_pool_pri(pool) ? "H" : ""; struct worker *worker = NULL; int id = -1; + char id_buf[16]; - spin_lock_irq(&gcwq->lock); - while (ida_get_new(&pool->worker_ida, &id)) { - spin_unlock_irq(&gcwq->lock); - if (!ida_pre_get(&pool->worker_ida, GFP_KERNEL)) - goto fail; - spin_lock_irq(&gcwq->lock); - } - spin_unlock_irq(&gcwq->lock); + 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(); + if (id < 0) + goto fail; worker = alloc_worker(); if (!worker) @@ -1801,41 +1707,47 @@ static struct worker *create_worker(struct worker_pool *pool) worker->pool = pool; worker->id = id; - if (gcwq->cpu != WORK_CPU_UNBOUND) - worker->task = kthread_create_on_node(worker_thread, - worker, cpu_to_node(gcwq->cpu), - "kworker/%u:%d%s", gcwq->cpu, id, pri); + if (pool->cpu >= 0) + snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id, + pool->attrs->nice < 0 ? "H" : ""); else - worker->task = kthread_create(worker_thread, worker, - "kworker/u:%d%s", id, pri); + snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id); + + worker->task = kthread_create_on_node(worker_thread, worker, pool->node, + "kworker/%s", id_buf); if (IS_ERR(worker->task)) goto fail; - if (worker_pool_pri(pool)) - set_user_nice(worker->task, HIGHPRI_NICE_LEVEL); + /* + * 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; /* - * Determine CPU binding of the new worker depending on - * %GCWQ_DISASSOCIATED. The caller is responsible for ensuring the - * flag remains stable across this function. See the comments - * above the flag definition for details. - * - * As an unbound worker may later become a regular one if CPU comes - * online, make sure every worker has %PF_THREAD_BOUND set. + * The caller is responsible for ensuring %POOL_DISASSOCIATED + * remains stable across this function. See the comments above the + * flag definition for details. */ - if (!(gcwq->flags & GCWQ_DISASSOCIATED)) { - kthread_bind(worker->task, gcwq->cpu); - } else { - worker->task->flags |= PF_THREAD_BOUND; + if (pool->flags & POOL_DISASSOCIATED) worker->flags |= WORKER_UNBOUND; - } + + /* successful, commit the pointer to idr */ + spin_lock_irq(&pool->lock); + idr_replace(&pool->worker_idr, worker, worker->id); + spin_unlock_irq(&pool->lock); return worker; + fail: if (id >= 0) { - spin_lock_irq(&gcwq->lock); - ida_remove(&pool->worker_ida, id); - spin_unlock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); + idr_remove(&pool->worker_idr, id); + spin_unlock_irq(&pool->lock); } kfree(worker); return NULL; @@ -1845,10 +1757,10 @@ fail: * start_worker - start a newly created worker * @worker: worker to start * - * Make the gcwq aware of @worker and start it. + * Make the pool aware of @worker and start it. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ static void start_worker(struct worker *worker) { @@ -1859,23 +1771,49 @@ static void start_worker(struct worker *worker) } /** + * 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 @gcwq stats accordingly. + * Destroy @worker and adjust @pool stats accordingly. * * CONTEXT: - * spin_lock_irq(gcwq->lock) which is released and regrabbed. + * spin_lock_irq(pool->lock) which is released and regrabbed. */ static void destroy_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; - struct global_cwq *gcwq = pool->gcwq; - int id = worker->id; + + lockdep_assert_held(&pool->manager_mutex); + lockdep_assert_held(&pool->lock); /* sanity check frenzy */ - BUG_ON(worker->current_work); - BUG_ON(!list_empty(&worker->scheduled)); + if (WARN_ON(worker->current_work) || + WARN_ON(!list_empty(&worker->scheduled))) + return; if (worker->flags & WORKER_STARTED) pool->nr_workers--; @@ -1885,21 +1823,21 @@ static void destroy_worker(struct worker *worker) list_del_init(&worker->entry); worker->flags |= WORKER_DIE; - spin_unlock_irq(&gcwq->lock); + idr_remove(&pool->worker_idr, worker->id); + + spin_unlock_irq(&pool->lock); kthread_stop(worker->task); kfree(worker); - spin_lock_irq(&gcwq->lock); - ida_remove(&pool->worker_ida, id); + spin_lock_irq(&pool->lock); } static void idle_worker_timeout(unsigned long __pool) { struct worker_pool *pool = (void *)__pool; - struct global_cwq *gcwq = pool->gcwq; - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); if (too_many_workers(pool)) { struct worker *worker; @@ -1918,35 +1856,33 @@ static void idle_worker_timeout(unsigned long __pool) } } - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); } -static bool send_mayday(struct work_struct *work) +static void send_mayday(struct work_struct *work) { - struct cpu_workqueue_struct *cwq = get_work_cwq(work); - struct workqueue_struct *wq = cwq->wq; - unsigned int cpu; + struct pool_workqueue *pwq = get_work_pwq(work); + struct workqueue_struct *wq = pwq->wq; - if (!(wq->flags & WQ_RESCUER)) - return false; + lockdep_assert_held(&wq_mayday_lock); + + if (!wq->rescuer) + return; /* mayday mayday mayday */ - cpu = cwq->pool->gcwq->cpu; - /* WORK_CPU_UNBOUND can't be set in cpumask, use cpu 0 instead */ - if (cpu == WORK_CPU_UNBOUND) - cpu = 0; - if (!mayday_test_and_set_cpu(cpu, wq->mayday_mask)) + if (list_empty(&pwq->mayday_node)) { + list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); - return true; + } } -static void gcwq_mayday_timeout(unsigned long __pool) +static void pool_mayday_timeout(unsigned long __pool) { struct worker_pool *pool = (void *)__pool; - struct global_cwq *gcwq = pool->gcwq; struct work_struct *work; - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&wq_mayday_lock); /* for wq->maydays */ + spin_lock(&pool->lock); if (need_to_create_worker(pool)) { /* @@ -1959,7 +1895,8 @@ static void gcwq_mayday_timeout(unsigned long __pool) send_mayday(work); } - spin_unlock_irq(&gcwq->lock); + spin_unlock(&pool->lock); + spin_unlock_irq(&wq_mayday_lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } @@ -1974,28 +1911,26 @@ static void gcwq_mayday_timeout(unsigned long __pool) * sent to all rescuers with works scheduled on @pool to resolve * possible allocation deadlock. * - * On return, need_to_create_worker() is guaranteed to be false and - * may_start_working() true. + * On return, need_to_create_worker() is guaranteed to be %false and + * may_start_working() %true. * * LOCKING: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed + * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. * * RETURNS: - * false if no action was taken and gcwq->lock stayed locked, true + * %false if no action was taken and pool->lock stayed locked, %true * otherwise. */ static bool maybe_create_worker(struct worker_pool *pool) -__releases(&gcwq->lock) -__acquires(&gcwq->lock) +__releases(&pool->lock) +__acquires(&pool->lock) { - struct global_cwq *gcwq = pool->gcwq; - if (!need_to_create_worker(pool)) return false; restart: - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); @@ -2006,9 +1941,10 @@ restart: worker = create_worker(pool); if (worker) { del_timer_sync(&pool->mayday_timer); - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); start_worker(worker); - BUG_ON(need_to_create_worker(pool)); + if (WARN_ON_ONCE(need_to_create_worker(pool))) + goto restart; return true; } @@ -2023,7 +1959,7 @@ restart: } del_timer_sync(&pool->mayday_timer); - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); if (need_to_create_worker(pool)) goto restart; return true; @@ -2037,11 +1973,11 @@ restart: * IDLE_WORKER_TIMEOUT. * * LOCKING: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed + * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Called only from manager. * * RETURNS: - * false if no action was taken and gcwq->lock stayed locked, true + * %false if no action was taken and pool->lock stayed locked, %true * otherwise. */ static bool maybe_destroy_workers(struct worker_pool *pool) @@ -2071,63 +2007,58 @@ static bool maybe_destroy_workers(struct worker_pool *pool) * manage_workers - manage worker pool * @worker: self * - * Assume the manager role and manage gcwq worker pool @worker belongs + * Assume the manager role and manage the worker pool @worker belongs * to. At any given time, there can be only zero or one manager per - * gcwq. The exclusion is handled automatically by this function. + * pool. The exclusion is handled automatically by this function. * * The caller can safely start processing works on false return. On * true return, it's guaranteed that need_to_create_worker() is false * and may_start_working() is true. * * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed + * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * * RETURNS: - * false if no action was taken and gcwq->lock stayed locked, true if - * some action was taken. + * spin_lock_irq(pool->lock) which may be released and regrabbed + * multiple times. Does GFP_KERNEL allocations. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; bool ret = false; - if (pool->flags & POOL_MANAGING_WORKERS) - return ret; - - pool->flags |= POOL_MANAGING_WORKERS; - /* - * To simplify both worker management and CPU hotplug, hold off - * management while hotplug is in progress. CPU hotplug path can't - * grab %POOL_MANAGING_WORKERS to achieve this because that can - * lead to idle worker depletion (all become busy thinking someone - * else is managing) which in turn can result in deadlock under - * extreme circumstances. Use @pool->assoc_mutex to synchronize - * manager against CPU hotplug. + * 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 + * else is managing the pool and the worker which failed trylock + * can proceed to executing work items. This means that anyone + * 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. * - * assoc_mutex would always be free unless CPU hotplug is in - * progress. trylock first without dropping @gcwq->lock. + * 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 (unlikely(!mutex_trylock(&pool->assoc_mutex))) { - spin_unlock_irq(&pool->gcwq->lock); - mutex_lock(&pool->assoc_mutex); - /* - * CPU hotplug could have happened while we were waiting - * for assoc_mutex. Hotplug itself can't handle us - * because manager isn't either on idle or busy list, and - * @gcwq's state and ours could have deviated. - * - * As hotplug is now excluded via assoc_mutex, we can - * simply try to bind. It will succeed or fail depending - * on @gcwq's current state. Try it and adjust - * %WORKER_UNBOUND accordingly. - */ - if (worker_maybe_bind_and_lock(worker)) - worker->flags &= ~WORKER_UNBOUND; - else - worker->flags |= WORKER_UNBOUND; + if (!mutex_trylock(&pool->manager_arb)) + return ret; + /* + * 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); ret = true; } @@ -2140,8 +2071,8 @@ static bool manage_workers(struct worker *worker) ret |= maybe_destroy_workers(pool); ret |= maybe_create_worker(pool); - pool->flags &= ~POOL_MANAGING_WORKERS; - mutex_unlock(&pool->assoc_mutex); + mutex_unlock(&pool->manager_mutex); + mutex_unlock(&pool->manager_arb); return ret; } @@ -2157,18 +2088,15 @@ static bool manage_workers(struct worker *worker) * call this function to process a work. * * CONTEXT: - * spin_lock_irq(gcwq->lock) which is released and regrabbed. + * spin_lock_irq(pool->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) -__releases(&gcwq->lock) -__acquires(&gcwq->lock) +__releases(&pool->lock) +__acquires(&pool->lock) { - struct cpu_workqueue_struct *cwq = get_work_cwq(work); + struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; - struct global_cwq *gcwq = pool->gcwq; - struct hlist_head *bwh = busy_worker_head(gcwq, work); - bool cpu_intensive = cwq->wq->flags & WQ_CPU_INTENSIVE; - work_func_t f = work->func; + bool cpu_intensive = pwq->wq->flags & WQ_CPU_INTENSIVE; int work_color; struct worker *collision; #ifdef CONFIG_LOCKDEP @@ -2186,11 +2114,11 @@ __acquires(&gcwq->lock) /* * Ensure we're on the correct CPU. DISASSOCIATED test is * necessary to avoid spurious warnings from rescuers servicing the - * unbound or a disassociated gcwq. + * unbound or a disassociated pool. */ WARN_ON_ONCE(!(worker->flags & WORKER_UNBOUND) && - !(gcwq->flags & GCWQ_DISASSOCIATED) && - raw_smp_processor_id() != gcwq->cpu); + !(pool->flags & POOL_DISASSOCIATED) && + raw_smp_processor_id() != pool->cpu); /* * A single work shouldn't be executed concurrently by @@ -2198,7 +2126,7 @@ __acquires(&gcwq->lock) * already processing the work. If so, defer the work to the * currently executing one. */ - collision = __find_worker_executing_work(gcwq, bwh, work); + collision = find_worker_executing_work(pool, work); if (unlikely(collision)) { move_linked_works(work, &collision->scheduled, NULL); return; @@ -2206,9 +2134,10 @@ __acquires(&gcwq->lock) /* claim and dequeue */ debug_work_deactivate(work); - hlist_add_head(&worker->hentry, bwh); + hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); worker->current_work = work; - worker->current_cwq = cwq; + worker->current_func = work->func; + worker->current_pwq = pwq; work_color = get_work_color(work); list_del_init(&work->entry); @@ -2221,53 +2150,56 @@ __acquires(&gcwq->lock) worker_set_flags(worker, WORKER_CPU_INTENSIVE, true); /* - * Unbound gcwq isn't concurrency managed and work items should be + * Unbound pool isn't concurrency managed and work items should be * executed ASAP. Wake up another worker if necessary. */ if ((worker->flags & WORKER_UNBOUND) && need_more_worker(pool)) wake_up_worker(pool); /* - * Record the last CPU and clear PENDING which should be the last - * update to @work. Also, do this inside @gcwq->lock so that + * Record the last pool and clear PENDING which should be the last + * update to @work. Also, do this inside @pool->lock so that * PENDING and queued state changes happen together while IRQ is * disabled. */ - set_work_cpu_and_clear_pending(work, gcwq->cpu); + set_work_pool_and_clear_pending(work, pool->id); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); - lock_map_acquire_read(&cwq->wq->lockdep_map); + lock_map_acquire_read(&pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); trace_workqueue_execute_start(work); - f(work); + worker->current_func(work); /* * While we must be careful to not use "work" after this, the trace * point will only record its address. */ trace_workqueue_execute_end(work); lock_map_release(&lockdep_map); - lock_map_release(&cwq->wq->lockdep_map); + lock_map_release(&pwq->wq->lockdep_map); if (unlikely(in_atomic() || lockdep_depth(current) > 0)) { pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n" " last function: %pf\n", - current->comm, preempt_count(), task_pid_nr(current), f); + current->comm, preempt_count(), task_pid_nr(current), + worker->current_func); debug_show_held_locks(current); dump_stack(); } - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); /* clear cpu intensive status */ if (unlikely(cpu_intensive)) worker_clr_flags(worker, WORKER_CPU_INTENSIVE); /* we're done with it, release */ - hlist_del_init(&worker->hentry); + hash_del(&worker->hentry); worker->current_work = NULL; - worker->current_cwq = NULL; - cwq_dec_nr_in_flight(cwq, work_color); + worker->current_func = NULL; + worker->current_pwq = NULL; + worker->desc_valid = false; + pwq_dec_nr_in_flight(pwq, work_color); } /** @@ -2279,7 +2211,7 @@ __acquires(&gcwq->lock) * fetches a work from the top and executes it. * * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed + * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) @@ -2295,36 +2227,28 @@ static void process_scheduled_works(struct worker *worker) * worker_thread - the worker thread function * @__worker: self * - * The gcwq worker thread function. There's a single dynamic pool of - * these per each cpu. These workers process all works regardless of - * their specific target workqueue. The only exception is works which - * belong to workqueues with a rescuer which will be explained in - * rescuer_thread(). + * The worker thread function. All workers belong to a worker_pool - + * either a per-cpu one or dynamic unbound one. These workers process all + * 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(). */ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct worker_pool *pool = worker->pool; - struct global_cwq *gcwq = pool->gcwq; /* tell the scheduler that this is a workqueue worker */ worker->task->flags |= PF_WQ_WORKER; woke_up: - spin_lock_irq(&gcwq->lock); - - /* we are off idle list if destruction or rebind is requested */ - if (unlikely(list_empty(&worker->entry))) { - spin_unlock_irq(&gcwq->lock); - - /* if DIE is set, destruction is requested */ - if (worker->flags & WORKER_DIE) { - worker->task->flags &= ~PF_WQ_WORKER; - return 0; - } + spin_lock_irq(&pool->lock); - /* otherwise, rebind */ - idle_worker_rebind(worker); - goto woke_up; + /* am I supposed to die? */ + if (unlikely(worker->flags & WORKER_DIE)) { + spin_unlock_irq(&pool->lock); + WARN_ON_ONCE(!list_empty(&worker->entry)); + worker->task->flags &= ~PF_WQ_WORKER; + return 0; } worker_leave_idle(worker); @@ -2342,14 +2266,16 @@ recheck: * preparing to process a work or actually processing it. * Make sure nobody diddled with it while I was sleeping. */ - BUG_ON(!list_empty(&worker->scheduled)); + WARN_ON_ONCE(!list_empty(&worker->scheduled)); /* - * When control reaches this point, we're guaranteed to have - * at least one idle worker or that someone else has already - * assumed the manager role. + * Finish PREP stage. We're guaranteed to have at least one idle + * worker or that someone else has already assumed the manager + * role. This is where @worker starts participating in concurrency + * management if applicable and concurrency management is restored + * after being rebound. See rebind_workers() for details. */ - worker_clr_flags(worker, WORKER_PREP); + worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = @@ -2373,95 +2299,106 @@ sleep: goto recheck; /* - * gcwq->lock is held and there's no work to process and no - * need to manage, sleep. Workers are woken up only while - * holding gcwq->lock or from local cpu, so setting the - * current state before releasing gcwq->lock is enough to - * prevent losing any event. + * pool->lock is held and there's no work to process and no need to + * manage, sleep. Workers are woken up only while holding + * pool->lock or from local cpu, so setting the current state + * before releasing pool->lock is enough to prevent losing any + * event. */ worker_enter_idle(worker); __set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); schedule(); goto woke_up; } /** * rescuer_thread - the rescuer thread function - * @__wq: the associated workqueue + * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each - * workqueue which has WQ_RESCUER set. + * workqueue which has WQ_MEM_RECLAIM set. * - * Regular work processing on a gcwq may block trying to create a new + * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of * developing into deadlock if some works currently on the same queue * need to be processed to satisfy the GFP_KERNEL allocation. This is * the problem rescuer solves. * - * When such condition is possible, the gcwq summons rescuers of all - * workqueues which have works queued on the gcwq and let them process + * When such condition is possible, the pool summons rescuers of all + * workqueues which have works queued on the pool and let them process * those works so that forward progress can be guaranteed. * * This should happen rarely. */ -static int rescuer_thread(void *__wq) +static int rescuer_thread(void *__rescuer) { - struct workqueue_struct *wq = __wq; - struct worker *rescuer = wq->rescuer; + struct worker *rescuer = __rescuer; + struct workqueue_struct *wq = rescuer->rescue_wq; struct list_head *scheduled = &rescuer->scheduled; - bool is_unbound = wq->flags & WQ_UNBOUND; - unsigned int cpu; set_user_nice(current, RESCUER_NICE_LEVEL); + + /* + * Mark rescuer as worker too. As WORKER_PREP is never cleared, it + * doesn't participate in concurrency management. + */ + rescuer->task->flags |= PF_WQ_WORKER; repeat: set_current_state(TASK_INTERRUPTIBLE); if (kthread_should_stop()) { __set_current_state(TASK_RUNNING); + rescuer->task->flags &= ~PF_WQ_WORKER; return 0; } - /* - * See whether any cpu is asking for help. Unbounded - * workqueues use cpu 0 in mayday_mask for CPU_UNBOUND. - */ - for_each_mayday_cpu(cpu, wq->mayday_mask) { - unsigned int tcpu = is_unbound ? WORK_CPU_UNBOUND : cpu; - struct cpu_workqueue_struct *cwq = get_cwq(tcpu, wq); - struct worker_pool *pool = cwq->pool; - struct global_cwq *gcwq = pool->gcwq; + /* see whether any pwq is asking for help */ + spin_lock_irq(&wq_mayday_lock); + + while (!list_empty(&wq->maydays)) { + struct pool_workqueue *pwq = list_first_entry(&wq->maydays, + struct pool_workqueue, mayday_node); + struct worker_pool *pool = pwq->pool; struct work_struct *work, *n; __set_current_state(TASK_RUNNING); - mayday_clear_cpu(cpu, wq->mayday_mask); + list_del_init(&pwq->mayday_node); + + spin_unlock_irq(&wq_mayday_lock); /* migrate to the target cpu if possible */ + worker_maybe_bind_and_lock(pool); rescuer->pool = pool; - worker_maybe_bind_and_lock(rescuer); /* * Slurp in all works issued via this workqueue and * process'em. */ - BUG_ON(!list_empty(&rescuer->scheduled)); + WARN_ON_ONCE(!list_empty(&rescuer->scheduled)); list_for_each_entry_safe(work, n, &pool->worklist, entry) - if (get_work_cwq(work) == cwq) + if (get_work_pwq(work) == pwq) move_linked_works(work, scheduled, &n); process_scheduled_works(rescuer); /* - * Leave this gcwq. If keep_working() is %true, notify a + * Leave this pool. If keep_working() is %true, notify a * regular worker; otherwise, we end up with 0 concurrency * and stalling the execution. */ if (keep_working(pool)) wake_up_worker(pool); - spin_unlock_irq(&gcwq->lock); + rescuer->pool = NULL; + spin_unlock(&pool->lock); + spin_lock(&wq_mayday_lock); } + spin_unlock_irq(&wq_mayday_lock); + + /* rescuers should never participate in concurrency management */ + WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); goto repeat; } @@ -2479,7 +2416,7 @@ static void wq_barrier_func(struct work_struct *work) /** * insert_wq_barrier - insert a barrier work - * @cwq: cwq to insert barrier into + * @pwq: pwq to insert barrier into * @barr: wq_barrier to insert * @target: target work to attach @barr to * @worker: worker currently executing @target, NULL if @target is not executing @@ -2496,12 +2433,12 @@ static void wq_barrier_func(struct work_struct *work) * after a work with LINKED flag set. * * Note that when @worker is non-NULL, @target may be modified - * underneath us, so we can't reliably determine cwq from @target. + * underneath us, so we can't reliably determine pwq from @target. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ -static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, +static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { @@ -2509,7 +2446,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, unsigned int linked = 0; /* - * debugobject calls are safe here even with gcwq->lock locked + * debugobject calls are safe here even with pool->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. @@ -2534,23 +2471,23 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, } debug_work_activate(&barr->work); - insert_work(cwq, &barr->work, head, + insert_work(pwq, &barr->work, head, work_color_to_flags(WORK_NO_COLOR) | linked); } /** - * flush_workqueue_prep_cwqs - prepare cwqs for workqueue flushing + * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing * @wq: workqueue being flushed * @flush_color: new flush color, < 0 for no-op * @work_color: new work color, < 0 for no-op * - * Prepare cwqs for workqueue flushing. + * Prepare pwqs for workqueue flushing. * - * If @flush_color is non-negative, flush_color on all cwqs should be - * -1. If no cwq has in-flight commands at the specified color, all - * cwq->flush_color's stay at -1 and %false is returned. If any cwq - * has in flight commands, its cwq->flush_color is set to - * @flush_color, @wq->nr_cwqs_to_flush is updated accordingly, cwq + * If @flush_color is non-negative, flush_color on all pwqs should be + * -1. If no pwq has in-flight commands at the specified color, all + * pwq->flush_color's stay at -1 and %false is returned. If any pwq + * has in flight commands, its pwq->flush_color is set to + * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq * wakeup logic is armed and %true is returned. * * The caller should have initialized @wq->first_flusher prior to @@ -2558,53 +2495,52 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, * @flush_color is negative, no flush color update is done and %false * is returned. * - * If @work_color is non-negative, all cwqs should have the same + * If @work_color is non-negative, all pwqs should have the same * work_color which is previous to @work_color and all will be * advanced to @work_color. * * CONTEXT: - * mutex_lock(wq->flush_mutex). + * mutex_lock(wq->mutex). * * RETURNS: * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ -static bool flush_workqueue_prep_cwqs(struct workqueue_struct *wq, +static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, int flush_color, int work_color) { bool wait = false; - unsigned int cpu; + struct pool_workqueue *pwq; if (flush_color >= 0) { - BUG_ON(atomic_read(&wq->nr_cwqs_to_flush)); - atomic_set(&wq->nr_cwqs_to_flush, 1); + WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush)); + atomic_set(&wq->nr_pwqs_to_flush, 1); } - for_each_cwq_cpu(cpu, wq) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - struct global_cwq *gcwq = cwq->pool->gcwq; + for_each_pwq(pwq, wq) { + struct worker_pool *pool = pwq->pool; - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); if (flush_color >= 0) { - BUG_ON(cwq->flush_color != -1); + WARN_ON_ONCE(pwq->flush_color != -1); - if (cwq->nr_in_flight[flush_color]) { - cwq->flush_color = flush_color; - atomic_inc(&wq->nr_cwqs_to_flush); + if (pwq->nr_in_flight[flush_color]) { + pwq->flush_color = flush_color; + atomic_inc(&wq->nr_pwqs_to_flush); wait = true; } } if (work_color >= 0) { - BUG_ON(work_color != work_next_color(cwq->work_color)); - cwq->work_color = work_color; + WARN_ON_ONCE(work_color != work_next_color(pwq->work_color)); + pwq->work_color = work_color; } - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); } - if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_cwqs_to_flush)) + if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) complete(&wq->first_flusher->done); return wait; @@ -2614,11 +2550,8 @@ static bool flush_workqueue_prep_cwqs(struct workqueue_struct *wq, * flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush * - * Forces execution of the workqueue and blocks until its completion. - * This is typically used in driver shutdown handlers. - * - * We sleep until all works which were queued on entry have been handled, - * but we are not livelocked by new incoming ones. + * This function sleeps until all work items which were queued on entry + * have finished execution, but it is not livelocked by new incoming ones. */ void flush_workqueue(struct workqueue_struct *wq) { @@ -2632,7 +2565,7 @@ void flush_workqueue(struct workqueue_struct *wq) lock_map_acquire(&wq->lockdep_map); lock_map_release(&wq->lockdep_map); - mutex_lock(&wq->flush_mutex); + mutex_lock(&wq->mutex); /* * Start-to-wait phase @@ -2645,17 +2578,17 @@ void flush_workqueue(struct workqueue_struct *wq) * becomes our flush_color and work_color is advanced * by one. */ - BUG_ON(!list_empty(&wq->flusher_overflow)); + WARN_ON_ONCE(!list_empty(&wq->flusher_overflow)); this_flusher.flush_color = wq->work_color; wq->work_color = next_color; if (!wq->first_flusher) { /* no flush in progress, become the first flusher */ - BUG_ON(wq->flush_color != this_flusher.flush_color); + WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); wq->first_flusher = &this_flusher; - if (!flush_workqueue_prep_cwqs(wq, wq->flush_color, + if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, wq->work_color)) { /* nothing to flush, done */ wq->flush_color = next_color; @@ -2664,9 +2597,9 @@ void flush_workqueue(struct workqueue_struct *wq) } } else { /* wait in queue */ - BUG_ON(wq->flush_color == this_flusher.flush_color); + WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color); list_add_tail(&this_flusher.list, &wq->flusher_queue); - flush_workqueue_prep_cwqs(wq, -1, wq->work_color); + flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } } else { /* @@ -2677,7 +2610,7 @@ void flush_workqueue(struct workqueue_struct *wq) list_add_tail(&this_flusher.list, &wq->flusher_overflow); } - mutex_unlock(&wq->flush_mutex); + mutex_unlock(&wq->mutex); wait_for_completion(&this_flusher.done); @@ -2690,7 +2623,7 @@ void flush_workqueue(struct workqueue_struct *wq) if (wq->first_flusher != &this_flusher) return; - mutex_lock(&wq->flush_mutex); + mutex_lock(&wq->mutex); /* we might have raced, check again with mutex held */ if (wq->first_flusher != &this_flusher) @@ -2698,8 +2631,8 @@ void flush_workqueue(struct workqueue_struct *wq) wq->first_flusher = NULL; - BUG_ON(!list_empty(&this_flusher.list)); - BUG_ON(wq->flush_color != this_flusher.flush_color); + WARN_ON_ONCE(!list_empty(&this_flusher.list)); + WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); while (true) { struct wq_flusher *next, *tmp; @@ -2712,8 +2645,8 @@ void flush_workqueue(struct workqueue_struct *wq) complete(&next->done); } - BUG_ON(!list_empty(&wq->flusher_overflow) && - wq->flush_color != work_next_color(wq->work_color)); + WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) && + wq->flush_color != work_next_color(wq->work_color)); /* this flush_color is finished, advance by one */ wq->flush_color = work_next_color(wq->flush_color); @@ -2733,25 +2666,25 @@ void flush_workqueue(struct workqueue_struct *wq) list_splice_tail_init(&wq->flusher_overflow, &wq->flusher_queue); - flush_workqueue_prep_cwqs(wq, -1, wq->work_color); + flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } if (list_empty(&wq->flusher_queue)) { - BUG_ON(wq->flush_color != wq->work_color); + WARN_ON_ONCE(wq->flush_color != wq->work_color); break; } /* * Need to flush more colors. Make the next flusher - * the new first flusher and arm cwqs. + * the new first flusher and arm pwqs. */ - BUG_ON(wq->flush_color == wq->work_color); - BUG_ON(wq->flush_color != next->flush_color); + WARN_ON_ONCE(wq->flush_color == wq->work_color); + WARN_ON_ONCE(wq->flush_color != next->flush_color); list_del_init(&next->list); wq->first_flusher = next; - if (flush_workqueue_prep_cwqs(wq, wq->flush_color, -1)) + if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) break; /* @@ -2762,7 +2695,7 @@ void flush_workqueue(struct workqueue_struct *wq) } out_unlock: - mutex_unlock(&wq->flush_mutex); + mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(flush_workqueue); @@ -2780,76 +2713,77 @@ EXPORT_SYMBOL_GPL(flush_workqueue); void drain_workqueue(struct workqueue_struct *wq) { unsigned int flush_cnt = 0; - unsigned int cpu; + struct pool_workqueue *pwq; /* * __queue_work() needs to test whether there are drainers, is much * hotter than drain_workqueue() and already looks at @wq->flags. - * Use WQ_DRAINING so that queue doesn't have to check nr_drainers. + * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. */ - spin_lock(&workqueue_lock); + mutex_lock(&wq->mutex); if (!wq->nr_drainers++) - wq->flags |= WQ_DRAINING; - spin_unlock(&workqueue_lock); + wq->flags |= __WQ_DRAINING; + mutex_unlock(&wq->mutex); reflush: flush_workqueue(wq); - for_each_cwq_cpu(cpu, wq) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + mutex_lock(&wq->mutex); + + for_each_pwq(pwq, wq) { bool drained; - spin_lock_irq(&cwq->pool->gcwq->lock); - drained = !cwq->nr_active && list_empty(&cwq->delayed_works); - spin_unlock_irq(&cwq->pool->gcwq->lock); + spin_lock_irq(&pwq->pool->lock); + drained = !pwq->nr_active && list_empty(&pwq->delayed_works); + spin_unlock_irq(&pwq->pool->lock); if (drained) continue; if (++flush_cnt == 10 || (flush_cnt % 100 == 0 && flush_cnt <= 1000)) - pr_warn("workqueue %s: flush on destruction isn't complete after %u tries\n", + pr_warn("workqueue %s: drain_workqueue() isn't complete after %u tries\n", wq->name, flush_cnt); + + mutex_unlock(&wq->mutex); goto reflush; } - spin_lock(&workqueue_lock); if (!--wq->nr_drainers) - wq->flags &= ~WQ_DRAINING; - spin_unlock(&workqueue_lock); + wq->flags &= ~__WQ_DRAINING; + mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(drain_workqueue); static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr) { struct worker *worker = NULL; - struct global_cwq *gcwq; - struct cpu_workqueue_struct *cwq; + struct worker_pool *pool; + struct pool_workqueue *pwq; might_sleep(); - gcwq = get_work_gcwq(work); - if (!gcwq) + + local_irq_disable(); + pool = get_work_pool(work); + if (!pool) { + local_irq_enable(); return false; + } - spin_lock_irq(&gcwq->lock); - if (!list_empty(&work->entry)) { - /* - * See the comment near try_to_grab_pending()->smp_rmb(). - * If it was re-queued to a different gcwq under us, we - * are not going to wait. - */ - smp_rmb(); - cwq = get_work_cwq(work); - if (unlikely(!cwq || gcwq != cwq->pool->gcwq)) + spin_lock(&pool->lock); + /* see the comment in try_to_grab_pending() with the same code */ + pwq = get_work_pwq(work); + if (pwq) { + if (unlikely(pwq->pool != pool)) goto already_gone; } else { - worker = find_worker_executing_work(gcwq, work); + worker = find_worker_executing_work(pool, work); if (!worker) goto already_gone; - cwq = worker->current_cwq; + pwq = worker->current_pwq; } - insert_wq_barrier(cwq, barr, work, worker); - spin_unlock_irq(&gcwq->lock); + insert_wq_barrier(pwq, barr, work, worker); + spin_unlock_irq(&pool->lock); /* * If @max_active is 1 or rescuer is in use, flushing another work @@ -2857,15 +2791,15 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr) * flusher is not running on the same workqueue by verifying write * access. */ - if (cwq->wq->saved_max_active == 1 || cwq->wq->flags & WQ_RESCUER) - lock_map_acquire(&cwq->wq->lockdep_map); + if (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer) + lock_map_acquire(&pwq->wq->lockdep_map); else - lock_map_acquire_read(&cwq->wq->lockdep_map); - lock_map_release(&cwq->wq->lockdep_map); + lock_map_acquire_read(&pwq->wq->lockdep_map); + lock_map_release(&pwq->wq->lockdep_map); return true; already_gone: - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); return false; } @@ -2961,8 +2895,7 @@ bool flush_delayed_work(struct delayed_work *dwork) { local_irq_disable(); if (del_timer_sync(&dwork->timer)) - __queue_work(dwork->cpu, - get_work_cwq(&dwork->work)->wq, &dwork->work); + __queue_work(dwork->cpu, dwork->wq, &dwork->work); local_irq_enable(); return flush_work(&dwork->work); } @@ -2992,7 +2925,8 @@ bool cancel_delayed_work(struct delayed_work *dwork) if (unlikely(ret < 0)) return false; - set_work_cpu_and_clear_pending(&dwork->work, work_cpu(&dwork->work)); + set_work_pool_and_clear_pending(&dwork->work, + get_work_pool_id(&dwork->work)); local_irq_restore(flags); return ret; } @@ -3014,66 +2948,6 @@ bool cancel_delayed_work_sync(struct delayed_work *dwork) EXPORT_SYMBOL(cancel_delayed_work_sync); /** - * schedule_work_on - put work task on a specific cpu - * @cpu: cpu to put the work task on - * @work: job to be done - * - * This puts a job on a specific cpu - */ -bool schedule_work_on(int cpu, struct work_struct *work) -{ - return queue_work_on(cpu, system_wq, work); -} -EXPORT_SYMBOL(schedule_work_on); - -/** - * schedule_work - put work task in global workqueue - * @work: job to be done - * - * Returns %false if @work was already on the kernel-global workqueue and - * %true otherwise. - * - * This puts a job in the kernel-global workqueue if it was not already - * queued and leaves it in the same position on the kernel-global - * workqueue otherwise. - */ -bool schedule_work(struct work_struct *work) -{ - return queue_work(system_wq, work); -} -EXPORT_SYMBOL(schedule_work); - -/** - * schedule_delayed_work_on - queue work in global workqueue on CPU after delay - * @cpu: cpu to use - * @dwork: job to be done - * @delay: number of jiffies to wait - * - * After waiting for a given time this puts a job in the kernel-global - * workqueue on the specified CPU. - */ -bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, - unsigned long delay) -{ - return queue_delayed_work_on(cpu, system_wq, dwork, delay); -} -EXPORT_SYMBOL(schedule_delayed_work_on); - -/** - * schedule_delayed_work - put work task in global workqueue after delay - * @dwork: job to be done - * @delay: number of jiffies to wait or 0 for immediate execution - * - * After waiting for a given time this puts a job in the kernel-global - * workqueue. - */ -bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) -{ - return queue_delayed_work(system_wq, dwork, delay); -} -EXPORT_SYMBOL(schedule_delayed_work); - -/** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * @@ -3166,51 +3040,1025 @@ int execute_in_process_context(work_func_t fn, struct execute_work *ew) } EXPORT_SYMBOL_GPL(execute_in_process_context); -int keventd_up(void) +#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) { - return system_wq != NULL; + 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 int alloc_cwqs(struct workqueue_struct *wq) +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; + /* - * cwqs are forced aligned according to WORK_STRUCT_FLAG_BITS. - * Make sure that the alignment isn't lower than that of - * unsigned long long. + * Adjusting max_active or creating new pwqs by applyting + * attributes breaks ordering guarantee. Disallow exposing ordered + * workqueues. */ - const size_t size = sizeof(struct cpu_workqueue_struct); - const size_t align = max_t(size_t, 1 << WORK_STRUCT_FLAG_BITS, - __alignof__(unsigned long long)); + if (WARN_ON(wq->flags & __WQ_ORDERED)) + return -EINVAL; - if (!(wq->flags & WQ_UNBOUND)) - wq->cpu_wq.pcpu = __alloc_percpu(size, align); - else { - void *ptr; + wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); + if (!wq_dev) + return -ENOMEM; + + wq_dev->wq = wq; + wq_dev->dev.bus = &wq_subsys; + wq_dev->dev.init_name = wq->name; + wq_dev->dev.release = wq_device_release; + + /* + * unbound_attrs are created separately. Suppress uevent until + * everything is ready. + */ + dev_set_uevent_suppress(&wq_dev->dev, true); + + ret = device_register(&wq_dev->dev); + if (ret) { + kfree(wq_dev); + wq->wq_dev = NULL; + return ret; + } + + if (wq->flags & WQ_UNBOUND) { + struct device_attribute *attr; + + for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { + ret = device_create_file(&wq_dev->dev, attr); + if (ret) { + device_unregister(&wq_dev->dev); + wq->wq_dev = NULL; + return ret; + } + } + } + + kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); + return 0; +} + +/** + * workqueue_sysfs_unregister - undo workqueue_sysfs_register() + * @wq: the workqueue to unregister + * + * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. + */ +static void workqueue_sysfs_unregister(struct workqueue_struct *wq) +{ + struct wq_device *wq_dev = wq->wq_dev; + + if (!wq->wq_dev) + return; + + wq->wq_dev = NULL; + device_unregister(&wq_dev->dev); +} +#else /* CONFIG_SYSFS */ +static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } +#endif /* CONFIG_SYSFS */ + +/** + * free_workqueue_attrs - free a workqueue_attrs + * @attrs: workqueue_attrs to free + * + * Undo alloc_workqueue_attrs(). + */ +void free_workqueue_attrs(struct workqueue_attrs *attrs) +{ + if (attrs) { + free_cpumask_var(attrs->cpumask); + kfree(attrs); + } +} + +/** + * alloc_workqueue_attrs - allocate a workqueue_attrs + * @gfp_mask: allocation mask to use + * + * Allocate a new workqueue_attrs, initialize with default settings and + * return it. Returns NULL on failure. + */ +struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask) +{ + struct workqueue_attrs *attrs; + + attrs = kzalloc(sizeof(*attrs), gfp_mask); + if (!attrs) + goto fail; + if (!alloc_cpumask_var(&attrs->cpumask, gfp_mask)) + goto fail; + + cpumask_copy(attrs->cpumask, cpu_possible_mask); + return attrs; +fail: + free_workqueue_attrs(attrs); + return NULL; +} + +static void copy_workqueue_attrs(struct workqueue_attrs *to, + const struct workqueue_attrs *from) +{ + to->nice = from->nice; + cpumask_copy(to->cpumask, from->cpumask); +} + +/* hash value of the content of @attr */ +static u32 wqattrs_hash(const struct workqueue_attrs *attrs) +{ + u32 hash = 0; + + hash = jhash_1word(attrs->nice, hash); + hash = jhash(cpumask_bits(attrs->cpumask), + BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); + return hash; +} + +/* content equality test */ +static bool wqattrs_equal(const struct workqueue_attrs *a, + const struct workqueue_attrs *b) +{ + if (a->nice != b->nice) + return false; + if (!cpumask_equal(a->cpumask, b->cpumask)) + return false; + return true; +} + +/** + * 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 + * inside @pool proper are initialized and put_unbound_pool() can be called + * on @pool safely to release it. + */ +static int init_worker_pool(struct worker_pool *pool) +{ + spin_lock_init(&pool->lock); + pool->id = -1; + pool->cpu = -1; + pool->node = NUMA_NO_NODE; + pool->flags |= POOL_DISASSOCIATED; + INIT_LIST_HEAD(&pool->worklist); + INIT_LIST_HEAD(&pool->idle_list); + hash_init(pool->busy_hash); + + init_timer_deferrable(&pool->idle_timer); + pool->idle_timer.function = idle_worker_timeout; + pool->idle_timer.data = (unsigned long)pool; + + setup_timer(&pool->mayday_timer, pool_mayday_timeout, + (unsigned long)pool); + + mutex_init(&pool->manager_arb); + mutex_init(&pool->manager_mutex); + idr_init(&pool->worker_idr); + + INIT_HLIST_NODE(&pool->hash_node); + pool->refcnt = 1; + + /* shouldn't fail above this point */ + pool->attrs = alloc_workqueue_attrs(GFP_KERNEL); + if (!pool->attrs) + return -ENOMEM; + return 0; +} + +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); + free_workqueue_attrs(pool->attrs); + kfree(pool); +} + +/** + * put_unbound_pool - put a worker_pool + * @pool: worker_pool to put + * + * Put @pool. If its refcnt reaches zero, it gets destroyed in sched-RCU + * safe manner. get_unbound_pool() calls this function on its failure path + * and this function should be able to release pools which went through, + * successfully or not, init_worker_pool(). + * + * Should be called with wq_pool_mutex held. + */ +static void put_unbound_pool(struct worker_pool *pool) +{ + struct worker *worker; + + lockdep_assert_held(&wq_pool_mutex); + + if (--pool->refcnt) + return; + + /* sanity checks */ + if (WARN_ON(!(pool->flags & POOL_DISASSOCIATED)) || + WARN_ON(!list_empty(&pool->worklist))) + return; + + /* release id and unhash */ + if (pool->id >= 0) + idr_remove(&worker_pool_idr, pool->id); + hash_del(&pool->hash_node); + + /* + * Become the manager and destroy all workers. Grabbing + * manager_arb prevents @pool's workers from blocking on + * manager_mutex. + */ + mutex_lock(&pool->manager_arb); + mutex_lock(&pool->manager_mutex); + spin_lock_irq(&pool->lock); + + while ((worker = first_worker(pool))) + destroy_worker(worker); + WARN_ON(pool->nr_workers || pool->nr_idle); + + spin_unlock_irq(&pool->lock); + mutex_unlock(&pool->manager_mutex); + mutex_unlock(&pool->manager_arb); + + /* shut down the timers */ + del_timer_sync(&pool->idle_timer); + del_timer_sync(&pool->mayday_timer); + + /* sched-RCU protected to allow dereferences from get_work_pool() */ + call_rcu_sched(&pool->rcu, rcu_free_pool); +} + +/** + * get_unbound_pool - get a worker_pool with the specified attributes + * @attrs: the attributes of the worker_pool to get + * + * 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. + * + * Should be called with wq_pool_mutex held. + */ +static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) +{ + u32 hash = wqattrs_hash(attrs); + struct worker_pool *pool; + int node; + + lockdep_assert_held(&wq_pool_mutex); + + /* do we already have a matching pool? */ + hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { + if (wqattrs_equal(pool->attrs, attrs)) { + pool->refcnt++; + goto out_unlock; + } + } + + /* nope, create a new one */ + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + 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); + + /* 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) + goto fail; + + /* install */ + hash_add(unbound_pool_hash, &pool->hash_node, hash); +out_unlock: + return pool; +fail: + if (pool) + put_unbound_pool(pool); + return NULL; +} + +static void rcu_free_pwq(struct rcu_head *rcu) +{ + kmem_cache_free(pwq_cache, + container_of(rcu, struct pool_workqueue, rcu)); +} + +/* + * Scheduled on system_wq by put_pwq() when an unbound pwq hits zero refcnt + * and needs to be destroyed. + */ +static void pwq_unbound_release_workfn(struct work_struct *work) +{ + struct pool_workqueue *pwq = container_of(work, struct pool_workqueue, + unbound_release_work); + struct workqueue_struct *wq = pwq->wq; + struct worker_pool *pool = pwq->pool; + bool is_last; + + 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); + mutex_unlock(&wq->mutex); + + mutex_lock(&wq_pool_mutex); + put_unbound_pool(pool); + mutex_unlock(&wq_pool_mutex); + + call_rcu_sched(&pwq->rcu, rcu_free_pwq); + + /* + * If we're the last pwq going away, @wq is already dead and no one + * is gonna access it anymore. Free it. + */ + if (is_last) { + free_workqueue_attrs(wq->unbound_attrs); + kfree(wq); + } +} + +/** + * pwq_adjust_max_active - update a pwq's max_active to the current setting + * @pwq: target pool_workqueue + * + * If @pwq isn't freezing, set @pwq->max_active to the associated + * workqueue's saved_max_active and activate delayed work items + * accordingly. If @pwq is freezing, clear @pwq->max_active to zero. + */ +static void pwq_adjust_max_active(struct pool_workqueue *pwq) +{ + struct workqueue_struct *wq = pwq->wq; + bool freezable = wq->flags & WQ_FREEZABLE; + + /* for @wq->saved_max_active */ + lockdep_assert_held(&wq->mutex); + + /* fast exit for non-freezable wqs */ + if (!freezable && pwq->max_active == wq->saved_max_active) + return; + + spin_lock_irq(&pwq->pool->lock); + + if (!freezable || !(pwq->pool->flags & POOL_FREEZING)) { + pwq->max_active = wq->saved_max_active; + + while (!list_empty(&pwq->delayed_works) && + pwq->nr_active < pwq->max_active) + pwq_activate_first_delayed(pwq); /* - * Allocate enough room to align cwq and put an extra - * pointer at the end pointing back to the originally - * allocated pointer which will be used for free. + * Need to kick a worker after thawed or an unbound wq's + * max_active is bumped. It's a slow path. Do it always. */ - ptr = kzalloc(size + align + sizeof(void *), GFP_KERNEL); - if (ptr) { - wq->cpu_wq.single = PTR_ALIGN(ptr, align); - *(void **)(wq->cpu_wq.single + 1) = ptr; + wake_up_worker(pwq->pool); + } else { + pwq->max_active = 0; + } + + spin_unlock_irq(&pwq->pool->lock); +} + +/* initialize newly alloced @pwq which is associated with @wq and @pool */ +static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, + struct worker_pool *pool) +{ + BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK); + + memset(pwq, 0, sizeof(*pwq)); + + pwq->pool = pool; + pwq->wq = wq; + pwq->flush_color = -1; + pwq->refcnt = 1; + INIT_LIST_HEAD(&pwq->delayed_works); + INIT_LIST_HEAD(&pwq->pwqs_node); + INIT_LIST_HEAD(&pwq->mayday_node); + INIT_WORK(&pwq->unbound_release_work, pwq_unbound_release_workfn); +} + +/* sync @pwq with the current state of its associated wq and link it */ +static void link_pwq(struct pool_workqueue *pwq) +{ + struct workqueue_struct *wq = pwq->wq; + + lockdep_assert_held(&wq->mutex); + + /* may be called multiple times, ignore if already linked */ + if (!list_empty(&pwq->pwqs_node)) + return; + + /* + * Set the matching work_color. This is synchronized with + * wq->mutex to avoid confusing flush_workqueue(). + */ + pwq->work_color = wq->work_color; + + /* sync max_active to the current setting */ + pwq_adjust_max_active(pwq); + + /* link in @pwq */ + list_add_rcu(&pwq->pwqs_node, &wq->pwqs); +} + +/* obtain a pool matching @attr and create a pwq associating the pool and @wq */ +static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs) +{ + struct worker_pool *pool; + struct pool_workqueue *pwq; + + lockdep_assert_held(&wq_pool_mutex); + + pool = get_unbound_pool(attrs); + if (!pool) + return NULL; + + pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); + if (!pwq) { + put_unbound_pool(pool); + return NULL; + } + + init_pwq(pwq, wq, pool); + 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 + * @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. + * + * If NUMA affinity is not enabled, @attrs->cpumask is always used. If + * enabled and @node has online CPUs requested by @attrs, the returned + * cpumask is the intersection of the possible CPUs of @node and + * @attrs->cpumask. + * + * The caller is responsible for ensuring that the cpumask of @node stays + * stable. + */ +static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node, + int cpu_going_down, cpumask_t *cpumask) +{ + if (!wq_numa_enabled || attrs->no_numa) + goto use_dfl; + + /* does @node have any online CPUs @attrs wants? */ + cpumask_and(cpumask, cpumask_of_node(node), attrs->cpumask); + if (cpu_going_down >= 0) + cpumask_clear_cpu(cpu_going_down, cpumask); + + if (cpumask_empty(cpumask)) + goto use_dfl; + + /* yeap, return possible CPUs in @node that @attrs wants */ + cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]); + return !cpumask_equal(cpumask, attrs->cpumask); + +use_dfl: + cpumask_copy(cpumask, attrs->cpumask); + return false; +} + +/* install @pwq into @wq's numa_pwq_tbl[] for @node and return the old pwq */ +static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq, + int node, + struct pool_workqueue *pwq) +{ + struct pool_workqueue *old_pwq; + + lockdep_assert_held(&wq->mutex); + + /* link_pwq() can handle duplicate calls */ + link_pwq(pwq); + + old_pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); + rcu_assign_pointer(wq->numa_pwq_tbl[node], pwq); + 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) +{ + struct workqueue_attrs *new_attrs, *tmp_attrs; + struct pool_workqueue **pwq_tbl, *dfl_pwq; + int node, ret; + + /* only unbound workqueues can change attributes */ + if (WARN_ON(!(wq->flags & WQ_UNBOUND))) + return -EINVAL; + + /* creating multiple pwqs breaks ordering guarantee */ + if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs))) + return -EINVAL; + + pwq_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; + + /* make a copy of @attrs and sanitize it */ + copy_workqueue_attrs(new_attrs, attrs); + cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); + + /* + * We may create multiple pwqs with differing cpumasks. Make a + * copy of @new_attrs which will be modified and used to obtain + * pools. + */ + 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; + + 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; + } else { + dfl_pwq->refcnt++; + pwq_tbl[node] = dfl_pwq; } } - /* just in case, make sure it's actually aligned */ - BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align)); - return wq->cpu_wq.v ? 0 : -ENOMEM; + mutex_unlock(&wq_pool_mutex); + + /* all pwqs have been created successfully, let's install'em */ + mutex_lock(&wq->mutex); + + copy_workqueue_attrs(wq->unbound_attrs, new_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]); + + /* @dfl_pwq might not have been used, ensure it's linked */ + link_pwq(dfl_pwq); + swap(wq->dfl_pwq, dfl_pwq); + + mutex_unlock(&wq->mutex); + + /* put the old pwqs */ + for_each_node(node) + put_pwq_unlocked(pwq_tbl[node]); + put_pwq_unlocked(dfl_pwq); + + put_online_cpus(); + ret = 0; + /* fall through */ +out_free: + free_workqueue_attrs(tmp_attrs); + free_workqueue_attrs(new_attrs); + kfree(pwq_tbl); + 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; } -static void free_cwqs(struct workqueue_struct *wq) +/** + * wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug + * @wq: the target workqueue + * @cpu: the CPU coming up or going down + * @online: whether @cpu is coming up or going down + * + * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and + * %CPU_DOWN_FAILED. @cpu is being hot[un]plugged, update NUMA affinity of + * @wq accordingly. + * + * If NUMA affinity can't be adjusted due to memory allocation failure, it + * falls back to @wq->dfl_pwq which may not be optimal but is always + * correct. + * + * Note that when the last allowed CPU of a NUMA node goes offline for a + * workqueue with a cpumask spanning multiple nodes, the workers which were + * already executing the work items for the workqueue will lose their CPU + * affinity and may execute on any CPU. This is similar to how per-cpu + * workqueues behave on CPU_DOWN. If a workqueue user wants strict + * affinity, it's the user's responsibility to flush the work item from + * CPU_DOWN_PREPARE. + */ +static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, + bool online) { - if (!(wq->flags & WQ_UNBOUND)) - free_percpu(wq->cpu_wq.pcpu); - else if (wq->cpu_wq.single) { - /* the pointer to free is stored right after the cwq */ - kfree(*(void **)(wq->cpu_wq.single + 1)); + int node = cpu_to_node(cpu); + int cpu_off = online ? -1 : cpu; + struct pool_workqueue *old_pwq = NULL, *pwq; + struct workqueue_attrs *target_attrs; + cpumask_t *cpumask; + + lockdep_assert_held(&wq_pool_mutex); + + if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND)) + return; + + /* + * We don't wanna alloc/free wq_attrs for each wq for each CPU. + * Let's use a preallocated one. The following buf is protected by + * CPU hotplug exclusion. + */ + 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. + */ + if (wq_calc_node_cpumask(wq->unbound_attrs, node, cpu_off, cpumask)) { + if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask)) + goto out_unlock; + } else { + if (pwq == wq->dfl_pwq) + goto out_unlock; + else + 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); + goto out_unlock; + } + + /* + * 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. + */ + mutex_lock(&wq->mutex); + old_pwq = numa_pwq_tbl_install(wq, node, pwq); + goto out_unlock; + +use_dfl_pwq: + spin_lock_irq(&wq->dfl_pwq->pool->lock); + get_pwq(wq->dfl_pwq); + spin_unlock_irq(&wq->dfl_pwq->pool->lock); + old_pwq = numa_pwq_tbl_install(wq, node, wq->dfl_pwq); +out_unlock: + mutex_unlock(&wq->mutex); + put_pwq_unlocked(old_pwq); +} + +static int alloc_and_link_pwqs(struct workqueue_struct *wq) +{ + bool highpri = wq->flags & WQ_HIGHPRI; + int cpu; + + if (!(wq->flags & WQ_UNBOUND)) { + wq->cpu_pwqs = alloc_percpu(struct pool_workqueue); + if (!wq->cpu_pwqs) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct pool_workqueue *pwq = + per_cpu_ptr(wq->cpu_pwqs, cpu); + struct worker_pool *cpu_pools = + per_cpu(cpu_worker_pools, cpu); + + init_pwq(pwq, wq, &cpu_pools[highpri]); + + mutex_lock(&wq->mutex); + link_pwq(pwq); + mutex_unlock(&wq->mutex); + } + return 0; + } else { + return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } } @@ -3232,30 +4080,28 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, struct lock_class_key *key, const char *lock_name, ...) { - va_list args, args1; + size_t tbl_size = 0; + va_list args; struct workqueue_struct *wq; - unsigned int cpu; - size_t namelen; + struct pool_workqueue *pwq; - /* determine namelen, allocate wq and format name */ - va_start(args, lock_name); - va_copy(args1, args); - namelen = vsnprintf(NULL, 0, fmt, args) + 1; + /* allocate wq and format name */ + if (flags & WQ_UNBOUND) + tbl_size = wq_numa_tbl_len * sizeof(wq->numa_pwq_tbl[0]); - wq = kzalloc(sizeof(*wq) + namelen, GFP_KERNEL); + wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL); if (!wq) - goto err; + return NULL; - vsnprintf(wq->name, namelen, fmt, args1); - va_end(args); - va_end(args1); + if (flags & WQ_UNBOUND) { + wq->unbound_attrs = alloc_workqueue_attrs(GFP_KERNEL); + if (!wq->unbound_attrs) + goto err_free_wq; + } - /* - * Workqueues which may be used during memory reclaim should - * have a rescuer to guarantee forward progress. - */ - if (flags & WQ_MEM_RECLAIM) - flags |= WQ_RESCUER; + va_start(args, lock_name); + vsnprintf(wq->name, sizeof(wq->name), fmt, args); + va_end(args); max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); @@ -3263,72 +4109,70 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, /* init wq */ wq->flags = flags; wq->saved_max_active = max_active; - mutex_init(&wq->flush_mutex); - atomic_set(&wq->nr_cwqs_to_flush, 0); + mutex_init(&wq->mutex); + atomic_set(&wq->nr_pwqs_to_flush, 0); + INIT_LIST_HEAD(&wq->pwqs); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); + INIT_LIST_HEAD(&wq->maydays); lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); INIT_LIST_HEAD(&wq->list); - if (alloc_cwqs(wq) < 0) - goto err; + if (alloc_and_link_pwqs(wq) < 0) + goto err_free_wq; - for_each_cwq_cpu(cpu, wq) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - struct global_cwq *gcwq = get_gcwq(cpu); - int pool_idx = (bool)(flags & WQ_HIGHPRI); - - BUG_ON((unsigned long)cwq & WORK_STRUCT_FLAG_MASK); - cwq->pool = &gcwq->pools[pool_idx]; - cwq->wq = wq; - cwq->flush_color = -1; - cwq->max_active = max_active; - INIT_LIST_HEAD(&cwq->delayed_works); - } - - if (flags & WQ_RESCUER) { + /* + * Workqueues which may be used during memory reclaim should + * have a rescuer to guarantee forward progress. + */ + if (flags & WQ_MEM_RECLAIM) { struct worker *rescuer; - if (!alloc_mayday_mask(&wq->mayday_mask, GFP_KERNEL)) - goto err; - - wq->rescuer = rescuer = alloc_worker(); + rescuer = alloc_worker(); if (!rescuer) - goto err; + goto err_destroy; - rescuer->task = kthread_create(rescuer_thread, wq, "%s", + rescuer->rescue_wq = wq; + rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", wq->name); - if (IS_ERR(rescuer->task)) - goto err; + if (IS_ERR(rescuer->task)) { + kfree(rescuer); + goto err_destroy; + } - rescuer->task->flags |= PF_THREAD_BOUND; + wq->rescuer = rescuer; + rescuer->task->flags |= PF_NO_SETAFFINITY; wake_up_process(rescuer->task); } + if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) + goto err_destroy; + /* - * workqueue_lock protects global freeze state and workqueues - * list. Grab it, set max_active accordingly and add the new - * workqueue to workqueues list. + * wq_pool_mutex protects global freeze state and workqueues list. + * Grab it, adjust max_active and add the new @wq to workqueues + * list. */ - spin_lock(&workqueue_lock); + mutex_lock(&wq_pool_mutex); - if (workqueue_freezing && wq->flags & WQ_FREEZABLE) - for_each_cwq_cpu(cpu, wq) - get_cwq(cpu, wq)->max_active = 0; + mutex_lock(&wq->mutex); + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); + mutex_unlock(&wq->mutex); list_add(&wq->list, &workqueues); - spin_unlock(&workqueue_lock); + mutex_unlock(&wq_pool_mutex); return wq; -err: - if (wq) { - free_cwqs(wq); - free_mayday_mask(wq->mayday_mask); - kfree(wq->rescuer); - kfree(wq); - } + +err_free_wq: + free_workqueue_attrs(wq->unbound_attrs); + kfree(wq); + return NULL; +err_destroy: + destroy_workqueue(wq); return NULL; } EXPORT_SYMBOL_GPL(__alloc_workqueue_key); @@ -3341,60 +4185,78 @@ EXPORT_SYMBOL_GPL(__alloc_workqueue_key); */ void destroy_workqueue(struct workqueue_struct *wq) { - unsigned int cpu; + struct pool_workqueue *pwq; + int node; /* drain it before proceeding with destruction */ drain_workqueue(wq); + /* sanity checks */ + mutex_lock(&wq->mutex); + for_each_pwq(pwq, wq) { + int i; + + for (i = 0; i < WORK_NR_COLORS; i++) { + if (WARN_ON(pwq->nr_in_flight[i])) { + mutex_unlock(&wq->mutex); + return; + } + } + + if (WARN_ON((pwq != wq->dfl_pwq) && (pwq->refcnt > 1)) || + WARN_ON(pwq->nr_active) || + WARN_ON(!list_empty(&pwq->delayed_works))) { + mutex_unlock(&wq->mutex); + return; + } + } + mutex_unlock(&wq->mutex); + /* * wq list is used to freeze wq, remove from list after * flushing is complete in case freeze races us. */ - spin_lock(&workqueue_lock); - list_del(&wq->list); - spin_unlock(&workqueue_lock); + mutex_lock(&wq_pool_mutex); + list_del_init(&wq->list); + mutex_unlock(&wq_pool_mutex); - /* sanity check */ - for_each_cwq_cpu(cpu, wq) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - int i; + workqueue_sysfs_unregister(wq); - for (i = 0; i < WORK_NR_COLORS; i++) - BUG_ON(cwq->nr_in_flight[i]); - BUG_ON(cwq->nr_active); - BUG_ON(!list_empty(&cwq->delayed_works)); - } - - if (wq->flags & WQ_RESCUER) { + if (wq->rescuer) { kthread_stop(wq->rescuer->task); - free_mayday_mask(wq->mayday_mask); kfree(wq->rescuer); + wq->rescuer = NULL; } - free_cwqs(wq); - kfree(wq); -} -EXPORT_SYMBOL_GPL(destroy_workqueue); - -/** - * cwq_set_max_active - adjust max_active of a cwq - * @cwq: target cpu_workqueue_struct - * @max_active: new max_active value. - * - * Set @cwq->max_active to @max_active and activate delayed works if - * increased. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock). - */ -static void cwq_set_max_active(struct cpu_workqueue_struct *cwq, int max_active) -{ - cwq->max_active = max_active; + if (!(wq->flags & WQ_UNBOUND)) { + /* + * The base ref is never dropped on per-cpu pwqs. Directly + * free the pwqs and wq. + */ + free_percpu(wq->cpu_pwqs); + kfree(wq); + } else { + /* + * We're the sole accessor of @wq at this point. Directly + * access numa_pwq_tbl[] and dfl_pwq to put the base refs. + * @wq will be freed when the last pwq is released. + */ + for_each_node(node) { + pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); + RCU_INIT_POINTER(wq->numa_pwq_tbl[node], NULL); + put_pwq_unlocked(pwq); + } - while (!list_empty(&cwq->delayed_works) && - cwq->nr_active < cwq->max_active) - cwq_activate_first_delayed(cwq); + /* + * Put dfl_pwq. @wq may be freed any time after dfl_pwq is + * put. Don't access it afterwards. + */ + pwq = wq->dfl_pwq; + wq->dfl_pwq = NULL; + put_pwq_unlocked(pwq); + } } +EXPORT_SYMBOL_GPL(destroy_workqueue); /** * workqueue_set_max_active - adjust max_active of a workqueue @@ -3408,29 +4270,37 @@ static void cwq_set_max_active(struct cpu_workqueue_struct *cwq, int max_active) */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { - unsigned int cpu; + struct pool_workqueue *pwq; + + /* disallow meddling with max_active for ordered workqueues */ + if (WARN_ON(wq->flags & __WQ_ORDERED)) + return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); - spin_lock(&workqueue_lock); + mutex_lock(&wq->mutex); wq->saved_max_active = max_active; - for_each_cwq_cpu(cpu, wq) { - struct global_cwq *gcwq = get_gcwq(cpu); - - spin_lock_irq(&gcwq->lock); + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); - if (!(wq->flags & WQ_FREEZABLE) || - !(gcwq->flags & GCWQ_FREEZING)) - cwq_set_max_active(get_cwq(gcwq->cpu, wq), max_active); + mutex_unlock(&wq->mutex); +} +EXPORT_SYMBOL_GPL(workqueue_set_max_active); - spin_unlock_irq(&gcwq->lock); - } +/** + * current_is_workqueue_rescuer - is %current workqueue rescuer? + * + * Determine whether %current is a workqueue rescuer. Can be used from + * work functions to determine whether it's being run off the rescuer task. + */ +bool current_is_workqueue_rescuer(void) +{ + struct worker *worker = current_wq_worker(); - spin_unlock(&workqueue_lock); + return worker && worker->rescue_wq; } -EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** * workqueue_congested - test whether a workqueue is congested @@ -3444,28 +4314,24 @@ EXPORT_SYMBOL_GPL(workqueue_set_max_active); * RETURNS: * %true if congested, %false otherwise. */ -bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq) +bool workqueue_congested(int cpu, struct workqueue_struct *wq) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + struct pool_workqueue *pwq; + bool ret; - return !list_empty(&cwq->delayed_works); -} -EXPORT_SYMBOL_GPL(workqueue_congested); + rcu_read_lock_sched(); -/** - * work_cpu - return the last known associated cpu for @work - * @work: the work of interest - * - * RETURNS: - * CPU number if @work was ever queued. WORK_CPU_NONE otherwise. - */ -unsigned int work_cpu(struct work_struct *work) -{ - struct global_cwq *gcwq = get_work_gcwq(work); + if (!(wq->flags & WQ_UNBOUND)) + pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); + else + pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); + + ret = !list_empty(&pwq->delayed_works); + rcu_read_unlock_sched(); - return gcwq ? gcwq->cpu : WORK_CPU_NONE; + return ret; } -EXPORT_SYMBOL_GPL(work_cpu); +EXPORT_SYMBOL_GPL(workqueue_congested); /** * work_busy - test whether a work is currently pending or running @@ -3474,118 +4340,277 @@ EXPORT_SYMBOL_GPL(work_cpu); * Test whether @work is currently pending or running. There is no * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. - * Especially for reentrant wqs, the pending state might hide the - * running state. * * RETURNS: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) { - struct global_cwq *gcwq = get_work_gcwq(work); + struct worker_pool *pool; unsigned long flags; unsigned int ret = 0; - if (!gcwq) - return 0; - - spin_lock_irqsave(&gcwq->lock, flags); - if (work_pending(work)) ret |= WORK_BUSY_PENDING; - if (find_worker_executing_work(gcwq, work)) - ret |= WORK_BUSY_RUNNING; - spin_unlock_irqrestore(&gcwq->lock, flags); + local_irq_save(flags); + pool = get_work_pool(work); + if (pool) { + spin_lock(&pool->lock); + if (find_worker_executing_work(pool, work)) + ret |= WORK_BUSY_RUNNING; + spin_unlock(&pool->lock); + } + local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(work_busy); +/** + * set_worker_desc - set description for the current work item + * @fmt: printf-style format string + * @...: arguments for the format string + * + * This function can be called by a running work function to describe what + * the work item is about. If the worker task gets dumped, this + * information will be printed out together to help debugging. The + * description can be at most WORKER_DESC_LEN including the trailing '\0'. + */ +void set_worker_desc(const char *fmt, ...) +{ + struct worker *worker = current_wq_worker(); + va_list args; + + if (worker) { + va_start(args, fmt); + vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); + va_end(args); + worker->desc_valid = true; + } +} + +/** + * print_worker_info - print out worker information and description + * @log_lvl: the log level to use when printing + * @task: target task + * + * If @task is a worker and currently executing a work item, print out the + * name of the workqueue being serviced and worker description set with + * set_worker_desc() by the currently executing work item. + * + * This function can be safely called on any task as long as the + * task_struct itself is accessible. While safe, this function isn't + * synchronized and may print out mixups or garbages of limited length. + */ +void print_worker_info(const char *log_lvl, struct task_struct *task) +{ + work_func_t *fn = NULL; + char name[WQ_NAME_LEN] = { }; + char desc[WORKER_DESC_LEN] = { }; + struct pool_workqueue *pwq = NULL; + struct workqueue_struct *wq = NULL; + bool desc_valid = false; + struct worker *worker; + + if (!(task->flags & PF_WQ_WORKER)) + return; + + /* + * This function is called without any synchronization and @task + * could be in any state. Be careful with dereferences. + */ + worker = probe_kthread_data(task); + + /* + * Carefully copy the associated workqueue's workfn and name. Keep + * the original last '\0' in case the original contains garbage. + */ + probe_kernel_read(&fn, &worker->current_func, sizeof(fn)); + probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq)); + probe_kernel_read(&wq, &pwq->wq, sizeof(wq)); + probe_kernel_read(name, wq->name, sizeof(name) - 1); + + /* copy worker description */ + probe_kernel_read(&desc_valid, &worker->desc_valid, sizeof(desc_valid)); + if (desc_valid) + probe_kernel_read(desc, worker->desc, sizeof(desc) - 1); + + if (fn || name[0] || desc[0]) { + printk("%sWorkqueue: %s %pf", log_lvl, name, fn); + if (desc[0]) + pr_cont(" (%s)", desc); + pr_cont("\n"); + } +} + /* * CPU hotplug. * * There are two challenges in supporting CPU hotplug. Firstly, there - * are a lot of assumptions on strong associations among work, cwq and - * gcwq which make migrating pending and scheduled works very + * are a lot of assumptions on strong associations among work, pwq and + * pool which make migrating pending and scheduled works very * difficult to implement without impacting hot paths. Secondly, - * gcwqs serve mix of short, long and very long running works making + * worker pools serve mix of short, long and very long running works making * blocked draining impractical. * - * This is solved by allowing a gcwq to be disassociated from the CPU + * This is solved by allowing the pools to be disassociated from the CPU * running as an unbound one and allowing it to be reattached later if the * cpu comes back online. */ -/* claim manager positions of all pools */ -static void gcwq_claim_assoc_and_lock(struct global_cwq *gcwq) +static void wq_unbind_fn(struct work_struct *work) { + int cpu = smp_processor_id(); struct worker_pool *pool; + struct worker *worker; + int wi; - for_each_worker_pool(pool, gcwq) - mutex_lock_nested(&pool->assoc_mutex, pool - gcwq->pools); - spin_lock_irq(&gcwq->lock); -} + for_each_cpu_worker_pool(pool, cpu) { + WARN_ON_ONCE(cpu != smp_processor_id()); -/* release manager positions */ -static void gcwq_release_assoc_and_unlock(struct global_cwq *gcwq) -{ - struct worker_pool *pool; + mutex_lock(&pool->manager_mutex); + spin_lock_irq(&pool->lock); + + /* + * We've blocked all manager 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) + worker->flags |= WORKER_UNBOUND; + + pool->flags |= POOL_DISASSOCIATED; + + spin_unlock_irq(&pool->lock); + mutex_unlock(&pool->manager_mutex); + + /* + * Call schedule() so that we cross rq->lock and thus can + * guarantee sched callbacks see the %WORKER_UNBOUND flag. + * This is necessary as scheduler callbacks may be invoked + * from other cpus. + */ + schedule(); + + /* + * Sched callbacks are disabled now. Zap nr_running. + * After this, nr_running stays zero and need_more_worker() + * and keep_working() are always true as long as the + * worklist is not empty. This pool now behaves as an + * unbound (in terms of concurrency management) pool which + * are served by workers tied to the pool. + */ + atomic_set(&pool->nr_running, 0); - spin_unlock_irq(&gcwq->lock); - for_each_worker_pool(pool, gcwq) - mutex_unlock(&pool->assoc_mutex); + /* + * With concurrency management just turned off, a busy + * worker blocking could lead to lengthy stalls. Kick off + * unbound chain execution of currently pending work items. + */ + spin_lock_irq(&pool->lock); + wake_up_worker(pool); + spin_unlock_irq(&pool->lock); + } } -static void gcwq_unbind_fn(struct work_struct *work) +/** + * rebind_workers - rebind all workers of a pool to the associated CPU + * @pool: pool of interest + * + * @pool->cpu is coming online. Rebind all workers to the CPU. + */ +static void rebind_workers(struct worker_pool *pool) { - struct global_cwq *gcwq = get_gcwq(smp_processor_id()); - struct worker_pool *pool; struct worker *worker; - struct hlist_node *pos; - int i; - - BUG_ON(gcwq->cpu != smp_processor_id()); + int wi; - gcwq_claim_assoc_and_lock(gcwq); + lockdep_assert_held(&pool->manager_mutex); /* - * We've claimed all manager positions. 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. + * 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 + * of all workers first and then clear UNBOUND. As we're called + * from CPU_ONLINE, the following shouldn't fail. */ - for_each_worker_pool(pool, gcwq) - list_for_each_entry(worker, &pool->idle_list, entry) - worker->flags |= WORKER_UNBOUND; + for_each_pool_worker(worker, wi, pool) + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, + pool->attrs->cpumask) < 0); - for_each_busy_worker(worker, i, pos, gcwq) - worker->flags |= WORKER_UNBOUND; + spin_lock_irq(&pool->lock); - gcwq->flags |= GCWQ_DISASSOCIATED; + for_each_pool_worker(worker, wi, pool) { + unsigned int worker_flags = worker->flags; - gcwq_release_assoc_and_unlock(gcwq); + /* + * A bound idle worker should actually be on the runqueue + * of the associated CPU for local wake-ups targeting it to + * work. Kick all idle workers so that they migrate to the + * associated CPU. Doing this in the same loop as + * replacing UNBOUND with REBOUND is safe as no worker will + * be bound before @pool->lock is released. + */ + if (worker_flags & WORKER_IDLE) + wake_up_process(worker->task); - /* - * Call schedule() so that we cross rq->lock and thus can guarantee - * sched callbacks see the %WORKER_UNBOUND flag. This is necessary - * as scheduler callbacks may be invoked from other cpus. - */ - schedule(); + /* + * We want to clear UNBOUND but can't directly call + * worker_clr_flags() or adjust nr_running. Atomically + * replace UNBOUND with another NOT_RUNNING flag REBOUND. + * @worker will clear REBOUND using worker_clr_flags() when + * it initiates the next execution cycle thus restoring + * concurrency management. Note that when or whether + * @worker clears REBOUND doesn't affect correctness. + * + * ACCESS_ONCE() is necessary because @worker->flags may be + * tested without holding any lock in + * wq_worker_waking_up(). Without it, NOT_RUNNING test may + * fail incorrectly leading to premature concurrency + * management operations. + */ + WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND)); + worker_flags |= WORKER_REBOUND; + worker_flags &= ~WORKER_UNBOUND; + ACCESS_ONCE(worker->flags) = worker_flags; + } - /* - * Sched callbacks are disabled now. Zap nr_running. After this, - * nr_running stays zero and need_more_worker() and keep_working() - * are always true as long as the worklist is not empty. @gcwq now - * behaves as unbound (in terms of concurrency management) gcwq - * which is served by workers tied to the CPU. - * - * On return from this function, the current worker would trigger - * unbound chain execution of pending work items if other workers - * didn't already. - */ - for_each_worker_pool(pool, gcwq) - atomic_set(get_pool_nr_running(pool), 0); + spin_unlock_irq(&pool->lock); +} + +/** + * restore_unbound_workers_cpumask - restore cpumask of unbound workers + * @pool: unbound pool of interest + * @cpu: the CPU which is coming up + * + * An unbound pool may end up with a cpumask which doesn't have any online + * CPUs. When a worker of such pool get scheduled, the scheduler resets + * its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any + * online CPU before, cpus_allowed of all its workers should be restored. + */ +static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) +{ + static cpumask_t cpumask; + struct worker *worker; + int wi; + + lockdep_assert_held(&pool->manager_mutex); + + /* is @cpu allowed for @pool? */ + if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) + return; + + /* is @cpu the only online CPU? */ + cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); + if (cpumask_weight(&cpumask) != 1) + return; + + /* as we're called from CPU_ONLINE, the following shouldn't fail */ + for_each_pool_worker(worker, wi, pool) + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, + pool->attrs->cpumask) < 0); } /* @@ -3596,34 +4621,46 @@ static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { - unsigned int cpu = (unsigned long)hcpu; - struct global_cwq *gcwq = get_gcwq(cpu); + int cpu = (unsigned long)hcpu; struct worker_pool *pool; + struct workqueue_struct *wq; + int pi; switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - for_each_worker_pool(pool, gcwq) { - struct worker *worker; - + for_each_cpu_worker_pool(pool, cpu) { if (pool->nr_workers) continue; - - worker = create_worker(pool); - if (!worker) + if (create_and_start_worker(pool) < 0) return NOTIFY_BAD; - - spin_lock_irq(&gcwq->lock); - start_worker(worker); - spin_unlock_irq(&gcwq->lock); } break; case CPU_DOWN_FAILED: case CPU_ONLINE: - gcwq_claim_assoc_and_lock(gcwq); - gcwq->flags &= ~GCWQ_DISASSOCIATED; - rebind_workers(gcwq); - gcwq_release_assoc_and_unlock(gcwq); + 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); + + rebind_workers(pool); + } else if (pool->cpu < 0) { + restore_unbound_workers_cpumask(pool, cpu); + } + + mutex_unlock(&pool->manager_mutex); + } + + /* update NUMA affinity of unbound workqueues */ + list_for_each_entry(wq, &workqueues, list) + wq_update_unbound_numa(wq, cpu, true); + + mutex_unlock(&wq_pool_mutex); break; } return NOTIFY_OK; @@ -3637,14 +4674,23 @@ static int __cpuinit workqueue_cpu_down_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { - unsigned int cpu = (unsigned long)hcpu; + int cpu = (unsigned long)hcpu; struct work_struct unbind_work; + struct workqueue_struct *wq; switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: - /* unbinding should happen on the local CPU */ - INIT_WORK_ONSTACK(&unbind_work, gcwq_unbind_fn); + /* unbinding per-cpu workers should happen on the local CPU */ + INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn); queue_work_on(cpu, system_highpri_wq, &unbind_work); + + /* update NUMA affinity of unbound workqueues */ + mutex_lock(&wq_pool_mutex); + list_for_each_entry(wq, &workqueues, list) + wq_update_unbound_numa(wq, cpu, false); + mutex_unlock(&wq_pool_mutex); + + /* wait for per-cpu unbinding to finish */ flush_work(&unbind_work); break; } @@ -3677,7 +4723,7 @@ static void work_for_cpu_fn(struct work_struct *work) * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. */ -long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) +long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; @@ -3695,41 +4741,40 @@ EXPORT_SYMBOL_GPL(work_on_cpu); * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable - * workqueues will queue new works to their frozen_works list instead of - * gcwq->worklist. + * workqueues will queue new works to their delayed_works list instead of + * pool->worklist. * * CONTEXT: - * Grabs and releases workqueue_lock and gcwq->lock's. + * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void freeze_workqueues_begin(void) { - unsigned int cpu; + struct worker_pool *pool; + struct workqueue_struct *wq; + struct pool_workqueue *pwq; + int pi; - spin_lock(&workqueue_lock); + mutex_lock(&wq_pool_mutex); - BUG_ON(workqueue_freezing); + WARN_ON_ONCE(workqueue_freezing); workqueue_freezing = true; - for_each_gcwq_cpu(cpu) { - struct global_cwq *gcwq = get_gcwq(cpu); - struct workqueue_struct *wq; - - spin_lock_irq(&gcwq->lock); - - BUG_ON(gcwq->flags & GCWQ_FREEZING); - gcwq->flags |= GCWQ_FREEZING; - - list_for_each_entry(wq, &workqueues, list) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - - if (cwq && wq->flags & WQ_FREEZABLE) - cwq->max_active = 0; - } + /* 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); + } - spin_unlock_irq(&gcwq->lock); + list_for_each_entry(wq, &workqueues, list) { + mutex_lock(&wq->mutex); + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); + mutex_unlock(&wq->mutex); } - spin_unlock(&workqueue_lock); + mutex_unlock(&wq_pool_mutex); } /** @@ -3739,7 +4784,7 @@ void freeze_workqueues_begin(void) * between freeze_workqueues_begin() and thaw_workqueues(). * * CONTEXT: - * Grabs and releases workqueue_lock. + * Grabs and releases wq_pool_mutex. * * RETURNS: * %true if some freezable workqueues are still busy. %false if freezing @@ -3747,34 +4792,34 @@ void freeze_workqueues_begin(void) */ bool freeze_workqueues_busy(void) { - unsigned int cpu; bool busy = false; + struct workqueue_struct *wq; + struct pool_workqueue *pwq; - spin_lock(&workqueue_lock); + mutex_lock(&wq_pool_mutex); - BUG_ON(!workqueue_freezing); + WARN_ON_ONCE(!workqueue_freezing); - for_each_gcwq_cpu(cpu) { - struct workqueue_struct *wq; + list_for_each_entry(wq, &workqueues, list) { + if (!(wq->flags & WQ_FREEZABLE)) + continue; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. */ - list_for_each_entry(wq, &workqueues, list) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - - if (!cwq || !(wq->flags & WQ_FREEZABLE)) - continue; - - BUG_ON(cwq->nr_active < 0); - if (cwq->nr_active) { + rcu_read_lock_sched(); + for_each_pwq(pwq, wq) { + WARN_ON_ONCE(pwq->nr_active < 0); + if (pwq->nr_active) { busy = true; + rcu_read_unlock_sched(); goto out_unlock; } } + rcu_read_unlock_sched(); } out_unlock: - spin_unlock(&workqueue_lock); + mutex_unlock(&wq_pool_mutex); return busy; } @@ -3782,110 +4827,144 @@ out_unlock: * thaw_workqueues - thaw workqueues * * Thaw workqueues. Normal queueing is restored and all collected - * frozen works are transferred to their respective gcwq worklists. + * frozen works are transferred to their respective pool worklists. * * CONTEXT: - * Grabs and releases workqueue_lock and gcwq->lock's. + * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void thaw_workqueues(void) { - unsigned int cpu; + struct workqueue_struct *wq; + struct pool_workqueue *pwq; + struct worker_pool *pool; + int pi; - spin_lock(&workqueue_lock); + mutex_lock(&wq_pool_mutex); if (!workqueue_freezing) goto out_unlock; - for_each_gcwq_cpu(cpu) { - struct global_cwq *gcwq = get_gcwq(cpu); - struct worker_pool *pool; - struct workqueue_struct *wq; + /* 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); + } - spin_lock_irq(&gcwq->lock); + /* restore max_active and repopulate worklist */ + list_for_each_entry(wq, &workqueues, list) { + mutex_lock(&wq->mutex); + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); + mutex_unlock(&wq->mutex); + } - BUG_ON(!(gcwq->flags & GCWQ_FREEZING)); - gcwq->flags &= ~GCWQ_FREEZING; + workqueue_freezing = false; +out_unlock: + mutex_unlock(&wq_pool_mutex); +} +#endif /* CONFIG_FREEZER */ - list_for_each_entry(wq, &workqueues, list) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); +static void __init wq_numa_init(void) +{ + cpumask_var_t *tbl; + int node, cpu; - if (!cwq || !(wq->flags & WQ_FREEZABLE)) - continue; + /* determine NUMA pwq table len - highest node id + 1 */ + for_each_node(node) + wq_numa_tbl_len = max(wq_numa_tbl_len, node + 1); - /* restore max_active and repopulate worklist */ - cwq_set_max_active(cwq, wq->saved_max_active); - } + if (num_possible_nodes() <= 1) + return; - for_each_worker_pool(pool, gcwq) - wake_up_worker(pool); + if (wq_disable_numa) { + pr_info("workqueue: NUMA affinity support disabled\n"); + return; + } + + wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(GFP_KERNEL); + BUG_ON(!wq_update_unbound_numa_attrs_buf); - spin_unlock_irq(&gcwq->lock); + /* + * We want masks of possible CPUs of each node which isn't readily + * 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); + BUG_ON(!tbl); + + for_each_node(node) + BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL, node)); + + for_each_possible_cpu(cpu) { + node = cpu_to_node(cpu); + if (WARN_ON(node == NUMA_NO_NODE)) { + pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu); + /* happens iff arch is bonkers, let's just proceed */ + return; + } + cpumask_set_cpu(cpu, tbl[node]); } - workqueue_freezing = false; -out_unlock: - spin_unlock(&workqueue_lock); + wq_numa_possible_cpumask = tbl; + wq_numa_enabled = true; } -#endif /* CONFIG_FREEZER */ static int __init init_workqueues(void) { - unsigned int cpu; - int i; - - /* make sure we have enough bits for OFFQ CPU number */ - BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_CPU_SHIFT)) < - WORK_CPU_LAST); - - cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP); - hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN); + int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; + int i, cpu; - /* initialize gcwqs */ - for_each_gcwq_cpu(cpu) { - struct global_cwq *gcwq = get_gcwq(cpu); - struct worker_pool *pool; + /* 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); - spin_lock_init(&gcwq->lock); - gcwq->cpu = cpu; - gcwq->flags |= GCWQ_DISASSOCIATED; + WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); - for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) - INIT_HLIST_HEAD(&gcwq->busy_hash[i]); + pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); - for_each_worker_pool(pool, gcwq) { - pool->gcwq = gcwq; - INIT_LIST_HEAD(&pool->worklist); - INIT_LIST_HEAD(&pool->idle_list); + cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP); + hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN); - init_timer_deferrable(&pool->idle_timer); - pool->idle_timer.function = idle_worker_timeout; - pool->idle_timer.data = (unsigned long)pool; + wq_numa_init(); - setup_timer(&pool->mayday_timer, gcwq_mayday_timeout, - (unsigned long)pool); + /* initialize CPU pools */ + for_each_possible_cpu(cpu) { + struct worker_pool *pool; - mutex_init(&pool->assoc_mutex); - ida_init(&pool->worker_ida); + i = 0; + for_each_cpu_worker_pool(pool, cpu) { + BUG_ON(init_worker_pool(pool)); + pool->cpu = cpu; + cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); + pool->attrs->nice = std_nice[i++]; + pool->node = cpu_to_node(cpu); + + /* alloc pool ID */ + mutex_lock(&wq_pool_mutex); + BUG_ON(worker_pool_assign_id(pool)); + mutex_unlock(&wq_pool_mutex); } } /* create the initial worker */ - for_each_online_gcwq_cpu(cpu) { - struct global_cwq *gcwq = get_gcwq(cpu); + for_each_online_cpu(cpu) { struct worker_pool *pool; - if (cpu != WORK_CPU_UNBOUND) - gcwq->flags &= ~GCWQ_DISASSOCIATED; + for_each_cpu_worker_pool(pool, cpu) { + pool->flags &= ~POOL_DISASSOCIATED; + BUG_ON(create_and_start_worker(pool) < 0); + } + } - for_each_worker_pool(pool, gcwq) { - struct worker *worker; + /* create default unbound wq attrs */ + for (i = 0; i < NR_STD_WORKER_POOLS; i++) { + struct workqueue_attrs *attrs; - worker = create_worker(pool); - BUG_ON(!worker); - spin_lock_irq(&gcwq->lock); - start_worker(worker); - spin_unlock_irq(&gcwq->lock); - } + BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL))); + attrs->nice = std_nice[i]; + unbound_std_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", 0, 0); |