blob: e7b005ff375033f1bf7e67ac6b69f08bd3a888bb [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-only
/*
* kernel/workqueue.c - generic async execution with shared worker pool
*
* Copyright (C) 2002 Ingo Molnar
*
* Derived from the taskqueue/keventd code by:
* David Woodhouse <dwmw2@infradead.org>
* Andrew Morton
* Kai Petzke <wpp@marie.physik.tu-berlin.de>
* Theodore Ts'o <tytso@mit.edu>
*
* Made to use alloc_percpu by Christoph Lameter.
*
* Copyright (C) 2010 SUSE Linux Products GmbH
* Copyright (C) 2010 Tejun Heo <tj@kernel.org>
*
* This is the generic async execution mechanism. Work items as are
* executed in process context. The worker pool is shared and
* automatically managed. There are two worker pools for each CPU (one for
* normal work items and the other for high priority ones) and some extra
* pools for workqueues which are not bound to any specific CPU - the
* number of these backing pools is dynamic.
*
* Please read Documentation/core-api/workqueue.rst for details.
*/
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/signal.h>
#include <linux/completion.h>
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/kthread.h>
#include <linux/hardirq.h>
#include <linux/mempolicy.h>
#include <linux/freezer.h>
#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 <linux/sched/isolation.h>
#include <linux/sched/debug.h>
#include <linux/nmi.h>
#include <linux/kvm_para.h>
#include <linux/delay.h>
#include <linux/irq_work.h>
#include "workqueue_internal.h"
enum worker_pool_flags {
/*
* worker_pool flags
*
* 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 pool behaves as an unbound one.
*
* Note that DISASSOCIATED should be flipped only while holding
* wq_pool_attach_mutex to avoid changing binding state while
* worker_attach_to_pool() is in progress.
*
* As there can only be one concurrent BH execution context per CPU, a
* BH pool is per-CPU and always DISASSOCIATED.
*/
POOL_BH = 1 << 0, /* is a BH pool */
POOL_MANAGER_ACTIVE = 1 << 1, /* being managed */
POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */
POOL_BH_DRAINING = 1 << 3, /* draining after CPU offline */
};
enum worker_flags {
/* worker flags */
WORKER_DIE = 1 << 1, /* die die die */
WORKER_IDLE = 1 << 2, /* is idle */
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_CPU_INTENSIVE |
WORKER_UNBOUND | WORKER_REBOUND,
};
enum work_cancel_flags {
WORK_CANCEL_DELAYED = 1 << 0, /* canceling a delayed_work */
WORK_CANCEL_DISABLE = 1 << 1, /* canceling to disable */
};
enum wq_internal_consts {
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 */
MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */
IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */
MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2,
/* call for help after 10ms
(min two ticks) */
MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */
CREATE_COOLDOWN = HZ, /* time to breath after fail */
/*
* Rescue workers are used only on emergencies and shared by
* all cpus. Give MIN_NICE.
*/
RESCUER_NICE_LEVEL = MIN_NICE,
HIGHPRI_NICE_LEVEL = MIN_NICE,
WQ_NAME_LEN = 32,
WORKER_ID_LEN = 10 + WQ_NAME_LEN, /* "kworker/R-" + WQ_NAME_LEN */
};
/*
* We don't want to trap softirq for too long. See MAX_SOFTIRQ_TIME and
* MAX_SOFTIRQ_RESTART in kernel/softirq.c. These are macros because
* msecs_to_jiffies() can't be an initializer.
*/
#define BH_WORKER_JIFFIES msecs_to_jiffies(2)
#define BH_WORKER_RESTARTS 10
/*
* Structure fields follow one of the following exclusion rules.
*
* I: Modifiable by initialization/destruction paths and read-only for
* everyone else.
*
* P: Preemption protected. Disabling preemption is enough and should
* only be modified and accessed from the local cpu.
*
* L: pool->lock protected. Access with pool->lock held.
*
* LN: pool->lock and wq_node_nr_active->lock protected for writes. Either for
* reads.
*
* K: Only modified by worker while holding pool->lock. Can be safely read by
* self, while holding pool->lock or from IRQ context if %current is the
* kworker.
*
* S: Only modified by worker self.
*
* A: wq_pool_attach_mutex protected.
*
* PL: wq_pool_mutex protected.
*
* PR: wq_pool_mutex protected for writes. RCU protected for reads.
*
* PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads.
*
* PWR: wq_pool_mutex and wq->mutex protected for writes. Either or
* RCU for reads.
*
* WQ: wq->mutex protected.
*
* WR: wq->mutex protected for writes. RCU protected for reads.
*
* WO: wq->mutex protected for writes. Updated with WRITE_ONCE() and can be read
* with READ_ONCE() without locking.
*
* MD: wq_mayday_lock protected.
*
* WD: Used internally by the watchdog.
*/
/* struct worker is defined in workqueue_internal.h */
struct worker_pool {
raw_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; /* L: flags */
unsigned long watchdog_ts; /* L: watchdog timestamp */
bool cpu_stall; /* WD: stalled cpu bound pool */
/*
* The counter is incremented in a process context on the associated CPU
* w/ preemption disabled, and decremented or reset in the same context
* but w/ pool->lock held. The readers grab pool->lock and are
* guaranteed to see if the counter reached zero.
*/
int nr_running;
struct list_head worklist; /* L: list of pending works */
int nr_workers; /* L: total number of workers */
int nr_idle; /* L: currently idle workers */
struct list_head idle_list; /* L: list of idle workers */
struct timer_list idle_timer; /* L: worker idle timeout */
struct work_struct idle_cull_work; /* L: worker idle cleanup */
struct timer_list mayday_timer; /* L: SOS timer for workers */
/* 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 */
struct worker *manager; /* L: purely informational */
struct list_head workers; /* A: attached workers */
struct ida worker_ida; /* worker IDs for task name */
struct workqueue_attrs *attrs; /* I: worker attributes */
struct hlist_node hash_node; /* PL: unbound_pool_hash node */
int refcnt; /* PL: refcnt for unbound pools */
/*
* Destruction of pool is RCU protected to allow dereferences
* from get_work_pool().
*/
struct rcu_head rcu;
};
/*
* Per-pool_workqueue statistics. These can be monitored using
* tools/workqueue/wq_monitor.py.
*/
enum pool_workqueue_stats {
PWQ_STAT_STARTED, /* work items started execution */
PWQ_STAT_COMPLETED, /* work items completed execution */
PWQ_STAT_CPU_TIME, /* total CPU time consumed */
PWQ_STAT_CPU_INTENSIVE, /* wq_cpu_intensive_thresh_us violations */
PWQ_STAT_CM_WAKEUP, /* concurrency-management worker wakeups */
PWQ_STAT_REPATRIATED, /* unbound workers brought back into scope */
PWQ_STAT_MAYDAY, /* maydays to rescuer */
PWQ_STAT_RESCUED, /* linked work items executed by rescuer */
PWQ_NR_STATS,
};
/*
* The per-pool workqueue. While queued, bits below WORK_PWQ_SHIFT
* 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 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 */
bool plugged; /* L: execution suspended */
/*
* nr_active management and WORK_STRUCT_INACTIVE:
*
* When pwq->nr_active >= max_active, new work item is queued to
* pwq->inactive_works instead of pool->worklist and marked with
* WORK_STRUCT_INACTIVE.
*
* All work items marked with WORK_STRUCT_INACTIVE do not participate in
* nr_active and all work items in pwq->inactive_works are marked with
* WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE work items are
* in pwq->inactive_works. Some of them are ready to run in
* pool->worklist or worker->scheduled. Those work itmes are only struct
* wq_barrier which is used for flush_work() and should not participate
* in nr_active. For non-barrier work item, it is marked with
* WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works.
*/
int nr_active; /* L: nr of active works */
struct list_head inactive_works; /* L: inactive works */
struct list_head pending_node; /* LN: node on wq_node_nr_active->pending_pwqs */
struct list_head pwqs_node; /* WR: node on wq->pwqs */
struct list_head mayday_node; /* MD: node on wq->maydays */
u64 stats[PWQ_NR_STATS];
/*
* Release of unbound pwq is punted to a kthread_worker. See put_pwq()
* and pwq_release_workfn() for details. pool_workqueue itself is also
* RCU protected so that the first pwq can be determined without
* grabbing wq->mutex.
*/
struct kthread_work release_work;
struct rcu_head rcu;
} __aligned(1 << WORK_STRUCT_PWQ_SHIFT);
/*
* Structure used to wait for workqueue flush.
*/
struct wq_flusher {
struct list_head list; /* WQ: list of flushers */
int flush_color; /* WQ: flush color waiting for */
struct completion done; /* flush completion */
};
struct wq_device;
/*
* Unlike in a per-cpu workqueue where max_active limits its concurrency level
* on each CPU, in an unbound workqueue, max_active applies to the whole system.
* As sharing a single nr_active across multiple sockets can be very expensive,
* the counting and enforcement is per NUMA node.
*
* The following struct is used to enforce per-node max_active. When a pwq wants
* to start executing a work item, it should increment ->nr using
* tryinc_node_nr_active(). If acquisition fails due to ->nr already being over
* ->max, the pwq is queued on ->pending_pwqs. As in-flight work items finish
* and decrement ->nr, node_activate_pending_pwq() activates the pending pwqs in
* round-robin order.
*/
struct wq_node_nr_active {
int max; /* per-node max_active */
atomic_t nr; /* per-node nr_active */
raw_spinlock_t lock; /* nests inside pool locks */
struct list_head pending_pwqs; /* LN: pwqs with inactive works */
};
/*
* The externally visible workqueue. It relays the issued work items to
* the appropriate worker_pool through its pool_workqueues.
*/
struct workqueue_struct {
struct list_head pwqs; /* WR: all pwqs of this wq */
struct list_head list; /* PR: 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; /* MD: rescue worker */
int nr_drainers; /* WQ: drain in progress */
/* See alloc_workqueue() function comment for info on min/max_active */
int max_active; /* WO: max active works */
int min_active; /* WO: min active works */
int saved_max_active; /* WQ: saved max_active */
int saved_min_active; /* WQ: saved min_active */
struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */
struct pool_workqueue __rcu *dfl_pwq; /* PW: only for unbound wqs */
#ifdef CONFIG_SYSFS
struct wq_device *wq_dev; /* I: for sysfs interface */
#endif
#ifdef CONFIG_LOCKDEP
char *lock_name;
struct lock_class_key key;
struct lockdep_map lockdep_map;
#endif
char name[WQ_NAME_LEN]; /* I: workqueue name */
/*
* Destruction of workqueue_struct is RCU protected to allow walking
* the workqueues list without grabbing wq_pool_mutex.
* This is used to dump all workqueues from sysrq.
*/
struct rcu_head rcu;
/* hot fields used during command issue, aligned to cacheline */
unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */
struct pool_workqueue __rcu * __percpu *cpu_pwq; /* I: per-cpu pwqs */
struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */
};
/*
* Each pod type describes how CPUs should be grouped for unbound workqueues.
* See the comment above workqueue_attrs->affn_scope.
*/
struct wq_pod_type {
int nr_pods; /* number of pods */
cpumask_var_t *pod_cpus; /* pod -> cpus */
int *pod_node; /* pod -> node */
int *cpu_pod; /* cpu -> pod */
};
struct work_offq_data {
u32 pool_id;
u32 disable;
u32 flags;
};
static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = {
[WQ_AFFN_DFL] = "default",
[WQ_AFFN_CPU] = "cpu",
[WQ_AFFN_SMT] = "smt",
[WQ_AFFN_CACHE] = "cache",
[WQ_AFFN_NUMA] = "numa",
[WQ_AFFN_SYSTEM] = "system",
};
/*
* Per-cpu work items which run for longer than the following threshold are
* automatically considered CPU intensive and excluded from concurrency
* management to prevent them from noticeably delaying other per-cpu work items.
* ULONG_MAX indicates that the user hasn't overridden it with a boot parameter.
* The actual value is initialized in wq_cpu_intensive_thresh_init().
*/
static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX;
module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644);
#ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT
static unsigned int wq_cpu_intensive_warning_thresh = 4;
module_param_named(cpu_intensive_warning_thresh, wq_cpu_intensive_warning_thresh, uint, 0644);
#endif
/* see the comment above the definition of WQ_POWER_EFFICIENT */
static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT);
module_param_named(power_efficient, wq_power_efficient, bool, 0444);
static bool wq_online; /* can kworkers be created yet? */
static bool wq_topo_initialized __read_mostly = false;
static struct kmem_cache *pwq_cache;
static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES];
static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE;
/* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */
static struct workqueue_attrs *unbound_wq_update_pwq_attrs_buf;
static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */
static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */
static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */
/* wait for manager to go away */
static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait);
static LIST_HEAD(workqueues); /* PR: list of all workqueues */
static bool workqueue_freezing; /* PL: have wqs started freezing? */
/* PL: mirror the cpu_online_mask excluding the CPU in the midst of hotplugging */
static cpumask_var_t wq_online_cpumask;
/* PL&A: allowable cpus for unbound wqs and work items */
static cpumask_var_t wq_unbound_cpumask;
/* PL: user requested unbound cpumask via sysfs */
static cpumask_var_t wq_requested_unbound_cpumask;
/* PL: isolated cpumask to be excluded from unbound cpumask */
static cpumask_var_t wq_isolated_cpumask;
/* for further constrain wq_unbound_cpumask by cmdline parameter*/
static struct cpumask wq_cmdline_cpumask __initdata;
/* CPU where unbound work was last round robin scheduled from this CPU */
static DEFINE_PER_CPU(int, wq_rr_cpu_last);
/*
* Local execution of unbound work items is no longer guaranteed. The
* following always forces round-robin CPU selection on unbound work items
* to uncover usages which depend on it.
*/
#ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU
static bool wq_debug_force_rr_cpu = true;
#else
static bool wq_debug_force_rr_cpu = false;
#endif
module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644);
/* to raise softirq for the BH worker pools on other CPUs */
static DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_work [NR_STD_WORKER_POOLS],
bh_pool_irq_works);
/* the BH worker pools */
static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
bh_worker_pools);
/* 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];
/* I: attributes used when instantiating ordered pools on demand */
static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
/*
* I: kthread_worker to release pwq's. pwq release needs to be bounced to a
* process context while holding a pool lock. Bounce to a dedicated kthread
* worker to avoid A-A deadlocks.
*/
static struct kthread_worker *pwq_release_worker __ro_after_init;
struct workqueue_struct *system_wq __ro_after_init;
EXPORT_SYMBOL(system_wq);
struct workqueue_struct *system_highpri_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_highpri_wq);
struct workqueue_struct *system_long_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_long_wq);
struct workqueue_struct *system_unbound_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_unbound_wq);
struct workqueue_struct *system_freezable_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_freezable_wq);
struct workqueue_struct *system_power_efficient_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_power_efficient_wq);
struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init;
EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq);
struct workqueue_struct *system_bh_wq;
EXPORT_SYMBOL_GPL(system_bh_wq);
struct workqueue_struct *system_bh_highpri_wq;
EXPORT_SYMBOL_GPL(system_bh_highpri_wq);
static int worker_thread(void *__worker);
static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
static void show_pwq(struct pool_workqueue *pwq);
static void show_one_worker_pool(struct worker_pool *pool);
#define CREATE_TRACE_POINTS
#include <trace/events/workqueue.h>
#define assert_rcu_or_pool_mutex() \
RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \
!lockdep_is_held(&wq_pool_mutex), \
"RCU or wq_pool_mutex should be held")
#define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \
RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \
!lockdep_is_held(&wq->mutex) && \
!lockdep_is_held(&wq_pool_mutex), \
"RCU, wq->mutex or wq_pool_mutex should be held")
#define for_each_bh_worker_pool(pool, cpu) \
for ((pool) = &per_cpu(bh_worker_pools, cpu)[0]; \
(pool) < &per_cpu(bh_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \
(pool)++)
#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)++)
/**
* for_each_pool - iterate through all worker_pools in the system
* @pool: iteration cursor
* @pi: integer used for iteration
*
* This must be called either with wq_pool_mutex held or 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.
*
* The if/else clause exists only for the lockdep assertion and can be
* ignored.
*/
#define for_each_pool(pool, pi) \
idr_for_each_entry(&worker_pool_idr, pool, pi) \
if (({ assert_rcu_or_pool_mutex(); false; })) { } \
else
/**
* for_each_pool_worker - iterate through all workers of a worker_pool
* @worker: iteration cursor
* @pool: worker_pool to iterate workers of
*
* This must be called with wq_pool_attach_mutex.
*
* The if/else clause exists only for the lockdep assertion and can be
* ignored.
*/
#define for_each_pool_worker(worker, pool) \
list_for_each_entry((worker), &(pool)->workers, node) \
if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \
else
/**
* 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 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, \
lockdep_is_held(&(wq->mutex)))
#ifdef CONFIG_DEBUG_OBJECTS_WORK
static const struct debug_obj_descr work_debug_descr;
static void *work_debug_hint(void *addr)
{
return ((struct work_struct *) addr)->func;
}
static bool work_is_static_object(void *addr)
{
struct work_struct *work = addr;
return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work));
}
/*
* fixup_init is called when:
* - an active object is initialized
*/
static bool work_fixup_init(void *addr, enum debug_obj_state state)
{
struct work_struct *work = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
cancel_work_sync(work);
debug_object_init(work, &work_debug_descr);
return true;
default:
return false;
}
}
/*
* fixup_free is called when:
* - an active object is freed
*/
static bool work_fixup_free(void *addr, enum debug_obj_state state)
{
struct work_struct *work = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
cancel_work_sync(work);
debug_object_free(work, &work_debug_descr);
return true;
default:
return false;
}
}
static const struct debug_obj_descr work_debug_descr = {
.name = "work_struct",
.debug_hint = work_debug_hint,
.is_static_object = work_is_static_object,
.fixup_init = work_fixup_init,
.fixup_free = work_fixup_free,
};
static inline void debug_work_activate(struct work_struct *work)
{
debug_object_activate(work, &work_debug_descr);
}
static inline void debug_work_deactivate(struct work_struct *work)
{
debug_object_deactivate(work, &work_debug_descr);
}
void __init_work(struct work_struct *work, int onstack)
{
if (onstack)
debug_object_init_on_stack(work, &work_debug_descr);
else
debug_object_init(work, &work_debug_descr);
}
EXPORT_SYMBOL_GPL(__init_work);
void destroy_work_on_stack(struct work_struct *work)
{
debug_object_free(work, &work_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_work_on_stack);
void destroy_delayed_work_on_stack(struct delayed_work *work)
{
destroy_timer_on_stack(&work->timer);
debug_object_free(&work->work, &work_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack);
#else
static inline void debug_work_activate(struct work_struct *work) { }
static inline void debug_work_deactivate(struct work_struct *work) { }
#endif
/**
* worker_pool_assign_id - allocate ID and assign it to @pool
* @pool: the pool pointer of interest
*
* Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned
* successfully, -errno on failure.
*/
static int worker_pool_assign_id(struct worker_pool *pool)
{
int ret;
lockdep_assert_held(&wq_pool_mutex);
ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE,
GFP_KERNEL);
if (ret >= 0) {
pool->id = ret;
return 0;
}
return ret;
}
static struct pool_workqueue __rcu **
unbound_pwq_slot(struct workqueue_struct *wq, int cpu)
{
if (cpu >= 0)
return per_cpu_ptr(wq->cpu_pwq, cpu);
else
return &wq->dfl_pwq;
}
/* @cpu < 0 for dfl_pwq */
static struct pool_workqueue *unbound_pwq(struct workqueue_struct *wq, int cpu)
{
return rcu_dereference_check(*unbound_pwq_slot(wq, cpu),
lockdep_is_held(&wq_pool_mutex) ||
lockdep_is_held(&wq->mutex));
}
/**
* unbound_effective_cpumask - effective cpumask of an unbound workqueue
* @wq: workqueue of interest
*
* @wq->unbound_attrs->cpumask contains the cpumask requested by the user which
* is masked with wq_unbound_cpumask to determine the effective cpumask. The
* default pwq is always mapped to the pool with the current effective cpumask.
*/
static struct cpumask *unbound_effective_cpumask(struct workqueue_struct *wq)
{
return unbound_pwq(wq, -1)->pool->attrs->__pod_cpumask;
}
static unsigned int work_color_to_flags(int color)
{
return color << WORK_STRUCT_COLOR_SHIFT;
}
static int get_work_color(unsigned long work_data)
{
return (work_data >> WORK_STRUCT_COLOR_SHIFT) &
((1 << WORK_STRUCT_COLOR_BITS) - 1);
}
static int work_next_color(int color)
{
return (color + 1) % WORK_NR_COLORS;
}
static unsigned long pool_offq_flags(struct worker_pool *pool)
{
return (pool->flags & POOL_BH) ? WORK_OFFQ_BH : 0;
}
/*
* 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_pwq(), set_work_pool_and_clear_pending() and mark_work_canceling()
* 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_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.
*/
static inline void set_work_data(struct work_struct *work, unsigned long data)
{
WARN_ON_ONCE(!work_pending(work));
atomic_long_set(&work->data, data | work_static(work));
}
static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq,
unsigned long flags)
{
set_work_data(work, (unsigned long)pwq | WORK_STRUCT_PENDING |
WORK_STRUCT_PWQ | flags);
}
static void set_work_pool_and_keep_pending(struct work_struct *work,
int pool_id, unsigned long flags)
{
set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) |
WORK_STRUCT_PENDING | flags);
}
static void set_work_pool_and_clear_pending(struct work_struct *work,
int pool_id, unsigned long flags)
{
/*
* The following wmb is paired with the implied mb in
* test_and_set_bit(PENDING) and ensures all updates to @work made
* here are visible to and precede any updates by the next PENDING
* owner.
*/
smp_wmb();
set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) |
flags);
/*
* The following mb guarantees that previous clear of a PENDING bit
* will not be reordered with any speculative LOADS or STORES from
* work->current_func, which is executed afterwards. This possible
* reordering can lead to a missed execution on attempt to queue
* the same @work. E.g. consider this case:
*
* CPU#0 CPU#1
* ---------------------------- --------------------------------
*
* 1 STORE event_indicated
* 2 queue_work_on() {
* 3 test_and_set_bit(PENDING)
* 4 } set_..._and_clear_pending() {
* 5 set_work_data() # clear bit
* 6 smp_mb()
* 7 work->current_func() {
* 8 LOAD event_indicated
* }
*
* Without an explicit full barrier speculative LOAD on line 8 can
* be executed before CPU#0 does STORE on line 1. If that happens,
* CPU#0 observes the PENDING bit is still set and new execution of
* a @work is not queued in a hope, that CPU#1 will eventually
* finish the queued @work. Meanwhile CPU#1 does not see
* event_indicated is set, because speculative LOAD was executed
* before actual STORE.
*/
smp_mb();
}
static inline struct pool_workqueue *work_struct_pwq(unsigned long data)
{
return (struct pool_workqueue *)(data & WORK_STRUCT_PWQ_MASK);
}
static struct pool_workqueue *get_work_pwq(struct work_struct *work)
{
unsigned long data = atomic_long_read(&work->data);
if (data & WORK_STRUCT_PWQ)
return work_struct_pwq(data);
else
return NULL;
}
/**
* get_work_pool - return the worker_pool a given work was associated with
* @work: the work item of interest
*
* Pools are created and destroyed under wq_pool_mutex, and allows read
* access under RCU read lock. As such, this function should be
* called under wq_pool_mutex or inside of a rcu_read_lock() region.
*
* 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.
*
* Return: The worker_pool @work was last associated with. %NULL if none.
*/
static struct worker_pool *get_work_pool(struct work_struct *work)
{
unsigned long data = atomic_long_read(&work->data);
int pool_id;
assert_rcu_or_pool_mutex();
if (data & WORK_STRUCT_PWQ)
return work_struct_pwq(data)->pool;
pool_id = data >> WORK_OFFQ_POOL_SHIFT;
if (pool_id == WORK_OFFQ_POOL_NONE)
return NULL;
return idr_find(&worker_pool_idr, pool_id);
}
static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits)
{
return (v >> shift) & ((1U << bits) - 1);
}
static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data)
{
WARN_ON_ONCE(data & WORK_STRUCT_PWQ);
offqd->pool_id = shift_and_mask(data, WORK_OFFQ_POOL_SHIFT,
WORK_OFFQ_POOL_BITS);
offqd->disable = shift_and_mask(data, WORK_OFFQ_DISABLE_SHIFT,
WORK_OFFQ_DISABLE_BITS);
offqd->flags = data & WORK_OFFQ_FLAG_MASK;
}
static unsigned long work_offqd_pack_flags(struct work_offq_data *offqd)
{
return ((unsigned long)offqd->disable << WORK_OFFQ_DISABLE_SHIFT) |
((unsigned long)offqd->flags);
}
/*
* 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 pool->lock held.
*/
/*
* Need to wake up a worker? Called from anything but currently
* running workers.
*
* Note that, because unbound workers never contribute to nr_running, this
* 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)
{
return !list_empty(&pool->worklist) && !pool->nr_running;
}
/* Can I start working? Called from busy but !running workers. */
static bool may_start_working(struct worker_pool *pool)
{
return pool->nr_idle;
}
/* Do I need to keep working? Called from currently running workers. */
static bool keep_working(struct worker_pool *pool)
{
return !list_empty(&pool->worklist) && (pool->nr_running <= 1);
}
/* Do we need a new worker? Called from manager. */
static bool need_to_create_worker(struct worker_pool *pool)
{
return need_more_worker(pool) && !may_start_working(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_MANAGER_ACTIVE;
int nr_idle = pool->nr_idle + managing; /* manager is considered idle */
int nr_busy = pool->nr_workers - nr_idle;
return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy;
}
/**
* worker_set_flags - set worker flags and adjust nr_running accordingly
* @worker: self
* @flags: flags to set
*
* Set @flags in @worker->flags and adjust nr_running accordingly.
*/
static inline void worker_set_flags(struct worker *worker, unsigned int flags)
{
struct worker_pool *pool = worker->pool;
lockdep_assert_held(&pool->lock);
/* If transitioning into NOT_RUNNING, adjust nr_running. */
if ((flags & WORKER_NOT_RUNNING) &&
!(worker->flags & WORKER_NOT_RUNNING)) {
pool->nr_running--;
}
worker->flags |= flags;
}
/**
* worker_clr_flags - clear worker flags and adjust nr_running accordingly
* @worker: self
* @flags: flags to clear
*
* Clear @flags in @worker->flags and adjust nr_running accordingly.
*/
static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
{
struct worker_pool *pool = worker->pool;
unsigned int oflags = worker->flags;
lockdep_assert_held(&pool->lock);
worker->flags &= ~flags;
/*
* If transitioning out of NOT_RUNNING, increment nr_running. Note
* that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask
* of multiple flags, not a single flag.
*/
if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING))
if (!(worker->flags & WORKER_NOT_RUNNING))
pool->nr_running++;
}
/* Return the first idle worker. Called with pool->lock held. */
static struct worker *first_idle_worker(struct worker_pool *pool)
{
if (unlikely(list_empty(&pool->idle_list)))
return NULL;
return list_first_entry(&pool->idle_list, struct worker, entry);
}
/**
* worker_enter_idle - enter idle state
* @worker: worker which is entering idle state
*
* @worker is entering idle state. Update stats and idle timer if
* necessary.
*
* LOCKING:
* raw_spin_lock_irq(pool->lock).
*/
static void worker_enter_idle(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
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 create_worker() */
worker->flags |= WORKER_IDLE;
pool->nr_idle++;
worker->last_active = jiffies;
/* idle_list is LIFO */
list_add(&worker->entry, &pool->idle_list);
if (too_many_workers(pool) && !timer_pending(&pool->idle_timer))
mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT);
/* Sanity check nr_running. */
WARN_ON_ONCE(pool->nr_workers == pool->nr_idle && pool->nr_running);
}
/**
* worker_leave_idle - leave idle state
* @worker: worker which is leaving idle state
*
* @worker is leaving idle state. Update stats.
*
* LOCKING:
* raw_spin_lock_irq(pool->lock).
*/
static void worker_leave_idle(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE)))
return;
worker_clr_flags(worker, WORKER_IDLE);
pool->nr_idle--;
list_del_init(&worker->entry);
}
/**
* 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 @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:
* raw_spin_lock_irq(pool->lock).
*
* Return:
* Pointer to worker which is executing @work if found, %NULL
* otherwise.
*/
static struct worker *find_worker_executing_work(struct worker_pool *pool,
struct work_struct *work)
{
struct worker *worker;
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;
}
/**
* move_linked_works - move linked works to a list
* @work: start of series of works to be scheduled
* @head: target list to append @work to
* @nextp: out parameter for nested worklist walking
*
* Schedule linked works starting from @work to @head. Work series to be
* scheduled starts at @work and includes any consecutive work with
* WORK_STRUCT_LINKED set in its predecessor. See assign_work() for details on
* @nextp.
*
* CONTEXT:
* raw_spin_lock_irq(pool->lock).
*/
static void move_linked_works(struct work_struct *work, struct list_head *head,
struct work_struct **nextp)
{
struct work_struct *n;
/*
* Linked worklist will always end before the end of the list,
* use NULL for list head.
*/
list_for_each_entry_safe_from(work, n, NULL, entry) {
list_move_tail(&work->entry, head);
if (!(*work_data_bits(work) & WORK_STRUCT_LINKED))
break;
}
/*
* If we're already inside safe list traversal and have moved
* multiple works to the scheduled queue, the next position
* needs to be updated.
*/
if (nextp)
*nextp = n;
}
/**
* assign_work - assign a work item and its linked work items to a worker
* @work: work to assign
* @worker: worker to assign to
* @nextp: out parameter for nested worklist walking
*
* Assign @work and its linked work items to @worker. If @work is already being
* executed by another worker in the same pool, it'll be punted there.
*
* If @nextp is not NULL, it's updated to point to the next work of the last
* scheduled work. This allows assign_work() to be nested inside
* list_for_each_entry_safe().
*
* Returns %true if @work was successfully assigned to @worker. %false if @work
* was punted to another worker already executing it.
*/
static bool assign_work(struct work_struct *work, struct worker *worker,
struct work_struct **nextp)
{
struct worker_pool *pool = worker->pool;
struct worker *collision;
lockdep_assert_held(&pool->lock);
/*
* A single work shouldn't be executed concurrently by multiple workers.
* __queue_work() ensures that @work doesn't jump to a different pool
* while still running in the previous pool. Here, we should ensure that
* @work is not executed concurrently by multiple workers from the same
* pool. Check whether anyone is already processing the work. If so,
* defer the work to the currently executing one.
*/
collision = find_worker_executing_work(pool, work);
if (unlikely(collision)) {
move_linked_works(work, &collision->scheduled, nextp);
return false;
}
move_linked_works(work, &worker->scheduled, nextp);
return true;
}
static struct irq_work *bh_pool_irq_work(struct worker_pool *pool)
{
int high = pool->attrs->nice == HIGHPRI_NICE_LEVEL ? 1 : 0;
return &per_cpu(bh_pool_irq_works, pool->cpu)[high];
}
static void kick_bh_pool(struct worker_pool *pool)
{
#ifdef CONFIG_SMP
/* see drain_dead_softirq_workfn() for BH_DRAINING */
if (unlikely(pool->cpu != smp_processor_id() &&
!(pool->flags & POOL_BH_DRAINING))) {
irq_work_queue_on(bh_pool_irq_work(pool), pool->cpu);
return;
}
#endif
if (pool->attrs->nice == HIGHPRI_NICE_LEVEL)
raise_softirq_irqoff(HI_SOFTIRQ);
else
raise_softirq_irqoff(TASKLET_SOFTIRQ);
}
/**
* kick_pool - wake up an idle worker if necessary
* @pool: pool to kick
*
* @pool may have pending work items. Wake up worker if necessary. Returns
* whether a worker was woken up.
*/
static bool kick_pool(struct worker_pool *pool)
{
struct worker *worker = first_idle_worker(pool);
struct task_struct *p;
lockdep_assert_held(&pool->lock);
if (!need_more_worker(pool) || !worker)
return false;
if (pool->flags & POOL_BH) {
kick_bh_pool(pool);
return true;
}
p = worker->task;
#ifdef CONFIG_SMP
/*
* Idle @worker is about to execute @work and waking up provides an
* opportunity to migrate @worker at a lower cost by setting the task's
* wake_cpu field. Let's see if we want to move @worker to improve
* execution locality.
*
* We're waking the worker that went idle the latest and there's some
* chance that @worker is marked idle but hasn't gone off CPU yet. If
* so, setting the wake_cpu won't do anything. As this is a best-effort
* optimization and the race window is narrow, let's leave as-is for
* now. If this becomes pronounced, we can skip over workers which are
* still on cpu when picking an idle worker.
*
* If @pool has non-strict affinity, @worker might have ended up outside
* its affinity scope. Repatriate.
*/
if (!pool->attrs->affn_strict &&
!cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) {
struct work_struct *work = list_first_entry(&pool->worklist,
struct work_struct, entry);
int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask,
cpu_online_mask);
if (wake_cpu < nr_cpu_ids) {
p->wake_cpu = wake_cpu;
get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++;
}
}
#endif
wake_up_process(p);
return true;
}
#ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT
/*
* Concurrency-managed per-cpu work items that hog CPU for longer than
* wq_cpu_intensive_thresh_us trigger the automatic CPU_INTENSIVE mechanism,
* which prevents them from stalling other concurrency-managed work items. If a
* work function keeps triggering this mechanism, it's likely that the work item
* should be using an unbound workqueue instead.
*
* wq_cpu_intensive_report() tracks work functions which trigger such conditions
* and report them so that they can be examined and converted to use unbound
* workqueues as appropriate. To avoid flooding the console, each violating work
* function is tracked and reported with exponential backoff.
*/
#define WCI_MAX_ENTS 128
struct wci_ent {
work_func_t func;
atomic64_t cnt;
struct hlist_node hash_node;
};
static struct wci_ent wci_ents[WCI_MAX_ENTS];
static int wci_nr_ents;
static DEFINE_RAW_SPINLOCK(wci_lock);
static DEFINE_HASHTABLE(wci_hash, ilog2(WCI_MAX_ENTS));
static struct wci_ent *wci_find_ent(work_func_t func)
{
struct wci_ent *ent;
hash_for_each_possible_rcu(wci_hash, ent, hash_node,
(unsigned long)func) {
if (ent->func == func)
return ent;
}
return NULL;
}
static void wq_cpu_intensive_report(work_func_t func)
{
struct wci_ent *ent;
restart:
ent = wci_find_ent(func);
if (ent) {
u64 cnt;
/*
* Start reporting from the warning_thresh and back off
* exponentially.
*/
cnt = atomic64_inc_return_relaxed(&ent->cnt);
if (wq_cpu_intensive_warning_thresh &&
cnt >= wq_cpu_intensive_warning_thresh &&
is_power_of_2(cnt + 1 - wq_cpu_intensive_warning_thresh))
printk_deferred(KERN_WARNING "workqueue: %ps hogged CPU for >%luus %llu times, consider switching to WQ_UNBOUND\n",
ent->func, wq_cpu_intensive_thresh_us,
atomic64_read(&ent->cnt));
return;
}
/*
* @func is a new violation. Allocate a new entry for it. If wcn_ents[]
* is exhausted, something went really wrong and we probably made enough
* noise already.
*/
if (wci_nr_ents >= WCI_MAX_ENTS)
return;
raw_spin_lock(&wci_lock);
if (wci_nr_ents >= WCI_MAX_ENTS) {
raw_spin_unlock(&wci_lock);
return;
}
if (wci_find_ent(func)) {
raw_spin_unlock(&wci_lock);
goto restart;
}
ent = &wci_ents[wci_nr_ents++];
ent->func = func;
atomic64_set(&ent->cnt, 0);
hash_add_rcu(wci_hash, &ent->hash_node, (unsigned long)func);
raw_spin_unlock(&wci_lock);
goto restart;
}
#else /* CONFIG_WQ_CPU_INTENSIVE_REPORT */
static void wq_cpu_intensive_report(work_func_t func) {}
#endif /* CONFIG_WQ_CPU_INTENSIVE_REPORT */
/**
* wq_worker_running - a worker is running again
* @task: task waking up
*
* This function is called when a worker returns from schedule()
*/
void wq_worker_running(struct task_struct *task)
{
struct worker *worker = kthread_data(task);
if (!READ_ONCE(worker->sleeping))
return;
/*
* If preempted by unbind_workers() between the WORKER_NOT_RUNNING check
* and the nr_running increment below, we may ruin the nr_running reset
* and leave with an unexpected pool->nr_running == 1 on the newly unbound
* pool. Protect against such race.
*/
preempt_disable();
if (!(worker->flags & WORKER_NOT_RUNNING))
worker->pool->nr_running++;
preempt_enable();
/*
* CPU intensive auto-detection cares about how long a work item hogged
* CPU without sleeping. Reset the starting timestamp on wakeup.
*/
worker->current_at = worker->task->se.sum_exec_runtime;
WRITE_ONCE(worker->sleeping, 0);
}
/**
* wq_worker_sleeping - a worker is going to sleep
* @task: task going to sleep
*
* This function is called from schedule() when a busy worker is
* going to sleep.
*/
void wq_worker_sleeping(struct task_struct *task)
{
struct worker *worker = kthread_data(task);
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;
pool = worker->pool;
/* Return if preempted before wq_worker_running() was reached */
if (READ_ONCE(worker->sleeping))
return;
WRITE_ONCE(worker->sleeping, 1);
raw_spin_lock_irq(&pool->lock);
/*
* Recheck in case unbind_workers() preempted us. We don't
* want to decrement nr_running after the worker is unbound
* and nr_running has been reset.
*/
if (worker->flags & WORKER_NOT_RUNNING) {
raw_spin_unlock_irq(&pool->lock);
return;
}
pool->nr_running--;
if (kick_pool(pool))
worker->current_pwq->stats[PWQ_STAT_CM_WAKEUP]++;
raw_spin_unlock_irq(&pool->lock);
}
/**
* wq_worker_tick - a scheduler tick occurred while a kworker is running
* @task: task currently running
*
* Called from sched_tick(). We're in the IRQ context and the current
* worker's fields which follow the 'K' locking rule can be accessed safely.
*/
void wq_worker_tick(struct task_struct *task)
{
struct worker *worker = kthread_data(task);
struct pool_workqueue *pwq = worker->current_pwq;
struct worker_pool *pool = worker->pool;
if (!pwq)
return;
pwq->stats[PWQ_STAT_CPU_TIME] += TICK_USEC;
if (!wq_cpu_intensive_thresh_us)
return;
/*
* If the current worker is concurrency managed and hogged the CPU for
* longer than wq_cpu_intensive_thresh_us, it's automatically marked
* CPU_INTENSIVE to avoid stalling other concurrency-managed work items.
*
* Set @worker->sleeping means that @worker is in the process of
* switching out voluntarily and won't be contributing to
* @pool->nr_running until it wakes up. As wq_worker_sleeping() also
* decrements ->nr_running, setting CPU_INTENSIVE here can lead to
* double decrements. The task is releasing the CPU anyway. Let's skip.
* We probably want to make this prettier in the future.
*/
if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) ||
worker->task->se.sum_exec_runtime - worker->current_at <
wq_cpu_intensive_thresh_us * NSEC_PER_USEC)
return;
raw_spin_lock(&pool->lock);
worker_set_flags(worker, WORKER_CPU_INTENSIVE);
wq_cpu_intensive_report(worker->current_func);
pwq->stats[PWQ_STAT_CPU_INTENSIVE]++;
if (kick_pool(pool))
pwq->stats[PWQ_STAT_CM_WAKEUP]++;
raw_spin_unlock(&pool->lock);
}
/**
* wq_worker_last_func - retrieve worker's last work function
* @task: Task to retrieve last work function of.
*
* Determine the last function a worker executed. This is called from
* the scheduler to get a worker's last known identity.
*
* CONTEXT:
* raw_spin_lock_irq(rq->lock)
*
* This function is called during schedule() when a kworker is going
* to sleep. It's used by psi to identify aggregation workers during
* dequeuing, to allow periodic aggregation to shut-off when that
* worker is the last task in the system or cgroup to go to sleep.
*
* As this function doesn't involve any workqueue-related locking, it
* only returns stable values when called from inside the scheduler's
* queuing and dequeuing paths, when @task, which must be a kworker,
* is guaranteed to not be processing any works.
*
* Return:
* The last work function %current executed as a worker, NULL if it
* hasn't executed any work yet.
*/
work_func_t wq_worker_last_func(struct task_struct *task)
{
struct worker *worker = kthread_data(task);
return worker->last_func;
}
/**
* wq_node_nr_active - Determine wq_node_nr_active to use
* @wq: workqueue of interest
* @node: NUMA node, can be %NUMA_NO_NODE
*
* Determine wq_node_nr_active to use for @wq on @node. Returns:
*
* - %NULL for per-cpu workqueues as they don't need to use shared nr_active.
*
* - node_nr_active[nr_node_ids] if @node is %NUMA_NO_NODE.
*
* - Otherwise, node_nr_active[@node].
*/
static struct wq_node_nr_active *wq_node_nr_active(struct workqueue_struct *wq,
int node)
{
if (!(wq->flags & WQ_UNBOUND))
return NULL;
if (node == NUMA_NO_NODE)
node = nr_node_ids;
return wq->node_nr_active[node];
}
/**
* wq_update_node_max_active - Update per-node max_actives to use
* @wq: workqueue to update
* @off_cpu: CPU that's going down, -1 if a CPU is not going down
*
* Update @wq->node_nr_active[]->max. @wq must be unbound. max_active is
* distributed among nodes according to the proportions of numbers of online
* cpus. The result is always between @wq->min_active and max_active.
*/
static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu)
{
struct cpumask *effective = unbound_effective_cpumask(wq);
int min_active = READ_ONCE(wq->min_active);
int max_active = READ_ONCE(wq->max_active);
int total_cpus, node;
lockdep_assert_held(&wq->mutex);
if (!wq_topo_initialized)
return;
if (off_cpu >= 0 && !cpumask_test_cpu(off_cpu, effective))
off_cpu = -1;
total_cpus = cpumask_weight_and(effective, cpu_online_mask);
if (off_cpu >= 0)
total_cpus--;
/* If all CPUs of the wq get offline, use the default values */
if (unlikely(!total_cpus)) {
for_each_node(node)
wq_node_nr_active(wq, node)->max = min_active;
wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active;
return;
}
for_each_node(node) {
int node_cpus;
node_cpus = cpumask_weight_and(effective, cpumask_of_node(node));
if (off_cpu >= 0 && cpu_to_node(off_cpu) == node)
node_cpus--;
wq_node_nr_active(wq, node)->max =
clamp(DIV_ROUND_UP(max_active * node_cpus, total_cpus),
min_active, max_active);
}
wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active;
}
/**
* 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)
{
lockdep_assert_held(&pwq->pool->lock);
if (likely(--pwq->refcnt))
return;
/*
* @pwq can't be released under pool->lock, bounce to a dedicated
* kthread_worker to avoid A-A deadlocks.
*/
kthread_queue_work(pwq_release_worker, &pwq->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 RCU protected, the
* following lock operations are safe.
*/
raw_spin_lock_irq(&pwq->pool->lock);
put_pwq(pwq);
raw_spin_unlock_irq(&pwq->pool->lock);
}
}
static bool pwq_is_empty(struct pool_workqueue *pwq)
{
return !pwq->nr_active && list_empty(&pwq->inactive_works);
}
static void __pwq_activate_work(struct pool_workqueue *pwq,
struct work_struct *work)
{
unsigned long *wdb = work_data_bits(work);
WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE));
trace_workqueue_activate_work(work);
if (list_empty(&pwq->pool->worklist))
pwq->pool->watchdog_ts = jiffies;
move_linked_works(work, &pwq->pool->worklist, NULL);
__clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb);
}
static bool tryinc_node_nr_active(struct wq_node_nr_active *nna)
{
int max = READ_ONCE(nna->max);
while (true) {
int old, tmp;
old = atomic_read(&nna->nr);
if (old >= max)
return false;
tmp = atomic_cmpxchg_relaxed(&nna->nr, old, old + 1);
if (tmp == old)
return true;
}
}
/**
* pwq_tryinc_nr_active - Try to increment nr_active for a pwq
* @pwq: pool_workqueue of interest
* @fill: max_active may have increased, try to increase concurrency level
*
* Try to increment nr_active for @pwq. Returns %true if an nr_active count is
* successfully obtained. %false otherwise.
*/
static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill)
{
struct workqueue_struct *wq = pwq->wq;
struct worker_pool *pool = pwq->pool;
struct wq_node_nr_active *nna = wq_node_nr_active(wq, pool->node);
bool obtained = false;
lockdep_assert_held(&pool->lock);
if (!nna) {
/* BH or per-cpu workqueue, pwq->nr_active is sufficient */
obtained = pwq->nr_active < READ_ONCE(wq->max_active);
goto out;
}
if (unlikely(pwq->plugged))
return false;
/*
* Unbound workqueue uses per-node shared nr_active $nna. If @pwq is
* already waiting on $nna, pwq_dec_nr_active() will maintain the
* concurrency level. Don't jump the line.
*
* We need to ignore the pending test after max_active has increased as
* pwq_dec_nr_active() can only maintain the concurrency level but not
* increase it. This is indicated by @fill.
*/
if (!list_empty(&pwq->pending_node) && likely(!fill))
goto out;
obtained = tryinc_node_nr_active(nna);
if (obtained)
goto out;
/*
* Lockless acquisition failed. Lock, add ourself to $nna->pending_pwqs
* and try again. The smp_mb() is paired with the implied memory barrier
* of atomic_dec_return() in pwq_dec_nr_active() to ensure that either
* we see the decremented $nna->nr or they see non-empty
* $nna->pending_pwqs.
*/
raw_spin_lock(&nna->lock);
if (list_empty(&pwq->pending_node))
list_add_tail(&pwq->pending_node, &nna->pending_pwqs);
else if (likely(!fill))
goto out_unlock;
smp_mb();
obtained = tryinc_node_nr_active(nna);
/*
* If @fill, @pwq might have already been pending. Being spuriously
* pending in cold paths doesn't affect anything. Let's leave it be.
*/
if (obtained && likely(!fill))
list_del_init(&pwq->pending_node);
out_unlock:
raw_spin_unlock(&nna->lock);
out:
if (obtained)
pwq->nr_active++;
return obtained;
}
/**
* pwq_activate_first_inactive - Activate the first inactive work item on a pwq
* @pwq: pool_workqueue of interest
* @fill: max_active may have increased, try to increase concurrency level
*
* Activate the first inactive work item of @pwq if available and allowed by
* max_active limit.
*
* Returns %true if an inactive work item has been activated. %false if no
* inactive work item is found or max_active limit is reached.
*/
static bool pwq_activate_first_inactive(struct pool_workqueue *pwq, bool fill)
{
struct work_struct *work =
list_first_entry_or_null(&pwq->inactive_works,
struct work_struct, entry);
if (work && pwq_tryinc_nr_active(pwq, fill)) {
__pwq_activate_work(pwq, work);
return true;
} else {
return false;
}
}
/**
* unplug_oldest_pwq - unplug the oldest pool_workqueue
* @wq: workqueue_struct where its oldest pwq is to be unplugged
*
* This function should only be called for ordered workqueues where only the
* oldest pwq is unplugged, the others are plugged to suspend execution to
* ensure proper work item ordering::
*
* dfl_pwq --------------+ [P] - plugged
* |
* v
* pwqs -> A -> B [P] -> C [P] (newest)
* | | |
* 1 3 5
* | | |
* 2 4 6
*
* When the oldest pwq is drained and removed, this function should be called
* to unplug the next oldest one to start its work item execution. Note that
* pwq's are linked into wq->pwqs with the oldest first, so the first one in
* the list is the oldest.
*/
static void unplug_oldest_pwq(struct workqueue_struct *wq)
{
struct pool_workqueue *pwq;
lockdep_assert_held(&wq->mutex);
/* Caller should make sure that pwqs isn't empty before calling */
pwq = list_first_entry_or_null(&wq->pwqs, struct pool_workqueue,
pwqs_node);
raw_spin_lock_irq(&pwq->pool->lock);
if (pwq->plugged) {
pwq->plugged = false;
if (pwq_activate_first_inactive(pwq, true))
kick_pool(pwq->pool);
}
raw_spin_unlock_irq(&pwq->pool->lock);
}
/**
* node_activate_pending_pwq - Activate a pending pwq on a wq_node_nr_active
* @nna: wq_node_nr_active to activate a pending pwq for
* @caller_pool: worker_pool the caller is locking
*
* Activate a pwq in @nna->pending_pwqs. Called with @caller_pool locked.
* @caller_pool may be unlocked and relocked to lock other worker_pools.
*/
static void node_activate_pending_pwq(struct wq_node_nr_active *nna,
struct worker_pool *caller_pool)
{
struct worker_pool *locked_pool = caller_pool;
struct pool_workqueue *pwq;
struct work_struct *work;
lockdep_assert_held(&caller_pool->lock);
raw_spin_lock(&nna->lock);
retry:
pwq = list_first_entry_or_null(&nna->pending_pwqs,
struct pool_workqueue, pending_node);
if (!pwq)
goto out_unlock;
/*
* If @pwq is for a different pool than @locked_pool, we need to lock
* @pwq->pool->lock. Let's trylock first. If unsuccessful, do the unlock
* / lock dance. For that, we also need to release @nna->lock as it's
* nested inside pool locks.
*/
if (pwq->pool != locked_pool) {
raw_spin_unlock(&locked_pool->lock);
locked_pool = pwq->pool;
if (!raw_spin_trylock(&locked_pool->lock)) {
raw_spin_unlock(&nna->lock);
raw_spin_lock(&locked_pool->lock);
raw_spin_lock(&nna->lock);
goto retry;
}
}
/*
* $pwq may not have any inactive work items due to e.g. cancellations.
* Drop it from pending_pwqs and see if there's another one.
*/
work = list_first_entry_or_null(&pwq->inactive_works,
struct work_struct, entry);
if (!work) {
list_del_init(&pwq->pending_node);
goto retry;
}
/*
* Acquire an nr_active count and activate the inactive work item. If
* $pwq still has inactive work items, rotate it to the end of the
* pending_pwqs so that we round-robin through them. This means that
* inactive work items are not activated in queueing order which is fine
* given that there has never been any ordering across different pwqs.
*/
if (likely(tryinc_node_nr_active(nna))) {
pwq->nr_active++;
__pwq_activate_work(pwq, work);
if (list_empty(&pwq->inactive_works))
list_del_init(&pwq->pending_node);
else
list_move_tail(&pwq->pending_node, &nna->pending_pwqs);
/* if activating a foreign pool, make sure it's running */
if (pwq->pool != caller_pool)
kick_pool(pwq->pool);
}
out_unlock:
raw_spin_unlock(&nna->lock);
if (locked_pool != caller_pool) {
raw_spin_unlock(&locked_pool->lock);
raw_spin_lock(&caller_pool->lock);
}
}
/**
* pwq_dec_nr_active - Retire an active count
* @pwq: pool_workqueue of interest
*
* Decrement @pwq's nr_active and try to activate the first inactive work item.
* For unbound workqueues, this function may temporarily drop @pwq->pool->lock.
*/
static void pwq_dec_nr_active(struct pool_workqueue *pwq)
{
struct worker_pool *pool = pwq->pool;
struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pool->node);
lockdep_assert_held(&pool->lock);
/*
* @pwq->nr_active should be decremented for both percpu and unbound
* workqueues.
*/
pwq->nr_active--;
/*
* For a percpu workqueue, it's simple. Just need to kick the first
* inactive work item on @pwq itself.
*/
if (!nna) {
pwq_activate_first_inactive(pwq, false);
return;
}
/*
* If @pwq is for an unbound workqueue, it's more complicated because
* multiple pwqs and pools may be sharing the nr_active count. When a
* pwq needs to wait for an nr_active count, it puts itself on
* $nna->pending_pwqs. The following atomic_dec_return()'s implied
* memory barrier is paired with smp_mb() in pwq_tryinc_nr_active() to
* guarantee that either we see non-empty pending_pwqs or they see
* decremented $nna->nr.
*
* $nna->max may change as CPUs come online/offline and @pwq->wq's
* max_active gets updated. However, it is guaranteed to be equal to or
* larger than @pwq->wq->min_active which is above zero unless freezing.
* This maintains the forward progress guarantee.
*/
if (atomic_dec_return(&nna->nr) >= READ_ONCE(nna->max))
return;
if (!list_empty(&nna->pending_pwqs))
node_activate_pending_pwq(nna, pool);
}
/**
* pwq_dec_nr_in_flight - decrement pwq's nr_in_flight
* @pwq: pwq of interest
* @work_data: work_data of work which left the queue
*
* A work either has completed or is removed from pending queue,
* decrement nr_in_flight of its pwq and handle workqueue flushing.
*
* NOTE:
* For unbound workqueues, this function may temporarily drop @pwq->pool->lock
* and thus should be called after all other state updates for the in-flight
* work item is complete.
*
* CONTEXT:
* raw_spin_lock_irq(pool->lock).
*/
static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_data)
{
int color = get_work_color(work_data);
if (!(work_data & WORK_STRUCT_INACTIVE))
pwq_dec_nr_active(pwq);
pwq->nr_in_flight[color]--;
/* is flush in progress and are we at the flushing tip? */
if (likely(pwq->flush_color != color))
goto out_put;
/* are there still in-flight works? */
if (pwq->nr_in_flight[color])
goto out_put;
/* this pwq is done, clear flush_color */
pwq->flush_color = -1;
/*
* If this was the last pwq, wake up the first flusher. It
* will handle the rest.
*/
if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush))
complete(&pwq->wq->first_flusher->done);
out_put:
put_pwq(pwq);
}
/**
* try_to_grab_pending - steal work item from worklist and disable irq
* @work: work item to steal
* @cflags: %WORK_CANCEL_ flags
* @irq_flags: place to store irq state
*
* Try to grab PENDING bit of @work. This function can handle @work in any
* stable state - idle, on timer or on worklist.
*
* Return:
*
* ======== ================================================================
* 1 if @work was pending and we successfully stole PENDING
* 0 if @work was idle and we claimed PENDING
* -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry
* ======== ================================================================
*
* Note:
* On >= 0 return, the caller owns @work's PENDING bit. To avoid getting
* interrupted while holding PENDING and @work off queue, irq must be
* disabled on entry. This, combined with delayed_work->timer being
* irqsafe, ensures that we return -EAGAIN for finite short period of time.
*
* On successful return, >= 0, irq is disabled and the caller is
* responsible for releasing it using local_irq_restore(*@irq_flags).
*
* This function is safe to call from any context including IRQ handler.
*/
static int try_to_grab_pending(struct work_struct *work, u32 cflags,
unsigned long *irq_flags)
{
struct worker_pool *pool;
struct pool_workqueue *pwq;
local_irq_save(*irq_flags);
/* try to steal the timer if it exists */
if (cflags & WORK_CANCEL_DELAYED) {
struct delayed_work *dwork = to_delayed_work(work);
/*
* dwork->timer is irqsafe. If del_timer() fails, it's
* guaranteed that the timer is not queued anywhere and not
* running on the local CPU.
*/
if (likely(del_timer(&dwork->timer)))
return 1;
}
/* try to claim PENDING the normal way */
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)))
return 0;
rcu_read_lock();
/*
* The queueing is in progress, or it is already queued. Try to
* steal it from ->worklist without clearing WORK_STRUCT_PENDING.
*/
pool = get_work_pool(work);
if (!pool)
goto fail;
raw_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) {
unsigned long work_data = *work_data_bits(work);
debug_work_deactivate(work);
/*
* A cancelable inactive work item must be in the
* pwq->inactive_works since a queued barrier can't be
* canceled (see the comments in insert_wq_barrier()).
*
* An inactive work item cannot be deleted directly because
* it might have linked barrier work items which, if left
* on the inactive_works list, will confuse pwq->nr_active
* management later on and cause stall. Move the linked
* barrier work items to the worklist when deleting the grabbed
* item. Also keep WORK_STRUCT_INACTIVE in work_data, so that
* it doesn't participate in nr_active management in later
* pwq_dec_nr_in_flight().
*/
if (work_data & WORK_STRUCT_INACTIVE)
move_linked_works(work, &pwq->pool->worklist, NULL);
list_del_init(&work->entry);
/*
* work->data points to pwq iff queued. Let's point to pool. As
* this destroys work->data needed by the next step, stash it.
*/
set_work_pool_and_keep_pending(work, pool->id,
pool_offq_flags(pool));
/* must be the last step, see the function comment */
pwq_dec_nr_in_flight(pwq, work_data);
raw_spin_unlock(&pool->lock);
rcu_read_unlock();
return 1;
}
raw_spin_unlock(&pool->lock);
fail:
rcu_read_unlock();
local_irq_restore(*irq_flags);
return -EAGAIN;
}
/**
* work_grab_pending - steal work item from worklist and disable irq
* @work: work item to steal
* @cflags: %WORK_CANCEL_ flags
* @irq_flags: place to store IRQ state
*
* Grab PENDING bit of @work. @work can be in any stable state - idle, on timer
* or on worklist.
*
* Can be called from any context. IRQ is disabled on return with IRQ state
* stored in *@irq_flags. The caller is responsible for re-enabling it using
* local_irq_restore().
*
* Returns %true if @work was pending. %false if idle.
*/
static bool work_grab_pending(struct work_struct *work, u32 cflags,
unsigned long *irq_flags)
{
int ret;
while (true) {
ret = try_to_grab_pending(work, cflags, irq_flags);
if (ret >= 0)
return ret;
cpu_relax();
}
}
/**
* 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 @pwq after @head. @extra_flags is or'd to
* work_struct flags.
*
* CONTEXT:
* raw_spin_lock_irq(pool->lock).
*/
static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
struct list_head *head, unsigned int extra_flags)
{
debug_work_activate(work);
/* record the work call stack in order to print it in KASAN reports */
kasan_record_aux_stack_noalloc(work);
/* we own @work, set data and link */
set_work_pwq(work, pwq, extra_flags);
list_add_tail(&work->entry, head);
get_pwq(pwq);
}
/*
* Test whether @work is being queued from another work executing on the
* same workqueue.
*/
static bool is_chained_work(struct workqueue_struct *wq)
{
struct worker *worker;
worker = current_wq_worker();
/*
* Return %true iff I'm a worker executing a work item on @wq. If
* I'm @worker, it's safe to dereference it without locking.
*/
return worker && worker->current_pwq->wq == wq;
}
/*
* When queueing an unbound work item to a wq, prefer local CPU if allowed
* by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to
* avoid perturbing sensitive tasks.
*/
static int wq_select_unbound_cpu(int cpu)
{
int new_cpu;
if (likely(!wq_debug_force_rr_cpu)) {
if (cpumask_test_cpu(cpu, wq_unbound_cpumask))
return cpu;
} else {
pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n");
}
new_cpu = __this_cpu_read(wq_rr_cpu_last);
new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask);
if (unlikely(new_cpu >= nr_cpu_ids)) {
new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask);
if (unlikely(new_cpu >= nr_cpu_ids))
return cpu;
}
__this_cpu_write(wq_rr_cpu_last, new_cpu);
return new_cpu;
}
static void __queue_work(int cpu, struct workqueue_struct *wq,
struct work_struct *work)
{
struct pool_workqueue *pwq;
struct worker_pool *last_pool, *pool;
unsigned int work_flags;
unsigned int req_cpu = cpu;
/*
* While a work item is PENDING && off queue, a task trying to
* steal the PENDING will busy-loop waiting for it to either get
* queued or lose PENDING. Grabbing PENDING and queueing should
* happen with IRQ disabled.
*/
lockdep_assert_irqs_disabled();
/*
* For a draining wq, only works from the same workqueue are
* allowed. The __WQ_DESTROYING helps to spot the issue that
* queues a new work item to a wq after destroy_workqueue(wq).
*/
if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) &&
WARN_ON_ONCE(!is_chained_work(wq))))
return;
rcu_read_lock();
retry:
/* pwq which will be used unless @work is executing elsewhere */
if (req_cpu == WORK_CPU_UNBOUND) {
if (wq->flags & WQ_UNBOUND)
cpu = wq_select_unbound_cpu(raw_smp_processor_id());
else
cpu = raw_smp_processor_id();
}
pwq = rcu_dereference(*per_cpu_ptr(wq->cpu_pwq, cpu));
pool = pwq->pool;
/*
* 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.
*
* For ordered workqueue, work items must be queued on the newest pwq
* for accurate order management. Guaranteed order also guarantees
* non-reentrancy. See the comments above unplug_oldest_pwq().
*/
last_pool = get_work_pool(work);
if (last_pool && last_pool != pool && !(wq->flags & __WQ_ORDERED)) {
struct worker *worker;
raw_spin_lock(&last_pool->lock);
worker = find_worker_executing_work(last_pool, work);
if (worker && worker->current_pwq->wq == wq) {
pwq = worker->current_pwq;
pool = pwq->pool;
WARN_ON_ONCE(pool != last_pool);
} else {
/* meh... not running there, queue here */
raw_spin_unlock(&last_pool->lock);
raw_spin_lock(&pool->lock);
}
} else {
raw_spin_lock(&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 unbound pwqs never die without
* another pwq replacing it in cpu_pwq 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) {
raw_spin_unlock(&pool->lock);
cpu_relax();
goto retry;
}
/* oops */
WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt",
wq->name, cpu);
}
/* pwq determined, queue */
trace_workqueue_queue_work(req_cpu, pwq, work);
if (WARN_ON(!list_empty(&work->entry)))
goto out;
pwq->nr_in_flight[pwq->work_color]++;
work_flags = work_color_to_flags(pwq->work_color);
/*
* Limit the number of concurrently active work items to max_active.
* @work must also queue behind existing inactive work items to maintain
* ordering when max_active changes. See wq_adjust_max_active().
*/
if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) {
if (list_empty(&pool->worklist))
pool->watchdog_ts = jiffies;
trace_workqueue_activate_work(work);
insert_work(pwq, work, &pool->worklist, work_flags);
kick_pool(pool);
} else {
work_flags |= WORK_STRUCT_INACTIVE;
insert_work(pwq, work, &pwq->inactive_works, work_flags);
}
out:
raw_spin_unlock(&pool->lock);
rcu_read_unlock();
}
static bool clear_pending_if_disabled(struct work_struct *work)
{
unsigned long data = *work_data_bits(work);
struct work_offq_data offqd;
if (likely((data & WORK_STRUCT_PWQ) ||
!(data & WORK_OFFQ_DISABLE_MASK)))
return false;
work_offqd_unpack(&offqd, data);
set_work_pool_and_clear_pending(work, offqd.pool_id,
work_offqd_pack_flags(&offqd));
return true;
}
/**
* queue_work_on - queue work on specific cpu
* @cpu: CPU number to execute work on
* @wq: workqueue to use
* @work: work to queue
*
* We queue the work to a specific CPU, the caller must ensure it
* can't go away. Callers that fail to ensure that the specified
* CPU cannot go away will execute on a randomly chosen CPU.
* But note well that callers specifying a CPU that never has been
* online will get a splat.
*
* Return: %false if @work was already on a queue, %true otherwise.
*/
bool queue_work_on(int cpu, struct workqueue_struct *wq,
struct work_struct *work)
{
bool ret = false;
unsigned long irq_flags;
local_irq_save(irq_flags);
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) &&
!clear_pending_if_disabled(work)) {
__queue_work(cpu, wq, work);
ret = true;
}
local_irq_restore(irq_flags);
return ret;
}
EXPORT_SYMBOL(queue_work_on);
/**
* select_numa_node_cpu - Select a CPU based on NUMA node
* @node: NUMA node ID that we want to select a CPU from
*
* This function will attempt to find a "random" cpu available on a given
* node. If there are no CPUs available on the given node it will return
* WORK_CPU_UNBOUND indicating that we should just schedule to any
* available CPU if we need to schedule this work.
*/
static int select_numa_node_cpu(int node)
{
int cpu;
/* Delay binding to CPU if node is not valid or online */
if (node < 0 || node >= MAX_NUMNODES || !node_online(node))
return WORK_CPU_UNBOUND;
/* Use local node/cpu if we are already there */
cpu = raw_smp_processor_id();
if (node == cpu_to_node(cpu))
return cpu;
/* Use "random" otherwise know as "first" online CPU of node */
cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask);
/* If CPU is valid return that, otherwise just defer */
return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND;
}
/**
* queue_work_node - queue work on a "random" cpu for a given NUMA node
* @node: NUMA node that we are targeting the work for
* @wq: workqueue to use
* @work: work to queue
*
* We queue the work to a "random" CPU within a given NUMA node. The basic
* idea here is to provide a way to somehow associate work with a given
* NUMA node.
*
* This function will only make a best effort attempt at getting this onto
* the right NUMA node. If no node is requested or the requested node is
* offline then we just fall back to standard queue_work behavior.
*
* Currently the "random" CPU ends up being the first available CPU in the
* intersection of cpu_online_mask and the cpumask of the node, unless we
* are running on the node. In that case we just use the current CPU.
*
* Return: %false if @work was already on a queue, %true otherwise.
*/
bool queue_work_node(int node, struct workqueue_struct *wq,
struct work_struct *work)
{
unsigned long irq_flags;
bool ret = false;
/*
* This current implementation is specific to unbound workqueues.
* Specifically we only return the first available CPU for a given
* node instead of cycling through individual CPUs within the node.
*
* If this is used with a per-cpu workqueue then the logic in
* workqueue_select_cpu_near would need to be updated to allow for
* some round robin type logic.
*/
WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND));
local_irq_save(irq_flags);
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) &&
!clear_pending_if_disabled(work)) {
int cpu = select_numa_node_cpu(node);
__queue_work(cpu, wq, work);
ret = true;
}
local_irq_restore(irq_flags);
return ret;
}
EXPORT_SYMBOL_GPL(queue_work_node);
void delayed_work_timer_fn(struct timer_list *t)
{
struct delayed_work *dwork = from_timer(dwork, t, timer);
/* should have been called from irqsafe timer with irq already off */
__queue_work(dwork->cpu, dwork->wq, &dwork->work);
}
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;
WARN_ON_ONCE(!wq);
WARN_ON_ONCE(timer->function != delayed_work_timer_fn);
WARN_ON_ONCE(timer_pending(timer));
WARN_ON_ONCE(!list_empty(&work->entry));
/*
* If @delay is 0, queue @dwork->work immediately. This is for
* both optimization and correctness. The earliest @timer can
* expire is on the closest next tick and delayed_work users depend
* on that there's no such delay when @delay is 0.
*/
if (!delay) {
__queue_work(cpu, wq, &dwork->work);
return;
}
dwork->wq = wq;
dwork->cpu = cpu;
timer->expires = jiffies + delay;
if (housekeeping_enabled(HK_TYPE_TIMER)) {
/* If the current cpu is a housekeeping cpu, use it. */
cpu = smp_processor_id();
if (!housekeeping_test_cpu(cpu, HK_TYPE_TIMER))
cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
add_timer_on(timer, cpu);
} else {
if (likely(cpu == WORK_CPU_UNBOUND))
add_timer_global(timer);
else
add_timer_on(timer, cpu);
}
}
/**
* queue_delayed_work_on - queue work on specific CPU after delay
* @cpu: CPU number to execute work on
* @wq: workqueue to use
* @dwork: work to queue
* @delay: number of jiffies to wait before queueing
*
* Return: %false if @work was already on a queue, %true otherwise. If
* @delay is zero and @dwork is idle, it will be scheduled for immediate
* execution.
*/
bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *dwork, unsigned long delay)
{
struct work_struct *work = &dwork->work;
bool ret = false;
unsigned long irq_flags;
/* read the comment in __queue_work() */
local_irq_save(irq_flags);
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) &&
!clear_pending_if_disabled(work)) {
__queue_delayed_work(cpu, wq, dwork, delay);
ret = true;
}
local_irq_restore(irq_flags);
return ret;
}
EXPORT_SYMBOL(queue_delayed_work_on);
/**
* 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
* @dwork: work to queue
* @delay: number of jiffies to wait before queueing
*
* If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise,
* modify @dwork's timer so that it expires after @delay. If @delay is
* zero, @work is guaranteed to be scheduled immediately regardless of its
* current state.
*
* Return: %false if @dwork was idle and queued, %true if @dwork was
* pending and its timer was modified.
*
* This function is safe to call from any context including IRQ handler.
* See try_to_grab_pending() for details.
*/
bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *dwork, unsigned long delay)
{
unsigned long irq_flags;
bool ret;
ret = work_grab_pending(&dwork->work, WORK_CANCEL_DELAYED, &irq_flags);
if (!clear_pending_if_disabled(&dwork->work))
__queue_delayed_work(cpu, wq, dwork, delay);
local_irq_restore(irq_flags);
return ret;
}
EXPORT_SYMBOL_GPL(mod_delayed_work_on);
static void rcu_work_rcufn(struct rcu_head *rcu)
{
struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu);
/* read the comment in __queue_work() */
local_irq_disable();
__queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work);
local_irq_enable();
}
/**
* queue_rcu_work - queue work after a RCU grace period
* @wq: workqueue to use
* @rwork: work to queue
*
* Return: %false if @rwork was already pending, %true otherwise. Note
* that a full RCU grace period is guaranteed only after a %true return.
* While @rwork is guaranteed to be executed after a %false return, the
* execution may happen before a full RCU grace period has passed.
*/
bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork)
{
struct work_struct *work = &rwork->work;
/*
* rcu_work can't be canceled or disabled. Warn if the user reached
* inside @rwork and disabled the inner work.
*/
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) &&
!WARN_ON_ONCE(clear_pending_if_disabled(work))) {
rwork->wq = wq;
call_rcu_hurry(&rwork->rcu, rcu_work_rcufn);
return true;
}
return false;
}
EXPORT_SYMBOL(queue_rcu_work);
static struct worker *alloc_worker(int node)
{
struct worker *worker;
worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node);
if (worker) {
INIT_LIST_HEAD(&worker->entry);
INIT_LIST_HEAD(&worker->scheduled);
INIT_LIST_HEAD(&worker->node);
/* on creation a worker is in !idle && prep state */
worker->flags = WORKER_PREP;
}
return worker;
}
static cpumask_t *pool_allowed_cpus(struct worker_pool *pool)
{
if (pool->cpu < 0 && pool->attrs->affn_strict)
return pool->attrs->__pod_cpumask;
else
return pool->attrs->cpumask;
}
/**
* worker_attach_to_pool() - attach a worker to a pool
* @worker: worker to be attached
* @pool: the target pool
*
* Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and
* cpu-binding of @worker are kept coordinated with the pool across
* cpu-[un]hotplugs.
*/
static void worker_attach_to_pool(struct worker *worker,
struct worker_pool *pool)
{
mutex_lock(&wq_pool_attach_mutex);
/*
* The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains stable
* across this function. See the comments above the flag definition for
* details. BH workers are, while per-CPU, always DISASSOCIATED.
*/
if (pool->flags & POOL_DISASSOCIATED) {
worker->flags |= WORKER_UNBOUND;
} else {
WARN_ON_ONCE(pool->flags & POOL_BH);
kthread_set_per_cpu(worker->task, pool->cpu);
}
if (worker->rescue_wq)
set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool));
list_add_tail(&worker->node, &pool->workers);
worker->pool = pool;
mutex_unlock(&wq_pool_attach_mutex);
}
static void unbind_worker(struct worker *worker)
{
lockdep_assert_held(&wq_pool_attach_mutex);
kthread_set_per_cpu(worker->task, -1);
if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask))
WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0);
else
WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0);
}
static void detach_worker(struct worker *worker)
{
lockdep_assert_held(&wq_pool_attach_mutex);
unbind_worker(worker);
list_del(&worker->node);
worker->pool = NULL;
}
/**
* worker_detach_from_pool() - detach a worker from its pool
* @worker: worker which is attached to its pool
*
* Undo the attaching which had been done in worker_attach_to_pool(). The
* caller worker shouldn't access to the pool after detached except it has
* other reference to the pool.
*/
static void worker_detach_from_pool(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
/* there is one permanent BH worker per CPU which should never detach */
WARN_ON_ONCE(pool->flags & POOL_BH);
mutex_lock(&wq_pool_attach_mutex);
detach_worker(worker);
mutex_unlock(&wq_pool_attach_mutex);
/* clear leftover flags without pool->lock after it is detached */
worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND);
}
static int format_worker_id(char *buf, size_t size, struct worker *worker,
struct worker_pool *pool)
{
if (worker->rescue_wq)
return scnprintf(buf, size, "kworker/R-%s",
worker->rescue_wq->name);
if (pool) {
if (pool->cpu >= 0)
return scnprintf(buf, size, "kworker/%d:%d%s",
pool->cpu, worker->id,
pool->attrs->nice < 0 ? "H" : "");
else
return scnprintf(buf, size, "kworker/u%d:%d",
pool->id, worker->id);
} else {
return scnprintf(buf, size, "kworker/dying");
}
}
/**
* create_worker - create a new workqueue worker
* @pool: pool the new worker will belong to
*
* Create and start a new worker which is attached to @pool.
*
* CONTEXT:
* Might sleep. Does GFP_KERNEL allocations.
*
* Return:
* Pointer to the newly created worker.
*/
static struct worker *create_worker(struct worker_pool *pool)
{
struct worker *worker;
int id;
/* ID is needed to determine kthread name */
id = ida_alloc(&pool->worker_ida, GFP_KERNEL);
if (id < 0) {
pr_err_once("workqueue: Failed to allocate a worker ID: %pe\n",
ERR_PTR(id));
return NULL;
}
worker = alloc_worker(pool->node);
if (!worker) {
pr_err_once("workqueue: Failed to allocate a worker\n");
goto fail;
}
worker->id = id;
if (!(pool->flags & POOL_BH)) {
char id_buf[WORKER_ID_LEN];
format_worker_id(id_buf, sizeof(id_buf), worker, pool);
worker->task = kthread_create_on_node(worker_thread, worker,
pool->node, "%s", id_buf);
if (IS_ERR(worker->task)) {
if (PTR_ERR(worker->task) == -EINTR) {
pr_err("workqueue: Interrupted when creating a worker thread \"%s\"\n",
id_buf);
} else {
pr_err_once("workqueue: Failed to create a worker thread: %pe",
worker->task);
}
goto fail;
}
set_user_nice(worker->task, pool->attrs->nice);
kthread_bind_mask(worker->task, pool_allowed_cpus(pool));
}
/* successful, attach the worker to the pool */
worker_attach_to_pool(worker, pool);
/* start the newly created worker */
raw_spin_lock_irq(&pool->lock);
worker->pool->nr_workers++;
worker_enter_idle(worker);
/*
* @worker is waiting on a completion in kthread() and will trigger hung
* check if not woken up soon. As kick_pool() is noop if @pool is empty,
* wake it up explicitly.
*/
if (worker->task)
wake_up_process(worker->task);
raw_spin_unlock_irq(&pool->lock);
return worker;
fail:
ida_free(&pool->worker_ida, id);
kfree(worker);
return NULL;
}
static void detach_dying_workers(struct list_head *cull_list)
{
struct worker *worker;
list_for_each_entry(worker, cull_list, entry)
detach_worker(worker);
}
static void reap_dying_workers(struct list_head *cull_list)
{
struct worker *worker, *tmp;
list_for_each_entry_safe(worker, tmp, cull_list, entry) {
list_del_init(&worker->entry);
kthread_stop_put(worker->task);
kfree(worker);
}
}
/**
* set_worker_dying - Tag a worker for destruction
* @worker: worker to be destroyed
* @list: transfer worker away from its pool->idle_list and into list
*
* Tag @worker for destruction and adjust @pool stats accordingly. The worker
* should be idle.
*
* CONTEXT:
* raw_spin_lock_irq(pool->lock).
*/
static void set_worker_dying(struct worker *worker, struct list_head *list)
{
struct worker_pool *pool = worker->pool;
lockdep_assert_held(&pool->lock);
lockdep_assert_held(&wq_pool_attach_mutex);
/* sanity check frenzy */
if (WARN_ON(worker->current_work) ||
WARN_ON(!list_empty(&worker->scheduled)) ||
WARN_ON(!(worker->flags & WORKER_IDLE)))
return;
pool->nr_workers--;
pool->nr_idle--;
worker->flags |= WORKER_DIE;
list_move(&worker->entry, list);
/* get an extra task struct reference for later kthread_stop_put() */
get_task_struct(worker->task);
}
/**
* idle_worker_timeout - check if some idle workers can now be deleted.
* @t: The pool's idle_timer that just expired
*
* The timer is armed in worker_enter_idle(). Note that it isn't disarmed in
* worker_leave_idle(), as a worker flicking between idle and active while its
* pool is at the too_many_workers() tipping point would cause too much timer
* housekeeping overhead. Since IDLE_WORKER_TIMEOUT is long enough, we just let
* it expire and re-evaluate things from there.
*/
static void idle_worker_timeout(struct timer_list *t)
{
struct worker_pool *pool = from_timer(pool, t, idle_timer);
bool do_cull = false;
if (work_pending(&pool->idle_cull_work))
return;
raw_spin_lock_irq(&pool->lock);
if (too_many_workers(pool)) {
struct worker *worker;
unsigned long expires;
/* idle_list is kept in LIFO order, check the last one */
worker = list_last_entry(&pool->idle_list, struct worker, entry);
expires = worker->last_active + IDLE_WORKER_TIMEOUT;
do_cull = !time_before(jiffies, expires);
if (!do_cull)
mod_timer(&pool->idle_timer, expires);
}
raw_spin_unlock_irq(&pool->lock);
if (do_cull)
queue_work(system_unbound_wq, &pool->idle_cull_work);
}
/**
* idle_cull_fn - cull workers that have been idle for too long.
* @work: the pool's work for handling these idle workers
*
* This goes through a pool's idle workers and gets rid of those that have been
* idle for at least IDLE_WORKER_TIMEOUT seconds.
*
* We don't want to disturb isolated CPUs because of a pcpu kworker being
* culled, so this also resets worker affinity. This requires a sleepable
* context, hence the split between timer callback and work item.
*/
static void idle_cull_fn(struct work_struct *work)
{
struct worker_pool *pool = container_of(work, struct worker_pool, idle_cull_work);
LIST_HEAD(cull_list);
/*
* Grabbing wq_pool_attach_mutex here ensures an already-running worker
* cannot proceed beyong set_pf_worker() in its self-destruct path.
* This is required as a previously-preempted worker could run after
* set_worker_dying() has happened but before detach_dying_workers() did.
*/
mutex_lock(&wq_pool_attach_mutex);
raw_spin_lock_irq(&pool->lock);
while (too_many_workers(pool)) {
struct worker *worker;
unsigned long expires;
worker = list_last_entry(&pool->idle_list, struct worker, entry);
expires = worker->last_active + IDLE_WORKER_TIMEOUT;
if (time_before(jiffies, expires)) {
mod_timer(&pool->idle_timer, expires);
break;
}
set_worker_dying(worker, &cull_list);
}
raw_spin_unlock_irq(&pool->lock);
detach_dying_workers(&cull_list);
mutex_unlock(&wq_pool_attach_mutex);
reap_dying_workers(&cull_list);
}
static void send_mayday(struct work_struct *work)
{
struct pool_workqueue *pwq = get_work_pwq(work);
struct workqueue_struct *wq = pwq->wq;
lockdep_assert_held(&wq_mayday_lock);
if (!wq->rescuer)
return;
/* mayday mayday mayday */
if (list_empty(&pwq->mayday_node)) {
/*
* If @pwq is for an unbound wq, its base ref may be put at
* any time due to an attribute change. Pin @pwq until the
* rescuer is done with it.
*/
get_pwq(pwq);
list_add_tail(&pwq->mayday_node, &wq->maydays);
wake_up_process(wq->rescuer->task);
pwq->stats[PWQ_STAT_MAYDAY]++;
}
}
static void pool_mayday_timeout(struct timer_list *t)
{
struct worker_pool *pool = from_timer(pool, t, mayday_timer);
struct work_struct *work;
raw_spin_lock_irq(&pool->lock);
raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */
if (need_to_create_worker(pool)) {
/*
* We've been trying to create a new worker but
* haven't been successful. We might be hitting an
* allocation deadlock. Send distress signals to
* rescuers.
*/
list_for_each_entry(work, &pool->worklist, entry)
send_mayday(work);
}
raw_spin_unlock(&wq_mayday_lock);
raw_spin_unlock_irq(&pool->lock);
mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL);
}
/**
* maybe_create_worker - create a new worker if necessary
* @pool: pool to create a new worker for
*
* Create a new worker for @pool if necessary. @pool is guaranteed to
* have at least one idle worker on return from this function. If
* creating a new worker takes longer than MAYDAY_INTERVAL, mayday is
* sent to all rescuers with works scheduled on @pool to resolve
* possible allocation deadlock.
*
* On return, need_to_create_worker() is guaranteed to be %false and
* may_start_working() %true.
*
* LOCKING:
* raw_spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Does GFP_KERNEL allocations. Called only from
* manager.
*/
static void maybe_create_worker(struct worker_pool *pool)
__releases(&pool->lock)
__acquires(&pool->lock)
{
restart:
raw_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);
while (true) {
if (create_worker(pool) || !need_to_create_worker(pool))
break;
schedule_timeout_interruptible(CREATE_COOLDOWN);
if (!need_to_create_worker(pool))
break;
}
del_timer_sync(&pool->mayday_timer);
raw_spin_lock_irq(&pool->lock);
/*
* This is necessary even after a new worker was just successfully
* created as @pool->lock was dropped and the new worker might have
* already become busy.
*/
if (need_to_create_worker(pool))
goto restart;
}
/**
* manage_workers - manage worker pool
* @worker: self
*
* 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
* 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:
* raw_spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Does GFP_KERNEL allocations.
*
* Return:
* %false if the pool doesn't need management and the caller can safely
* start processing works, %true if management function was performed and
* the conditions that the caller verified before calling the function may
* no longer be true.
*/
static bool manage_workers(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
if (pool->flags & POOL_MANAGER_ACTIVE)
return false;
pool->flags |= POOL_MANAGER_ACTIVE;
pool->manager = worker;
maybe_create_worker(pool);
pool->manager = NULL;
pool->flags &= ~POOL_MANAGER_ACTIVE;
rcuwait_wake_up(&manager_wait);
return true;
}
/**
* process_one_work - process single work
* @worker: self
* @work: work to process
*
* Process @work. This function contains all the logics necessary to
* process a single work including synchronization against and
* interaction with other workers on the same cpu, queueing and
* flushing. As long as context requirement is met, any worker can
* call this function to process a work.
*
* CONTEXT:
* raw_spin_lock_irq(pool->lock) which is released and regrabbed.
*/
static void process_one_work(struct worker *worker, struct work_struct *work)
__releases(&pool->lock)
__acquires(&pool->lock)
{
struct pool_workqueue *pwq = get_work_pwq(work);
struct worker_pool *pool = worker->pool;
unsigned long work_data;
int lockdep_start_depth, rcu_start_depth;
bool bh_draining = pool->flags & POOL_BH_DRAINING;
#ifdef CONFIG_LOCKDEP
/*
* It is permissible to free the struct work_struct from
* inside the function that is called from it, this we need to
* take into account for lockdep too. To avoid bogus "held
* lock freed" warnings as well as problems when looking into
* work->lockdep_map, make a copy and use that here.
*/
struct lockdep_map lockdep_map;
lockdep_copy_map(&lockdep_map, &work->lockdep_map);
#endif
/* ensure we're on the correct CPU */
WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) &&
raw_smp_processor_id() != pool->cpu);
/* claim and dequeue */
debug_work_deactivate(work);
hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work);
worker->current_work = work;
worker->current_func = work->func;
worker->current_pwq = pwq;
if (worker->task)
worker->current_at = worker->task->se.sum_exec_runtime;
work_data = *work_data_bits(work);
worker->current_color = get_work_color(work_data);
/*
* Record wq name for cmdline and debug reporting, may get
* overridden through set_worker_desc().
*/
strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN);
list_del_init(&work->entry);
/*
* CPU intensive works don't participate in concurrency management.
* They're the scheduler's responsibility. This takes @worker out
* of concurrency management and the next code block will chain
* execution of the pending work items.
*/
if (unlikely(pwq->wq->flags & WQ_CPU_INTENSIVE))
worker_set_flags(worker, WORKER_CPU_INTENSIVE);
/*
* Kick @pool if necessary. It's always noop for per-cpu worker pools
* since nr_running would always be >= 1 at this point. This is used to
* chain execution of the pending work items for WORKER_NOT_RUNNING
* workers such as the UNBOUND and CPU_INTENSIVE ones.
*/
kick_pool(pool);
/*
* 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_pool_and_clear_pending(work, pool->id, pool_offq_flags(pool));
pwq->stats[PWQ_STAT_STARTED]++;
raw_spin_unlock_irq(&pool->lock);
rcu_start_depth = rcu_preempt_depth();
lockdep_start_depth = lockdep_depth(current);
/* see drain_dead_softirq_workfn() */
if (!bh_draining)
lock_map_acquire(&pwq->wq->lockdep_map);
lock_map_acquire(&lockdep_map);
/*
* Strictly speaking we should mark the invariant state without holding
* any locks, that is, before these two lock_map_acquire()'s.
*
* However, that would result in:
*
* A(W1)
* WFC(C)
* A(W1)
* C(C)
*
* Which would create W1->C->W1 dependencies, even though there is no
* actual deadlock possible. There are two solutions, using a
* read-recursive acquire on the work(queue) 'locks', but this will then
* hit the lockdep limitation on recursive locks, or simply discard
* these locks.
*
* AFAICT there is no possible deadlock scenario between the
* flush_work() and complete() primitives (except for single-threaded
* workqueues), so hiding them isn't a problem.
*/
lockdep_invariant_state(true);
trace_workqueue_execute_start(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, worker->current_func);
pwq->stats[PWQ_STAT_COMPLETED]++;
lock_map_release(&lockdep_map);
if (!bh_draining)
lock_map_release(&pwq->wq->lockdep_map);
if (unlikely((worker->task && in_atomic()) ||
lockdep_depth(current) != lockdep_start_depth ||
rcu_preempt_depth() != rcu_start_depth)) {
pr_err("BUG: workqueue leaked atomic, lock or RCU: %s[%d]\n"
" preempt=0x%08x lock=%d->%d RCU=%d->%d workfn=%ps\n",
current->comm, task_pid_nr(current), preempt_count(),
lockdep_start_depth, lockdep_depth(current),
rcu_start_depth, rcu_preempt_depth(),
worker->current_func);
debug_show_held_locks(current);
dump_stack();
}
/*
* The following prevents a kworker from hogging CPU on !PREEMPTION
* kernels, where a requeueing work item waiting for something to
* happen could deadlock with stop_machine as such work item could
* indefinitely requeue itself while all other CPUs are trapped in
* stop_machine. At the same time, report a quiescent RCU state so
* the same condition doesn't freeze RCU.
*/
if (worker->task)
cond_resched();
raw_spin_lock_irq(&pool->lock);
/*
* In addition to %WQ_CPU_INTENSIVE, @worker may also have been marked
* CPU intensive by wq_worker_tick() if @work hogged CPU longer than
* wq_cpu_intensive_thresh_us. Clear it.
*/
worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
/* tag the worker for identification in schedule() */
worker->last_func = worker->current_func;
/* we're done with it, release */
hash_del(&worker->hentry);
worker->current_work = NULL;
worker->current_func = NULL;
worker->current_pwq = NULL;
worker->current_color = INT_MAX;
/* must be the last step, see the function comment */
pwq_dec_nr_in_flight(pwq, work_data);
}
/**
* process_scheduled_works - process scheduled works
* @worker: self
*
* Process all scheduled works. Please note that the scheduled list
* may change while processing a work, so this function repeatedly
* fetches a work from the top and executes it.
*
* CONTEXT:
* raw_spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times.
*/
static void process_scheduled_works(struct worker *worker)
{
struct work_struct *work;
bool first = true;
while ((work = list_first_entry_or_null(&worker->scheduled,
struct work_struct, entry))) {
if (first) {
worker->pool->watchdog_ts = jiffies;
first = false;
}
process_one_work(worker, work);
}
}
static void set_pf_worker(bool val)
{
mutex_lock(&wq_pool_attach_mutex);
if (val)
current->flags |= PF_WQ_WORKER;
else
current->flags &= ~PF_WQ_WORKER;
mutex_unlock(&wq_pool_attach_mutex);
}
/**
* worker_thread - the worker thread function
* @__worker: self
*
* 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().
*
* Return: 0
*/
static int worker_thread(void *__worker)
{
struct worker *worker = __worker;
struct worker_pool *pool = worker->pool;
/* tell the scheduler that this is a workqueue worker */
set_pf_worker(true);
woke_up:
raw_spin_lock_irq(&pool->lock);
/* am I supposed to die? */
if (unlikely(worker->flags & WORKER_DIE)) {
raw_spin_unlock_irq(&pool->lock);
set_pf_worker(false);
ida_free(&pool->worker_ida, worker->id);
return 0;
}
worker_leave_idle(worker);
recheck:
/* no more worker necessary? */
if (!need_more_worker(pool))
goto sleep;
/* do we need to manage? */
if (unlikely(!may_start_working(pool)) && manage_workers(worker))
goto recheck;
/*
* ->scheduled list can only be filled while a worker is
* preparing to process a work or actually processing it.
* Make sure nobody diddled with it while I was sleeping.
*/
WARN_ON_ONCE(!list_empty(&worker->scheduled));
/*
* 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_REBOUND);
do {
struct work_struct *work =
list_first_entry(&pool->worklist,
struct work_struct, entry);
if (assign_work(work, worker, NULL))
process_scheduled_works(worker);
} while (keep_working(pool));
worker_set_flags(worker, WORKER_PREP);
sleep:
/*
* 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_IDLE);
raw_spin_unlock_irq(&pool->lock);
schedule();
goto woke_up;
}
/**
* rescuer_thread - the rescuer thread function
* @__rescuer: self
*
* Workqueue rescuer thread function. There's one rescuer for each
* workqueue which has WQ_MEM_RECLAIM set.
*
* Regular work processing on a pool may block trying to create a new
* worker which uses GFP_KERNEL allocation which has slight chance of
* 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 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.
*
* Return: 0
*/
static int rescuer_thread(void *