linux/kernel/workqueue.c

// 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 <[email protected]>
 *     Andrew Morton
 *     Kai Petzke <[email protected]>
 *     Theodore Ts'o <[email protected]>
 *
 * Made to use alloc_percpu by Christoph Lameter.
 *
 * Copyright (C) 2010		SUSE Linux Products GmbH
 * Copyright (C) 2010		Tejun Heo <[email protected]>
 *
 * 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 { … };

enum worker_flags { … };

enum work_cancel_flags { … };

enum wq_internal_consts { … };

/*
 * 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 …
#define BH_WORKER_RESTARTS …

/*
 * 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 { … };

/*
 * Per-pool_workqueue statistics. These can be monitored using
 * tools/workqueue/wq_monitor.py.
 */
enum pool_workqueue_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 { … } __aligned(…);

/*
 * Structure used to wait for workqueue flush.
 */
struct wq_flusher { … };

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 { … };

/*
 * The externally visible workqueue.  It relays the issued work items to
 * the appropriate worker_pool through its pool_workqueues.
 */
struct workqueue_struct { … };

/*
 * Each pod type describes how CPUs should be grouped for unbound workqueues.
 * See the comment above workqueue_attrs->affn_scope.
 */
struct wq_pod_type { … };

struct work_offq_data { … };

static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = …;

/*
 * 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 = …;
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 = …;
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(…);
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 = …;

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 = …;

/* 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 = …;

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 = …;
#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(…);
struct workqueue_struct *system_highpri_wq __ro_after_init;
EXPORT_SYMBOL_GPL(…);
struct workqueue_struct *system_long_wq __ro_after_init;
EXPORT_SYMBOL_GPL(…);
struct workqueue_struct *system_unbound_wq __ro_after_init;
EXPORT_SYMBOL_GPL(…);
struct workqueue_struct *system_freezable_wq __ro_after_init;
EXPORT_SYMBOL_GPL(…);
struct workqueue_struct *system_power_efficient_wq __ro_after_init;
EXPORT_SYMBOL_GPL(…);
struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init;
EXPORT_SYMBOL_GPL(…);
struct workqueue_struct *system_bh_wq;
EXPORT_SYMBOL_GPL(…);
struct workqueue_struct *system_bh_highpri_wq;
EXPORT_SYMBOL_GPL(…);

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() …

#define assert_rcu_or_wq_mutex_or_pool_mutex(wq) …

#define for_each_bh_worker_pool(pool, cpu) …

#define for_each_cpu_worker_pool(pool, cpu) …

/**
 * 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) …

/**
 * 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) …

/**
 * 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) …

#ifdef CONFIG_DEBUG_OBJECTS_WORK

static const struct debug_obj_descr work_debug_descr;

static void *work_debug_hint(void *addr)
{ … }

static bool work_is_static_object(void *addr)
{ … }

/*
 * fixup_init is called when:
 * - an active object is initialized
 */
static bool work_fixup_init(void *addr, enum debug_obj_state state)
{ … }

/*
 * fixup_free is called when:
 * - an active object is freed
 */
static bool work_fixup_free(void *addr, enum debug_obj_state state)
{ … }

static const struct debug_obj_descr work_debug_descr = …;

static inline void debug_work_activate(struct work_struct *work)
{ … }

static inline void debug_work_deactivate(struct work_struct *work)
{ … }

void __init_work(struct work_struct *work, int onstack)
{ … }
EXPORT_SYMBOL_GPL(…);

void destroy_work_on_stack(struct work_struct *work)
{ … }
EXPORT_SYMBOL_GPL(…);

void destroy_delayed_work_on_stack(struct delayed_work *work)
{ … }
EXPORT_SYMBOL_GPL(…);

#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)
{ … }

static struct pool_workqueue __rcu **
unbound_pwq_slot(struct workqueue_struct *wq, int cpu)
{ … }

/* @cpu < 0 for dfl_pwq */
static struct pool_workqueue *unbound_pwq(struct workqueue_struct *wq, int cpu)
{ … }

/**
 * 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)
{ … }

static unsigned int work_color_to_flags(int color)
{ … }

static int get_work_color(unsigned long work_data)
{ … }

static int work_next_color(int color)
{ … }

static unsigned long pool_offq_flags(struct worker_pool *pool)
{ … }

/*
 * 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)
{ … }

static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq,
			 unsigned long flags)
{ … }

static void set_work_pool_and_keep_pending(struct work_struct *work,
					   int pool_id, unsigned long flags)
{ … }

static void set_work_pool_and_clear_pending(struct work_struct *work,
					    int pool_id, unsigned long flags)
{ … }

static inline struct pool_workqueue *work_struct_pwq(unsigned long data)
{ … }

static struct pool_workqueue *get_work_pwq(struct work_struct *work)
{ … }

/**
 * 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)
{ … }

static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits)
{ … }

static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data)
{ … }

static unsigned long work_offqd_pack_flags(struct work_offq_data *offqd)
{ … }

/*
 * 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)
{ … }

/* Can I start working?  Called from busy but !running workers. */
static bool may_start_working(struct worker_pool *pool)
{ … }

/* Do I need to keep working?  Called from currently running workers. */
static bool keep_working(struct worker_pool *pool)
{ … }

/* Do we need a new worker?  Called from manager. */
static bool need_to_create_worker(struct worker_pool *pool)
{ … }

/* Do we have too many workers and should some go away? */
static bool too_many_workers(struct worker_pool *pool)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/* Return the first idle worker.  Called with pool->lock held. */
static struct worker *first_idle_worker(struct worker_pool *pool)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

static struct irq_work *bh_pool_irq_work(struct worker_pool *pool)
{ … }

static void kick_bh_pool(struct worker_pool *pool)
{ … }

/**
 * 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)
{ … }

#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 …

struct wci_ent { … };

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)
{ … }

static void wq_cpu_intensive_report(work_func_t func)
{ … }

#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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

static bool pwq_is_empty(struct pool_workqueue *pwq)
{ … }

static void __pwq_activate_work(struct pool_workqueue *pwq,
				struct work_struct *work)
{ … }

static bool tryinc_node_nr_active(struct wq_node_nr_active *nna)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/*
 * Test whether @work is being queued from another work executing on the
 * same workqueue.
 */
static bool is_chained_work(struct workqueue_struct *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)
{ … }

static void __queue_work(int cpu, struct workqueue_struct *wq,
			 struct work_struct *work)
{ … }

static bool clear_pending_if_disabled(struct work_struct *work)
{ … }

/**
 * 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)
{ … }
EXPORT_SYMBOL(…);

/**
 * 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)
{ … }

/**
 * 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)
{ … }
EXPORT_SYMBOL_GPL(…);

void delayed_work_timer_fn(struct timer_list *t)
{ … }
EXPORT_SYMBOL(…);

static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
				struct delayed_work *dwork, unsigned long delay)
{ … }

/**
 * 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)
{ … }
EXPORT_SYMBOL(…);

/**
 * 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)
{ … }
EXPORT_SYMBOL_GPL(…);

static void rcu_work_rcufn(struct rcu_head *rcu)
{ … }

/**
 * 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)
{ … }
EXPORT_SYMBOL(…);

static struct worker *alloc_worker(int node)
{ … }

static cpumask_t *pool_allowed_cpus(struct worker_pool *pool)
{ … }

/**
 * 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)
{ … }

static void unbind_worker(struct worker *worker)
{ … }


static void detach_worker(struct worker *worker)
{ … }

/**
 * 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)
{ … }

static int format_worker_id(char *buf, size_t size, struct worker *worker,
			    struct worker_pool *pool)
{ … }

/**
 * 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)
{ … }

static void detach_dying_workers(struct list_head *cull_list)
{ … }

static void reap_dying_workers(struct list_head *cull_list)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

static void send_mayday(struct work_struct *work)
{ … }

static void pool_mayday_timeout(struct timer_list *t)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

static void set_pf_worker(bool val)
{ … }

/**
 * 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)
{ … }

/**
 * 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 *__rescuer)
{ … }

static void bh_worker(struct worker *worker)
{ … }

/*
 * TODO: Convert all tasklet users to workqueue and use softirq directly.
 *
 * This is currently called from tasklet[_hi]action() and thus is also called
 * whenever there are tasklets to run. Let's do an early exit if there's nothing
 * queued. Once conversion from tasklet is complete, the need_more_worker() test
 * can be dropped.
 *
 * After full conversion, we'll add worker->softirq_action, directly use the
 * softirq action and obtain the worker pointer from the softirq_action pointer.
 */
void workqueue_softirq_action(bool highpri)
{ … }

struct wq_drain_dead_softirq_work { … };

static void drain_dead_softirq_workfn(struct work_struct *work)
{ … }

/*
 * @cpu is dead. Drain the remaining BH work items on the current CPU. It's
 * possible to allocate dead_work per CPU and avoid flushing. However, then we
 * have to worry about draining overlapping with CPU coming back online or
 * nesting (one CPU's dead_work queued on another CPU which is also dead and so
 * on). Let's keep it simple and drain them synchronously. These are BH work
 * items which shouldn't be requeued on the same pool. Shouldn't take long.
 */
void workqueue_softirq_dead(unsigned int cpu)
{ … }

/**
 * check_flush_dependency - check for flush dependency sanity
 * @target_wq: workqueue being flushed
 * @target_work: work item being flushed (NULL for workqueue flushes)
 *
 * %current is trying to flush the whole @target_wq or @target_work on it.
 * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not
 * reclaiming memory or running on a workqueue which doesn't have
 * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to
 * a deadlock.
 */
static void check_flush_dependency(struct workqueue_struct *target_wq,
				   struct work_struct *target_work)
{ … }

struct wq_barrier { … };

static void wq_barrier_func(struct work_struct *work)
{ … }

/**
 * insert_wq_barrier - insert a barrier work
 * @pwq: pwq to insert barrier into
 * @barr: wq_barrier to insert
 * @target: target work to attach @barr to
 * @worker: worker currently executing @target, NULL if @target is not executing
 *
 * @barr is linked to @target such that @barr is completed only after
 * @target finishes execution.  Please note that the ordering
 * guarantee is observed only with respect to @target and on the local
 * cpu.
 *
 * Currently, a queued barrier can't be canceled.  This is because
 * try_to_grab_pending() can't determine whether the work to be
 * grabbed is at the head of the queue and thus can't clear LINKED
 * flag of the previous work while there must be a valid next work
 * after a work with LINKED flag set.
 *
 * Note that when @worker is non-NULL, @target may be modified
 * underneath us, so we can't reliably determine pwq from @target.
 *
 * CONTEXT:
 * raw_spin_lock_irq(pool->lock).
 */
static void insert_wq_barrier(struct pool_workqueue *pwq,
			      struct wq_barrier *barr,
			      struct work_struct *target, struct worker *worker)
{ … }

/**
 * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing
 * @wq: workqueue being flushed
 * @flush_color: new flush color, < 0 for no-op
 * @work_color: new work color, < 0 for no-op
 *
 * Prepare pwqs for workqueue flushing.
 *
 * If @flush_color is non-negative, flush_color on all pwqs should be
 * -1.  If no pwq has in-flight commands at the specified color, all
 * pwq->flush_color's stay at -1 and %false is returned.  If any pwq
 * has in flight commands, its pwq->flush_color is set to
 * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq
 * wakeup logic is armed and %true is returned.
 *
 * The caller should have initialized @wq->first_flusher prior to
 * calling this function with non-negative @flush_color.  If
 * @flush_color is negative, no flush color update is done and %false
 * is returned.
 *
 * If @work_color is non-negative, all pwqs should have the same
 * work_color which is previous to @work_color and all will be
 * advanced to @work_color.
 *
 * CONTEXT:
 * mutex_lock(wq->mutex).
 *
 * Return:
 * %true if @flush_color >= 0 and there's something to flush.  %false
 * otherwise.
 */
static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
				      int flush_color, int work_color)
{ … }

static void touch_wq_lockdep_map(struct workqueue_struct *wq)
{ … }

static void touch_work_lockdep_map(struct work_struct *work,
				   struct workqueue_struct *wq)
{ … }

/**
 * __flush_workqueue - ensure that any scheduled work has run to completion.
 * @wq: workqueue to flush
 *
 * This function sleeps until all work items which were queued on entry
 * have finished execution, but it is not livelocked by new incoming ones.
 */
void __flush_workqueue(struct workqueue_struct *wq)
{ … }
EXPORT_SYMBOL(…);

/**
 * drain_workqueue - drain a workqueue
 * @wq: workqueue to drain
 *
 * Wait until the workqueue becomes empty.  While draining is in progress,
 * only chain queueing is allowed.  IOW, only currently pending or running
 * work items on @wq can queue further work items on it.  @wq is flushed
 * repeatedly until it becomes empty.  The number of flushing is determined
 * by the depth of chaining and should be relatively short.  Whine if it
 * takes too long.
 */
void drain_workqueue(struct workqueue_struct *wq)
{ … }
EXPORT_SYMBOL_GPL(…);

static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
			     bool from_cancel)
{ … }

static bool __flush_work(struct work_struct *work, bool from_cancel)
{ … }

/**
 * flush_work - wait for a work to finish executing the last queueing instance
 * @work: the work to flush
 *
 * Wait until @work has finished execution.  @work is guaranteed to be idle
 * on return if it hasn't been requeued since flush started.
 *
 * Return:
 * %true if flush_work() waited for the work to finish execution,
 * %false if it was already idle.
 */
bool flush_work(struct work_struct *work)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * flush_delayed_work - wait for a dwork to finish executing the last queueing
 * @dwork: the delayed work to flush
 *
 * Delayed timer is cancelled and the pending work is queued for
 * immediate execution.  Like flush_work(), this function only
 * considers the last queueing instance of @dwork.
 *
 * Return:
 * %true if flush_work() waited for the work to finish execution,
 * %false if it was already idle.
 */
bool flush_delayed_work(struct delayed_work *dwork)
{ … }
EXPORT_SYMBOL(…);

/**
 * flush_rcu_work - wait for a rwork to finish executing the last queueing
 * @rwork: the rcu work to flush
 *
 * Return:
 * %true if flush_rcu_work() waited for the work to finish execution,
 * %false if it was already idle.
 */
bool flush_rcu_work(struct rcu_work *rwork)
{ … }
EXPORT_SYMBOL(…);

static void work_offqd_disable(struct work_offq_data *offqd)
{ … }

static void work_offqd_enable(struct work_offq_data *offqd)
{ … }

static bool __cancel_work(struct work_struct *work, u32 cflags)
{ … }

static bool __cancel_work_sync(struct work_struct *work, u32 cflags)
{ … }

/*
 * See cancel_delayed_work()
 */
bool cancel_work(struct work_struct *work)
{ … }
EXPORT_SYMBOL(…);

/**
 * cancel_work_sync - cancel a work and wait for it to finish
 * @work: the work to cancel
 *
 * Cancel @work and wait for its execution to finish. This function can be used
 * even if the work re-queues itself or migrates to another workqueue. On return
 * from this function, @work is guaranteed to be not pending or executing on any
 * CPU as long as there aren't racing enqueues.
 *
 * cancel_work_sync(&delayed_work->work) must not be used for delayed_work's.
 * Use cancel_delayed_work_sync() instead.
 *
 * Must be called from a sleepable context if @work was last queued on a non-BH
 * workqueue. Can also be called from non-hardirq atomic contexts including BH
 * if @work was last queued on a BH workqueue.
 *
 * Returns %true if @work was pending, %false otherwise.
 */
bool cancel_work_sync(struct work_struct *work)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * cancel_delayed_work - cancel a delayed work
 * @dwork: delayed_work to cancel
 *
 * Kill off a pending delayed_work.
 *
 * Return: %true if @dwork was pending and canceled; %false if it wasn't
 * pending.
 *
 * Note:
 * The work callback function may still be running on return, unless
 * it returns %true and the work doesn't re-arm itself.  Explicitly flush or
 * use cancel_delayed_work_sync() to wait on it.
 *
 * This function is safe to call from any context including IRQ handler.
 */
bool cancel_delayed_work(struct delayed_work *dwork)
{ … }
EXPORT_SYMBOL(…);

/**
 * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish
 * @dwork: the delayed work cancel
 *
 * This is cancel_work_sync() for delayed works.
 *
 * Return:
 * %true if @dwork was pending, %false otherwise.
 */
bool cancel_delayed_work_sync(struct delayed_work *dwork)
{ … }
EXPORT_SYMBOL(…);

/**
 * disable_work - Disable and cancel a work item
 * @work: work item to disable
 *
 * Disable @work by incrementing its disable count and cancel it if currently
 * pending. As long as the disable count is non-zero, any attempt to queue @work
 * will fail and return %false. The maximum supported disable depth is 2 to the
 * power of %WORK_OFFQ_DISABLE_BITS, currently 65536.
 *
 * Can be called from any context. Returns %true if @work was pending, %false
 * otherwise.
 */
bool disable_work(struct work_struct *work)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * disable_work_sync - Disable, cancel and drain a work item
 * @work: work item to disable
 *
 * Similar to disable_work() but also wait for @work to finish if currently
 * executing.
 *
 * Must be called from a sleepable context if @work was last queued on a non-BH
 * workqueue. Can also be called from non-hardirq atomic contexts including BH
 * if @work was last queued on a BH workqueue.
 *
 * Returns %true if @work was pending, %false otherwise.
 */
bool disable_work_sync(struct work_struct *work)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * enable_work - Enable a work item
 * @work: work item to enable
 *
 * Undo disable_work[_sync]() by decrementing @work's disable count. @work can
 * only be queued if its disable count is 0.
 *
 * Can be called from any context. Returns %true if the disable count reached 0.
 * Otherwise, %false.
 */
bool enable_work(struct work_struct *work)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * disable_delayed_work - Disable and cancel a delayed work item
 * @dwork: delayed work item to disable
 *
 * disable_work() for delayed work items.
 */
bool disable_delayed_work(struct delayed_work *dwork)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * disable_delayed_work_sync - Disable, cancel and drain a delayed work item
 * @dwork: delayed work item to disable
 *
 * disable_work_sync() for delayed work items.
 */
bool disable_delayed_work_sync(struct delayed_work *dwork)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * enable_delayed_work - Enable a delayed work item
 * @dwork: delayed work item to enable
 *
 * enable_work() for delayed work items.
 */
bool enable_delayed_work(struct delayed_work *dwork)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * schedule_on_each_cpu - execute a function synchronously on each online CPU
 * @func: the function to call
 *
 * schedule_on_each_cpu() executes @func on each online CPU using the
 * system workqueue and blocks until all CPUs have completed.
 * schedule_on_each_cpu() is very slow.
 *
 * Return:
 * 0 on success, -errno on failure.
 */
int schedule_on_each_cpu(work_func_t func)
{ … }

/**
 * execute_in_process_context - reliably execute the routine with user context
 * @fn:		the function to execute
 * @ew:		guaranteed storage for the execute work structure (must
 *		be available when the work executes)
 *
 * Executes the function immediately if process context is available,
 * otherwise schedules the function for delayed execution.
 *
 * Return:	0 - function was executed
 *		1 - function was scheduled for execution
 */
int execute_in_process_context(work_func_t fn, struct execute_work *ew)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * free_workqueue_attrs - free a workqueue_attrs
 * @attrs: workqueue_attrs to free
 *
 * Undo alloc_workqueue_attrs().
 */
void free_workqueue_attrs(struct workqueue_attrs *attrs)
{ … }

/**
 * alloc_workqueue_attrs - allocate a workqueue_attrs
 *
 * Allocate a new workqueue_attrs, initialize with default settings and
 * return it.
 *
 * Return: The allocated new workqueue_attr on success. %NULL on failure.
 */
struct workqueue_attrs *alloc_workqueue_attrs(void)
{ … }

static void copy_workqueue_attrs(struct workqueue_attrs *to,
				 const struct workqueue_attrs *from)
{ … }

/*
 * Some attrs fields are workqueue-only. Clear them for worker_pool's. See the
 * comments in 'struct workqueue_attrs' definition.
 */
static void wqattrs_clear_for_pool(struct workqueue_attrs *attrs)
{ … }

/* hash value of the content of @attr */
static u32 wqattrs_hash(const struct workqueue_attrs *attrs)
{ … }

/* content equality test */
static bool wqattrs_equal(const struct workqueue_attrs *a,
			  const struct workqueue_attrs *b)
{ … }

/* Update @attrs with actually available CPUs */
static void wqattrs_actualize_cpumask(struct workqueue_attrs *attrs,
				      const cpumask_t *unbound_cpumask)
{ … }

/* find wq_pod_type to use for @attrs */
static const struct wq_pod_type *
wqattrs_pod_type(const struct workqueue_attrs *attrs)
{ … }

/**
 * init_worker_pool - initialize a newly zalloc'd worker_pool
 * @pool: worker_pool to initialize
 *
 * Initialize a newly zalloc'd @pool.  It also allocates @pool->attrs.
 *
 * Return: 0 on success, -errno on failure.  Even on failure, all fields
 * inside @pool proper are initialized and put_unbound_pool() can be called
 * on @pool safely to release it.
 */
static int init_worker_pool(struct worker_pool *pool)
{ … }

#ifdef CONFIG_LOCKDEP
static void wq_init_lockdep(struct workqueue_struct *wq)
{ … }

static void wq_unregister_lockdep(struct workqueue_struct *wq)
{ … }

static void wq_free_lockdep(struct workqueue_struct *wq)
{ … }
#else
static void wq_init_lockdep(struct workqueue_struct *wq)
{
}

static void wq_unregister_lockdep(struct workqueue_struct *wq)
{
}

static void wq_free_lockdep(struct workqueue_struct *wq)
{
}
#endif

static void free_node_nr_active(struct wq_node_nr_active **nna_ar)
{ … }

static void init_node_nr_active(struct wq_node_nr_active *nna)
{ … }

/*
 * Each node's nr_active counter will be accessed mostly from its own node and
 * should be allocated in the node.
 */
static int alloc_node_nr_active(struct wq_node_nr_active **nna_ar)
{ … }

static void rcu_free_wq(struct rcu_head *rcu)
{ … }

static void rcu_free_pool(struct rcu_head *rcu)
{ … }

/**
 * put_unbound_pool - put a worker_pool
 * @pool: worker_pool to put
 *
 * Put @pool.  If its refcnt reaches zero, it gets destroyed in RCU
 * safe manner.  get_unbound_pool() calls this function on its failure path
 * and this function should be able to release pools which went through,
 * successfully or not, init_worker_pool().
 *
 * Should be called with wq_pool_mutex held.
 */
static void put_unbound_pool(struct worker_pool *pool)
{ … }

/**
 * get_unbound_pool - get a worker_pool with the specified attributes
 * @attrs: the attributes of the worker_pool to get
 *
 * Obtain a worker_pool which has the same attributes as @attrs, bump the
 * reference count and return it.  If there already is a matching
 * worker_pool, it will be used; otherwise, this function attempts to
 * create a new one.
 *
 * Should be called with wq_pool_mutex held.
 *
 * Return: On success, a worker_pool with the same attributes as @attrs.
 * On failure, %NULL.
 */
static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
{ … }

/*
 * Scheduled on pwq_release_worker by put_pwq() when an unbound pwq hits zero
 * refcnt and needs to be destroyed.
 */
static void pwq_release_workfn(struct kthread_work *work)
{ … }

/* initialize newly allocated @pwq which is associated with @wq and @pool */
static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq,
		     struct worker_pool *pool)
{ … }

/* sync @pwq with the current state of its associated wq and link it */
static void link_pwq(struct pool_workqueue *pwq)
{ … }

/* obtain a pool matching @attr and create a pwq associating the pool and @wq */
static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq,
					const struct workqueue_attrs *attrs)
{ … }

static void apply_wqattrs_lock(void)
{ … }

static void apply_wqattrs_unlock(void)
{ … }

/**
 * wq_calc_pod_cpumask - calculate a wq_attrs' cpumask for a pod
 * @attrs: the wq_attrs of the default pwq of the target workqueue
 * @cpu: the target CPU
 *
 * Calculate the cpumask a workqueue with @attrs should use on @pod.
 * The result is stored in @attrs->__pod_cpumask.
 *
 * If pod affinity is not enabled, @attrs->cpumask is always used. If enabled
 * and @pod has online CPUs requested by @attrs, the returned cpumask is the
 * intersection of the possible CPUs of @pod and @attrs->cpumask.
 *
 * The caller is responsible for ensuring that the cpumask of @pod stays stable.
 */
static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu)
{ … }

/* install @pwq into @wq and return the old pwq, @cpu < 0 for dfl_pwq */
static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq,
					int cpu, struct pool_workqueue *pwq)
{ … }

/* context to store the prepared attrs & pwqs before applying */
struct apply_wqattrs_ctx { … };

/* free the resources after success or abort */
static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx)
{ … }

/* allocate the attrs and pwqs for later installation */
static struct apply_wqattrs_ctx *
apply_wqattrs_prepare(struct workqueue_struct *wq,
		      const struct workqueue_attrs *attrs,
		      const cpumask_var_t unbound_cpumask)
{ … }

/* set attrs and install prepared pwqs, @ctx points to old pwqs on return */
static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx)
{ … }

static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
					const struct workqueue_attrs *attrs)
{ … }

/**
 * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue
 * @wq: the target workqueue
 * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs()
 *
 * Apply @attrs to an unbound workqueue @wq. Unless disabled, this function maps
 * a separate pwq to each CPU pod with possibles CPUs in @attrs->cpumask so that
 * work items are affine to the pod it was issued on. Older pwqs are released as
 * in-flight work items finish. Note that a work item which repeatedly requeues
 * itself back-to-back will stay on its current pwq.
 *
 * Performs GFP_KERNEL allocations.
 *
 * Return: 0 on success and -errno on failure.
 */
int apply_workqueue_attrs(struct workqueue_struct *wq,
			  const struct workqueue_attrs *attrs)
{ … }

/**
 * unbound_wq_update_pwq - update a pwq slot for CPU hot[un]plug
 * @wq: the target workqueue
 * @cpu: the CPU to update the pwq slot for
 *
 * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and
 * %CPU_DOWN_FAILED.  @cpu is in the same pod of the CPU being hot[un]plugged.
 *
 *
 * If pod affinity can't be adjusted due to memory allocation failure, it falls
 * back to @wq->dfl_pwq which may not be optimal but is always correct.
 *
 * Note that when the last allowed CPU of a pod goes offline for a workqueue
 * with a cpumask spanning multiple pods, the workers which were already
 * executing the work items for the workqueue will lose their CPU affinity and
 * may execute on any CPU. This is similar to how per-cpu workqueues behave on
 * CPU_DOWN. If a workqueue user wants strict affinity, it's the user's
 * responsibility to flush the work item from CPU_DOWN_PREPARE.
 */
static void unbound_wq_update_pwq(struct workqueue_struct *wq, int cpu)
{ … }

static int alloc_and_link_pwqs(struct workqueue_struct *wq)
{ … }

static int wq_clamp_max_active(int max_active, unsigned int flags,
			       const char *name)
{ … }

/*
 * Workqueues which may be used during memory reclaim should have a rescuer
 * to guarantee forward progress.
 */
static int init_rescuer(struct workqueue_struct *wq)
{ … }

/**
 * wq_adjust_max_active - update a wq's max_active to the current setting
 * @wq: target workqueue
 *
 * If @wq isn't freezing, set @wq->max_active to the saved_max_active and
 * activate inactive work items accordingly. If @wq is freezing, clear
 * @wq->max_active to zero.
 */
static void wq_adjust_max_active(struct workqueue_struct *wq)
{ … }

__printf(1, 4)
struct workqueue_struct *alloc_workqueue(const char *fmt,
					 unsigned int flags,
					 int max_active, ...)
{ … }
EXPORT_SYMBOL_GPL(…);

static bool pwq_busy(struct pool_workqueue *pwq)
{ … }

/**
 * destroy_workqueue - safely terminate a workqueue
 * @wq: target workqueue
 *
 * Safely destroy a workqueue. All work currently pending will be done first.
 */
void destroy_workqueue(struct workqueue_struct *wq)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * workqueue_set_max_active - adjust max_active of a workqueue
 * @wq: target workqueue
 * @max_active: new max_active value.
 *
 * Set max_active of @wq to @max_active. See the alloc_workqueue() function
 * comment.
 *
 * CONTEXT:
 * Don't call from IRQ context.
 */
void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * workqueue_set_min_active - adjust min_active of an unbound workqueue
 * @wq: target unbound workqueue
 * @min_active: new min_active value
 *
 * Set min_active of an unbound workqueue. Unlike other types of workqueues, an
 * unbound workqueue is not guaranteed to be able to process max_active
 * interdependent work items. Instead, an unbound workqueue is guaranteed to be
 * able to process min_active number of interdependent work items which is
 * %WQ_DFL_MIN_ACTIVE by default.
 *
 * Use this function to adjust the min_active value between 0 and the current
 * max_active.
 */
void workqueue_set_min_active(struct workqueue_struct *wq, int min_active)
{ … }

/**
 * current_work - retrieve %current task's work struct
 *
 * Determine if %current task is a workqueue worker and what it's working on.
 * Useful to find out the context that the %current task is running in.
 *
 * Return: work struct if %current task is a workqueue worker, %NULL otherwise.
 */
struct work_struct *current_work(void)
{ … }
EXPORT_SYMBOL(…);

/**
 * current_is_workqueue_rescuer - is %current workqueue rescuer?
 *
 * Determine whether %current is a workqueue rescuer.  Can be used from
 * work functions to determine whether it's being run off the rescuer task.
 *
 * Return: %true if %current is a workqueue rescuer. %false otherwise.
 */
bool current_is_workqueue_rescuer(void)
{ … }

/**
 * workqueue_congested - test whether a workqueue is congested
 * @cpu: CPU in question
 * @wq: target workqueue
 *
 * Test whether @wq's cpu workqueue for @cpu is congested.  There is
 * no synchronization around this function and the test result is
 * unreliable and only useful as advisory hints or for debugging.
 *
 * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU.
 *
 * With the exception of ordered workqueues, all workqueues have per-cpu
 * pool_workqueues, each with its own congested state. A workqueue being
 * congested on one CPU doesn't mean that the workqueue is contested on any
 * other CPUs.
 *
 * Return:
 * %true if congested, %false otherwise.
 */
bool workqueue_congested(int cpu, struct workqueue_struct *wq)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * work_busy - test whether a work is currently pending or running
 * @work: the work to be tested
 *
 * Test whether @work is currently pending or running.  There is no
 * synchronization around this function and the test result is
 * unreliable and only useful as advisory hints or for debugging.
 *
 * Return:
 * OR'd bitmask of WORK_BUSY_* bits.
 */
unsigned int work_busy(struct work_struct *work)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * set_worker_desc - set description for the current work item
 * @fmt: printf-style format string
 * @...: arguments for the format string
 *
 * This function can be called by a running work function to describe what
 * the work item is about.  If the worker task gets dumped, this
 * information will be printed out together to help debugging.  The
 * description can be at most WORKER_DESC_LEN including the trailing '\0'.
 */
void set_worker_desc(const char *fmt, ...)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * print_worker_info - print out worker information and description
 * @log_lvl: the log level to use when printing
 * @task: target task
 *
 * If @task is a worker and currently executing a work item, print out the
 * name of the workqueue being serviced and worker description set with
 * set_worker_desc() by the currently executing work item.
 *
 * This function can be safely called on any task as long as the
 * task_struct itself is accessible.  While safe, this function isn't
 * synchronized and may print out mixups or garbages of limited length.
 */
void print_worker_info(const char *log_lvl, struct task_struct *task)
{ … }

static void pr_cont_pool_info(struct worker_pool *pool)
{ … }

static void pr_cont_worker_id(struct worker *worker)
{ … }

struct pr_cont_work_struct { … };

static void pr_cont_work_flush(bool comma, work_func_t func, struct pr_cont_work_struct *pcwsp)
{ … }

static void pr_cont_work(bool comma, struct work_struct *work, struct pr_cont_work_struct *pcwsp)
{ … }

static void show_pwq(struct pool_workqueue *pwq)
{ … }

/**
 * show_one_workqueue - dump state of specified workqueue
 * @wq: workqueue whose state will be printed
 */
void show_one_workqueue(struct workqueue_struct *wq)
{ … }

/**
 * show_one_worker_pool - dump state of specified worker pool
 * @pool: worker pool whose state will be printed
 */
static void show_one_worker_pool(struct worker_pool *pool)
{ … }

/**
 * show_all_workqueues - dump workqueue state
 *
 * Called from a sysrq handler and prints out all busy workqueues and pools.
 */
void show_all_workqueues(void)
{ … }

/**
 * show_freezable_workqueues - dump freezable workqueue state
 *
 * Called from try_to_freeze_tasks() and prints out all freezable workqueues
 * still busy.
 */
void show_freezable_workqueues(void)
{ … }

/* used to show worker information through /proc/PID/{comm,stat,status} */
void wq_worker_comm(char *buf, size_t size, struct task_struct *task)
{ … }

#ifdef CONFIG_SMP

/*
 * CPU hotplug.
 *
 * There are two challenges in supporting CPU hotplug.  Firstly, there
 * are a lot of assumptions on strong associations among work, pwq and
 * pool which make migrating pending and scheduled works very
 * difficult to implement without impacting hot paths.  Secondly,
 * worker pools serve mix of short, long and very long running works making
 * blocked draining impractical.
 *
 * This is solved by allowing the pools to be disassociated from the CPU
 * running as an unbound one and allowing it to be reattached later if the
 * cpu comes back online.
 */

static void unbind_workers(int cpu)
{ … }

/**
 * rebind_workers - rebind all workers of a pool to the associated CPU
 * @pool: pool of interest
 *
 * @pool->cpu is coming online.  Rebind all workers to the CPU.
 */
static void rebind_workers(struct worker_pool *pool)
{ … }

/**
 * restore_unbound_workers_cpumask - restore cpumask of unbound workers
 * @pool: unbound pool of interest
 * @cpu: the CPU which is coming up
 *
 * An unbound pool may end up with a cpumask which doesn't have any online
 * CPUs.  When a worker of such pool get scheduled, the scheduler resets
 * its cpus_allowed.  If @cpu is in @pool's cpumask which didn't have any
 * online CPU before, cpus_allowed of all its workers should be restored.
 */
static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
{ … }

int workqueue_prepare_cpu(unsigned int cpu)
{ … }

int workqueue_online_cpu(unsigned int cpu)
{ … }

int workqueue_offline_cpu(unsigned int cpu)
{ … }

struct work_for_cpu { … };

static void work_for_cpu_fn(struct work_struct *work)
{ … }

/**
 * work_on_cpu_key - run a function in thread context on a particular cpu
 * @cpu: the cpu to run on
 * @fn: the function to run
 * @arg: the function arg
 * @key: The lock class key for lock debugging purposes
 *
 * It is up to the caller to ensure that the cpu doesn't go offline.
 * The caller must not hold any locks which would prevent @fn from completing.
 *
 * Return: The value @fn returns.
 */
long work_on_cpu_key(int cpu, long (*fn)(void *),
		     void *arg, struct lock_class_key *key)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * work_on_cpu_safe_key - run a function in thread context on a particular cpu
 * @cpu: the cpu to run on
 * @fn:  the function to run
 * @arg: the function argument
 * @key: The lock class key for lock debugging purposes
 *
 * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold
 * any locks which would prevent @fn from completing.
 *
 * Return: The value @fn returns.
 */
long work_on_cpu_safe_key(int cpu, long (*fn)(void *),
			  void *arg, struct lock_class_key *key)
{ … }
EXPORT_SYMBOL_GPL(…);
#endif /* CONFIG_SMP */

#ifdef CONFIG_FREEZER

/**
 * freeze_workqueues_begin - begin freezing workqueues
 *
 * Start freezing workqueues.  After this function returns, all freezable
 * workqueues will queue new works to their inactive_works list instead of
 * pool->worklist.
 *
 * CONTEXT:
 * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's.
 */
void freeze_workqueues_begin(void)
{ … }

/**
 * freeze_workqueues_busy - are freezable workqueues still busy?
 *
 * Check whether freezing is complete.  This function must be called
 * between freeze_workqueues_begin() and thaw_workqueues().
 *
 * CONTEXT:
 * Grabs and releases wq_pool_mutex.
 *
 * Return:
 * %true if some freezable workqueues are still busy.  %false if freezing
 * is complete.
 */
bool freeze_workqueues_busy(void)
{ … }

/**
 * thaw_workqueues - thaw workqueues
 *
 * Thaw workqueues.  Normal queueing is restored and all collected
 * frozen works are transferred to their respective pool worklists.
 *
 * CONTEXT:
 * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's.
 */
void thaw_workqueues(void)
{ … }
#endif /* CONFIG_FREEZER */

static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
{ … }

/**
 * workqueue_unbound_exclude_cpumask - Exclude given CPUs from unbound cpumask
 * @exclude_cpumask: the cpumask to be excluded from wq_unbound_cpumask
 *
 * This function can be called from cpuset code to provide a set of isolated
 * CPUs that should be excluded from wq_unbound_cpumask.
 */
int workqueue_unbound_exclude_cpumask(cpumask_var_t exclude_cpumask)
{ … }

static int parse_affn_scope(const char *val)
{ … }

static int wq_affn_dfl_set(const char *val, const struct kernel_param *kp)
{ … }

static int wq_affn_dfl_get(char *buffer, const struct kernel_param *kp)
{ … }

static const struct kernel_param_ops wq_affn_dfl_ops = …;

module_param_cb(…);

#ifdef CONFIG_SYSFS
/*
 * Workqueues with WQ_SYSFS flag set is visible to userland via
 * /sys/bus/workqueue/devices/WQ_NAME.  All visible workqueues have the
 * following attributes.
 *
 *  per_cpu		RO bool	: whether the workqueue is per-cpu or unbound
 *  max_active		RW int	: maximum number of in-flight work items
 *
 * Unbound workqueues have the following extra attributes.
 *
 *  nice		RW int	: nice value of the workers
 *  cpumask		RW mask	: bitmask of allowed CPUs for the workers
 *  affinity_scope	RW str  : worker CPU affinity scope (cache, numa, none)
 *  affinity_strict	RW bool : worker CPU affinity is strict
 */
struct wq_device { … };

static struct workqueue_struct *dev_to_wq(struct device *dev)
{ … }

static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr,
			    char *buf)
{ … }
static DEVICE_ATTR_RO(per_cpu);

static ssize_t max_active_show(struct device *dev,
			       struct device_attribute *attr, char *buf)
{ … }

static ssize_t max_active_store(struct device *dev,
				struct device_attribute *attr, const char *buf,
				size_t count)
{ … }
static DEVICE_ATTR_RW(max_active);

static struct attribute *wq_sysfs_attrs[] = …;
ATTRIBUTE_GROUPS(…);

static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr,
			    char *buf)
{ … }

/* prepare workqueue_attrs for sysfs store operations */
static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq)
{ … }

static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr,
			     const char *buf, size_t count)
{ … }

static ssize_t wq_cpumask_show(struct device *dev,
			       struct device_attribute *attr, char *buf)
{ … }

static ssize_t wq_cpumask_store(struct device *dev,
				struct device_attribute *attr,
				const char *buf, size_t count)
{ … }

static ssize_t wq_affn_scope_show(struct device *dev,
				  struct device_attribute *attr, char *buf)
{ … }

static ssize_t wq_affn_scope_store(struct device *dev,
				   struct device_attribute *attr,
				   const char *buf, size_t count)
{ … }

static ssize_t wq_affinity_strict_show(struct device *dev,
				       struct device_attribute *attr, char *buf)
{ … }

static ssize_t wq_affinity_strict_store(struct device *dev,
					struct device_attribute *attr,
					const char *buf, size_t count)
{ … }

static struct device_attribute wq_sysfs_unbound_attrs[] = …;

static const struct bus_type wq_subsys = …;

/**
 *  workqueue_set_unbound_cpumask - Set the low-level unbound cpumask
 *  @cpumask: the cpumask to set
 *
 *  The low-level workqueues cpumask is a global cpumask that limits
 *  the affinity of all unbound workqueues.  This function check the @cpumask
 *  and apply it to all unbound workqueues and updates all pwqs of them.
 *
 *  Return:	0	- Success
 *		-EINVAL	- Invalid @cpumask
 *		-ENOMEM	- Failed to allocate memory for attrs or pwqs.
 */
static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
{ … }

static ssize_t __wq_cpumask_show(struct device *dev,
		struct device_attribute *attr, char *buf, cpumask_var_t mask)
{ … }

static ssize_t cpumask_requested_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{ … }
static DEVICE_ATTR_RO(cpumask_requested);

static ssize_t cpumask_isolated_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{ … }
static DEVICE_ATTR_RO(cpumask_isolated);

static ssize_t cpumask_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{ … }

static ssize_t cpumask_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t count)
{ … }
static DEVICE_ATTR_RW(cpumask);

static struct attribute *wq_sysfs_cpumask_attrs[] = …;
ATTRIBUTE_GROUPS(…);

static int __init wq_sysfs_init(void)
{ … }
core_initcall(wq_sysfs_init);

static void wq_device_release(struct device *dev)
{ … }

/**
 * workqueue_sysfs_register - make a workqueue visible in sysfs
 * @wq: the workqueue to register
 *
 * Expose @wq in sysfs under /sys/bus/workqueue/devices.
 * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set
 * which is the preferred method.
 *
 * Workqueue user should use this function directly iff it wants to apply
 * workqueue_attrs before making the workqueue visible in sysfs; otherwise,
 * apply_workqueue_attrs() may race against userland updating the
 * attributes.
 *
 * Return: 0 on success, -errno on failure.
 */
int workqueue_sysfs_register(struct workqueue_struct *wq)
{ … }

/**
 * workqueue_sysfs_unregister - undo workqueue_sysfs_register()
 * @wq: the workqueue to unregister
 *
 * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister.
 */
static void workqueue_sysfs_unregister(struct workqueue_struct *wq)
{ … }
#else	/* CONFIG_SYSFS */
static void workqueue_sysfs_unregister(struct workqueue_struct *wq)	{ }
#endif	/* CONFIG_SYSFS */

/*
 * Workqueue watchdog.
 *
 * Stall may be caused by various bugs - missing WQ_MEM_RECLAIM, illegal
 * flush dependency, a concurrency managed work item which stays RUNNING
 * indefinitely.  Workqueue stalls can be very difficult to debug as the
 * usual warning mechanisms don't trigger and internal workqueue state is
 * largely opaque.
 *
 * Workqueue watchdog monitors all worker pools periodically and dumps
 * state if some pools failed to make forward progress for a while where
 * forward progress is defined as the first item on ->worklist changing.
 *
 * This mechanism is controlled through the kernel parameter
 * "workqueue.watchdog_thresh" which can be updated at runtime through the
 * corresponding sysfs parameter file.
 */
#ifdef CONFIG_WQ_WATCHDOG

static unsigned long wq_watchdog_thresh = …;
static struct timer_list wq_watchdog_timer;

static unsigned long wq_watchdog_touched = …;
static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = …;

/*
 * Show workers that might prevent the processing of pending work items.
 * The only candidates are CPU-bound workers in the running state.
 * Pending work items should be handled by another idle worker
 * in all other situations.
 */
static void show_cpu_pool_hog(struct worker_pool *pool)
{ … }

static void show_cpu_pools_hogs(void)
{ … }

static void wq_watchdog_reset_touched(void)
{ … }

static void wq_watchdog_timer_fn(struct timer_list *unused)
{ … }

notrace void wq_watchdog_touch(int cpu)
{ … }

static void wq_watchdog_set_thresh(unsigned long thresh)
{ … }

static int wq_watchdog_param_set_thresh(const char *val,
					const struct kernel_param *kp)
{ … }

static const struct kernel_param_ops wq_watchdog_thresh_ops = …;

module_param_cb(…);

static void wq_watchdog_init(void)
{ … }

#else	/* CONFIG_WQ_WATCHDOG */

static inline void wq_watchdog_init(void) { }

#endif	/* CONFIG_WQ_WATCHDOG */

static void bh_pool_kick_normal(struct irq_work *irq_work)
{ … }

static void bh_pool_kick_highpri(struct irq_work *irq_work)
{ … }

static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask)
{ … }

static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, int nice)
{ … }

/**
 * workqueue_init_early - early init for workqueue subsystem
 *
 * This is the first step of three-staged workqueue subsystem initialization and
 * invoked as soon as the bare basics - memory allocation, cpumasks and idr are
 * up. It sets up all the data structures and system workqueues and allows early
 * boot code to create workqueues and queue/cancel work items. Actual work item
 * execution starts only after kthreads can be created and scheduled right
 * before early initcalls.
 */
void __init workqueue_init_early(void)
{ … }

static void __init wq_cpu_intensive_thresh_init(void)
{ … }

/**
 * workqueue_init - bring workqueue subsystem fully online
 *
 * This is the second step of three-staged workqueue subsystem initialization
 * and invoked as soon as kthreads can be created and scheduled. Workqueues have
 * been created and work items queued on them, but there are no kworkers
 * executing the work items yet. Populate the worker pools with the initial
 * workers and enable future kworker creations.
 */
void __init workqueue_init(void)
{ … }

/*
 * Initialize @pt by first initializing @pt->cpu_pod[] with pod IDs according to
 * @cpu_shares_pod(). Each subset of CPUs that share a pod is assigned a unique
 * and consecutive pod ID. The rest of @pt is initialized accordingly.
 */
static void __init init_pod_type(struct wq_pod_type *pt,
				 bool (*cpus_share_pod)(int, int))
{ … }

static bool __init cpus_dont_share(int cpu0, int cpu1)
{ … }

static bool __init cpus_share_smt(int cpu0, int cpu1)
{ … }

static bool __init cpus_share_numa(int cpu0, int cpu1)
{ … }

/**
 * workqueue_init_topology - initialize CPU pods for unbound workqueues
 *
 * This is the third step of three-staged workqueue subsystem initialization and
 * invoked after SMP and topology information are fully initialized. It
 * initializes the unbound CPU pods accordingly.
 */
void __init workqueue_init_topology(void)
{ … }

void __warn_flushing_systemwide_wq(void)
{ … }
EXPORT_SYMBOL(…);

static int __init workqueue_unbound_cpus_setup(char *str)
{ … }
__setup(…);