UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/kernel/workqueue.c

6029 lines
165 KiB
C
Raw Blame History

// 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/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/nmi.h>
#include "workqueue_internal.h"
enum {
/*
* 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.
*/
POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */
POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */
/* 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,
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 = 24,
};
/*
* 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.
*
* X: During normal operation, modification requires pool->lock and should
* be done only from local cpu. Either disabling preemption on local
* cpu or grabbing pool->lock is enough for read access. If
* POOL_DISASSOCIATED is set, it's identical to L.
*
* 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.
*
* MD: wq_mayday_lock protected.
*/
/* struct worker is defined in workqueue_internal.h */
struct worker_pool {
spinlock_t lock; /* the pool lock */
int cpu; /* I: the associated cpu */
int node; /* I: the associated node ID */
int id; /* I: pool ID */
unsigned int flags; /* X: flags */
unsigned long watchdog_ts; /* L: watchdog timestamp */
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; /* X: list of idle workers */
struct timer_list idle_timer; /* L: worker idle timeout */
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 completion *detach_completion; /* all workers detached */
struct ida worker_ida; /* worker IDs for task name */
struct workqueue_attrs *attrs; /* I: worker attributes */
struct hlist_node hash_node; /* PL: unbound_pool_hash node */
int refcnt; /* PL: refcnt for unbound pools */
/*
* The current concurrency level. As it's likely to be accessed
* from other CPUs during try_to_wake_up(), put it in a separate
* cacheline.
*/
atomic_t nr_running ____cacheline_aligned_in_smp;
/*
* Destruction of pool is RCU protected to allow dereferences
* from get_work_pool().
*/
struct rcu_head rcu;
} ____cacheline_aligned_in_smp;
/*
* The per-pool workqueue. While queued, the lower WORK_STRUCT_FLAG_BITS
* of work_struct->data are used for flags and the remaining high bits
* point to the pwq; thus, pwqs need to be aligned at two's power of the
* number of flag bits.
*/
struct pool_workqueue {
struct worker_pool *pool; /* I: the associated pool */
struct workqueue_struct *wq; /* I: the owning workqueue */
int work_color; /* L: current color */
int flush_color; /* L: flushing color */
int refcnt; /* L: reference count */
int nr_in_flight[WORK_NR_COLORS];
/* L: nr of in_flight works */
int nr_active; /* L: nr of active works */
int max_active; /* L: max active works */
struct list_head delayed_works; /* L: delayed works */
struct list_head pwqs_node; /* WR: node on wq->pwqs */
struct list_head mayday_node; /* MD: node on wq->maydays */
/*
* Release of unbound pwq is punted to system_wq. See put_pwq()
* and pwq_unbound_release_workfn() for details. pool_workqueue
* itself is also RCU protected so that the first pwq can be
* determined without grabbing wq->mutex.
*/
struct work_struct unbound_release_work;
struct rcu_head rcu;
} __aligned(1 << WORK_STRUCT_FLAG_BITS);
/*
* Structure used to wait for workqueue flush.
*/
struct wq_flusher {
struct list_head list; /* WQ: list of flushers */
int flush_color; /* WQ: flush color waiting for */
struct completion done; /* flush completion */
};
struct wq_device;
/*
* 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 */
int saved_max_active; /* WQ: saved pwq max_active */
struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */
struct pool_workqueue *dfl_pwq; /* PW: only for unbound wqs */
#ifdef CONFIG_SYSFS
struct wq_device *wq_dev; /* I: for sysfs interface */
#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 __percpu *cpu_pwqs; /* I: per-cpu pwqs */
struct pool_workqueue __rcu *numa_pwq_tbl[]; /* PWR: unbound pwqs indexed by node */
};
static struct kmem_cache *pwq_cache;
static cpumask_var_t *wq_numa_possible_cpumask;
/* possible CPUs of each node */
static bool wq_disable_numa;
module_param_named(disable_numa, wq_disable_numa, bool, 0444);
/* see the comment above the definition of WQ_POWER_EFFICIENT */
static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT);
module_param_named(power_efficient, wq_power_efficient, bool, 0444);
static bool wq_online; /* can kworkers be created yet? */
static bool wq_numa_enabled; /* unbound NUMA affinity enabled */
/* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */
static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf;
static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */
static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */
static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */
static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */
static LIST_HEAD(workqueues); /* PR: list of all workqueues */
static bool workqueue_freezing; /* PL: have wqs started freezing? */
/* PL: allowable cpus for unbound wqs and work items */
static cpumask_var_t wq_unbound_cpumask;
/* 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);
/* 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];
struct workqueue_struct *system_wq __read_mostly;
EXPORT_SYMBOL(system_wq);
struct workqueue_struct *system_highpri_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_highpri_wq);
struct workqueue_struct *system_long_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_long_wq);
struct workqueue_struct *system_unbound_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_unbound_wq);
struct workqueue_struct *system_freezable_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_freezable_wq);
struct workqueue_struct *system_power_efficient_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_power_efficient_wq);
struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq);
static int worker_thread(void *__worker);
static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
static void show_pwq(struct pool_workqueue *pwq);
#define CREATE_TRACE_POINTS
#include <trace/events/workqueue.h>
#define assert_rcu_or_pool_mutex() \
RCU_LOCKDEP_WARN(!rcu_read_lock_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_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_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 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 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 assing it to @pool
* @pool: the pool pointer of interest
*
* Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned
* successfully, -errno on failure.
*/
static int worker_pool_assign_id(struct worker_pool *pool)
{
int ret;
lockdep_assert_held(&wq_pool_mutex);
ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE,
GFP_KERNEL);
if (ret >= 0) {
pool->id = ret;
return 0;
}
return ret;
}
/**
* unbound_pwq_by_node - return the unbound pool_workqueue for the given node
* @wq: the target workqueue
* @node: the node ID
*
* This must be called with any of wq_pool_mutex, wq->mutex 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.
*
* Return: The unbound pool_workqueue for @node.
*/
static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq,
int node)
{
assert_rcu_or_wq_mutex_or_pool_mutex(wq);
/*
* XXX: @node can be NUMA_NO_NODE if CPU goes offline while a
* delayed item is pending. The plan is to keep CPU -> NODE
* mapping valid and stable across CPU on/offlines. Once that
* happens, this workaround can be removed.
*/
if (unlikely(node == NUMA_NO_NODE))
return wq->dfl_pwq;
return rcu_dereference_raw(wq->numa_pwq_tbl[node]);
}
static unsigned int work_color_to_flags(int color)
{
return color << WORK_STRUCT_COLOR_SHIFT;
}
static int get_work_color(struct work_struct *work)
{
return (*work_data_bits(work) >> WORK_STRUCT_COLOR_SHIFT) &
((1 << WORK_STRUCT_COLOR_BITS) - 1);
}
static int work_next_color(int color)
{
return (color + 1) % WORK_NR_COLORS;
}
/*
* 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(), mark_work_canceling()
* and clear_work_data() can be used to set the pwq, pool or clear
* work->data. These functions should only be called while the work is
* owned - ie. while the PENDING bit is set.
*
* get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq
* corresponding to a work. Pool is available once the work has been
* queued anywhere after initialization until it is sync canceled. pwq is
* available only while the work item is queued.
*
* %WORK_OFFQ_CANCELING is used to mark a work item which is being
* canceled. While being canceled, a work item may have its PENDING set
* but stay off timer and worklist for arbitrarily long and nobody should
* try to steal the PENDING bit.
*/
static inline void set_work_data(struct work_struct *work, unsigned long data,
unsigned long flags)
{
WARN_ON_ONCE(!work_pending(work));
atomic_long_set(&work->data, data | flags | work_static(work));
}
static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq,
unsigned long extra_flags)
{
set_work_data(work, (unsigned long)pwq,
WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags);
}
static void set_work_pool_and_keep_pending(struct work_struct *work,
int pool_id)
{
set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT,
WORK_STRUCT_PENDING);
}
static void set_work_pool_and_clear_pending(struct work_struct *work,
int pool_id)
{
/*
* 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, 0);
/*
* 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 void clear_work_data(struct work_struct *work)
{
smp_wmb(); /* see set_work_pool_and_clear_pending() */
set_work_data(work, WORK_STRUCT_NO_POOL, 0);
}
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 (void *)(data & WORK_STRUCT_WQ_DATA_MASK);
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 ((struct pool_workqueue *)
(data & WORK_STRUCT_WQ_DATA_MASK))->pool;
pool_id = data >> WORK_OFFQ_POOL_SHIFT;
if (pool_id == WORK_OFFQ_POOL_NONE)
return NULL;
return idr_find(&worker_pool_idr, pool_id);
}
/**
* get_work_pool_id - return the worker pool ID a given work is associated with
* @work: the work item of interest
*
* Return: The worker_pool ID @work was last associated with.
* %WORK_OFFQ_POOL_NONE if none.
*/
static int get_work_pool_id(struct work_struct *work)
{
unsigned long data = atomic_long_read(&work->data);
if (data & WORK_STRUCT_PWQ)
return ((struct pool_workqueue *)
(data & WORK_STRUCT_WQ_DATA_MASK))->pool->id;
return data >> WORK_OFFQ_POOL_SHIFT;
}
static void mark_work_canceling(struct work_struct *work)
{
unsigned long pool_id = get_work_pool_id(work);
pool_id <<= WORK_OFFQ_POOL_SHIFT;
set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING);
}
static bool work_is_canceling(struct work_struct *work)
{
unsigned long data = atomic_long_read(&work->data);
return !(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_CANCELING);
}
/*
* Policy functions. These define the policies on how the global worker
* pools are managed. Unless noted otherwise, these functions assume that
* they're being called with pool->lock held.
*/
static bool __need_more_worker(struct worker_pool *pool)
{
return !atomic_read(&pool->nr_running);
}
/*
* 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) && __need_more_worker(pool);
}
/* 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) &&
atomic_read(&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;
}
/*
* Wake up functions.
*/
/* Return the first idle worker. Safe with preemption disabled */
static struct worker *first_idle_worker(struct worker_pool *pool)
{
if (unlikely(list_empty(&pool->idle_list)))
return NULL;
return list_first_entry(&pool->idle_list, struct worker, entry);
}
/**
* wake_up_worker - wake up an idle worker
* @pool: worker pool to wake worker from
*
* Wake up the first idle worker of @pool.
*
* CONTEXT:
* spin_lock_irq(pool->lock).
*/
static void wake_up_worker(struct worker_pool *pool)
{
struct worker *worker = first_idle_worker(pool);
if (likely(worker))
wake_up_process(worker->task);
}
/**
* 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 (!worker->sleeping)
return;
if (!(worker->flags & WORKER_NOT_RUNNING))
atomic_inc(&worker->pool->nr_running);
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 *next, *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;
if (WARN_ON_ONCE(worker->sleeping))
return;
worker->sleeping = 1;
spin_lock_irq(&pool->lock);
/*
* The counterpart of the following dec_and_test, implied mb,
* worklist not empty test sequence is in insert_work().
* Please read comment there.
*
* NOT_RUNNING is clear. This means that we're bound to and
* running on the local cpu w/ rq lock held and preemption
* disabled, which in turn means that none else could be
* manipulating idle_list, so dereferencing idle_list without pool
* lock is safe.
*/
if (atomic_dec_and_test(&pool->nr_running) &&
!list_empty(&pool->worklist)) {
next = first_idle_worker(pool);
if (next)
wake_up_process(next->task);
}
spin_unlock_irq(&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:
* 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;
}
/**
* 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.
*
* CONTEXT:
* spin_lock_irq(pool->lock)
*/
static inline void worker_set_flags(struct worker *worker, unsigned int flags)
{
struct worker_pool *pool = worker->pool;
WARN_ON_ONCE(worker->task != current);
/* If transitioning into NOT_RUNNING, adjust nr_running. */
if ((flags & WORKER_NOT_RUNNING) &&
!(worker->flags & WORKER_NOT_RUNNING)) {
atomic_dec(&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.
*
* CONTEXT:
* spin_lock_irq(pool->lock)
*/
static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
{
struct worker_pool *pool = worker->pool;
unsigned int oflags = worker->flags;
WARN_ON_ONCE(worker->task != current);
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))
atomic_inc(&pool->nr_running);
}
/**
* 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:
* 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.
*
* If @nextp is not NULL, it's updated to point to the next work of
* the last scheduled work. This allows move_linked_works() to be
* nested inside outer list_for_each_entry_safe().
*
* CONTEXT:
* 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;
}
/**
* 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;
if (WARN_ON_ONCE(!(pwq->wq->flags & WQ_UNBOUND)))
return;
/*
* @pwq can't be released under pool->lock, bounce to
* pwq_unbound_release_workfn(). This never recurses on the same
* pool->lock as this path is taken only for unbound workqueues and
* the release work item is scheduled on a per-cpu workqueue. To
* avoid lockdep warning, unbound pool->locks are given lockdep
* subclass of 1 in get_unbound_pool().
*/
schedule_work(&pwq->unbound_release_work);
}
/**
* put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock
* @pwq: pool_workqueue to put (can be %NULL)
*
* put_pwq() with locking. This function also allows %NULL @pwq.
*/
static void put_pwq_unlocked(struct pool_workqueue *pwq)
{
if (pwq) {
/*
* As both pwqs and pools are RCU protected, the
* following lock operations are safe.
*/
spin_lock_irq(&pwq->pool->lock);
put_pwq(pwq);
spin_unlock_irq(&pwq->pool->lock);
}
}
static void pwq_activate_delayed_work(struct work_struct *work)
{
struct pool_workqueue *pwq = get_work_pwq(work);
trace_workqueue_activate_work(work);
if (list_empty(&pwq->pool->worklist))
pwq->pool->watchdog_ts = jiffies;
move_linked_works(work, &pwq->pool->worklist, NULL);
__clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work));
pwq->nr_active++;
}
static void pwq_activate_first_delayed(struct pool_workqueue *pwq)
{
struct work_struct *work = list_first_entry(&pwq->delayed_works,
struct work_struct, entry);
pwq_activate_delayed_work(work);
}
/**
* pwq_dec_nr_in_flight - decrement pwq's nr_in_flight
* @pwq: pwq of interest
* @color: color of work which left the queue
*
* A work either has completed or is removed from pending queue,
* decrement nr_in_flight of its pwq and handle workqueue flushing.
*
* CONTEXT:
* spin_lock_irq(pool->lock).
*/
static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color)
{
/* uncolored work items don't participate in flushing or nr_active */
if (color == WORK_NO_COLOR)
goto out_put;
pwq->nr_in_flight[color]--;
pwq->nr_active--;
if (!list_empty(&pwq->delayed_works)) {
/* one down, submit a delayed one */
if (pwq->nr_active < pwq->max_active)
pwq_activate_first_delayed(pwq);
}
/* is flush in progress and are we at the flushing tip? */
if (likely(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
* @is_dwork: @work is a delayed_work
* @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
* -ENOENT if someone else is canceling @work, this state may persist
* for arbitrarily long
*
* Note:
* On >= 0 return, the caller owns @work's PENDING bit. To avoid getting
* interrupted while holding PENDING and @work off queue, irq must be
* disabled on entry. This, combined with delayed_work->timer being
* 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(*@flags).
*
* This function is safe to call from any context including IRQ handler.
*/
static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
unsigned long *flags)
{
struct worker_pool *pool;
struct pool_workqueue *pwq;
local_irq_save(*flags);
/* try to steal the timer if it exists */
if (is_dwork) {
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;
spin_lock(&pool->lock);
/*
* work->data is guaranteed to point to pwq only while the work
* item is queued on pwq->wq, and both updating work->data to point
* to pwq on queueing and to pool on dequeueing are done under
* pwq->pool->lock. This in turn guarantees that, if work->data
* points to pwq which is associated with a locked pool, the work
* item is currently queued on that pool.
*/
pwq = get_work_pwq(work);
if (pwq && pwq->pool == pool) {
debug_work_deactivate(work);
/*
* A delayed work item cannot be grabbed directly because
* it might have linked NO_COLOR work items which, if left
* on the delayed_list, will confuse pwq->nr_active
* management later on and cause stall. Make sure the work
* item is activated before grabbing.
*/
if (*work_data_bits(work) & WORK_STRUCT_DELAYED)
pwq_activate_delayed_work(work);
list_del_init(&work->entry);
pwq_dec_nr_in_flight(pwq, get_work_color(work));
/* work->data points to pwq iff queued, point to pool */
set_work_pool_and_keep_pending(work, pool->id);
spin_unlock(&pool->lock);
rcu_read_unlock();
return 1;
}
spin_unlock(&pool->lock);
fail:
rcu_read_unlock();
local_irq_restore(*flags);
if (work_is_canceling(work))
return -ENOENT;
cpu_relax();
return -EAGAIN;
}
/**
* 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:
* 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)
{
struct worker_pool *pool = pwq->pool;
/* we own @work, set data and link */
set_work_pwq(work, pwq, extra_flags);
list_add_tail(&work->entry, head);
get_pwq(pwq);
/*
* Ensure either wq_worker_sleeping() sees the above
* list_add_tail() or we see zero nr_running to avoid workers lying
* around lazily while there are works to be processed.
*/
smp_mb();
if (__need_more_worker(pool))
wake_up_worker(pool);
}
/*
* 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)
{
static bool printed_dbg_warning;
int new_cpu;
if (likely(!wq_debug_force_rr_cpu)) {
if (cpumask_test_cpu(cpu, wq_unbound_cpumask))
return cpu;
} else if (!printed_dbg_warning) {
pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n");
printed_dbg_warning = true;
}
if (cpumask_empty(wq_unbound_cpumask))
return cpu;
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;
struct list_head *worklist;
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();
debug_work_activate(work);
/* if draining, only works from the same workqueue are allowed */
if (unlikely(wq->flags & __WQ_DRAINING) &&
WARN_ON_ONCE(!is_chained_work(wq)))
return;
rcu_read_lock();
retry:
if (req_cpu == WORK_CPU_UNBOUND)
cpu = wq_select_unbound_cpu(raw_smp_processor_id());
/* pwq which will be used unless @work is executing elsewhere */
if (!(wq->flags & WQ_UNBOUND))
pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
else
pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
/*
* If @work was previously on a different pool, it might still be
* running there, in which case the work needs to be queued on that
* pool to guarantee non-reentrancy.
*/
last_pool = get_work_pool(work);
if (last_pool && last_pool != pwq->pool) {
struct worker *worker;
spin_lock(&last_pool->lock);
worker = find_worker_executing_work(last_pool, work);
if (worker && worker->current_pwq->wq == wq) {
pwq = worker->current_pwq;
} else {
/* meh... not running there, queue here */
spin_unlock(&last_pool->lock);
spin_lock(&pwq->pool->lock);
}
} else {
spin_lock(&pwq->pool->lock);
}
/*
* pwq is determined and locked. For unbound pools, we could have
* raced with pwq release and it could already be dead. If its
* refcnt is zero, repeat pwq selection. Note that pwqs never die
* without another pwq replacing it in the numa_pwq_tbl or while
* work items are executing on it, so the retrying is guaranteed to
* make forward-progress.
*/
if (unlikely(!pwq->refcnt)) {
if (wq->flags & WQ_UNBOUND) {
spin_unlock(&pwq->pool->lock);
cpu_relax();
goto retry;
}
/* oops */
WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt",
wq->name, cpu);
}
/* 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);
if (likely(pwq->nr_active < pwq->max_active)) {
trace_workqueue_activate_work(work);
pwq->nr_active++;
worklist = &pwq->pool->worklist;
if (list_empty(worklist))
pwq->pool->watchdog_ts = jiffies;
} else {
work_flags |= WORK_STRUCT_DELAYED;
worklist = &pwq->delayed_works;
}
insert_work(pwq, work, worklist, work_flags);
out:
spin_unlock(&pwq->pool->lock);
rcu_read_unlock();
}
/**
* 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.
*
* 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 flags;
local_irq_save(flags);
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
__queue_work(cpu, wq, work);
ret = true;
}
local_irq_restore(flags);
return ret;
}
EXPORT_SYMBOL(queue_work_on);
/**
* workqueue_select_cpu_near - 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 workqueue_select_cpu_near(int node)
{
int cpu;
/* No point in doing this if NUMA isn't enabled for workqueues */
if (!wq_numa_enabled)
return WORK_CPU_UNBOUND;
/* 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 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(flags);
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
int cpu = workqueue_select_cpu_near(node);
__queue_work(cpu, wq, work);
ret = true;
}
local_irq_restore(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 (unlikely(cpu != WORK_CPU_UNBOUND))
add_timer_on(timer, cpu);
else
add_timer(timer);
}
/**
* 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 flags;
/* read the comment in __queue_work() */
local_irq_save(flags);
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
__queue_delayed_work(cpu, wq, dwork, delay);
ret = true;
}
local_irq_restore(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 flags;
int ret;
do {
ret = try_to_grab_pending(&dwork->work, true, &flags);
} while (unlikely(ret == -EAGAIN));
if (likely(ret >= 0)) {
__queue_delayed_work(cpu, wq, dwork, delay);
local_irq_restore(flags);
}
/* -ENOENT from try_to_grab_pending() becomes %true */
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;
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
rwork->wq = wq;
call_rcu(&rwork->rcu, rcu_work_rcufn);
return true;
}
return false;
}
EXPORT_SYMBOL(queue_rcu_work);
/**
* 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:
* 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. Because unbind_workers() releases
* pool->lock between setting %WORKER_UNBOUND and zapping
* nr_running, the warning may trigger spuriously. Check iff
* unbind is not in progress.
*/
WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) &&
pool->nr_workers == pool->nr_idle &&
atomic_read(&pool->nr_running));
}
/**
* worker_leave_idle - leave idle state
* @worker: worker which is leaving idle state
*
* @worker is leaving idle state. Update stats.
*
* LOCKING:
* 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);
}
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;
}
/**
* 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);
/*
* set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
* online CPUs. It'll be re-applied when any of the CPUs come up.
*/
set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
/*
* The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains
* stable across this function. See the comments above the flag
* definition for details.
*/
if (pool->flags & POOL_DISASSOCIATED)
worker->flags |= WORKER_UNBOUND;
list_add_tail(&worker->node, &pool->workers);
worker->pool = pool;
mutex_unlock(&wq_pool_attach_mutex);
}
/**
* 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;
struct completion *detach_completion = NULL;
mutex_lock(&wq_pool_attach_mutex);
list_del(&worker->node);
worker->pool = NULL;
if (list_empty(&pool->workers))
detach_completion = pool->detach_completion;
mutex_unlock(&wq_pool_attach_mutex);
/* clear leftover flags without pool->lock after it is detached */
worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND);
if (detach_completion)
complete(detach_completion);
}
/**
* create_worker - create a new workqueue worker
* @pool: pool the new worker will belong to
*
* Create 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 = NULL;
int id = -1;
char id_buf[16];
/* ID is needed to determine kthread name */
id = ida_simple_get(&pool->worker_ida, 0, 0, GFP_KERNEL);
if (id < 0)
goto fail;
worker = alloc_worker(pool->node);
if (!worker)
goto fail;
worker->id = id;
if (pool->cpu >= 0)
snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id,
pool->attrs->nice < 0 ? "H" : "");
else
snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id);
worker->task = kthread_create_on_node(worker_thread, worker, pool->node,
"kworker/%s", id_buf);
if (IS_ERR(worker->task))
goto fail;
set_user_nice(worker->task, pool->attrs->nice);
kthread_bind_mask(worker->task, pool->attrs->cpumask);
/* successful, attach the worker to the pool */
worker_attach_to_pool(worker, pool);
/* start the newly created worker */
spin_lock_irq(&pool->lock);
worker->pool->nr_workers++;
worker_enter_idle(worker);
wake_up_process(worker->task);
spin_unlock_irq(&pool->lock);
return worker;
fail:
if (id >= 0)
ida_simple_remove(&pool->worker_ida, id);
kfree(worker);
return NULL;
}
/**
* destroy_worker - destroy a workqueue worker
* @worker: worker to be destroyed
*
* Destroy @worker and adjust @pool stats accordingly. The worker should
* be idle.
*
* CONTEXT:
* spin_lock_irq(pool->lock).
*/
static void destroy_worker(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
lockdep_assert_held(&pool->lock);
/* 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--;
list_del_init(&worker->entry);
worker->flags |= WORKER_DIE;
wake_up_process(worker->task);
}
static void idle_worker_timeout(struct timer_list *t)
{
struct worker_pool *pool = from_timer(pool, t, idle_timer);
spin_lock_irq(&pool->lock);
while (too_many_workers(pool)) {
struct worker *worker;
unsigned long expires;
/* idle_list is kept in LIFO order, check the last one */
worker = list_entry(pool->idle_list.prev, struct worker, entry);
expires = worker->last_active + IDLE_WORKER_TIMEOUT;
if (time_before(jiffies, expires)) {
mod_timer(&pool->idle_timer, expires);
break;
}
destroy_worker(worker);
}
spin_unlock_irq(&pool->lock);
}
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);
}
}
static void pool_mayday_timeout(struct timer_list *t)
{
struct worker_pool *pool = from_timer(pool, t, mayday_timer);
struct work_struct *work;
spin_lock_irq(&pool->lock);
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);
}
spin_unlock(&wq_mayday_lock);
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:
* 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:
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);
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:
* 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;
wake_up(&wq_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:
* 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;
bool cpu_intensive = pwq->wq->flags & WQ_CPU_INTENSIVE;
int work_color;
struct worker *collision;
#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);
/*
* A single work shouldn't be executed concurrently by
* multiple workers on a single cpu. 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, NULL);
return;
}
/* 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;
work_color = get_work_color(work);
/*
* 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(cpu_intensive))
worker_set_flags(worker, WORKER_CPU_INTENSIVE);
/*
* Wake up another worker if necessary. The condition is always
* false for normal per-cpu workers since nr_running would always
* be >= 1 at this point. This is used to chain execution of the
* pending work items for WORKER_NOT_RUNNING workers such as the
* UNBOUND and CPU_INTENSIVE ones.
*/
if (need_more_worker(pool))
wake_up_worker(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);
spin_unlock_irq(&pool->lock);
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);
lock_map_release(&lockdep_map);
lock_map_release(&pwq->wq->lockdep_map);
if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n"
" last function: %ps\n",
current->comm, preempt_count(), task_pid_nr(current),
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.
*/
cond_resched();
spin_lock_irq(&pool->lock);
/* clear cpu intensive status */
if (unlikely(cpu_intensive))
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;
pwq_dec_nr_in_flight(pwq, work_color);
}
/**
* 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:
* spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times.
*/
static void process_scheduled_works(struct worker *worker)
{
while (!list_empty(&worker->scheduled)) {
struct work_struct *work = list_first_entry(&worker->scheduled,
struct work_struct, entry);
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:
spin_lock_irq(&pool->lock);
/* am I supposed to die? */
if (unlikely(worker->flags & WORKER_DIE)) {
spin_unlock_irq(&pool->lock);
WARN_ON_ONCE(!list_empty(&worker->entry));
set_pf_worker(false);
set_task_comm(worker->task, "kworker/dying");
ida_simple_remove(&pool->worker_ida, worker->id);
worker_detach_from_pool(worker);
kfree(worker);
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);
pool->watchdog_ts = jiffies;
if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) {
/* optimization path, not strictly necessary */
process_one_work(worker, work);
if (unlikely(!list_empty(&worker->scheduled)))
process_scheduled_works(worker);
} else {
move_linked_works(work, &worker->scheduled, 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);
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 *__rescuer)
{
struct worker *rescuer = __rescuer;
struct workqueue_struct *wq = rescuer->rescue_wq;
struct list_head *scheduled = &rescuer->scheduled;
bool should_stop;
set_user_nice(current, RESCUER_NICE_LEVEL);
/*
* Mark rescuer as worker too. As WORKER_PREP is never cleared, it
* doesn't participate in concurrency management.
*/
set_pf_worker(true);
repeat:
set_current_state(TASK_IDLE);
/*
* By the time the rescuer is requested to stop, the workqueue
* shouldn't have any work pending, but @wq->maydays may still have
* pwq(s) queued. This can happen by non-rescuer workers consuming
* all the work items before the rescuer got to them. Go through
* @wq->maydays processing before acting on should_stop so that the
* list is always empty on exit.
*/
should_stop = kthread_should_stop();
/* see whether any pwq is asking for help */
spin_lock_irq(&wq_mayday_lock);
while (!list_empty(&wq->maydays)) {
struct pool_workqueue *pwq = list_first_entry(&wq->maydays,
struct pool_workqueue, mayday_node);
struct worker_pool *pool = pwq->pool;
struct work_struct *work, *n;
bool first = true;
__set_current_state(TASK_RUNNING);
list_del_init(&pwq->mayday_node);
spin_unlock_irq(&wq_mayday_lock);
worker_attach_to_pool(rescuer, pool);
spin_lock_irq(&pool->lock);
/*
* Slurp in all works issued via this workqueue and
* process'em.
*/
WARN_ON_ONCE(!list_empty(scheduled));
list_for_each_entry_safe(work, n, &pool->worklist, entry) {
if (get_work_pwq(work) == pwq) {
if (first)
pool->watchdog_ts = jiffies;
move_linked_works(work, scheduled, &n);
}
first = false;
}
if (!list_empty(scheduled)) {
process_scheduled_works(rescuer);
/*
* The above execution of rescued work items could
* have created more to rescue through
* pwq_activate_first_delayed() or chained
* queueing. Let's put @pwq back on mayday list so
* that such back-to-back work items, which may be
* being used to relieve memory pressure, don't
* incur MAYDAY_INTERVAL delay inbetween.
*/
if (need_to_create_worker(pool)) {
spin_lock(&wq_mayday_lock);
/*
* Queue iff we aren't racing destruction
* and somebody else hasn't queued it already.
*/
if (wq->rescuer && list_empty(&pwq->mayday_node)) {
get_pwq(pwq);
list_add_tail(&pwq->mayday_node, &wq->maydays);
}
spin_unlock(&wq_mayday_lock);
}
}
/*
* Put the reference grabbed by send_mayday(). @pool won't
* go away while we're still attached to it.
*/
put_pwq(pwq);
/*
* Leave this pool. If need_more_worker() is %true, notify a
* regular worker; otherwise, we end up with 0 concurrency
* and stalling the execution.
*/
if (need_more_worker(pool))
wake_up_worker(pool);
spin_unlock_irq(&pool->lock);
worker_detach_from_pool(rescuer);
spin_lock_irq(&wq_mayday_lock);
}
spin_unlock_irq(&wq_mayday_lock);
if (should_stop) {
__set_current_state(TASK_RUNNING);
set_pf_worker(false);
return 0;
}
/* rescuers should never participate in concurrency management */
WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING));
schedule();
goto repeat;
}
/**
* 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)
{
work_func_t target_func = target_work ? target_work->func : NULL;
struct worker *worker;
if (target_wq->flags & WQ_MEM_RECLAIM)
return;
worker = current_wq_worker();
WARN_ONCE(current->flags & PF_MEMALLOC,
"workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps",
current->pid, current->comm, target_wq->name, target_func);
WARN_ONCE(worker && ((worker->current_pwq->wq->flags &
(WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM),
"workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps",
worker->current_pwq->wq->name, worker->current_func,
target_wq->name, target_func);
}
struct wq_barrier {
struct work_struct work;
struct completion done;
struct task_struct *task; /* purely informational */
};
static void wq_barrier_func(struct work_struct *work)
{
struct wq_barrier *barr = container_of(work, struct wq_barrier, work);
complete(&barr->done);
}
/**
* 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:
* 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)
{
struct list_head *head;
unsigned int linked = 0;
/*
* debugobject calls are safe here even with pool->lock locked
* as we know for sure that this will not trigger any of the
* checks and call back into the fixup functions where we
* might deadlock.
*/
INIT_WORK_ONSTACK(&barr->work, wq_barrier_func);
__set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work));
init_completion_map(&barr->done, &target->lockdep_map);
barr->task = current;
/*
* If @target is currently being executed, schedule the
* barrier to the worker; otherwise, put it after @target.
*/
if (worker)
head = worker->scheduled.next;
else {
unsigned long *bits = work_data_bits(target);
head = target->entry.next;
/* there can already be other linked works, inherit and set */
linked = *bits & WORK_STRUCT_LINKED;
__set_bit(WORK_STRUCT_LINKED_BIT, bits);
}
debug_work_activate(&barr->work);
insert_work(pwq, &barr->work, head,
work_color_to_flags(WORK_NO_COLOR) | linked);
}
/**
* 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)
{
bool wait = false;
struct pool_workqueue *pwq;
if (flush_color >= 0) {
WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush));
atomic_set(&wq->nr_pwqs_to_flush, 1);
}
for_each_pwq(pwq, wq) {
struct worker_pool *pool = pwq->pool;
spin_lock_irq(&pool->lock);
if (flush_color >= 0) {
WARN_ON_ONCE(pwq->flush_color != -1);
if (pwq->nr_in_flight[flush_color]) {
pwq->flush_color = flush_color;
atomic_inc(&wq->nr_pwqs_to_flush);
wait = true;
}
}
if (work_color >= 0) {
WARN_ON_ONCE(work_color != work_next_color(pwq->work_color));
pwq->work_color = work_color;
}
spin_unlock_irq(&pool->lock);
}
if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush))
complete(&wq->first_flusher->done);
return wait;
}
/**
* 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)
{
struct wq_flusher this_flusher = {
.list = LIST_HEAD_INIT(this_flusher.list),
.flush_color = -1,
.done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, wq->lockdep_map),
};
int next_color;
if (WARN_ON(!wq_online))
return;
lock_map_acquire(&wq->lockdep_map);
lock_map_release(&wq->lockdep_map);
mutex_lock(&wq->mutex);
/*
* Start-to-wait phase
*/
next_color = work_next_color(wq->work_color);
if (next_color != wq->flush_color) {
/*
* Color space is not full. The current work_color
* becomes our flush_color and work_color is advanced
* by one.
*/
WARN_ON_ONCE(!list_empty(&wq->flusher_overflow));
this_flusher.flush_color = wq->work_color;
wq->work_color = next_color;
if (!wq->first_flusher) {
/* no flush in progress, become the first flusher */
WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color);
wq->first_flusher = &this_flusher;
if (!flush_workqueue_prep_pwqs(wq, wq->flush_color,
wq->work_color)) {
/* nothing to flush, done */
wq->flush_color = next_color;
wq->first_flusher = NULL;
goto out_unlock;
}
} else {
/* wait in queue */
WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color);
list_add_tail(&this_flusher.list, &wq->flusher_queue);
flush_workqueue_prep_pwqs(wq, -1, wq->work_color);
}
} else {
/*
* Oops, color space is full, wait on overflow queue.
* The next flush completion will assign us
* flush_color and transfer to flusher_queue.
*/
list_add_tail(&this_flusher.list, &wq->flusher_overflow);
}
check_flush_dependency(wq, NULL);
mutex_unlock(&wq->mutex);
wait_for_completion(&this_flusher.done);
/*
* Wake-up-and-cascade phase
*
* First flushers are responsible for cascading flushes and
* handling overflow. Non-first flushers can simply return.
*/
if (wq->first_flusher != &this_flusher)
return;
mutex_lock(&wq->mutex);
/* we might have raced, check again with mutex held */
if (wq->first_flusher != &this_flusher)
goto out_unlock;
wq->first_flusher = NULL;
WARN_ON_ONCE(!list_empty(&this_flusher.list));
WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color);
while (true) {
struct wq_flusher *next, *tmp;
/* complete all the flushers sharing the current flush color */
list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) {
if (next->flush_color != wq->flush_color)
break;
list_del_init(&next->list);
complete(&next->done);
}
WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) &&
wq->flush_color != work_next_color(wq->work_color));
/* this flush_color is finished, advance by one */
wq->flush_color = work_next_color(wq->flush_color);
/* one color has been freed, handle overflow queue */
if (!list_empty(&wq->flusher_overflow)) {
/*
* Assign the same color to all overflowed
* flushers, advance work_color and append to
* flusher_queue. This is the start-to-wait
* phase for these overflowed flushers.
*/
list_for_each_entry(tmp, &wq->flusher_overflow, list)
tmp->flush_color = wq->work_color;
wq->work_color = work_next_color(wq->work_color);
list_splice_tail_init(&wq->flusher_overflow,
&wq->flusher_queue);
flush_workqueue_prep_pwqs(wq, -1, wq->work_color);
}
if (list_empty(&wq->flusher_queue)) {
WARN_ON_ONCE(wq->flush_color != wq->work_color);
break;
}
/*
* Need to flush more colors. Make the next flusher
* the new first flusher and arm pwqs.
*/
WARN_ON_ONCE(wq->flush_color == wq->work_color);
WARN_ON_ONCE(wq->flush_color != next->flush_color);
list_del_init(&next->list);
wq->first_flusher = next;
if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1))
break;
/*
* Meh... this color is already done, clear first
* flusher and repeat cascading.
*/
wq->first_flusher = NULL;
}
out_unlock:
mutex_unlock(&wq->mutex);
}
EXPORT_SYMBOL(flush_workqueue);
/**
* 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)
{
unsigned int flush_cnt = 0;
struct pool_workqueue *pwq;
/*
* __queue_work() needs to test whether there are drainers, is much
* hotter than drain_workqueue() and already looks at @wq->flags.
* Use __WQ_DRAINING so that queue doesn't have to check nr_drainers.
*/
mutex_lock(&wq->mutex);
if (!wq->nr_drainers++)
wq->flags |= __WQ_DRAINING;
mutex_unlock(&wq->mutex);
reflush:
flush_workqueue(wq);
mutex_lock(&wq->mutex);
for_each_pwq(pwq, wq) {
bool drained;
spin_lock_irq(&pwq->pool->lock);
drained = !pwq->nr_active && list_empty(&pwq->delayed_works);
spin_unlock_irq(&pwq->pool->lock);
if (drained)
continue;
if (++flush_cnt == 10 ||
(flush_cnt % 100 == 0 && flush_cnt <= 1000))
pr_warn("workqueue %s: drain_workqueue() isn't complete after %u tries\n",
wq->name, flush_cnt);
mutex_unlock(&wq->mutex);
goto reflush;
}
if (!--wq->nr_drainers)
wq->flags &= ~__WQ_DRAINING;
mutex_unlock(&wq->mutex);
}
EXPORT_SYMBOL_GPL(drain_workqueue);
static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
bool from_cancel)
{
struct worker *worker = NULL;
struct worker_pool *pool;
struct pool_workqueue *pwq;
might_sleep();
rcu_read_lock();
pool = get_work_pool(work);
if (!pool) {
rcu_read_unlock();
return false;
}
spin_lock_irq(&pool->lock);
/* see the comment in try_to_grab_pending() with the same code */
pwq = get_work_pwq(work);
if (pwq) {
if (unlikely(pwq->pool != pool))
goto already_gone;
} else {
worker = find_worker_executing_work(pool, work);
if (!worker)
goto already_gone;
pwq = worker->current_pwq;
}
check_flush_dependency(pwq->wq, work);
insert_wq_barrier(pwq, barr, work, worker);
spin_unlock_irq(&pool->lock);
/*
* Force a lock recursion deadlock when using flush_work() inside a
* single-threaded or rescuer equipped workqueue.
*
* For single threaded workqueues the deadlock happens when the work
* is after the work issuing the flush_work(). For rescuer equipped
* workqueues the deadlock happens when the rescuer stalls, blocking
* forward progress.
*/
if (!from_cancel &&
(pwq->wq->saved_max_active == 1 || pwq->wq->rescuer)) {
lock_map_acquire(&pwq->wq->lockdep_map);
lock_map_release(&pwq->wq->lockdep_map);
}
rcu_read_unlock();
return true;
already_gone:
spin_unlock_irq(&pool->lock);
rcu_read_unlock();
return false;
}
static bool __flush_work(struct work_struct *work, bool from_cancel)
{
struct wq_barrier barr;
if (WARN_ON(!wq_online))
return false;
if (WARN_ON(!work->func))
return false;
if (!from_cancel) {
lock_map_acquire(&work->lockdep_map);
lock_map_release(&work->lockdep_map);
}
if (start_flush_work(work, &barr, from_cancel)) {
wait_for_completion(&barr.done);
destroy_work_on_stack(&barr.work);
return true;
} else {
return false;
}
}
/**
* 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)
{
return __flush_work(work, false);
}
EXPORT_SYMBOL_GPL(flush_work);
struct cwt_wait {
wait_queue_entry_t wait;
struct work_struct *work;
};
static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
{
struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait);
if (cwait->work != key)
return 0;
return autoremove_wake_function(wait, mode, sync, key);
}
static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
{
static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq);
unsigned long flags;
int ret;
do {
ret = try_to_grab_pending(work, is_dwork, &flags);
/*
* If someone else is already canceling, wait for it to
* finish. flush_work() doesn't work for PREEMPT_NONE
* because we may get scheduled between @work's completion
* and the other canceling task resuming and clearing
* CANCELING - flush_work() will return false immediately
* as @work is no longer busy, try_to_grab_pending() will
* return -ENOENT as @work is still being canceled and the
* other canceling task won't be able to clear CANCELING as
* we're hogging the CPU.
*
* Let's wait for completion using a waitqueue. As this
* may lead to the thundering herd problem, use a custom
* wake function which matches @work along with exclusive
* wait and wakeup.
*/
if (unlikely(ret == -ENOENT)) {
struct cwt_wait cwait;
init_wait(&cwait.wait);
cwait.wait.func = cwt_wakefn;
cwait.work = work;
prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait,
TASK_UNINTERRUPTIBLE);
if (work_is_canceling(work))
schedule();
finish_wait(&cancel_waitq, &cwait.wait);
}
} while (unlikely(ret < 0));
/* tell other tasks trying to grab @work to back off */
mark_work_canceling(work);
local_irq_restore(flags);
/*
* This allows canceling during early boot. We know that @work
* isn't executing.
*/
if (wq_online)
__flush_work(work, true);
clear_work_data(work);
/*
* Paired with prepare_to_wait() above so that either
* waitqueue_active() is visible here or !work_is_canceling() is
* visible there.
*/
smp_mb();
if (waitqueue_active(&cancel_waitq))
__wake_up(&cancel_waitq, TASK_NORMAL, 1, work);
return ret;
}
/**
* 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.
*
* cancel_work_sync(&delayed_work->work) must not be used for
* delayed_work's. Use cancel_delayed_work_sync() instead.
*
* The caller must ensure that the workqueue on which @work was last
* queued can't be destroyed before this function returns.
*
* Return:
* %true if @work was pending, %false otherwise.
*/
bool cancel_work_sync(struct work_struct *work)
{
return __cancel_work_timer(work, false);
}
EXPORT_SYMBOL_GPL(cancel_work_sync);
/**
* 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)
{
local_irq_disable();
if (del_timer_sync(&dwork->timer))
__queue_work(dwork->cpu, dwork->wq, &dwork->work);
local_irq_enable();
return flush_work(&dwork->work);
}
EXPORT_SYMBOL(flush_delayed_work);
/**
* 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)
{
if (test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&rwork->work))) {
rcu_barrier();
flush_work(&rwork->work);
return true;
} else {
return flush_work(&rwork->work);
}
}
EXPORT_SYMBOL(flush_rcu_work);
static bool __cancel_work(struct work_struct *work, bool is_dwork)
{
unsigned long flags;
int ret;
do {
ret = try_to_grab_pending(work, is_dwork, &flags);
} while (unlikely(ret == -EAGAIN));
if (unlikely(ret < 0))
return false;
set_work_pool_and_clear_pending(work, get_work_pool_id(work));
local_irq_restore(flags);
return ret;
}
/**
* 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)
{
return __cancel_work(&dwork->work, true);
}
EXPORT_SYMBOL(cancel_delayed_work);
/**
* 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)
{
return __cancel_work_timer(&dwork->work, true);
}
EXPORT_SYMBOL(cancel_delayed_work_sync);
/**
* 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)
{
int cpu;
struct work_struct __percpu *works;
works = alloc_percpu(struct work_struct);
if (!works)
return -ENOMEM;
get_online_cpus();
for_each_online_cpu(cpu) {
struct work_struct *work = per_cpu_ptr(works, cpu);
INIT_WORK(work, func);
schedule_work_on(cpu, work);
}
for_each_online_cpu(cpu)
flush_work(per_cpu_ptr(works, cpu));
put_online_cpus();
free_percpu(works);
return 0;
}
/**
* 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)
{
if (!in_interrupt()) {
fn(&ew->work);
return 0;
}
INIT_WORK(&ew->work, fn);
schedule_work(&ew->work);
return 1;
}
EXPORT_SYMBOL_GPL(execute_in_process_context);
/**
* free_workqueue_attrs - free a workqueue_attrs
* @attrs: workqueue_attrs to free
*
* Undo alloc_workqueue_attrs().
*/
void free_workqueue_attrs(struct workqueue_attrs *attrs)
{
if (attrs) {
free_cpumask_var(attrs->cpumask);
kfree(attrs);
}
}
/**
* alloc_workqueue_attrs - allocate a workqueue_attrs
*
* 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)
{
struct workqueue_attrs *attrs;
attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
if (!attrs)
goto fail;
if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL))
goto fail;
cpumask_copy(attrs->cpumask, cpu_possible_mask);
return attrs;
fail:
free_workqueue_attrs(attrs);
return NULL;
}
static void copy_workqueue_attrs(struct workqueue_attrs *to,
const struct workqueue_attrs *from)
{
to->nice = from->nice;
cpumask_copy(to->cpumask, from->cpumask);
/*
* Unlike hash and equality test, this function doesn't ignore
* ->no_numa as it is used for both pool and wq attrs. Instead,
* get_unbound_pool() explicitly clears ->no_numa after copying.
*/
to->no_numa = from->no_numa;
}
/* hash value of the content of @attr */
static u32 wqattrs_hash(const struct workqueue_attrs *attrs)
{
u32 hash = 0;
hash = jhash_1word(attrs->nice, hash);
hash = jhash(cpumask_bits(attrs->cpumask),
BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash);
return hash;
}
/* content equality test */
static bool wqattrs_equal(const struct workqueue_attrs *a,
const struct workqueue_attrs *b)
{
if (a->nice != b->nice)
return false;
if (!cpumask_equal(a->cpumask, b->cpumask))
return false;
return true;
}
/**
* init_worker_pool - initialize a newly zalloc'd worker_pool
* @pool: worker_pool to initialize
*
* 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)
{
spin_lock_init(&pool->lock);
pool->id = -1;
pool->cpu = -1;
pool->node = NUMA_NO_NODE;
pool->flags |= POOL_DISASSOCIATED;
pool->watchdog_ts = jiffies;
INIT_LIST_HEAD(&pool->worklist);
INIT_LIST_HEAD(&pool->idle_list);
hash_init(pool->busy_hash);
timer_setup(&pool->idle_timer, idle_worker_timeout, TIMER_DEFERRABLE);
timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0);
INIT_LIST_HEAD(&pool->workers);
ida_init(&pool->worker_ida);
INIT_HLIST_NODE(&pool->hash_node);
pool->refcnt = 1;
/* shouldn't fail above this point */
pool->attrs = alloc_workqueue_attrs();
if (!pool->attrs)
return -ENOMEM;
return 0;
}
#ifdef CONFIG_LOCKDEP
static void wq_init_lockdep(struct workqueue_struct *wq)
{
char *lock_name;
lockdep_register_key(&wq->key);
lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name);
if (!lock_name)
lock_name = wq->name;
wq->lock_name = lock_name;
lockdep_init_map(&wq->lockdep_map, lock_name, &wq->key, 0);
}
static void wq_unregister_lockdep(struct workqueue_struct *wq)
{
lockdep_unregister_key(&wq->key);
}
static void wq_free_lockdep(struct workqueue_struct *wq)
{
if (wq->lock_name != wq->name)
kfree(wq->lock_name);
}
#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 rcu_free_wq(struct rcu_head *rcu)
{
struct workqueue_struct *wq =
container_of(rcu, struct workqueue_struct, rcu);
wq_free_lockdep(wq);
if (!(wq->flags & WQ_UNBOUND))
free_percpu(wq->cpu_pwqs);
else
free_workqueue_attrs(wq->unbound_attrs);
kfree(wq->rescuer);
kfree(wq);
}
static void rcu_free_pool(struct rcu_head *rcu)
{
struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu);
ida_destroy(&pool->worker_ida);
free_workqueue_attrs(pool->attrs);
kfree(pool);
}
/**
* put_unbound_pool - put a worker_pool
* @pool: worker_pool to put
*
* Put @pool. If its refcnt reaches zero, it gets destroyed in 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)
{
DECLARE_COMPLETION_ONSTACK(detach_completion);
struct worker *worker;
lockdep_assert_held(&wq_pool_mutex);
if (--pool->refcnt)
return;
/* sanity checks */
if (WARN_ON(!(pool->cpu < 0)) ||
WARN_ON(!list_empty(&pool->worklist)))
return;
/* release id and unhash */
if (pool->id >= 0)
idr_remove(&worker_pool_idr, pool->id);
hash_del(&pool->hash_node);
/*
* Become the manager and destroy all workers. This prevents
* @pool's workers from blocking on attach_mutex. We're the last
* manager and @pool gets freed with the flag set.
*/
spin_lock_irq(&pool->lock);
wait_event_lock_irq(wq_manager_wait,
!(pool->flags & POOL_MANAGER_ACTIVE), pool->lock);
pool->flags |= POOL_MANAGER_ACTIVE;
while ((worker = first_idle_worker(pool)))
destroy_worker(worker);
WARN_ON(pool->nr_workers || pool->nr_idle);
spin_unlock_irq(&pool->lock);
mutex_lock(&wq_pool_attach_mutex);
if (!list_empty(&pool->workers))
pool->detach_completion = &detach_completion;
mutex_unlock(&wq_pool_attach_mutex);
if (pool->detach_completion)
wait_for_completion(pool->detach_completion);
/* shut down the timers */
del_timer_sync(&pool->idle_timer);
del_timer_sync(&pool->mayday_timer);
/* RCU protected to allow dereferences from get_work_pool() */
call_rcu(&pool->rcu, rcu_free_pool);
}
/**
* get_unbound_pool - get a worker_pool with the specified attributes
* @attrs: the attributes of the worker_pool to get
*
* Obtain a worker_pool which has the same attributes as @attrs, bump the
* reference count and return it. If there already is a matching
* worker_pool, it will be used; otherwise, this function attempts to
* create a new one.
*
* Should be called with wq_pool_mutex held.
*
* Return: On success, a worker_pool with the same attributes as @attrs.
* On failure, %NULL.
*/
static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
{
u32 hash = wqattrs_hash(attrs);
struct worker_pool *pool;
int node;
int target_node = NUMA_NO_NODE;
lockdep_assert_held(&wq_pool_mutex);
/* do we already have a matching pool? */
hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) {
if (wqattrs_equal(pool->attrs, attrs)) {
pool->refcnt++;
return pool;
}
}
/* if cpumask is contained inside a NUMA node, we belong to that node */
if (wq_numa_enabled) {
for_each_node(node) {
if (cpumask_subset(attrs->cpumask,
wq_numa_possible_cpumask[node])) {
target_node = node;
break;
}
}
}
/* nope, create a new one */
pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, target_node);
if (!pool || init_worker_pool(pool) < 0)
goto fail;
lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */
copy_workqueue_attrs(pool->attrs, attrs);
pool->node = target_node;
/*
* no_numa isn't a worker_pool attribute, always clear it. See
* 'struct workqueue_attrs' comments for detail.
*/
pool->attrs->no_numa = false;
if (worker_pool_assign_id(pool) < 0)
goto fail;
/* create and start the initial worker */
if (wq_online && !create_worker(pool))
goto fail;
/* install */
hash_add(unbound_pool_hash, &pool->hash_node, hash);
return pool;
fail:
if (pool)
put_unbound_pool(pool);
return NULL;
}
static void rcu_free_pwq(struct rcu_head *rcu)
{
kmem_cache_free(pwq_cache,
container_of(rcu, struct pool_workqueue, rcu));
}
/*
* Scheduled on system_wq by put_pwq() when an unbound pwq hits zero refcnt
* and needs to be destroyed.
*/
static void pwq_unbound_release_workfn(struct work_struct *work)
{
struct pool_workqueue *pwq = container_of(work, struct pool_workqueue,
unbound_release_work);
struct workqueue_struct *wq = pwq->wq;
struct worker_pool *pool = pwq->pool;
bool is_last;
if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
return;
mutex_lock(&wq->mutex);
list_del_rcu(&pwq->pwqs_node);
is_last = list_empty(&wq->pwqs);
mutex_unlock(&wq->mutex);
mutex_lock(&wq_pool_mutex);
put_unbound_pool(pool);
mutex_unlock(&wq_pool_mutex);
call_rcu(&pwq->rcu, rcu_free_pwq);
/*
* If we're the last pwq going away, @wq is already dead and no one
* is gonna access it anymore. Schedule RCU free.
*/
if (is_last) {
wq_unregister_lockdep(wq);
call_rcu(&wq->rcu, rcu_free_wq);
}
}
/**
* pwq_adjust_max_active - update a pwq's max_active to the current setting
* @pwq: target pool_workqueue
*
* If @pwq isn't freezing, set @pwq->max_active to the associated
* workqueue's saved_max_active and activate delayed work items
* accordingly. If @pwq is freezing, clear @pwq->max_active to zero.
*/
static void pwq_adjust_max_active(struct pool_workqueue *pwq)
{
struct workqueue_struct *wq = pwq->wq;
bool freezable = wq->flags & WQ_FREEZABLE;
unsigned long flags;
/* for @wq->saved_max_active */
lockdep_assert_held(&wq->mutex);
/* fast exit for non-freezable wqs */
if (!freezable && pwq->max_active == wq->saved_max_active)
return;
/* this function can be called during early boot w/ irq disabled */
spin_lock_irqsave(&pwq->pool->lock, flags);
/*
* During [un]freezing, the caller is responsible for ensuring that
* this function is called at least once after @workqueue_freezing
* is updated and visible.
*/
if (!freezable || !workqueue_freezing) {
pwq->max_active = wq->saved_max_active;
while (!list_empty(&pwq->delayed_works) &&
pwq->nr_active < pwq->max_active)
pwq_activate_first_delayed(pwq);
/*
* Need to kick a worker after thawed or an unbound wq's
* max_active is bumped. It's a slow path. Do it always.
*/
wake_up_worker(pwq->pool);
} else {
pwq->max_active = 0;
}
spin_unlock_irqrestore(&pwq->pool->lock, flags);
}
/* initialize newly alloced @pwq which is associated with @wq and @pool */
static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq,
struct worker_pool *pool)
{
BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK);
memset(pwq, 0, sizeof(*pwq));
pwq->pool = pool;
pwq->wq = wq;
pwq->flush_color = -1;
pwq->refcnt = 1;
INIT_LIST_HEAD(&pwq->delayed_works);
INIT_LIST_HEAD(&pwq->pwqs_node);
INIT_LIST_HEAD(&pwq->mayday_node);
INIT_WORK(&pwq->unbound_release_work, pwq_unbound_release_workfn);
}
/* sync @pwq with the current state of its associated wq and link it */
static void link_pwq(struct pool_workqueue *pwq)
{
struct workqueue_struct *wq = pwq->wq;
lockdep_assert_held(&wq->mutex);
/* may be called multiple times, ignore if already linked */
if (!list_empty(&pwq->pwqs_node))
return;
/* set the matching work_color */
pwq->work_color = wq->work_color;
/* sync max_active to the current setting */
pwq_adjust_max_active(pwq);
/* link in @pwq */
list_add_rcu(&pwq->pwqs_node, &wq->pwqs);
}
/* obtain a pool matching @attr and create a pwq associating the pool and @wq */
static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq,
const struct workqueue_attrs *attrs)
{
struct worker_pool *pool;
struct pool_workqueue *pwq;
lockdep_assert_held(&wq_pool_mutex);
pool = get_unbound_pool(attrs);
if (!pool)
return NULL;
pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node);
if (!pwq) {
put_unbound_pool(pool);
return NULL;
}
init_pwq(pwq, wq, pool);
return pwq;
}
/**
* wq_calc_node_cpumask - calculate a wq_attrs' cpumask for the specified node
* @attrs: the wq_attrs of the default pwq of the target workqueue
* @node: the target NUMA node
* @cpu_going_down: if >= 0, the CPU to consider as offline
* @cpumask: outarg, the resulting cpumask
*
* Calculate the cpumask a workqueue with @attrs should use on @node. If
* @cpu_going_down is >= 0, that cpu is considered offline during
* calculation. The result is stored in @cpumask.
*
* If NUMA affinity is not enabled, @attrs->cpumask is always used. If
* enabled and @node has online CPUs requested by @attrs, the returned
* cpumask is the intersection of the possible CPUs of @node and
* @attrs->cpumask.
*
* The caller is responsible for ensuring that the cpumask of @node stays
* stable.
*
* Return: %true if the resulting @cpumask is different from @attrs->cpumask,
* %false if equal.
*/
static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node,
int cpu_going_down, cpumask_t *cpumask)
{
if (!wq_numa_enabled || attrs->no_numa)
goto use_dfl;
/* does @node have any online CPUs @attrs wants? */
cpumask_and(cpumask, cpumask_of_node(node), attrs->cpumask);
if (cpu_going_down >= 0)
cpumask_clear_cpu(cpu_going_down, cpumask);
if (cpumask_empty(cpumask))
goto use_dfl;
/* yeap, return possible CPUs in @node that @attrs wants */
cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]);
if (cpumask_empty(cpumask)) {
pr_warn_once("WARNING: workqueue cpumask: online intersect > "
"possible intersect\n");
return false;
}
return !cpumask_equal(cpumask, attrs->cpumask);
use_dfl:
cpumask_copy(cpumask, attrs->cpumask);
return false;
}
/* install @pwq into @wq's numa_pwq_tbl[] for @node and return the old pwq */
static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq,
int node,
struct pool_workqueue *pwq)
{
struct pool_workqueue *old_pwq;
lockdep_assert_held(&wq_pool_mutex);
lockdep_assert_held(&wq->mutex);
/* link_pwq() can handle duplicate calls */
link_pwq(pwq);
old_pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]);
rcu_assign_pointer(wq->numa_pwq_tbl[node], pwq);
return old_pwq;
}
/* context to store the prepared attrs & pwqs before applying */
struct apply_wqattrs_ctx {
struct workqueue_struct *wq; /* target workqueue */
struct workqueue_attrs *attrs; /* attrs to apply */
struct list_head list; /* queued for batching commit */
struct pool_workqueue *dfl_pwq;
struct pool_workqueue *pwq_tbl[];
};
/* free the resources after success or abort */
static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx)
{
if (ctx) {
int node;
for_each_node(node)
put_pwq_unlocked(ctx->pwq_tbl[node]);
put_pwq_unlocked(ctx->dfl_pwq);
free_workqueue_attrs(ctx->attrs);
kfree(ctx);
}
}
/* allocate the attrs and pwqs for later installation */
static struct apply_wqattrs_ctx *
apply_wqattrs_prepare(struct workqueue_struct *wq,
const struct workqueue_attrs *attrs)
{
struct apply_wqattrs_ctx *ctx;
struct workqueue_attrs *new_attrs, *tmp_attrs;
int node;
lockdep_assert_held(&wq_pool_mutex);
ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_node_ids), GFP_KERNEL);
new_attrs = alloc_workqueue_attrs();
tmp_attrs = alloc_workqueue_attrs();
if (!ctx || !new_attrs || !tmp_attrs)
goto out_free;
/*
* Calculate the attrs of the default pwq.
* If the user configured cpumask doesn't overlap with the
* wq_unbound_cpumask, we fallback to the wq_unbound_cpumask.
*/
copy_workqueue_attrs(new_attrs, attrs);
cpumask_and(new_attrs->cpumask, new_attrs->cpumask, wq_unbound_cpumask);
if (unlikely(cpumask_empty(new_attrs->cpumask)))
cpumask_copy(new_attrs->cpumask, wq_unbound_cpumask);
/*
* We may create multiple pwqs with differing cpumasks. Make a
* copy of @new_attrs which will be modified and used to obtain
* pools.
*/
copy_workqueue_attrs(tmp_attrs, new_attrs);
/*
* If something goes wrong during CPU up/down, we'll fall back to
* the default pwq covering whole @attrs->cpumask. Always create
* it even if we don't use it immediately.
*/
ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs);
if (!ctx->dfl_pwq)
goto out_free;
for_each_node(node) {
if (wq_calc_node_cpumask(new_attrs, node, -1, tmp_attrs->cpumask)) {
ctx->pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs);
if (!ctx->pwq_tbl[node])
goto out_free;
} else {
ctx->dfl_pwq->refcnt++;
ctx->pwq_tbl[node] = ctx->dfl_pwq;
}
}
/* save the user configured attrs and sanitize it. */
copy_workqueue_attrs(new_attrs, attrs);
cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask);
ctx->attrs = new_attrs;
ctx->wq = wq;
free_workqueue_attrs(tmp_attrs);
return ctx;
out_free:
free_workqueue_attrs(tmp_attrs);
free_workqueue_attrs(new_attrs);
apply_wqattrs_cleanup(ctx);
return NULL;
}
/* set attrs and install prepared pwqs, @ctx points to old pwqs on return */
static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx)
{
int node;
/* all pwqs have been created successfully, let's install'em */
mutex_lock(&ctx->wq->mutex);
copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs);
/* save the previous pwq and install the new one */
for_each_node(node)
ctx->pwq_tbl[node] = numa_pwq_tbl_install(ctx->wq, node,
ctx->pwq_tbl[node]);
/* @dfl_pwq might not have been used, ensure it's linked */
link_pwq(ctx->dfl_pwq);
swap(ctx->wq->dfl_pwq, ctx->dfl_pwq);
mutex_unlock(&ctx->wq->mutex);
}
static void apply_wqattrs_lock(void)
{
/* CPUs should stay stable across pwq creations and installations */
get_online_cpus();
mutex_lock(&wq_pool_mutex);
}
static void apply_wqattrs_unlock(void)
{
mutex_unlock(&wq_pool_mutex);
put_online_cpus();
}
static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
const struct workqueue_attrs *attrs)
{
struct apply_wqattrs_ctx *ctx;
/* only unbound workqueues can change attributes */
if (WARN_ON(!(wq->flags & WQ_UNBOUND)))
return -EINVAL;
/* creating multiple pwqs breaks ordering guarantee */
if (!list_empty(&wq->pwqs)) {
if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
return -EINVAL;
wq->flags &= ~__WQ_ORDERED;
}
ctx = apply_wqattrs_prepare(wq, attrs);
if (!ctx)
return -ENOMEM;
/* the ctx has been prepared successfully, let's commit it */
apply_wqattrs_commit(ctx);
apply_wqattrs_cleanup(ctx);
return 0;
}
/**
* apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue
* @wq: the target workqueue
* @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs()
*
* Apply @attrs to an unbound workqueue @wq. Unless disabled, on NUMA
* machines, this function maps a separate pwq to each NUMA node with
* possibles CPUs in @attrs->cpumask so that work items are affine to the
* NUMA node it was issued on. Older pwqs are released as in-flight work
* items finish. Note that a work item which repeatedly requeues itself
* back-to-back will stay on its current pwq.
*
* Performs GFP_KERNEL allocations.
*
* Assumes caller has CPU hotplug read exclusion, i.e. get_online_cpus().
*
* Return: 0 on success and -errno on failure.
*/
int apply_workqueue_attrs(struct workqueue_struct *wq,
const struct workqueue_attrs *attrs)
{
int ret;
lockdep_assert_cpus_held();
mutex_lock(&wq_pool_mutex);
ret = apply_workqueue_attrs_locked(wq, attrs);
mutex_unlock(&wq_pool_mutex);
return ret;
}
/**
* wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug
* @wq: the target workqueue
* @cpu: the CPU coming up or going down
* @online: whether @cpu is coming up or going down
*
* This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and
* %CPU_DOWN_FAILED. @cpu is being hot[un]plugged, update NUMA affinity of
* @wq accordingly.
*
* If NUMA affinity can't be adjusted due to memory allocation failure, it
* falls back to @wq->dfl_pwq which may not be optimal but is always
* correct.
*
* Note that when the last allowed CPU of a NUMA node goes offline for a
* workqueue with a cpumask spanning multiple nodes, the workers which were
* already executing the work items for the workqueue will lose their CPU
* affinity and may execute on any CPU. This is similar to how per-cpu
* workqueues behave on CPU_DOWN. If a workqueue user wants strict
* affinity, it's the user's responsibility to flush the work item from
* CPU_DOWN_PREPARE.
*/
static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
bool online)
{
int node = cpu_to_node(cpu);
int cpu_off = online ? -1 : cpu;
struct pool_workqueue *old_pwq = NULL, *pwq;
struct workqueue_attrs *target_attrs;
cpumask_t *cpumask;
lockdep_assert_held(&wq_pool_mutex);
if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND) ||
wq->unbound_attrs->no_numa)
return;
/*
* We don't wanna alloc/free wq_attrs for each wq for each CPU.
* Let's use a preallocated one. The following buf is protected by
* CPU hotplug exclusion.
*/
target_attrs = wq_update_unbound_numa_attrs_buf;
cpumask = target_attrs->cpumask;
copy_workqueue_attrs(target_attrs, wq->unbound_attrs);
pwq = unbound_pwq_by_node(wq, node);
/*
* Let's determine what needs to be done. If the target cpumask is
* different from the default pwq's, we need to compare it to @pwq's
* and create a new one if they don't match. If the target cpumask
* equals the default pwq's, the default pwq should be used.
*/
if (wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, cpu_off, cpumask)) {
if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask))
return;
} else {
goto use_dfl_pwq;
}
/* create a new pwq */
pwq = alloc_unbound_pwq(wq, target_attrs);
if (!pwq) {
pr_warn("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n",
wq->name);
goto use_dfl_pwq;
}
/* Install the new pwq. */
mutex_lock(&wq->mutex);
old_pwq = numa_pwq_tbl_install(wq, node, pwq);
goto out_unlock;
use_dfl_pwq:
mutex_lock(&wq->mutex);
spin_lock_irq(&wq->dfl_pwq->pool->lock);
get_pwq(wq->dfl_pwq);
spin_unlock_irq(&wq->dfl_pwq->pool->lock);
old_pwq = numa_pwq_tbl_install(wq, node, wq->dfl_pwq);
out_unlock:
mutex_unlock(&wq->mutex);
put_pwq_unlocked(old_pwq);
}
static int alloc_and_link_pwqs(struct workqueue_struct *wq)
{
bool highpri = wq->flags & WQ_HIGHPRI;
int cpu, ret;
if (!(wq->flags & WQ_UNBOUND)) {
wq->cpu_pwqs = alloc_percpu(struct pool_workqueue);
if (!wq->cpu_pwqs)
return -ENOMEM;
for_each_possible_cpu(cpu) {
struct pool_workqueue *pwq =
per_cpu_ptr(wq->cpu_pwqs, cpu);
struct worker_pool *cpu_pools =
per_cpu(cpu_worker_pools, cpu);
init_pwq(pwq, wq, &cpu_pools[highpri]);
mutex_lock(&wq->mutex);
link_pwq(pwq);
mutex_unlock(&wq->mutex);
}
return 0;
}
get_online_cpus();
if (wq->flags & __WQ_ORDERED) {
ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
/* there should only be single pwq for ordering guarantee */
WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
"ordering guarantee broken for workqueue %s\n", wq->name);
} else {
ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
}
put_online_cpus();
return ret;
}
static int wq_clamp_max_active(int max_active, unsigned int flags,
const char *name)
{
int lim = flags & WQ_UNBOUND ? WQ_UNBOUND_MAX_ACTIVE : WQ_MAX_ACTIVE;
if (max_active < 1 || max_active > lim)
pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n",
max_active, name, 1, lim);
return clamp_val(max_active, 1, lim);
}
/*
* Workqueues which may be used during memory reclaim should have a rescuer
* to guarantee forward progress.
*/
static int init_rescuer(struct workqueue_struct *wq)
{
struct worker *rescuer;
int ret;
if (!(wq->flags & WQ_MEM_RECLAIM))
return 0;
rescuer = alloc_worker(NUMA_NO_NODE);
if (!rescuer)
return -ENOMEM;
rescuer->rescue_wq = wq;
rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", wq->name);
ret = PTR_ERR_OR_ZERO(rescuer->task);
if (ret) {
kfree(rescuer);
return ret;
}
wq->rescuer = rescuer;
kthread_bind_mask(rescuer->task, cpu_possible_mask);
wake_up_process(rescuer->task);
return 0;
}
__printf(1, 4)
struct workqueue_struct *alloc_workqueue(const char *fmt,
unsigned int flags,
int max_active, ...)
{
size_t tbl_size = 0;
va_list args;
struct workqueue_struct *wq;
struct pool_workqueue *pwq;
/*
* Unbound && max_active == 1 used to imply ordered, which is no
* longer the case on NUMA machines due to per-node pools. While
* alloc_ordered_workqueue() is the right way to create an ordered
* workqueue, keep the previous behavior to avoid subtle breakages
* on NUMA.
*/
if ((flags & WQ_UNBOUND) && max_active == 1)
flags |= __WQ_ORDERED;
/* see the comment above the definition of WQ_POWER_EFFICIENT */
if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
flags |= WQ_UNBOUND;
/* allocate wq and format name */
if (flags & WQ_UNBOUND)
tbl_size = nr_node_ids * sizeof(wq->numa_pwq_tbl[0]);
wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL);
if (!wq)
return NULL;
if (flags & WQ_UNBOUND) {
wq->unbound_attrs = alloc_workqueue_attrs();
if (!wq->unbound_attrs)
goto err_free_wq;
}
va_start(args, max_active);
vsnprintf(wq->name, sizeof(wq->name), fmt, args);
va_end(args);
max_active = max_active ?: WQ_DFL_ACTIVE;
max_active = wq_clamp_max_active(max_active, flags, wq->name);
/* init wq */
wq->flags = flags;
wq->saved_max_active = max_active;
mutex_init(&wq->mutex);
atomic_set(&wq->nr_pwqs_to_flush, 0);
INIT_LIST_HEAD(&wq->pwqs);
INIT_LIST_HEAD(&wq->flusher_queue);
INIT_LIST_HEAD(&wq->flusher_overflow);
INIT_LIST_HEAD(&wq->maydays);
wq_init_lockdep(wq);
INIT_LIST_HEAD(&wq->list);
if (alloc_and_link_pwqs(wq) < 0)
goto err_unreg_lockdep;
if (wq_online && init_rescuer(wq) < 0)
goto err_destroy;
if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq))
goto err_destroy;
/*
* wq_pool_mutex protects global freeze state and workqueues list.
* Grab it, adjust max_active and add the new @wq to workqueues
* list.
*/
mutex_lock(&wq_pool_mutex);
mutex_lock(&wq->mutex);
for_each_pwq(pwq, wq)
pwq_adjust_max_active(pwq);
mutex_unlock(&wq->mutex);
list_add_tail_rcu(&wq->list, &workqueues);
mutex_unlock(&wq_pool_mutex);
return wq;
err_unreg_lockdep:
wq_unregister_lockdep(wq);
wq_free_lockdep(wq);
err_free_wq:
free_workqueue_attrs(wq->unbound_attrs);
kfree(wq);
return NULL;
err_destroy:
destroy_workqueue(wq);
return NULL;
}
EXPORT_SYMBOL_GPL(alloc_workqueue);
static bool pwq_busy(struct pool_workqueue *pwq)
{
int i;
for (i = 0; i < WORK_NR_COLORS; i++)
if (pwq->nr_in_flight[i])
return true;
if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1))
return true;
if (pwq->nr_active || !list_empty(&pwq->delayed_works))
return true;
return false;
}
/**
* 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)
{
struct pool_workqueue *pwq;
int node;
/*
* Remove it from sysfs first so that sanity check failure doesn't
* lead to sysfs name conflicts.
*/
workqueue_sysfs_unregister(wq);
/* drain it before proceeding with destruction */
drain_workqueue(wq);
/* kill rescuer, if sanity checks fail, leave it w/o rescuer */
if (wq->rescuer) {
struct worker *rescuer = wq->rescuer;
/* this prevents new queueing */
spin_lock_irq(&wq_mayday_lock);
wq->rescuer = NULL;
spin_unlock_irq(&wq_mayday_lock);
/* rescuer will empty maydays list before exiting */
kthread_stop(rescuer->task);
kfree(rescuer);
}
/*
* Sanity checks - grab all the locks so that we wait for all
* in-flight operations which may do put_pwq().
*/
mutex_lock(&wq_pool_mutex);
mutex_lock(&wq->mutex);
for_each_pwq(pwq, wq) {
spin_lock_irq(&pwq->pool->lock);
if (WARN_ON(pwq_busy(pwq))) {
pr_warn("%s: %s has the following busy pwq\n",
__func__, wq->name);
show_pwq(pwq);
spin_unlock_irq(&pwq->pool->lock);
mutex_unlock(&wq->mutex);
mutex_unlock(&wq_pool_mutex);
show_workqueue_state();
return;
}
spin_unlock_irq(&pwq->pool->lock);
}
mutex_unlock(&wq->mutex);
mutex_unlock(&wq_pool_mutex);
/*
* wq list is used to freeze wq, remove from list after
* flushing is complete in case freeze races us.
*/
mutex_lock(&wq_pool_mutex);
list_del_rcu(&wq->list);
mutex_unlock(&wq_pool_mutex);
if (!(wq->flags & WQ_UNBOUND)) {
wq_unregister_lockdep(wq);
/*
* The base ref is never dropped on per-cpu pwqs. Directly
* schedule RCU free.
*/
call_rcu(&wq->rcu, rcu_free_wq);
} else {
/*
* We're the sole accessor of @wq at this point. Directly
* access numa_pwq_tbl[] and dfl_pwq to put the base refs.
* @wq will be freed when the last pwq is released.
*/
for_each_node(node) {
pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]);
RCU_INIT_POINTER(wq->numa_pwq_tbl[node], NULL);
put_pwq_unlocked(pwq);
}
/*
* Put dfl_pwq. @wq may be freed any time after dfl_pwq is
* put. Don't access it afterwards.
*/
pwq = wq->dfl_pwq;
wq->dfl_pwq = NULL;
put_pwq_unlocked(pwq);
}
}
EXPORT_SYMBOL_GPL(destroy_workqueue);
/**
* workqueue_set_max_active - adjust max_active of a workqueue
* @wq: target workqueue
* @max_active: new max_active value.
*
* Set max_active of @wq to @max_active.
*
* CONTEXT:
* Don't call from IRQ context.
*/
void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
{
struct pool_workqueue *pwq;
/* disallow meddling with max_active for ordered workqueues */
if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
return;
max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
mutex_lock(&wq->mutex);
wq->flags &= ~__WQ_ORDERED;
wq->saved_max_active = max_active;
for_each_pwq(pwq, wq)
pwq_adjust_max_active(pwq);
mutex_unlock(&wq->mutex);
}
EXPORT_SYMBOL_GPL(workqueue_set_max_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)
{
struct worker *worker = current_wq_worker();
return worker ? worker->current_work : NULL;
}
EXPORT_SYMBOL(current_work);
/**
* 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)
{
struct worker *worker = current_wq_worker();
return worker && worker->rescue_wq;
}
/**
* 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.
* Note that both per-cpu and unbound workqueues may be associated with
* multiple pool_workqueues which have separate congested states. A
* workqueue being congested on one CPU doesn't mean the workqueue is also
* contested on other CPUs / NUMA nodes.
*
* Return:
* %true if congested, %false otherwise.
*/
bool workqueue_congested(int cpu, struct workqueue_struct *wq)
{
struct pool_workqueue *pwq;
bool ret;
rcu_read_lock();
preempt_disable();
if (cpu == WORK_CPU_UNBOUND)
cpu = smp_processor_id();
if (!(wq->flags & WQ_UNBOUND))
pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
else
pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
ret = !list_empty(&pwq->delayed_works);
preempt_enable();
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(workqueue_congested);
/**
* 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)
{
struct worker_pool *pool;
unsigned long flags;
unsigned int ret = 0;
if (work_pending(work))
ret |= WORK_BUSY_PENDING;
rcu_read_lock();
pool = get_work_pool(work);
if (pool) {
spin_lock_irqsave(&pool->lock, flags);
if (find_worker_executing_work(pool, work))
ret |= WORK_BUSY_RUNNING;
spin_unlock_irqrestore(&pool->lock, flags);
}
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(work_busy);
/**
* set_worker_desc - set description for the current work item
* @fmt: printf-style format string
* @...: arguments for the format string
*
* This function can be called by a running work function to describe what
* the work item is about. If the worker task gets dumped, this
* information will be printed out together to help debugging. The
* description can be at most WORKER_DESC_LEN including the trailing '\0'.
*/
void set_worker_desc(const char *fmt, ...)
{
struct worker *worker = current_wq_worker();
va_list args;
if (worker) {
va_start(args, fmt);
vsnprintf(worker->desc, sizeof(worker->desc), fmt, args);
va_end(args);
}
}
EXPORT_SYMBOL_GPL(set_worker_desc);
/**
* print_worker_info - print out worker information and description
* @log_lvl: the log level to use when printing
* @task: target task
*
* If @task is a worker and currently executing a work item, print out the
* name of the workqueue being serviced and worker description set with
* set_worker_desc() by the currently executing work item.
*
* This function can be safely called on any task as long as the
* task_struct itself is accessible. While safe, this function isn't
* synchronized and may print out mixups or garbages of limited length.
*/
void print_worker_info(const char *log_lvl, struct task_struct *task)
{
work_func_t *fn = NULL;
char name[WQ_NAME_LEN] = { };
char desc[WORKER_DESC_LEN] = { };
struct pool_workqueue *pwq = NULL;
struct workqueue_struct *wq = NULL;
struct worker *worker;
if (!(task->flags & PF_WQ_WORKER))
return;
/*
* This function is called without any synchronization and @task
* could be in any state. Be careful with dereferences.
*/
worker = kthread_probe_data(task);
/*
* Carefully copy the associated workqueue's workfn, name and desc.
* Keep the original last '\0' in case the original is garbage.
*/
probe_kernel_read(&fn, &worker->current_func, sizeof(fn));
probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq));
probe_kernel_read(&wq, &pwq->wq, sizeof(wq));
probe_kernel_read(name, wq->name, sizeof(name) - 1);
probe_kernel_read(desc, worker->desc, sizeof(desc) - 1);
if (fn || name[0] || desc[0]) {
printk("%sWorkqueue: %s %ps", log_lvl, name, fn);
if (strcmp(name, desc))
pr_cont(" (%s)", desc);
pr_cont("\n");
}
}
static void pr_cont_pool_info(struct worker_pool *pool)
{
pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask);
if (pool->node != NUMA_NO_NODE)
pr_cont(" node=%d", pool->node);
pr_cont(" flags=0x%x nice=%d", pool->flags, pool->attrs->nice);
}
static void pr_cont_work(bool comma, struct work_struct *work)
{
if (work->func == wq_barrier_func) {
struct wq_barrier *barr;
barr = container_of(work, struct wq_barrier, work);
pr_cont("%s BAR(%d)", comma ? "," : "",
task_pid_nr(barr->task));
} else {
pr_cont("%s %ps", comma ? "," : "", work->func);
}
}
static void show_pwq(struct pool_workqueue *pwq)
{
struct worker_pool *pool = pwq->pool;
struct work_struct *work;
struct worker *worker;
bool has_in_flight = false, has_pending = false;
int bkt;
pr_info(" pwq %d:", pool->id);
pr_cont_pool_info(pool);
pr_cont(" active=%d/%d refcnt=%d%s\n",
pwq->nr_active, pwq->max_active, pwq->refcnt,
!list_empty(&pwq->mayday_node) ? " MAYDAY" : "");
hash_for_each(pool->busy_hash, bkt, worker, hentry) {
if (worker->current_pwq == pwq) {
has_in_flight = true;
break;
}
}
if (has_in_flight) {
bool comma = false;
pr_info(" in-flight:");
hash_for_each(pool->busy_hash, bkt, worker, hentry) {
if (worker->current_pwq != pwq)
continue;
pr_cont("%s %d%s:%ps", comma ? "," : "",
task_pid_nr(worker->task),
worker->rescue_wq ? "(RESCUER)" : "",
worker->current_func);
list_for_each_entry(work, &worker->scheduled, entry)
pr_cont_work(false, work);
comma = true;
}
pr_cont("\n");
}
list_for_each_entry(work, &pool->worklist, entry) {
if (get_work_pwq(work) == pwq) {
has_pending = true;
break;
}
}
if (has_pending) {
bool comma = false;
pr_info(" pending:");
list_for_each_entry(work, &pool->worklist, entry) {
if (get_work_pwq(work) != pwq)
continue;
pr_cont_work(comma, work);
comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED);
}
pr_cont("\n");
}
if (!list_empty(&pwq->delayed_works)) {
bool comma = false;
pr_info(" delayed:");
list_for_each_entry(work, &pwq->delayed_works, entry) {
pr_cont_work(comma, work);
comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED);
}
pr_cont("\n");
}
}
/**
* show_workqueue_state - dump workqueue state
*
* Called from a sysrq handler or try_to_freeze_tasks() and prints out
* all busy workqueues and pools.
*/
void show_workqueue_state(void)
{
struct workqueue_struct *wq;
struct worker_pool *pool;
unsigned long flags;
int pi;
rcu_read_lock();
pr_info("Showing busy workqueues and worker pools:\n");
list_for_each_entry_rcu(wq, &workqueues, list) {
struct pool_workqueue *pwq;
bool idle = true;
for_each_pwq(pwq, wq) {
if (pwq->nr_active || !list_empty(&pwq->delayed_works)) {
idle = false;
break;
}
}
if (idle)
continue;
pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags);
for_each_pwq(pwq, wq) {
spin_lock_irqsave(&pwq->pool->lock, flags);
if (pwq->nr_active || !list_empty(&pwq->delayed_works))
show_pwq(pwq);
spin_unlock_irqrestore(&pwq->pool->lock, flags);
/*
* We could be printing a lot from atomic context, e.g.
* sysrq-t -> show_workqueue_state(). Avoid triggering
* hard lockup.
*/
touch_nmi_watchdog();
}
}
for_each_pool(pool, pi) {
struct worker *worker;
bool first = true;
spin_lock_irqsave(&pool->lock, flags);
if (pool->nr_workers == pool->nr_idle)
goto next_pool;
pr_info("pool %d:", pool->id);
pr_cont_pool_info(pool);
pr_cont(" hung=%us workers=%d",
jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000,
pool->nr_workers);
if (pool->manager)
pr_cont(" manager: %d",
task_pid_nr(pool->manager->task));
list_for_each_entry(worker, &pool->idle_list, entry) {
pr_cont(" %s%d", first ? "idle: " : "",
task_pid_nr(worker->task));
first = false;
}
pr_cont("\n");
next_pool:
spin_unlock_irqrestore(&pool->lock, flags);
/*
* We could be printing a lot from atomic context, e.g.
* sysrq-t -> show_workqueue_state(). Avoid triggering
* hard lockup.
*/
touch_nmi_watchdog();
}
rcu_read_unlock();
}
/* used to show worker information through /proc/PID/{comm,stat,status} */
void wq_worker_comm(char *buf, size_t size, struct task_struct *task)
{
int off;
/* always show the actual comm */
off = strscpy(buf, task->comm, size);
if (off < 0)
return;
/* stabilize PF_WQ_WORKER and worker pool association */
mutex_lock(&wq_pool_attach_mutex);
if (task->flags & PF_WQ_WORKER) {
struct worker *worker = kthread_data(task);
struct worker_pool *pool = worker->pool;
if (pool) {
spin_lock_irq(&pool->lock);
/*
* ->desc tracks information (wq name or
* set_worker_desc()) for the latest execution. If
* current, prepend '+', otherwise '-'.
*/
if (worker->desc[0] != '\0') {
if (worker->current_work)
scnprintf(buf + off, size - off, "+%s",
worker->desc);
else
scnprintf(buf + off, size - off, "-%s",
worker->desc);
}
spin_unlock_irq(&pool->lock);
}
}
mutex_unlock(&wq_pool_attach_mutex);
}
#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)
{
struct worker_pool *pool;
struct worker *worker;
for_each_cpu_worker_pool(pool, cpu) {
mutex_lock(&wq_pool_attach_mutex);
spin_lock_irq(&pool->lock);
/*
* We've blocked all attach/detach operations. Make all workers
* unbound and set DISASSOCIATED. Before this, all workers
* except for the ones which are still executing works from
* before the last CPU down must be on the cpu. After
* this, they may become diasporas.
*/
for_each_pool_worker(worker, pool)
worker->flags |= WORKER_UNBOUND;
pool->flags |= POOL_DISASSOCIATED;
spin_unlock_irq(&pool->lock);
mutex_unlock(&wq_pool_attach_mutex);
/*
* Call schedule() so that we cross rq->lock and thus can
* guarantee sched callbacks see the %WORKER_UNBOUND flag.
* This is necessary as scheduler callbacks may be invoked
* from other cpus.
*/
schedule();
/*
* Sched callbacks are disabled now. Zap nr_running.
* After this, nr_running stays zero and need_more_worker()
* and keep_working() are always true as long as the
* worklist is not empty. This pool now behaves as an
* unbound (in terms of concurrency management) pool which
* are served by workers tied to the pool.
*/
atomic_set(&pool->nr_running, 0);
/*
* With concurrency management just turned off, a busy
* worker blocking could lead to lengthy stalls. Kick off
* unbound chain execution of currently pending work items.
*/
spin_lock_irq(&pool->lock);
wake_up_worker(pool);
spin_unlock_irq(&pool->lock);
}
}
/**
* rebind_workers - rebind all workers of a pool to the associated CPU
* @pool: pool of interest
*
* @pool->cpu is coming online. Rebind all workers to the CPU.
*/
static void rebind_workers(struct worker_pool *pool)
{
struct worker *worker;
lockdep_assert_held(&wq_pool_attach_mutex);
/*
* Restore CPU affinity of all workers. As all idle workers should
* be on the run-queue of the associated CPU before any local
* wake-ups for concurrency management happen, restore CPU affinity
* of all workers first and then clear UNBOUND. As we're called
* from CPU_ONLINE, the following shouldn't fail.
*/
for_each_pool_worker(worker, pool)
WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
pool->attrs->cpumask) < 0);
spin_lock_irq(&pool->lock);
pool->flags &= ~POOL_DISASSOCIATED;
for_each_pool_worker(worker, pool) {
unsigned int worker_flags = worker->flags;
/*
* A bound idle worker should actually be on the runqueue
* of the associated CPU for local wake-ups targeting it to
* work. Kick all idle workers so that they migrate to the
* associated CPU. Doing this in the same loop as
* replacing UNBOUND with REBOUND is safe as no worker will
* be bound before @pool->lock is released.
*/
if (worker_flags & WORKER_IDLE)
wake_up_process(worker->task);
/*
* We want to clear UNBOUND but can't directly call
* worker_clr_flags() or adjust nr_running. Atomically
* replace UNBOUND with another NOT_RUNNING flag REBOUND.
* @worker will clear REBOUND using worker_clr_flags() when
* it initiates the next execution cycle thus restoring
* concurrency management. Note that when or whether
* @worker clears REBOUND doesn't affect correctness.
*
* WRITE_ONCE() is necessary because @worker->flags may be
* tested without holding any lock in
* wq_worker_running(). Without it, NOT_RUNNING test may
* fail incorrectly leading to premature concurrency
* management operations.
*/
WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND));
worker_flags |= WORKER_REBOUND;
worker_flags &= ~WORKER_UNBOUND;
WRITE_ONCE(worker->flags, worker_flags);
}
spin_unlock_irq(&pool->lock);
}
/**
* restore_unbound_workers_cpumask - restore cpumask of unbound workers
* @pool: unbound pool of interest
* @cpu: the CPU which is coming up
*
* An unbound pool may end up with a cpumask which doesn't have any online
* CPUs. When a worker of such pool get scheduled, the scheduler resets
* its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any
* online CPU before, cpus_allowed of all its workers should be restored.
*/
static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
{
static cpumask_t cpumask;
struct worker *worker;
lockdep_assert_held(&wq_pool_attach_mutex);
/* is @cpu allowed for @pool? */
if (!cpumask_test_cpu(cpu, pool->attrs->cpumask))
return;
cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask);
/* as we're called from CPU_ONLINE, the following shouldn't fail */
for_each_pool_worker(worker, pool)
WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0);
}
int workqueue_prepare_cpu(unsigned int cpu)
{
struct worker_pool *pool;
for_each_cpu_worker_pool(pool, cpu) {
if (pool->nr_workers)
continue;
if (!create_worker(pool))
return -ENOMEM;
}
return 0;
}
int workqueue_online_cpu(unsigned int cpu)
{
struct worker_pool *pool;
struct workqueue_struct *wq;
int pi;
mutex_lock(&wq_pool_mutex);
for_each_pool(pool, pi) {
mutex_lock(&wq_pool_attach_mutex);
if (pool->cpu == cpu)
rebind_workers(pool);
else if (pool->cpu < 0)
restore_unbound_workers_cpumask(pool, cpu);
mutex_unlock(&wq_pool_attach_mutex);
}
/* update NUMA affinity of unbound workqueues */
list_for_each_entry(wq, &workqueues, list)
wq_update_unbound_numa(wq, cpu, true);
mutex_unlock(&wq_pool_mutex);
return 0;
}
int workqueue_offline_cpu(unsigned int cpu)
{
struct workqueue_struct *wq;
/* unbinding per-cpu workers should happen on the local CPU */
if (WARN_ON(cpu != smp_processor_id()))
return -1;
unbind_workers(cpu);
/* update NUMA affinity of unbound workqueues */
mutex_lock(&wq_pool_mutex);
list_for_each_entry(wq, &workqueues, list)
wq_update_unbound_numa(wq, cpu, false);
mutex_unlock(&wq_pool_mutex);
return 0;
}
struct work_for_cpu {
struct work_struct work;
long (*fn)(void *);
void *arg;
long ret;
};
static void work_for_cpu_fn(struct work_struct *work)
{
struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work);
wfc->ret = wfc->fn(wfc->arg);
}
/**
* work_on_cpu - 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
*
* It is up to the caller to ensure that the cpu doesn't go offline.
* The caller must not hold any locks which would prevent @fn from completing.
*
* Return: The value @fn returns.
*/
long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
{
struct work_for_cpu wfc = { .fn = fn, .arg = arg };
INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
schedule_work_on(cpu, &wfc.work);
flush_work(&wfc.work);
destroy_work_on_stack(&wfc.work);
return wfc.ret;
}
EXPORT_SYMBOL_GPL(work_on_cpu);
/**
* work_on_cpu_safe - 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
*
* 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(int cpu, long (*fn)(void *), void *arg)
{
long ret = -ENODEV;
get_online_cpus();
if (cpu_online(cpu))
ret = work_on_cpu(cpu, fn, arg);
put_online_cpus();
return ret;
}
EXPORT_SYMBOL_GPL(work_on_cpu_safe);
#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 delayed_works list instead of
* pool->worklist.
*
* CONTEXT:
* Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's.
*/
void freeze_workqueues_begin(void)
{
struct workqueue_struct *wq;
struct pool_workqueue *pwq;
mutex_lock(&wq_pool_mutex);
WARN_ON_ONCE(workqueue_freezing);
workqueue_freezing = true;
list_for_each_entry(wq, &workqueues, list) {
mutex_lock(&wq->mutex);
for_each_pwq(pwq, wq)
pwq_adjust_max_active(pwq);
mutex_unlock(&wq->mutex);
}
mutex_unlock(&wq_pool_mutex);
}
/**
* 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)
{
bool busy = false;
struct workqueue_struct *wq;
struct pool_workqueue *pwq;
mutex_lock(&wq_pool_mutex);
WARN_ON_ONCE(!workqueue_freezing);
list_for_each_entry(wq, &workqueues, list) {
if (!(wq->flags & WQ_FREEZABLE))
continue;
/*
* nr_active is monotonically decreasing. It's safe
* to peek without lock.
*/
rcu_read_lock();
for_each_pwq(pwq, wq) {
WARN_ON_ONCE(pwq->nr_active < 0);
if (pwq->nr_active) {
busy = true;
rcu_read_unlock();
goto out_unlock;
}
}
rcu_read_unlock();
}
out_unlock:
mutex_unlock(&wq_pool_mutex);
return busy;
}
/**
* 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)
{
struct workqueue_struct *wq;
struct pool_workqueue *pwq;
mutex_lock(&wq_pool_mutex);
if (!workqueue_freezing)
goto out_unlock;
workqueue_freezing = false;
/* restore max_active and repopulate worklist */
list_for_each_entry(wq, &workqueues, list) {
mutex_lock(&wq->mutex);
for_each_pwq(pwq, wq)
pwq_adjust_max_active(pwq);
mutex_unlock(&wq->mutex);
}
out_unlock:
mutex_unlock(&wq_pool_mutex);
}
#endif /* CONFIG_FREEZER */
static int workqueue_apply_unbound_cpumask(void)
{
LIST_HEAD(ctxs);
int ret = 0;
struct workqueue_struct *wq;
struct apply_wqattrs_ctx *ctx, *n;
lockdep_assert_held(&wq_pool_mutex);
list_for_each_entry(wq, &workqueues, list) {
if (!(wq->flags & WQ_UNBOUND))
continue;
/* creating multiple pwqs breaks ordering guarantee */
if (wq->flags & __WQ_ORDERED)
continue;
ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs);
if (!ctx) {
ret = -ENOMEM;
break;
}
list_add_tail(&ctx->list, &ctxs);
}
list_for_each_entry_safe(ctx, n, &ctxs, list) {
if (!ret)
apply_wqattrs_commit(ctx);
apply_wqattrs_cleanup(ctx);
}
return ret;
}
/**
* workqueue_set_unbound_cpumask - Set the low-level unbound cpumask
* @cpumask: the cpumask to set
*
* The low-level workqueues cpumask is a global cpumask that limits
* the affinity of all unbound workqueues. This function check the @cpumask
* and apply it to all unbound workqueues and updates all pwqs of them.
*
* Retun: 0 - Success
* -EINVAL - Invalid @cpumask
* -ENOMEM - Failed to allocate memory for attrs or pwqs.
*/
int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
{
int ret = -EINVAL;
cpumask_var_t saved_cpumask;
if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL))
return -ENOMEM;
/*
* Not excluding isolated cpus on purpose.
* If the user wishes to include them, we allow that.
*/
cpumask_and(cpumask, cpumask, cpu_possible_mask);
if (!cpumask_empty(cpumask)) {
apply_wqattrs_lock();
/* save the old wq_unbound_cpumask. */
cpumask_copy(saved_cpumask, wq_unbound_cpumask);
/* update wq_unbound_cpumask at first and apply it to wqs. */
cpumask_copy(wq_unbound_cpumask, cpumask);
ret = workqueue_apply_unbound_cpumask();
/* restore the wq_unbound_cpumask when failed. */
if (ret < 0)
cpumask_copy(wq_unbound_cpumask, saved_cpumask);
apply_wqattrs_unlock();
}
free_cpumask_var(saved_cpumask);
return ret;
}
#ifdef CONFIG_SYSFS
/*
* Workqueues with WQ_SYSFS flag set is visible to userland via
* /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the
* following attributes.
*
* per_cpu RO bool : whether the workqueue is per-cpu or unbound
* max_active RW int : maximum number of in-flight work items
*
* Unbound workqueues have the following extra attributes.
*
* pool_ids RO int : the associated pool IDs for each node
* nice RW int : nice value of the workers
* cpumask RW mask : bitmask of allowed CPUs for the workers
* numa RW bool : whether enable NUMA affinity
*/
struct wq_device {
struct workqueue_struct *wq;
struct device dev;
};
static struct workqueue_struct *dev_to_wq(struct device *dev)
{
struct wq_device *wq_dev = container_of(dev, struct wq_device, dev);
return wq_dev->wq;
}
static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct workqueue_struct *wq = dev_to_wq(dev);
return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND));
}
static DEVICE_ATTR_RO(per_cpu);
static ssize_t max_active_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct workqueue_struct *wq = dev_to_wq(dev);
return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active);
}
static ssize_t max_active_store(struct device *dev,
struct device_attribute *attr, const char *buf,
size_t count)
{
struct workqueue_struct *wq = dev_to_wq(dev);
int val;
if (sscanf(buf, "%d", &val) != 1 || val <= 0)
return -EINVAL;
workqueue_set_max_active(wq, val);
return count;
}
static DEVICE_ATTR_RW(max_active);
static struct attribute *wq_sysfs_attrs[] = {
&dev_attr_per_cpu.attr,
&dev_attr_max_active.attr,
NULL,
};
ATTRIBUTE_GROUPS(wq_sysfs);
static ssize_t wq_pool_ids_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct workqueue_struct *wq = dev_to_wq(dev);
const char *delim = "";
int node, written = 0;
get_online_cpus();
rcu_read_lock();
for_each_node(node) {
written += scnprintf(buf + written, PAGE_SIZE - written,
"%s%d:%d", delim, node,
unbound_pwq_by_node(wq, node)->pool->id);
delim = " ";
}
written += scnprintf(buf + written, PAGE_SIZE - written, "\n");
rcu_read_unlock();
put_online_cpus();
return written;
}
static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct workqueue_struct *wq = dev_to_wq(dev);
int written;
mutex_lock(&wq->mutex);
written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice);
mutex_unlock(&wq->mutex);
return written;
}
/* prepare workqueue_attrs for sysfs store operations */
static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq)
{
struct workqueue_attrs *attrs;
lockdep_assert_held(&wq_pool_mutex);
attrs = alloc_workqueue_attrs();
if (!attrs)
return NULL;
copy_workqueue_attrs(attrs, wq->unbound_attrs);
return attrs;
}
static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct workqueue_struct *wq = dev_to_wq(dev);
struct workqueue_attrs *attrs;
int ret = -ENOMEM;
apply_wqattrs_lock();
attrs = wq_sysfs_prep_attrs(wq);
if (!attrs)
goto out_unlock;
if (sscanf(buf, "%d", &attrs->nice) == 1 &&
attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE)
ret = apply_workqueue_attrs_locked(wq, attrs);
else
ret = -EINVAL;
out_unlock:
apply_wqattrs_unlock();
free_workqueue_attrs(attrs);
return ret ?: count;
}
static ssize_t wq_cpumask_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct workqueue_struct *wq = dev_to_wq(dev);
int written;
mutex_lock(&wq->mutex);
written = scnprintf(buf, PAGE_SIZE, "%*pb\n",
cpumask_pr_args(wq->unbound_attrs->cpumask));
mutex_unlock(&wq->mutex);
return written;
}
static ssize_t wq_cpumask_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct workqueue_struct *wq = dev_to_wq(dev);
struct workqueue_attrs *attrs;
int ret = -ENOMEM;
apply_wqattrs_lock();
attrs = wq_sysfs_prep_attrs(wq);
if (!attrs)
goto out_unlock;
ret = cpumask_parse(buf, attrs->cpumask);
if (!ret)
ret = apply_workqueue_attrs_locked(wq, attrs);
out_unlock:
apply_wqattrs_unlock();
free_workqueue_attrs(attrs);
return ret ?: count;
}
static ssize_t wq_numa_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct workqueue_struct *wq = dev_to_wq(dev);
int written;
mutex_lock(&wq->mutex);
written = scnprintf(buf, PAGE_SIZE, "%d\n",
!wq->unbound_attrs->no_numa);
mutex_unlock(&wq->mutex);
return written;
}
static ssize_t wq_numa_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct workqueue_struct *wq = dev_to_wq(dev);
struct workqueue_attrs *attrs;
int v, ret = -ENOMEM;
apply_wqattrs_lock();
attrs = wq_sysfs_prep_attrs(wq);
if (!attrs)
goto out_unlock;
ret = -EINVAL;
if (sscanf(buf, "%d", &v) == 1) {
attrs->no_numa = !v;
ret = apply_workqueue_attrs_locked(wq, attrs);
}
out_unlock:
apply_wqattrs_unlock();
free_workqueue_attrs(attrs);
return ret ?: count;
}
static struct device_attribute wq_sysfs_unbound_attrs[] = {
__ATTR(pool_ids, 0444, wq_pool_ids_show, NULL),
__ATTR(nice, 0644, wq_nice_show, wq_nice_store),
__ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store),
__ATTR(numa, 0644, wq_numa_show, wq_numa_store),
__ATTR_NULL,
};
static struct bus_type wq_subsys = {
.name = "workqueue",
.dev_groups = wq_sysfs_groups,
};
static ssize_t wq_unbound_cpumask_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
int written;
mutex_lock(&wq_pool_mutex);
written = scnprintf(buf, PAGE_SIZE, "%*pb\n",
cpumask_pr_args(wq_unbound_cpumask));
mutex_unlock(&wq_pool_mutex);
return written;
}
static ssize_t wq_unbound_cpumask_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
cpumask_var_t cpumask;
int ret;
if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL))
return -ENOMEM;
ret = cpumask_parse(buf, cpumask);
if (!ret)
ret = workqueue_set_unbound_cpumask(cpumask);
free_cpumask_var(cpumask);
return ret ? ret : count;
}
static struct device_attribute wq_sysfs_cpumask_attr =
__ATTR(cpumask, 0644, wq_unbound_cpumask_show,
wq_unbound_cpumask_store);
static int __init wq_sysfs_init(void)
{
int err;
err = subsys_virtual_register(&wq_subsys, NULL);
if (err)
return err;
return device_create_file(wq_subsys.dev_root, &wq_sysfs_cpumask_attr);
}
core_initcall(wq_sysfs_init);
static void wq_device_release(struct device *dev)
{
struct wq_device *wq_dev = container_of(dev, struct wq_device, dev);
kfree(wq_dev);
}
/**
* workqueue_sysfs_register - make a workqueue visible in sysfs
* @wq: the workqueue to register
*
* Expose @wq in sysfs under /sys/bus/workqueue/devices.
* alloc_workqueue*() automatically calls this function if WQ_SYSFS is set
* which is the preferred method.
*
* Workqueue user should use this function directly iff it wants to apply
* workqueue_attrs before making the workqueue visible in sysfs; otherwise,
* apply_workqueue_attrs() may race against userland updating the
* attributes.
*
* Return: 0 on success, -errno on failure.
*/
int workqueue_sysfs_register(struct workqueue_struct *wq)
{
struct wq_device *wq_dev;
int ret;
/*
* Adjusting max_active or creating new pwqs by applying
* attributes breaks ordering guarantee. Disallow exposing ordered
* workqueues.
*/
if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
return -EINVAL;
wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL);
if (!wq_dev)
return -ENOMEM;
wq_dev->wq = wq;
wq_dev->dev.bus = &wq_subsys;
wq_dev->dev.release = wq_device_release;
dev_set_name(&wq_dev->dev, "%s", wq->name);
/*
* unbound_attrs are created separately. Suppress uevent until
* everything is ready.
*/
dev_set_uevent_suppress(&wq_dev->dev, true);
ret = device_register(&wq_dev->dev);
if (ret) {
put_device(&wq_dev->dev);
wq->wq_dev = NULL;
return ret;
}
if (wq->flags & WQ_UNBOUND) {
struct device_attribute *attr;
for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) {
ret = device_create_file(&wq_dev->dev, attr);
if (ret) {
device_unregister(&wq_dev->dev);
wq->wq_dev = NULL;
return ret;
}
}
}
dev_set_uevent_suppress(&wq_dev->dev, false);
kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD);
return 0;
}
/**
* workqueue_sysfs_unregister - undo workqueue_sysfs_register()
* @wq: the workqueue to unregister
*
* If @wq is registered to sysfs by workqueue_sysfs_register(), unregister.
*/
static void workqueue_sysfs_unregister(struct workqueue_struct *wq)
{
struct wq_device *wq_dev = wq->wq_dev;
if (!wq->wq_dev)
return;
wq->wq_dev = NULL;
device_unregister(&wq_dev->dev);
}
#else /* CONFIG_SYSFS */
static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { }
#endif /* CONFIG_SYSFS */
/*
* 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 = 30;
static struct timer_list wq_watchdog_timer;
static unsigned long wq_watchdog_touched = INITIAL_JIFFIES;
static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES;
static void wq_watchdog_reset_touched(void)
{
int cpu;
wq_watchdog_touched = jiffies;
for_each_possible_cpu(cpu)
per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies;
}
static void wq_watchdog_timer_fn(struct timer_list *unused)
{
unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ;
bool lockup_detected = false;
struct worker_pool *pool;
int pi;
if (!thresh)
return;
rcu_read_lock();
for_each_pool(pool, pi) {
unsigned long pool_ts, touched, ts;
if (list_empty(&pool->worklist))
continue;
/* get the latest of pool and touched timestamps */
pool_ts = READ_ONCE(pool->watchdog_ts);
touched = READ_ONCE(wq_watchdog_touched);
if (time_after(pool_ts, touched))
ts = pool_ts;
else
ts = touched;
if (pool->cpu >= 0) {
unsigned long cpu_touched =
READ_ONCE(per_cpu(wq_watchdog_touched_cpu,
pool->cpu));
if (time_after(cpu_touched, ts))
ts = cpu_touched;
}
/* did we stall? */
if (time_after(jiffies, ts + thresh)) {
lockup_detected = true;
pr_emerg("BUG: workqueue lockup - pool");
pr_cont_pool_info(pool);
pr_cont(" stuck for %us!\n",
jiffies_to_msecs(jiffies - pool_ts) / 1000);
}
}
rcu_read_unlock();
if (lockup_detected)
show_workqueue_state();
wq_watchdog_reset_touched();
mod_timer(&wq_watchdog_timer, jiffies + thresh);
}
notrace void wq_watchdog_touch(int cpu)
{
if (cpu >= 0)
per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies;
else
wq_watchdog_touched = jiffies;
}
static void wq_watchdog_set_thresh(unsigned long thresh)
{
wq_watchdog_thresh = 0;
del_timer_sync(&wq_watchdog_timer);
if (thresh) {
wq_watchdog_thresh = thresh;
wq_watchdog_reset_touched();
mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ);
}
}
static int wq_watchdog_param_set_thresh(const char *val,
const struct kernel_param *kp)
{
unsigned long thresh;
int ret;
ret = kstrtoul(val, 0, &thresh);
if (ret)
return ret;
if (system_wq)
wq_watchdog_set_thresh(thresh);
else
wq_watchdog_thresh = thresh;
return 0;
}
static const struct kernel_param_ops wq_watchdog_thresh_ops = {
.set = wq_watchdog_param_set_thresh,
.get = param_get_ulong,
};
module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh,
0644);
static void wq_watchdog_init(void)
{
timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE);
wq_watchdog_set_thresh(wq_watchdog_thresh);
}
#else /* CONFIG_WQ_WATCHDOG */
static inline void wq_watchdog_init(void) { }
#endif /* CONFIG_WQ_WATCHDOG */
static void __init wq_numa_init(void)
{
cpumask_var_t *tbl;
int node, cpu;
if (num_possible_nodes() <= 1)
return;
if (wq_disable_numa) {
pr_info("workqueue: NUMA affinity support disabled\n");
return;
}
wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs();
BUG_ON(!wq_update_unbound_numa_attrs_buf);
/*
* We want masks of possible CPUs of each node which isn't readily
* available. Build one from cpu_to_node() which should have been
* fully initialized by now.
*/
tbl = kcalloc(nr_node_ids, sizeof(tbl[0]), GFP_KERNEL);
BUG_ON(!tbl);
for_each_node(node)
BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
node_online(node) ? node : NUMA_NO_NODE));
for_each_possible_cpu(cpu) {
node = cpu_to_node(cpu);
if (WARN_ON(node == NUMA_NO_NODE)) {
pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu);
/* happens iff arch is bonkers, let's just proceed */
return;
}
cpumask_set_cpu(cpu, tbl[node]);
}
wq_numa_possible_cpumask = tbl;
wq_numa_enabled = true;
}
/**
* workqueue_init_early - early init for workqueue subsystem
*
* This is the first half of two-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.
*/
int __init workqueue_init_early(void)
{
int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
int hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ;
int i, cpu;
WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL));
cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(hk_flags));
pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
/* initialize CPU pools */
for_each_possible_cpu(cpu) {
struct worker_pool *pool;
i = 0;
for_each_cpu_worker_pool(pool, cpu) {
BUG_ON(init_worker_pool(pool));
pool->cpu = cpu;
cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu));
pool->attrs->nice = std_nice[i++];
pool->node = cpu_to_node(cpu);
/* alloc pool ID */
mutex_lock(&wq_pool_mutex);
BUG_ON(worker_pool_assign_id(pool));
mutex_unlock(&wq_pool_mutex);
}
}
/* create default unbound and ordered wq attrs */
for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
struct workqueue_attrs *attrs;
BUG_ON(!(attrs = alloc_workqueue_attrs()));
attrs->nice = std_nice[i];
unbound_std_wq_attrs[i] = attrs;
/*
* An ordered wq should have only one pwq as ordering is
* guaranteed by max_active which is enforced by pwqs.
* Turn off NUMA so that dfl_pwq is used for all nodes.
*/
BUG_ON(!(attrs = alloc_workqueue_attrs()));
attrs->nice = std_nice[i];
attrs->no_numa = true;
ordered_wq_attrs[i] = attrs;
}
system_wq = alloc_workqueue("events", 0, 0);
system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0);
system_long_wq = alloc_workqueue("events_long", 0, 0);
system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
WQ_UNBOUND_MAX_ACTIVE);
system_freezable_wq = alloc_workqueue("events_freezable",
WQ_FREEZABLE, 0);
system_power_efficient_wq = alloc_workqueue("events_power_efficient",
WQ_POWER_EFFICIENT, 0);
system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient",
WQ_FREEZABLE | WQ_POWER_EFFICIENT,
0);
BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
!system_unbound_wq || !system_freezable_wq ||
!system_power_efficient_wq ||
!system_freezable_power_efficient_wq);
return 0;
}
/**
* workqueue_init - bring workqueue subsystem fully online
*
* This is the latter half of two-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.
*/
int __init workqueue_init(void)
{
struct workqueue_struct *wq;
struct worker_pool *pool;
int cpu, bkt;
/*
* It'd be simpler to initialize NUMA in workqueue_init_early() but
* CPU to node mapping may not be available that early on some
* archs such as power and arm64. As per-cpu pools created
* previously could be missing node hint and unbound pools NUMA
* affinity, fix them up.
*
* Also, while iterating workqueues, create rescuers if requested.
*/
wq_numa_init();
mutex_lock(&wq_pool_mutex);
for_each_possible_cpu(cpu) {
for_each_cpu_worker_pool(pool, cpu) {
pool->node = cpu_to_node(cpu);
}
}
list_for_each_entry(wq, &workqueues, list) {
wq_update_unbound_numa(wq, smp_processor_id(), true);
WARN(init_rescuer(wq),
"workqueue: failed to create early rescuer for %s",
wq->name);
}
mutex_unlock(&wq_pool_mutex);
/* create the initial workers */
for_each_online_cpu(cpu) {
for_each_cpu_worker_pool(pool, cpu) {
pool->flags &= ~POOL_DISASSOCIATED;
BUG_ON(!create_worker(pool));
}
}
hash_for_each(unbound_pool_hash, bkt, pool, hash_node)
BUG_ON(!create_worker(pool));
wq_online = true;
wq_watchdog_init();
return 0;
}
Reference in New Issue View Git Blame Copy Permalink