v4.14.292-rt138-rc1 stable review patch.
If anyone has any objections, please let me know.
-----------
The recent changes to the random() code require that the workqueue code
in v4.14-rt is updated. Given the code proximity, v4.19.255-rt113 was
the selected target.
Included in this patch:
- convert struct worker_pool lock and wq_mayday_lock to raw_spinlock_t
- backport swait_event_lock_irq() macros
- misc workqueue changes from v4.19.255-rt113
Files touched:
include/linux/swait.h
include/linux/workqueue.h
kernel/workqueue.c
Signed-off-by: Luis Claudio R. Goncalves <lgoncalv@xxxxxxxxxx>
---
Notes:
This kernel works fine (tested with LTP and stress-ng, both with and
without lockdep enabled. But on poweroff or reboot there are tree
backtraces coming from the commit listed below, part of the all-in-one
"workqueue: update code to match v4.19.255-rt113" patch:
8c37f7c23c02f workqueue: Try to catch flush_work() without INIT_WORK().
This commits translates to the following statement in __flush_work(),
from kernel/workqueue.c:
if (WARN_ON(!work->func))
return false;
Should I remove this change? The fix requires a good amount of changes
and takes us farther away from stock v4.14 in a dangerous way.
And an even more important question, is this all-in-one patch
acceptable? Should I backport all the individual commits instead?
include/linux/swait.h | 14 +
include/linux/workqueue.h | 10 +-
kernel/workqueue.c | 623 ++++++++++++++++++++------------------
3 files changed, 338 insertions(+), 309 deletions(-)
diff --git a/include/linux/swait.h b/include/linux/swait.h
index 853f3e61a9f4c..d41917e222d1b 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -286,4 +286,18 @@ do { \
__ret; \
})
+#define __swait_event_lock_irq(wq, condition, lock, cmd) \
+ ___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \
+ raw_spin_unlock_irq(&lock); \
+ cmd; \
+ schedule(); \
+ raw_spin_lock_irq(&lock))
+
+#define swait_event_lock_irq(wq_head, condition, lock) \
+ do { \
+ if (condition) \
+ break; \
+ __swait_event_lock_irq(wq_head, condition, lock, ); \
+ } while (0)
+
#endif /* _LINUX_SWAIT_H */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 1c527abb1ae58..bbb14d6b6ba38 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -219,7 +219,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; }
\
__init_work((_work), _onstack); \
(_work)->data = (atomic_long_t) WORK_DATA_INIT(); \
- lockdep_init_map(&(_work)->lockdep_map, #_work, &__key, 0); \
+ lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, &__key, 0); \
INIT_LIST_HEAD(&(_work)->entry); \
(_work)->func = (_func); \
} while (0)
@@ -399,7 +399,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
static struct lock_class_key __key; \
const char *__lock_name; \
\
- __lock_name = #fmt#args; \
+ __lock_name = "(wq_completion)"#fmt#args; \
\
__alloc_workqueue_key((fmt), (flags), (max_active), \
&__key, __lock_name, ##args); \
@@ -437,10 +437,6 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
extern void destroy_workqueue(struct workqueue_struct *wq);
-struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask);
-void free_workqueue_attrs(struct workqueue_attrs *attrs);
-int apply_workqueue_attrs(struct workqueue_struct *wq,
- const struct workqueue_attrs *attrs);
int workqueue_set_unbound_cpumask(cpumask_var_t cpumask);
extern bool queue_work_on(int cpu, struct workqueue_struct *wq,
@@ -458,7 +454,6 @@ extern int schedule_on_each_cpu(work_func_t func);
int execute_in_process_context(work_func_t fn, struct execute_work *);
extern bool flush_work(struct work_struct *work);
-extern bool cancel_work(struct work_struct *work);
extern bool cancel_work_sync(struct work_struct *work);
extern bool flush_delayed_work(struct delayed_work *dwork);
@@ -474,6 +469,7 @@ extern unsigned int work_busy(struct work_struct *work);
extern __printf(1, 2) void set_worker_desc(const char *fmt, ...);
extern void print_worker_info(const char *log_lvl, struct task_struct *task);
extern void show_workqueue_state(void);
+extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task);
/**
* queue_work - queue work on a workqueue
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index bc526b793e838..d52953d01ba29 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -38,7 +38,6 @@
#include <linux/hardirq.h>
#include <linux/mempolicy.h>
#include <linux/freezer.h>
-#include <linux/kallsyms.h>
#include <linux/debug_locks.h>
#include <linux/lockdep.h>
#include <linux/idr.h>
@@ -49,8 +48,6 @@
#include <linux/moduleparam.h>
#include <linux/uaccess.h>
#include <linux/nmi.h>
-#include <linux/locallock.h>
-#include <linux/delay.h>
#include <linux/kvm_para.h>
#include "workqueue_internal.h"
@@ -69,7 +66,7 @@ enum {
* be executing on any CPU. The pool behaves as an unbound one.
*
* Note that DISASSOCIATED should be flipped only while holding
- * attach_mutex to avoid changing binding state while
+ * wq_pool_attach_mutex to avoid changing binding state while
* worker_attach_to_pool() is in progress.
*/
POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */
@@ -126,12 +123,7 @@ enum {
* cpu or grabbing pool->lock is enough for read access. If
* POOL_DISASSOCIATED is set, it's identical to L.
*
- * On RT we need the extra protection via rt_lock_idle_list() for
- * the list manipulations against read access from
- * wq_worker_sleeping(). All other places are nicely serialized via
- * pool->lock.
- *
- * A: pool->attach_mutex protected.
+ * A: wq_pool_attach_mutex protected.
*
* PL: wq_pool_mutex protected.
*
@@ -152,7 +144,7 @@ enum {
/* struct worker is defined in workqueue_internal.h */
struct worker_pool {
- spinlock_t lock; /* the pool lock */
+ raw_spinlock_t lock; /* the pool lock */
int cpu; /* I: the associated cpu */
int node; /* I: the associated node ID */
int id; /* I: pool ID */
@@ -161,10 +153,9 @@ struct worker_pool {
unsigned long watchdog_ts; /* L: watchdog timestamp */
struct list_head worklist; /* L: list of pending works */
- int nr_workers; /* L: total number of workers */
- /* nr_idle includes the ones off idle_list for rebinding */
- int nr_idle; /* L: currently idle ones */
+ 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 */
@@ -174,9 +165,7 @@ struct worker_pool {
DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER);
/* L: hash of busy workers */
- /* see manage_workers() for details on the two manager mutexes */
struct worker *manager; /* L: purely informational */
- struct mutex attach_mutex; /* attach/detach exclusion */
struct list_head workers; /* A: attached workers */
struct completion *detach_completion; /* all workers detached */
@@ -307,8 +296,9 @@ static bool wq_numa_enabled; /* unbound NUMA affinity enabled */
static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf;
static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */
-static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */
-static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */
+static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */
+static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */
+static DECLARE_SWAIT_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? */
@@ -360,8 +350,6 @@ 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 DEFINE_LOCAL_IRQ_LOCK(pendingb_lock);
-
static int worker_thread(void *__worker);
static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
@@ -411,14 +399,14 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
* @worker: iteration cursor
* @pool: worker_pool to iterate workers of
*
- * This must be called with @pool->attach_mutex.
+ * 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(&pool->attach_mutex); false; })) { } \
+ if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \
else
/**
@@ -438,31 +426,6 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \
else
-#ifdef CONFIG_PREEMPT_RT_BASE
-static inline void rt_lock_idle_list(struct worker_pool *pool)
-{
- preempt_disable();
-}
-static inline void rt_unlock_idle_list(struct worker_pool *pool)
-{
- preempt_enable();
-}
-static inline void sched_lock_idle_list(struct worker_pool *pool) { }
-static inline void sched_unlock_idle_list(struct worker_pool *pool) { }
-#else
-static inline void rt_lock_idle_list(struct worker_pool *pool) { }
-static inline void rt_unlock_idle_list(struct worker_pool *pool) { }
-static inline void sched_lock_idle_list(struct worker_pool *pool)
-{
- spin_lock_irq(&pool->lock);
-}
-static inline void sched_unlock_idle_list(struct worker_pool *pool)
-{
- spin_unlock_irq(&pool->lock);
-}
-#endif
-
-
#ifdef CONFIG_DEBUG_OBJECTS_WORK
static struct debug_obj_descr work_debug_descr;
@@ -865,20 +828,14 @@ static struct worker *first_idle_worker(struct worker_pool *pool)
* Wake up the first idle worker of @pool.
*
* CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
*/
static void wake_up_worker(struct worker_pool *pool)
{
- struct worker *worker;
-
- rt_lock_idle_list(pool);
-
- worker = first_idle_worker(pool);
+ struct worker *worker = first_idle_worker(pool);
if (likely(worker))
wake_up_process(worker->task);
-
- rt_unlock_idle_list(pool);
}
/**
@@ -907,7 +864,7 @@ void wq_worker_running(struct task_struct *task)
*/
void wq_worker_sleeping(struct task_struct *task)
{
- struct worker *worker = kthread_data(task);
+ struct worker *next, *worker = kthread_data(task);
struct worker_pool *pool;
/*
@@ -924,18 +881,26 @@ void wq_worker_sleeping(struct task_struct *task)
return;
worker->sleeping = 1;
+ raw_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)) {
- sched_lock_idle_list(pool);
- wake_up_worker(pool);
- sched_unlock_idle_list(pool);
+ next = first_idle_worker(pool);
+ if (next)
+ wake_up_process(next->task);
}
+ raw_spin_unlock_irq(&pool->lock);
}
/**
@@ -946,7 +911,7 @@ void wq_worker_sleeping(struct task_struct *task)
* Set @flags in @worker->flags and adjust nr_running accordingly.
*
* CONTEXT:
- * spin_lock_irq(pool->lock)
+ * raw_spin_lock_irq(pool->lock)
*/
static inline void worker_set_flags(struct worker *worker, unsigned int flags)
{
@@ -971,7 +936,7 @@ static inline void worker_set_flags(struct worker *worker, unsigned int flags)
* Clear @flags in @worker->flags and adjust nr_running accordingly.
*
* CONTEXT:
- * spin_lock_irq(pool->lock)
+ * raw_spin_lock_irq(pool->lock)
*/
static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
{
@@ -1019,7 +984,7 @@ static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
* actually occurs, it should be easy to locate the culprit work function.
*
* CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
*
* Return:
* Pointer to worker which is executing @work if found, %NULL
@@ -1054,7 +1019,7 @@ static struct worker *find_worker_executing_work(struct worker_pool *pool,
* nested inside outer list_for_each_entry_safe().
*
* CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
*/
static void move_linked_works(struct work_struct *work, struct list_head *head,
struct work_struct **nextp)
@@ -1132,11 +1097,9 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq)
* As both pwqs and pools are RCU protected, the
* following lock operations are safe.
*/
- rcu_read_lock();
- local_spin_lock_irq(pendingb_lock, &pwq->pool->lock);
+ raw_spin_lock_irq(&pwq->pool->lock);
put_pwq(pwq);
- local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock);
- rcu_read_unlock();
+ raw_spin_unlock_irq(&pwq->pool->lock);
}
}
@@ -1169,7 +1132,7 @@ static void pwq_activate_first_delayed(struct pool_workqueue *pwq)
* decrement nr_in_flight of its pwq and handle workqueue flushing.
*
* CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
*/
static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color)
{
@@ -1240,7 +1203,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
struct worker_pool *pool;
struct pool_workqueue *pwq;
- local_lock_irqsave(pendingb_lock, *flags);
+ local_irq_save(*flags);
/* try to steal the timer if it exists */
if (is_dwork) {
@@ -1268,7 +1231,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
if (!pool)
goto fail;
- spin_lock(&pool->lock);
+ raw_spin_lock(&pool->lock);
/*
* work->data is guaranteed to point to pwq only while the work
* item is queued on pwq->wq, and both updating work->data to point
@@ -1297,17 +1260,17 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
/* work->data points to pwq iff queued, point to pool */
set_work_pool_and_keep_pending(work, pool->id);
- spin_unlock(&pool->lock);
+ raw_spin_unlock(&pool->lock);
rcu_read_unlock();
return 1;
}
- spin_unlock(&pool->lock);
+ raw_spin_unlock(&pool->lock);
fail:
rcu_read_unlock();
- local_unlock_irqrestore(pendingb_lock, *flags);
+ local_irq_restore(*flags);
if (work_is_canceling(work))
return -ENOENT;
- cpu_chill();
+ cpu_relax();
return -EAGAIN;
}
@@ -1322,7 +1285,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
* work_struct flags.
*
* CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
*/
static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
struct list_head *head, unsigned int extra_flags)
@@ -1409,7 +1372,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
* queued or lose PENDING. Grabbing PENDING and queueing should
* happen with IRQ disabled.
*/
- WARN_ON_ONCE_NONRT(!irqs_disabled());
+ WARN_ON_ONCE(!irqs_disabled());
/* if draining, only works from the same workqueue are allowed */
@@ -1438,7 +1401,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
if (last_pool && last_pool != pwq->pool) {
struct worker *worker;
- spin_lock(&last_pool->lock);
+ raw_spin_lock(&last_pool->lock);
worker = find_worker_executing_work(last_pool, work);
@@ -1446,11 +1409,11 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
pwq = worker->current_pwq;
} else {
/* meh... not running there, queue here */
- spin_unlock(&last_pool->lock);
- spin_lock(&pwq->pool->lock);
+ raw_spin_unlock(&last_pool->lock);
+ raw_spin_lock(&pwq->pool->lock);
}
} else {
- spin_lock(&pwq->pool->lock);
+ raw_spin_lock(&pwq->pool->lock);
}
/*
@@ -1463,7 +1426,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
*/
if (unlikely(!pwq->refcnt)) {
if (wq->flags & WQ_UNBOUND) {
- spin_unlock(&pwq->pool->lock);
+ raw_spin_unlock(&pwq->pool->lock);
cpu_relax();
goto retry;
}
@@ -1496,7 +1459,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
insert_work(pwq, work, worklist, work_flags);
out:
- spin_unlock(&pwq->pool->lock);
+ raw_spin_unlock(&pwq->pool->lock);
rcu_read_unlock();
}
@@ -1517,14 +1480,14 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq,
bool ret = false;
unsigned long flags;
- local_lock_irqsave(pendingb_lock,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_unlock_irqrestore(pendingb_lock, flags);
+ local_irq_restore(flags);
return ret;
}
EXPORT_SYMBOL(queue_work_on);
@@ -1532,12 +1495,11 @@ EXPORT_SYMBOL(queue_work_on);
void delayed_work_timer_fn(unsigned long __data)
{
struct delayed_work *dwork = (struct delayed_work *)__data;
+ unsigned long flags;
- /* XXX */
- /* local_lock(pendingb_lock); */
- /* should have been called from irqsafe timer with irq already off */
+ local_irq_save(flags);
__queue_work(dwork->cpu, dwork->wq, &dwork->work);
- /* local_unlock(pendingb_lock); */
+ local_irq_restore(flags);
}
EXPORT_SYMBOL(delayed_work_timer_fn);
@@ -1593,14 +1555,14 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
unsigned long flags;
/* read the comment in __queue_work() */
- local_lock_irqsave(pendingb_lock, flags);
+ 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_unlock_irqrestore(pendingb_lock, flags);
+ local_irq_restore(flags);
return ret;
}
EXPORT_SYMBOL(queue_delayed_work_on);
@@ -1635,7 +1597,7 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
if (likely(ret >= 0)) {
__queue_delayed_work(cpu, wq, dwork, delay);
- local_unlock_irqrestore(pendingb_lock, flags);
+ local_irq_restore(flags);
}
/* -ENOENT from try_to_grab_pending() becomes %true */
@@ -1651,7 +1613,7 @@ EXPORT_SYMBOL_GPL(mod_delayed_work_on);
* necessary.
*
* LOCKING:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
*/
static void worker_enter_idle(struct worker *worker)
{
@@ -1668,15 +1630,13 @@ static void worker_enter_idle(struct worker *worker)
worker->last_active = jiffies;
/* idle_list is LIFO */
- rt_lock_idle_list(pool);
list_add(&worker->entry, &pool->idle_list);
- rt_unlock_idle_list(pool);
if (too_many_workers(pool) && !timer_pending(&pool->idle_timer))
mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT);
/*
- * Sanity check nr_running. Because wq_unbind_fn() releases
+ * 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.
@@ -1693,7 +1653,7 @@ static void worker_enter_idle(struct worker *worker)
* @worker is leaving idle state. Update stats.
*
* LOCKING:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
*/
static void worker_leave_idle(struct worker *worker)
{
@@ -1703,9 +1663,7 @@ static void worker_leave_idle(struct worker *worker)
return;
worker_clr_flags(worker, WORKER_IDLE);
pool->nr_idle--;
- rt_lock_idle_list(pool);
list_del_init(&worker->entry);
- rt_unlock_idle_list(pool);
}
static struct worker *alloc_worker(int node)
@@ -1735,46 +1693,46 @@ static struct worker *alloc_worker(int node)
static void worker_attach_to_pool(struct worker *worker,
struct worker_pool *pool)
{
- mutex_lock(&pool->attach_mutex);
+ 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 pool->attach_mutex ensures %POOL_DISASSOCIATED remains
- * stable across this function. See the comments above the
- * flag definition for details.
+ * 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;
+ if (worker->rescue_wq)
+ set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
+
list_add_tail(&worker->node, &pool->workers);
+ worker->pool = pool;
- mutex_unlock(&pool->attach_mutex);
+ mutex_unlock(&wq_pool_attach_mutex);
}
/**
* worker_detach_from_pool() - detach a worker from its pool
* @worker: worker which is attached to its pool
- * @pool: the pool @worker is attached to
*
* Undo the attaching which had been done in worker_attach_to_pool(). The
* caller worker shouldn't access to the pool after detached except it has
* other reference to the pool.
*/
-static void worker_detach_from_pool(struct worker *worker,
- struct worker_pool *pool)
+static void worker_detach_from_pool(struct worker *worker)
{
+ struct worker_pool *pool = worker->pool;
struct completion *detach_completion = NULL;
- mutex_lock(&pool->attach_mutex);
+ 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(&pool->attach_mutex);
+ mutex_unlock(&wq_pool_attach_mutex);
/* clear leftover flags without pool->lock after it is detached */
worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND);
@@ -1810,7 +1768,6 @@ static struct worker *create_worker(struct worker_pool *pool)
if (!worker)
goto fail;
- worker->pool = pool;
worker->id = id;
if (pool->cpu >= 0)
@@ -1831,11 +1788,11 @@ static struct worker *create_worker(struct worker_pool *pool)
worker_attach_to_pool(worker, pool);
/* start the newly created worker */
- spin_lock_irq(&pool->lock);
+ raw_spin_lock_irq(&pool->lock);
worker->pool->nr_workers++;
worker_enter_idle(worker);
wake_up_process(worker->task);
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock_irq(&pool->lock);
return worker;
@@ -1854,7 +1811,7 @@ static struct worker *create_worker(struct worker_pool *pool)
* be idle.
*
* CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
*/
static void destroy_worker(struct worker *worker)
{
@@ -1871,9 +1828,7 @@ static void destroy_worker(struct worker *worker)
pool->nr_workers--;
pool->nr_idle--;
- rt_lock_idle_list(pool);
list_del_init(&worker->entry);
- rt_unlock_idle_list(pool);
worker->flags |= WORKER_DIE;
wake_up_process(worker->task);
}
@@ -1882,7 +1837,7 @@ static void idle_worker_timeout(unsigned long __pool)
{
struct worker_pool *pool = (void *)__pool;
- spin_lock_irq(&pool->lock);
+ raw_spin_lock_irq(&pool->lock);
while (too_many_workers(pool)) {
struct worker *worker;
@@ -1900,7 +1855,7 @@ static void idle_worker_timeout(unsigned long __pool)
destroy_worker(worker);
}
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock_irq(&pool->lock);
}
static void send_mayday(struct work_struct *work)
@@ -1931,8 +1886,8 @@ static void pool_mayday_timeout(unsigned long __pool)
struct worker_pool *pool = (void *)__pool;
struct work_struct *work;
- spin_lock_irq(&pool->lock);
- spin_lock(&wq_mayday_lock); /* for wq->maydays */
+ raw_spin_lock_irq(&pool->lock);
+ raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */
if (need_to_create_worker(pool)) {
/*
@@ -1945,8 +1900,8 @@ static void pool_mayday_timeout(unsigned long __pool)
send_mayday(work);
}
- spin_unlock(&wq_mayday_lock);
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock(&wq_mayday_lock);
+ raw_spin_unlock_irq(&pool->lock);
mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL);
}
@@ -1965,7 +1920,7 @@ static void pool_mayday_timeout(unsigned long __pool)
* may_start_working() %true.
*
* LOCKING:
- * spin_lock_irq(pool->lock) which may be released and regrabbed
+ * raw_spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Does GFP_KERNEL allocations. Called only from
* manager.
*/
@@ -1974,7 +1929,7 @@ __releases(&pool->lock)
__acquires(&pool->lock)
{
restart:
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock_irq(&pool->lock);
/* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */
mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT);
@@ -1990,7 +1945,7 @@ __acquires(&pool->lock)
}
del_timer_sync(&pool->mayday_timer);
- spin_lock_irq(&pool->lock);
+ raw_spin_lock_irq(&pool->lock);
/*
* This is necessary even after a new worker was just successfully
* created as @pool->lock was dropped and the new worker might have
@@ -2013,7 +1968,7 @@ __acquires(&pool->lock)
* and may_start_working() is true.
*
* CONTEXT:
- * spin_lock_irq(pool->lock) which may be released and regrabbed
+ * raw_spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Does GFP_KERNEL allocations.
*
* Return:
@@ -2036,7 +1991,7 @@ static bool manage_workers(struct worker *worker)
pool->manager = NULL;
pool->flags &= ~POOL_MANAGER_ACTIVE;
- wake_up(&wq_manager_wait);
+ swake_up(&wq_manager_wait);
return true;
}
@@ -2052,7 +2007,7 @@ static bool manage_workers(struct worker *worker)
* call this function to process a work.
*
* CONTEXT:
- * spin_lock_irq(pool->lock) which is released and regrabbed.
+ * raw_spin_lock_irq(pool->lock) which is released and regrabbed.
*/
static void process_one_work(struct worker *worker, struct work_struct *work)
__releases(&pool->lock)
@@ -2099,6 +2054,12 @@ __acquires(&pool->lock)
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);
/*
@@ -2128,7 +2089,7 @@ __acquires(&pool->lock)
*/
set_work_pool_and_clear_pending(work, pool->id);
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock_irq(&pool->lock);
lock_map_acquire(&pwq->wq->lockdep_map);
lock_map_acquire(&lockdep_map);
@@ -2181,9 +2142,9 @@ __acquires(&pool->lock)
* stop_machine. At the same time, report a quiescent RCU state so
* the same condition doesn't freeze RCU.
*/
- cond_resched_rcu_qs();
+ cond_resched();
- spin_lock_irq(&pool->lock);
+ raw_spin_lock_irq(&pool->lock);
/* clear cpu intensive status */
if (unlikely(cpu_intensive))
@@ -2194,7 +2155,6 @@ __acquires(&pool->lock)
worker->current_work = NULL;
worker->current_func = NULL;
worker->current_pwq = NULL;
- worker->desc_valid = false;
pwq_dec_nr_in_flight(pwq, work_color);
}
@@ -2207,7 +2167,7 @@ __acquires(&pool->lock)
* fetches a work from the top and executes it.
*
* CONTEXT:
- * spin_lock_irq(pool->lock) which may be released and regrabbed
+ * raw_spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times.
*/
static void process_scheduled_works(struct worker *worker)
@@ -2219,6 +2179,16 @@ static void process_scheduled_works(struct worker *worker)
}
}
+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
@@ -2237,19 +2207,19 @@ static int worker_thread(void *__worker)
struct worker_pool *pool = worker->pool;
/* tell the scheduler that this is a workqueue worker */
- worker->task->flags |= PF_WQ_WORKER;
+ set_pf_worker(true);
woke_up:
- spin_lock_irq(&pool->lock);
+ raw_spin_lock_irq(&pool->lock);
/* am I supposed to die? */
if (unlikely(worker->flags & WORKER_DIE)) {
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock_irq(&pool->lock);
WARN_ON_ONCE(!list_empty(&worker->entry));
- worker->task->flags &= ~PF_WQ_WORKER;
+ set_pf_worker(false);
set_task_comm(worker->task, "kworker/dying");
ida_simple_remove(&pool->worker_ida, worker->id);
- worker_detach_from_pool(worker, pool);
+ worker_detach_from_pool(worker);
kfree(worker);
return 0;
}
@@ -2309,7 +2279,7 @@ static int worker_thread(void *__worker)
*/
worker_enter_idle(worker);
__set_current_state(TASK_IDLE);
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock_irq(&pool->lock);
schedule();
goto woke_up;
}
@@ -2348,7 +2318,7 @@ static int rescuer_thread(void *__rescuer)
* Mark rescuer as worker too. As WORKER_PREP is never cleared, it
* doesn't participate in concurrency management.
*/
- rescuer->task->flags |= PF_WQ_WORKER;
+ set_pf_worker(true);
repeat:
set_current_state(TASK_IDLE);
@@ -2363,7 +2333,7 @@ static int rescuer_thread(void *__rescuer)
should_stop = kthread_should_stop();
/* see whether any pwq is asking for help */
- spin_lock_irq(&wq_mayday_lock);
+ raw_spin_lock_irq(&wq_mayday_lock);
while (!list_empty(&wq->maydays)) {
struct pool_workqueue *pwq = list_first_entry(&wq->maydays,
@@ -2375,12 +2345,11 @@ static int rescuer_thread(void *__rescuer)
__set_current_state(TASK_RUNNING);
list_del_init(&pwq->mayday_node);
- spin_unlock_irq(&wq_mayday_lock);
+ raw_spin_unlock_irq(&wq_mayday_lock);
worker_attach_to_pool(rescuer, pool);
- spin_lock_irq(&pool->lock);
- rescuer->pool = pool;
+ raw_spin_lock_irq(&pool->lock);
/*
* Slurp in all works issued via this workqueue and
@@ -2409,7 +2378,7 @@ static int rescuer_thread(void *__rescuer)
* incur MAYDAY_INTERVAL delay inbetween.
*/
if (need_to_create_worker(pool)) {
- spin_lock(&wq_mayday_lock);
+ raw_spin_lock(&wq_mayday_lock);
/*
* Queue iff we aren't racing destruction
* and somebody else hasn't queued it already.
@@ -2418,7 +2387,7 @@ static int rescuer_thread(void *__rescuer)
get_pwq(pwq);
list_add_tail(&pwq->mayday_node, &wq->maydays);
}
- spin_unlock(&wq_mayday_lock);
+ raw_spin_unlock(&wq_mayday_lock);
}
}
@@ -2436,19 +2405,18 @@ static int rescuer_thread(void *__rescuer)
if (need_more_worker(pool))
wake_up_worker(pool);
- rescuer->pool = NULL;
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock_irq(&pool->lock);
- worker_detach_from_pool(rescuer, pool);
+ worker_detach_from_pool(rescuer);
- spin_lock_irq(&wq_mayday_lock);
+ raw_spin_lock_irq(&wq_mayday_lock);
}
- spin_unlock_irq(&wq_mayday_lock);
+ raw_spin_unlock_irq(&wq_mayday_lock);
if (should_stop) {
__set_current_state(TASK_RUNNING);
- rescuer->task->flags &= ~PF_WQ_WORKER;
+ set_pf_worker(false);
return 0;
}
@@ -2524,7 +2492,7 @@ static void wq_barrier_func(struct work_struct *work)
* underneath us, so we can't reliably determine pwq from @target.
*
* CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
*/
static void insert_wq_barrier(struct pool_workqueue *pwq,
struct wq_barrier *barr,
@@ -2551,6 +2519,7 @@ static void insert_wq_barrier(struct pool_workqueue *pwq,
"(complete)wq_barr::done",
target->lockdep_map.key, 1);
__init_completion(&barr->done);
+
barr->task = current;
/*
@@ -2618,7 +2587,7 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
for_each_pwq(pwq, wq) {
struct worker_pool *pool = pwq->pool;
- spin_lock_irq(&pool->lock);
+ raw_spin_lock_irq(&pool->lock);
if (flush_color >= 0) {
WARN_ON_ONCE(pwq->flush_color != -1);
@@ -2635,7 +2604,7 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
pwq->work_color = work_color;
}
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock_irq(&pool->lock);
}
if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush))
@@ -2835,9 +2804,9 @@ void drain_workqueue(struct workqueue_struct *wq)
for_each_pwq(pwq, wq) {
bool drained;
- spin_lock_irq(&pwq->pool->lock);
+ raw_spin_lock_irq(&pwq->pool->lock);
drained = !pwq->nr_active && list_empty(&pwq->delayed_works);
- spin_unlock_irq(&pwq->pool->lock);
+ raw_spin_unlock_irq(&pwq->pool->lock);
if (drained)
continue;
@@ -2857,7 +2826,8 @@ void drain_workqueue(struct workqueue_struct *wq)
}
EXPORT_SYMBOL_GPL(drain_workqueue);
-static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
+static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
+ bool from_cancel)
{
struct worker *worker = NULL;
struct worker_pool *pool;
@@ -2872,7 +2842,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
return false;
}
- spin_lock_irq(&pool->lock);
+ raw_spin_lock_irq(&pool->lock);
/* see the comment in try_to_grab_pending() with the same code */
pwq = get_work_pwq(work);
if (pwq) {
@@ -2888,7 +2858,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
check_flush_dependency(pwq->wq, work);
insert_wq_barrier(pwq, barr, work, worker);
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock_irq(&pool->lock);
/*
* Force a lock recursion deadlock when using flush_work() inside a
@@ -2899,40 +2869,35 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
* workqueues the deadlock happens when the rescuer stalls, blocking
* forward progress.
*/
- if (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer) {
+ 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);
+ raw_spin_unlock_irq(&pool->lock);
rcu_read_unlock();
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)
+static bool __flush_work(struct work_struct *work, bool from_cancel)
{
struct wq_barrier barr;
if (WARN_ON(!wq_online))
return false;
- lock_map_acquire(&work->lockdep_map);
- lock_map_release(&work->lockdep_map);
+ if (WARN_ON(!work->func))
+ return false;
- if (start_flush_work(work, &barr)) {
+ 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;
@@ -2940,6 +2905,22 @@ bool flush_work(struct work_struct *work)
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 {
@@ -2997,14 +2978,14 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
/* tell other tasks trying to grab @work to back off */
mark_work_canceling(work);
- local_unlock_irqrestore(pendingb_lock, flags);
+ local_irq_restore(flags);
/*
* This allows canceling during early boot. We know that @work
* isn't executing.
*/
if (wq_online)
- flush_work(work);
+ __flush_work(work, true);
clear_work_data(work);
@@ -3058,10 +3039,10 @@ EXPORT_SYMBOL_GPL(cancel_work_sync);
*/
bool flush_delayed_work(struct delayed_work *dwork)
{
- local_lock_irq(pendingb_lock);
+ local_irq_disable();
if (del_timer_sync(&dwork->timer))
__queue_work(dwork->cpu, dwork->wq, &dwork->work);
- local_unlock_irq(pendingb_lock);
+ local_irq_enable();
return flush_work(&dwork->work);
}
EXPORT_SYMBOL(flush_delayed_work);
@@ -3079,18 +3060,10 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork)
return false;
set_work_pool_and_clear_pending(work, get_work_pool_id(work));
- local_unlock_irqrestore(pendingb_lock, flags);
+ local_irq_restore(flags);
return ret;
}
-/*
- * See cancel_delayed_work()
- */
-bool cancel_work(struct work_struct *work)
-{
- return __cancel_work(work, false);
-}
-
/**
* cancel_delayed_work - cancel a delayed work
* @dwork: delayed_work to cancel
@@ -3197,7 +3170,7 @@ EXPORT_SYMBOL_GPL(execute_in_process_context);
*
* Undo alloc_workqueue_attrs().
*/
-void free_workqueue_attrs(struct workqueue_attrs *attrs)
+static void free_workqueue_attrs(struct workqueue_attrs *attrs)
{
if (attrs) {
free_cpumask_var(attrs->cpumask);
@@ -3207,21 +3180,20 @@ void free_workqueue_attrs(struct workqueue_attrs *attrs)
/**
* alloc_workqueue_attrs - allocate a workqueue_attrs
- * @gfp_mask: allocation mask to use
*
* Allocate a new workqueue_attrs, initialize with default settings and
* return it.
*
* Return: The allocated new workqueue_attr on success. %NULL on failure.
*/
-struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask)
+static struct workqueue_attrs *alloc_workqueue_attrs(void)
{
struct workqueue_attrs *attrs;
- attrs = kzalloc(sizeof(*attrs), gfp_mask);
+ attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
if (!attrs)
goto fail;
- if (!alloc_cpumask_var(&attrs->cpumask, gfp_mask))
+ if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL))
goto fail;
cpumask_copy(attrs->cpumask, cpu_possible_mask);
@@ -3278,7 +3250,7 @@ static bool wqattrs_equal(const struct workqueue_attrs *a,
*/
static int init_worker_pool(struct worker_pool *pool)
{
- spin_lock_init(&pool->lock);
+ raw_spin_lock_init(&pool->lock);
pool->id = -1;
pool->cpu = -1;
pool->node = NUMA_NO_NODE;
@@ -3294,7 +3266,6 @@ static int init_worker_pool(struct worker_pool *pool)
setup_timer(&pool->mayday_timer, pool_mayday_timeout,
(unsigned long)pool);
- mutex_init(&pool->attach_mutex);
INIT_LIST_HEAD(&pool->workers);
ida_init(&pool->worker_ida);
@@ -3302,7 +3273,7 @@ static int init_worker_pool(struct worker_pool *pool)
pool->refcnt = 1;
/* shouldn't fail above this point */
- pool->attrs = alloc_workqueue_attrs(GFP_KERNEL);
+ pool->attrs = alloc_workqueue_attrs();
if (!pool->attrs)
return -ENOMEM;
return 0;
@@ -3367,20 +3338,20 @@ static void put_unbound_pool(struct worker_pool *pool)
* @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,
+ raw_spin_lock_irq(&pool->lock);
+ swait_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);
+ raw_spin_unlock_irq(&pool->lock);
- mutex_lock(&pool->attach_mutex);
+ mutex_lock(&wq_pool_attach_mutex);
if (!list_empty(&pool->workers))
pool->detach_completion = &detach_completion;
- mutex_unlock(&pool->attach_mutex);
+ mutex_unlock(&wq_pool_attach_mutex);
if (pool->detach_completion)
wait_for_completion(pool->detach_completion);
@@ -3535,7 +3506,7 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
return;
/* this function can be called during early boot w/ irq disabled */
- spin_lock_irqsave(&pwq->pool->lock, flags);
+ raw_spin_lock_irqsave(&pwq->pool->lock, flags);
/*
* During [un]freezing, the caller is responsible for ensuring that
@@ -3565,7 +3536,7 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
pwq->max_active = 0;
}
- spin_unlock_irqrestore(&pwq->pool->lock, flags);
+ raw_spin_unlock_irqrestore(&pwq->pool->lock, flags);
}
/* initialize newly alloced @pwq which is associated with @wq and @pool */
@@ -3735,12 +3706,11 @@ apply_wqattrs_prepare(struct workqueue_struct *wq,
int node;
lockdep_assert_held(&wq_pool_mutex);
-
ctx = kzalloc(sizeof(*ctx) + nr_node_ids * sizeof(ctx->pwq_tbl[0]),
GFP_KERNEL);
- new_attrs = alloc_workqueue_attrs(GFP_KERNEL);
- tmp_attrs = alloc_workqueue_attrs(GFP_KERNEL);
+ new_attrs = alloc_workqueue_attrs();
+ tmp_attrs = alloc_workqueue_attrs();
if (!ctx || !new_attrs || !tmp_attrs)
goto out_free;
@@ -3876,7 +3846,7 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
*
* Return: 0 on success and -errno on failure.
*/
-int apply_workqueue_attrs(struct workqueue_struct *wq,
+static int apply_workqueue_attrs(struct workqueue_struct *wq,
const struct workqueue_attrs *attrs)
{
int ret;
@@ -3964,9 +3934,9 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
use_dfl_pwq:
mutex_lock(&wq->mutex);
- spin_lock_irq(&wq->dfl_pwq->pool->lock);
+ raw_spin_lock_irq(&wq->dfl_pwq->pool->lock);
get_pwq(wq->dfl_pwq);
- spin_unlock_irq(&wq->dfl_pwq->pool->lock);
+ raw_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);
@@ -4020,6 +3990,37 @@ static int wq_clamp_max_active(int max_active, unsigned int flags,
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;
+}
+
struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
unsigned int flags,
int max_active,
@@ -4054,7 +4055,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
return NULL;
if (flags & WQ_UNBOUND) {
- wq->unbound_attrs = alloc_workqueue_attrs(GFP_KERNEL);
+ wq->unbound_attrs = alloc_workqueue_attrs();
if (!wq->unbound_attrs)
goto err_free_wq;
}
@@ -4082,29 +4083,8 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
if (alloc_and_link_pwqs(wq) < 0)
goto err_free_wq;
- /*
- * Workqueues which may be used during memory reclaim should
- * have a rescuer to guarantee forward progress.
- */
- if (flags & WQ_MEM_RECLAIM) {
- struct worker *rescuer;
-
- rescuer = alloc_worker(NUMA_NO_NODE);
- if (!rescuer)
- goto err_destroy;
-
- rescuer->rescue_wq = wq;
- rescuer->task = kthread_create(rescuer_thread, rescuer, "%s",
- wq->name);
- if (IS_ERR(rescuer->task)) {
- kfree(rescuer);
- goto err_destroy;
- }
-
- wq->rescuer = rescuer;
- kthread_bind_mask(rescuer->task, cpu_possible_mask);
- wake_up_process(rescuer->task);
- }
+ if (wq_online && init_rescuer(wq) < 0)
+ goto err_destroy;
if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq))
goto err_destroy;
@@ -4162,9 +4142,9 @@ void destroy_workqueue(struct workqueue_struct *wq)
struct worker *rescuer = wq->rescuer;
/* this prevents new queueing */
- spin_lock_irq(&wq_mayday_lock);
+ raw_spin_lock_irq(&wq_mayday_lock);
wq->rescuer = NULL;
- spin_unlock_irq(&wq_mayday_lock);
+ raw_spin_unlock_irq(&wq_mayday_lock);
/* rescuer will empty maydays list before exiting */
kthread_stop(rescuer->task);
@@ -4359,10 +4339,10 @@ unsigned int work_busy(struct work_struct *work)
rcu_read_lock();
pool = get_work_pool(work);
if (pool) {
- spin_lock_irqsave(&pool->lock, flags);
+ raw_spin_lock_irqsave(&pool->lock, flags);
if (find_worker_executing_work(pool, work))
ret |= WORK_BUSY_RUNNING;
- spin_unlock_irqrestore(&pool->lock, flags);
+ raw_spin_unlock_irqrestore(&pool->lock, flags);
}
rcu_read_unlock();
@@ -4389,9 +4369,9 @@ void set_worker_desc(const char *fmt, ...)
va_start(args, fmt);
vsnprintf(worker->desc, sizeof(worker->desc), fmt, args);
va_end(args);
- worker->desc_valid = true;
}
}
+EXPORT_SYMBOL_GPL(set_worker_desc);
/**
* print_worker_info - print out worker information and description
@@ -4413,7 +4393,6 @@ void print_worker_info(const char *log_lvl, struct task_struct *task)
char desc[WORKER_DESC_LEN] = { };
struct pool_workqueue *pwq = NULL;
struct workqueue_struct *wq = NULL;
- bool desc_valid = false;
struct worker *worker;
if (!(task->flags & PF_WQ_WORKER))
@@ -4426,22 +4405,18 @@ void print_worker_info(const char *log_lvl, struct task_struct *task)
worker = kthread_probe_data(task);
/*
- * Carefully copy the associated workqueue's workfn and name. Keep
- * the original last '\0' in case the original contains garbage.
+ * 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);
-
- /* copy worker description */
- probe_kernel_read(&desc_valid, &worker->desc_valid, sizeof(desc_valid));
- if (desc_valid)
- probe_kernel_read(desc, worker->desc, sizeof(desc) - 1);
+ probe_kernel_read(desc, worker->desc, sizeof(desc) - 1);
if (fn || name[0] || desc[0]) {
printk("%sWorkqueue: %s %pf", log_lvl, name, fn);
- if (desc[0])
+ if (strcmp(name, desc))
pr_cont(" (%s)", desc);
pr_cont("\n");
}
@@ -4574,10 +4549,10 @@ void show_workqueue_state(void)
pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags);
for_each_pwq(pwq, wq) {
- spin_lock_irqsave(&pwq->pool->lock, flags);
+ raw_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);
+ raw_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
@@ -4591,7 +4566,7 @@ void show_workqueue_state(void)
struct worker *worker;
bool first = true;
- spin_lock_irqsave(&pool->lock, flags);
+ raw_spin_lock_irqsave(&pool->lock, flags);
if (pool->nr_workers == pool->nr_idle)
goto next_pool;
@@ -4610,7 +4585,7 @@ void show_workqueue_state(void)
}
pr_cont("\n");
next_pool:
- spin_unlock_irqrestore(&pool->lock, flags);
+ raw_spin_unlock_irqrestore(&pool->lock, flags);
/*
* We could be printing a lot from atomic context, e.g.
* sysrq-t -> show_workqueue_state(). Avoid triggering
@@ -4622,6 +4597,47 @@ void show_workqueue_state(void)
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) {
+ raw_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);
+ }
+ raw_spin_unlock_irq(&pool->lock);
+ }
+ }
+
+ mutex_unlock(&wq_pool_attach_mutex);
+}
+
+#ifdef CONFIG_SMP
+
/*
* CPU hotplug.
*
@@ -4637,15 +4653,14 @@ void show_workqueue_state(void)
* cpu comes back online.
*/
-static void wq_unbind_fn(struct work_struct *work)
+static void unbind_workers(int cpu)
{
- int cpu = smp_processor_id();
struct worker_pool *pool;
struct worker *worker;
for_each_cpu_worker_pool(pool, cpu) {
- mutex_lock(&pool->attach_mutex);
- spin_lock_irq(&pool->lock);
+ mutex_lock(&wq_pool_attach_mutex);
+ raw_spin_lock_irq(&pool->lock);
/*
* We've blocked all attach/detach operations. Make all workers
@@ -4659,8 +4674,8 @@ static void wq_unbind_fn(struct work_struct *work)
pool->flags |= POOL_DISASSOCIATED;
- spin_unlock_irq(&pool->lock);
- mutex_unlock(&pool->attach_mutex);
+ raw_spin_unlock_irq(&pool->lock);
+ mutex_unlock(&wq_pool_attach_mutex);
/*
* Call schedule() so that we cross rq->lock and thus can
@@ -4685,9 +4700,9 @@ static void wq_unbind_fn(struct work_struct *work)
* worker blocking could lead to lengthy stalls. Kick off
* unbound chain execution of currently pending work items.
*/
- spin_lock_irq(&pool->lock);
+ raw_spin_lock_irq(&pool->lock);
wake_up_worker(pool);
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock_irq(&pool->lock);
}
}
@@ -4701,7 +4716,7 @@ static void rebind_workers(struct worker_pool *pool)
{
struct worker *worker;
- lockdep_assert_held(&pool->attach_mutex);
+ lockdep_assert_held(&wq_pool_attach_mutex);
/*
* Restore CPU affinity of all workers. As all idle workers should
@@ -4714,17 +4729,7 @@ static void rebind_workers(struct worker_pool *pool)
WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
pool->attrs->cpumask) < 0);
- spin_lock_irq(&pool->lock);
-
- /*
- * XXX: CPU hotplug notifiers are weird and can call DOWN_FAILED
- * w/o preceding DOWN_PREPARE. Work around it. CPU hotplug is
- * being reworked and this can go away in time.
- */
- if (!(pool->flags & POOL_DISASSOCIATED)) {
- spin_unlock_irq(&pool->lock);
- return;
- }
+ raw_spin_lock_irq(&pool->lock);
pool->flags &= ~POOL_DISASSOCIATED;
@@ -4751,7 +4756,7 @@ static void rebind_workers(struct worker_pool *pool)
* concurrency management. Note that when or whether
* @worker clears REBOUND doesn't affect correctness.
*
- * ACCESS_ONCE() is necessary because @worker->flags may be
+ * WRITE_ONCE() is necessary because @worker->flags may be
* tested without holding any lock in
* wq_worker_waking_up(). Without it, NOT_RUNNING test may
* fail incorrectly leading to premature concurrency
@@ -4760,10 +4765,10 @@ static void rebind_workers(struct worker_pool *pool)
WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND));
worker_flags |= WORKER_REBOUND;
worker_flags &= ~WORKER_UNBOUND;
- ACCESS_ONCE(worker->flags) = worker_flags;
+ WRITE_ONCE(worker->flags, worker_flags);
}
- spin_unlock_irq(&pool->lock);
+ raw_spin_unlock_irq(&pool->lock);
}
/**
@@ -4781,7 +4786,7 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
static cpumask_t cpumask;
struct worker *worker;
- lockdep_assert_held(&pool->attach_mutex);
+ lockdep_assert_held(&wq_pool_attach_mutex);
/* is @cpu allowed for @pool? */
if (!cpumask_test_cpu(cpu, pool->attrs->cpumask))
@@ -4816,14 +4821,14 @@ int workqueue_online_cpu(unsigned int cpu)
mutex_lock(&wq_pool_mutex);
for_each_pool(pool, pi) {
- mutex_lock(&pool->attach_mutex);
+ 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(&pool->attach_mutex);
+ mutex_unlock(&wq_pool_attach_mutex);
}
/* update NUMA affinity of unbound workqueues */
@@ -4836,12 +4841,13 @@ int workqueue_online_cpu(unsigned int cpu)
int workqueue_offline_cpu(unsigned int cpu)
{
- struct work_struct unbind_work;
struct workqueue_struct *wq;
/* unbinding per-cpu workers should happen on the local CPU */
- INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn);
- queue_work_on(cpu, system_highpri_wq, &unbind_work);
+ if (WARN_ON(cpu != smp_processor_id()))
+ return -1;
+
+ unbind_workers(cpu);
/* update NUMA affinity of unbound workqueues */
mutex_lock(&wq_pool_mutex);
@@ -4849,14 +4855,9 @@ int workqueue_offline_cpu(unsigned int cpu)
wq_update_unbound_numa(wq, cpu, false);
mutex_unlock(&wq_pool_mutex);
- /* wait for per-cpu unbinding to finish */
- flush_work(&unbind_work);
- destroy_work_on_stack(&unbind_work);
return 0;
}
-#ifdef CONFIG_SMP
-
struct work_for_cpu {
struct work_struct work;
long (*fn)(void *);
@@ -5081,12 +5082,22 @@ 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();
+ if (cpumask_equal(cpumask, wq_unbound_cpumask)) {
+ ret = 0;
+ goto out_unlock;
+ }
+
+ if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL)) {
+ ret = -ENOMEM;
+ goto out_unlock;
+ }
/* save the old wq_unbound_cpumask. */
cpumask_copy(saved_cpumask, wq_unbound_cpumask);
@@ -5099,10 +5110,11 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
if (ret < 0)
cpumask_copy(wq_unbound_cpumask, saved_cpumask);
+ free_cpumask_var(saved_cpumask);
+out_unlock:
apply_wqattrs_unlock();
}
- free_cpumask_var(saved_cpumask);
return ret;
}
@@ -5117,9 +5129,10 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
*
* Unbound workqueues have the following extra attributes.
*
- * id RO int : the associated pool ID
+ * 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;
@@ -5214,7 +5227,7 @@ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq)
lockdep_assert_held(&wq_pool_mutex);
- attrs = alloc_workqueue_attrs(GFP_KERNEL);
+ attrs = alloc_workqueue_attrs();
if (!attrs)
return NULL;
@@ -5645,7 +5658,7 @@ static void __init wq_numa_init(void)
return;
}
- wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(GFP_KERNEL);
+ wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs();
BUG_ON(!wq_update_unbound_numa_attrs_buf);
/*
@@ -5653,7 +5666,7 @@ static void __init wq_numa_init(void)
* available. Build one from cpu_to_node() which should have been
* fully initialized by now.
*/
- tbl = kzalloc(nr_node_ids * sizeof(tbl[0]), GFP_KERNEL);
+ tbl = kcalloc(nr_node_ids, sizeof(tbl[0]), GFP_KERNEL);
BUG_ON(!tbl);
for_each_node(node)
@@ -5719,7 +5732,7 @@ int __init workqueue_init_early(void)
for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
struct workqueue_attrs *attrs;
- BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
+ BUG_ON(!(attrs = alloc_workqueue_attrs()));
attrs->nice = std_nice[i];
unbound_std_wq_attrs[i] = attrs;
@@ -5728,7 +5741,7 @@ int __init workqueue_init_early(void)
* 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(GFP_KERNEL)));
+ BUG_ON(!(attrs = alloc_workqueue_attrs()));
attrs->nice = std_nice[i];
attrs->no_numa = true;
ordered_wq_attrs[i] = attrs;
@@ -5775,6 +5788,8 @@ int __init workqueue_init(void)
* 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();
@@ -5786,8 +5801,12 @@ int __init workqueue_init(void)
}
}
- list_for_each_entry(wq, &workqueues, list)
+ 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);
--
2.37.3
