linux/kernel/workqueue.c

841 lines
20 KiB
C
Raw Normal View History

/*
* linux/kernel/workqueue.c
*
* Generic mechanism for defining kernel helper threads for running
* arbitrary tasks in process context.
*
* Started by Ingo Molnar, Copyright (C) 2002
*
* Derived from the taskqueue/keventd code by:
*
* David Woodhouse <dwmw2@infradead.org>
* Andrew Morton <andrewm@uow.edu.au>
* Kai Petzke <wpp@marie.physik.tu-berlin.de>
* Theodore Ts'o <tytso@mit.edu>
*
* Made to use alloc_percpu by Christoph Lameter <clameter@sgi.com>.
*/
#include <linux/module.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/kallsyms.h>
#include <linux/debug_locks.h>
/*
* The per-CPU workqueue (if single thread, we always use the first
* possible cpu).
*/
struct cpu_workqueue_struct {
spinlock_t lock;
struct list_head worklist;
wait_queue_head_t more_work;
struct work_struct *current_work;
struct workqueue_struct *wq;
struct task_struct *thread;
int run_depth; /* Detect run_workqueue() recursion depth */
} ____cacheline_aligned;
/*
* The externally visible workqueue abstraction is an array of
* per-CPU workqueues:
*/
struct workqueue_struct {
struct cpu_workqueue_struct *cpu_wq;
struct list_head list;
const char *name;
int singlethread;
int freezeable; /* Freeze threads during suspend */
};
/* All the per-cpu workqueues on the system, for hotplug cpu to add/remove
threads to each one as cpus come/go. */
static DEFINE_MUTEX(workqueue_mutex);
static LIST_HEAD(workqueues);
static int singlethread_cpu __read_mostly;
static cpumask_t cpu_singlethread_map __read_mostly;
/*
* _cpu_down() first removes CPU from cpu_online_map, then CPU_DEAD
* flushes cwq->worklist. This means that flush_workqueue/wait_on_work
* which comes in between can't use for_each_online_cpu(). We could
* use cpu_possible_map, the cpumask below is more a documentation
* than optimization.
*/
static cpumask_t cpu_populated_map __read_mostly;
/* If it's single threaded, it isn't in the list of workqueues. */
static inline int is_single_threaded(struct workqueue_struct *wq)
{
return wq->singlethread;
}
static const cpumask_t *wq_cpu_map(struct workqueue_struct *wq)
{
return is_single_threaded(wq)
? &cpu_singlethread_map : &cpu_populated_map;
}
static
struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu)
{
if (unlikely(is_single_threaded(wq)))
cpu = singlethread_cpu;
return per_cpu_ptr(wq->cpu_wq, cpu);
}
[PATCH] WorkStruct: Use direct assignment rather than cmpxchg() Use direct assignment rather than cmpxchg() as the latter is unavailable and unimplementable on some platforms and is actually unnecessary. The use of cmpxchg() was to guard against two possibilities, neither of which can actually occur: (1) The pending flag may have been unset or may be cleared. However, given where it's called, the pending flag is _always_ set. I don't think it can be unset whilst we're in set_wq_data(). Once the work is enqueued to be actually run, the only way off the queue is for it to be actually run. If it's a delayed work item, then the bit can't be cleared by the timer because we haven't started the timer yet. Also, the pending bit can't be cleared by cancelling the delayed work _until_ the work item has had its timer started. (2) The workqueue pointer might change. This can only happen in two cases: (a) The work item has just been queued to actually run, and so we're protected by the appropriate workqueue spinlock. (b) A delayed work item is being queued, and so the timer hasn't been started yet, and so no one else knows about the work item or can access it (the pending bit protects us). Besides, set_wq_data() _sets_ the workqueue pointer unconditionally, so it can be assigned instead. So, replacing the set_wq_data() with a straight assignment would be okay in most cases. The problem is where we end up tangling with test_and_set_bit() emulated using spinlocks, and even then it's not a problem _provided_ test_and_set_bit() doesn't attempt to modify the word if the bit was set. If that's a problem, then a bitops-proofed assignment will be required - equivalent to atomic_set() vs other atomic_xxx() ops. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 19:33:26 +08:00
/*
* Set the workqueue on which a work item is to be run
* - Must *only* be called if the pending flag is set
*/
static inline void set_wq_data(struct work_struct *work,
struct cpu_workqueue_struct *cwq)
{
[PATCH] WorkStruct: Use direct assignment rather than cmpxchg() Use direct assignment rather than cmpxchg() as the latter is unavailable and unimplementable on some platforms and is actually unnecessary. The use of cmpxchg() was to guard against two possibilities, neither of which can actually occur: (1) The pending flag may have been unset or may be cleared. However, given where it's called, the pending flag is _always_ set. I don't think it can be unset whilst we're in set_wq_data(). Once the work is enqueued to be actually run, the only way off the queue is for it to be actually run. If it's a delayed work item, then the bit can't be cleared by the timer because we haven't started the timer yet. Also, the pending bit can't be cleared by cancelling the delayed work _until_ the work item has had its timer started. (2) The workqueue pointer might change. This can only happen in two cases: (a) The work item has just been queued to actually run, and so we're protected by the appropriate workqueue spinlock. (b) A delayed work item is being queued, and so the timer hasn't been started yet, and so no one else knows about the work item or can access it (the pending bit protects us). Besides, set_wq_data() _sets_ the workqueue pointer unconditionally, so it can be assigned instead. So, replacing the set_wq_data() with a straight assignment would be okay in most cases. The problem is where we end up tangling with test_and_set_bit() emulated using spinlocks, and even then it's not a problem _provided_ test_and_set_bit() doesn't attempt to modify the word if the bit was set. If that's a problem, then a bitops-proofed assignment will be required - equivalent to atomic_set() vs other atomic_xxx() ops. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 19:33:26 +08:00
unsigned long new;
BUG_ON(!work_pending(work));
new = (unsigned long) cwq | (1UL << WORK_STRUCT_PENDING);
new |= WORK_STRUCT_FLAG_MASK & *work_data_bits(work);
atomic_long_set(&work->data, new);
}
static inline
struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
{
return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK);
}
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
static void insert_work(struct cpu_workqueue_struct *cwq,
struct work_struct *work, int tail)
{
set_wq_data(work, cwq);
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
/*
* Ensure that we get the right work->data if we see the
* result of list_add() below, see try_to_grab_pending().
*/
smp_wmb();
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
if (tail)
list_add_tail(&work->entry, &cwq->worklist);
else
list_add(&work->entry, &cwq->worklist);
wake_up(&cwq->more_work);
}
/* Preempt must be disabled. */
static void __queue_work(struct cpu_workqueue_struct *cwq,
struct work_struct *work)
{
unsigned long flags;
spin_lock_irqsave(&cwq->lock, flags);
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
insert_work(cwq, work, 1);
spin_unlock_irqrestore(&cwq->lock, flags);
}
/**
* queue_work - queue work on a workqueue
* @wq: workqueue to use
* @work: work to queue
*
* Returns 0 if @work was already on a queue, non-zero otherwise.
*
* We queue the work to the CPU it was submitted, but there is no
* guarantee that it will be processed by that CPU.
*/
int fastcall queue_work(struct workqueue_struct *wq, struct work_struct *work)
{
int ret = 0;
if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
BUG_ON(!list_empty(&work->entry));
__queue_work(wq_per_cpu(wq, get_cpu()), work);
put_cpu();
ret = 1;
}
return ret;
}
EXPORT_SYMBOL_GPL(queue_work);
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 17:28:13 +08:00
void delayed_work_timer_fn(unsigned long __data)
{
struct delayed_work *dwork = (struct delayed_work *)__data;
struct cpu_workqueue_struct *cwq = get_wq_data(&dwork->work);
struct workqueue_struct *wq = cwq->wq;
__queue_work(wq_per_cpu(wq, smp_processor_id()), &dwork->work);
}
/**
* queue_delayed_work - queue work on a workqueue after delay
* @wq: workqueue to use
* @dwork: delayable work to queue
* @delay: number of jiffies to wait before queueing
*
* Returns 0 if @work was already on a queue, non-zero otherwise.
*/
int fastcall queue_delayed_work(struct workqueue_struct *wq,
struct delayed_work *dwork, unsigned long delay)
{
timer_stats_timer_set_start_info(&dwork->timer);
if (delay == 0)
return queue_work(wq, &dwork->work);
return queue_delayed_work_on(-1, wq, dwork, delay);
}
EXPORT_SYMBOL_GPL(queue_delayed_work);
/**
* 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
*
* Returns 0 if @work was already on a queue, non-zero otherwise.
*/
int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *dwork, unsigned long delay)
{
int ret = 0;
struct timer_list *timer = &dwork->timer;
struct work_struct *work = &dwork->work;
if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
BUG_ON(timer_pending(timer));
BUG_ON(!list_empty(&work->entry));
/* This stores cwq for the moment, for the timer_fn */
set_wq_data(work, wq_per_cpu(wq, raw_smp_processor_id()));
timer->expires = jiffies + delay;
timer->data = (unsigned long)dwork;
timer->function = delayed_work_timer_fn;
if (unlikely(cpu >= 0))
add_timer_on(timer, cpu);
else
add_timer(timer);
ret = 1;
}
return ret;
}
EXPORT_SYMBOL_GPL(queue_delayed_work_on);
static void run_workqueue(struct cpu_workqueue_struct *cwq)
{
spin_lock_irq(&cwq->lock);
cwq->run_depth++;
if (cwq->run_depth > 3) {
/* morton gets to eat his hat */
printk("%s: recursion depth exceeded: %d\n",
__FUNCTION__, cwq->run_depth);
dump_stack();
}
while (!list_empty(&cwq->worklist)) {
struct work_struct *work = list_entry(cwq->worklist.next,
struct work_struct, entry);
work_func_t f = work->func;
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
cwq->current_work = work;
list_del_init(cwq->worklist.next);
spin_unlock_irq(&cwq->lock);
BUG_ON(get_wq_data(work) != cwq);
work_clear_pending(work);
2006-11-22 22:55:48 +08:00
f(work);
if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
printk(KERN_ERR "BUG: workqueue leaked lock or atomic: "
"%s/0x%08x/%d\n",
current->comm, preempt_count(),
current->pid);
printk(KERN_ERR " last function: ");
print_symbol("%s\n", (unsigned long)f);
debug_show_held_locks(current);
dump_stack();
}
spin_lock_irq(&cwq->lock);
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
cwq->current_work = NULL;
}
cwq->run_depth--;
spin_unlock_irq(&cwq->lock);
}
static int worker_thread(void *__cwq)
{
struct cpu_workqueue_struct *cwq = __cwq;
DEFINE_WAIT(wait);
if (!cwq->wq->freezeable)
current->flags |= PF_NOFREEZE;
set_user_nice(current, -5);
for (;;) {
prepare_to_wait(&cwq->more_work, &wait, TASK_INTERRUPTIBLE);
if (!freezing(current) &&
!kthread_should_stop() &&
list_empty(&cwq->worklist))
schedule();
finish_wait(&cwq->more_work, &wait);
try_to_freeze();
if (kthread_should_stop())
break;
run_workqueue(cwq);
}
return 0;
}
struct wq_barrier {
struct work_struct work;
struct completion done;
};
static void wq_barrier_func(struct work_struct *work)
{
struct wq_barrier *barr = container_of(work, struct wq_barrier, work);
complete(&barr->done);
}
static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
struct wq_barrier *barr, int tail)
{
INIT_WORK(&barr->work, wq_barrier_func);
__set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));
init_completion(&barr->done);
insert_work(cwq, &barr->work, tail);
}
static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
{
int active;
if (cwq->thread == current) {
/*
* Probably keventd trying to flush its own queue. So simply run
* it by hand rather than deadlocking.
*/
run_workqueue(cwq);
active = 1;
} else {
struct wq_barrier barr;
active = 0;
spin_lock_irq(&cwq->lock);
if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
insert_wq_barrier(cwq, &barr, 1);
active = 1;
}
spin_unlock_irq(&cwq->lock);
workqueue: fix flush_workqueue() vs CPU_DEAD race Many thanks to Srivatsa Vaddagiri for the helpful discussion and for spotting the bug in my previous attempt. work->func() (and thus flush_workqueue()) must not use workqueue_mutex, this leads to deadlock when CPU_DEAD does kthread_stop(). However without this mutex held we can't detect CPU_DEAD in progress, which can move pending works to another CPU while the dead one is not on cpu_online_map. Change flush_workqueue() to use for_each_possible_cpu(). This means that flush_cpu_workqueue() may hit CPU which is already dead. However in that case !list_empty(&cwq->worklist) || cwq->current_work != NULL means that CPU_DEAD in progress, it will do kthread_stop() + take_over_work() so we can proceed and insert a barrier. We hold cwq->lock, so we are safe. Also, add migrate_sequence incremented by take_over_work() under cwq->lock. If take_over_work() happened before we checked this CPU, we should see the new value after spin_unlock(). Further possible changes: remove CPU_DEAD handling (along with take_over_work, migrate_sequence) from workqueue.c. CPU_DEAD just sets cwq->please_exit_after_flush flag. CPU_UP_PREPARE->create_workqueue_thread() clears this flag, and creates the new thread if cwq->thread == NULL. This way the workqueue/cpu-hotplug interaction is almost zero, workqueue_mutex just protects "workqueues" list, CPU_LOCK_ACQUIRE/CPU_LOCK_RELEASE go away. Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Cc: "Pallipadi, Venkatesh" <venkatesh.pallipadi@intel.com> Cc: Gautham shenoy <ego@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:07 +08:00
if (active)
wait_for_completion(&barr.done);
}
return active;
}
/**
* flush_workqueue - ensure that any scheduled work has run to completion.
* @wq: workqueue to flush
*
* Forces execution of the workqueue and blocks until its completion.
* This is typically used in driver shutdown handlers.
*
* We sleep until all works which were queued on entry have been handled,
* but we are not livelocked by new incoming ones.
*
* This function used to run the workqueues itself. Now we just wait for the
* helper threads to do it.
*/
void fastcall flush_workqueue(struct workqueue_struct *wq)
{
const cpumask_t *cpu_map = wq_cpu_map(wq);
int cpu;
might_sleep();
for_each_cpu_mask(cpu, *cpu_map)
flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
}
EXPORT_SYMBOL_GPL(flush_workqueue);
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
/*
* Upon a successful return, the caller "owns" WORK_STRUCT_PENDING bit,
* so this work can't be re-armed in any way.
*/
static int try_to_grab_pending(struct work_struct *work)
{
struct cpu_workqueue_struct *cwq;
int ret = 0;
if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work)))
return 1;
/*
* The queueing is in progress, or it is already queued. Try to
* steal it from ->worklist without clearing WORK_STRUCT_PENDING.
*/
cwq = get_wq_data(work);
if (!cwq)
return ret;
spin_lock_irq(&cwq->lock);
if (!list_empty(&work->entry)) {
/*
* This work is queued, but perhaps we locked the wrong cwq.
* In that case we must see the new value after rmb(), see
* insert_work()->wmb().
*/
smp_rmb();
if (cwq == get_wq_data(work)) {
list_del_init(&work->entry);
ret = 1;
}
}
spin_unlock_irq(&cwq->lock);
return ret;
}
static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
struct work_struct *work)
{
struct wq_barrier barr;
int running = 0;
spin_lock_irq(&cwq->lock);
if (unlikely(cwq->current_work == work)) {
insert_wq_barrier(cwq, &barr, 0);
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
running = 1;
}
spin_unlock_irq(&cwq->lock);
if (unlikely(running))
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
wait_for_completion(&barr.done);
}
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
static void wait_on_work(struct work_struct *work)
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
{
struct cpu_workqueue_struct *cwq;
struct workqueue_struct *wq;
const cpumask_t *cpu_map;
int cpu;
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
might_sleep();
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
cwq = get_wq_data(work);
if (!cwq)
return;
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
wq = cwq->wq;
cpu_map = wq_cpu_map(wq);
for_each_cpu_mask(cpu, *cpu_map)
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
}
/**
* cancel_work_sync - block until a work_struct's callback has terminated
* @work: the work which is to be flushed
*
* cancel_work_sync() will cancel the work if it is queued. If the work's
* callback appears to be running, cancel_work_sync() will block until it
* has completed.
*
* It is possible to use this function if the work re-queues itself. It can
* cancel the work even if it migrates to another workqueue, however in that
* case it only guarantees that work->func() has completed on the last queued
* workqueue.
*
* cancel_work_sync(&delayed_work->work) should be used only if ->timer is not
* pending, otherwise it goes into a busy-wait loop until the timer expires.
*
* The caller must ensure that workqueue_struct on which this work was last
* queued can't be destroyed before this function returns.
*/
void cancel_work_sync(struct work_struct *work)
{
while (!try_to_grab_pending(work))
cpu_relax();
wait_on_work(work);
work_clear_pending(work);
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
}
EXPORT_SYMBOL_GPL(cancel_work_sync);
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
/**
* cancel_rearming_delayed_work - reliably kill off a delayed work.
* @dwork: the delayed work struct
*
* It is possible to use this function if @dwork rearms itself via queue_work()
* or queue_delayed_work(). See also the comment for cancel_work_sync().
*/
void cancel_rearming_delayed_work(struct delayed_work *dwork)
{
while (!del_timer(&dwork->timer) &&
!try_to_grab_pending(&dwork->work))
cpu_relax();
wait_on_work(&dwork->work);
work_clear_pending(&dwork->work);
}
EXPORT_SYMBOL(cancel_rearming_delayed_work);
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
static struct workqueue_struct *keventd_wq __read_mostly;
/**
* schedule_work - put work task in global workqueue
* @work: job to be done
*
* This puts a job in the kernel-global workqueue.
*/
int fastcall schedule_work(struct work_struct *work)
{
return queue_work(keventd_wq, work);
}
EXPORT_SYMBOL(schedule_work);
/**
* schedule_delayed_work - put work task in global workqueue after delay
* @dwork: job to be done
* @delay: number of jiffies to wait or 0 for immediate execution
*
* After waiting for a given time this puts a job in the kernel-global
* workqueue.
*/
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 17:28:13 +08:00
int fastcall schedule_delayed_work(struct delayed_work *dwork,
unsigned long delay)
{
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 17:28:13 +08:00
timer_stats_timer_set_start_info(&dwork->timer);
return queue_delayed_work(keventd_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_delayed_work);
/**
* schedule_delayed_work_on - queue work in global workqueue on CPU after delay
* @cpu: cpu to use
* @dwork: job to be done
* @delay: number of jiffies to wait
*
* After waiting for a given time this puts a job in the kernel-global
* workqueue on the specified CPU.
*/
int schedule_delayed_work_on(int cpu,
struct delayed_work *dwork, unsigned long delay)
{
return queue_delayed_work_on(cpu, keventd_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_delayed_work_on);
/**
* schedule_on_each_cpu - call a function on each online CPU from keventd
* @func: the function to call
*
* Returns zero on success.
* Returns -ve errno on failure.
*
* Appears to be racy against CPU hotplug.
*
* schedule_on_each_cpu() is very slow.
*/
2006-11-22 22:55:48 +08:00
int schedule_on_each_cpu(work_func_t func)
{
int cpu;
struct work_struct *works;
works = alloc_percpu(struct work_struct);
if (!works)
return -ENOMEM;
preempt_disable(); /* CPU hotplug */
for_each_online_cpu(cpu) {
struct work_struct *work = per_cpu_ptr(works, cpu);
INIT_WORK(work, func);
set_bit(WORK_STRUCT_PENDING, work_data_bits(work));
__queue_work(per_cpu_ptr(keventd_wq->cpu_wq, cpu), work);
}
preempt_enable();
flush_workqueue(keventd_wq);
free_percpu(works);
return 0;
}
void flush_scheduled_work(void)
{
flush_workqueue(keventd_wq);
}
EXPORT_SYMBOL(flush_scheduled_work);
/**
* 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.
*
* Returns: 0 - function was executed
* 1 - function was scheduled for execution
*/
2006-11-22 22:55:48 +08:00
int execute_in_process_context(work_func_t fn, struct execute_work *ew)
{
if (!in_interrupt()) {
2006-11-22 22:55:48 +08:00
fn(&ew->work);
return 0;
}
2006-11-22 22:55:48 +08:00
INIT_WORK(&ew->work, fn);
schedule_work(&ew->work);
return 1;
}
EXPORT_SYMBOL_GPL(execute_in_process_context);
int keventd_up(void)
{
return keventd_wq != NULL;
}
int current_is_keventd(void)
{
struct cpu_workqueue_struct *cwq;
int cpu = smp_processor_id(); /* preempt-safe: keventd is per-cpu */
int ret = 0;
BUG_ON(!keventd_wq);
cwq = per_cpu_ptr(keventd_wq->cpu_wq, cpu);
if (current == cwq->thread)
ret = 1;
return ret;
}
static struct cpu_workqueue_struct *
init_cpu_workqueue(struct workqueue_struct *wq, int cpu)
{
struct cpu_workqueue_struct *cwq = per_cpu_ptr(wq->cpu_wq, cpu);
cwq->wq = wq;
spin_lock_init(&cwq->lock);
INIT_LIST_HEAD(&cwq->worklist);
init_waitqueue_head(&cwq->more_work);
return cwq;
}
static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
{
struct workqueue_struct *wq = cwq->wq;
const char *fmt = is_single_threaded(wq) ? "%s" : "%s/%d";
struct task_struct *p;
p = kthread_create(worker_thread, cwq, fmt, wq->name, cpu);
/*
* Nobody can add the work_struct to this cwq,
* if (caller is __create_workqueue)
* nobody should see this wq
* else // caller is CPU_UP_PREPARE
* cpu is not on cpu_online_map
* so we can abort safely.
*/
if (IS_ERR(p))
return PTR_ERR(p);
cwq->thread = p;
return 0;
}
static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
{
struct task_struct *p = cwq->thread;
if (p != NULL) {
if (cpu >= 0)
kthread_bind(p, cpu);
wake_up_process(p);
}
}
struct workqueue_struct *__create_workqueue(const char *name,
int singlethread, int freezeable)
{
struct workqueue_struct *wq;
struct cpu_workqueue_struct *cwq;
int err = 0, cpu;
wq = kzalloc(sizeof(*wq), GFP_KERNEL);
if (!wq)
return NULL;
wq->cpu_wq = alloc_percpu(struct cpu_workqueue_struct);
if (!wq->cpu_wq) {
kfree(wq);
return NULL;
}
wq->name = name;
wq->singlethread = singlethread;
wq->freezeable = freezeable;
INIT_LIST_HEAD(&wq->list);
if (singlethread) {
cwq = init_cpu_workqueue(wq, singlethread_cpu);
err = create_workqueue_thread(cwq, singlethread_cpu);
start_workqueue_thread(cwq, -1);
} else {
mutex_lock(&workqueue_mutex);
list_add(&wq->list, &workqueues);
for_each_possible_cpu(cpu) {
cwq = init_cpu_workqueue(wq, cpu);
if (err || !cpu_online(cpu))
continue;
err = create_workqueue_thread(cwq, cpu);
start_workqueue_thread(cwq, cpu);
}
mutex_unlock(&workqueue_mutex);
}
if (err) {
destroy_workqueue(wq);
wq = NULL;
}
return wq;
}
EXPORT_SYMBOL_GPL(__create_workqueue);
static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
{
/*
* Our caller is either destroy_workqueue() or CPU_DEAD,
* workqueue_mutex protects cwq->thread
*/
if (cwq->thread == NULL)
return;
/*
* If the caller is CPU_DEAD the single flush_cpu_workqueue()
* is not enough, a concurrent flush_workqueue() can insert a
* barrier after us.
* When ->worklist becomes empty it is safe to exit because no
* more work_structs can be queued on this cwq: flush_workqueue
* checks list_empty(), and a "normal" queue_work() can't use
* a dead CPU.
*/
while (flush_cpu_workqueue(cwq))
;
kthread_stop(cwq->thread);
cwq->thread = NULL;
}
/**
* 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)
{
const cpumask_t *cpu_map = wq_cpu_map(wq);
struct cpu_workqueue_struct *cwq;
int cpu;
mutex_lock(&workqueue_mutex);
list_del(&wq->list);
mutex_unlock(&workqueue_mutex);
for_each_cpu_mask(cpu, *cpu_map) {
cwq = per_cpu_ptr(wq->cpu_wq, cpu);
cleanup_workqueue_thread(cwq, cpu);
}
free_percpu(wq->cpu_wq);
kfree(wq);
}
EXPORT_SYMBOL_GPL(destroy_workqueue);
static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
unsigned int cpu = (unsigned long)hcpu;
struct cpu_workqueue_struct *cwq;
struct workqueue_struct *wq;
action &= ~CPU_TASKS_FROZEN;
switch (action) {
case CPU_LOCK_ACQUIRE:
mutex_lock(&workqueue_mutex);
return NOTIFY_OK;
case CPU_LOCK_RELEASE:
mutex_unlock(&workqueue_mutex);
return NOTIFY_OK;
case CPU_UP_PREPARE:
cpu_set(cpu, cpu_populated_map);
}
list_for_each_entry(wq, &workqueues, list) {
cwq = per_cpu_ptr(wq->cpu_wq, cpu);
switch (action) {
case CPU_UP_PREPARE:
if (!create_workqueue_thread(cwq, cpu))
break;
printk(KERN_ERR "workqueue for %i failed\n", cpu);
return NOTIFY_BAD;
case CPU_ONLINE:
start_workqueue_thread(cwq, cpu);
break;
case CPU_UP_CANCELED:
start_workqueue_thread(cwq, -1);
case CPU_DEAD:
cleanup_workqueue_thread(cwq, cpu);
break;
}
}
return NOTIFY_OK;
}
void __init init_workqueues(void)
{
cpu_populated_map = cpu_online_map;
singlethread_cpu = first_cpu(cpu_possible_map);
cpu_singlethread_map = cpumask_of_cpu(singlethread_cpu);
hotcpu_notifier(workqueue_cpu_callback, 0);
keventd_wq = create_workqueue("events");
BUG_ON(!keventd_wq);
}