The patch titled
make cancel_rearming_delayed_work() reliable
has been added to the -mm tree. Its filename is
make-cancel_rearming_delayed_work-reliable.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: make cancel_rearming_delayed_work() reliable
From: Oleg Nesterov <oleg@xxxxxxxxxx>
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).
Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: David Chinner <dgc@xxxxxxx>
Cc: David Howells <dhowells@xxxxxxxxxx>
Cc: Gautham Shenoy <ego@xxxxxxxxxx>
Cc: Jarek Poplawski <jarkao2@xxxxx>
Cc: Srivatsa Vaddagiri <vatsa@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
kernel/workqueue.c | 137 +++++++++++++++++++++++++++----------------
1 files changed, 88 insertions(+), 49 deletions(-)
diff -puN kernel/workqueue.c~make-cancel_rearming_delayed_work-reliable kernel/workqueue.c
--- a/kernel/workqueue.c~make-cancel_rearming_delayed_work-reliable
+++ a/kernel/workqueue.c
@@ -120,6 +120,11 @@ static void insert_work(struct cpu_workq
struct work_struct *work, int tail)
{
set_wq_data(work, cwq);
+ /*
+ * Ensure that we get the right work->data if we see the
+ * result of list_add() below, see try_to_grab_pending().
+ */
+ smp_wmb();
if (tail)
list_add_tail(&work->entry, &cwq->worklist);
else
@@ -383,7 +388,46 @@ void fastcall flush_workqueue(struct wor
}
EXPORT_SYMBOL_GPL(flush_workqueue);
-static void wait_on_work(struct cpu_workqueue_struct *cwq,
+/*
+ * Upon a successfull 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,
struct work_struct *work)
{
struct wq_barrier barr;
@@ -400,20 +444,7 @@ static void wait_on_work(struct cpu_work
wait_for_completion(&barr.done);
}
-/**
- * cancel_work_sync - block until a work_struct's callback has terminated
- * @work: the work which is to be flushed
- *
- * cancel_work_sync() will attempt to 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.
- *
- * cancel_work_sync() is designed to be used when the caller is tearing down
- * data structures which the callback function operates upon. It is expected
- * that, prior to calling cancel_work_sync(), the caller has arranged for the
- * work to not be requeued.
- */
-void cancel_work_sync(struct work_struct *work)
+static void wait_on_work(struct work_struct *work)
{
struct cpu_workqueue_struct *cwq;
struct workqueue_struct *wq;
@@ -423,29 +454,59 @@ void cancel_work_sync(struct work_struct
might_sleep();
cwq = get_wq_data(work);
- /* Was it ever queued ? */
if (!cwq)
return;
- /*
- * This work can't be re-queued, no need to re-check that
- * get_wq_data() is still the same when we take cwq->lock.
- */
- spin_lock_irq(&cwq->lock);
- list_del_init(&work->entry);
- work_clear_pending(work);
- spin_unlock_irq(&cwq->lock);
-
wq = cwq->wq;
cpu_map = wq_cpu_map(wq);
for_each_cpu_mask(cpu, *cpu_map)
- wait_on_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
+ 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 garantees that work->func() has completed on the last queued
+ * workqueue.
+ *
+ * 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))
+ ;
+ wait_on_work(work);
+ work_clear_pending(work);
}
EXPORT_SYMBOL_GPL(cancel_work_sync);
+/**
+ * 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))
+ ;
+ wait_on_work(&dwork->work);
+ work_clear_pending(&dwork->work);
+}
+EXPORT_SYMBOL(cancel_rearming_delayed_work);
-static struct workqueue_struct *keventd_wq;
+static struct workqueue_struct *keventd_wq __read_mostly;
/**
* schedule_work - put work task in global workqueue
@@ -532,28 +593,6 @@ void flush_scheduled_work(void)
EXPORT_SYMBOL(flush_scheduled_work);
/**
- * cancel_rearming_delayed_work - kill off a delayed work whose handler rearms the delayed work.
- * @dwork: the delayed work struct
- *
- * Note that the work callback function may still be running on return from
- * cancel_delayed_work(). Run flush_workqueue() or cancel_work_sync() to wait
- * on it.
- */
-void cancel_rearming_delayed_work(struct delayed_work *dwork)
-{
- struct cpu_workqueue_struct *cwq = get_wq_data(&dwork->work);
-
- /* Was it ever queued ? */
- if (cwq != NULL) {
- struct workqueue_struct *wq = cwq->wq;
-
- while (!cancel_delayed_work(dwork))
- flush_workqueue(wq);
- }
-}
-EXPORT_SYMBOL(cancel_rearming_delayed_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
_
Patches currently in -mm which might be from oleg@xxxxxxxxxx are
origin.patch
fix-refrigerator-vs-thaw_process-race.patch
clone-flag-clone_parent_tidptr-leaves-invalid-results-in-memory.patch
allow-access-to-proc-pid-fd-after-setuid.patch
freezer-task-exit_state-should-be-treated-as-bolean.patch
softlockup-trivial-s-99-max_rt_prio.patch
merge-sys_clone-sys_unshare-nsproxy-and-namespace.patch
fix-race-between-proc_get_inode-and-remove_proc_entry.patch
getrusage-fill-ru_inblock-and-ru_oublock-fields-if-possible.patch
futex-restartable-futex_wait.patch
add-support-for-deferrable-timers-respun.patch
add-a-new-deferrable-delayed-work-init.patch
reimplement-flush_workqueue.patch
implement-flush_work.patch
flush_workqueue-use-preempt_disable-to-hold-off-cpu-hotplug.patch
flush_cpu_workqueue-dont-flush-an-empty-worklist.patch
aio-use-flush_work.patch
kblockd-use-flush_work.patch
relayfs-use-flush_keventd_work.patch
tg3-use-flush_keventd_work.patch
e1000-use-flush_keventd_work.patch
libata-use-flush_work.patch
phy-use-flush_work.patch
call-cpu_chain-with-cpu_down_failed-if-cpu_down_prepare-failed.patch
slab-use-cpu_lock_.patch
workqueue-fix-freezeable-workqueues-implementation.patch
workqueue-fix-flush_workqueue-vs-cpu_dead-race.patch
workqueue-dont-clear-cwq-thread-until-it-exits.patch
workqueue-dont-migrate-pending-works-from-the-dead-cpu.patch
workqueue-kill-run_scheduled_work.patch
workqueue-dont-save-interrupts-in-run_workqueue.patch
workqueue-make-cancel_rearming_delayed_workqueue-work-on-idle-dwork.patch
workqueue-introduce-cpu_singlethread_map.patch
workqueue-introduce-workqueue_struct-singlethread.patch
workqueue-make-init_workqueues-__init.patch
workqueues-shift-kthread_bind-from-cpu_up_prepare-to-cpu_online.patch
make-queue_delayed_work-friendly-to-flush_fork.patch
unify-queue_delayed_work-and-queue_delayed_work_on.patch
workqueue-introduce-wq_per_cpu-helper.patch
make-cancel_rearming_delayed_work-work-on-any-workqueue-not-just-keventd_wq.patch
ipvs-flush-defense_work-before-module-unload.patch
workqueue-kill-noautorel-works.patch
worker_thread-dont-play-with-signals.patch
worker_thread-fix-racy-try_to_freeze-usage.patch
zap_other_threads-remove-unneeded-exit_signal-change.patch
slab-shutdown-cache_reaper-when-cpu-goes-down.patch
unify-flush_work-flush_work_keventd-and-rename-it-to-cancel_work_sync.patch
____call_usermodehelper-dont-flush_signals.patch
freezer-read-pf_borrowed_mm-in-a-nonracy-way.patch
freezer-close-theoretical-race-between-refrigerator-and-thaw_tasks.patch
freezer-remove-pf_nofreeze-from-rcutorture-thread.patch
freezer-remove-pf_nofreeze-from-bluetooth-threads.patch
freezer-add-try_to_freeze-calls-to-all-kernel-threads.patch
freezer-fix-vfork-problem.patch
freezer-take-kernel_execve-into-consideration.patch
kthread-dont-depend-on-work-queues-take-2.patch
change-reparent_to_init-to-reparent_to_kthreadd.patch
nlmclnt_recovery-dont-use-clone_sighand.patch
usbatm_heavy_init-dont-use-clone_sighand.patch
wait_for_helper-remove-unneeded-do_sigaction.patch
worker_thread-dont-play-with-sigchld-and-numa-policy.patch
change-kernel-threads-to-ignore-signals-instead-of-blocking-them.patch
fix-kthread_create-vs-freezer-theoretical-race.patch
fix-pf_nofreeze-and-freezeable-race-2.patch
freezer-document-task_lock-in-thaw_process.patch
move-frozen_process-to-kernel-power-processc.patch
remvoe-kthread_bind-call-from-_cpu_down.patch
separate-freezer-from-pm-code-rev-2.patch
introduce-freezer-flags-rev-2.patch
make-cancel_rearming_delayed_work-reliable.patch
make-cancel_rearming_delayed_work-reliable-spelling.patch
dont-init-pgrp-and-__session-in-init_signals.patch
add-suspend-related-notifications-for-cpu-hotplug-cleanup.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
