lkml.org 
[lkml]   [2007]   [May]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[PATCH] 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).

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>

--- OLD/kernel/workqueue.c~1_CRDW 2007-05-02 23:29:07.000000000 +0400
+++ OLD/kernel/workqueue.c 2007-05-03 22:42:29.000000000 +0400
@@ -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
@@ -381,7 +386,46 @@ 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;
@@ -398,20 +442,7 @@ 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;
@@ -421,29 +452,59 @@ 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
@@ -530,28 +591,6 @@ 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
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2007-05-03 22:45    [from the cache]
©2003-2011 Jasper Spaans