X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=kernel%2Fkernel%2Fworkqueue.c;fp=kernel%2Fkernel%2Fworkqueue.c;h=d5b0f4fc0eb0c82a4a2fd09d5cc79f44a2335926;hb=52f993b8e89487ec9ee15a7fb4979e0f09a45b27;hp=efd1f5822f4e23072f9b79778548300f1593ea03;hpb=c189ccac5702322ed843fe17057035b7222a59b6;p=kvmfornfv.git

diff --git a/kernel/kernel/workqueue.c b/kernel/kernel/workqueue.c
index efd1f5822..d5b0f4fc0 100644
--- a/kernel/kernel/workqueue.c
+++ b/kernel/kernel/workqueue.c
@@ -683,6 +683,35 @@ static void set_work_pool_and_clear_pending(struct work_struct *work,
 	 */
 	smp_wmb();
 	set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0);
+	/*
+	 * The following mb guarantees that previous clear of a PENDING bit
+	 * will not be reordered with any speculative LOADS or STORES from
+	 * work->current_func, which is executed afterwards.  This possible
+	 * reordering can lead to a missed execution on attempt to qeueue
+	 * the same @work.  E.g. consider this case:
+	 *
+	 *   CPU#0                         CPU#1
+	 *   ----------------------------  --------------------------------
+	 *
+	 * 1  STORE event_indicated
+	 * 2  queue_work_on() {
+	 * 3    test_and_set_bit(PENDING)
+	 * 4 }                             set_..._and_clear_pending() {
+	 * 5                                 set_work_data() # clear bit
+	 * 6                                 smp_mb()
+	 * 7                               work->current_func() {
+	 * 8				      LOAD event_indicated
+	 *				   }
+	 *
+	 * Without an explicit full barrier speculative LOAD on line 8 can
+	 * be executed before CPU#0 does STORE on line 1.  If that happens,
+	 * CPU#0 observes the PENDING bit is still set and new execution of
+	 * a @work is not queued in a hope, that CPU#1 will eventually
+	 * finish the queued @work.  Meanwhile CPU#1 does not see
+	 * event_indicated is set, because speculative LOAD was executed
+	 * before actual STORE.
+	 */
+	smp_mb();
 }
 
 static void clear_work_data(struct work_struct *work)
@@ -1106,9 +1135,11 @@ 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);
 		put_pwq(pwq);
 		local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock);
+		rcu_read_unlock();
 	}
 }
 
@@ -4466,6 +4497,17 @@ static void rebind_workers(struct worker_pool *pool)
 						  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;
+	}
+
 	pool->flags &= ~POOL_DISASSOCIATED;
 
 	for_each_pool_worker(worker, pool) {