Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull one last block fix from Jens Axboe:
 "We've had an issue with scsi-mq where probing takes forever.  This was
  bisected down to the percpu changes for blk_mq_queue_enter(), and the
  fact we now suffer an RCU grace period when killing a queue.  SCSI
  creates and destroys tons of queues, so this let to 10s of seconds of
  stalls at boot for some.

  Tejun has a real fix for this, but it's too involved for 3.17.  So
  this is a temporary workaround to expedite the queue killing until we
  can fold in the real fix for 3.18 when that merge window opens"

* 'for-linus' of git://git.kernel.dk/linux-block:
  blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall during probe

3 files changed, 27 insertions, 1 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index c88e6089746d..df8e1e09dd17 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -119,7 +119,16 @@ void blk_mq_freeze_queue(struct request_queue *q)
         spin_unlock_irq(q->queue_lock);
 
         if (freeze) {
-                percpu_ref_kill(&q->mq_usage_counter);
+                /*
+                 * XXX: Temporary kludge to work around SCSI blk-mq stall.
+                 * SCSI synchronously creates and destroys many queues
+                 * back-to-back during probe leading to lengthy stalls.
+                 * This will be fixed by keeping ->mq_usage_counter in
+                 * atomic mode until genhd registration, but, for now,
+                 * let's work around using expedited synchronization.
+                 */
+                __percpu_ref_kill_expedited(&q->mq_usage_counter);
+
                 blk_mq_run_queues(q, false);
         }
         wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter));
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 3dfbf237cd8f..ef5894ca8e50 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -71,6 +71,7 @@ void percpu_ref_reinit(struct percpu_ref *ref);
 void percpu_ref_exit(struct percpu_ref *ref);
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
                                  percpu_ref_func_t *confirm_kill);
+void __percpu_ref_kill_expedited(struct percpu_ref *ref);
 
 /**
  * percpu_ref_kill - drop the initial ref
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index fe5a3342e960..a89cf09a8268 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -184,3 +184,19 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
         call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
+
+/*
+ * XXX: Temporary kludge to work around SCSI blk-mq stall.  Used only by
+ * block/blk-mq.c::blk_mq_freeze_queue().  Will be removed during v3.18
+ * devel cycle.  Do not use anywhere else.
+ */
+void __percpu_ref_kill_expedited(struct percpu_ref *ref)
+{
+        WARN_ONCE(ref->pcpu_count_ptr & PCPU_REF_DEAD,
+                  "percpu_ref_kill() called more than once on %pf!",
+                  ref->release);
+
+        ref->pcpu_count_ptr |= PCPU_REF_DEAD;
+        synchronize_sched_expedited();
+        percpu_ref_kill_rcu(&ref->rcu);
+}