blk-mq: fix hang caused by freeze/unfreeze sequence

The following is a description of a hang in blk_mq_freeze_queue_wait().
The hang happens on attempt to freeze a queue while another task does
queue unfreeze.

The root cause is an incorrect sequence of percpu_ref_resurrect() and
percpu_ref_kill() and as a result those two can be swapped:

 CPU#0                         CPU#1
 ----------------              -----------------
 q1 = blk_mq_init_queue(shared_tags)

                                q2 = blk_mq_init_queue(shared_tags):
                                  blk_mq_add_queue_tag_set(shared_tags):
                                    blk_mq_update_tag_set_depth(shared_tags):
				     list_for_each_entry()
                                      blk_mq_freeze_queue(q1)
                                       > percpu_ref_kill()
                                       > blk_mq_freeze_queue_wait()

 blk_cleanup_queue(q1)
  blk_mq_freeze_queue(q1)
   > percpu_ref_kill()
                 ^^^^^^ freeze_depth can't guarantee the order

                                      blk_mq_unfreeze_queue()
                                        > percpu_ref_resurrect()

   > blk_mq_freeze_queue_wait()
                 ^^^^^^ Hang here!!!!

This wrong sequence raises kernel warning:
percpu_ref_kill_and_confirm called more than once on blk_queue_usage_counter_release!
WARNING: CPU: 0 PID: 11854 at lib/percpu-refcount.c:336 percpu_ref_kill_and_confirm+0x99/0xb0

But the most unpleasant effect is a hang of a blk_mq_freeze_queue_wait(),
which waits for a zero of a q_usage_counter, which never happens
because percpu-ref was reinited (instead of being killed) and stays in
PERCPU state forever.

How to reproduce:
 - "insmod null_blk.ko shared_tags=1 nr_devices=0 queue_mode=2"
 - cpu0: python Script.py 0; taskset the corresponding process running on cpu0
 - cpu1: python Script.py 1; taskset the corresponding process running on cpu1

 Script.py:
 ------
 #!/usr/bin/python3

import os
import sys

while True:
    on = "echo 1 > /sys/kernel/config/nullb/%s/power" % sys.argv[1]
    off = "echo 0 > /sys/kernel/config/nullb/%s/power" % sys.argv[1]
    os.system(on)
    os.system(off)
------

This bug was first reported and fixed by Roman, previous discussion:
[1] Message id: 1443287365-4244-7-git-send-email-akinobu.mita@gmail.com
[2] Message id: 1443563240-29306-6-git-send-email-tj@kernel.org
[3] https://patchwork.kernel.org/patch/9268199/

Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Roman Pen <roman.penyaev@profitbricks.com>
Signed-off-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 18 insertions, 11 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 419d600e6637..1bf83a0df0f6 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -413,7 +413,7 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 		smp_rmb();
 
 		wait_event(q->mq_freeze_wq,
-			   (atomic_read(&q->mq_freeze_depth) == 0 &&
+			   (!q->mq_freeze_depth &&
 			    (pm || (blk_pm_request_resume(q),
 				    !blk_queue_pm_only(q)))) ||
 			   blk_queue_dying(q));
@@ -503,6 +503,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	spin_lock_init(&q->queue_lock);
 
 	init_waitqueue_head(&q->mq_freeze_wq);
+	mutex_init(&q->mq_freeze_lock);
 
 	/*
 	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 08a6248d8536..32b8ad3d341b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -144,13 +144,14 @@ void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
 
 void blk_freeze_queue_start(struct request_queue *q)
 {
-	int freeze_depth;
-
-	freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
-	if (freeze_depth == 1) {
+	mutex_lock(&q->mq_freeze_lock);
+	if (++q->mq_freeze_depth == 1) {
 		percpu_ref_kill(&q->q_usage_counter);
+		mutex_unlock(&q->mq_freeze_lock);
 		if (queue_is_mq(q))
 			blk_mq_run_hw_queues(q, false);
+	} else {
+		mutex_unlock(&q->mq_freeze_lock);
 	}
 }
 EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
@@ -199,14 +200,14 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
 void blk_mq_unfreeze_queue(struct request_queue *q)
 {
-	int freeze_depth;
-
-	freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
-	WARN_ON_ONCE(freeze_depth < 0);
-	if (!freeze_depth) {
+	mutex_lock(&q->mq_freeze_lock);
+	q->mq_freeze_depth--;
+	WARN_ON_ONCE(q->mq_freeze_depth < 0);
+	if (!q->mq_freeze_depth) {
 		percpu_ref_resurrect(&q->q_usage_counter);
 		wake_up_all(&q->mq_freeze_wq);
 	}
+	mutex_unlock(&q->mq_freeze_lock);
 }
 EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1aafeb923e7b..592669bcc536 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -542,7 +542,7 @@ struct request_queue {
 	struct list_head	unused_hctx_list;
 	spinlock_t		unused_hctx_lock;
 
-	atomic_t		mq_freeze_depth;
+	int			mq_freeze_depth;
 
 #if defined(CONFIG_BLK_DEV_BSG)
 	struct bsg_class_device bsg_dev;
@@ -554,6 +554,11 @@ struct request_queue {
 #endif
 	struct rcu_head		rcu_head;
 	wait_queue_head_t	mq_freeze_wq;
+	/*
+	 * Protect concurrent access to q_usage_counter by
+	 * percpu_ref_kill() and percpu_ref_reinit().
+	 */
+	struct mutex		mq_freeze_lock;
 	struct percpu_ref	q_usage_counter;
 
 	struct blk_mq_tag_set	*tag_set;