releases/4.9.219/blk-mq-sync-the-update-nr_hw_queues-with-blk_mq_queue_tag_busy_iter.patch

From f5bbbbe4d63577026f908a809f22f5fd5a90ea1f Mon Sep 17 00:00:00 2001
From: Jianchao Wang <jianchao.w.wang@oracle.com>
Date: Tue, 21 Aug 2018 15:15:04 +0800
Subject: blk-mq: sync the update nr_hw_queues with blk_mq_queue_tag_busy_iter

From: Jianchao Wang <jianchao.w.wang@oracle.com>

commit f5bbbbe4d63577026f908a809f22f5fd5a90ea1f upstream.

For blk-mq, part_in_flight/rw will invoke blk_mq_in_flight/rw to
account the inflight requests. It will access the queue_hw_ctx and
nr_hw_queues w/o any protection. When updating nr_hw_queues and
blk_mq_in_flight/rw occur concurrently, panic comes up.

Before update nr_hw_queues, the q will be frozen. So we could use
q_usage_counter to avoid the race. percpu_ref_is_zero is used here
so that we will not miss any in-flight request. The access to
nr_hw_queues and queue_hw_ctx in blk_mq_queue_tag_busy_iter are
under rcu critical section, __blk_mq_update_nr_hw_queues could use
synchronize_rcu to ensure the zeroed q_usage_counter to be globally
visible.

Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Cc: Giuliano Procida <gprocida@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 block/blk-mq-tag.c |   14 +++++++++++++-
 block/blk-mq.c     |    4 ++++
 2 files changed, 17 insertions(+), 1 deletion(-)

--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -336,6 +336,18 @@ void blk_mq_queue_tag_busy_iter(struct r
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
+	/*
+	 * __blk_mq_update_nr_hw_queues will update the nr_hw_queues and
+	 * queue_hw_ctx after freeze the queue. So we could use q_usage_counter
+	 * to avoid race with it. __blk_mq_update_nr_hw_queues will users
+	 * synchronize_rcu to ensure all of the users go out of the critical
+	 * section below and see zeroed q_usage_counter.
+	 */
+	rcu_read_lock();
+	if (percpu_ref_is_zero(&q->q_usage_counter)) {
+		rcu_read_unlock();
+		return;
+	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		struct blk_mq_tags *tags = hctx->tags;
@@ -351,7 +363,7 @@ void blk_mq_queue_tag_busy_iter(struct r
 			bt_for_each(hctx, &tags->breserved_tags, fn, priv, true);
 		bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false);
 	}
-
+	rcu_read_unlock();
 }
 
 static unsigned int bt_unused_tags(const struct sbitmap_queue *bt)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2346,6 +2346,10 @@ void blk_mq_update_nr_hw_queues(struct b
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_unfreeze_queue(q);
+	/*
+	 * Sync with blk_mq_queue_tag_busy_iter.
+	 */
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);