diff options
author | Jianchao Wang <jianchao.w.wang@oracle.com> | 2018-08-21 15:15:04 +0800 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2020-04-13 10:34:22 +0200 |
commit | 574eb136ec7f315c3ef2ca68fa9b3e16c56baa24 (patch) | |
tree | 3c9941c0ccd551656da46022d5758720f69c9bfc /block | |
parent | c0eab61c136f671bccdf7530dd86cdb66e4ae7ba (diff) | |
download | linux-stable-574eb136ec7f315c3ef2ca68fa9b3e16c56baa24.tar.gz linux-stable-574eb136ec7f315c3ef2ca68fa9b3e16c56baa24.tar.bz2 linux-stable-574eb136ec7f315c3ef2ca68fa9b3e16c56baa24.zip |
blk-mq: sync the update nr_hw_queues with blk_mq_queue_tag_busy_iter
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>
Diffstat (limited to 'block')
-rw-r--r-- | block/blk-mq-tag.c | 14 | ||||
-rw-r--r-- | block/blk-mq.c | 4 |
2 files changed, 17 insertions, 1 deletions
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 3d2ab65d2dd1..4c623ba0af86 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -334,6 +334,18 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, 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; @@ -349,7 +361,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, bt_for_each(hctx, &tags->breserved_tags, fn, priv, true); bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false); } - + rcu_read_unlock(); } static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, diff --git a/block/blk-mq.c b/block/blk-mq.c index eac444804736..9d53f476c517 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2748,6 +2748,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, 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(); } void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) |