diff options
| author | Ming Lei <ming.lei@redhat.com> | 2025-08-15 21:17:37 +0800 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2025-08-28 16:34:50 +0200 |
| commit | f9a9098ca82612006b9c71ce03b8fe189a437370 (patch) | |
| tree | b0a4cc6afef17dbdcdda3fa670ef8066640f5424 /block | |
| parent | e01facfb54a9b2e1ad7bbb00601a42b16d276d81 (diff) | |
| download | linux-f9a9098ca82612006b9c71ce03b8fe189a437370.tar.gz linux-f9a9098ca82612006b9c71ce03b8fe189a437370.tar.bz2 linux-f9a9098ca82612006b9c71ce03b8fe189a437370.zip | |
blk-mq: fix lockdep warning in __blk_mq_update_nr_hw_queues
[ Upstream commit 2d82f3bd8910eb65e30bb2a3c9b945bfb3b6d661 ]
Commit 5989bfe6ac6b ("block: restore two stage elevator switch while
running nr_hw_queue update") reintroduced a lockdep warning by calling
blk_mq_freeze_queue_nomemsave() before switching the I/O scheduler.
The function blk_mq_elv_switch_none() calls elevator_change_done().
Running this while the queue is frozen causes a lockdep warning.
Fix this by reordering the operations: first, switch the I/O scheduler
to 'none', and then freeze the queue. This ensures that elevator_change_done()
is not called on an already frozen queue. And this way is safe because
elevator_set_none() does freeze queue before switching to none.
Also we still have to rely on blk_mq_elv_switch_back() for switching
back, and it has to cover unfrozen queue case.
Cc: Nilay Shroff <nilay@linux.ibm.com>
Cc: Yu Kuai <yukuai3@huawei.com>
Fixes: 5989bfe6ac6b ("block: restore two stage elevator switch while running nr_hw_queue update")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Link: https://lore.kernel.org/r/20250815131737.331692-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Diffstat (limited to 'block')
| -rw-r--r-- | block/blk-mq.c | 13 |
1 files changed, 9 insertions, 4 deletions
diff --git a/block/blk-mq.c b/block/blk-mq.c index 4cb2f5ca8656..355db0abe44b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -5031,6 +5031,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, unsigned int memflags; int i; struct xarray elv_tbl, et_tbl; + bool queues_frozen = false; lockdep_assert_held(&set->tag_list_lock); @@ -5054,9 +5055,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, blk_mq_sysfs_unregister_hctxs(q); } - list_for_each_entry(q, &set->tag_list, tag_set_list) - blk_mq_freeze_queue_nomemsave(q); - /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done @@ -5066,6 +5064,9 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, if (blk_mq_elv_switch_none(q, &elv_tbl)) goto switch_back; + list_for_each_entry(q, &set->tag_list, tag_set_list) + blk_mq_freeze_queue_nomemsave(q); + queues_frozen = true; if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0) goto switch_back; @@ -5089,8 +5090,12 @@ fallback: } switch_back: /* The blk_mq_elv_switch_back unfreezes queue for us. */ - list_for_each_entry(q, &set->tag_list, tag_set_list) + list_for_each_entry(q, &set->tag_list, tag_set_list) { + /* switch_back expects queue to be frozen */ + if (!queues_frozen) + blk_mq_freeze_queue_nomemsave(q); blk_mq_elv_switch_back(q, &elv_tbl, &et_tbl); + } list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_sysfs_register_hctxs(q); |