From 1fe782f0126cb4cb0b4e8d87b5c9458d1640698e Mon Sep 17 00:00:00 2001 From: Li Nan Date: Sat, 3 Jun 2023 14:50:36 +0800 Subject: [PATCH] md/raid10: fix taks hung in raid10d hulk inclusion category: bugfix bugzilla: 188380, https://gitee.com/openeuler/kernel/issues/I6GISC CVE: NA -------------------------------- commit fe630de009d0 ("md/raid10: avoid deadlock on recovery.") allowed normal io and sync io to exist at the same time. Task hung will occur as below: T1 T2 T3 T4 raid10d handle_read_error allow_barrier conf->nr_pending-- -> 0 //submit sync io raid10_sync_request raise_barrier ->will not be blocked ... //submit to drivers raid10_read_request wait_barrier conf->nr_pending++ -> 1 //retry read fail raid10_end_read_request reschedule_retry add to retry_list conf->nr_queued++ -> 1 //sync io fail end_sync_read __end_sync_read reschedule_retry add to retry_list conf->nr_queued++ -> 2 ... handle_read_error freeze_array wait nr_pending == nr_queued+1 ->1 ->3 //task hung retry read and sync io will be added to retry_list(nr_queued->2) if they fails. raid10d() called handle_read_error() and hung in freeze_array(). nr_queued will not decrease because raid10d is blocked, nr_pending will not increase because conf->barrier is not released. Fix it by moving allow_barrier() after raid10_read_request(). raise_barrier() will wait for nr_waiting to become 0. Therefore, sync io and regular io will not be issued at the same time. We also removed the check of nr_queued. It can be 0 but don't need to be blocked. MD_RECOVERY_RUNNING always is set after this patch, because all sync io is waitting in raise_barrier(), remove it, too. Fixes: fe630de009d0 ("md/raid10: avoid deadlock on recovery.") Signed-off-by: Li Nan Reviewed-by: Hou Tao --- drivers/md/raid10.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 74a4ba9f9cee..4bdf14f459fe 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -971,11 +971,15 @@ static bool stop_waiting_barrier(struct r10conf *conf) (!bio_list_empty(&bio_list[0]) || !bio_list_empty(&bio_list[1]))) return true; - /* move on if recovery thread is blocked by us */ - if (conf->mddev->thread->tsk == current && - test_bit(MD_RECOVERY_RUNNING, &conf->mddev->recovery) && - conf->nr_queued > 0) + /* + * move on if io is issued from raid10d(), nr_pending is not released + * from original io(see handle_read_error()). All raise barrier is + * blocked until this io is done. + */ + if (conf->mddev->thread->tsk == current) { + WARN_ON_ONCE(atomic_read(&conf->nr_pending) == 0); return true; + } return false; } @@ -2605,9 +2609,13 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio) md_error(mddev, rdev); rdev_dec_pending(rdev, mddev); - allow_barrier(conf); r10_bio->state = 0; raid10_read_request(mddev, r10_bio->master_bio, r10_bio, true); + /* + * allow_barrier after re-submit to ensure no sync io + * can be issued while regular io pending. + */ + allow_barrier(conf); } static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) -- GitLab