From f52f5c71f3d4bb0992800139d2f35cf9f6f6e0ee Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 5 Dec 2023 17:42:15 +0800 Subject: md: fix stopping sync thread Currently sync thread is stopped from multiple contex: - idle_sync_thread - frozen_sync_thread - __md_stop_writes - md_set_readonly - do_md_stop And there are some problems: 1) sync_work is flushed while reconfig_mutex is grabbed, this can deadlock because the work function will grab reconfig_mutex as well. 2) md_reap_sync_thread() can't be called directly while md_do_sync() is not finished yet, for example, commit 130443d60b1b ("md: refactor idle/frozen_sync_thread() to fix deadlock"). 3) If MD_RECOVERY_RUNNING is not set, there is no need to stop sync_thread at all because sync_thread must not be registered. Factor out a helper stop_sync_thread(), so that above contex will behave the same. Fix 1) by flushing sync_work after reconfig_mutex is released, before waiting for sync_thread to be done; Fix 2) bt letting daemon thread to unregister sync_thread; Fix 3) by always checking MD_RECOVERY_RUNNING first. Fixes: db5e653d7c9f ("md: delay choosing sync action to md_start_sync()") Signed-off-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20231205094215.1824240-4-yukuai1@huaweicloud.com --- drivers/md/md.c | 90 ++++++++++++++++++++++++--------------------------------- 1 file changed, 37 insertions(+), 53 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 2d8e45a1af23..bc9d67af1961 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4840,25 +4840,29 @@ action_show(struct mddev *mddev, char *page) return sprintf(page, "%s\n", type); } -static void stop_sync_thread(struct mddev *mddev) +/** + * stop_sync_thread() - wait for sync_thread to stop if it's running. + * @mddev: the array. + * @locked: if set, reconfig_mutex will still be held after this function + * return; if not set, reconfig_mutex will be released after this + * function return. + * @check_seq: if set, only wait for curent running sync_thread to stop, noted + * that new sync_thread can still start. + */ +static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq) { - if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) - return; + int sync_seq; - if (mddev_lock(mddev)) - return; + if (check_seq) + sync_seq = atomic_read(&mddev->sync_seq); - /* - * Check again in case MD_RECOVERY_RUNNING is cleared before lock is - * held. - */ if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { - mddev_unlock(mddev); + if (!locked) + mddev_unlock(mddev); return; } - if (work_pending(&mddev->sync_work)) - flush_workqueue(md_misc_wq); + mddev_unlock(mddev); set_bit(MD_RECOVERY_INTR, &mddev->recovery); /* @@ -4866,21 +4870,28 @@ static void stop_sync_thread(struct mddev *mddev) * never happen */ md_wakeup_thread_directly(mddev->sync_thread); + if (work_pending(&mddev->sync_work)) + flush_work(&mddev->sync_work); - mddev_unlock(mddev); + wait_event(resync_wait, + !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || + (check_seq && sync_seq != atomic_read(&mddev->sync_seq))); + + if (locked) + mddev_lock_nointr(mddev); } static void idle_sync_thread(struct mddev *mddev) { - int sync_seq = atomic_read(&mddev->sync_seq); - mutex_lock(&mddev->sync_mutex); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - stop_sync_thread(mddev); - wait_event(resync_wait, sync_seq != atomic_read(&mddev->sync_seq) || - !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)); + if (mddev_lock(mddev)) { + mutex_unlock(&mddev->sync_mutex); + return; + } + stop_sync_thread(mddev, false, true); mutex_unlock(&mddev->sync_mutex); } @@ -4888,11 +4899,13 @@ static void frozen_sync_thread(struct mddev *mddev) { mutex_lock(&mddev->sync_mutex); set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - stop_sync_thread(mddev); - wait_event(resync_wait, mddev->sync_thread == NULL && - !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)); + if (mddev_lock(mddev)) { + mutex_unlock(&mddev->sync_mutex); + return; + } + stop_sync_thread(mddev, false, false); mutex_unlock(&mddev->sync_mutex); } @@ -6264,14 +6277,7 @@ static void md_clean(struct mddev *mddev) static void __md_stop_writes(struct mddev *mddev) { - set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - if (work_pending(&mddev->sync_work)) - flush_workqueue(md_misc_wq); - if (mddev->sync_thread) { - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_reap_sync_thread(mddev); - } - + stop_sync_thread(mddev, true, false); del_timer_sync(&mddev->safemode_timer); if (mddev->pers && mddev->pers->quiesce) { @@ -6363,18 +6369,8 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); md_wakeup_thread(mddev->thread); } - if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - - /* - * Thread might be blocked waiting for metadata update which will now - * never happen - */ - md_wakeup_thread_directly(mddev->sync_thread); - mddev_unlock(mddev); - wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING, - &mddev->recovery)); + stop_sync_thread(mddev, false, false); wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); mddev_lock_nointr(mddev); @@ -6428,20 +6424,8 @@ static int do_md_stop(struct mddev *mddev, int mode, set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); md_wakeup_thread(mddev->thread); } - if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - /* - * Thread might be blocked waiting for metadata update which will now - * never happen - */ - md_wakeup_thread_directly(mddev->sync_thread); - - mddev_unlock(mddev); - wait_event(resync_wait, (mddev->sync_thread == NULL && - !test_bit(MD_RECOVERY_RUNNING, - &mddev->recovery))); - mddev_lock_nointr(mddev); + stop_sync_thread(mddev, true, false); mutex_lock(&mddev->open_mutex); if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) || -- cgit v1.2.3