From 8b48ec23cc51a4e7c8dbaef5f34ebe67e1a80934 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Sat, 13 Feb 2021 01:49:59 +0100 Subject: md: don't unregister sync_thread with reconfig_mutex held Unregister sync_thread doesn't need to hold reconfig_mutex since it doesn't reconfigure array. And it could cause deadlock problem for raid5 as follows: 1. process A tried to reap sync thread with reconfig_mutex held after echo idle to sync_action. 2. raid5 sync thread was blocked if there were too many active stripes. 3. SB_CHANGE_PENDING was set (because of write IO comes from upper layer) which causes the number of active stripes can't be decreased. 4. SB_CHANGE_PENDING can't be cleared since md_check_recovery was not able to hold reconfig_mutex. More details in the link: https://lore.kernel.org/linux-raid/5ed54ffc-ce82-bf66-4eff-390cb23bc1ac@molgen.mpg.de/T/#t And add one parameter to md_reap_sync_thread since it could be called by dm-raid which doesn't hold reconfig_mutex. Reported-and-tested-by: Donald Buczek Signed-off-by: Guoqing Jiang Signed-off-by: Song Liu --- drivers/md/md.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 707e802d0082..1958a14a0c79 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4844,7 +4844,7 @@ action_store(struct mddev *mddev, const char *page, size_t len) flush_workqueue(md_misc_wq); if (mddev->sync_thread) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_reap_sync_thread(mddev); + md_reap_sync_thread(mddev, true); } mddev_unlock(mddev); } @@ -6213,7 +6213,7 @@ static void __md_stop_writes(struct mddev *mddev) flush_workqueue(md_misc_wq); if (mddev->sync_thread) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_reap_sync_thread(mddev); + md_reap_sync_thread(mddev, true); } del_timer_sync(&mddev->safemode_timer); @@ -9324,7 +9324,7 @@ void md_check_recovery(struct mddev *mddev) * ->spare_active and clear saved_raid_disk */ set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_reap_sync_thread(mddev); + md_reap_sync_thread(mddev, true); clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags); @@ -9359,7 +9359,7 @@ void md_check_recovery(struct mddev *mddev) goto unlock; } if (mddev->sync_thread) { - md_reap_sync_thread(mddev); + md_reap_sync_thread(mddev, true); goto unlock; } /* Set RUNNING before clearing NEEDED to avoid @@ -9432,14 +9432,18 @@ void md_check_recovery(struct mddev *mddev) } EXPORT_SYMBOL(md_check_recovery); -void md_reap_sync_thread(struct mddev *mddev) +void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held) { struct md_rdev *rdev; sector_t old_dev_sectors = mddev->dev_sectors; bool is_reshaped = false; + if (reconfig_mutex_held) + mddev_unlock(mddev); /* resync has finished, collect result */ md_unregister_thread(&mddev->sync_thread); + if (reconfig_mutex_held) + mddev_lock_nointr(mddev); if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && mddev->degraded != mddev->raid_disks) { -- cgit v1.2.3