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 <buczek@molgen.mpg.de>
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Song Liu <song@kernel.org>

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 9526ccbedafbac9ad74c413b2968a3bdc5da776d..5e41fbae3f6b05918d1a6c7e0471dad79f5d6051 100644 (file)
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3725,7 +3725,7 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
        if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
                if (mddev->sync_thread) {
                        set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-                       md_reap_sync_thread(mddev);
+                       md_reap_sync_thread(mddev, false);
                }
        } else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
                return -EBUSY;

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 707e802d0082a1ea8a1fd08f6cf259e8cc495ecd..1958a14a0c794add122f80360cc0c20b82563e45 100644 (file)
--- 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) {

diff --git a/drivers/md/md.h b/drivers/md/md.h
index cf2cbb17acbd423ccebf7d1a008fc47ae07ed6a5..5f62c46ac2d33e7fdf2228da72d946a8ba550e49 100644 (file)
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -719,7 +719,7 @@ extern struct md_thread *md_register_thread(
 extern void md_unregister_thread(struct md_thread **threadp);
 extern void md_wakeup_thread(struct md_thread *thread);
 extern void md_check_recovery(struct mddev *mddev);
-extern void md_reap_sync_thread(struct mddev *mddev);
+extern void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held);
 extern int mddev_init_writes_pending(struct mddev *mddev);
 extern bool md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);