Revert "md: don't unregister sync_thread with reconfig_mutex held"

The 07reshape5intr test is broke because of below path.

    md_reap_sync_thread
            -> mddev_unlock
            -> md_unregister_thread(&mddev->sync_thread)

And md_check_recovery is triggered by,

mddev_unlock -> md_wakeup_thread(mddev->thread)

then mddev->reshape_position is set to MaxSector in raid5_finish_reshape
since MD_RECOVERY_INTR is cleared in md_check_recovery, which means
feature_map is not set with MD_FEATURE_RESHAPE_ACTIVE and superblock's
reshape_position can't be updated accordingly.

Fixes: d0d1827b64334 ("md: don't unregister sync_thread with reconfig_mutex held")
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Guoqing Jiang <guoqing.jiang@linux.dev>
Signed-off-by: Song Liu <song@kernel.org>

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 5e41fbae3f6b05918d1a6c7e0471dad79f5d6051..9526ccbedafbac9ad74c413b2968a3bdc5da776d 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, false);
+                       md_reap_sync_thread(mddev);
                }
        } 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 8273ac5eef06a30fd9ccfcdc7b33a241a07f9f3d..c7ecb0bffda0d58678c57fa44be99aebf73f20d3 100644 (file)
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4831,7 +4831,7 @@ 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, true);
+                               md_reap_sync_thread(mddev);
                        }
                        mddev_unlock(mddev);
                }
@@ -6197,7 +6197,7 @@ 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, true);
+               md_reap_sync_thread(mddev);
        }
 
        del_timer_sync(&mddev->safemode_timer);
@@ -9303,7 +9303,7 @@ 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, true);
+                       md_reap_sync_thread(mddev);
                        clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
                        clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
                        clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
@@ -9338,7 +9338,7 @@ void md_check_recovery(struct mddev *mddev)
                        goto unlock;
                }
                if (mddev->sync_thread) {
-                       md_reap_sync_thread(mddev, true);
+                       md_reap_sync_thread(mddev);
                        goto unlock;
                }
                /* Set RUNNING before clearing NEEDED to avoid
@@ -9411,18 +9411,14 @@ void md_check_recovery(struct mddev *mddev)
 }
 EXPORT_SYMBOL(md_check_recovery);
 
-void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held)
+void md_reap_sync_thread(struct mddev *mddev)
 {
        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 5f62c46ac2d33e7fdf2228da72d946a8ba550e49..cf2cbb17acbd423ccebf7d1a008fc47ae07ed6a5 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, bool reconfig_mutex_held);
+extern void md_reap_sync_thread(struct mddev *mddev);
 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);