Revert "md: unlock mddev before reap sync_thread in action_store"

This reverts commit 9dfbdafda3b34e262e43e786077bab8e476a89d1.

Because it will introduce a defect that sync_thread can be running while
MD_RECOVERY_RUNNING is cleared, which will cause some unexpected problems,
for example:

list_add corruption. prev->next should be next (ffff0001ac1daba0), but was ffff0000ce1a02a0. (prev=ffff0000ce1a02a0).
Call trace:
 __list_add_valid+0xfc/0x140
 insert_work+0x78/0x1a0
 __queue_work+0x500/0xcf4
 queue_work_on+0xe8/0x12c
 md_check_recovery+0xa34/0xf30
 raid10d+0xb8/0x900 [raid10]
 md_thread+0x16c/0x2cc
 kthread+0x1a4/0x1ec
 ret_from_fork+0x10/0x18

This is because work is requeued while it's still inside workqueue:

t1:			t2:
action_store
 mddev_lock
  if (mddev->sync_thread)
   mddev_unlock
   md_unregister_thread
   // first sync_thread is done
			md_check_recovery
			 mddev_try_lock
			 /*
			  * once MD_RECOVERY_DONE is set, new sync_thread
			  * can start.
			  */
			 set_bit(MD_RECOVERY_RUNNING, &mddev->recovery)
			 INIT_WORK(&mddev->del_work, md_start_sync)
			 queue_work(md_misc_wq, &mddev->del_work)
			  test_and_set_bit(WORK_STRUCT_PENDING_BIT, ...)
			  // set pending bit
			  insert_work
			   list_add_tail
			 mddev_unlock
   mddev_lock_nointr
   md_reap_sync_thread
   // MD_RECOVERY_RUNNING is cleared
 mddev_unlock

t3:

// before queued work started from t2
md_check_recovery
 // MD_RECOVERY_RUNNING is not set, a new sync_thread can be started
 INIT_WORK(&mddev->del_work, md_start_sync)
  work->data = 0
  // work pending bit is cleared
 queue_work(md_misc_wq, &mddev->del_work)
  insert_work
   list_add_tail
   // list is corrupted

The above commit is reverted to fix the problem, the deadlock this
commit tries to fix will be fixed in following patches.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230529132037.2124527-2-yukuai1@huaweicloud.com

1 files changed, 2 insertions, 17 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 2e38ef421d69..d445d5fb7a01 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4764,19 +4764,6 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 			if (work_pending(&mddev->del_work))
 				flush_workqueue(md_misc_wq);
 			if (mddev->sync_thread) {
-				sector_t save_rp = mddev->reshape_position;
-
-				mddev_unlock(mddev);
-				set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-				md_unregister_thread(&mddev->sync_thread);
-				mddev_lock_nointr(mddev);
-				/*
-				 * set RECOVERY_INTR again and restore reshape
-				 * position in case others changed them after
-				 * got lock, eg, reshape_position_store and
-				 * md_check_recovery.
-				 */
-				mddev->reshape_position = save_rp;
 				set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 				md_reap_sync_thread(mddev);
 			}
@@ -6176,7 +6163,6 @@ 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_unregister_thread(&mddev->sync_thread);
 		md_reap_sync_thread(mddev);
 	}
 
@@ -9327,7 +9313,6 @@ void md_check_recovery(struct mddev *mddev)
 			 * ->spare_active and clear saved_raid_disk
 			 */
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_unregister_thread(&mddev->sync_thread);
 			md_reap_sync_thread(mddev);
 			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
@@ -9363,7 +9348,6 @@ void md_check_recovery(struct mddev *mddev)
 			goto unlock;
 		}
 		if (mddev->sync_thread) {
-			md_unregister_thread(&mddev->sync_thread);
 			md_reap_sync_thread(mddev);
 			goto unlock;
 		}
@@ -9443,7 +9427,8 @@ void md_reap_sync_thread(struct mddev *mddev)
 	sector_t old_dev_sectors = mddev->dev_sectors;
 	bool is_reshaped = false;
 
-	/* sync_thread should be unregistered, collect result */
+	/* resync has finished, collect result */
+	md_unregister_thread(&mddev->sync_thread);
 	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
 	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
 	    mddev->degraded != mddev->raid_disks) {