[1/2] Revert "md/raid5: Wait for MD_SB_CHANGE_PENDING in raid5d"

Commit Message

Junxiao Bi Nov. 7, 2023, 5:57 p.m. UTC

This reverts commit 5e2cf333b7bd5d3e62595a44d598a254c697cd74.

That commit introduced the following race and can cause system hung.

 md_write_start:                                                                        raid5d:
 if (mddev->safemode == 1)
     mddev->safemode = 0;
 /* sync_checkers is always 0 when writes_pending is in per-cpu mode */
 if (mddev->in_sync || mddev->sync_checkers) {
     spin_lock(&mddev->lock);
     if (mddev->in_sync) {
         mddev->in_sync = 0;
         set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
         set_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
                                                                                        >>> running before md_write_start wake up it
                                                                                        if (mddev->sb_flags & ~(1 << MD_SB_CHANGE_PENDING)) {
                                                                                              spin_unlock_irq(&conf->device_lock);
                                                                                              md_check_recovery(mddev);
                                                                                              spin_lock_irq(&conf->device_lock);

                                                                                              /*
                                                                                               * Waiting on MD_SB_CHANGE_PENDING below may deadlock
                                                                                               * seeing md_check_recovery() is needed to clear
                                                                                               * the flag when using mdmon.
                                                                                               */
                                                                                              continue;
                                                                                         }

                                                                                         wait_event_lock_irq(mddev->sb_wait,     >>>>>>>>>>> hung
                                                                                             !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
                                                                                             conf->device_lock);
         md_wakeup_thread(mddev->thread);
         did_change = 1;
     }
     spin_unlock(&mddev->lock);
 }

 ...

 wait_event(mddev->sb_wait,    >>>>>>>>>> hung
    !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) ||
    mddev->suspended);

Next patch will fix the issue that reverted commit is fixing in a new way.

Fixes: 5e2cf333b7bd ("md/raid5: Wait for MD_SB_CHANGE_PENDING in raid5d")
Signed-off-by: Junxiao Bi <[e-mail]>
---
 drivers/md/raid5.c | 12 ------------
 1 file changed, 12 deletions(-)

Patch

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index dc031d42f53b..fcc8a44dd4fd 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -36,7 +36,6 @@ 
  */
 
 #include <linux/blkdev.h>
-#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
@@ -6820,18 +6819,7 @@  static void raid5d(struct md_thread *thread)
 			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
 			spin_lock_irq(&conf->device_lock);
-
-			/*
-			 * Waiting on MD_SB_CHANGE_PENDING below may deadlock
-			 * seeing md_check_recovery() is needed to clear
-			 * the flag when using mdmon.
-			 */
-			continue;
 		}
-
-		wait_event_lock_irq(mddev->sb_wait,
-			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
-			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);