Merge tag 'md-6.8-20240216' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into block-6.8

Pull MD fixes from Song:

"1. Fix issues reported for dm-raid [1], by Yu Kuai. Please note that
    this PR only contains the first half of the set [2]. We still need
    more fixes in dm and md code (the rest of the set, or alternative
    fixes).
 2. Fix active_io leak, by Yu Kuai. The fix was posted in the same set
    [2]. But it actually fixes a separate issue [3].

 [1] https://lore.kernel.org/linux-raid/e5e8afe2-e9a8-49a2-5ab0-958d4065c55e@redhat.com/
 [2] https://lore.kernel.org/linux-raid/20240201092559.910982-1-yukuai1@huaweicloud.com/
 [3] https://lore.kernel.org/linux-raid/20240130172524.0000417b@linux.intel.com/ "

* tag 'md-6.8-20240216' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md: Don't suspend the array for interrupted reshape
  md: Don't register sync_thread for reshape directly
  md: Make sure md_do_sync() will set MD_RECOVERY_DONE
  md: Don't ignore read-only array in md_check_recovery()
  md: Don't ignore suspended array in md_check_recovery()
  md: Fix missing release of 'active_io' for flush

1 files changed, 2 insertions, 27 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8497880135ee..6a7a32f7fb91 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7936,11 +7936,7 @@ static int raid5_run(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		rcu_assign_pointer(mddev->sync_thread,
-			md_register_thread(md_do_sync, mddev, "reshape"));
-		if (!mddev->sync_thread)
-			goto abort;
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 
 	/* Ok, everything is just fine now */
@@ -8506,29 +8502,8 @@ static int raid5_start_reshape(struct mddev *mddev)
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "reshape"));
-	if (!mddev->sync_thread) {
-		mddev->recovery = 0;
-		spin_lock_irq(&conf->device_lock);
-		write_seqcount_begin(&conf->gen_lock);
-		mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks;
-		mddev->new_chunk_sectors =
-			conf->chunk_sectors = conf->prev_chunk_sectors;
-		mddev->new_layout = conf->algorithm = conf->prev_algo;
-		rdev_for_each(rdev, mddev)
-			rdev->new_data_offset = rdev->data_offset;
-		smp_wmb();
-		conf->generation --;
-		conf->reshape_progress = MaxSector;
-		mddev->reshape_position = MaxSector;
-		write_seqcount_end(&conf->gen_lock);
-		spin_unlock_irq(&conf->device_lock);
-		return -EAGAIN;
-	}
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	conf->reshape_checkpoint = jiffies;
-	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 }