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

drivers/md/md.c

@@ -579,8 +579,12 @@ static void submit_flushes(struct work_struct *ws)
 			rcu_read_lock();
 		}
 	rcu_read_unlock();
-	if (atomic_dec_and_test(&mddev->flush_pending))
+	if (atomic_dec_and_test(&mddev->flush_pending)) {
+		/* The pair is percpu_ref_get() from md_flush_request() */
+		percpu_ref_put(&mddev->active_io);
+
 		queue_work(md_wq, &mddev->flush_work);
+	}
 }
 
 static void md_submit_flush_data(struct work_struct *ws)
@@ -8788,12 +8792,16 @@ void md_do_sync(struct md_thread *thread)
 	int ret;
 
 	/* just incase thread restarts... */
-	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
+	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
-	    test_bit(MD_RECOVERY_WAIT, &mddev->recovery))
 		return;
-	if (!md_is_rdwr(mddev)) {/* never try to sync a read-only array */
+
+	if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+		goto skip;
+
+	if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) ||
+	    !md_is_rdwr(mddev)) {/* never try to sync a read-only array */
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-		return;
+		goto skip;
 	}
 
 	if (mddev_is_clustered(mddev)) {
@@ -9368,13 +9376,19 @@ static void md_start_sync(struct work_struct *ws)
 	struct mddev *mddev = container_of(ws, struct mddev, sync_work);
 	int spares = 0;
 	bool suspend = false;
+	char *name;
 
-	if (md_spares_need_change(mddev))
+	/*
+	 * If reshape is still in progress, spares won't be added or removed
+	 * from conf until reshape is done.
+	 */
+	if (mddev->reshape_position == MaxSector &&
+	    md_spares_need_change(mddev)) {
 		suspend = true;
+		mddev_suspend(mddev, false);
+	}
 
-	suspend ? mddev_suspend_and_lock_nointr(mddev) :
+	mddev_lock_nointr(mddev);
-		  mddev_lock_nointr(mddev);
-
 	if (!md_is_rdwr(mddev)) {
 		/*
 		 * On a read-only array we can:
@@ -9400,8 +9414,10 @@ static void md_start_sync(struct work_struct *ws)
 	if (spares)
 		md_bitmap_write_all(mddev->bitmap);
 
+	name = test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ?
+			"reshape" : "resync";
 	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "resync"));
+			   md_register_thread(md_do_sync, mddev, name));
 	if (!mddev->sync_thread) {
 		pr_warn("%s: could not start resync thread...\n",
 			mdname(mddev));
@@ -9445,6 +9461,20 @@ not_running:
 		sysfs_notify_dirent_safe(mddev->sysfs_action);
 }
 
+static void unregister_sync_thread(struct mddev *mddev)
+{
+	if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
+		/* resync/recovery still happening */
+		clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		return;
+	}
+
+	if (WARN_ON_ONCE(!mddev->sync_thread))
+		return;
+
+	md_reap_sync_thread(mddev);
+}
+
 /*
  * This routine is regularly called by all per-raid-array threads to
  * deal with generic issues like resync and super-block update.
@@ -9469,9 +9499,6 @@ not_running:
  */
 void md_check_recovery(struct mddev *mddev)
 {
-	if (READ_ONCE(mddev->suspended))
-		return;
-
 	if (mddev->bitmap)
 		md_bitmap_daemon_work(mddev);
 
@@ -9485,7 +9512,8 @@ void md_check_recovery(struct mddev *mddev)
 	}
 
 	if (!md_is_rdwr(mddev) &&
-	    !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
+	    !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) &&
+	    !test_bit(MD_RECOVERY_DONE, &mddev->recovery))
 		return;
 	if ( ! (
 		(mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING)) ||
@@ -9507,8 +9535,7 @@ void md_check_recovery(struct mddev *mddev)
 			struct md_rdev *rdev;
 
 			if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-				/* sync_work already queued. */
+				unregister_sync_thread(mddev);
-				clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 				goto unlock;
 			}
 
@@ -9571,16 +9598,7 @@ void md_check_recovery(struct mddev *mddev)
 		 * still set.
 		 */
 		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-			if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
+			unregister_sync_thread(mddev);
-				/* resync/recovery still happening */
-				clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-				goto unlock;
-			}
-
-			if (WARN_ON_ONCE(!mddev->sync_thread))
-				goto unlock;
-
-			md_reap_sync_thread(mddev);
 			goto unlock;
 		}
 

drivers/md/raid10.c

@@ -4175,11 +4175,7 @@ static int raid10_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);
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-		rcu_assign_pointer(mddev->sync_thread,
-			md_register_thread(md_do_sync, mddev, "reshape"));
-		if (!mddev->sync_thread)
-			goto out_free_conf;
 	}
 
 	return 0;
@@ -4573,16 +4569,8 @@ out:
 	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);
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-
-	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "reshape"));
-	if (!mddev->sync_thread) {
-		ret = -EAGAIN;
-		goto abort;
-	}
 	conf->reshape_checkpoint = jiffies;
-	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 

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);
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-		rcu_assign_pointer(mddev->sync_thread,
-			md_register_thread(md_do_sync, mddev, "reshape"));
-		if (!mddev->sync_thread)
-			goto abort;
 	}
 
 	/* 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);
+	set_bit(MD_RECOVERY_NEEDED, &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;
-	}
 	conf->reshape_checkpoint = jiffies;
-	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 }