Merge branch 'md-next' of...

Merge branch 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.11/drivers

Pull MD changes from Song:

"Summary:
 1. Fix race condition in md_ioctl(), by Dae R. Jeong;
 2. Initialize read_slot properly for raid10, by Kevin Vigor;
 3. Code cleanup, by Pankaj Gupta;
 4. md-cluster resync/reshape fix, by Zhao Heming."

* 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md/cluster: fix deadlock when node is doing resync job
  md/cluster: block reshape with remote resync job
  md: use current request time as base for ktime comparisons
  md: add comments in md_flush_request()
  md: improve variable names in md_flush_request()
  md/raid10: initialize r10_bio->read_slot before use.
  md: fix a warning caused by a race between concurrent md_ioctl()s

drivers/md/md-cluster.c

@@ -664,9 +664,27 @@ static void recv_daemon(struct md_thread *thread)
  * Takes the lock on the TOKEN lock resource so no other
  * node can communicate while the operation is underway.
  */
-static int lock_token(struct md_cluster_info *cinfo, bool mddev_locked)
+static int lock_token(struct md_cluster_info *cinfo)
 {
-	int error, set_bit = 0;
+	int error;
+
+	error = dlm_lock_sync(cinfo->token_lockres, DLM_LOCK_EX);
+	if (error) {
+		pr_err("md-cluster(%s:%d): failed to get EX on TOKEN (%d)\n",
+				__func__, __LINE__, error);
+	} else {
+		/* Lock the receive sequence */
+		mutex_lock(&cinfo->recv_mutex);
+	}
+	return error;
+}
+
+/* lock_comm()
+ * Sets the MD_CLUSTER_SEND_LOCK bit to lock the send channel.
+ */
+static int lock_comm(struct md_cluster_info *cinfo, bool mddev_locked)
+{
+	int rv, set_bit = 0;
 	struct mddev *mddev = cinfo->mddev;
 
 	/*
@@ -677,34 +695,19 @@ static int lock_token(struct md_cluster_info *cinfo, bool mddev_locked)
 	 */
 	if (mddev_locked && !test_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD,
 				      &cinfo->state)) {
-		error = test_and_set_bit_lock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD,
+		rv = test_and_set_bit_lock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD,
 					      &cinfo->state);
-		WARN_ON_ONCE(error);
+		WARN_ON_ONCE(rv);
 		md_wakeup_thread(mddev->thread);
 		set_bit = 1;
 	}
-	error = dlm_lock_sync(cinfo->token_lockres, DLM_LOCK_EX);
-	if (set_bit)
-		clear_bit_unlock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
 
-	if (error)
-		pr_err("md-cluster(%s:%d): failed to get EX on TOKEN (%d)\n",
-				__func__, __LINE__, error);
-
-	/* Lock the receive sequence */
-	mutex_lock(&cinfo->recv_mutex);
-	return error;
-}
-
-/* lock_comm()
- * Sets the MD_CLUSTER_SEND_LOCK bit to lock the send channel.
- */
-static int lock_comm(struct md_cluster_info *cinfo, bool mddev_locked)
-{
 	wait_event(cinfo->wait,
 		   !test_and_set_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state));
-
-	return lock_token(cinfo, mddev_locked);
+	rv = lock_token(cinfo);
+	if (set_bit)
+		clear_bit_unlock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
+	return rv;
 }
 
 static void unlock_comm(struct md_cluster_info *cinfo)
@@ -784,9 +787,11 @@ static int sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg,
 {
 	int ret;
 
-	lock_comm(cinfo, mddev_locked);
-	ret = __sendmsg(cinfo, cmsg);
-	unlock_comm(cinfo);
+	ret = lock_comm(cinfo, mddev_locked);
+	if (!ret) {
+		ret = __sendmsg(cinfo, cmsg);
+		unlock_comm(cinfo);
+	}
 	return ret;
 }
 
@@ -1061,7 +1066,7 @@ static int metadata_update_start(struct mddev *mddev)
 		return 0;
 	}
 
-	ret = lock_token(cinfo, 1);
+	ret = lock_token(cinfo);
 	clear_bit_unlock(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state);
 	return ret;
 }
@@ -1255,7 +1260,10 @@ static void update_size(struct mddev *mddev, sector_t old_dev_sectors)
 	int raid_slot = -1;
 
 	md_update_sb(mddev, 1);
-	lock_comm(cinfo, 1);
+	if (lock_comm(cinfo, 1)) {
+		pr_err("%s: lock_comm failed\n", __func__);
+		return;
+	}
 
 	memset(&cmsg, 0, sizeof(cmsg));
 	cmsg.type = cpu_to_le32(METADATA_UPDATED);
@@ -1407,7 +1415,8 @@ static int add_new_disk(struct mddev *mddev, struct md_rdev *rdev)
 	cmsg.type = cpu_to_le32(NEWDISK);
 	memcpy(cmsg.uuid, uuid, 16);
 	cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
-	lock_comm(cinfo, 1);
+	if (lock_comm(cinfo, 1))
+		return -EAGAIN;
 	ret = __sendmsg(cinfo, &cmsg);
 	if (ret) {
 		unlock_comm(cinfo);

drivers/md/md.c

@@ -639,7 +639,7 @@ static void md_submit_flush_data(struct work_struct *ws)
 	 * could wait for this and below md_handle_request could wait for those
 	 * bios because of suspend check
 	 */
-	mddev->last_flush = mddev->start_flush;
+	mddev->prev_flush_start = mddev->start_flush;
 	mddev->flush_bio = NULL;
 	wake_up(&mddev->sb_wait);
 
@@ -660,13 +660,17 @@ static void md_submit_flush_data(struct work_struct *ws)
  */
 bool md_flush_request(struct mddev *mddev, struct bio *bio)
 {
-	ktime_t start = ktime_get_boottime();
+	ktime_t req_start = ktime_get_boottime();
 	spin_lock_irq(&mddev->lock);
+	/* flush requests wait until ongoing flush completes,
+	 * hence coalescing all the pending requests.
+	 */
 	wait_event_lock_irq(mddev->sb_wait,
 			    !mddev->flush_bio ||
-			    ktime_after(mddev->last_flush, start),
+			    ktime_before(req_start, mddev->prev_flush_start),
 			    mddev->lock);
-	if (!ktime_after(mddev->last_flush, start)) {
+	/* new request after previous flush is completed */
+	if (ktime_after(req_start, mddev->prev_flush_start)) {
 		WARN_ON(mddev->flush_bio);
 		mddev->flush_bio = bio;
 		bio = NULL;
@@ -6949,8 +6953,10 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev)
 		goto busy;
 
 kick_rdev:
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->remove_disk(mddev, rdev);
+	if (mddev_is_clustered(mddev)) {
+		if (md_cluster_ops->remove_disk(mddev, rdev))
+			goto busy;
+	}
 
 	md_kick_rdev_from_array(rdev);
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
@@ -7279,6 +7285,7 @@ static int update_raid_disks(struct mddev *mddev, int raid_disks)
 		return -EINVAL;
 	if (mddev->sync_thread ||
 	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	    test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) ||
 	    mddev->reshape_position != MaxSector)
 		return -EBUSY;
 
@@ -7589,8 +7596,11 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			err = -EBUSY;
 			goto out;
 		}
-		WARN_ON_ONCE(test_bit(MD_CLOSING, &mddev->flags));
-		set_bit(MD_CLOSING, &mddev->flags);
+		if (test_and_set_bit(MD_CLOSING, &mddev->flags)) {
+			mutex_unlock(&mddev->open_mutex);
+			err = -EBUSY;
+			goto out;
+		}
 		did_set_md_closing = true;
 		mutex_unlock(&mddev->open_mutex);
 		sync_blockdev(bdev);
@@ -9660,8 +9670,11 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 		}
 	}
 
-	if (mddev->raid_disks != le32_to_cpu(sb->raid_disks))
-		update_raid_disks(mddev, le32_to_cpu(sb->raid_disks));
+	if (mddev->raid_disks != le32_to_cpu(sb->raid_disks)) {
+		ret = update_raid_disks(mddev, le32_to_cpu(sb->raid_disks));
+		if (ret)
+			pr_warn("md: updating array disks failed. %d\n", ret);
+	}
 
 	/*
 	 * Since mddev->delta_disks has already updated in update_raid_disks,

drivers/md/md.h

@@ -495,9 +495,9 @@ struct mddev {
 	 */
 	struct bio *flush_bio;
 	atomic_t flush_pending;
-	ktime_t start_flush, last_flush; /* last_flush is when the last completed
-					  * flush was started.
-					  */
+	ktime_t start_flush, prev_flush_start; /* prev_flush_start is when the previous completed
+						* flush was started.
+						*/
 	struct work_struct flush_work;
 	struct work_struct event_work;	/* used by dm to report failure event */
 	mempool_t *serial_info_pool;

drivers/md/raid10.c

@@ -1127,7 +1127,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	struct md_rdev *err_rdev = NULL;
 	gfp_t gfp = GFP_NOIO;
 
-	if (r10_bio->devs[slot].rdev) {
+	if (slot >= 0 && r10_bio->devs[slot].rdev) {
 		/*
 		 * This is an error retry, but we cannot
 		 * safely dereference the rdev in the r10_bio,
@@ -1508,6 +1508,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 	r10_bio->mddev = mddev;
 	r10_bio->sector = bio->bi_iter.bi_sector;
 	r10_bio->state = 0;
+	r10_bio->read_slot = -1;
 	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->geo.raid_disks);
 
 	if (bio_data_dir(bio) == READ)