Merge tag 'for-5.11/drivers-2020-12-14' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Nothing major in here:

   - NVMe pull request from Christoph:
        - nvmet passthrough improvements (Chaitanya Kulkarni)
        - fcloop error injection support (James Smart)
        - read-only support for zoned namespaces without Zone Append
          (Javier González)
        - improve some error message (Minwoo Im)
        - reject I/O to offline fabrics namespaces (Victor Gladkov)
        - PCI queue allocation cleanups (Niklas Schnelle)
        - remove an unused allocation in nvmet (Amit Engel)
        - a Kconfig spelling fix (Colin Ian King)
        - nvme_req_qid simplication (Baolin Wang)

   - MD pull request from Song:
        - Fix race condition in md_ioctl() (Dae R. Jeong)
        - Initialize read_slot properly for raid10 (Kevin Vigor)
        - Code cleanup (Pankaj Gupta)
        - md-cluster resync/reshape fix (Zhao Heming)

   - Move null_blk into its own directory (Damien Le Moal)

   - null_blk zone and discard improvements (Damien Le Moal)

   - bcache race fix (Dongsheng Yang)

   - Set of rnbd fixes/improvements (Gioh Kim, Guoqing Jiang, Jack Wang,
     Lutz Pogrell, Md Haris Iqbal)

   - lightnvm NULL pointer deref fix (tangzhenhao)

   - sr in_interrupt() removal (Sebastian Andrzej Siewior)

   - FC endpoint security support for s390/dasd (Jan Höppner, Sebastian
     Ott, Vineeth Vijayan). From the s390 arch guys, arch bits included
     as it made it easier for them to funnel the feature through the
     block driver tree.

   - Follow up fixes (Colin Ian King)"

* tag 'for-5.11/drivers-2020-12-14' of git://git.kernel.dk/linux-block: (64 commits)
  block: drop dead assignments in loop_init()
  sr: Remove in_interrupt() usage in sr_init_command().
  sr: Switch the sector size back to 2048 if sr_read_sector() changed it.
  cdrom: Reset sector_size back it is not 2048.
  drivers/lightnvm: fix a null-ptr-deref bug in pblk-core.c
  null_blk: Move driver into its own directory
  null_blk: Allow controlling max_hw_sectors limit
  null_blk: discard zones on reset
  null_blk: cleanup discard handling
  null_blk: Improve implicit zone close
  null_blk: improve zone locking
  block: Align max_hw_sectors to logical blocksize
  null_blk: Fail zone append to conventional zones
  null_blk: Fix zone size initialization
  bcache: fix race between setting bdev state to none and new write request direct to backing
  block/rnbd: fix a null pointer dereference on dev->blk_symlink_name
  block/rnbd-clt: Dynamically alloc buffer for pathname & blk_symlink_name
  block/rnbd: call kobject_put in the failure path
  Documentation/ABI/rnbd-srv: add document for force_close
  block/rnbd-srv: close a mapped device from server side.
  ...

6 files changed, 75 insertions, 52 deletions

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 04fa40868fbe..0e06d721cd8e 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1114,9 +1114,6 @@ static void cancel_writeback_rate_update_dwork(struct cached_dev *dc)
 static void cached_dev_detach_finish(struct work_struct *w)
 {
 	struct cached_dev *dc = container_of(w, struct cached_dev, detach);
-	struct closure cl;
-
-	closure_init_stack(&cl);
 
 	BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags));
 	BUG_ON(refcount_read(&dc->count));
@@ -1130,12 +1127,6 @@ static void cached_dev_detach_finish(struct work_struct *w)
 		dc->writeback_thread = NULL;
 	}
 
-	memset(&dc->sb.set_uuid, 0, 16);
-	SET_BDEV_STATE(&dc->sb, BDEV_STATE_NONE);
-
-	bch_write_bdev_super(dc, &cl);
-	closure_sync(&cl);
-
 	mutex_lock(&bch_register_lock);
 
 	calc_cached_dev_sectors(dc->disk.c);
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 3c74996978da..a129e4d2707c 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -705,6 +705,15 @@ static int bch_writeback_thread(void *arg)
 			 * bch_cached_dev_detach().
 			 */
 			if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)) {
+				struct closure cl;
+
+				closure_init_stack(&cl);
+				memset(&dc->sb.set_uuid, 0, 16);
+				SET_BDEV_STATE(&dc->sb, BDEV_STATE_NONE);
+
+				bch_write_bdev_super(dc, &cl);
+				closure_sync(&cl);
+
 				up_write(&dc->writeback_lock);
 				break;
 			}
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 35e2690c1803..7fbd41e156c9 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -663,9 +663,27 @@ out:
  * 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;
 
 	/*
@@ -676,34 +694,19 @@ 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)
@@ -783,9 +786,11 @@ 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;
 }
 
@@ -1060,7 +1065,7 @@ 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;
 }
@@ -1254,7 +1259,10 @@ 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);
@@ -1403,7 +1411,8 @@ 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);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0445f44ae635..ca409428b4fc 100644
--- a/drivers/md/md.c
+++ b/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;
@@ -6944,8 +6948,10 @@ 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);
@@ -7274,6 +7280,7 @@ 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;
 
@@ -7584,8 +7591,11 @@ 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);
@@ -9634,8 +9644,11 @@ 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,
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 2175a5ac4f7c..34070ab30a8a 100644
--- a/drivers/md/md.h
+++ b/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;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 800fe0628d25..c5d88ef6a45c 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1128,7 +1128,7 @@ 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,
@@ -1491,6 +1491,7 @@ 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->copies);
 
 	if (bio_data_dir(bio) == READ)