Merge tag 'for-6.13/block-20241118' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Keith:
      - Use uring_cmd helper (Pavel)
      - Host Memory Buffer allocation enhancements (Christoph)
      - Target persistent reservation support (Guixin)
      - Persistent reservation tracing (Guixen)
      - NVMe 2.1 specification support (Keith)
      - Rotational Meta Support (Matias, Wang, Keith)
      - Volatile cache detection enhancment (Guixen)

 - MD updates via Song:
      - Maintainers update
      - raid5 sync IO fix
      - Enhance handling of faulty and blocked devices
      - raid5-ppl atomic improvement
      - md-bitmap fix

 - Support for manually defining embedded partition tables

 - Zone append fixes and cleanups

 - Stop sending the queued requests in the plug list to the driver
   ->queue_rqs() handle in reverse order.

 - Zoned write plug cleanups

 - Cleanups disk stats tracking and add support for disk stats for
   passthrough IO

 - Add preparatory support for file system atomic writes

 - Add lockdep support for queue freezing. Already found a bunch of
   issues, and some fixes for that are in here. More will be coming.

 - Fix race between queue stopping/quiescing and IO queueing

 - ublk recovery improvements

 - Fix ublk mmap for 64k pages

 - Various fixes and cleanups

* tag 'for-6.13/block-20241118' of git://git.kernel.dk/linux: (118 commits)
  MAINTAINERS: Update git tree for mdraid subsystem
  block: make struct rq_list available for !CONFIG_BLOCK
  block/genhd: use seq_put_decimal_ull for diskstats decimal values
  block: don't reorder requests in blk_mq_add_to_batch
  block: don't reorder requests in blk_add_rq_to_plug
  block: add a rq_list type
  block: remove rq_list_move
  virtio_blk: reverse request order in virtio_queue_rqs
  nvme-pci: reverse request order in nvme_queue_rqs
  btrfs: validate queue limits
  block: export blk_validate_limits
  nvmet: add tracing of reservation commands
  nvme: parse reservation commands's action and rtype to string
  nvmet: report ns's vwc not present
  md/raid5: Increase r5conf.cache_name size
  block: remove the ioprio field from struct request
  block: remove the write_hint field from struct request
  nvme: check ns's volatile write cache not present
  nvme: add rotational support
  nvme: use command set independent id ns if available
  ...

1 files changed, 64 insertions, 23 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 862b1fb71d86..18989231791a 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1159,6 +1159,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	int slot = r10_bio->read_slot;
 	struct md_rdev *err_rdev = NULL;
 	gfp_t gfp = GFP_NOIO;
+	int error;
 
 	if (slot >= 0 && r10_bio->devs[slot].rdev) {
 		/*
@@ -1206,6 +1207,10 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	if (max_sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, max_sectors,
 					      gfp, &conf->bio_split);
+		if (IS_ERR(split)) {
+			error = PTR_ERR(split);
+			goto err_handle;
+		}
 		bio_chain(split, bio);
 		allow_barrier(conf);
 		submit_bio_noacct(bio);
@@ -1236,6 +1241,11 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	mddev_trace_remap(mddev, read_bio, r10_bio->sector);
 	submit_bio_noacct(read_bio);
 	return;
+err_handle:
+	atomic_dec(&rdev->nr_pending);
+	bio->bi_status = errno_to_blk_status(error);
+	set_bit(R10BIO_Uptodate, &r10_bio->state);
+	raid_end_bio_io(r10_bio);
 }
 
 static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
@@ -1285,9 +1295,9 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 
 static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
 {
-	int i;
 	struct r10conf *conf = mddev->private;
 	struct md_rdev *blocked_rdev;
+	int i;
 
 retry_wait:
 	blocked_rdev = NULL;
@@ -1295,40 +1305,36 @@ retry_wait:
 		struct md_rdev *rdev, *rrdev;
 
 		rdev = conf->mirrors[i].rdev;
-		rrdev = conf->mirrors[i].replacement;
-		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
-			atomic_inc(&rdev->nr_pending);
-			blocked_rdev = rdev;
-			break;
-		}
-		if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) {
-			atomic_inc(&rrdev->nr_pending);
-			blocked_rdev = rrdev;
-			break;
-		}
-
-		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
+		if (rdev) {
 			sector_t dev_sector = r10_bio->devs[i].addr;
 
 			/*
 			 * Discard request doesn't care the write result
 			 * so it doesn't need to wait blocked disk here.
 			 */
-			if (!r10_bio->sectors)
-				continue;
-
-			if (rdev_has_badblock(rdev, dev_sector,
-					      r10_bio->sectors) < 0) {
+			if (test_bit(WriteErrorSeen, &rdev->flags) &&
+			    r10_bio->sectors &&
+			    rdev_has_badblock(rdev, dev_sector,
+					      r10_bio->sectors) < 0)
 				/*
-				 * Mustn't write here until the bad block
-				 * is acknowledged
+				 * Mustn't write here until the bad
+				 * block is acknowledged
 				 */
-				atomic_inc(&rdev->nr_pending);
 				set_bit(BlockedBadBlocks, &rdev->flags);
+
+			if (rdev_blocked(rdev)) {
 				blocked_rdev = rdev;
+				atomic_inc(&rdev->nr_pending);
 				break;
 			}
 		}
+
+		rrdev = conf->mirrors[i].replacement;
+		if (rrdev && rdev_blocked(rrdev)) {
+			atomic_inc(&rrdev->nr_pending);
+			blocked_rdev = rrdev;
+			break;
+		}
 	}
 
 	if (unlikely(blocked_rdev)) {
@@ -1347,9 +1353,10 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 				 struct r10bio *r10_bio)
 {
 	struct r10conf *conf = mddev->private;
-	int i;
+	int i, k;
 	sector_t sectors;
 	int max_sectors;
+	int error;
 
 	if ((mddev_is_clustered(mddev) &&
 	     md_cluster_ops->area_resyncing(mddev, WRITE,
@@ -1482,6 +1489,10 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	if (r10_bio->sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, r10_bio->sectors,
 					      GFP_NOIO, &conf->bio_split);
+		if (IS_ERR(split)) {
+			error = PTR_ERR(split);
+			goto err_handle;
+		}
 		bio_chain(split, bio);
 		allow_barrier(conf);
 		submit_bio_noacct(bio);
@@ -1503,6 +1514,26 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 			raid10_write_one_disk(mddev, r10_bio, bio, true, i);
 	}
 	one_write_done(r10_bio);
+	return;
+err_handle:
+	for (k = 0;  k < i; k++) {
+		int d = r10_bio->devs[k].devnum;
+		struct md_rdev *rdev = conf->mirrors[d].rdev;
+		struct md_rdev *rrdev = conf->mirrors[d].replacement;
+
+		if (r10_bio->devs[k].bio) {
+			rdev_dec_pending(rdev, mddev);
+			r10_bio->devs[k].bio = NULL;
+		}
+		if (r10_bio->devs[k].repl_bio) {
+			rdev_dec_pending(rrdev, mddev);
+			r10_bio->devs[k].repl_bio = NULL;
+		}
+	}
+
+	bio->bi_status = errno_to_blk_status(error);
+	set_bit(R10BIO_Uptodate, &r10_bio->state);
+	raid_end_bio_io(r10_bio);
 }
 
 static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
@@ -1644,6 +1675,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
 	if (remainder) {
 		split_size = stripe_size - remainder;
 		split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split);
+		if (IS_ERR(split)) {
+			bio->bi_status = errno_to_blk_status(PTR_ERR(split));
+			bio_endio(bio);
+			return 0;
+		}
 		bio_chain(split, bio);
 		allow_barrier(conf);
 		/* Resend the fist split part */
@@ -1654,6 +1690,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
 	if (remainder) {
 		split_size = bio_sectors(bio) - remainder;
 		split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split);
+		if (IS_ERR(split)) {
+			bio->bi_status = errno_to_blk_status(PTR_ERR(split));
+			bio_endio(bio);
+			return 0;
+		}
 		bio_chain(split, bio);
 		allow_barrier(conf);
 		/* Resend the second split part */