Merge tag 'block-6.13-20242901' of git://git.kernel.dk/linux

Pull more block updates from Jens Axboe:

 - NVMe pull request via Keith:
      - Use correct srcu list traversal (Breno)
      - Scatter-gather support for metadata (Keith)
      - Fabrics shutdown race condition fix (Nilay)
      - Persistent reservations updates (Guixin)

 - Add the required bits for MD atomic write support for raid0/1/10

 - Correct return value for unknown opcode in ublk

 - Fix deadlock with zone revalidation

 - Fix for the io priority request vs bio cleanups

 - Use the correct unsigned int type for various limit helpers

 - Fix for a race in loop

 - Cleanup blk_rq_prep_clone() to prevent uninit-value warning and make
   it easier for actual humans to read

 - Fix potential UAF when iterating tags

 - A few fixes for bfq-iosched UAF issues

 - Fix for brd discard not decrementing the allocated page count

 - Various little fixes and cleanups

* tag 'block-6.13-20242901' of git://git.kernel.dk/linux: (36 commits)
  brd: decrease the number of allocated pages which discarded
  block, bfq: fix bfqq uaf in bfq_limit_depth()
  block: Don't allow an atomic write be truncated in blkdev_write_iter()
  mq-deadline: don't call req_get_ioprio from the I/O completion handler
  block: Prevent potential deadlock in blk_revalidate_disk_zones()
  block: Remove extra part pointer NULLify in blk_rq_init()
  nvme: tuning pr code by using defined structs and macros
  nvme: introduce change ptpl and iekey definition
  block: return bool from get_disk_ro and bdev_read_only
  block: remove a duplicate definition for bdev_read_only
  block: return bool from blk_rq_aligned
  block: return unsigned int from blk_lim_dma_alignment_and_pad
  block: return unsigned int from queue_dma_alignment
  block: return unsigned int from bdev_io_opt
  block: req->bio is always set in the merge code
  block: don't bother checking the data direction for merges
  block: blk-mq: fix uninit-value in blk_rq_prep_clone and refactor
  Revert "block, bfq: merge bfq_release_process_ref() into bfq_put_cooperator()"
  md/raid10: Atomic write support
  md/raid1: Atomic write support
  ...

1 files changed, 18 insertions, 2 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 18989231791a..7d7a8a2524dc 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1255,6 +1255,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	const enum req_op op = bio_op(bio);
 	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
 	const blk_opf_t do_fua = bio->bi_opf & REQ_FUA;
+	const blk_opf_t do_atomic = bio->bi_opf & REQ_ATOMIC;
 	unsigned long flags;
 	struct r10conf *conf = mddev->private;
 	struct md_rdev *rdev;
@@ -1273,7 +1274,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	mbio->bi_iter.bi_sector	= (r10_bio->devs[n_copy].addr +
 				   choose_data_offset(r10_bio, rdev));
 	mbio->bi_end_io	= raid10_end_write_request;
-	mbio->bi_opf = op | do_sync | do_fua;
+	mbio->bi_opf = op | do_sync | do_fua | do_atomic;
 	if (!replacement && test_bit(FailFast,
 				     &conf->mirrors[devnum].rdev->flags)
 			 && enough(conf, devnum))
@@ -1468,7 +1469,21 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 				continue;
 			}
 			if (is_bad) {
-				int good_sectors = first_bad - dev_sector;
+				int good_sectors;
+
+				/*
+				 * We cannot atomically write this, so just
+				 * error in that case. It could be possible to
+				 * atomically write other mirrors, but the
+				 * complexity of supporting that is not worth
+				 * the benefit.
+				 */
+				if (bio->bi_opf & REQ_ATOMIC) {
+					error = -EIO;
+					goto err_handle;
+				}
+
+				good_sectors = first_bad - dev_sector;
 				if (good_sectors < max_sectors)
 					max_sectors = good_sectors;
 			}
@@ -4025,6 +4040,7 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 	lim.max_write_zeroes_sectors = 0;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
+	lim.features |= BLK_FEAT_ATOMIC_WRITES_STACKED;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
 	if (err) {
 		queue_limits_cancel_update(mddev->gendisk->queue);