Merge tag 'for-6.8/block-2024-01-18' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Keith:
      - tcp, fc, and rdma target fixes (Maurizio, Daniel, Hannes,
        Christoph)
      - discard fixes and improvements (Christoph)
      - timeout debug improvements (Keith, Max)
      - various cleanups (Daniel, Max, Giuxen)
      - trace event string fixes (Arnd)
      - shadow doorbell setup on reset fix (William)
      - a write zeroes quirk for SK Hynix (Jim)

 - MD pull request via Song:
      - Sparse warning since v6.0 (Bart)
      - /proc/mdstat regression since v6.7 (Yu Kuai)

 - Use symbolic error value (Christian)

 - IO Priority documentation update (Christian)

 - Fix for accessing queue limits without having entered the queue
   (Christoph, me)

 - Fix for loop dio support (Christoph)

 - Move null_blk off deprecated ida interface (Christophe)

 - Ensure nbd initializes full msghdr (Eric)

 - Fix for a regression with the folio conversion, which is now easier
   to hit because of an unrelated change (Matthew)

 - Remove redundant check in virtio-blk (Li)

 - Fix for a potential hang in sbitmap (Ming)

 - Fix for partial zone appending (Damien)

 - Misc changes and fixes (Bart, me, Kemeng, Dmitry)

* tag 'for-6.8/block-2024-01-18' of git://git.kernel.dk/linux: (45 commits)
  Documentation: block: ioprio: Update schedulers
  loop: fix the the direct I/O support check when used on top of block devices
  blk-mq: Remove the hctx 'run' debugfs attribute
  nbd: always initialize struct msghdr completely
  block: Fix iterating over an empty bio with bio_for_each_folio_all
  block: bio-integrity: fix kcalloc() arguments order
  virtio_blk: remove duplicate check if queue is broken in virtblk_done
  sbitmap: remove stale comment in sbq_calc_wake_batch
  block: Correct a documentation comment in blk-cgroup.c
  null_blk: Remove usage of the deprecated ida_simple_xx() API
  block: ensure we hold a queue reference when using queue limits
  blk-mq: rename blk_mq_can_use_cached_rq
  block: print symbolic error name instead of error code
  blk-mq: fix IO hang from sbitmap wakeup race
  nvmet-rdma: avoid circular locking dependency on install_queue()
  nvmet-tcp: avoid circular locking dependency on install_queue()
  nvme-pci: set doorbell config before unquiescing
  block: fix partial zone append completion handling in req_bio_endio()
  block/iocost: silence warning on 'last_period' potentially being unused
  md/raid1: Use blk_opf_t for read and write operations
  ...

1 files changed, 39 insertions, 11 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index c11c97afa0bc..aa87fcfda1ec 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -772,11 +772,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 		/*
 		 * Partial zone append completions cannot be supported as the
 		 * BIO fragments may end up not being written sequentially.
+		 * For such case, force the completed nbytes to be equal to
+		 * the BIO size so that bio_advance() sets the BIO remaining
+		 * size to 0 and we end up calling bio_endio() before returning.
 		 */
-		if (bio->bi_iter.bi_size != nbytes)
+		if (bio->bi_iter.bi_size != nbytes) {
 			bio->bi_status = BLK_STS_IOERR;
-		else
+			nbytes = bio->bi_iter.bi_size;
+		} else {
 			bio->bi_iter.bi_sector = rq->__sector;
+		}
 	}
 
 	bio_advance(bio, nbytes);
@@ -1860,6 +1865,22 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	__add_wait_queue(wq, wait);
 
 	/*
+	 * Add one explicit barrier since blk_mq_get_driver_tag() may
+	 * not imply barrier in case of failure.
+	 *
+	 * Order adding us to wait queue and allocating driver tag.
+	 *
+	 * The pair is the one implied in sbitmap_queue_wake_up() which
+	 * orders clearing sbitmap tag bits and waitqueue_active() in
+	 * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless
+	 *
+	 * Otherwise, re-order of adding wait queue and getting driver tag
+	 * may cause __sbitmap_queue_wake_up() to wake up nothing because
+	 * the waitqueue_active() may not observe us in wait queue.
+	 */
+	smp_mb();
+
+	/*
 	 * It's possible that a tag was freed in the window between the
 	 * allocation failure and adding the hardware queue to the wait
 	 * queue.
@@ -2891,8 +2912,11 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	return NULL;
 }
 
-/* return true if this @rq can be used for @bio */
-static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug,
+/*
+ * Check if we can use the passed on request for submitting the passed in bio,
+ * and remove it from the request list if it can be used.
+ */
+static bool blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 		struct bio *bio)
 {
 	enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf);
@@ -2952,12 +2976,6 @@ void blk_mq_submit_bio(struct bio *bio)
 	blk_status_t ret;
 
 	bio = blk_queue_bounce(bio, q);
-	if (bio_may_exceed_limits(bio, &q->limits)) {
-		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
-		if (!bio)
-			return;
-	}
-
 	bio_set_ioprio(bio);
 
 	if (plug) {
@@ -2966,16 +2984,26 @@ void blk_mq_submit_bio(struct bio *bio)
 			rq = NULL;
 	}
 	if (rq) {
+		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+			if (!bio)
+				return;
+		}
 		if (!bio_integrity_prep(bio))
 			return;
 		if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
 			return;
-		if (blk_mq_can_use_cached_rq(rq, plug, bio))
+		if (blk_mq_use_cached_rq(rq, plug, bio))
 			goto done;
 		percpu_ref_get(&q->q_usage_counter);
 	} else {
 		if (unlikely(bio_queue_enter(bio)))
 			return;
+		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+			if (!bio)
+				goto fail;
+		}
 		if (!bio_integrity_prep(bio))
 			goto fail;
 	}