Merge tag 'for-6.12/block-20240925' of git://git.kernel.dk/linux

Pull more block updates from Jens Axboe:

 - Improve blk-integrity segment counting and merging (Keith)

 - NVMe pull request via Keith:
      - Multipath fixes (Hannes)
      - Sysfs attribute list NULL terminate fix (Shin'ichiro)
      - Remove problematic read-back (Keith)

 - Fix for a regression with the IO scheduler switching freezing from
   6.11 (Damien)

 - Use a raw spinlock for sbitmap, as it may get called from preempt
   disabled context (Ming)

 - Cleanup for bd_claiming waiting, using var_waitqueue() rather than
   the bit waitqueues, as that more accurately describes that it does
   (Neil)

 - Various cleanups (Kanchan, Qiu-ji, David)

* tag 'for-6.12/block-20240925' of git://git.kernel.dk/linux:
  nvme: remove CC register read-back during enabling
  nvme: null terminate nvme_tls_attrs
  nvme-multipath: avoid hang on inaccessible namespaces
  nvme-multipath: system fails to create generic nvme device
  lib/sbitmap: define swap_lock as raw_spinlock_t
  block: Remove unused blk_limits_io_{min,opt}
  drbd: Fix atomicity violation in drbd_uuid_set_bm()
  block: Fix elv_iosched_local_module handling of "none" scheduler
  block: remove bogus union
  block: change wait on bd_claiming to use a var_waitqueue
  blk-integrity: improved sg segment mapping
  block: unexport blk_rq_count_integrity_sg
  nvme-rdma: use request to get integrity segments
  scsi: use request to get integrity segments
  block: provide a request helper for user integrity segments
  blk-integrity: consider entire bio list for merging
  blk-integrity: properly account for segments
  blk-mq: set the nr_integrity_segments from bio
  blk-mq: unconditional nr_integrity_segments

7 files changed, 37 insertions, 59 deletions

diff --git a/block/bdev.c b/block/bdev.c
index 33f9c4605e3a..738e3c8457e7 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -555,7 +555,7 @@ retry:
 
 	/* if claiming is already in progress, wait for it to finish */
 	if (whole->bd_claiming) {
-		wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0);
+		wait_queue_head_t *wq = __var_waitqueue(&whole->bd_claiming);
 		DEFINE_WAIT(wait);
 
 		prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
@@ -578,7 +578,7 @@ static void bd_clear_claiming(struct block_device *whole, void *holder)
 	/* tell others that we're done */
 	BUG_ON(whole->bd_claiming != holder);
 	whole->bd_claiming = NULL;
-	wake_up_bit(&whole->bd_claiming, 0);
+	wake_up_var(&whole->bd_claiming);
 }
 
 /**
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 96a2653905ae..88e3ad73c385 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -367,7 +367,6 @@ free_bvec:
 		kfree(bvec);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(bio_integrity_map_user);
 
 /**
  * bio_integrity_prep - Prepare bio for integrity I/O
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 010decc892ea..0a2b1c5d0ebf 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -53,7 +53,6 @@ new_segment:
 
 	return segments;
 }
-EXPORT_SYMBOL(blk_rq_count_integrity_sg);
 
 /**
  * blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist
@@ -63,19 +62,20 @@ EXPORT_SYMBOL(blk_rq_count_integrity_sg);
  *
  * Description: Map the integrity vectors in request into a
  * scatterlist.  The scatterlist must be big enough to hold all
- * elements.  I.e. sized using blk_rq_count_integrity_sg().
+ * elements.  I.e. sized using blk_rq_count_integrity_sg() or
+ * rq->nr_integrity_segments.
  */
-int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio,
-			    struct scatterlist *sglist)
+int blk_rq_map_integrity_sg(struct request *rq, struct scatterlist *sglist)
 {
 	struct bio_vec iv, ivprv = { NULL };
+	struct request_queue *q = rq->q;
 	struct scatterlist *sg = NULL;
+	struct bio *bio = rq->bio;
 	unsigned int segments = 0;
 	struct bvec_iter iter;
 	int prev = 0;
 
 	bio_for_each_integrity_vec(iv, bio, iter) {
-
 		if (prev) {
 			if (!biovec_phys_mergeable(q, &ivprv, &iv))
 				goto new_segment;
@@ -103,10 +103,30 @@ new_segment:
 	if (sg)
 		sg_mark_end(sg);
 
+	/*
+	 * Something must have been wrong if the figured number of segment
+	 * is bigger than number of req's physical integrity segments
+	 */
+	BUG_ON(segments > rq->nr_integrity_segments);
+	BUG_ON(segments > queue_max_integrity_segments(q));
 	return segments;
 }
 EXPORT_SYMBOL(blk_rq_map_integrity_sg);
 
+int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf,
+			      ssize_t bytes, u32 seed)
+{
+	int ret = bio_integrity_map_user(rq->bio, ubuf, bytes, seed);
+
+	if (ret)
+		return ret;
+
+	rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q, rq->bio);
+	rq->cmd_flags |= REQ_INTEGRITY;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blk_rq_integrity_map_user);
+
 bool blk_integrity_merge_rq(struct request_queue *q, struct request *req,
 			    struct request *next)
 {
@@ -134,7 +154,6 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 			     struct bio *bio)
 {
 	int nr_integrity_segs;
-	struct bio *next = bio->bi_next;
 
 	if (blk_integrity_rq(req) == 0 && bio_integrity(bio) == NULL)
 		return true;
@@ -145,16 +164,11 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 	if (bio_integrity(req->bio)->bip_flags != bio_integrity(bio)->bip_flags)
 		return false;
 
-	bio->bi_next = NULL;
 	nr_integrity_segs = blk_rq_count_integrity_sg(q, bio);
-	bio->bi_next = next;
-
 	if (req->nr_integrity_segments + nr_integrity_segs >
 	    q->limits.max_integrity_segments)
 		return false;
 
-	req->nr_integrity_segments += nr_integrity_segs;
-
 	return true;
 }
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 56769c4bcd79..ad763ec313b6 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -639,6 +639,9 @@ static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
 	 * counters.
 	 */
 	req->nr_phys_segments += nr_phys_segs;
+	if (bio_integrity(bio))
+		req->nr_integrity_segments += blk_rq_count_integrity_sg(req->q,
+									bio);
 	return 1;
 
 no_merge:
@@ -731,6 +734,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 
 	/* Merge is OK... */
 	req->nr_phys_segments = total_phys_segments;
+	req->nr_integrity_segments += next->nr_integrity_segments;
 	return 1;
 }
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 831c5cf5d874..4b2c8e940f59 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -376,9 +376,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	rq->io_start_time_ns = 0;
 	rq->stats_sectors = 0;
 	rq->nr_phys_segments = 0;
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
 	rq->nr_integrity_segments = 0;
-#endif
 	rq->end_io = NULL;
 	rq->end_io_data = NULL;
 
@@ -2546,6 +2544,9 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 	rq->__sector = bio->bi_iter.bi_sector;
 	rq->write_hint = bio->bi_write_hint;
 	blk_rq_bio_prep(rq, bio, nr_segs);
+	if (bio_integrity(bio))
+		rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q,
+								      bio);
 
 	/* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */
 	err = blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index cd8a8eabc9a5..a446654ddee5 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -437,48 +437,6 @@ int queue_limits_set(struct request_queue *q, struct queue_limits *lim)
 }
 EXPORT_SYMBOL_GPL(queue_limits_set);
 
-/**
- * blk_limits_io_min - set minimum request size for a device
- * @limits: the queue limits
- * @min:  smallest I/O size in bytes
- *
- * Description:
- *   Some devices have an internal block size bigger than the reported
- *   hardware sector size.  This function can be used to signal the
- *   smallest I/O the device can perform without incurring a performance
- *   penalty.
- */
-void blk_limits_io_min(struct queue_limits *limits, unsigned int min)
-{
-	limits->io_min = min;
-
-	if (limits->io_min < limits->logical_block_size)
-		limits->io_min = limits->logical_block_size;
-
-	if (limits->io_min < limits->physical_block_size)
-		limits->io_min = limits->physical_block_size;
-}
-EXPORT_SYMBOL(blk_limits_io_min);
-
-/**
- * blk_limits_io_opt - set optimal request size for a device
- * @limits: the queue limits
- * @opt:  smallest I/O size in bytes
- *
- * Description:
- *   Storage devices may report an optimal I/O size, which is the
- *   device's preferred unit for sustained I/O.  This is rarely reported
- *   for disk drives.  For RAID arrays it is usually the stripe width or
- *   the internal track size.  A properly aligned multiple of
- *   optimal_io_size is the preferred request size for workloads where
- *   sustained throughput is desired.
- */
-void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt)
-{
-	limits->io_opt = opt;
-}
-EXPORT_SYMBOL(blk_limits_io_opt);
-
 static int queue_limit_alignment_offset(const struct queue_limits *lim,
 		sector_t sector)
 {
diff --git a/block/elevator.c b/block/elevator.c
index c355b55d0107..4122026b11f1 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -715,7 +715,9 @@ int elv_iosched_load_module(struct gendisk *disk, const char *buf,
 
 	strscpy(elevator_name, buf, sizeof(elevator_name));
 
-	return request_module("%s-iosched", strstrip(elevator_name));
+	request_module("%s-iosched", strstrip(elevator_name));
+
+	return 0;
 }
 
 ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,