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

block/bdev.c

@@ -555,7 +555,7 @@ int bd_prepare_to_claim(struct block_device *bdev, void *holder,
 
 	/* 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);
 }
 
 /**

block/bio-integrity.c

@@ -367,7 +367,6 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes,
 		kfree(bvec);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(bio_integrity_map_user);
 
 /**
  * bio_integrity_prep - Prepare bio for integrity I/O

block/blk-integrity.c

@@ -53,7 +53,6 @@ int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *bio)
 
 	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 @@ int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio,
 	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;
 }
 

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;
 }
 

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);

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)
 {

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,

drivers/block/drbd/drbd_main.c

@@ -3399,10 +3399,12 @@ void drbd_uuid_new_current(struct drbd_device *device) __must_hold(local)
 void drbd_uuid_set_bm(struct drbd_device *device, u64 val) __must_hold(local)
 {
 	unsigned long flags;
-	if (device->ldev->md.uuid[UI_BITMAP] == 0 && val == 0)
+	spin_lock_irqsave(&device->ldev->md.uuid_lock, flags);
+	if (device->ldev->md.uuid[UI_BITMAP] == 0 && val == 0) {
+		spin_unlock_irqrestore(&device->ldev->md.uuid_lock, flags);
 		return;
+	}
 
-	spin_lock_irqsave(&device->ldev->md.uuid_lock, flags);
 	if (val == 0) {
 		drbd_uuid_move_history(device);
 		device->ldev->md.uuid[UI_HISTORY_START] = device->ldev->md.uuid[UI_BITMAP];

drivers/nvme/host/core.c

@@ -2468,11 +2468,6 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 	if (ret)
 		return ret;
 
-	/* Flush write to device (required if transport is PCI) */
-	ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CC, &ctrl->ctrl_config);
-	if (ret)
-		return ret;
-
 	/* CAP value may change after initial CC write */
 	ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap);
 	if (ret)

drivers/nvme/host/ioctl.c

@@ -3,7 +3,6 @@
  * Copyright (c) 2011-2014, Intel Corporation.
  * Copyright (c) 2017-2021 Christoph Hellwig.
  */
-#include <linux/bio-integrity.h>
 #include <linux/blk-integrity.h>
 #include <linux/ptrace.h>	/* for force_successful_syscall_return */
 #include <linux/nvme_ioctl.h>
@@ -153,11 +152,10 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		bio_set_dev(bio, bdev);
 
 	if (has_metadata) {
-		ret = bio_integrity_map_user(bio, meta_buffer, meta_len,
+		ret = blk_rq_integrity_map_user(req, meta_buffer, meta_len,
 						meta_seed);
 		if (ret)
 			goto out_unmap;
-		req->cmd_flags |= REQ_INTEGRITY;
 	}
 
 	return ret;

drivers/nvme/host/multipath.c

@@ -421,6 +421,9 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 {
 	struct nvme_ns *ns;
 
+	if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
+		return NULL;
+
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
 		if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags))
 			continue;
@@ -648,7 +651,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 		rc = device_add_disk(&head->subsys->dev, head->disk,
 				     nvme_ns_attr_groups);
 		if (rc) {
-			clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags);
+			clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags);
 			return;
 		}
 		nvme_add_ns_head_cdev(head);
@@ -969,11 +972,16 @@ void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
-	kblockd_schedule_work(&head->requeue_work);
-	if (test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
+	if (test_and_clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
 		nvme_cdev_del(&head->cdev, &head->cdev_device);
 		del_gendisk(head->disk);
 	}
+	/*
+	 * requeue I/O after NVME_NSHEAD_DISK_LIVE has been cleared
+	 * to allow multipath to fail all I/O.
+	 */
+	synchronize_srcu(&head->srcu);
+	kblockd_schedule_work(&head->requeue_work);
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)

drivers/nvme/host/rdma.c

@@ -1496,7 +1496,7 @@ static int nvme_rdma_dma_map_req(struct ib_device *ibdev, struct request *rq,
 		req->metadata_sgl->sg_table.sgl =
 			(struct scatterlist *)(req->metadata_sgl + 1);
 		ret = sg_alloc_table_chained(&req->metadata_sgl->sg_table,
-				blk_rq_count_integrity_sg(rq->q, rq->bio),
+				rq->nr_integrity_segments,
 				req->metadata_sgl->sg_table.sgl,
 				NVME_INLINE_METADATA_SG_CNT);
 		if (unlikely(ret)) {
@@ -1504,8 +1504,8 @@ static int nvme_rdma_dma_map_req(struct ib_device *ibdev, struct request *rq,
 			goto out_unmap_sg;
 		}
 
-		req->metadata_sgl->nents = blk_rq_map_integrity_sg(rq->q,
-				rq->bio, req->metadata_sgl->sg_table.sgl);
+		req->metadata_sgl->nents = blk_rq_map_integrity_sg(rq,
+				req->metadata_sgl->sg_table.sgl);
 		*pi_count = ib_dma_map_sg(ibdev,
 					  req->metadata_sgl->sg_table.sgl,
 					  req->metadata_sgl->nents,

drivers/nvme/host/sysfs.c

@@ -767,6 +767,7 @@ static struct attribute *nvme_tls_attrs[] = {
 	&dev_attr_tls_key.attr,
 	&dev_attr_tls_configured_key.attr,
 	&dev_attr_tls_keyring.attr,
+	NULL,
 };
 
 static umode_t nvme_tls_attrs_are_visible(struct kobject *kobj,

drivers/scsi/scsi_lib.c

@@ -1163,7 +1163,6 @@ blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd)
 
 	if (blk_integrity_rq(rq)) {
 		struct scsi_data_buffer *prot_sdb = cmd->prot_sdb;
-		int ivecs;
 
 		if (WARN_ON_ONCE(!prot_sdb)) {
 			/*
@@ -1175,20 +1174,15 @@ blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd)
 			goto out_free_sgtables;
 		}
 
-		ivecs = blk_rq_count_integrity_sg(rq->q, rq->bio);
-
-		if (sg_alloc_table_chained(&prot_sdb->table, ivecs,
+		if (sg_alloc_table_chained(&prot_sdb->table,
+				rq->nr_integrity_segments,
 				prot_sdb->table.sgl,
 				SCSI_INLINE_PROT_SG_CNT)) {
 			ret = BLK_STS_RESOURCE;
 			goto out_free_sgtables;
 		}
 
-		count = blk_rq_map_integrity_sg(rq->q, rq->bio,
-						prot_sdb->table.sgl);
-		BUG_ON(count > ivecs);
-		BUG_ON(count > queue_max_integrity_segments(rq->q));
-
+		count = blk_rq_map_integrity_sg(rq, prot_sdb->table.sgl);
 		cmd->prot_sdb = prot_sdb;
 		cmd->prot_sdb->table.nents = count;
 	}

include/linux/blk-integrity.h

@@ -25,9 +25,10 @@ static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t,
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
-int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
-				   struct scatterlist *);
+int blk_rq_map_integrity_sg(struct request *, struct scatterlist *);
 int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
+int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf,
+			      ssize_t bytes, u32 seed);
 
 static inline bool
 blk_integrity_queue_supports_integrity(struct request_queue *q)
@@ -96,12 +97,18 @@ static inline int blk_rq_count_integrity_sg(struct request_queue *q,
 {
 	return 0;
 }
-static inline int blk_rq_map_integrity_sg(struct request_queue *q,
-					  struct bio *b,
+static inline int blk_rq_map_integrity_sg(struct request *q,
 					  struct scatterlist *s)
 {
 	return 0;
 }
+static inline int blk_rq_integrity_map_user(struct request *rq,
+					    void __user *ubuf,
+					    ssize_t bytes,
+					    u32 seed)
+{
+	return -EINVAL;
+}
 static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
 {
 	return NULL;

include/linux/blk-mq.h

@@ -149,10 +149,7 @@ struct request {
 	 * physical address coalescing is performed.
 	 */
 	unsigned short nr_phys_segments;
-
-#ifdef CONFIG_BLK_DEV_INTEGRITY
 	unsigned short nr_integrity_segments;
-#endif
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	struct bio_crypt_ctx *crypt_ctx;

include/linux/blk_types.h

@@ -251,11 +251,9 @@ struct bio {
 	struct bio_crypt_ctx	*bi_crypt_context;
 #endif
 
-	union {
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	struct bio_integrity_payload *bi_integrity; /* data integrity */
 #endif
-	};
 
 	unsigned short		bi_vcnt;	/* how many bio_vec's */
 

include/linux/blkdev.h

@@ -968,8 +968,6 @@ static inline void blk_queue_disable_write_zeroes(struct request_queue *q)
 /*
  * Access functions for manipulating queue properties
  */
-extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
-extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
 extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth);
 extern void blk_set_stacking_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,

include/linux/sbitmap.h

@@ -40,7 +40,7 @@ struct sbitmap_word {
 	/**
 	 * @swap_lock: serializes simultaneous updates of ->word and ->cleared
 	 */
-	spinlock_t swap_lock;
+	raw_spinlock_t swap_lock;
 } ____cacheline_aligned_in_smp;
 
 /**

lib/sbitmap.c

@@ -65,7 +65,7 @@ static inline bool sbitmap_deferred_clear(struct sbitmap_word *map,
 {
 	unsigned long mask, word_mask;
 
-	guard(spinlock_irqsave)(&map->swap_lock);
+	guard(raw_spinlock_irqsave)(&map->swap_lock);
 
 	if (!map->cleared) {
 		if (depth == 0)
@@ -136,7 +136,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
 	}
 
 	for (i = 0; i < sb->map_nr; i++)
-		spin_lock_init(&sb->map[i].swap_lock);
+		raw_spin_lock_init(&sb->map[i].swap_lock);
 
 	return 0;
 }