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
...

Documentation/block/ioprio.rst

···
 Intro
 -----
 
-With the introduction of cfq v3 (aka cfq-ts or time sliced cfq), basic io
-priorities are supported for reads on files.  This enables users to io nice
-processes or process groups, similar to what has been possible with cpu
-scheduling for ages.  This document mainly details the current possibilities
-with cfq; other io schedulers do not support io priorities thus far.
+The io priority feature enables users to io nice processes or process groups,
+similar to what has been possible with cpu scheduling for ages. Support for io
+priorities is io scheduler dependent and currently supported by bfq and
+mq-deadline.
 
 Scheduling classes
 ------------------
 
-CFQ implements three generic scheduling classes that determine how io is
-served for a process.
+Three generic scheduling classes are implemented for io priorities that
+determine how io is served for a process.
 
 IOPRIO_CLASS_RT: This is the realtime io class. This scheduling class is given
 higher priority than any other in the system, processes from this class are

block/bio-integrity.c

···
 	if (nr_vecs > BIO_MAX_VECS)
 		return -E2BIG;
 	if (nr_vecs > UIO_FASTIOV) {
-		bvec = kcalloc(sizeof(*bvec), nr_vecs, GFP_KERNEL);
+		bvec = kcalloc(nr_vecs, sizeof(*bvec), GFP_KERNEL);
 		if (!bvec)
 			return -ENOMEM;
 		pages = NULL;

block/blk-cgroup.c

···
  * @disk: gendisk the new blkg is associated with
  * @gfp_mask: allocation mask to use
  *
- * Allocate a new blkg assocating @blkcg and @q.
+ * Allocate a new blkg associating @blkcg and @disk.
  */
 static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 				   gfp_t gfp_mask)

block/blk-iocost.c

···
 static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
 {
 	struct ioc *ioc = iocg->ioc;
-	u64 last_period, cur_period;
+	u64 __maybe_unused last_period, cur_period;
 	u64 vtime, vtarget;
 	int i;
 

block/blk-mq-debugfs.c

···
 	return res;
 }
 
-static int hctx_run_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	seq_printf(m, "%lu\n", hctx->run);
-	return 0;
-}
-
-static ssize_t hctx_run_write(void *data, const char __user *buf, size_t count,
-			      loff_t *ppos)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	hctx->run = 0;
-	return count;
-}
-
 static int hctx_active_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
···
 	{"tags_bitmap", 0400, hctx_tags_bitmap_show},
 	{"sched_tags", 0400, hctx_sched_tags_show},
 	{"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show},
-	{"run", 0600, hctx_run_show, hctx_run_write},
 	{"active", 0400, hctx_active_show},
 	{"dispatch_busy", 0400, hctx_dispatch_busy_show},
 	{"type", 0400, hctx_type_show},

block/blk-mq-sched.c

···
 	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
 		return;
 
-	hctx->run++;
-
 	/*
 	 * A return of -EAGAIN is an indication that hctx->dispatch is not
 	 * empty and we must run again in order to avoid starving flushes.

block/blk-mq.c

···
 		/*
 		 * 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);
···
 	__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.
···
 	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);
···
 	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) {
···
 			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;
 	}

block/ioprio.c

···
 	return ret;
 }
 
-/*
- * If the task has set an I/O priority, use that. Otherwise, return
- * the default I/O priority.
- *
- * Expected to be called for current task or with task_lock() held to keep
- * io_context stable.
- */
-int __get_task_ioprio(struct task_struct *p)
-{
-	struct io_context *ioc = p->io_context;
-	int prio;
-
-	if (p != current)
-		lockdep_assert_held(&p->alloc_lock);
-	if (ioc)
-		prio = ioc->ioprio;
-	else
-		prio = IOPRIO_DEFAULT;
-
-	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
-		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
-					 task_nice_ioprio(p));
-	return prio;
-}
-EXPORT_SYMBOL_GPL(__get_task_ioprio);
-
 static int get_task_ioprio(struct task_struct *p)
 {
 	int ret;

block/partitions/core.c

···
 	part = add_partition(disk, p, from, size, state->parts[p].flags,
 			     &state->parts[p].info);
 	if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) {
-		printk(KERN_ERR " %s: p%d could not be added: %ld\n",
-		       disk->disk_name, p, -PTR_ERR(part));
+		printk(KERN_ERR " %s: p%d could not be added: %pe\n",
+		       disk->disk_name, p, part);
 		return true;
 	}
 

drivers/block/loop.c

···
 	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
 }
 
+/*
+ * We support direct I/O only if lo_offset is aligned with the logical I/O size
+ * of backing device, and the logical block size of loop is bigger than that of
+ * the backing device.
+ */
+static bool lo_bdev_can_use_dio(struct loop_device *lo,
+		struct block_device *backing_bdev)
+{
+	unsigned short sb_bsize = bdev_logical_block_size(backing_bdev);
+
+	if (queue_logical_block_size(lo->lo_queue) < sb_bsize)
+		return false;
+	if (lo->lo_offset & (sb_bsize - 1))
+		return false;
+	return true;
+}
+
 static void __loop_update_dio(struct loop_device *lo, bool dio)
 {
 	struct file *file = lo->lo_backing_file;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	unsigned short sb_bsize = 0;
-	unsigned dio_align = 0;
+	struct inode *inode = file->f_mapping->host;
+	struct block_device *backing_bdev = NULL;
 	bool use_dio;
 
-	if (inode->i_sb->s_bdev) {
-		sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
-		dio_align = sb_bsize - 1;
-	}
+	if (S_ISBLK(inode->i_mode))
+		backing_bdev = I_BDEV(inode);
+	else if (inode->i_sb->s_bdev)
+		backing_bdev = inode->i_sb->s_bdev;
 
-	/*
-	 * We support direct I/O only if lo_offset is aligned with the
-	 * logical I/O size of backing device, and the logical block
-	 * size of loop is bigger than the backing device's.
-	 *
-	 * TODO: the above condition may be loosed in the future, and
-	 * direct I/O may be switched runtime at that time because most
-	 * of requests in sane applications should be PAGE_SIZE aligned
-	 */
-	if (dio) {
-		if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
-		    !(lo->lo_offset & dio_align) &&
-		    (file->f_mode & FMODE_CAN_ODIRECT))
-			use_dio = true;
-		else
-			use_dio = false;
-	} else {
-		use_dio = false;
-	}
+	use_dio = dio && (file->f_mode & FMODE_CAN_ODIRECT) &&
+		(!backing_bdev || lo_bdev_can_use_dio(lo, backing_bdev));
 
 	if (lo->use_dio == use_dio)
 		return;

drivers/block/nbd.c

···
 		       struct iov_iter *iter, int msg_flags, int *sent)
 {
 	int result;
-	struct msghdr msg;
+	struct msghdr msg = {} ;
 	unsigned int noreclaim_flag;
 
 	if (unlikely(!sock)) {
···
 	do {
 		sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
 		sock->sk->sk_use_task_frag = false;
-		msg.msg_name = NULL;
-		msg.msg_namelen = 0;
-		msg.msg_control = NULL;
-		msg.msg_controllen = 0;
 		msg.msg_flags = msg_flags | MSG_NOSIGNAL;
 
 		if (send)

drivers/block/null_blk/main.c

···
 
 	dev = nullb->dev;
 
-	ida_simple_remove(&nullb_indexes, nullb->index);
+	ida_free(&nullb_indexes, nullb->index);
 
 	list_del_init(&nullb->list);
 
···
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 
 	mutex_lock(&lock);
-	rv = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL);
+	rv = ida_alloc(&nullb_indexes, GFP_KERNEL);
 	if (rv < 0) {
 		mutex_unlock(&lock);
 		goto out_cleanup_zone;

drivers/block/virtio_blk.c

···
 				blk_mq_complete_request(req);
 			req_done = true;
 		}
-		if (unlikely(virtqueue_is_broken(vq)))
-			break;
 	} while (!virtqueue_enable_cb(vq));
 
 	/* In case queue is stopped waiting for more buffers. */

drivers/md/md.c

···
 	seq_printf(seq, "\n");
 }
 
+static void status_personalities(struct seq_file *seq)
+{
+	struct md_personality *pers;
+
+	seq_puts(seq, "Personalities : ");
+	spin_lock(&pers_lock);
+	list_for_each_entry(pers, &pers_list, list)
+		seq_printf(seq, "[%s] ", pers->name);
+
+	spin_unlock(&pers_lock);
+	seq_puts(seq, "\n");
+}
+
 static int status_resync(struct seq_file *seq, struct mddev *mddev)
 {
 	sector_t max_sectors, resync, res;
···
 static void *md_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(&all_mddevs_lock)
 {
-	struct md_personality *pers;
-
-	seq_puts(seq, "Personalities : ");
-	spin_lock(&pers_lock);
-	list_for_each_entry(pers, &pers_list, list)
-		seq_printf(seq, "[%s] ", pers->name);
-
-	spin_unlock(&pers_lock);
-	seq_puts(seq, "\n");
 	seq->poll_event = atomic_read(&md_event_count);
-
 	spin_lock(&all_mddevs_lock);
 
-	return seq_list_start(&all_mddevs, *pos);
+	return seq_list_start_head(&all_mddevs, *pos);
 }
 
 static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
···
 static void md_seq_stop(struct seq_file *seq, void *v)
 	__releases(&all_mddevs_lock)
 {
-	status_unused(seq);
 	spin_unlock(&all_mddevs_lock);
 }
 
 static int md_seq_show(struct seq_file *seq, void *v)
 {
-	struct mddev *mddev = list_entry(v, struct mddev, all_mddevs);
+	struct mddev *mddev;
 	sector_t sectors;
 	struct md_rdev *rdev;
 
+	if (v == &all_mddevs) {
+		status_personalities(seq);
+		if (list_empty(&all_mddevs))
+			status_unused(seq);
+		return 0;
+	}
+
+	mddev = list_entry(v, struct mddev, all_mddevs);
 	if (!mddev_get(mddev))
 		return 0;
 
···
 	}
 	spin_unlock(&mddev->lock);
 	spin_lock(&all_mddevs_lock);
+
+	if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs))
+		status_unused(seq);
+
 	if (atomic_dec_and_test(&mddev->active))
 		__mddev_put(mddev);
 

drivers/md/raid1.c

···
 }
 
 static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
-			   int sectors, struct page *page, int rw)
+			   int sectors, struct page *page, blk_opf_t rw)
 {
 	if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
 		/* success */
 		return 1;
-	if (rw == WRITE) {
+	if (rw == REQ_OP_WRITE) {
 		set_bit(WriteErrorSeen, &rdev->flags);
 		if (!test_and_set_bit(WantReplacement,
 				      &rdev->flags))
···
 			rdev = conf->mirrors[d].rdev;
 			if (r1_sync_page_io(rdev, sect, s,
 					    pages[idx],
-					    WRITE) == 0) {
+					    REQ_OP_WRITE) == 0) {
 				r1_bio->bios[d]->bi_end_io = NULL;
 				rdev_dec_pending(rdev, mddev);
 			}
···
 			rdev = conf->mirrors[d].rdev;
 			if (r1_sync_page_io(rdev, sect, s,
 					    pages[idx],
-					    READ) != 0)
+					    REQ_OP_READ) != 0)
 				atomic_add(s, &rdev->corrected_errors);
 		}
 		sectors -= s;
···
 			    !test_bit(Faulty, &rdev->flags)) {
 				atomic_inc(&rdev->nr_pending);
 				r1_sync_page_io(rdev, sect, s,
-						conf->tmppage, WRITE);
+						conf->tmppage, REQ_OP_WRITE);
 				rdev_dec_pending(rdev, mddev);
 			}
 		}
···
 			    !test_bit(Faulty, &rdev->flags)) {
 				atomic_inc(&rdev->nr_pending);
 				if (r1_sync_page_io(rdev, sect, s,
-						    conf->tmppage, READ)) {
+						conf->tmppage, REQ_OP_READ)) {
 					atomic_add(s, &rdev->corrected_errors);
 					pr_info("md/raid1:%s: read error corrected (%d sectors at %llu on %pg)\n",
 						mdname(mddev), s,

drivers/nvme/common/keyring.c

···
  * should be preferred to 'generated' PSKs,
  * and SHA-384 should be preferred to SHA-256.
  */
-struct nvme_tls_psk_priority_list {
+static struct nvme_tls_psk_priority_list {
 	bool generated;
 	enum nvme_tcp_tls_cipher cipher;
 } nvme_tls_psk_prio[] = {

drivers/nvme/host/core.c

···
 		struct nvme_ns_head *head)
 {
 	struct request_queue *queue = disk->queue;
-	u32 size = queue_logical_block_size(queue);
+	u32 max_discard_sectors;
 
-	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX))
-		ctrl->max_discard_sectors =
-			nvme_lba_to_sect(head, ctrl->dmrsl);
-
-	if (ctrl->max_discard_sectors == 0) {
+	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX)) {
+		max_discard_sectors = nvme_lba_to_sect(head, ctrl->dmrsl);
+	} else if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
+		max_discard_sectors = UINT_MAX;
+	} else {
 		blk_queue_max_discard_sectors(queue, 0);
 		return;
 	}
···
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
 
-	queue->limits.discard_granularity = size;
-
-	/* If discard is already enabled, don't reset queue limits */
+	/*
+	 * If discard is already enabled, don't reset queue limits.
+	 *
+	 * This works around the fact that the block layer can't cope well with
+	 * updating the hardware limits when overridden through sysfs.  This is
+	 * harmless because discard limits in NVMe are purely advisory.
+	 */
 	if (queue->limits.max_discard_sectors)
 		return;
 
-	blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors);
-	blk_queue_max_discard_segments(queue, ctrl->max_discard_segments);
+	blk_queue_max_discard_sectors(queue, max_discard_sectors);
+	if (ctrl->dmrl)
+		blk_queue_max_discard_segments(queue, ctrl->dmrl);
+	else
+		blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
+	queue->limits.discard_granularity = queue_logical_block_size(queue);
 
 	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
 		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
···
 	struct nvme_id_ctrl_nvm *id;
 	int ret;
 
-	if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
-		ctrl->max_discard_sectors = UINT_MAX;
-		ctrl->max_discard_segments = NVME_DSM_MAX_RANGES;
-	} else {
-		ctrl->max_discard_sectors = 0;
-		ctrl->max_discard_segments = 0;
-	}
-
 	/*
 	 * Even though NVMe spec explicitly states that MDTS is not applicable
 	 * to the write-zeroes, we are cautious and limit the size to the
···
 	if (ret)
 		goto free_data;
 
-	if (id->dmrl)
-		ctrl->max_discard_segments = id->dmrl;
+	ctrl->dmrl = id->dmrl;
 	ctrl->dmrsl = le32_to_cpu(id->dmrsl);
 	if (id->wzsl)
 		ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl);

drivers/nvme/host/nvme.h

···
 	u32 max_hw_sectors;
 	u32 max_segments;
 	u32 max_integrity_segments;
-	u32 max_discard_sectors;
-	u32 max_discard_segments;
 	u32 max_zeroes_sectors;
 #ifdef CONFIG_BLK_DEV_ZONED
 	u32 max_zone_append;
 #endif
 	u16 crdt[3];
 	u16 oncs;
+	u8 dmrl;
 	u32 dmrsl;
 	u16 oacs;
 	u16 sqsize;
···
 extern struct device_attribute dev_attr_ana_state;
 extern struct device_attribute subsys_attr_iopolicy;
 
+static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
+{
+	return disk->fops == &nvme_ns_head_ops;
+}
 #else
 #define multipath false
 static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
···
 static inline void nvme_mpath_end_request(struct request *rq)
 {
 }
+static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
+{
+	return false;
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 int nvme_revalidate_zones(struct nvme_ns *ns);
···
 
 static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 {
-	return dev_to_disk(dev)->private_data;
+	struct gendisk *disk = dev_to_disk(dev);
+
+	WARN_ON(nvme_disk_is_ns_head(disk));
+	return disk->private_data;
 }
 
 #ifdef CONFIG_NVME_HWMON

drivers/nvme/host/pci.c

···
 	struct request *abort_req;
 	struct nvme_command cmd = { };
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
+	u8 opcode;
 
 	/* If PCI error recovery process is happening, we cannot reset or
 	 * the recovery mechanism will surely fail.
···
 
 	if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, completion polled\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) QID %d timeout, completion polled\n",
+			 req->tag, nvme_cid(req), nvmeq->qid);
 		return BLK_EH_DONE;
 	}
 
···
 		fallthrough;
 	case NVME_CTRL_DELETING:
 		dev_warn_ratelimited(dev->ctrl.device,
-			 "I/O %d QID %d timeout, disable controller\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) QID %d timeout, disable controller\n",
+			 req->tag, nvme_cid(req), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		nvme_dev_disable(dev, true);
 		return BLK_EH_DONE;
···
 	 * command was already aborted once before and still hasn't been
 	 * returned to the driver, or if this is the admin queue.
 	 */
+	opcode = nvme_req(req)->cmd->common.opcode;
 	if (!nvmeq->qid || iod->aborted) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, reset controller\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, reset controller\n",
+			 req->tag, nvme_cid(req), opcode,
+			 nvme_opcode_str(nvmeq->qid, opcode, 0), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		goto disable;
 	}
···
 	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
 
 	dev_warn(nvmeq->dev->ctrl.device,
-		"I/O %d (%s) QID %d timeout, aborting\n",
-		 req->tag,
-		 nvme_get_opcode_str(nvme_req(req)->cmd->common.opcode),
-		 nvmeq->qid);
+		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, aborting req_op:%s(%u) size:%u\n",
+		 req->tag, nvme_cid(req), opcode, nvme_get_opcode_str(opcode),
+		 nvmeq->qid, blk_op_str(req_op(req)), req_op(req),
+		 blk_rq_bytes(req));
 
 	abort_req = blk_mq_alloc_request(dev->ctrl.admin_q, nvme_req_op(&cmd),
 					 BLK_MQ_REQ_NOWAIT);
···
 	 * controller around but remove all namespaces.
 	 */
 	if (dev->online_queues > 1) {
+		nvme_dbbuf_set(dev);
 		nvme_unquiesce_io_queues(&dev->ctrl);
 		nvme_wait_freeze(&dev->ctrl);
 		nvme_pci_update_nr_queues(dev);
-		nvme_dbbuf_set(dev);
 		nvme_unfreeze(&dev->ctrl);
 	} else {
 		dev_warn(dev->ctrl.device, "IO queues lost\n");
···
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1c5c, 0x174a),   /* SK Hynix P31 SSD */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1c5c, 0x1D59),   /* SK Hynix BC901 */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x15b7, 0x2001),   /*  Sandisk Skyhawk */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1d97, 0x2263),   /* SPCC */

drivers/nvme/host/pr.c

···
 		struct nvme_command *c, void *data, unsigned int data_len)
 {
 	if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
-	    bdev->bd_disk->fops == &nvme_ns_head_ops)
+	    nvme_disk_is_ns_head(bdev->bd_disk))
 		return nvme_send_ns_head_pr_command(bdev, c, data, data_len);
 
 	return nvme_send_ns_pr_command(bdev->bd_disk->private_data, c, data,

drivers/nvme/host/rdma.c

···
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_rdma_queue *queue = req->queue;
 	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+	u8 opcode = req->req.cmd->common.opcode;
+	u8 fctype = req->req.cmd->fabrics.fctype;
+	int qid = nvme_rdma_queue_idx(queue);
 
-	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
-		 rq->tag, nvme_rdma_queue_idx(queue));
+	dev_warn(ctrl->ctrl.device,
+		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout\n",
+		 rq->tag, nvme_cid(rq), opcode,
+		 nvme_opcode_str(qid, opcode, fctype), qid);
 
 	if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) {
 		/*

drivers/nvme/host/sysfs.c

···
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	if (disk->fops == &nvme_bdev_ops)
-		return nvme_get_ns_from_dev(dev)->head;
-	else
+	if (nvme_disk_is_ns_head(disk))
 		return disk->private_data;
+	return nvme_get_ns_from_dev(dev)->head;
 }
 
 static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
···
 	}
 #ifdef CONFIG_NVME_MULTIPATH
 	if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
-		if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */
+		/* per-path attr */
+		if (nvme_disk_is_ns_head(dev_to_disk(dev)))
 			return 0;
 		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
 			return 0;

drivers/nvme/host/tcp.c

···
 						      ctrl->opts->subsysnqn);
 		if (!pskid) {
 			dev_err(ctrl->device, "no valid PSK found\n");
-			ret = -ENOKEY;
-			goto out_free_queue;
+			return -ENOKEY;
 		}
 	}
 
 	ret = nvme_tcp_alloc_queue(ctrl, 0, pskid);
 	if (ret)
-		goto out_free_queue;
+		return ret;
 
 	ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl));
 	if (ret)
···
 	int qid = nvme_tcp_queue_id(req->queue);
 
 	dev_warn(ctrl->device,
-		"queue %d: timeout cid %#x type %d opcode %#x (%s)\n",
-		nvme_tcp_queue_id(req->queue), nvme_cid(rq), pdu->hdr.type,
-		opc, nvme_opcode_str(qid, opc, fctype));
+		 "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n",
+		 rq->tag, nvme_cid(rq), pdu->hdr.type, opc,
+		 nvme_opcode_str(qid, opc, fctype), qid);
 
 	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) {
 		/*

drivers/nvme/target/fc.c

···
 	list_for_each_entry(host, &tgtport->host_list, host_list) {
 		if (host->hosthandle == hosthandle && !host->invalid) {
 			if (nvmet_fc_hostport_get(host))
-				return (host);
+				return host;
 		}
 	}
 

drivers/nvme/target/fcloop.c

···
 {
 	struct fcloop_nport *nport =
 		container_of(ref, struct fcloop_nport, ref);
-	unsigned long flags;
-
-	spin_lock_irqsave(&fcloop_lock, flags);
-	list_del(&nport->nport_list);
-	spin_unlock_irqrestore(&fcloop_lock, flags);
 
 	kfree(nport);
 }
···
 	if (rport && nport->tport)
 		nport->tport->remoteport = NULL;
 	nport->rport = NULL;
+
+	list_del(&nport->nport_list);
 
 	return rport;
 }

drivers/nvme/target/rdma.c

···
 #define NVMET_RDMA_MAX_MDTS			8
 #define NVMET_RDMA_MAX_METADATA_MDTS		5
 
+#define NVMET_RDMA_BACKLOG 128
+
 struct nvmet_rdma_srq;
 
 struct nvmet_rdma_cmd {
···
 	}
 
 	if (queue->host_qid == 0) {
-		/* Let inflight controller teardown complete */
-		flush_workqueue(nvmet_wq);
+		struct nvmet_rdma_queue *q;
+		int pending = 0;
+
+		/* Check for pending controller teardown */
+		mutex_lock(&nvmet_rdma_queue_mutex);
+		list_for_each_entry(q, &nvmet_rdma_queue_list, queue_list) {
+			if (q->nvme_sq.ctrl == queue->nvme_sq.ctrl &&
+			    q->state == NVMET_RDMA_Q_DISCONNECTING)
+				pending++;
+		}
+		mutex_unlock(&nvmet_rdma_queue_mutex);
+		if (pending > NVMET_RDMA_BACKLOG)
+			return NVME_SC_CONNECT_CTRL_BUSY;
 	}
 
 	ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
···
 		goto out_destroy_id;
 	}
 
-	ret = rdma_listen(cm_id, 128);
+	ret = rdma_listen(cm_id, NVMET_RDMA_BACKLOG);
 	if (ret) {
 		pr_err("listening to %pISpcs failed (%d)\n", addr, ret);
 		goto out_destroy_id;

drivers/nvme/target/tcp.c

···
 #include "nvmet.h"
 
 #define NVMET_TCP_DEF_INLINE_DATA_SIZE	(4 * PAGE_SIZE)
+#define NVMET_TCP_MAXH2CDATA		0x400000 /* 16M arbitrary limit */
+#define NVMET_TCP_BACKLOG 128
 
 static int param_store_val(const char *str, int *val, int min, int max)
 {
···
 	icresp->hdr.pdo = 0;
 	icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen);
 	icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0);
-	icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */
+	icresp->maxdata = cpu_to_le32(NVMET_TCP_MAXH2CDATA);
 	icresp->cpda = 0;
 	if (queue->hdr_digest)
 		icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
···
 {
 	struct nvme_tcp_data_pdu *data = &queue->pdu.data;
 	struct nvmet_tcp_cmd *cmd;
+	unsigned int exp_data_len;
 
 	if (likely(queue->nr_cmds)) {
 		if (unlikely(data->ttag >= queue->nr_cmds)) {
 			pr_err("queue %d: received out of bound ttag %u, nr_cmds %u\n",
 				queue->idx, data->ttag, queue->nr_cmds);
-			nvmet_tcp_fatal_error(queue);
-			return -EPROTO;
+			goto err_proto;
 		}
 		cmd = &queue->cmds[data->ttag];
 	} else {
···
 		pr_err("ttag %u unexpected data offset %u (expected %u)\n",
 			data->ttag, le32_to_cpu(data->data_offset),
 			cmd->rbytes_done);
-		/* FIXME: use path and transport errors */
-		nvmet_req_complete(&cmd->req,
-			NVME_SC_INVALID_FIELD | NVME_SC_DNR);
-		return -EPROTO;
+		goto err_proto;
 	}
 
+	exp_data_len = le32_to_cpu(data->hdr.plen) -
+			nvmet_tcp_hdgst_len(queue) -
+			nvmet_tcp_ddgst_len(queue) -
+			sizeof(*data);
+
 	cmd->pdu_len = le32_to_cpu(data->data_length);
+	if (unlikely(cmd->pdu_len != exp_data_len ||
+		     cmd->pdu_len == 0 ||
+		     cmd->pdu_len > NVMET_TCP_MAXH2CDATA)) {
+		pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len);
+		goto err_proto;
+	}
 	cmd->pdu_recv = 0;
 	nvmet_tcp_build_pdu_iovec(cmd);
 	queue->cmd = cmd;
 	queue->rcv_state = NVMET_TCP_RECV_DATA;
 
 	return 0;
+
+err_proto:
+	/* FIXME: use proper transport errors */
+	nvmet_tcp_fatal_error(queue);
+	return -EPROTO;
 }
 
 static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue)
···
 		 (int)sizeof(struct nvme_tcp_icreq_pdu));
 	if (hdr->type == nvme_tcp_icreq &&
 	    hdr->hlen == sizeof(struct nvme_tcp_icreq_pdu) &&
-	    hdr->plen == (__le32)sizeof(struct nvme_tcp_icreq_pdu)) {
+	    hdr->plen == cpu_to_le32(sizeof(struct nvme_tcp_icreq_pdu))) {
 		pr_debug("queue %d: icreq detected\n",
 			 queue->idx);
 		return len;
···
 		goto err_sock;
 	}
 
-	ret = kernel_listen(port->sock, 128);
+	ret = kernel_listen(port->sock, NVMET_TCP_BACKLOG);
 	if (ret) {
 		pr_err("failed to listen %d on port sock\n", ret);
 		goto err_sock;
···
 		container_of(sq, struct nvmet_tcp_queue, nvme_sq);
 
 	if (sq->qid == 0) {
-		/* Let inflight controller teardown complete */
-		flush_workqueue(nvmet_wq);
+		struct nvmet_tcp_queue *q;
+		int pending = 0;
+
+		/* Check for pending controller teardown */
+		mutex_lock(&nvmet_tcp_queue_mutex);
+		list_for_each_entry(q, &nvmet_tcp_queue_list, queue_list) {
+			if (q->nvme_sq.ctrl == sq->ctrl &&
+			    q->state == NVMET_TCP_Q_DISCONNECTING)
+				pending++;
+		}
+		mutex_unlock(&nvmet_tcp_queue_mutex);
+		if (pending > NVMET_TCP_BACKLOG)
+			return NVME_SC_CONNECT_CTRL_BUSY;
 	}
 
 	queue->nr_cmds = sq->size * 2;

drivers/nvme/target/trace.c

···
 	return ret;
 }
 
-const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl)
+const char *nvmet_trace_ctrl_id(struct trace_seq *p, u16 ctrl_id)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
 
···
 	 * If we can know the extra data of the connect command in this stage,
 	 * we can update this print statement later.
 	 */
-	if (ctrl)
-		trace_seq_printf(p, "%d", ctrl->cntlid);
+	if (ctrl_id)
+		trace_seq_printf(p, "%d", ctrl_id);
 	else
 		trace_seq_printf(p, "_");
 	trace_seq_putc(p, 0);

drivers/nvme/target/trace.h

···
 	 nvmet_trace_parse_nvm_cmd(p, opcode, cdw10) :			\
 	 nvmet_trace_parse_admin_cmd(p, opcode, cdw10)))
 
-const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl);
-#define __print_ctrl_name(ctrl)				\
-	nvmet_trace_ctrl_name(p, ctrl)
+const char *nvmet_trace_ctrl_id(struct trace_seq *p, u16 ctrl_id);
+#define __print_ctrl_id(ctrl_id)			\
+	nvmet_trace_ctrl_id(p, ctrl_id)
 
 const char *nvmet_trace_disk_name(struct trace_seq *p, char *name);
 #define __print_disk_name(name)				\
 	nvmet_trace_disk_name(p, name)
 
 #ifndef TRACE_HEADER_MULTI_READ
-static inline struct nvmet_ctrl *nvmet_req_to_ctrl(struct nvmet_req *req)
+static inline u16 nvmet_req_to_ctrl_id(struct nvmet_req *req)
 {
-	return req->sq->ctrl;
+	/*
+	 * The queue and controller pointers are not valid until an association
+	 * has been established.
+	 */
+	if (!req->sq || !req->sq->ctrl)
+		return 0;
+	return req->sq->ctrl->cntlid;
 }
 
 static inline void __assign_req_name(char *name, struct nvmet_req *req)
···
 		return;
 	}
 
-	strncpy(name, req->ns->device_path,
-		min_t(size_t, DISK_NAME_LEN, strlen(req->ns->device_path)));
+	strscpy_pad(name, req->ns->device_path, DISK_NAME_LEN);
 }
 #endif
 
···
 	TP_ARGS(req, cmd),
 	TP_STRUCT__entry(
 		__field(struct nvme_command *, cmd)
-		__field(struct nvmet_ctrl *, ctrl)
+		__field(u16, ctrl_id)
 		__array(char, disk, DISK_NAME_LEN)
 		__field(int, qid)
 		__field(u16, cid)
···
 	),
 	TP_fast_assign(
 		__entry->cmd = cmd;
-		__entry->ctrl = nvmet_req_to_ctrl(req);
+		__entry->ctrl_id = nvmet_req_to_ctrl_id(req);
 		__assign_req_name(__entry->disk, req);
 		__entry->qid = req->sq->qid;
 		__entry->cid = cmd->common.command_id;
···
 		__entry->flags = cmd->common.flags;
 		__entry->nsid = le32_to_cpu(cmd->common.nsid);
 		__entry->metadata = le64_to_cpu(cmd->common.metadata);
-		memcpy(__entry->cdw10, &cmd->common.cdw10,
+		memcpy(__entry->cdw10, &cmd->common.cdws,
 			sizeof(__entry->cdw10));
 	),
 	TP_printk("nvmet%s: %sqid=%d, cmdid=%u, nsid=%u, flags=%#x, "
 		  "meta=%#llx, cmd=(%s, %s)",
-		__print_ctrl_name(__entry->ctrl),
+		__print_ctrl_id(__entry->ctrl_id),
 		__print_disk_name(__entry->disk),
 		__entry->qid, __entry->cid, __entry->nsid,
 		__entry->flags, __entry->metadata,
···
 	TP_PROTO(struct nvmet_req *req),
 	TP_ARGS(req),
 	TP_STRUCT__entry(
-		__field(struct nvmet_ctrl *, ctrl)
+		__field(u16, ctrl_id)
 		__array(char, disk, DISK_NAME_LEN)
 		__field(int, qid)
 		__field(int, cid)
···
 		__field(u16, status)
 	),
 	TP_fast_assign(
-		__entry->ctrl = nvmet_req_to_ctrl(req);
+		__entry->ctrl_id = nvmet_req_to_ctrl_id(req);
 		__entry->qid = req->cq->qid;
 		__entry->cid = req->cqe->command_id;
 		__entry->result = le64_to_cpu(req->cqe->result.u64);
···
 		__assign_req_name(__entry->disk, req);
 	),
 	TP_printk("nvmet%s: %sqid=%d, cmdid=%u, res=%#llx, status=%#x",
-		__print_ctrl_name(__entry->ctrl),
+		__print_ctrl_id(__entry->ctrl_id),
 		__print_disk_name(__entry->disk),
 		__entry->qid, __entry->cid, __entry->result, __entry->status)
 

include/linux/bio.h

···
 {
 	struct bio_vec *bvec = bio_first_bvec_all(bio) + i;
 
+	if (unlikely(i >= bio->bi_vcnt)) {
+		fi->folio = NULL;
+		return;
+	}
+
 	fi->folio = page_folio(bvec->bv_page);
 	fi->offset = bvec->bv_offset +
 			PAGE_SIZE * (bvec->bv_page - &fi->folio->page);
···
 		fi->offset = 0;
 		fi->length = min(folio_size(fi->folio), fi->_seg_count);
 		fi->_next = folio_next(fi->folio);
-	} else if (fi->_i + 1 < bio->bi_vcnt) {
-		bio_first_folio(fi, bio, fi->_i + 1);
 	} else {
-		fi->folio = NULL;
+		bio_first_folio(fi, bio, fi->_i + 1);
 	}
 }
 

include/linux/blk-mq.h

···
 	 */
 	struct blk_mq_tags	*sched_tags;
 
-	/** @run: Number of dispatched requests. */
-	unsigned long		run;
-
 	/** @numa_node: NUMA node the storage adapter has been connected to. */
 	unsigned int		numa_node;
 	/** @queue_num: Index of this hardware queue. */

include/linux/ioprio.h

···
 }
 
 #ifdef CONFIG_BLOCK
-int __get_task_ioprio(struct task_struct *p);
+/*
+ * If the task has set an I/O priority, use that. Otherwise, return
+ * the default I/O priority.
+ *
+ * Expected to be called for current task or with task_lock() held to keep
+ * io_context stable.
+ */
+static inline int __get_task_ioprio(struct task_struct *p)
+{
+	struct io_context *ioc = p->io_context;
+	int prio;
+
+	if (!ioc)
+		return IOPRIO_DEFAULT;
+
+	if (p != current)
+		lockdep_assert_held(&p->alloc_lock);
+
+	prio = ioc->ioprio;
+	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
+		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
+					 task_nice_ioprio(p));
+	return prio;
+}
 #else
 static inline int __get_task_ioprio(struct task_struct *p)
 {

include/linux/nvme.h

···
 #define NVMF_TRSVCID_SIZE	32
 #define NVMF_TRADDR_SIZE	256
 #define NVMF_TSAS_SIZE		256
-#define NVMF_AUTH_HASH_LEN	64
 
 #define NVME_DISC_SUBSYS_NAME	"nqn.2014-08.org.nvmexpress.discovery"
 

lib/sbitmap.c

···
 	unsigned int shallow_depth;
 
 	/*
-	 * For each batch, we wake up one queue. We need to make sure that our
-	 * batch size is small enough that the full depth of the bitmap,
-	 * potentially limited by a shallow depth, is enough to wake up all of
-	 * the queues.
-	 *
 	 * Each full word of the bitmap has bits_per_word bits, and there might
 	 * be a partial word. There are depth / bits_per_word full words and
 	 * depth % bits_per_word bits left over. In bitwise arithmetic: