Merge tag 'for-7.0/block-20260206' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull block updates from Jens Axboe:

 - Support for batch request processing for ublk, improving the
   efficiency of the kernel/ublk server communication. This can yield
   nice 7-12% performance improvements

 - Support for integrity data for ublk

 - Various other ublk improvements and additions, including a ton of
   selftests additions and updated

 - Move the handling of blk-crypto software fallback from below the
   block layer to above it. This reduces the complexity of dealing with
   bio splitting

 - Series fixing a number of potential deadlocks in blk-mq related to
   the queue usage counter and writeback throttling and rq-qos debugfs
   handling

 - Add an async_depth queue attribute, to resolve a performance
   regression that's been around for a qhilw related to the scheduler
   depth handling

 - Only use task_work for IOPOLL completions on NVMe, if it is necessary
   to do so. An earlier fix for an issue resulted in all these
   completions being punted to task_work, to guarantee that completions
   were only run for a given io_uring ring when it was local to that
   ring. With the new changes, we can detect if it's necessary to use
   task_work or not, and avoid it if possible.

 - rnbd fixes:
      - Fix refcount underflow in device unmap path
      - Handle PREFLUSH and NOUNMAP flags properly in protocol
      - Fix server-side bi_size for special IOs
      - Zero response buffer before use
      - Fix trace format for flags
      - Add .release to rnbd_dev_ktype

 - MD pull requests via Yu Kuai
      - Fix raid5_run() to return error when log_init() fails
      - Fix IO hang with degraded array with llbitmap
      - Fix percpu_ref not resurrected on suspend timeout in llbitmap
      - Fix GPF in write_page caused by resize race
      - Fix NULL pointer dereference in process_metadata_update
      - Fix hang when stopping arrays with metadata through dm-raid
      - Fix any_working flag handling in raid10_sync_request
      - Refactor sync/recovery code path, improve error handling for
        badblocks, and remove unused recovery_disabled field
      - Consolidate mddev boolean fields into mddev_flags
      - Use mempool to allocate stripe_request_ctx and make sure
        max_sectors is not less than io_opt in raid5
      - Fix return value of mddev_trylock
      - Fix memory leak in raid1_run()
      - Add Li Nan as mdraid reviewer

 - Move phys_vec definitions to the kernel types, mostly in preparation
   for some VFIO and RDMA changes

 - Improve the speed for secure erase for some devices

 - Various little rust updates

 - Various other minor fixes, improvements, and cleanups

* tag 'for-7.0/block-20260206' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (162 commits)
  blk-mq: ABI/sysfs-block: fix docs build warnings
  selftests: ublk: organize test directories by test ID
  block: decouple secure erase size limit from discard size limit
  block: remove redundant kill_bdev() call in set_blocksize()
  blk-mq: add documentation for new queue attribute async_dpeth
  block, bfq: convert to use request_queue->async_depth
  mq-deadline: covert to use request_queue->async_depth
  kyber: covert to use request_queue->async_depth
  blk-mq: add a new queue sysfs attribute async_depth
  blk-mq: factor out a helper blk_mq_limit_depth()
  blk-mq-sched: unify elevators checking for async requests
  block: convert nr_requests to unsigned int
  block: don't use strcpy to copy blockdev name
  blk-mq-debugfs: warn about possible deadlock
  blk-mq-debugfs: add missing debugfs_mutex in blk_mq_debugfs_register_hctxs()
  blk-mq-debugfs: remove blk_mq_debugfs_unregister_rqos()
  blk-mq-debugfs: make blk_mq_debugfs_register_rqos() static
  blk-rq-qos: fix possible debugfs_mutex deadlock
  blk-mq-debugfs: factor out a helper to register debugfs for all rq_qos
  blk-wbt: fix possible deadlock to nest pcpu_alloc_mutex under q_usage_counter
  ...

Author: torvalds

Documentation/ABI/stable/sysfs-block

@@ -609,6 +609,51 @@ Description:
 		enabled, and whether tags are shared.
 
 
+What:		/sys/block/<disk>/queue/async_depth
+Date:		August 2025
+Contact:	linux-block@vger.kernel.org
+Description:
+		[RW] Controls how many asynchronous requests may be allocated
+		in the block layer. The value is always capped at nr_requests.
+
+		When no elevator is active (none):
+
+		- async_depth is always equal to nr_requests.
+
+		For bfq scheduler:
+
+		- By default, async_depth is set to 75% of nr_requests.
+		  Internal limits are then derived from this value:
+
+		  * Sync writes: limited to async_depth (≈75% of nr_requests).
+		  * Async I/O: limited to ~2/3 of async_depth (≈50% of
+		    nr_requests).
+
+		  If a bfq_queue is weight-raised:
+
+		  * Sync writes: limited to ~1/2 of async_depth (≈37% of
+		    nr_requests).
+		  * Async I/O: limited to ~1/4 of async_depth (≈18% of
+		    nr_requests).
+
+		- If the user writes a custom value to async_depth, BFQ will
+		  recompute these limits proportionally based on the new value.
+
+		For Kyber:
+
+		- By default async_depth is set to 75% of nr_requests.
+		- If the user writes a custom value to async_depth, then it
+		  overrides the default and directly controls the limit for
+		  writes and async I/O.
+
+		For mq-deadline:
+
+		- By default async_depth is set to nr_requests.
+		- If the user writes a custom value to async_depth, then it
+		  overrides the default and directly controls the limit for
+		  writes and async I/O.
+
+
 What:		/sys/block/<disk>/queue/nr_zones
 Date:		November 2018
 Contact:	Damien Le Moal <damien.lemoal@wdc.com>

Documentation/block/biovecs.rst

@@ -135,7 +135,6 @@ Usage of helpers:
 	bio_first_bvec_all()
 	bio_first_page_all()
 	bio_first_folio_all()
-	bio_last_bvec_all()
 
 * The following helpers iterate over single-page segment. The passed 'struct
   bio_vec' will contain a single-page IO vector during the iteration::

Documentation/block/inline-encryption.rst

@@ -206,6 +206,12 @@ it to a bio, given the blk_crypto_key and the data unit number that will be used
 for en/decryption.  Users don't need to worry about freeing the bio_crypt_ctx
 later, as that happens automatically when the bio is freed or reset.
 
+To submit a bio that uses inline encryption, users must call
+``blk_crypto_submit_bio()`` instead of the usual ``submit_bio()``.  This will
+submit the bio to the underlying driver if it supports inline crypto, or else
+call the blk-crypto fallback routines before submitting normal bios to the
+underlying drivers.
+
 Finally, when done using inline encryption with a blk_crypto_key on a
 block_device, users must call ``blk_crypto_evict_key()``.  This ensures that
 the key is evicted from all keyslots it may be programmed into and unlinked from

Documentation/block/ublk.rst

@@ -260,9 +260,12 @@ The following IO commands are communicated via io_uring passthrough command,
 and each command is only for forwarding the IO and committing the result
 with specified IO tag in the command data:
 
-- ``UBLK_IO_FETCH_REQ``
+Traditional Per-I/O Commands
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-  Sent from the server IO pthread for fetching future incoming IO requests
+- ``UBLK_U_IO_FETCH_REQ``
+
+  Sent from the server I/O pthread for fetching future incoming I/O requests
   destined to ``/dev/ublkb*``. This command is sent only once from the server
   IO pthread for ublk driver to setup IO forward environment.
 
@@ -278,7 +281,7 @@ with specified IO tag in the command data:
   supported by the driver, daemons must be per-queue instead - i.e. all I/Os
   associated to a single qid must be handled by the same task.
 
-- ``UBLK_IO_COMMIT_AND_FETCH_REQ``
+- ``UBLK_U_IO_COMMIT_AND_FETCH_REQ``
 
   When an IO request is destined to ``/dev/ublkb*``, the driver stores
   the IO's ``ublksrv_io_desc`` to the specified mapped area; then the
@@ -293,7 +296,7 @@ with specified IO tag in the command data:
   requests with the same IO tag. That is, ``UBLK_IO_COMMIT_AND_FETCH_REQ``
   is reused for both fetching request and committing back IO result.
 
-- ``UBLK_IO_NEED_GET_DATA``
+- ``UBLK_U_IO_NEED_GET_DATA``
 
   With ``UBLK_F_NEED_GET_DATA`` enabled, the WRITE request will be firstly
   issued to ublk server without data copy. Then, IO backend of ublk server
@@ -322,6 +325,59 @@ with specified IO tag in the command data:
   ``UBLK_IO_COMMIT_AND_FETCH_REQ`` to the server, ublkdrv needs to copy
   the server buffer (pages) read to the IO request pages.
 
+Batch I/O Commands (UBLK_F_BATCH_IO)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The ``UBLK_F_BATCH_IO`` feature provides an alternative high-performance
+I/O handling model that replaces the traditional per-I/O commands with
+per-queue batch commands. This significantly reduces communication overhead
+and enables better load balancing across multiple server tasks.
+
+Key differences from traditional mode:
+
+- **Per-queue vs Per-I/O**: Commands operate on queues rather than individual I/Os
+- **Batch processing**: Multiple I/Os are handled in single operations
+- **Multishot commands**: Use io_uring multishot for reduced submission overhead
+- **Flexible task assignment**: Any task can handle any I/O (no per-I/O daemons)
+- **Better load balancing**: Tasks can adjust their workload dynamically
+
+Batch I/O Commands:
+
+- ``UBLK_U_IO_PREP_IO_CMDS``
+
+  Prepares multiple I/O commands in batch. The server provides a buffer
+  containing multiple I/O descriptors that will be processed together.
+  This reduces the number of individual command submissions required.
+
+- ``UBLK_U_IO_COMMIT_IO_CMDS``
+
+  Commits results for multiple I/O operations in batch, and prepares the
+  I/O descriptors to accept new requests. The server provides a buffer
+  containing the results of multiple completed I/Os, allowing efficient
+  bulk completion of requests.
+
+- ``UBLK_U_IO_FETCH_IO_CMDS``
+
+  **Multishot command** for fetching I/O commands in batch. This is the key
+  command that enables high-performance batch processing:
+
+  * Uses io_uring multishot capability for reduced submission overhead
+  * Single command can fetch multiple I/O requests over time
+  * Buffer size determines maximum batch size per operation
+  * Multiple fetch commands can be submitted for load balancing
+  * Only one fetch command is active at any time per queue
+  * Supports dynamic load balancing across multiple server tasks
+
+  It is one typical multishot io_uring request with provided buffer, and it
+  won't be completed until any failure is triggered.
+
+  Each task can submit ``UBLK_U_IO_FETCH_IO_CMDS`` with different buffer
+  sizes to control how much work it handles. This enables sophisticated
+  load balancing strategies in multi-threaded servers.
+
+Migration: Applications using traditional commands (``UBLK_U_IO_FETCH_REQ``,
+``UBLK_U_IO_COMMIT_AND_FETCH_REQ``) cannot use batch mode simultaneously.
+
 Zero copy
 ---------
 

MAINTAINERS

@@ -24276,6 +24276,7 @@ F:	include/linux/property.h
 SOFTWARE RAID (Multiple Disks) SUPPORT
 M:	Song Liu <song@kernel.org>
 M:	Yu Kuai <yukuai@fnnas.com>
+R:	Li Nan <linan122@huawei.com>
 L:	linux-raid@vger.kernel.org
 S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-raid/list/

block/bdev.c

@@ -208,7 +208,6 @@ int set_blocksize(struct file *file, int size)
 
 		inode->i_blkbits = blksize_bits(size);
 		mapping_set_folio_min_order(inode->i_mapping, get_order(size));
-		kill_bdev(bdev);
 		filemap_invalidate_unlock(inode->i_mapping);
 		inode_unlock(inode);
 	}

block/bfq-iosched.c

@@ -231,7 +231,7 @@ static struct kmem_cache *bfq_pool;
 #define BFQ_RQ_SEEKY(bfqd, last_pos, rq) \
 	(get_sdist(last_pos, rq) >			\
 	 BFQQ_SEEK_THR &&				\
-	 (!blk_queue_nonrot(bfqd->queue) ||		\
+	 (blk_queue_rot(bfqd->queue) ||			\
 	  blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT))
 #define BFQQ_CLOSE_THR		(sector_t)(8 * 1024)
 #define BFQQ_SEEKY(bfqq)	(hweight32(bfqq->seek_history) > 19)
@@ -697,7 +697,7 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 	unsigned int limit, act_idx;
 
 	/* Sync reads have full depth available */
-	if (op_is_sync(opf) && !op_is_write(opf))
+	if (blk_mq_is_sync_read(opf))
 		limit = data->q->nr_requests;
 	else
 		limit = bfqd->async_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)];
@@ -4165,7 +4165,7 @@ static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 
 	/* don't use too short time intervals */
 	if (delta_usecs < 1000) {
-		if (blk_queue_nonrot(bfqd->queue))
+		if (!blk_queue_rot(bfqd->queue))
 			 /*
 			  * give same worst-case guarantees as idling
 			  * for seeky
@@ -4487,7 +4487,7 @@ static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd,
 					     struct bfq_queue *bfqq)
 {
 	bool rot_without_queueing =
-		!blk_queue_nonrot(bfqd->queue) && !bfqd->hw_tag,
+		blk_queue_rot(bfqd->queue) && !bfqd->hw_tag,
 		bfqq_sequential_and_IO_bound,
 		idling_boosts_thr;
 
@@ -4521,7 +4521,7 @@ static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd,
 	 * flash-based device.
 	 */
 	idling_boosts_thr = rot_without_queueing ||
-		((!blk_queue_nonrot(bfqd->queue) || !bfqd->hw_tag) &&
+		((blk_queue_rot(bfqd->queue) || !bfqd->hw_tag) &&
 		 bfqq_sequential_and_IO_bound);
 
 	/*
@@ -4722,7 +4722,7 @@ bfq_choose_bfqq_for_injection(struct bfq_data *bfqd)
 			 * there is only one in-flight large request
 			 * at a time.
 			 */
-			if (blk_queue_nonrot(bfqd->queue) &&
+			if (!blk_queue_rot(bfqd->queue) &&
 			    blk_rq_sectors(bfqq->next_rq) >=
 			    BFQQ_SECT_THR_NONROT &&
 			    bfqd->tot_rq_in_driver >= 1)
@@ -6340,7 +6340,7 @@ static void bfq_update_hw_tag(struct bfq_data *bfqd)
 	bfqd->hw_tag_samples = 0;
 
 	bfqd->nonrot_with_queueing =
-		blk_queue_nonrot(bfqd->queue) && bfqd->hw_tag;
+		!blk_queue_rot(bfqd->queue) && bfqd->hw_tag;
 }
 
 static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
@@ -7112,39 +7112,29 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
 static void bfq_depth_updated(struct request_queue *q)
 {
 	struct bfq_data *bfqd = q->elevator->elevator_data;
-	unsigned int nr_requests = q->nr_requests;
+	unsigned int async_depth = q->async_depth;
 
 	/*
-	 * In-word depths if no bfq_queue is being weight-raised:
-	 * leaving 25% of tags only for sync reads.
+	 * By default:
+	 *  - sync reads are not limited
+	 * If bfqq is not being weight-raised:
+	 *  - sync writes are limited to 75%(async depth default value)
+	 *  - async IO are limited to 50%
+	 * If bfqq is being weight-raised:
+	 *  - sync writes are limited to ~37%
+	 *  - async IO are limited to ~18
 	 *
-	 * In next formulas, right-shift the value
-	 * (1U<<bt->sb.shift), instead of computing directly
-	 * (1U<<(bt->sb.shift - something)), to be robust against
-	 * any possible value of bt->sb.shift, without having to
-	 * limit 'something'.
+	 * If request_queue->async_depth is updated by user, all limit are
+	 * updated relatively.
 	 */
-	/* no more than 50% of tags for async I/O */
-	bfqd->async_depths[0][0] = max(nr_requests >> 1, 1U);
-	/*
-	 * no more than 75% of tags for sync writes (25% extra tags
-	 * w.r.t. async I/O, to prevent async I/O from starving sync
-	 * writes)
-	 */
-	bfqd->async_depths[0][1] = max((nr_requests * 3) >> 2, 1U);
+	bfqd->async_depths[0][1] = async_depth;
+	bfqd->async_depths[0][0] = max(async_depth * 2 / 3, 1U);
+	bfqd->async_depths[1][1] = max(async_depth >> 1, 1U);
+	bfqd->async_depths[1][0] = max(async_depth >> 2, 1U);
 
 	/*
-	 * In-word depths in case some bfq_queue is being weight-
-	 * raised: leaving ~63% of tags for sync reads. This is the
-	 * highest percentage for which, in our tests, application
-	 * start-up times didn't suffer from any regression due to tag
-	 * shortage.
+	 * Due to cgroup qos, the allowed request for bfqq might be 1
 	 */
-	/* no more than ~18% of tags for async I/O */
-	bfqd->async_depths[1][0] = max((nr_requests * 3) >> 4, 1U);
-	/* no more than ~37% of tags for sync writes (~20% extra tags) */
-	bfqd->async_depths[1][1] = max((nr_requests * 6) >> 4, 1U);
-
 	blk_mq_set_min_shallow_depth(q, 1);
 }
 
@@ -7293,7 +7283,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_queue *eq)
 	INIT_HLIST_HEAD(&bfqd->burst_list);
 
 	bfqd->hw_tag = -1;
-	bfqd->nonrot_with_queueing = blk_queue_nonrot(bfqd->queue);
+	bfqd->nonrot_with_queueing = !blk_queue_rot(bfqd->queue);
 
 	bfqd->bfq_max_budget = bfq_default_max_budget;
 
@@ -7328,9 +7318,9 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_queue *eq)
 	 * Begin by assuming, optimistically, that the device peak
 	 * rate is equal to 2/3 of the highest reference rate.
 	 */
-	bfqd->rate_dur_prod = ref_rate[blk_queue_nonrot(bfqd->queue)] *
-		ref_wr_duration[blk_queue_nonrot(bfqd->queue)];
-	bfqd->peak_rate = ref_rate[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
+	bfqd->rate_dur_prod = ref_rate[!blk_queue_rot(bfqd->queue)] *
+		ref_wr_duration[!blk_queue_rot(bfqd->queue)];
+	bfqd->peak_rate = ref_rate[!blk_queue_rot(bfqd->queue)] * 2 / 3;
 
 	/* see comments on the definition of next field inside bfq_data */
 	bfqd->actuator_load_threshold = 4;
@@ -7365,6 +7355,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_queue *eq)
 	blk_queue_flag_set(QUEUE_FLAG_DISABLE_WBT_DEF, q);
 	wbt_disable_default(q->disk);
 	blk_stat_enable_accounting(q);
+	q->async_depth = (q->nr_requests * 3) >> 2;
 
 	return 0;
 

block/bio-integrity-auto.c

@@ -52,19 +52,7 @@ static bool bip_should_check(struct bio_integrity_payload *bip)
 
 static bool bi_offload_capable(struct blk_integrity *bi)
 {
-	switch (bi->csum_type) {
-	case BLK_INTEGRITY_CSUM_CRC64:
-		return bi->metadata_size == sizeof(struct crc64_pi_tuple);
-	case BLK_INTEGRITY_CSUM_CRC:
-	case BLK_INTEGRITY_CSUM_IP:
-		return bi->metadata_size == sizeof(struct t10_pi_tuple);
-	default:
-		pr_warn_once("%s: unknown integrity checksum type:%d\n",
-			__func__, bi->csum_type);
-		fallthrough;
-	case BLK_INTEGRITY_CSUM_NONE:
-		return false;
-	}
+	return bi->metadata_size == bi->pi_tuple_size;
 }
 
 /**

block/bio.c

@@ -301,9 +301,12 @@ EXPORT_SYMBOL(bio_init);
  */
 void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf)
 {
+	struct bio_vec          *bv = bio->bi_io_vec;
+
 	bio_uninit(bio);
 	memset(bio, 0, BIO_RESET_BYTES);
 	atomic_set(&bio->__bi_remaining, 1);
+	bio->bi_io_vec = bv;
 	bio->bi_bdev = bdev;
 	if (bio->bi_bdev)
 		bio_associate_blkg(bio);
@@ -1196,8 +1199,8 @@ void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter)
 {
 	WARN_ON_ONCE(bio->bi_max_vecs);
 
-	bio->bi_vcnt = iter->nr_segs;
 	bio->bi_io_vec = (struct bio_vec *)iter->bvec;
+	bio->bi_iter.bi_idx = 0;
 	bio->bi_iter.bi_bvec_done = iter->iov_offset;
 	bio->bi_iter.bi_size = iov_iter_count(iter);
 	bio_set_flag(bio, BIO_CLONED);