Merge tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Series of merge handling cleanups (Baolin, Christoph)

 - Series of blk-throttle fixes and cleanups (Baolin)

 - Series cleaning up BDI, seperating the block device from the
   backing_dev_info (Christoph)

 - Removal of bdget() as a generic API (Christoph)

 - Removal of blkdev_get() as a generic API (Christoph)

 - Cleanup of is-partition checks (Christoph)

 - Series reworking disk revalidation (Christoph)

 - Series cleaning up bio flags (Christoph)

 - bio crypt fixes (Eric)

 - IO stats inflight tweak (Gabriel)

 - blk-mq tags fixes (Hannes)

 - Buffer invalidation fixes (Jan)

 - Allow soft limits for zone append (Johannes)

 - Shared tag set improvements (John, Kashyap)

 - Allow IOPRIO_CLASS_RT for CAP_SYS_NICE (Khazhismel)

 - DM no-wait support (Mike, Konstantin)

 - Request allocation improvements (Ming)

 - Allow md/dm/bcache to use IO stat helpers (Song)

 - Series improving blk-iocost (Tejun)

 - Various cleanups (Geert, Damien, Danny, Julia, Tetsuo, Tian, Wang,
   Xianting, Yang, Yufen, yangerkun)

* tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block: (191 commits)
  block: fix uapi blkzoned.h comments
  blk-mq: move cancel of hctx->run_work to the front of blk_exit_queue
  blk-mq: get rid of the dead flush handle code path
  block: get rid of unnecessary local variable
  block: fix comment and add lockdep assert
  blk-mq: use helper function to test hw stopped
  block: use helper function to test queue register
  block: remove redundant mq check
  block: invoke blk_mq_exit_sched no matter whether have .exit_sched
  percpu_ref: don't refer to ref->data if it isn't allocated
  block: ratelimit handle_bad_sector() message
  blk-throttle: Re-use the throtl_set_slice_end()
  blk-throttle: Open code __throtl_de/enqueue_tg()
  blk-throttle: Move service tree validation out of the throtl_rb_first()
  blk-throttle: Move the list operation after list validation
  blk-throttle: Fix IO hang for a corner case
  blk-throttle: Avoid tracking latency if low limit is invalid
  blk-throttle: Avoid getting the current time if tg->last_finish_time is 0
  blk-throttle: Remove a meaningless parameter for throtl_downgrade_state()
  block: Remove redundant 'return' statement
  ...

Documentation/filesystems/locking.rst

@@ -488,9 +488,6 @@ getgeo:			no
 swap_slot_free_notify:	no	(see below)
 ======================= ===================
 
-unlock_native_capacity and revalidate_disk are called only from
-check_disk_change().
-
 swap_slot_free_notify is called with swap_lock and sometimes the page lock
 held.
 

Documentation/userspace-api/ioctl/hdio.rst

@@ -181,7 +181,7 @@ HDIO_SET_UNMASKINTR
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY	Controller busy
@@ -231,7 +231,7 @@ HDIO_SET_MULTCOUNT
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range supported by disk.
 	  - EBUSY	Controller busy or blockmode already set.
@@ -295,7 +295,7 @@ HDIO_GET_IDENTITY
 		the ATA specification.
 
 	error returns:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - ENOMSG	IDENTIFY DEVICE information not available
 
 	notes:
@@ -355,7 +355,7 @@ HDIO_SET_KEEPSETTINGS
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY		Controller busy
@@ -1055,7 +1055,7 @@ HDIO_SET_32BIT
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 3]
 	  - EBUSY	Controller busy
@@ -1085,7 +1085,7 @@ HDIO_SET_NOWERR
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY		Controller busy
@@ -1113,7 +1113,7 @@ HDIO_SET_DMA
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY	Controller busy
@@ -1141,7 +1141,7 @@ HDIO_SET_PIO_MODE
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 255]
 	  - EBUSY	Controller busy
@@ -1237,7 +1237,7 @@ HDIO_SET_WCACHE
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY	Controller busy
@@ -1265,7 +1265,7 @@ HDIO_SET_ACOUSTIC
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 254]
 	  - EBUSY	Controller busy
@@ -1305,7 +1305,7 @@ HDIO_SET_ADDRESS
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 2]
 	  - EBUSY		Controller busy
@@ -1331,7 +1331,7 @@ HDIO_SET_IDE_SCSI
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY	Controller busy

block/Kconfig

@@ -161,8 +161,6 @@ config BLK_WBT_MQ
 	depends on BLK_WBT
 	help
 	Enable writeback throttling by default on multiqueue devices.
-	Multiqueue currently doesn't have support for IO scheduling,
-	enabling this option is recommended.
 
 config BLK_DEBUG_FS
 	bool "Block layer debugging information in debugfs"

block/bfq-iosched.c

@@ -4640,6 +4640,9 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 
+	if (!atomic_read(&hctx->elevator_queued))
+		return false;
+
 	/*
 	 * Avoiding lock: a race on bfqd->busy_queues should cause at
 	 * most a call to dispatch for nothing
@@ -5554,6 +5557,7 @@ static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		bfq_insert_request(hctx, rq, at_head);
+		atomic_inc(&hctx->elevator_queued);
 	}
 }
 
@@ -5921,6 +5925,7 @@ static void bfq_finish_requeue_request(struct request *rq)
 
 		bfq_completed_request(bfqq, bfqd);
 		bfq_finish_requeue_request_body(bfqq);
+		atomic_dec(&rq->mq_hctx->elevator_queued);
 
 		spin_unlock_irqrestore(&bfqd->lock, flags);
 	} else {
@@ -6360,8 +6365,8 @@ static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)
 	struct blk_mq_tags *tags = hctx->sched_tags;
 	unsigned int min_shallow;
 
-	min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags);
-	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow);
+	min_shallow = bfq_update_depths(bfqd, tags->bitmap_tags);
+	sbitmap_queue_min_shallow_depth(tags->bitmap_tags, min_shallow);
 }
 
 static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)

block/bio.c

@@ -713,20 +713,18 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 
 	__bio_clone_fast(b, bio);
 
-	bio_crypt_clone(b, bio, gfp_mask);
+	if (bio_crypt_clone(b, bio, gfp_mask) < 0)
+		goto err_put;
 
-	if (bio_integrity(bio)) {
-		int ret;
+	if (bio_integrity(bio) &&
+	    bio_integrity_clone(b, bio, gfp_mask) < 0)
+		goto err_put;
 
-		ret = bio_integrity_clone(b, bio, gfp_mask);
+	return b;
 
-		if (ret < 0) {
+err_put:
 	bio_put(b);
 	return NULL;
-		}
-	}
-
-	return b;
 }
 EXPORT_SYMBOL(bio_clone_fast);
 

block/blk-cgroup.c

@@ -119,6 +119,8 @@ static void blkg_async_bio_workfn(struct work_struct *work)
 					     async_bio_work);
 	struct bio_list bios = BIO_EMPTY_LIST;
 	struct bio *bio;
+	struct blk_plug plug;
+	bool need_plug = false;
 
 	/* as long as there are pending bios, @blkg can't go away */
 	spin_lock_bh(&blkg->async_bio_lock);
@@ -126,8 +128,15 @@ static void blkg_async_bio_workfn(struct work_struct *work)
 	bio_list_init(&blkg->async_bios);
 	spin_unlock_bh(&blkg->async_bio_lock);
 
+	/* start plug only when bio_list contains at least 2 bios */
+	if (bios.head && bios.head->bi_next) {
+		need_plug = true;
+		blk_start_plug(&plug);
+	}
 	while ((bio = bio_list_pop(&bios)))
 		submit_bio(bio);
+	if (need_plug)
+		blk_finish_plug(&plug);
 }
 
 /**
@@ -1613,16 +1622,24 @@ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now)
 static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 {
 	unsigned long pflags;
+	bool clamp;
 	u64 now = ktime_to_ns(ktime_get());
 	u64 exp;
 	u64 delay_nsec = 0;
 	int tok;
 
 	while (blkg->parent) {
-		if (atomic_read(&blkg->use_delay)) {
+		int use_delay = atomic_read(&blkg->use_delay);
+
+		if (use_delay) {
+			u64 this_delay;
+
 			blkcg_scale_delay(blkg, now);
-			delay_nsec = max_t(u64, delay_nsec,
-					   atomic64_read(&blkg->delay_nsec));
+			this_delay = atomic64_read(&blkg->delay_nsec);
+			if (this_delay > delay_nsec) {
+				delay_nsec = this_delay;
+				clamp = use_delay > 0;
+			}
 		}
 		blkg = blkg->parent;
 	}
@@ -1634,9 +1651,12 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 	 * Let's not sleep for all eternity if we've amassed a huge delay.
 	 * Swapping or metadata IO can accumulate 10's of seconds worth of
 	 * delay, and we want userspace to be able to do _something_ so cap the
-	 * delays at 1 second.  If there's 10's of seconds worth of delay then
-	 * the tasks will be delayed for 1 second for every syscall.
+	 * delays at 0.25s. If there's 10's of seconds worth of delay then the
+	 * tasks will be delayed for 0.25 second for every syscall. If
+	 * blkcg_set_delay() was used as indicated by negative use_delay, the
+	 * caller is responsible for regulating the range.
 	 */
+	if (clamp)
 		delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);
 
 	if (use_memdelay)

block/blk-crypto-internal.h

@@ -142,13 +142,24 @@ static inline void blk_crypto_free_request(struct request *rq)
 		__blk_crypto_free_request(rq);
 }
 
-void __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
+int __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
 			     gfp_t gfp_mask);
-static inline void blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
+/**
+ * blk_crypto_rq_bio_prep - Prepare a request's crypt_ctx when its first bio
+ *			    is inserted
+ * @rq: The request to prepare
+ * @bio: The first bio being inserted into the request
+ * @gfp_mask: Memory allocation flags
+ *
+ * Return: 0 on success, -ENOMEM if out of memory.  -ENOMEM is only possible if
+ *	   @gfp_mask doesn't include %__GFP_DIRECT_RECLAIM.
+ */
+static inline int blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
 					 gfp_t gfp_mask)
 {
 	if (bio_has_crypt_ctx(bio))
-		__blk_crypto_rq_bio_prep(rq, bio, gfp_mask);
+		return __blk_crypto_rq_bio_prep(rq, bio, gfp_mask);
+	return 0;
 }
 
 /**

block/blk-crypto.c

@@ -81,7 +81,15 @@ subsys_initcall(bio_crypt_ctx_init);
 void bio_crypt_set_ctx(struct bio *bio, const struct blk_crypto_key *key,
 		       const u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], gfp_t gfp_mask)
 {
-	struct bio_crypt_ctx *bc = mempool_alloc(bio_crypt_ctx_pool, gfp_mask);
+	struct bio_crypt_ctx *bc;
+
+	/*
+	 * The caller must use a gfp_mask that contains __GFP_DIRECT_RECLAIM so
+	 * that the mempool_alloc() can't fail.
+	 */
+	WARN_ON_ONCE(!(gfp_mask & __GFP_DIRECT_RECLAIM));
+
+	bc = mempool_alloc(bio_crypt_ctx_pool, gfp_mask);
 
 	bc->bc_key = key;
 	memcpy(bc->bc_dun, dun, sizeof(bc->bc_dun));
@@ -95,10 +103,13 @@ void __bio_crypt_free_ctx(struct bio *bio)
 	bio->bi_crypt_context = NULL;
 }
 
-void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask)
+int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask)
 {
 	dst->bi_crypt_context = mempool_alloc(bio_crypt_ctx_pool, gfp_mask);
+	if (!dst->bi_crypt_context)
+		return -ENOMEM;
 	*dst->bi_crypt_context = *src->bi_crypt_context;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(__bio_crypt_clone);
 
@@ -280,20 +291,16 @@ bool __blk_crypto_bio_prep(struct bio **bio_ptr)
 	return false;
 }
 
-/**
- * __blk_crypto_rq_bio_prep - Prepare a request's crypt_ctx when its first bio
- *			      is inserted
- *
- * @rq: The request to prepare
- * @bio: The first bio being inserted into the request
- * @gfp_mask: gfp mask
- */
-void __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
+int __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
 			     gfp_t gfp_mask)
 {
-	if (!rq->crypt_ctx)
+	if (!rq->crypt_ctx) {
 		rq->crypt_ctx = mempool_alloc(bio_crypt_ctx_pool, gfp_mask);
+		if (!rq->crypt_ctx)
+			return -ENOMEM;
+	}
 	*rq->crypt_ctx = *bio->bi_crypt_context;
+	return 0;
 }
 
 /**

block/blk-integrity.c

@@ -183,7 +183,6 @@ bool blk_integrity_merge_rq(struct request_queue *q, struct request *req,
 
 	return true;
 }
-EXPORT_SYMBOL(blk_integrity_merge_rq);
 
 bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 			     struct bio *bio)
@@ -212,7 +211,6 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 
 	return true;
 }
-EXPORT_SYMBOL(blk_integrity_merge_bio);
 
 struct integrity_sysfs_entry {
 	struct attribute attr;
@@ -408,7 +406,7 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 	bi->tuple_size = template->tuple_size;
 	bi->tag_size = template->tag_size;
 
-	disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	if (disk->queue->ksm) {
@@ -428,7 +426,7 @@ EXPORT_SYMBOL(blk_integrity_register);
  */
 void blk_integrity_unregister(struct gendisk *disk)
 {
-	disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
+	blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
 }
 EXPORT_SYMBOL(blk_integrity_unregister);

block/blk-iolatency.c

@@ -1046,7 +1046,7 @@ static int __init iolatency_init(void)
 
 static void __exit iolatency_exit(void)
 {
-	return blkcg_policy_unregister(&blkcg_policy_iolatency);
+	blkcg_policy_unregister(&blkcg_policy_iolatency);
 }
 
 module_init(iolatency_init);

block/blk-lib.c

@@ -64,7 +64,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		return -EINVAL;
 
 	/* In case the discard request is in a partition */
-	if (bdev->bd_partno)
+	if (bdev_is_partition(bdev))
 		part_offset = bdev->bd_part->start_sect;
 
 	while (nr_sects) {

block/blk-map.c

@@ -12,7 +12,8 @@
 #include "blk.h"
 
 struct bio_map_data {
-	int is_our_pages;
+	bool is_our_pages : 1;
+	bool is_null_mapped : 1;
 	struct iov_iter iter;
 	struct iovec iov[];
 };
@@ -108,7 +109,7 @@ static int bio_uncopy_user(struct bio *bio)
 	struct bio_map_data *bmd = bio->bi_private;
 	int ret = 0;
 
-	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
+	if (!bmd->is_null_mapped) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
 		 * don't copy into a random user address space, just free
@@ -126,24 +127,12 @@ static int bio_uncopy_user(struct bio *bio)
 	return ret;
 }
 
-/**
- *	bio_copy_user_iov	-	copy user data to bio
- *	@q:		destination block queue
- *	@map_data:	pointer to the rq_map_data holding pages (if necessary)
- *	@iter:		iovec iterator
- *	@gfp_mask:	memory allocation flags
- *
- *	Prepares and returns a bio for indirect user io, bouncing data
- *	to/from kernel pages as necessary. Must be paired with
- *	call bio_uncopy_user() on io completion.
- */
-static struct bio *bio_copy_user_iov(struct request_queue *q,
-		struct rq_map_data *map_data, struct iov_iter *iter,
-		gfp_t gfp_mask)
+static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
+		struct iov_iter *iter, gfp_t gfp_mask)
 {
 	struct bio_map_data *bmd;
 	struct page *page;
-	struct bio *bio;
+	struct bio *bio, *bounce_bio;
 	int i = 0, ret;
 	int nr_pages;
 	unsigned int len = iter->count;
@@ -151,14 +140,15 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
 
 	bmd = bio_alloc_map_data(iter, gfp_mask);
 	if (!bmd)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	/*
 	 * We need to do a deep copy of the iov_iter including the iovecs.
 	 * The caller provided iov might point to an on-stack or otherwise
 	 * shortlived one.
 	 */
-	bmd->is_our_pages = map_data ? 0 : 1;
+	bmd->is_our_pages = !map_data;
+	bmd->is_null_mapped = (map_data && map_data->null_mapped);
 
 	nr_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE);
 	if (nr_pages > BIO_MAX_PAGES)
@@ -168,8 +158,7 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
 	bio = bio_kmalloc(gfp_mask, nr_pages);
 	if (!bio)
 		goto out_bmd;
-
-	ret = 0;
+	bio->bi_opf |= req_op(rq);
 
 	if (map_data) {
 		nr_pages = 1 << map_data->page_order;
@@ -186,7 +175,7 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
 		if (map_data) {
 			if (i == map_data->nr_entries * nr_pages) {
 				ret = -ENOMEM;
-				break;
+				goto cleanup;
 			}
 
 			page = map_data->pages[i / nr_pages];
@@ -194,14 +183,14 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
 
 			i++;
 		} else {
-			page = alloc_page(q->bounce_gfp | gfp_mask);
+			page = alloc_page(rq->q->bounce_gfp | gfp_mask);
 			if (!page) {
 				ret = -ENOMEM;
-				break;
+				goto cleanup;
 			}
 		}
 
-		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) {
+		if (bio_add_pc_page(rq->q, bio, page, bytes, offset) < bytes) {
 			if (!map_data)
 				__free_page(page);
 			break;
@@ -211,9 +200,6 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
 		offset = 0;
 	}
 
-	if (ret)
-		goto cleanup;
-
 	if (map_data)
 		map_data->offset += bio->bi_iter.bi_size;
 
@@ -233,41 +219,42 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
 	}
 
 	bio->bi_private = bmd;
-	if (map_data && map_data->null_mapped)
-		bio_set_flag(bio, BIO_NULL_MAPPED);
-	return bio;
+
+	bounce_bio = bio;
+	ret = blk_rq_append_bio(rq, &bounce_bio);
+	if (ret)
+		goto cleanup;
+
+	/*
+	 * We link the bounce buffer in and could have to traverse it later, so
+	 * we have to get a ref to prevent it from being freed
+	 */
+	bio_get(bounce_bio);
+	return 0;
 cleanup:
 	if (!map_data)
 		bio_free_pages(bio);
 	bio_put(bio);
 out_bmd:
 	kfree(bmd);
-	return ERR_PTR(ret);
+	return ret;
 }
 
-/**
- *	bio_map_user_iov - map user iovec into bio
- *	@q:		the struct request_queue for the bio
- *	@iter:		iovec iterator
- *	@gfp_mask:	memory allocation flags
- *
- *	Map the user space address into a bio suitable for io to a block
- *	device. Returns an error pointer in case of error.
- */
-static struct bio *bio_map_user_iov(struct request_queue *q,
-		struct iov_iter *iter, gfp_t gfp_mask)
+static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
+		gfp_t gfp_mask)
 {
-	unsigned int max_sectors = queue_max_hw_sectors(q);
-	int j;
-	struct bio *bio;
+	unsigned int max_sectors = queue_max_hw_sectors(rq->q);
+	struct bio *bio, *bounce_bio;
 	int ret;
+	int j;
 
 	if (!iov_iter_count(iter))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_PAGES));
 	if (!bio)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
+	bio->bi_opf |= req_op(rq);
 
 	while (iov_iter_count(iter)) {
 		struct page **pages;
@@ -283,7 +270,7 @@ static struct bio *bio_map_user_iov(struct request_queue *q,
 
 		npages = DIV_ROUND_UP(offs + bytes, PAGE_SIZE);
 
-		if (unlikely(offs & queue_dma_alignment(q))) {
+		if (unlikely(offs & queue_dma_alignment(rq->q))) {
 			ret = -EINVAL;
 			j = 0;
 		} else {
@@ -295,7 +282,7 @@ static struct bio *bio_map_user_iov(struct request_queue *q,
 				if (n > bytes)
 					n = bytes;
 
-				if (!bio_add_hw_page(q, bio, page, n, offs,
+				if (!bio_add_hw_page(rq->q, bio, page, n, offs,
 						     max_sectors, &same_page)) {
 					if (same_page)
 						put_page(page);
@@ -319,21 +306,31 @@ static struct bio *bio_map_user_iov(struct request_queue *q,
 			break;
 	}
 
-	bio_set_flag(bio, BIO_USER_MAPPED);
-
 	/*
-	 * subtle -- if bio_map_user_iov() ended up bouncing a bio,
-	 * it would normally disappear when its bi_end_io is run.
-	 * however, we need it for the unmap, so grab an extra
-	 * reference to it
+	 * Subtle: if we end up needing to bounce a bio, it would normally
+	 * disappear when its bi_end_io is run.  However, we need the original
+	 * bio for the unmap, so grab an extra reference to it
 	 */
 	bio_get(bio);
-	return bio;
 
+	bounce_bio = bio;
+	ret = blk_rq_append_bio(rq, &bounce_bio);
+	if (ret)
+		goto out_put_orig;
+
+	/*
+	 * We link the bounce buffer in and could have to traverse it
+	 * later, so we have to get a ref to prevent it from being freed
+	 */
+	bio_get(bounce_bio);
+	return 0;
+
+ out_put_orig:
+	bio_put(bio);
  out_unmap:
 	bio_release_pages(bio, false);
 	bio_put(bio);
-	return ERR_PTR(ret);
+	return ret;
 }
 
 /**
@@ -557,55 +554,6 @@ int blk_rq_append_bio(struct request *rq, struct bio **bio)
 }
 EXPORT_SYMBOL(blk_rq_append_bio);
 
-static int __blk_rq_unmap_user(struct bio *bio)
-{
-	int ret = 0;
-
-	if (bio) {
-		if (bio_flagged(bio, BIO_USER_MAPPED))
-			bio_unmap_user(bio);
-		else
-			ret = bio_uncopy_user(bio);
-	}
-
-	return ret;
-}
-
-static int __blk_rq_map_user_iov(struct request *rq,
-		struct rq_map_data *map_data, struct iov_iter *iter,
-		gfp_t gfp_mask, bool copy)
-{
-	struct request_queue *q = rq->q;
-	struct bio *bio, *orig_bio;
-	int ret;
-
-	if (copy)
-		bio = bio_copy_user_iov(q, map_data, iter, gfp_mask);
-	else
-		bio = bio_map_user_iov(q, iter, gfp_mask);
-
-	if (IS_ERR(bio))
-		return PTR_ERR(bio);
-
-	bio->bi_opf &= ~REQ_OP_MASK;
-	bio->bi_opf |= req_op(rq);
-
-	orig_bio = bio;
-
-	/*
-	 * We link the bounce buffer in and could have to traverse it
-	 * later so we have to get a ref to prevent it from being freed
-	 */
-	ret = blk_rq_append_bio(rq, &bio);
-	if (ret) {
-		__blk_rq_unmap_user(orig_bio);
-		return ret;
-	}
-	bio_get(bio);
-
-	return 0;
-}
-
 /**
  * blk_rq_map_user_iov - map user data to a request, for passthrough requests
  * @q:		request queue where request should be inserted
@@ -649,7 +597,10 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 
 	i = *iter;
 	do {
-		ret =__blk_rq_map_user_iov(rq, map_data, &i, gfp_mask, copy);
+		if (copy)
+			ret = bio_copy_user_iov(rq, map_data, &i, gfp_mask);
+		else
+			ret = bio_map_user_iov(rq, &i, gfp_mask);
 		if (ret)
 			goto unmap_rq;
 		if (!bio)
@@ -700,9 +651,13 @@ int blk_rq_unmap_user(struct bio *bio)
 		if (unlikely(bio_flagged(bio, BIO_BOUNCED)))
 			mapped_bio = bio->bi_private;
 
-		ret2 = __blk_rq_unmap_user(mapped_bio);
+		if (bio->bi_private) {
+			ret2 = bio_uncopy_user(mapped_bio);
 			if (ret2 && !ret)
 				ret = ret2;
+		} else {
+			bio_unmap_user(mapped_bio);
+		}
 
 		mapped_bio = bio;
 		bio = bio->bi_next;

block/blk-merge.c

@@ -11,6 +11,7 @@
 #include <trace/events/block.h>
 
 #include "blk.h"
+#include "blk-rq-qos.h"
 
 static inline bool bio_will_gap(struct request_queue *q,
 		struct request *prev_rq, struct bio *prev, struct bio *next)
@@ -579,7 +580,8 @@ int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs)
 	return ll_new_hw_segment(req, bio, nr_segs);
 }
 
-int ll_front_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs)
+static int ll_front_merge_fn(struct request *req, struct bio *bio,
+		unsigned int nr_segs)
 {
 	if (req_gap_front_merge(req, bio))
 		return 0;
@@ -809,7 +811,8 @@ static struct request *attempt_merge(struct request_queue *q,
 	return next;
 }
 
-struct request *attempt_back_merge(struct request_queue *q, struct request *rq)
+static struct request *attempt_back_merge(struct request_queue *q,
+		struct request *rq)
 {
 	struct request *next = elv_latter_request(q, rq);
 
@@ -819,7 +822,8 @@ struct request *attempt_back_merge(struct request_queue *q, struct request *rq)
 	return NULL;
 }
 
-struct request *attempt_front_merge(struct request_queue *q, struct request *rq)
+static struct request *attempt_front_merge(struct request_queue *q,
+		struct request *rq)
 {
 	struct request *prev = elv_former_request(q, rq);
 
@@ -895,3 +899,238 @@ enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
 		return ELEVATOR_FRONT_MERGE;
 	return ELEVATOR_NO_MERGE;
 }
+
+static void blk_account_io_merge_bio(struct request *req)
+{
+	if (!blk_do_io_stat(req))
+		return;
+
+	part_stat_lock();
+	part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
+	part_stat_unlock();
+}
+
+enum bio_merge_status {
+	BIO_MERGE_OK,
+	BIO_MERGE_NONE,
+	BIO_MERGE_FAILED,
+};
+
+static enum bio_merge_status bio_attempt_back_merge(struct request *req,
+		struct bio *bio, unsigned int nr_segs)
+{
+	const int ff = bio->bi_opf & REQ_FAILFAST_MASK;
+
+	if (!ll_back_merge_fn(req, bio, nr_segs))
+		return BIO_MERGE_FAILED;
+
+	trace_block_bio_backmerge(req->q, req, bio);
+	rq_qos_merge(req->q, req, bio);
+
+	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+		blk_rq_set_mixed_merge(req);
+
+	req->biotail->bi_next = bio;
+	req->biotail = bio;
+	req->__data_len += bio->bi_iter.bi_size;
+
+	bio_crypt_free_ctx(bio);
+
+	blk_account_io_merge_bio(req);
+	return BIO_MERGE_OK;
+}
+
+static enum bio_merge_status bio_attempt_front_merge(struct request *req,
+		struct bio *bio, unsigned int nr_segs)
+{
+	const int ff = bio->bi_opf & REQ_FAILFAST_MASK;
+
+	if (!ll_front_merge_fn(req, bio, nr_segs))
+		return BIO_MERGE_FAILED;
+
+	trace_block_bio_frontmerge(req->q, req, bio);
+	rq_qos_merge(req->q, req, bio);
+
+	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+		blk_rq_set_mixed_merge(req);
+
+	bio->bi_next = req->bio;
+	req->bio = bio;
+
+	req->__sector = bio->bi_iter.bi_sector;
+	req->__data_len += bio->bi_iter.bi_size;
+
+	bio_crypt_do_front_merge(req, bio);
+
+	blk_account_io_merge_bio(req);
+	return BIO_MERGE_OK;
+}
+
+static enum bio_merge_status bio_attempt_discard_merge(struct request_queue *q,
+		struct request *req, struct bio *bio)
+{
+	unsigned short segments = blk_rq_nr_discard_segments(req);
+
+	if (segments >= queue_max_discard_segments(q))
+		goto no_merge;
+	if (blk_rq_sectors(req) + bio_sectors(bio) >
+	    blk_rq_get_max_sectors(req, blk_rq_pos(req)))
+		goto no_merge;
+
+	rq_qos_merge(q, req, bio);
+
+	req->biotail->bi_next = bio;
+	req->biotail = bio;
+	req->__data_len += bio->bi_iter.bi_size;
+	req->nr_phys_segments = segments + 1;
+
+	blk_account_io_merge_bio(req);
+	return BIO_MERGE_OK;
+no_merge:
+	req_set_nomerge(q, req);
+	return BIO_MERGE_FAILED;
+}
+
+static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
+						   struct request *rq,
+						   struct bio *bio,
+						   unsigned int nr_segs,
+						   bool sched_allow_merge)
+{
+	if (!blk_rq_merge_ok(rq, bio))
+		return BIO_MERGE_NONE;
+
+	switch (blk_try_merge(rq, bio)) {
+	case ELEVATOR_BACK_MERGE:
+		if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio))
+			return bio_attempt_back_merge(rq, bio, nr_segs);
+		break;
+	case ELEVATOR_FRONT_MERGE:
+		if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio))
+			return bio_attempt_front_merge(rq, bio, nr_segs);
+		break;
+	case ELEVATOR_DISCARD_MERGE:
+		return bio_attempt_discard_merge(q, rq, bio);
+	default:
+		return BIO_MERGE_NONE;
+	}
+
+	return BIO_MERGE_FAILED;
+}
+
+/**
+ * blk_attempt_plug_merge - try to merge with %current's plugged list
+ * @q: request_queue new bio is being queued at
+ * @bio: new bio being queued
+ * @nr_segs: number of segments in @bio
+ * @same_queue_rq: pointer to &struct request that gets filled in when
+ * another request associated with @q is found on the plug list
+ * (optional, may be %NULL)
+ *
+ * Determine whether @bio being queued on @q can be merged with a request
+ * on %current's plugged list.  Returns %true if merge was successful,
+ * otherwise %false.
+ *
+ * Plugging coalesces IOs from the same issuer for the same purpose without
+ * going through @q->queue_lock.  As such it's more of an issuing mechanism
+ * than scheduling, and the request, while may have elvpriv data, is not
+ * added on the elevator at this point.  In addition, we don't have
+ * reliable access to the elevator outside queue lock.  Only check basic
+ * merging parameters without querying the elevator.
+ *
+ * Caller must ensure !blk_queue_nomerges(q) beforehand.
+ */
+bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
+		unsigned int nr_segs, struct request **same_queue_rq)
+{
+	struct blk_plug *plug;
+	struct request *rq;
+	struct list_head *plug_list;
+
+	plug = blk_mq_plug(q, bio);
+	if (!plug)
+		return false;
+
+	plug_list = &plug->mq_list;
+
+	list_for_each_entry_reverse(rq, plug_list, queuelist) {
+		if (rq->q == q && same_queue_rq) {
+			/*
+			 * Only blk-mq multiple hardware queues case checks the
+			 * rq in the same queue, there should be only one such
+			 * rq in a queue
+			 **/
+			*same_queue_rq = rq;
+		}
+
+		if (rq->q != q)
+			continue;
+
+		if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
+		    BIO_MERGE_OK)
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Iterate list of requests and see if we can merge this bio with any
+ * of them.
+ */
+bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
+			struct bio *bio, unsigned int nr_segs)
+{
+	struct request *rq;
+	int checked = 8;
+
+	list_for_each_entry_reverse(rq, list, queuelist) {
+		if (!checked--)
+			break;
+
+		switch (blk_attempt_bio_merge(q, rq, bio, nr_segs, true)) {
+		case BIO_MERGE_NONE:
+			continue;
+		case BIO_MERGE_OK:
+			return true;
+		case BIO_MERGE_FAILED:
+			return false;
+		}
+
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(blk_bio_list_merge);
+
+bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
+		unsigned int nr_segs, struct request **merged_request)
+{
+	struct request *rq;
+
+	switch (elv_merge(q, &rq, bio)) {
+	case ELEVATOR_BACK_MERGE:
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			return false;
+		if (bio_attempt_back_merge(rq, bio, nr_segs) != BIO_MERGE_OK)
+			return false;
+		*merged_request = attempt_back_merge(q, rq);
+		if (!*merged_request)
+			elv_merged_request(q, rq, ELEVATOR_BACK_MERGE);
+		return true;
+	case ELEVATOR_FRONT_MERGE:
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			return false;
+		if (bio_attempt_front_merge(rq, bio, nr_segs) != BIO_MERGE_OK)
+			return false;
+		*merged_request = attempt_front_merge(q, rq);
+		if (!*merged_request)
+			elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE);
+		return true;
+	case ELEVATOR_DISCARD_MERGE:
+		return bio_attempt_discard_merge(q, rq, bio) == BIO_MERGE_OK;
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);

block/blk-mq-debugfs.c

@@ -116,6 +116,7 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(SAME_FORCE),
 	QUEUE_FLAG_NAME(DEAD),
 	QUEUE_FLAG_NAME(INIT_DONE),
+	QUEUE_FLAG_NAME(STABLE_WRITES),
 	QUEUE_FLAG_NAME(POLL),
 	QUEUE_FLAG_NAME(WC),
 	QUEUE_FLAG_NAME(FUA),
@@ -240,7 +241,7 @@ static const char *const alloc_policy_name[] = {
 #define HCTX_FLAG_NAME(name) [ilog2(BLK_MQ_F_##name)] = #name
 static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(SHOULD_MERGE),
-	HCTX_FLAG_NAME(TAG_SHARED),
+	HCTX_FLAG_NAME(TAG_QUEUE_SHARED),
 	HCTX_FLAG_NAME(BLOCKING),
 	HCTX_FLAG_NAME(NO_SCHED),
 	HCTX_FLAG_NAME(STACKING),
@@ -452,11 +453,11 @@ static void blk_mq_debugfs_tags_show(struct seq_file *m,
 		   atomic_read(&tags->active_queues));
 
 	seq_puts(m, "\nbitmap_tags:\n");
-	sbitmap_queue_show(&tags->bitmap_tags, m);
+	sbitmap_queue_show(tags->bitmap_tags, m);
 
 	if (tags->nr_reserved_tags) {
 		seq_puts(m, "\nbreserved_tags:\n");
-		sbitmap_queue_show(&tags->breserved_tags, m);
+		sbitmap_queue_show(tags->breserved_tags, m);
 	}
 }
 
@@ -487,7 +488,7 @@ static int hctx_tags_bitmap_show(void *data, struct seq_file *m)
 	if (res)
 		goto out;
 	if (hctx->tags)
-		sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m);
+		sbitmap_bitmap_show(&hctx->tags->bitmap_tags->sb, m);
 	mutex_unlock(&q->sysfs_lock);
 
 out:
@@ -521,7 +522,7 @@ static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m)
 	if (res)
 		goto out;
 	if (hctx->sched_tags)
-		sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m);
+		sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags->sb, m);
 	mutex_unlock(&q->sysfs_lock);
 
 out:

block/blk-mq-sched.c

@@ -18,21 +18,6 @@
 #include "blk-mq-tag.h"
 #include "blk-wbt.h"
 
-void blk_mq_sched_free_hctx_data(struct request_queue *q,
-				 void (*exit)(struct blk_mq_hw_ctx *))
-{
-	struct blk_mq_hw_ctx *hctx;
-	int i;
-
-	queue_for_each_hw_ctx(q, hctx, i) {
-		if (exit && hctx->sched_data)
-			exit(hctx);
-		kfree(hctx->sched_data);
-		hctx->sched_data = NULL;
-	}
-}
-EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
-
 void blk_mq_sched_assign_ioc(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -359,104 +344,6 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	}
 }
 
-bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
-		unsigned int nr_segs, struct request **merged_request)
-{
-	struct request *rq;
-
-	switch (elv_merge(q, &rq, bio)) {
-	case ELEVATOR_BACK_MERGE:
-		if (!blk_mq_sched_allow_merge(q, rq, bio))
-			return false;
-		if (!bio_attempt_back_merge(rq, bio, nr_segs))
-			return false;
-		*merged_request = attempt_back_merge(q, rq);
-		if (!*merged_request)
-			elv_merged_request(q, rq, ELEVATOR_BACK_MERGE);
-		return true;
-	case ELEVATOR_FRONT_MERGE:
-		if (!blk_mq_sched_allow_merge(q, rq, bio))
-			return false;
-		if (!bio_attempt_front_merge(rq, bio, nr_segs))
-			return false;
-		*merged_request = attempt_front_merge(q, rq);
-		if (!*merged_request)
-			elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE);
-		return true;
-	case ELEVATOR_DISCARD_MERGE:
-		return bio_attempt_discard_merge(q, rq, bio);
-	default:
-		return false;
-	}
-}
-EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
-
-/*
- * Iterate list of requests and see if we can merge this bio with any
- * of them.
- */
-bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
-			   struct bio *bio, unsigned int nr_segs)
-{
-	struct request *rq;
-	int checked = 8;
-
-	list_for_each_entry_reverse(rq, list, queuelist) {
-		bool merged = false;
-
-		if (!checked--)
-			break;
-
-		if (!blk_rq_merge_ok(rq, bio))
-			continue;
-
-		switch (blk_try_merge(rq, bio)) {
-		case ELEVATOR_BACK_MERGE:
-			if (blk_mq_sched_allow_merge(q, rq, bio))
-				merged = bio_attempt_back_merge(rq, bio,
-						nr_segs);
-			break;
-		case ELEVATOR_FRONT_MERGE:
-			if (blk_mq_sched_allow_merge(q, rq, bio))
-				merged = bio_attempt_front_merge(rq, bio,
-						nr_segs);
-			break;
-		case ELEVATOR_DISCARD_MERGE:
-			merged = bio_attempt_discard_merge(q, rq, bio);
-			break;
-		default:
-			continue;
-		}
-
-		return merged;
-	}
-
-	return false;
-}
-EXPORT_SYMBOL_GPL(blk_mq_bio_list_merge);
-
-/*
- * Reverse check our software queue for entries that we could potentially
- * merge with. Currently includes a hand-wavy stop count of 8, to not spend
- * too much time checking for merges.
- */
-static bool blk_mq_attempt_merge(struct request_queue *q,
-				 struct blk_mq_hw_ctx *hctx,
-				 struct blk_mq_ctx *ctx, struct bio *bio,
-				 unsigned int nr_segs)
-{
-	enum hctx_type type = hctx->type;
-
-	lockdep_assert_held(&ctx->lock);
-
-	if (blk_mq_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) {
-		ctx->rq_merged++;
-		return true;
-	}
-
-	return false;
-}
-
 bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs)
 {
@@ -470,14 +357,24 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
 		return e->type->ops.bio_merge(hctx, bio, nr_segs);
 
 	type = hctx->type;
-	if ((hctx->flags & BLK_MQ_F_SHOULD_MERGE) &&
-			!list_empty_careful(&ctx->rq_lists[type])) {
+	if (!(hctx->flags & BLK_MQ_F_SHOULD_MERGE) ||
+	    list_empty_careful(&ctx->rq_lists[type]))
+		return false;
+
 	/* default per sw-queue merge */
 	spin_lock(&ctx->lock);
-		ret = blk_mq_attempt_merge(q, hctx, ctx, bio, nr_segs);
-		spin_unlock(&ctx->lock);
+	/*
+	 * Reverse check our software queue for entries that we could
+	 * potentially merge with. Currently includes a hand-wavy stop
+	 * count of 8, to not spend too much time checking for merges.
+	 */
+	if (blk_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) {
+		ctx->rq_merged++;
+		ret = true;
 	}
 
+	spin_unlock(&ctx->lock);
+
 	return ret;
 }
 
@@ -525,13 +422,7 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
-	/* flush rq in flush machinery need to be dispatched directly */
-	if (!(rq->rq_flags & RQF_FLUSH_SEQ) && op_is_flush(rq->cmd_flags)) {
-		blk_insert_flush(rq);
-		goto run;
-	}
-
-	WARN_ON(e && (rq->tag != -1));
+	WARN_ON(e && (rq->tag != BLK_MQ_NO_TAG));
 
 	if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) {
 		/*
@@ -616,9 +507,11 @@ static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
 				   struct blk_mq_hw_ctx *hctx,
 				   unsigned int hctx_idx)
 {
+	unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
+
 	if (hctx->sched_tags) {
 		blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx);
-		blk_mq_free_rq_map(hctx->sched_tags);
+		blk_mq_free_rq_map(hctx->sched_tags, flags);
 		hctx->sched_tags = NULL;
 	}
 }
@@ -628,10 +521,12 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q,
 				   unsigned int hctx_idx)
 {
 	struct blk_mq_tag_set *set = q->tag_set;
+	/* Clear HCTX_SHARED so tags are init'ed */
+	unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
 	int ret;
 
 	hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests,
-					       set->reserved_tags);
+					       set->reserved_tags, flags);
 	if (!hctx->sched_tags)
 		return -ENOMEM;
 
@@ -649,8 +544,11 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
+		/* Clear HCTX_SHARED so tags are freed */
+		unsigned int flags = hctx->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
+
 		if (hctx->sched_tags) {
-			blk_mq_free_rq_map(hctx->sched_tags);
+			blk_mq_free_rq_map(hctx->sched_tags, flags);
 			hctx->sched_tags = NULL;
 		}
 	}

block/blk-mq-sched.h

@@ -5,9 +5,6 @@
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
 
-void blk_mq_sched_free_hctx_data(struct request_queue *q,
-				 void (*exit)(struct blk_mq_hw_ctx *));
-
 void blk_mq_sched_assign_ioc(struct request *rq);
 
 void blk_mq_sched_request_inserted(struct request *rq);

block/blk-mq-sysfs.c

@@ -36,8 +36,6 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj)
 	struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
 						  kobj);
 
-	cancel_delayed_work_sync(&hctx->run_work);
-
 	if (hctx->flags & BLK_MQ_F_BLOCKING)
 		cleanup_srcu_struct(hctx->srcu);
 	blk_free_flush_queue(hctx->fq);

block/blk-mq-tag.c

@@ -23,9 +23,18 @@
  */
 bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		struct request_queue *q = hctx->queue;
+		struct blk_mq_tag_set *set = q->tag_set;
+
+		if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) &&
+		    !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
+			atomic_inc(&set->active_queues_shared_sbitmap);
+	} else {
 		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
 		    !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
 			atomic_inc(&hctx->tags->active_queues);
+	}
 
 	return true;
 }
@@ -35,9 +44,9 @@ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
  */
 void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
 {
-	sbitmap_queue_wake_all(&tags->bitmap_tags);
+	sbitmap_queue_wake_all(tags->bitmap_tags);
 	if (include_reserve)
-		sbitmap_queue_wake_all(&tags->breserved_tags);
+		sbitmap_queue_wake_all(tags->breserved_tags);
 }
 
 /*
@@ -47,11 +56,19 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
 void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 {
 	struct blk_mq_tags *tags = hctx->tags;
+	struct request_queue *q = hctx->queue;
+	struct blk_mq_tag_set *set = q->tag_set;
 
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE,
+					&q->queue_flags))
+			return;
+		atomic_dec(&set->active_queues_shared_sbitmap);
+	} else {
 		if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
 			return;
-
 		atomic_dec(&tags->active_queues);
+	}
 
 	blk_mq_tag_wakeup_all(tags, false);
 }
@@ -59,7 +76,8 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
 			    struct sbitmap_queue *bt)
 {
-	if (!data->q->elevator && !hctx_may_queue(data->hctx, bt))
+	if (!data->q->elevator && !(data->flags & BLK_MQ_REQ_RESERVED) &&
+			!hctx_may_queue(data->hctx, bt))
 		return BLK_MQ_NO_TAG;
 
 	if (data->shallow_depth)
@@ -82,10 +100,10 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 			WARN_ON_ONCE(1);
 			return BLK_MQ_NO_TAG;
 		}
-		bt = &tags->breserved_tags;
+		bt = tags->breserved_tags;
 		tag_offset = 0;
 	} else {
-		bt = &tags->bitmap_tags;
+		bt = tags->bitmap_tags;
 		tag_offset = tags->nr_reserved_tags;
 	}
 
@@ -131,9 +149,9 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 						data->ctx);
 		tags = blk_mq_tags_from_data(data);
 		if (data->flags & BLK_MQ_REQ_RESERVED)
-			bt = &tags->breserved_tags;
+			bt = tags->breserved_tags;
 		else
-			bt = &tags->bitmap_tags;
+			bt = tags->bitmap_tags;
 
 		/*
 		 * If destination hw queue is changed, fake wake up on
@@ -167,10 +185,10 @@ void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
 		const int real_tag = tag - tags->nr_reserved_tags;
 
 		BUG_ON(real_tag >= tags->nr_tags);
-		sbitmap_queue_clear(&tags->bitmap_tags, real_tag, ctx->cpu);
+		sbitmap_queue_clear(tags->bitmap_tags, real_tag, ctx->cpu);
 	} else {
 		BUG_ON(tag >= tags->nr_reserved_tags);
-		sbitmap_queue_clear(&tags->breserved_tags, tag, ctx->cpu);
+		sbitmap_queue_clear(tags->breserved_tags, tag, ctx->cpu);
 	}
 }
 
@@ -197,7 +215,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	 * We can hit rq == NULL here, because the tagging functions
 	 * test and set the bit before assigning ->rqs[].
 	 */
-	if (rq && rq->q == hctx->queue)
+	if (rq && rq->q == hctx->queue && rq->mq_hctx == hctx)
 		return iter_data->fn(hctx, rq, iter_data->data, reserved);
 	return true;
 }
@@ -298,9 +316,9 @@ static void __blk_mq_all_tag_iter(struct blk_mq_tags *tags,
 	WARN_ON_ONCE(flags & BT_TAG_ITER_RESERVED);
 
 	if (tags->nr_reserved_tags)
-		bt_tags_for_each(tags, &tags->breserved_tags, fn, priv,
+		bt_tags_for_each(tags, tags->breserved_tags, fn, priv,
 				 flags | BT_TAG_ITER_RESERVED);
-	bt_tags_for_each(tags, &tags->bitmap_tags, fn, priv, flags);
+	bt_tags_for_each(tags, tags->bitmap_tags, fn, priv, flags);
 }
 
 /**
@@ -398,9 +416,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 	/*
 	 * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and queue_hw_ctx
 	 * while the queue is frozen. So we can use q_usage_counter to avoid
-	 * racing with it. __blk_mq_update_nr_hw_queues() uses
-	 * synchronize_rcu() to ensure this function left the critical section
-	 * below.
+	 * racing with it.
 	 */
 	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return;
@@ -416,8 +432,8 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 			continue;
 
 		if (tags->nr_reserved_tags)
-			bt_for_each(hctx, &tags->breserved_tags, fn, priv, true);
-		bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false);
+			bt_for_each(hctx, tags->breserved_tags, fn, priv, true);
+		bt_for_each(hctx, tags->bitmap_tags, fn, priv, false);
 	}
 	blk_queue_exit(q);
 }
@@ -429,30 +445,64 @@ static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,
 				       node);
 }
 
-static struct blk_mq_tags *blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
+static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
 				   int node, int alloc_policy)
 {
 	unsigned int depth = tags->nr_tags - tags->nr_reserved_tags;
 	bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR;
 
-	if (bt_alloc(&tags->bitmap_tags, depth, round_robin, node))
-		goto free_tags;
-	if (bt_alloc(&tags->breserved_tags, tags->nr_reserved_tags, round_robin,
-		     node))
+	if (bt_alloc(&tags->__bitmap_tags, depth, round_robin, node))
+		return -ENOMEM;
+	if (bt_alloc(&tags->__breserved_tags, tags->nr_reserved_tags,
+		     round_robin, node))
 		goto free_bitmap_tags;
 
-	return tags;
+	tags->bitmap_tags = &tags->__bitmap_tags;
+	tags->breserved_tags = &tags->__breserved_tags;
+
+	return 0;
 free_bitmap_tags:
-	sbitmap_queue_free(&tags->bitmap_tags);
-free_tags:
-	kfree(tags);
-	return NULL;
+	sbitmap_queue_free(&tags->__bitmap_tags);
+	return -ENOMEM;
+}
+
+int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags)
+{
+	unsigned int depth = set->queue_depth - set->reserved_tags;
+	int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags);
+	bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR;
+	int i, node = set->numa_node;
+
+	if (bt_alloc(&set->__bitmap_tags, depth, round_robin, node))
+		return -ENOMEM;
+	if (bt_alloc(&set->__breserved_tags, set->reserved_tags,
+		     round_robin, node))
+		goto free_bitmap_tags;
+
+	for (i = 0; i < set->nr_hw_queues; i++) {
+		struct blk_mq_tags *tags = set->tags[i];
+
+		tags->bitmap_tags = &set->__bitmap_tags;
+		tags->breserved_tags = &set->__breserved_tags;
+	}
+
+	return 0;
+free_bitmap_tags:
+	sbitmap_queue_free(&set->__bitmap_tags);
+	return -ENOMEM;
+}
+
+void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set)
+{
+	sbitmap_queue_free(&set->__bitmap_tags);
+	sbitmap_queue_free(&set->__breserved_tags);
 }
 
 struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 				     unsigned int reserved_tags,
-				     int node, int alloc_policy)
+				     int node, unsigned int flags)
 {
+	int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(flags);
 	struct blk_mq_tags *tags;
 
 	if (total_tags > BLK_MQ_TAG_MAX) {
@@ -467,13 +517,22 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 
-	return blk_mq_init_bitmap_tags(tags, node, alloc_policy);
+	if (flags & BLK_MQ_F_TAG_HCTX_SHARED)
+		return tags;
+
+	if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) {
+		kfree(tags);
+		return NULL;
+	}
+	return tags;
 }
 
-void blk_mq_free_tags(struct blk_mq_tags *tags)
+void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags)
 {
-	sbitmap_queue_free(&tags->bitmap_tags);
-	sbitmap_queue_free(&tags->breserved_tags);
+	if (!(flags & BLK_MQ_F_TAG_HCTX_SHARED)) {
+		sbitmap_queue_free(tags->bitmap_tags);
+		sbitmap_queue_free(tags->breserved_tags);
+	}
 	kfree(tags);
 }
 
@@ -492,6 +551,8 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 	 */
 	if (tdepth > tags->nr_tags) {
 		struct blk_mq_tag_set *set = hctx->queue->tag_set;
+		/* Only sched tags can grow, so clear HCTX_SHARED flag  */
+		unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
 		struct blk_mq_tags *new;
 		bool ret;
 
@@ -506,30 +567,35 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 			return -EINVAL;
 
 		new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth,
-				tags->nr_reserved_tags);
+				tags->nr_reserved_tags, flags);
 		if (!new)
 			return -ENOMEM;
 		ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth);
 		if (ret) {
-			blk_mq_free_rq_map(new);
+			blk_mq_free_rq_map(new, flags);
 			return -ENOMEM;
 		}
 
 		blk_mq_free_rqs(set, *tagsptr, hctx->queue_num);
-		blk_mq_free_rq_map(*tagsptr);
+		blk_mq_free_rq_map(*tagsptr, flags);
 		*tagsptr = new;
 	} else {
 		/*
 		 * Don't need (or can't) update reserved tags here, they
 		 * remain static and should never need resizing.
 		 */
-		sbitmap_queue_resize(&tags->bitmap_tags,
+		sbitmap_queue_resize(tags->bitmap_tags,
 				tdepth - tags->nr_reserved_tags);
 	}
 
 	return 0;
 }
 
+void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size)
+{
+	sbitmap_queue_resize(&set->__bitmap_tags, size - set->reserved_tags);
+}
+
 /**
  * blk_mq_unique_tag() - return a tag that is unique queue-wide
  * @rq: request for which to compute a unique tag

block/blk-mq-tag.h

@@ -2,8 +2,6 @@
 #ifndef INT_BLK_MQ_TAG_H
 #define INT_BLK_MQ_TAG_H
 
-#include "blk-mq.h"
-
 /*
  * Tag address space map.
  */
@@ -13,17 +11,25 @@ struct blk_mq_tags {
 
 	atomic_t active_queues;
 
-	struct sbitmap_queue bitmap_tags;
-	struct sbitmap_queue breserved_tags;
+	struct sbitmap_queue *bitmap_tags;
+	struct sbitmap_queue *breserved_tags;
+
+	struct sbitmap_queue __bitmap_tags;
+	struct sbitmap_queue __breserved_tags;
 
 	struct request **rqs;
 	struct request **static_rqs;
 	struct list_head page_list;
 };
 
+extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
+					unsigned int reserved_tags,
+					int node, unsigned int flags);
+extern void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags);
 
-extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy);
-extern void blk_mq_free_tags(struct blk_mq_tags *tags);
+extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set,
+				      unsigned int flags);
+extern void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set);
 
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
 extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
@@ -31,6 +37,9 @@ extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
 extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_tags **tags,
 					unsigned int depth, bool can_grow);
+extern void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set,
+					     unsigned int size);
+
 extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv);
@@ -56,7 +65,7 @@ extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *);
 
 static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
-	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
+	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
 		return false;
 
 	return __blk_mq_tag_busy(hctx);
@@ -64,43 +73,12 @@ static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 
 static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 {
-	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
+	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
 		return;
 
 	__blk_mq_tag_idle(hctx);
 }
 
-/*
- * For shared tag users, we track the number of currently active users
- * and attempt to provide a fair share of the tag depth for each of them.
- */
-static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
-				  struct sbitmap_queue *bt)
-{
-	unsigned int depth, users;
-
-	if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_SHARED))
-		return true;
-	if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
-		return true;
-
-	/*
-	 * Don't try dividing an ant
-	 */
-	if (bt->sb.depth == 1)
-		return true;
-
-	users = atomic_read(&hctx->tags->active_queues);
-	if (!users)
-		return true;
-
-	/*
-	 * Allow at least some tags
-	 */
-	depth = max((bt->sb.depth + users - 1) / users, 4U);
-	return atomic_read(&hctx->nr_active) < depth;
-}
-
 static inline bool blk_mq_tag_is_reserved(struct blk_mq_tags *tags,
 					  unsigned int tag)
 {

block/blk-mq.h

@@ -53,11 +53,12 @@ struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
  */
 void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		     unsigned int hctx_idx);
-void blk_mq_free_rq_map(struct blk_mq_tags *tags);
+void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags);
 struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 					unsigned int hctx_idx,
 					unsigned int nr_tags,
-					unsigned int reserved_tags);
+					unsigned int reserved_tags,
+					unsigned int flags);
 int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		     unsigned int hctx_idx, unsigned int depth);
 
@@ -158,6 +159,11 @@ struct blk_mq_alloc_data {
 	struct blk_mq_hw_ctx *hctx;
 };
 
+static inline bool blk_mq_is_sbitmap_shared(unsigned int flags)
+{
+	return flags & BLK_MQ_F_TAG_HCTX_SHARED;
+}
+
 static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
 {
 	if (data->q->elevator)
@@ -193,6 +199,28 @@ static inline bool blk_mq_get_dispatch_budget(struct request_queue *q)
 	return true;
 }
 
+static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap);
+	else
+		atomic_inc(&hctx->nr_active);
+}
+
+static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap);
+	else
+		atomic_dec(&hctx->nr_active);
+}
+
+static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap);
+	return atomic_read(&hctx->nr_active);
+}
 static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 					   struct request *rq)
 {
@@ -201,7 +229,7 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 
 	if (rq->rq_flags & RQF_MQ_INFLIGHT) {
 		rq->rq_flags &= ~RQF_MQ_INFLIGHT;
-		atomic_dec(&hctx->nr_active);
+		__blk_mq_dec_active_requests(hctx);
 	}
 }
 
@@ -253,4 +281,46 @@ static inline struct blk_plug *blk_mq_plug(struct request_queue *q,
 	return NULL;
 }
 
+/*
+ * For shared tag users, we track the number of currently active users
+ * and attempt to provide a fair share of the tag depth for each of them.
+ */
+static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
+				  struct sbitmap_queue *bt)
+{
+	unsigned int depth, users;
+
+	if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
+		return true;
+
+	/*
+	 * Don't try dividing an ant
+	 */
+	if (bt->sb.depth == 1)
+		return true;
+
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		struct request_queue *q = hctx->queue;
+		struct blk_mq_tag_set *set = q->tag_set;
+
+		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &q->queue_flags))
+			return true;
+		users = atomic_read(&set->active_queues_shared_sbitmap);
+	} else {
+		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+			return true;
+		users = atomic_read(&hctx->tags->active_queues);
+	}
+
+	if (!users)
+		return true;
+
+	/*
+	 * Allow at least some tags
+	 */
+	depth = max((bt->sb.depth + users - 1) / users, 4U);
+	return __blk_mq_active_requests(hctx) < depth;
+}
+
+
 #endif

block/blk-settings.c

@@ -172,15 +172,13 @@ EXPORT_SYMBOL(blk_queue_max_hw_sectors);
  *
  * Description:
  *    If a driver doesn't want IOs to cross a given chunk size, it can set
- *    this limit and prevent merging across chunks. Note that the chunk size
- *    must currently be a power-of-2 in sectors. Also note that the block
- *    layer must accept a page worth of data at any offset. So if the
- *    crossing of chunks is a hard limitation in the driver, it must still be
- *    prepared to split single page bios.
+ *    this limit and prevent merging across chunks. Note that the block layer
+ *    must accept a page worth of data at any offset. So if the crossing of
+ *    chunks is a hard limitation in the driver, it must still be prepared
+ *    to split single page bios.
  **/
 void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
 {
-	BUG_ON(!is_power_of_2(chunk_sectors));
 	q->limits.chunk_sectors = chunk_sectors;
 }
 EXPORT_SYMBOL(blk_queue_chunk_sectors);
@@ -374,6 +372,19 @@ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
 }
 EXPORT_SYMBOL(blk_queue_alignment_offset);
 
+void blk_queue_update_readahead(struct request_queue *q)
+{
+	/*
+	 * For read-ahead of large files to be effective, we need to read ahead
+	 * at least twice the optimal I/O size.
+	 */
+	q->backing_dev_info->ra_pages =
+		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+	q->backing_dev_info->io_pages =
+		queue_max_sectors(q) >> (PAGE_SHIFT - 9);
+}
+EXPORT_SYMBOL_GPL(blk_queue_update_readahead);
+
 /**
  * blk_limits_io_min - set minimum request size for a device
  * @limits: the queue limits
@@ -452,6 +463,8 @@ EXPORT_SYMBOL(blk_limits_io_opt);
 void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
 {
 	blk_limits_io_opt(&q->limits, opt);
+	q->backing_dev_info->ra_pages =
+		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
 }
 EXPORT_SYMBOL(blk_queue_io_opt);
 
@@ -534,6 +547,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	t->io_min = max(t->io_min, b->io_min);
 	t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
+	t->chunk_sectors = lcm_not_zero(t->chunk_sectors, b->chunk_sectors);
 
 	/* Physical block size a multiple of the logical block size? */
 	if (t->physical_block_size & (t->logical_block_size - 1)) {
@@ -556,6 +570,13 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		ret = -1;
 	}
 
+	/* chunk_sectors a multiple of the physical block size? */
+	if ((t->chunk_sectors << 9) & (t->physical_block_size - 1)) {
+		t->chunk_sectors = 0;
+		t->misaligned = 1;
+		ret = -1;
+	}
+
 	t->raid_partial_stripes_expensive =
 		max(t->raid_partial_stripes_expensive,
 		    b->raid_partial_stripes_expensive);
@@ -594,10 +615,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			t->discard_granularity;
 	}
 
-	if (b->chunk_sectors)
-		t->chunk_sectors = min_not_zero(t->chunk_sectors,
-						b->chunk_sectors);
-
 	t->zoned = max(t->zoned, b->zoned);
 	return ret;
 }
@@ -629,8 +646,7 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 		       top, bottom);
 	}
 
-	t->backing_dev_info->io_pages =
-		t->limits.max_sectors >> (PAGE_SHIFT - 9);
+	blk_queue_update_readahead(disk->queue);
 }
 EXPORT_SYMBOL(disk_stack_limits);
 

block/blk.h

@@ -114,6 +114,11 @@ static inline bool bio_integrity_endio(struct bio *bio)
 	return true;
 }
 
+bool blk_integrity_merge_rq(struct request_queue *, struct request *,
+		struct request *);
+bool blk_integrity_merge_bio(struct request_queue *, struct request *,
+		struct bio *);
+
 static inline bool integrity_req_gap_back_merge(struct request *req,
 		struct bio *next)
 {
@@ -137,6 +142,16 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 void blk_integrity_add(struct gendisk *);
 void blk_integrity_del(struct gendisk *);
 #else /* CONFIG_BLK_DEV_INTEGRITY */
+static inline bool blk_integrity_merge_rq(struct request_queue *rq,
+		struct request *r1, struct request *r2)
+{
+	return true;
+}
+static inline bool blk_integrity_merge_bio(struct request_queue *rq,
+		struct request *r, struct bio *b)
+{
+	return true;
+}
 static inline bool integrity_req_gap_back_merge(struct request *req,
 		struct bio *next)
 {
@@ -169,14 +184,10 @@ static inline void blk_integrity_del(struct gendisk *disk)
 unsigned long blk_rq_timeout(unsigned long timeout);
 void blk_add_timer(struct request *req);
 
-bool bio_attempt_front_merge(struct request *req, struct bio *bio,
-		unsigned int nr_segs);
-bool bio_attempt_back_merge(struct request *req, struct bio *bio,
-		unsigned int nr_segs);
-bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
-		struct bio *bio);
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs, struct request **same_queue_rq);
+bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
+			struct bio *bio, unsigned int nr_segs);
 
 void blk_account_io_start(struct request *req);
 void blk_account_io_done(struct request *req, u64 now);
@@ -223,10 +234,6 @@ ssize_t part_timeout_store(struct device *, struct device_attribute *,
 void __blk_queue_split(struct bio **bio, unsigned int *nr_segs);
 int ll_back_merge_fn(struct request *req, struct bio *bio,
 		unsigned int nr_segs);
-int ll_front_merge_fn(struct request *req,  struct bio *bio,
-		unsigned int nr_segs);
-struct request *attempt_back_merge(struct request_queue *q, struct request *rq);
-struct request *attempt_front_merge(struct request_queue *q, struct request *rq);
 int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 				struct request *next);
 unsigned int blk_recalc_rq_segments(struct request *rq);
@@ -350,7 +357,7 @@ char *disk_name(struct gendisk *hd, int partno, char *buf);
 #define ADDPART_FLAG_NONE	0
 #define ADDPART_FLAG_RAID	1
 #define ADDPART_FLAG_WHOLEDISK	2
-void delete_partition(struct gendisk *disk, struct hd_struct *part);
+void delete_partition(struct hd_struct *part);
 int bdev_add_partition(struct block_device *bdev, int partno,
 		sector_t start, sector_t length);
 int bdev_del_partition(struct block_device *bdev, int partno);

block/bounce.c

@@ -267,22 +267,21 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask,
 		break;
 	}
 
-	bio_crypt_clone(bio, bio_src, gfp_mask);
+	if (bio_crypt_clone(bio, bio_src, gfp_mask) < 0)
+		goto err_put;
 
-	if (bio_integrity(bio_src)) {
-		int ret;
-
-		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
-		if (ret < 0) {
-			bio_put(bio);
-			return NULL;
-		}
-	}
+	if (bio_integrity(bio_src) &&
+	    bio_integrity_clone(bio, bio_src, gfp_mask) < 0)
+		goto err_put;
 
 	bio_clone_blkg_association(bio, bio_src);
 	blkcg_bio_issue_init(bio);
 
 	return bio;
+
+err_put:
+	bio_put(bio);
+	return NULL;
 }
 
 static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,

block/bsg-lib.c

@@ -207,7 +207,7 @@ static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req)
 
 	BUG_ON(!req->nr_phys_segments);
 
-	buf->sg_list = kzalloc(sz, GFP_KERNEL);
+	buf->sg_list = kmalloc(sz, GFP_KERNEL);
 	if (!buf->sg_list)
 		return -ENOMEM;
 	sg_init_table(buf->sg_list, req->nr_phys_segments);

block/elevator.c

@@ -191,7 +191,6 @@ static void elevator_release(struct kobject *kobj)
 void __elevator_exit(struct request_queue *q, struct elevator_queue *e)
 {
 	mutex_lock(&e->sysfs_lock);
-	if (e->type->ops.exit_sched)
 	blk_mq_exit_sched(q, e);
 	mutex_unlock(&e->sysfs_lock);
 
@@ -480,16 +479,13 @@ static struct kobj_type elv_ktype = {
 	.release	= elevator_release,
 };
 
-/*
- * elv_register_queue is called from either blk_register_queue or
- * elevator_switch, elevator switch is prevented from being happen
- * in the two paths, so it is safe to not hold q->sysfs_lock.
- */
 int elv_register_queue(struct request_queue *q, bool uevent)
 {
 	struct elevator_queue *e = q->elevator;
 	int error;
 
+	lockdep_assert_held(&q->sysfs_lock);
+
 	error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
 	if (!error) {
 		struct elv_fs_entry *attr = e->type->elevator_attrs;
@@ -508,13 +504,10 @@ int elv_register_queue(struct request_queue *q, bool uevent)
 	return error;
 }
 
-/*
- * elv_unregister_queue is called from either blk_unregister_queue or
- * elevator_switch, elevator switch is prevented from being happen
- * in the two paths, so it is safe to not hold q->sysfs_lock.
- */
 void elv_unregister_queue(struct request_queue *q)
 {
+	lockdep_assert_held(&q->sysfs_lock);
+
 	if (q) {
 		struct elevator_queue *e = q->elevator;
 
@@ -616,7 +609,7 @@ int elevator_switch_mq(struct request_queue *q,
 
 static inline bool elv_support_iosched(struct request_queue *q)
 {
-	if (!q->mq_ops ||
+	if (!queue_is_mq(q) ||
 	    (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED)))
 		return false;
 	return true;
@@ -673,7 +666,7 @@ void elevator_init_mq(struct request_queue *q)
 	if (!elv_support_iosched(q))
 		return;
 
-	WARN_ON_ONCE(test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags));
+	WARN_ON_ONCE(blk_queue_registered(q));
 
 	if (unlikely(q->elevator))
 		return;
@@ -764,7 +757,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 {
 	int ret;
 
-	if (!queue_is_mq(q) || !elv_support_iosched(q))
+	if (!elv_support_iosched(q))
 		return count;
 
 	ret = __elevator_change(q, name);

block/ioctl.c

@@ -23,7 +23,7 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 		return -EACCES;
 	if (copy_from_user(&p, upart, sizeof(struct blkpg_partition)))
 		return -EFAULT;
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		return -EINVAL;
 
 	if (p.pno <= 0)
@@ -94,7 +94,7 @@ static int blkdev_reread_part(struct block_device *bdev)
 {
 	int ret;
 
-	if (!disk_part_scan_enabled(bdev->bd_disk) || bdev != bdev->bd_contains)
+	if (!disk_part_scan_enabled(bdev->bd_disk) || bdev_is_partition(bdev))
 		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
@@ -112,8 +112,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 	uint64_t range[2];
 	uint64_t start, len;
 	struct request_queue *q = bdev_get_queue(bdev);
-	struct address_space *mapping = bdev->bd_inode->i_mapping;
-
+	int err;
 
 	if (!(mode & FMODE_WRITE))
 		return -EBADF;
@@ -134,7 +133,11 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 
 	if (start + len > i_size_read(bdev->bd_inode))
 		return -EINVAL;
-	truncate_inode_pages_range(mapping, start, start + len - 1);
+
+	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
+	if (err)
+		return err;
+
 	return blkdev_issue_discard(bdev, start >> 9, len >> 9,
 				    GFP_KERNEL, flags);
 }
@@ -143,8 +146,8 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 		unsigned long arg)
 {
 	uint64_t range[2];
-	struct address_space *mapping;
 	uint64_t start, end, len;
+	int err;
 
 	if (!(mode & FMODE_WRITE))
 		return -EBADF;
@@ -166,8 +169,9 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages */
-	mapping = bdev->bd_inode->i_mapping;
-	truncate_inode_pages_range(mapping, start, end);
+	err = truncate_bdev_range(bdev, mode, start, end);
+	if (err)
+		return err;
 
 	return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
 			BLKDEV_ZERO_NOUNMAP);
@@ -474,15 +478,14 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
 	if (get_user(n, argp))
 		return -EFAULT;
 
-	if (!(mode & FMODE_EXCL)) {
-		bdgrab(bdev);
-		if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
-			return -EBUSY;
-	}
+	if (mode & FMODE_EXCL)
+		return set_blocksize(bdev, n);
 
+	if (IS_ERR(blkdev_get_by_dev(bdev->bd_dev, mode | FMODE_EXCL, &bdev)))
+		return -EBUSY;
 	ret = set_blocksize(bdev, n);
-	if (!(mode & FMODE_EXCL))
 	blkdev_put(bdev, mode | FMODE_EXCL);
+
 	return ret;
 }
 

block/ioprio.c

@@ -69,7 +69,7 @@ int ioprio_check_cap(int ioprio)
 
 	switch (class) {
 		case IOPRIO_CLASS_RT:
-			if (!capable(CAP_SYS_ADMIN))
+			if (!capable(CAP_SYS_NICE) && !capable(CAP_SYS_ADMIN))
 				return -EPERM;
 			fallthrough;
 			/* rt has prio field too */

block/kyber-iosched.c

@@ -359,7 +359,7 @@ static unsigned int kyber_sched_tags_shift(struct request_queue *q)
 	 * All of the hardware queues have the same depth, so we can just grab
 	 * the shift of the first one.
 	 */
-	return q->queue_hw_ctx[0]->sched_tags->bitmap_tags.sb.shift;
+	return q->queue_hw_ctx[0]->sched_tags->bitmap_tags->sb.shift;
 }
 
 static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
@@ -502,7 +502,7 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 	khd->batching = 0;
 
 	hctx->sched_data = khd;
-	sbitmap_queue_min_shallow_depth(&hctx->sched_tags->bitmap_tags,
+	sbitmap_queue_min_shallow_depth(hctx->sched_tags->bitmap_tags,
 					kqd->async_depth);
 
 	return 0;
@@ -573,7 +573,7 @@ static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio,
 	bool merged;
 
 	spin_lock(&kcq->lock);
-	merged = blk_mq_bio_list_merge(hctx->queue, rq_list, bio, nr_segs);
+	merged = blk_bio_list_merge(hctx->queue, rq_list, bio, nr_segs);
 	spin_unlock(&kcq->lock);
 
 	return merged;

block/mq-deadline.c

@@ -386,6 +386,8 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	spin_lock(&dd->lock);
 	rq = __dd_dispatch_request(dd);
 	spin_unlock(&dd->lock);
+	if (rq)
+		atomic_dec(&rq->mq_hctx->elevator_queued);
 
 	return rq;
 }
@@ -533,6 +535,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		dd_insert_request(hctx, rq, at_head);
+		atomic_inc(&hctx->elevator_queued);
 	}
 	spin_unlock(&dd->lock);
 }
@@ -579,6 +582,9 @@ static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
 
+	if (!atomic_read(&hctx->elevator_queued))
+		return false;
+
 	return !list_empty_careful(&dd->dispatch) ||
 		!list_empty_careful(&dd->fifo_list[0]) ||
 		!list_empty_careful(&dd->fifo_list[1]);

block/scsi_ioctl.c

@@ -37,8 +37,6 @@ const unsigned char scsi_command_size_tbl[8] =
 };
 EXPORT_SYMBOL(scsi_command_size_tbl);
 
-#include <scsi/sg.h>
-
 static int sg_get_version(int __user *p)
 {
 	static const int sg_version_num = 30527;
@@ -847,7 +845,7 @@ EXPORT_SYMBOL(scsi_cmd_ioctl);
 
 int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd)
 {
-	if (bd && bd == bd->bd_contains)
+	if (bd && !bdev_is_partition(bd))
 		return 0;
 
 	if (capable(CAP_SYS_RAWIO))

drivers/block/amiflop.c

@@ -1670,7 +1670,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	}
 
 	if (mode & (FMODE_READ|FMODE_WRITE)) {
-		check_disk_change(bdev);
+		bdev_check_media_change(bdev);
 		if (mode & FMODE_WRITE) {
 			int wrprot;
 

drivers/block/brd.c

@@ -403,7 +403,6 @@ static struct brd_device *brd_alloc(int i)
 	disk->flags		= GENHD_FL_EXT_DEVT;
 	sprintf(disk->disk_name, "ram%d", i);
 	set_capacity(disk, rd_size * 2);
-	brd->brd_queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
 
 	/* Tell the block layer that this is not a rotational device */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, brd->brd_queue);