Merge remote-tracking branch 'jens/for-5.10/block' into dm-5.10

DM depends on these block 5.10 commits:

22ada802 block: use lcm_not_zero() when stacking chunk_sectors
07d098e6 block: allow 'chunk_sectors' to be non-power-of-2
021a2446 block: add QUEUE_FLAG_NOWAIT
6abc4946 dm: add support for REQ_NOWAIT and enable it for linear target
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

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/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;
 	}
@@ -1634,10 +1651,13 @@ 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.
 	 */
-	delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);
+	if (clamp)
+		delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);
 
 	if (use_memdelay)
 		psi_memstall_enter(&pflags);

block/blk-core.c

@@ -116,8 +116,8 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->__sector = (sector_t) -1;
 	INIT_HLIST_NODE(&rq->hash);
 	RB_CLEAR_NODE(&rq->rb_node);
-	rq->tag = -1;
-	rq->internal_tag = -1;
+	rq->tag = BLK_MQ_NO_TAG;
+	rq->internal_tag = BLK_MQ_NO_TAG;
 	rq->start_time_ns = ktime_get_ns();
 	rq->part = NULL;
 	refcount_set(&rq->ref, 1);
@@ -538,11 +538,10 @@ struct request_queue *blk_alloc_queue(int node_id)
 	if (!q->stats)
 		goto fail_stats;
 
-	q->backing_dev_info->ra_pages = VM_READAHEAD_PAGES;
-	q->backing_dev_info->io_pages = VM_READAHEAD_PAGES;
-	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
 	q->node = node_id;
 
+	atomic_set(&q->nr_active_requests_shared_sbitmap, 0);
+
 	timer_setup(&q->backing_dev_info->laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, 0);
 	timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
@@ -643,162 +642,6 @@ void blk_put_request(struct request *req)
 }
 EXPORT_SYMBOL(blk_put_request);
 
-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();
-}
-
-bool 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 false;
-
-	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 true;
-}
-
-bool 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 false;
-
-	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 true;
-}
-
-bool 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 true;
-no_merge:
-	req_set_nomerge(q, req);
-	return false;
-}
-
-/**
- * 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) {
-		bool merged = false;
-
-		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 || !blk_rq_merge_ok(rq, bio))
-			continue;
-
-		switch (blk_try_merge(rq, bio)) {
-		case ELEVATOR_BACK_MERGE:
-			merged = bio_attempt_back_merge(rq, bio, nr_segs);
-			break;
-		case ELEVATOR_FRONT_MERGE:
-			merged = bio_attempt_front_merge(rq, bio, nr_segs);
-			break;
-		case ELEVATOR_DISCARD_MERGE:
-			merged = bio_attempt_discard_merge(q, rq, bio);
-			break;
-		default:
-			break;
-		}
-
-		if (merged)
-			return true;
-	}
-
-	return false;
-}
-
 static void handle_bad_sector(struct bio *bio, sector_t maxsector)
 {
 	char b[BDEVNAME_SIZE];
@@ -971,9 +814,9 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 
 	/*
 	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
-	 * if queue is not a request based queue.
+	 * if queue does not support NOWAIT.
 	 */
-	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q))
+	if ((bio->bi_opf & REQ_NOWAIT) && !blk_queue_nowait(q))
 		goto not_supported;
 
 	if (should_fail_bio(bio))
@@ -1301,14 +1144,28 @@ EXPORT_SYMBOL(submit_bio);
  *    limits when retrying requests on other queues. Those requests need
  *    to be checked against the new queue limits again during dispatch.
  */
-static int blk_cloned_rq_check_limits(struct request_queue *q,
+static blk_status_t blk_cloned_rq_check_limits(struct request_queue *q,
 				      struct request *rq)
 {
-	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, req_op(rq))) {
+	unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq));
+
+	if (blk_rq_sectors(rq) > max_sectors) {
+		/*
+		 * SCSI device does not have a good way to return if
+		 * Write Same/Zero is actually supported. If a device rejects
+		 * a non-read/write command (discard, write same,etc.) the
+		 * low-level device driver will set the relevant queue limit to
+		 * 0 to prevent blk-lib from issuing more of the offending
+		 * operations. Commands queued prior to the queue limit being
+		 * reset need to be completed with BLK_STS_NOTSUPP to avoid I/O
+		 * errors being propagated to upper layers.
+		 */
+		if (max_sectors == 0)
+			return BLK_STS_NOTSUPP;
+
 		printk(KERN_ERR "%s: over max size limit. (%u > %u)\n",
-			__func__, blk_rq_sectors(rq),
-			blk_queue_get_max_sectors(q, req_op(rq)));
-		return -EIO;
+			__func__, blk_rq_sectors(rq), max_sectors);
+		return BLK_STS_IOERR;
 	}
 
 	/*
@@ -1321,10 +1178,10 @@ static int blk_cloned_rq_check_limits(struct request_queue *q,
 	if (rq->nr_phys_segments > queue_max_segments(q)) {
 		printk(KERN_ERR "%s: over max segments limit. (%hu > %hu)\n",
 			__func__, rq->nr_phys_segments, queue_max_segments(q));
-		return -EIO;
+		return BLK_STS_IOERR;
 	}
 
-	return 0;
+	return BLK_STS_OK;
 }
 
 /**
@@ -1334,8 +1191,11 @@ static int blk_cloned_rq_check_limits(struct request_queue *q,
  */
 blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 {
-	if (blk_cloned_rq_check_limits(q, rq))
-		return BLK_STS_IOERR;
+	blk_status_t ret;
+
+	ret = blk_cloned_rq_check_limits(q, rq);
+	if (ret != BLK_STS_OK)
+		return ret;
 
 	if (rq->rq_disk &&
 	    should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
@@ -1461,10 +1321,9 @@ void blk_account_io_start(struct request *rq)
 	part_stat_unlock();
 }
 
-unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
-		unsigned int op)
+static unsigned long __part_start_io_acct(struct hd_struct *part,
+					  unsigned int sectors, unsigned int op)
 {
-	struct hd_struct *part = &disk->part0;
 	const int sgrp = op_stat_group(op);
 	unsigned long now = READ_ONCE(jiffies);
 
@@ -1477,12 +1336,26 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 
 	return now;
 }
+
+unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part,
+				 struct bio *bio)
+{
+	*part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector);
+
+	return __part_start_io_acct(*part, bio_sectors(bio), bio_op(bio));
+}
+EXPORT_SYMBOL_GPL(part_start_io_acct);
+
+unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
+				 unsigned int op)
+{
+	return __part_start_io_acct(&disk->part0, sectors, op);
+}
 EXPORT_SYMBOL(disk_start_io_acct);
 
-void disk_end_io_acct(struct gendisk *disk, unsigned int op,
-		unsigned long start_time)
+static void __part_end_io_acct(struct hd_struct *part, unsigned int op,
+			       unsigned long start_time)
 {
-	struct hd_struct *part = &disk->part0;
 	const int sgrp = op_stat_group(op);
 	unsigned long now = READ_ONCE(jiffies);
 	unsigned long duration = now - start_time;
@@ -1493,6 +1366,20 @@ void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 	part_stat_local_dec(part, in_flight[op_is_write(op)]);
 	part_stat_unlock();
 }
+
+void part_end_io_acct(struct hd_struct *part, struct bio *bio,
+		      unsigned long start_time)
+{
+	__part_end_io_acct(part, bio_op(bio), start_time);
+	hd_struct_put(part);
+}
+EXPORT_SYMBOL_GPL(part_end_io_acct);
+
+void disk_end_io_acct(struct gendisk *disk, unsigned int op,
+		      unsigned long start_time)
+{
+	__part_end_io_acct(&disk->part0, op, start_time);
+}
 EXPORT_SYMBOL(disk_end_io_acct);
 
 /*

block/blk-integrity.c

@@ -408,7 +408,7 @@ 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 +428,7 @@ 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-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 (ret2 && !ret)
-			ret = ret2;
+		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)
@@ -895,3 +896,203 @@ 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_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;
+}
+
+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;
+}
+
+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);

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;
@@ -368,7 +353,7 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *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))
+		if (bio_attempt_back_merge(rq, bio, nr_segs) != BIO_MERGE_OK)
 			return false;
 		*merged_request = attempt_back_merge(q, rq);
 		if (!*merged_request)
@@ -377,86 +362,20 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
 	case ELEVATOR_FRONT_MERGE:
 		if (!blk_mq_sched_allow_merge(q, rq, bio))
 			return false;
-		if (!bio_attempt_front_merge(rq, bio, nr_segs))
+		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);
+		return bio_attempt_discard_merge(q, rq, bio) == BIO_MERGE_OK;
 	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 +389,24 @@ 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])) {
-		/* default per sw-queue merge */
-		spin_lock(&ctx->lock);
-		ret = blk_mq_attempt_merge(q, hctx, ctx, bio, nr_segs);
-		spin_unlock(&ctx->lock);
+	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);
+	/*
+	 * 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;
 }
 
@@ -531,7 +460,7 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 		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 +545,11 @@ 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 +559,12 @@ 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 +582,11 @@ 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-tag.c

@@ -23,9 +23,18 @@
  */
 bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
-	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);
+	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;
-
-	if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
-		return;
-
-	atomic_dec(&tags->active_queues);
+	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,
-						   int node, int alloc_policy)
+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.c

@@ -519,7 +519,7 @@ void blk_mq_free_request(struct request *rq)
 
 	ctx->rq_completed[rq_is_sync(rq)]++;
 	if (rq->rq_flags & RQF_MQ_INFLIGHT)
-		atomic_dec(&hctx->nr_active);
+		__blk_mq_dec_active_requests(hctx);
 
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->backing_dev_info);
@@ -1096,19 +1096,20 @@ static inline unsigned int queued_to_index(unsigned int queued)
 
 static bool __blk_mq_get_driver_tag(struct request *rq)
 {
-	struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
+	struct sbitmap_queue *bt = rq->mq_hctx->tags->bitmap_tags;
 	unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
 	int tag;
 
 	blk_mq_tag_busy(rq->mq_hctx);
 
 	if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) {
-		bt = &rq->mq_hctx->tags->breserved_tags;
+		bt = rq->mq_hctx->tags->breserved_tags;
 		tag_offset = 0;
+	} else {
+		if (!hctx_may_queue(rq->mq_hctx, bt))
+			return false;
 	}
 
-	if (!hctx_may_queue(rq->mq_hctx, bt))
-		return false;
 	tag = __sbitmap_queue_get(bt);
 	if (tag == BLK_MQ_NO_TAG)
 		return false;
@@ -1124,10 +1125,10 @@ static bool blk_mq_get_driver_tag(struct request *rq)
 	if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq))
 		return false;
 
-	if ((hctx->flags & BLK_MQ_F_TAG_SHARED) &&
+	if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
 			!(rq->rq_flags & RQF_MQ_INFLIGHT)) {
 		rq->rq_flags |= RQF_MQ_INFLIGHT;
-		atomic_inc(&hctx->nr_active);
+		__blk_mq_inc_active_requests(hctx);
 	}
 	hctx->tags->rqs[rq->tag] = rq;
 	return true;
@@ -1145,7 +1146,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 		struct sbitmap_queue *sbq;
 
 		list_del_init(&wait->entry);
-		sbq = &hctx->tags->bitmap_tags;
+		sbq = hctx->tags->bitmap_tags;
 		atomic_dec(&sbq->ws_active);
 	}
 	spin_unlock(&hctx->dispatch_wait_lock);
@@ -1163,12 +1164,12 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 				 struct request *rq)
 {
-	struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags;
+	struct sbitmap_queue *sbq = hctx->tags->bitmap_tags;
 	struct wait_queue_head *wq;
 	wait_queue_entry_t *wait;
 	bool ret;
 
-	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) {
+	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
 		blk_mq_sched_mark_restart_hctx(hctx);
 
 		/*
@@ -1420,7 +1421,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 		bool needs_restart;
 		/* For non-shared tags, the RESTART check will suffice */
 		bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
-                        (hctx->flags & BLK_MQ_F_TAG_SHARED);
+			(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
 		bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET;
 
 		blk_mq_release_budgets(q, nr_budgets);
@@ -2296,20 +2297,21 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 	}
 }
 
-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)
 {
 	kfree(tags->rqs);
 	tags->rqs = NULL;
 	kfree(tags->static_rqs);
 	tags->static_rqs = NULL;
 
-	blk_mq_free_tags(tags);
+	blk_mq_free_tags(tags, 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)
 {
 	struct blk_mq_tags *tags;
 	int node;
@@ -2318,8 +2320,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 
-	tags = blk_mq_init_tags(nr_tags, reserved_tags, node,
-				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
+	tags = blk_mq_init_tags(nr_tags, reserved_tags, node, flags);
 	if (!tags)
 		return NULL;
 
@@ -2327,7 +2328,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
 				 node);
 	if (!tags->rqs) {
-		blk_mq_free_tags(tags);
+		blk_mq_free_tags(tags, flags);
 		return NULL;
 	}
 
@@ -2336,7 +2337,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 					node);
 	if (!tags->static_rqs) {
 		kfree(tags->rqs);
-		blk_mq_free_tags(tags);
+		blk_mq_free_tags(tags, flags);
 		return NULL;
 	}
 
@@ -2660,6 +2661,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 		goto free_hctx;
 
 	atomic_set(&hctx->nr_active, 0);
+	atomic_set(&hctx->elevator_queued, 0);
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 	hctx->numa_node = node;
@@ -2668,7 +2670,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	spin_lock_init(&hctx->lock);
 	INIT_LIST_HEAD(&hctx->dispatch);
 	hctx->queue = q;
-	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
+	hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED;
 
 	INIT_LIST_HEAD(&hctx->hctx_list);
 
@@ -2745,10 +2747,11 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set,
 					int hctx_idx)
 {
+	unsigned int flags = set->flags;
 	int ret = 0;
 
 	set->tags[hctx_idx] = blk_mq_alloc_rq_map(set, hctx_idx,
-					set->queue_depth, set->reserved_tags);
+					set->queue_depth, set->reserved_tags, flags);
 	if (!set->tags[hctx_idx])
 		return false;
 
@@ -2757,7 +2760,7 @@ static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set,
 	if (!ret)
 		return true;
 
-	blk_mq_free_rq_map(set->tags[hctx_idx]);
+	blk_mq_free_rq_map(set->tags[hctx_idx], flags);
 	set->tags[hctx_idx] = NULL;
 	return false;
 }
@@ -2765,9 +2768,11 @@ static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set,
 static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
 					 unsigned int hctx_idx)
 {
+	unsigned int flags = set->flags;
+
 	if (set->tags && set->tags[hctx_idx]) {
 		blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx);
-		blk_mq_free_rq_map(set->tags[hctx_idx]);
+		blk_mq_free_rq_map(set->tags[hctx_idx], flags);
 		set->tags[hctx_idx] = NULL;
 	}
 }
@@ -2885,14 +2890,14 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared)
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (shared)
-			hctx->flags |= BLK_MQ_F_TAG_SHARED;
+			hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
 		else
-			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
+			hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
 	}
 }
 
-static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set,
-					bool shared)
+static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set,
+					 bool shared)
 {
 	struct request_queue *q;
 
@@ -2913,9 +2918,9 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 	list_del(&q->tag_set_list);
 	if (list_is_singular(&set->tag_list)) {
 		/* just transitioned to unshared */
-		set->flags &= ~BLK_MQ_F_TAG_SHARED;
+		set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
 		/* update existing queue */
-		blk_mq_update_tag_set_depth(set, false);
+		blk_mq_update_tag_set_shared(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
 	INIT_LIST_HEAD(&q->tag_set_list);
@@ -2930,12 +2935,12 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
 	 * Check to see if we're transitioning to shared (from 1 to 2 queues).
 	 */
 	if (!list_empty(&set->tag_list) &&
-	    !(set->flags & BLK_MQ_F_TAG_SHARED)) {
-		set->flags |= BLK_MQ_F_TAG_SHARED;
+	    !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+		set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
 		/* update existing queue */
-		blk_mq_update_tag_set_depth(set, true);
+		blk_mq_update_tag_set_shared(set, true);
 	}
-	if (set->flags & BLK_MQ_F_TAG_SHARED)
+	if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
 		queue_set_hctx_shared(q, true);
 	list_add_tail(&q->tag_set_list, &set->tag_list);
 
@@ -3256,9 +3261,11 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 {
 	int i;
 
-	for (i = 0; i < set->nr_hw_queues; i++)
+	for (i = 0; i < set->nr_hw_queues; i++) {
 		if (!__blk_mq_alloc_map_and_request(set, i))
 			goto out_unwind;
+		cond_resched();
+	}
 
 	return 0;
 
@@ -3438,11 +3445,23 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (ret)
 		goto out_free_mq_map;
 
+	if (blk_mq_is_sbitmap_shared(set->flags)) {
+		atomic_set(&set->active_queues_shared_sbitmap, 0);
+
+		if (blk_mq_init_shared_sbitmap(set, set->flags)) {
+			ret = -ENOMEM;
+			goto out_free_mq_rq_maps;
+		}
+	}
+
 	mutex_init(&set->tag_list_lock);
 	INIT_LIST_HEAD(&set->tag_list);
 
 	return 0;
 
+out_free_mq_rq_maps:
+	for (i = 0; i < set->nr_hw_queues; i++)
+		blk_mq_free_map_and_requests(set, i);
 out_free_mq_map:
 	for (i = 0; i < set->nr_maps; i++) {
 		kfree(set->map[i].mq_map);
@@ -3461,6 +3480,9 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 	for (i = 0; i < set->nr_hw_queues; i++)
 		blk_mq_free_map_and_requests(set, i);
 
+	if (blk_mq_is_sbitmap_shared(set->flags))
+		blk_mq_exit_shared_sbitmap(set);
+
 	for (j = 0; j < set->nr_maps; j++) {
 		kfree(set->map[j].mq_map);
 		set->map[j].mq_map = NULL;
@@ -3497,6 +3519,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 		if (!hctx->sched_tags) {
 			ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr,
 							false);
+			if (!ret && blk_mq_is_sbitmap_shared(set->flags))
+				blk_mq_tag_resize_shared_sbitmap(set, nr);
 		} else {
 			ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags,
 							nr, true);

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-throttle.c

@@ -15,10 +15,10 @@
 #include "blk-cgroup-rwstat.h"
 
 /* Max dispatch from a group in 1 round */
-static int throtl_grp_quantum = 8;
+#define THROTL_GRP_QUANTUM 8
 
 /* Total max dispatch from all groups in one round */
-static int throtl_quantum = 32;
+#define THROTL_QUANTUM 32
 
 /* Throttling is performed over a slice and after that slice is renewed */
 #define DFL_THROTL_SLICE_HD (HZ / 10)
@@ -150,7 +150,7 @@ struct throtl_grp {
 	/* user configured IOPS limits */
 	unsigned int iops_conf[2][LIMIT_CNT];
 
-	/* Number of bytes disptached in current slice */
+	/* Number of bytes dispatched in current slice */
 	uint64_t bytes_disp[2];
 	/* Number of bio's dispatched in current slice */
 	unsigned int io_disp[2];
@@ -852,7 +852,7 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 	/*
 	 * A bio has been dispatched. Also adjust slice_end. It might happen
 	 * that initially cgroup limit was very low resulting in high
-	 * slice_end, but later limit was bumped up and bio was dispached
+	 * slice_end, but later limit was bumped up and bio was dispatched
 	 * sooner, then we need to reduce slice_end. A high bogus slice_end
 	 * is bad because it does not allow new slice to start.
 	 */
@@ -894,13 +894,19 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 }
 
 static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
-				  unsigned long *wait)
+				  u32 iops_limit, unsigned long *wait)
 {
 	bool rw = bio_data_dir(bio);
 	unsigned int io_allowed;
 	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
 	u64 tmp;
 
+	if (iops_limit == UINT_MAX) {
+		if (wait)
+			*wait = 0;
+		return true;
+	}
+
 	jiffy_elapsed = jiffies - tg->slice_start[rw];
 
 	/* Round up to the next throttle slice, wait time must be nonzero */
@@ -913,7 +919,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	 * have been trimmed.
 	 */
 
-	tmp = (u64)tg_iops_limit(tg, rw) * jiffy_elapsed_rnd;
+	tmp = (u64)iops_limit * jiffy_elapsed_rnd;
 	do_div(tmp, HZ);
 
 	if (tmp > UINT_MAX)
@@ -936,13 +942,19 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 }
 
 static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
-				 unsigned long *wait)
+				 u64 bps_limit, unsigned long *wait)
 {
 	bool rw = bio_data_dir(bio);
 	u64 bytes_allowed, extra_bytes, tmp;
 	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
 	unsigned int bio_size = throtl_bio_data_size(bio);
 
+	if (bps_limit == U64_MAX) {
+		if (wait)
+			*wait = 0;
+		return true;
+	}
+
 	jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw];
 
 	/* Slice has just started. Consider one slice interval */
@@ -951,7 +963,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 
 	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
 
-	tmp = tg_bps_limit(tg, rw) * jiffy_elapsed_rnd;
+	tmp = bps_limit * jiffy_elapsed_rnd;
 	do_div(tmp, HZ);
 	bytes_allowed = tmp;
 
@@ -963,7 +975,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 
 	/* Calc approx time to dispatch */
 	extra_bytes = tg->bytes_disp[rw] + bio_size - bytes_allowed;
-	jiffy_wait = div64_u64(extra_bytes * HZ, tg_bps_limit(tg, rw));
+	jiffy_wait = div64_u64(extra_bytes * HZ, bps_limit);
 
 	if (!jiffy_wait)
 		jiffy_wait = 1;
@@ -987,6 +999,8 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 {
 	bool rw = bio_data_dir(bio);
 	unsigned long bps_wait = 0, iops_wait = 0, max_wait = 0;
+	u64 bps_limit = tg_bps_limit(tg, rw);
+	u32 iops_limit = tg_iops_limit(tg, rw);
 
 	/*
  	 * Currently whole state machine of group depends on first bio
@@ -998,8 +1012,7 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 	       bio != throtl_peek_queued(&tg->service_queue.queued[rw]));
 
 	/* If tg->bps = -1, then BW is unlimited */
-	if (tg_bps_limit(tg, rw) == U64_MAX &&
-	    tg_iops_limit(tg, rw) == UINT_MAX) {
+	if (bps_limit == U64_MAX && iops_limit == UINT_MAX) {
 		if (wait)
 			*wait = 0;
 		return true;
@@ -1021,8 +1034,8 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 				jiffies + tg->td->throtl_slice);
 	}
 
-	if (tg_with_in_bps_limit(tg, bio, &bps_wait) &&
-	    tg_with_in_iops_limit(tg, bio, &iops_wait)) {
+	if (tg_with_in_bps_limit(tg, bio, bps_limit, &bps_wait) &&
+	    tg_with_in_iops_limit(tg, bio, iops_limit, &iops_wait)) {
 		if (wait)
 			*wait = 0;
 		return true;
@@ -1082,7 +1095,7 @@ static void throtl_add_bio_tg(struct bio *bio, struct throtl_qnode *qn,
 	 * If @tg doesn't currently have any bios queued in the same
 	 * direction, queueing @bio can change when @tg should be
 	 * dispatched.  Mark that @tg was empty.  This is automatically
-	 * cleaered on the next tg_update_disptime().
+	 * cleared on the next tg_update_disptime().
 	 */
 	if (!sq->nr_queued[rw])
 		tg->flags |= THROTL_TG_WAS_EMPTY;
@@ -1175,8 +1188,8 @@ static int throtl_dispatch_tg(struct throtl_grp *tg)
 {
 	struct throtl_service_queue *sq = &tg->service_queue;
 	unsigned int nr_reads = 0, nr_writes = 0;
-	unsigned int max_nr_reads = throtl_grp_quantum*3/4;
-	unsigned int max_nr_writes = throtl_grp_quantum - max_nr_reads;
+	unsigned int max_nr_reads = THROTL_GRP_QUANTUM * 3 / 4;
+	unsigned int max_nr_writes = THROTL_GRP_QUANTUM - max_nr_reads;
 	struct bio *bio;
 
 	/* Try to dispatch 75% READS and 25% WRITES */
@@ -1226,7 +1239,7 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
 		if (sq->nr_queued[0] || sq->nr_queued[1])
 			tg_update_disptime(tg);
 
-		if (nr_disp >= throtl_quantum)
+		if (nr_disp >= THROTL_QUANTUM)
 			break;
 	}
 
@@ -1303,7 +1316,7 @@ static void throtl_pending_timer_fn(struct timer_list *t)
 			}
 		}
 	} else {
-		/* reached the top-level, queue issueing */
+		/* reached the top-level, queue issuing */
 		queue_work(kthrotld_workqueue, &td->dispatch_work);
 	}
 out_unlock:
@@ -1314,8 +1327,8 @@ static void throtl_pending_timer_fn(struct timer_list *t)
  * blk_throtl_dispatch_work_fn - work function for throtl_data->dispatch_work
  * @work: work item being executed
  *
- * This function is queued for execution when bio's reach the bio_lists[]
- * of throtl_data->service_queue.  Those bio's are ready and issued by this
+ * This function is queued for execution when bios reach the bio_lists[]
+ * of throtl_data->service_queue.  Those bios are ready and issued by this
  * function.
  */
 static void blk_throtl_dispatch_work_fn(struct work_struct *work)
@@ -1428,8 +1441,8 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global)
 	 * that a group's limit are dropped suddenly and we don't want to
 	 * account recently dispatched IO with new low rate.
 	 */
-	throtl_start_new_slice(tg, 0);
-	throtl_start_new_slice(tg, 1);
+	throtl_start_new_slice(tg, READ);
+	throtl_start_new_slice(tg, WRITE);
 
 	if (tg->flags & THROTL_TG_PENDING) {
 		tg_update_disptime(tg);
@@ -2230,7 +2243,7 @@ bool blk_throtl_bio(struct bio *bio)
 
 		/*
 		 * @bio passed through this layer without being throttled.
-		 * Climb up the ladder.  If we''re already at the top, it
+		 * Climb up the ladder.  If we're already at the top, it
 		 * can be executed directly.
 		 */
 		qn = &tg->qnode_on_parent[rw];

block/blk.h

@@ -29,6 +29,12 @@ struct blk_flush_queue {
 	spinlock_t		mq_flush_lock;
 };
 
+enum bio_merge_status {
+	BIO_MERGE_OK,
+	BIO_MERGE_NONE,
+	BIO_MERGE_FAILED,
+};
+
 extern struct kmem_cache *blk_requestq_cachep;
 extern struct kobj_type blk_queue_ktype;
 extern struct ida blk_queue_ida;
@@ -169,14 +175,19 @@ 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);
+enum bio_merge_status bio_attempt_front_merge(struct request *req,
+					      struct bio *bio,
+					      unsigned int nr_segs);
+enum bio_merge_status bio_attempt_back_merge(struct request *req,
+					     struct bio *bio,
+					     unsigned int nr_segs);
+enum bio_merge_status 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);
@@ -350,7 +361,7 @@ 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/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/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/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;
@@ -854,7 +852,7 @@ 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))