Merge tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block/storage for 4.21.

  Larger than usual, it was a busy round with lots of goodies queued up.
  Most notable is the removal of the old IO stack, which has been a long
  time coming. No new features for a while, everything coming in this
  week has all been fixes for things that were previously merged.

  This contains:

   - Use atomic counters instead of semaphores for mtip32xx (Arnd)

   - Cleanup of the mtip32xx request setup (Christoph)

   - Fix for circular locking dependency in loop (Jan, Tetsuo)

   - bcache (Coly, Guoju, Shenghui)
      * Optimizations for writeback caching
      * Various fixes and improvements

   - nvme (Chaitanya, Christoph, Sagi, Jay, me, Keith)
      * host and target support for NVMe over TCP
      * Error log page support
      * Support for separate read/write/poll queues
      * Much improved polling
      * discard OOM fallback
      * Tracepoint improvements

   - lightnvm (Hans, Hua, Igor, Matias, Javier)
      * Igor added packed metadata to pblk. Now drives without metadata
        per LBA can be used as well.
      * Fix from Geert on uninitialized value on chunk metadata reads.
      * Fixes from Hans and Javier to pblk recovery and write path.
      * Fix from Hua Su to fix a race condition in the pblk recovery
        code.
      * Scan optimization added to pblk recovery from Zhoujie.
      * Small geometry cleanup from me.

   - Conversion of the last few drivers that used the legacy path to
     blk-mq (me)

   - Removal of legacy IO path in SCSI (me, Christoph)

   - Removal of legacy IO stack and schedulers (me)

   - Support for much better polling, now without interrupts at all.
     blk-mq adds support for multiple queue maps, which enables us to
     have a map per type. This in turn enables nvme to have separate
     completion queues for polling, which can then be interrupt-less.
     Also means we're ready for async polled IO, which is hopefully
     coming in the next release.

   - Killing of (now) unused block exports (Christoph)

   - Unification of the blk-rq-qos and blk-wbt wait handling (Josef)

   - Support for zoned testing with null_blk (Masato)

   - sx8 conversion to per-host tag sets (Christoph)

   - IO priority improvements (Damien)

   - mq-deadline zoned fix (Damien)

   - Ref count blkcg series (Dennis)

   - Lots of blk-mq improvements and speedups (me)

   - sbitmap scalability improvements (me)

   - Make core inflight IO accounting per-cpu (Mikulas)

   - Export timeout setting in sysfs (Weiping)

   - Cleanup the direct issue path (Jianchao)

   - Export blk-wbt internals in block debugfs for easier debugging
     (Ming)

   - Lots of other fixes and improvements"

* tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block: (364 commits)
  kyber: use sbitmap add_wait_queue/list_del wait helpers
  sbitmap: add helpers for add/del wait queue handling
  block: save irq state in blkg_lookup_create()
  dm: don't reuse bio for flushes
  nvme-pci: trace SQ status on completions
  nvme-rdma: implement polling queue map
  nvme-fabrics: allow user to pass in nr_poll_queues
  nvme-fabrics: allow nvmf_connect_io_queue to poll
  nvme-core: optionally poll sync commands
  block: make request_to_qc_t public
  nvme-tcp: fix spelling mistake "attepmpt" -> "attempt"
  nvme-tcp: fix endianess annotations
  nvmet-tcp: fix endianess annotations
  nvme-pci: refactor nvme_poll_irqdisable to make sparse happy
  nvme-pci: only set nr_maps to 2 if poll queues are supported
  nvmet: use a macro for default error location
  nvmet: fix comparison of a u16 with -1
  blk-mq: enable IO poll if .nr_queues of type poll > 0
  blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()
  blk-mq: skip zero-queue maps in blk_mq_map_swqueue
  ...

Documentation/ABI/testing/sysfs-block

@@ -244,7 +244,7 @@ Description:
 
 What:		/sys/block/<disk>/queue/zoned
 Date:		September 2016
-Contact:	Damien Le Moal <damien.lemoal@hgst.com>
+Contact:	Damien Le Moal <damien.lemoal@wdc.com>
 Description:
 		zoned indicates if the device is a zoned block device
 		and the zone model of the device if it is indeed zoned.
@@ -259,6 +259,14 @@ Description:
 		zone commands, they will be treated as regular block
 		devices and zoned will report "none".
 
+What:		/sys/block/<disk>/queue/nr_zones
+Date:		November 2018
+Contact:	Damien Le Moal <damien.lemoal@wdc.com>
+Description:
+		nr_zones indicates the total number of zones of a zoned block
+		device ("host-aware" or "host-managed" zone model). For regular
+		block devices, the value is always 0.
+
 What:		/sys/block/<disk>/queue/chunk_sectors
 Date:		September 2016
 Contact:	Hannes Reinecke <hare@suse.com>
@@ -268,6 +276,6 @@ Description:
 		indicates the size in 512B sectors of the RAID volume
 		stripe segment. For a zoned block device, either
 		host-aware or host-managed, chunk_sectors indicates the
-		size of 512B sectors of the zones of the device, with
+		size in 512B sectors of the zones of the device, with
 		the eventual exception of the last zone of the device
 		which may be smaller.

Documentation/admin-guide/cgroup-v2.rst

@@ -1879,8 +1879,10 @@ following two functions.
 
   wbc_init_bio(@wbc, @bio)
 	Should be called for each bio carrying writeback data and
-	associates the bio with the inode's owner cgroup.  Can be
-	called anytime between bio allocation and submission.
+	associates the bio with the inode's owner cgroup and the
+	corresponding request queue.  This must be called after
+	a queue (device) has been associated with the bio and
+	before submission.
 
   wbc_account_io(@wbc, @page, @bytes)
 	Should be called for each data segment being written out.
@@ -1899,7 +1901,7 @@ the configuration, the bio may be executed at a lower priority and if
 the writeback session is holding shared resources, e.g. a journal
 entry, may lead to priority inversion.  There is no one easy solution
 for the problem.  Filesystems can try to work around specific problem
-cases by skipping wbc_init_bio() or using bio_associate_blkcg()
+cases by skipping wbc_init_bio() and using bio_associate_blkg()
 directly.
 
 

Documentation/block/biodoc.txt

@@ -65,7 +65,6 @@ Description of Contents:
     3.2.3 I/O completion
     3.2.4 Implications for drivers that do not interpret bios (don't handle
  	  multiple segments)
-    3.2.5 Request command tagging
   3.3 I/O submission
 4. The I/O scheduler
 5. Scalability related changes
@@ -708,93 +707,6 @@ is crossed on completion of a transfer. (The end*request* functions should
 be used if only if the request has come down from block/bio path, not for
 direct access requests which only specify rq->buffer without a valid rq->bio)
 
-3.2.5 Generic request command tagging
-
-3.2.5.1 Tag helpers
-
-Block now offers some simple generic functionality to help support command
-queueing (typically known as tagged command queueing), ie manage more than
-one outstanding command on a queue at any given time.
-
-	blk_queue_init_tags(struct request_queue *q, int depth)
-
-	Initialize internal command tagging structures for a maximum
-	depth of 'depth'.
-
-	blk_queue_free_tags((struct request_queue *q)
-
-	Teardown tag info associated with the queue. This will be done
-	automatically by block if blk_queue_cleanup() is called on a queue
-	that is using tagging.
-
-The above are initialization and exit management, the main helpers during
-normal operations are:
-
-	blk_queue_start_tag(struct request_queue *q, struct request *rq)
-
-	Start tagged operation for this request. A free tag number between
-	0 and 'depth' is assigned to the request (rq->tag holds this number),
-	and 'rq' is added to the internal tag management. If the maximum depth
-	for this queue is already achieved (or if the tag wasn't started for
-	some other reason), 1 is returned. Otherwise 0 is returned.
-
-	blk_queue_end_tag(struct request_queue *q, struct request *rq)
-
-	End tagged operation on this request. 'rq' is removed from the internal
-	book keeping structures.
-
-To minimize struct request and queue overhead, the tag helpers utilize some
-of the same request members that are used for normal request queue management.
-This means that a request cannot both be an active tag and be on the queue
-list at the same time. blk_queue_start_tag() will remove the request, but
-the driver must remember to call blk_queue_end_tag() before signalling
-completion of the request to the block layer. This means ending tag
-operations before calling end_that_request_last()! For an example of a user
-of these helpers, see the IDE tagged command queueing support.
-
-3.2.5.2 Tag info
-
-Some block functions exist to query current tag status or to go from a
-tag number to the associated request. These are, in no particular order:
-
-	blk_queue_tagged(q)
-
-	Returns 1 if the queue 'q' is using tagging, 0 if not.
-
-	blk_queue_tag_request(q, tag)
-
-	Returns a pointer to the request associated with tag 'tag'.
-
-	blk_queue_tag_depth(q)
-	
-	Return current queue depth.
-
-	blk_queue_tag_queue(q)
-
-	Returns 1 if the queue can accept a new queued command, 0 if we are
-	at the maximum depth already.
-
-	blk_queue_rq_tagged(rq)
-
-	Returns 1 if the request 'rq' is tagged.
-
-3.2.5.2 Internal structure
-
-Internally, block manages tags in the blk_queue_tag structure:
-
-	struct blk_queue_tag {
-		struct request **tag_index;	/* array or pointers to rq */
-		unsigned long *tag_map;		/* bitmap of free tags */
-		struct list_head busy_list;	/* fifo list of busy tags */
-		int busy;			/* queue depth */
-		int max_depth;			/* max queue depth */
-	};
-
-Most of the above is simple and straight forward, however busy_list may need
-a bit of explaining. Normally we don't care too much about request ordering,
-but in the event of any barrier requests in the tag queue we need to ensure
-that requests are restarted in the order they were queue.
-
 3.3 I/O Submission
 
 The routine submit_bio() is used to submit a single io. Higher level i/o

Documentation/block/queue-sysfs.txt

@@ -64,7 +64,7 @@ guess, the kernel will put the process issuing IO to sleep for an amount
 of time, before entering a classic poll loop. This mode might be a
 little slower than pure classic polling, but it will be more efficient.
 If set to a value larger than 0, the kernel will put the process issuing
-IO to sleep for this amont of microseconds before entering classic
+IO to sleep for this amount of microseconds before entering classic
 polling.
 
 iostats (RW)
@@ -194,4 +194,31 @@ blk-throttle makes decision based on the samplings. Lower time means cgroups
 have more smooth throughput, but higher CPU overhead. This exists only when
 CONFIG_BLK_DEV_THROTTLING_LOW is enabled.
 
+zoned (RO)
+----------
+This indicates if the device is a zoned block device and the zone model of the
+device if it is indeed zoned. The possible values indicated by zoned are
+"none" for regular block devices and "host-aware" or "host-managed" for zoned
+block devices. The characteristics of host-aware and host-managed zoned block
+devices are described in the ZBC (Zoned Block Commands) and ZAC
+(Zoned Device ATA Command Set) standards. These standards also define the
+"drive-managed" zone model. However, since drive-managed zoned block devices
+do not support zone commands, they will be treated as regular block devices
+and zoned will report "none".
+
+nr_zones (RO)
+-------------
+For zoned block devices (zoned attribute indicating "host-managed" or
+"host-aware"), this indicates the total number of zones of the device.
+This is always 0 for regular block devices.
+
+chunk_sectors (RO)
+------------------
+This has different meaning depending on the type of the block device.
+For a RAID device (dm-raid), chunk_sectors indicates the size in 512B sectors
+of the RAID volume stripe segment. For a zoned block device, either host-aware
+or host-managed, chunk_sectors indicates the size in 512B sectors of the zones
+of the device, with the eventual exception of the last zone of the device which
+may be smaller.
+
 Jens Axboe <jens.axboe@oracle.com>, February 2009

Documentation/scsi/scsi-parameters.txt

@@ -97,11 +97,6 @@ parameters may be changed at runtime by the command
 			allowing boot to proceed.  none ignores them, expecting
 			user space to do the scan.
 
-	scsi_mod.use_blk_mq=
-			[SCSI] use blk-mq I/O path by default
-			See SCSI_MQ_DEFAULT in drivers/scsi/Kconfig.
-			Format: <y/n>
-
 	sim710=		[SCSI,HW]
 			See header of drivers/scsi/sim710.c.
 

block/Kconfig

@@ -155,12 +155,6 @@ config BLK_CGROUP_IOLATENCY
 
 	Note, this is an experimental interface and could be changed someday.
 
-config BLK_WBT_SQ
-	bool "Single queue writeback throttling"
-	depends on BLK_WBT
-	---help---
-	Enable writeback throttling by default on legacy single queue devices
-
 config BLK_WBT_MQ
 	bool "Multiqueue writeback throttling"
 	default y

block/Kconfig.iosched

@@ -3,67 +3,6 @@ if BLOCK
 
 menu "IO Schedulers"
 
-config IOSCHED_NOOP
-	bool
-	default y
-	---help---
-	  The no-op I/O scheduler is a minimal scheduler that does basic merging
-	  and sorting. Its main uses include non-disk based block devices like
-	  memory devices, and specialised software or hardware environments
-	  that do their own scheduling and require only minimal assistance from
-	  the kernel.
-
-config IOSCHED_DEADLINE
-	tristate "Deadline I/O scheduler"
-	default y
-	---help---
-	  The deadline I/O scheduler is simple and compact. It will provide
-	  CSCAN service with FIFO expiration of requests, switching to
-	  a new point in the service tree and doing a batch of IO from there
-	  in case of expiry.
-
-config IOSCHED_CFQ
-	tristate "CFQ I/O scheduler"
-	default y
-	---help---
-	  The CFQ I/O scheduler tries to distribute bandwidth equally
-	  among all processes in the system. It should provide a fair
-	  and low latency working environment, suitable for both desktop
-	  and server systems.
-
-	  This is the default I/O scheduler.
-
-config CFQ_GROUP_IOSCHED
-	bool "CFQ Group Scheduling support"
-	depends on IOSCHED_CFQ && BLK_CGROUP
-	---help---
-	  Enable group IO scheduling in CFQ.
-
-choice
-
-	prompt "Default I/O scheduler"
-	default DEFAULT_CFQ
-	help
-	  Select the I/O scheduler which will be used by default for all
-	  block devices.
-
-	config DEFAULT_DEADLINE
-		bool "Deadline" if IOSCHED_DEADLINE=y
-
-	config DEFAULT_CFQ
-		bool "CFQ" if IOSCHED_CFQ=y
-
-	config DEFAULT_NOOP
-		bool "No-op"
-
-endchoice
-
-config DEFAULT_IOSCHED
-	string
-	default "deadline" if DEFAULT_DEADLINE
-	default "cfq" if DEFAULT_CFQ
-	default "noop" if DEFAULT_NOOP
-
 config MQ_IOSCHED_DEADLINE
 	tristate "MQ deadline I/O scheduler"
 	default y

block/Makefile

@@ -3,7 +3,7 @@
 # Makefile for the kernel block layer
 #
 
-obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
+obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
@@ -18,9 +18,6 @@ obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_BLK_CGROUP_IOLATENCY)	+= blk-iolatency.o
-obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
-obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
-obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 obj-$(CONFIG_MQ_IOSCHED_DEADLINE)	+= mq-deadline.o
 obj-$(CONFIG_MQ_IOSCHED_KYBER)	+= kyber-iosched.o
 bfq-y				:= bfq-iosched.o bfq-wf2q.o bfq-cgroup.o

block/bfq-cgroup.c

@@ -334,7 +334,7 @@ static void bfqg_stats_xfer_dead(struct bfq_group *bfqg)
 
 	parent = bfqg_parent(bfqg);
 
-	lockdep_assert_held(bfqg_to_blkg(bfqg)->q->queue_lock);
+	lockdep_assert_held(&bfqg_to_blkg(bfqg)->q->queue_lock);
 
 	if (unlikely(!parent))
 		return;
@@ -642,7 +642,7 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
 	uint64_t serial_nr;
 
 	rcu_read_lock();
-	serial_nr = bio_blkcg(bio)->css.serial_nr;
+	serial_nr = __bio_blkcg(bio)->css.serial_nr;
 
 	/*
 	 * Check whether blkcg has changed.  The condition may trigger
@@ -651,7 +651,7 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
 	if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr))
 		goto out;
 
-	bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
+	bfqg = __bfq_bic_change_cgroup(bfqd, bic, __bio_blkcg(bio));
 	/*
 	 * Update blkg_path for bfq_log_* functions. We cache this
 	 * path, and update it here, for the following

block/bfq-iosched.c

@@ -399,9 +399,9 @@ static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
 		unsigned long flags;
 		struct bfq_io_cq *icq;
 
-		spin_lock_irqsave(q->queue_lock, flags);
+		spin_lock_irqsave(&q->queue_lock, flags);
 		icq = icq_to_bic(ioc_lookup_icq(ioc, q));
-		spin_unlock_irqrestore(q->queue_lock, flags);
+		spin_unlock_irqrestore(&q->queue_lock, flags);
 
 		return icq;
 	}
@@ -4066,7 +4066,7 @@ static void bfq_update_dispatch_stats(struct request_queue *q,
 	 * In addition, the following queue lock guarantees that
 	 * bfqq_group(bfqq) exists as well.
 	 */
-	spin_lock_irq(q->queue_lock);
+	spin_lock_irq(&q->queue_lock);
 	if (idle_timer_disabled)
 		/*
 		 * Since the idle timer has been disabled,
@@ -4085,7 +4085,7 @@ static void bfq_update_dispatch_stats(struct request_queue *q,
 		bfqg_stats_set_start_empty_time(bfqg);
 		bfqg_stats_update_io_remove(bfqg, rq->cmd_flags);
 	}
-	spin_unlock_irq(q->queue_lock);
+	spin_unlock_irq(&q->queue_lock);
 }
 #else
 static inline void bfq_update_dispatch_stats(struct request_queue *q,
@@ -4416,7 +4416,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
 
 	rcu_read_lock();
 
-	bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio));
+	bfqg = bfq_find_set_group(bfqd, __bio_blkcg(bio));
 	if (!bfqg) {
 		bfqq = &bfqd->oom_bfqq;
 		goto out;
@@ -4669,11 +4669,11 @@ static void bfq_update_insert_stats(struct request_queue *q,
 	 * In addition, the following queue lock guarantees that
 	 * bfqq_group(bfqq) exists as well.
 	 */
-	spin_lock_irq(q->queue_lock);
+	spin_lock_irq(&q->queue_lock);
 	bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, cmd_flags);
 	if (idle_timer_disabled)
 		bfqg_stats_update_idle_time(bfqq_group(bfqq));
-	spin_unlock_irq(q->queue_lock);
+	spin_unlock_irq(&q->queue_lock);
 }
 #else
 static inline void bfq_update_insert_stats(struct request_queue *q,
@@ -5414,9 +5414,9 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	}
 	eq->elevator_data = bfqd;
 
-	spin_lock_irq(q->queue_lock);
+	spin_lock_irq(&q->queue_lock);
 	q->elevator = eq;
-	spin_unlock_irq(q->queue_lock);
+	spin_unlock_irq(&q->queue_lock);
 
 	/*
 	 * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
@@ -5756,7 +5756,7 @@ static struct elv_fs_entry bfq_attrs[] = {
 };
 
 static struct elevator_type iosched_bfq_mq = {
-	.ops.mq = {
+	.ops = {
 		.limit_depth		= bfq_limit_depth,
 		.prepare_request	= bfq_prepare_request,
 		.requeue_request        = bfq_finish_requeue_request,
@@ -5777,7 +5777,6 @@ static struct elevator_type iosched_bfq_mq = {
 		.exit_sched		= bfq_exit_queue,
 	},
 
-	.uses_mq =		true,
 	.icq_size =		sizeof(struct bfq_io_cq),
 	.icq_align =		__alignof__(struct bfq_io_cq),
 	.elevator_attrs =	bfq_attrs,

block/bio-integrity.c

@@ -390,7 +390,6 @@ void bio_integrity_advance(struct bio *bio, unsigned int bytes_done)
 	bip->bip_iter.bi_sector += bytes_done >> 9;
 	bvec_iter_advance(bip->bip_vec, &bip->bip_iter, bytes);
 }
-EXPORT_SYMBOL(bio_integrity_advance);
 
 /**
  * bio_integrity_trim - Trim integrity vector
@@ -460,7 +459,6 @@ void bioset_integrity_free(struct bio_set *bs)
 	mempool_exit(&bs->bio_integrity_pool);
 	mempool_exit(&bs->bvec_integrity_pool);
 }
-EXPORT_SYMBOL(bioset_integrity_free);
 
 void __init bio_integrity_init(void)
 {

block/bio.c

@@ -244,7 +244,7 @@ struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx,
 
 void bio_uninit(struct bio *bio)
 {
-	bio_disassociate_task(bio);
+	bio_disassociate_blkg(bio);
 }
 EXPORT_SYMBOL(bio_uninit);
 
@@ -571,14 +571,13 @@ void bio_put(struct bio *bio)
 }
 EXPORT_SYMBOL(bio_put);
 
-inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
+int bio_phys_segments(struct request_queue *q, struct bio *bio)
 {
 	if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
 		blk_recount_segments(q, bio);
 
 	return bio->bi_phys_segments;
 }
-EXPORT_SYMBOL(bio_phys_segments);
 
 /**
  * 	__bio_clone_fast - clone a bio that shares the original bio's biovec
@@ -610,7 +609,8 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	bio->bi_iter = bio_src->bi_iter;
 	bio->bi_io_vec = bio_src->bi_io_vec;
 
-	bio_clone_blkcg_association(bio, bio_src);
+	bio_clone_blkg_association(bio, bio_src);
+	blkcg_bio_issue_init(bio);
 }
 EXPORT_SYMBOL(__bio_clone_fast);
 
@@ -901,7 +901,6 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
 
 static void submit_bio_wait_endio(struct bio *bio)
 {
@@ -1592,7 +1591,6 @@ void bio_set_pages_dirty(struct bio *bio)
 			set_page_dirty_lock(bvec->bv_page);
 	}
 }
-EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
 
 static void bio_release_pages(struct bio *bio)
 {
@@ -1662,17 +1660,33 @@ void bio_check_pages_dirty(struct bio *bio)
 	spin_unlock_irqrestore(&bio_dirty_lock, flags);
 	schedule_work(&bio_dirty_work);
 }
-EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
+
+void update_io_ticks(struct hd_struct *part, unsigned long now)
+{
+	unsigned long stamp;
+again:
+	stamp = READ_ONCE(part->stamp);
+	if (unlikely(stamp != now)) {
+		if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) {
+			__part_stat_add(part, io_ticks, 1);
+		}
+	}
+	if (part->partno) {
+		part = &part_to_disk(part)->part0;
+		goto again;
+	}
+}
 
 void generic_start_io_acct(struct request_queue *q, int op,
 			   unsigned long sectors, struct hd_struct *part)
 {
 	const int sgrp = op_stat_group(op);
-	int cpu = part_stat_lock();
 
-	part_round_stats(q, cpu, part);
-	part_stat_inc(cpu, part, ios[sgrp]);
-	part_stat_add(cpu, part, sectors[sgrp], sectors);
+	part_stat_lock();
+
+	update_io_ticks(part, jiffies);
+	part_stat_inc(part, ios[sgrp]);
+	part_stat_add(part, sectors[sgrp], sectors);
 	part_inc_in_flight(q, part, op_is_write(op));
 
 	part_stat_unlock();
@@ -1682,12 +1696,15 @@ EXPORT_SYMBOL(generic_start_io_acct);
 void generic_end_io_acct(struct request_queue *q, int req_op,
 			 struct hd_struct *part, unsigned long start_time)
 {
-	unsigned long duration = jiffies - start_time;
+	unsigned long now = jiffies;
+	unsigned long duration = now - start_time;
 	const int sgrp = op_stat_group(req_op);
-	int cpu = part_stat_lock();
 
-	part_stat_add(cpu, part, nsecs[sgrp], jiffies_to_nsecs(duration));
-	part_round_stats(q, cpu, part);
+	part_stat_lock();
+
+	update_io_ticks(part, now);
+	part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration));
+	part_stat_add(part, time_in_queue, duration);
 	part_dec_in_flight(q, part, op_is_write(req_op));
 
 	part_stat_unlock();
@@ -1957,102 +1974,133 @@ EXPORT_SYMBOL(bioset_init_from_src);
 
 #ifdef CONFIG_BLK_CGROUP
 
-#ifdef CONFIG_MEMCG
 /**
- * bio_associate_blkcg_from_page - associate a bio with the page's blkcg
+ * bio_disassociate_blkg - puts back the blkg reference if associated
  * @bio: target bio
- * @page: the page to lookup the blkcg from
  *
- * Associate @bio with the blkcg from @page's owning memcg.  This works like
- * every other associate function wrt references.
+ * Helper to disassociate the blkg from @bio if a blkg is associated.
  */
-int bio_associate_blkcg_from_page(struct bio *bio, struct page *page)
+void bio_disassociate_blkg(struct bio *bio)
 {
-	struct cgroup_subsys_state *blkcg_css;
-
-	if (unlikely(bio->bi_css))
-		return -EBUSY;
-	if (!page->mem_cgroup)
-		return 0;
-	blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup,
-				     &io_cgrp_subsys);
-	bio->bi_css = blkcg_css;
-	return 0;
+	if (bio->bi_blkg) {
+		blkg_put(bio->bi_blkg);
+		bio->bi_blkg = NULL;
+	}
 }
-#endif /* CONFIG_MEMCG */
+EXPORT_SYMBOL_GPL(bio_disassociate_blkg);
 
 /**
- * bio_associate_blkcg - associate a bio with the specified blkcg
+ * __bio_associate_blkg - associate a bio with the a blkg
  * @bio: target bio
- * @blkcg_css: css of the blkcg to associate
+ * @blkg: the blkg to associate
  *
- * Associate @bio with the blkcg specified by @blkcg_css.  Block layer will
- * treat @bio as if it were issued by a task which belongs to the blkcg.
+ * This tries to associate @bio with the specified @blkg.  Association failure
+ * is handled by walking up the blkg tree.  Therefore, the blkg associated can
+ * be anything between @blkg and the root_blkg.  This situation only happens
+ * when a cgroup is dying and then the remaining bios will spill to the closest
+ * alive blkg.
  *
- * This function takes an extra reference of @blkcg_css which will be put
- * when @bio is released.  The caller must own @bio and is responsible for
- * synchronizing calls to this function.
+ * A reference will be taken on the @blkg and will be released when @bio is
+ * freed.
  */
-int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
+static void __bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
 {
-	if (unlikely(bio->bi_css))
-		return -EBUSY;
-	css_get(blkcg_css);
-	bio->bi_css = blkcg_css;
-	return 0;
+	bio_disassociate_blkg(bio);
+
+	bio->bi_blkg = blkg_tryget_closest(blkg);
 }
-EXPORT_SYMBOL_GPL(bio_associate_blkcg);
 
 /**
- * bio_associate_blkg - associate a bio with the specified blkg
+ * bio_associate_blkg_from_css - associate a bio with a specified css
  * @bio: target bio
- * @blkg: the blkg to associate
+ * @css: target css
  *
- * Associate @bio with the blkg specified by @blkg.  This is the queue specific
- * blkcg information associated with the @bio, a reference will be taken on the
- * @blkg and will be freed when the bio is freed.
+ * Associate @bio with the blkg found by combining the css's blkg and the
+ * request_queue of the @bio.  This falls back to the queue's root_blkg if
+ * the association fails with the css.
  */
-int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
+void bio_associate_blkg_from_css(struct bio *bio,
+				 struct cgroup_subsys_state *css)
 {
-	if (unlikely(bio->bi_blkg))
-		return -EBUSY;
-	if (!blkg_try_get(blkg))
-		return -ENODEV;
-	bio->bi_blkg = blkg;
-	return 0;
+	struct request_queue *q = bio->bi_disk->queue;
+	struct blkcg_gq *blkg;
+
+	rcu_read_lock();
+
+	if (!css || !css->parent)
+		blkg = q->root_blkg;
+	else
+		blkg = blkg_lookup_create(css_to_blkcg(css), q);
+
+	__bio_associate_blkg(bio, blkg);
+
+	rcu_read_unlock();
 }
+EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css);
 
+#ifdef CONFIG_MEMCG
 /**
- * bio_disassociate_task - undo bio_associate_current()
+ * bio_associate_blkg_from_page - associate a bio with the page's blkg
  * @bio: target bio
+ * @page: the page to lookup the blkcg from
+ *
+ * Associate @bio with the blkg from @page's owning memcg and the respective
+ * request_queue.  If cgroup_e_css returns %NULL, fall back to the queue's
+ * root_blkg.
  */
-void bio_disassociate_task(struct bio *bio)
+void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
 {
-	if (bio->bi_ioc) {
-		put_io_context(bio->bi_ioc);
-		bio->bi_ioc = NULL;
-	}
-	if (bio->bi_css) {
-		css_put(bio->bi_css);
-		bio->bi_css = NULL;
-	}
-	if (bio->bi_blkg) {
-		blkg_put(bio->bi_blkg);
-		bio->bi_blkg = NULL;
-	}
+	struct cgroup_subsys_state *css;
+
+	if (!page->mem_cgroup)
+		return;
+
+	rcu_read_lock();
+
+	css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys);
+	bio_associate_blkg_from_css(bio, css);
+
+	rcu_read_unlock();
+}
+#endif /* CONFIG_MEMCG */
+
+/**
+ * bio_associate_blkg - associate a bio with a blkg
+ * @bio: target bio
+ *
+ * Associate @bio with the blkg found from the bio's css and request_queue.
+ * If one is not found, bio_lookup_blkg() creates the blkg.  If a blkg is
+ * already associated, the css is reused and association redone as the
+ * request_queue may have changed.
+ */
+void bio_associate_blkg(struct bio *bio)
+{
+	struct cgroup_subsys_state *css;
+
+	rcu_read_lock();
+
+	if (bio->bi_blkg)
+		css = &bio_blkcg(bio)->css;
+	else
+		css = blkcg_css();
+
+	bio_associate_blkg_from_css(bio, css);
+
+	rcu_read_unlock();
 }
+EXPORT_SYMBOL_GPL(bio_associate_blkg);
 
 /**
- * bio_clone_blkcg_association - clone blkcg association from src to dst bio
+ * bio_clone_blkg_association - clone blkg association from src to dst bio
  * @dst: destination bio
  * @src: source bio
  */
-void bio_clone_blkcg_association(struct bio *dst, struct bio *src)
+void bio_clone_blkg_association(struct bio *dst, struct bio *src)
 {
-	if (src->bi_css)
-		WARN_ON(bio_associate_blkcg(dst, src->bi_css));
+	if (src->bi_blkg)
+		__bio_associate_blkg(dst, src->bi_blkg);
 }
-EXPORT_SYMBOL_GPL(bio_clone_blkcg_association);
+EXPORT_SYMBOL_GPL(bio_clone_blkg_association);
 #endif /* CONFIG_BLK_CGROUP */
 
 static void __init biovec_init_slabs(void)

block/blk-exec.c

@@ -48,8 +48,6 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 			   struct request *rq, int at_head,
 			   rq_end_io_fn *done)
 {
-	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
-
 	WARN_ON(irqs_disabled());
 	WARN_ON(!blk_rq_is_passthrough(rq));
 
@@ -60,23 +58,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * don't check dying flag for MQ because the request won't
 	 * be reused after dying flag is set
 	 */
-	if (q->mq_ops) {
 	blk_mq_sched_insert_request(rq, at_head, true, false);
-		return;
-	}
-
-	spin_lock_irq(q->queue_lock);
-
-	if (unlikely(blk_queue_dying(q))) {
-		rq->rq_flags |= RQF_QUIET;
-		__blk_end_request_all(rq, BLK_STS_IOERR);
-		spin_unlock_irq(q->queue_lock);
-		return;
-	}
-
-	__elv_add_request(q, rq, where);
-	__blk_run_queue(q);
-	spin_unlock_irq(q->queue_lock);
 }
 EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
 

block/blk-ioc.c

@@ -28,7 +28,6 @@ void get_io_context(struct io_context *ioc)
 	BUG_ON(atomic_long_read(&ioc->refcount) <= 0);
 	atomic_long_inc(&ioc->refcount);
 }
-EXPORT_SYMBOL(get_io_context);
 
 static void icq_free_icq_rcu(struct rcu_head *head)
 {
@@ -48,10 +47,8 @@ static void ioc_exit_icq(struct io_cq *icq)
 	if (icq->flags & ICQ_EXITED)
 		return;
 
-	if (et->uses_mq && et->ops.mq.exit_icq)
-		et->ops.mq.exit_icq(icq);
-	else if (!et->uses_mq && et->ops.sq.elevator_exit_icq_fn)
-		et->ops.sq.elevator_exit_icq_fn(icq);
+	if (et->ops.exit_icq)
+		et->ops.exit_icq(icq);
 
 	icq->flags |= ICQ_EXITED;
 }
@@ -113,9 +110,9 @@ static void ioc_release_fn(struct work_struct *work)
 						struct io_cq, ioc_node);
 		struct request_queue *q = icq->q;
 
-		if (spin_trylock(q->queue_lock)) {
+		if (spin_trylock(&q->queue_lock)) {
 			ioc_destroy_icq(icq);
-			spin_unlock(q->queue_lock);
+			spin_unlock(&q->queue_lock);
 		} else {
 			spin_unlock_irqrestore(&ioc->lock, flags);
 			cpu_relax();
@@ -162,7 +159,6 @@ void put_io_context(struct io_context *ioc)
 	if (free_ioc)
 		kmem_cache_free(iocontext_cachep, ioc);
 }
-EXPORT_SYMBOL(put_io_context);
 
 /**
  * put_io_context_active - put active reference on ioc
@@ -173,7 +169,6 @@ EXPORT_SYMBOL(put_io_context);
  */
 void put_io_context_active(struct io_context *ioc)
 {
-	struct elevator_type *et;
 	unsigned long flags;
 	struct io_cq *icq;
 
@@ -187,25 +182,12 @@ void put_io_context_active(struct io_context *ioc)
 	 * reverse double locking.  Read comment in ioc_release_fn() for
 	 * explanation on the nested locking annotation.
 	 */
-retry:
 	spin_lock_irqsave_nested(&ioc->lock, flags, 1);
 	hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) {
 		if (icq->flags & ICQ_EXITED)
 			continue;
 
-		et = icq->q->elevator->type;
-		if (et->uses_mq) {
 		ioc_exit_icq(icq);
-		} else {
-			if (spin_trylock(icq->q->queue_lock)) {
-				ioc_exit_icq(icq);
-				spin_unlock(icq->q->queue_lock);
-			} else {
-				spin_unlock_irqrestore(&ioc->lock, flags);
-				cpu_relax();
-				goto retry;
-			}
-		}
 	}
 	spin_unlock_irqrestore(&ioc->lock, flags);
 
@@ -251,16 +233,11 @@ void ioc_clear_queue(struct request_queue *q)
 {
 	LIST_HEAD(icq_list);
 
-	spin_lock_irq(q->queue_lock);
+	spin_lock_irq(&q->queue_lock);
 	list_splice_init(&q->icq_list, &icq_list);
+	spin_unlock_irq(&q->queue_lock);
 
-	if (q->mq_ops) {
-		spin_unlock_irq(q->queue_lock);
 	__ioc_clear_queue(&icq_list);
-	} else {
-		__ioc_clear_queue(&icq_list);
-		spin_unlock_irq(q->queue_lock);
-	}
 }
 
 int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node)
@@ -336,7 +313,6 @@ struct io_context *get_task_io_context(struct task_struct *task,
 
 	return NULL;
 }
-EXPORT_SYMBOL(get_task_io_context);
 
 /**
  * ioc_lookup_icq - lookup io_cq from ioc
@@ -350,7 +326,7 @@ struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q)
 {
 	struct io_cq *icq;
 
-	lockdep_assert_held(q->queue_lock);
+	lockdep_assert_held(&q->queue_lock);
 
 	/*
 	 * icq's are indexed from @ioc using radix tree and hint pointer,
@@ -409,16 +385,14 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
 	INIT_HLIST_NODE(&icq->ioc_node);
 
 	/* lock both q and ioc and try to link @icq */
-	spin_lock_irq(q->queue_lock);
+	spin_lock_irq(&q->queue_lock);
 	spin_lock(&ioc->lock);
 
 	if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) {
 		hlist_add_head(&icq->ioc_node, &ioc->icq_list);
 		list_add(&icq->q_node, &q->icq_list);
-		if (et->uses_mq && et->ops.mq.init_icq)
-			et->ops.mq.init_icq(icq);
-		else if (!et->uses_mq && et->ops.sq.elevator_init_icq_fn)
-			et->ops.sq.elevator_init_icq_fn(icq);
+		if (et->ops.init_icq)
+			et->ops.init_icq(icq);
 	} else {
 		kmem_cache_free(et->icq_cache, icq);
 		icq = ioc_lookup_icq(ioc, q);
@@ -427,7 +401,7 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
 	}
 
 	spin_unlock(&ioc->lock);
-	spin_unlock_irq(q->queue_lock);
+	spin_unlock_irq(&q->queue_lock);
 	radix_tree_preload_end();
 	return icq;
 }

block/blk-iolatency.c

@@ -262,29 +262,25 @@ static inline void iolat_update_total_lat_avg(struct iolatency_grp *iolat,
 				   stat->rqs.mean);
 }
 
-static inline bool iolatency_may_queue(struct iolatency_grp *iolat,
-				       wait_queue_entry_t *wait,
-				       bool first_block)
+static void iolat_cleanup_cb(struct rq_wait *rqw, void *private_data)
 {
-	struct rq_wait *rqw = &iolat->rq_wait;
+	atomic_dec(&rqw->inflight);
+	wake_up(&rqw->wait);
+}
 
-	if (first_block && waitqueue_active(&rqw->wait) &&
-	    rqw->wait.head.next != &wait->entry)
-		return false;
+static bool iolat_acquire_inflight(struct rq_wait *rqw, void *private_data)
+{
+	struct iolatency_grp *iolat = private_data;
 	return rq_wait_inc_below(rqw, iolat->rq_depth.max_depth);
 }
 
 static void __blkcg_iolatency_throttle(struct rq_qos *rqos,
 				       struct iolatency_grp *iolat,
-				       spinlock_t *lock, bool issue_as_root,
+				       bool issue_as_root,
 				       bool use_memdelay)
-	__releases(lock)
-	__acquires(lock)
 {
 	struct rq_wait *rqw = &iolat->rq_wait;
 	unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay);
-	DEFINE_WAIT(wait);
-	bool first_block = true;
 
 	if (use_delay)
 		blkcg_schedule_throttle(rqos->q, use_memdelay);
@@ -301,27 +297,7 @@ static void __blkcg_iolatency_throttle(struct rq_qos *rqos,
 		return;
 	}
 
-	if (iolatency_may_queue(iolat, &wait, first_block))
-		return;
-
-	do {
-		prepare_to_wait_exclusive(&rqw->wait, &wait,
-					  TASK_UNINTERRUPTIBLE);
-
-		if (iolatency_may_queue(iolat, &wait, first_block))
-			break;
-		first_block = false;
-
-		if (lock) {
-			spin_unlock_irq(lock);
-			io_schedule();
-			spin_lock_irq(lock);
-		} else {
-			io_schedule();
-		}
-	} while (1);
-
-	finish_wait(&rqw->wait, &wait);
+	rq_qos_wait(rqw, iolat, iolat_acquire_inflight, iolat_cleanup_cb);
 }
 
 #define SCALE_DOWN_FACTOR 2
@@ -478,38 +454,15 @@ static void check_scale_change(struct iolatency_grp *iolat)
 	scale_change(iolat, direction > 0);
 }
 
-static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio,
-				     spinlock_t *lock)
+static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio)
 {
 	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
-	struct blkcg *blkcg;
-	struct blkcg_gq *blkg;
-	struct request_queue *q = rqos->q;
+	struct blkcg_gq *blkg = bio->bi_blkg;
 	bool issue_as_root = bio_issue_as_root_blkg(bio);
 
 	if (!blk_iolatency_enabled(blkiolat))
 		return;
 
-	rcu_read_lock();
-	blkcg = bio_blkcg(bio);
-	bio_associate_blkcg(bio, &blkcg->css);
-	blkg = blkg_lookup(blkcg, q);
-	if (unlikely(!blkg)) {
-		if (!lock)
-			spin_lock_irq(q->queue_lock);
-		blkg = blkg_lookup_create(blkcg, q);
-		if (IS_ERR(blkg))
-			blkg = NULL;
-		if (!lock)
-			spin_unlock_irq(q->queue_lock);
-	}
-	if (!blkg)
-		goto out;
-
-	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
-	bio_associate_blkg(bio, blkg);
-out:
-	rcu_read_unlock();
 	while (blkg && blkg->parent) {
 		struct iolatency_grp *iolat = blkg_to_lat(blkg);
 		if (!iolat) {
@@ -518,7 +471,7 @@ static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio,
 		}
 
 		check_scale_change(iolat);
-		__blkcg_iolatency_throttle(rqos, iolat, lock, issue_as_root,
+		__blkcg_iolatency_throttle(rqos, iolat, issue_as_root,
 				     (bio->bi_opf & REQ_SWAP) == REQ_SWAP);
 		blkg = blkg->parent;
 	}
@@ -640,7 +593,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
 	bool enabled = false;
 
 	blkg = bio->bi_blkg;
-	if (!blkg)
+	if (!blkg || !bio_flagged(bio, BIO_TRACKED))
 		return;
 
 	iolat = blkg_to_lat(bio->bi_blkg);
@@ -730,7 +683,7 @@ static void blkiolatency_timer_fn(struct timer_list *t)
 		 * We could be exiting, don't access the pd unless we have a
 		 * ref on the blkg.
 		 */
-		if (!blkg_try_get(blkg))
+		if (!blkg_tryget(blkg))
 			continue;
 
 		iolat = blkg_to_lat(blkg);

block/blk-merge.c

@@ -389,7 +389,6 @@ void blk_recount_segments(struct request_queue *q, struct bio *bio)
 
 	bio_set_flag(bio, BIO_SEG_VALID);
 }
-EXPORT_SYMBOL(blk_recount_segments);
 
 static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 				   struct bio *nxt)
@@ -596,17 +595,6 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 	return ll_new_hw_segment(q, req, bio);
 }
 
-/*
- * blk-mq uses req->special to carry normal driver per-request payload, it
- * does not indicate a prepared command that we cannot merge with.
- */
-static bool req_no_special_merge(struct request *req)
-{
-	struct request_queue *q = req->q;
-
-	return !q->mq_ops && req->special;
-}
-
 static bool req_attempt_discard_merge(struct request_queue *q, struct request *req,
 		struct request *next)
 {
@@ -632,13 +620,6 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	unsigned int seg_size =
 		req->biotail->bi_seg_back_size + next->bio->bi_seg_front_size;
 
-	/*
-	 * First check if the either of the requests are re-queued
-	 * requests.  Can't merge them if they are.
-	 */
-	if (req_no_special_merge(req) || req_no_special_merge(next))
-		return 0;
-
 	if (req_gap_back_merge(req, next->bio))
 		return 0;
 
@@ -703,12 +684,10 @@ static void blk_account_io_merge(struct request *req)
 {
 	if (blk_do_io_stat(req)) {
 		struct hd_struct *part;
-		int cpu;
 
-		cpu = part_stat_lock();
+		part_stat_lock();
 		part = req->part;
 
-		part_round_stats(req->q, cpu, part);
 		part_dec_in_flight(req->q, part, rq_data_dir(req));
 
 		hd_struct_put(part);
@@ -731,7 +710,8 @@ static inline bool blk_discard_mergable(struct request *req)
 	return false;
 }
 
-enum elv_merge blk_try_req_merge(struct request *req, struct request *next)
+static enum elv_merge blk_try_req_merge(struct request *req,
+					struct request *next)
 {
 	if (blk_discard_mergable(req))
 		return ELEVATOR_DISCARD_MERGE;
@@ -748,9 +728,6 @@ enum elv_merge blk_try_req_merge(struct request *req, struct request *next)
 static struct request *attempt_merge(struct request_queue *q,
 				     struct request *req, struct request *next)
 {
-	if (!q->mq_ops)
-		lockdep_assert_held(q->queue_lock);
-
 	if (!rq_mergeable(req) || !rq_mergeable(next))
 		return NULL;
 
@@ -758,8 +735,7 @@ static struct request *attempt_merge(struct request_queue *q,
 		return NULL;
 
 	if (rq_data_dir(req) != rq_data_dir(next)
-	    || req->rq_disk != next->rq_disk
-	    || req_no_special_merge(next))
+	    || req->rq_disk != next->rq_disk)
 		return NULL;
 
 	if (req_op(req) == REQ_OP_WRITE_SAME &&
@@ -773,6 +749,9 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (req->write_hint != next->write_hint)
 		return NULL;
 
+	if (req->ioprio != next->ioprio)
+		return NULL;
+
 	/*
 	 * If we are allowed to merge, then append bio list
 	 * from next to rq and release next. merge_requests_fn
@@ -828,10 +807,6 @@ static struct request *attempt_merge(struct request_queue *q,
 	 */
 	blk_account_io_merge(next);
 
-	req->ioprio = ioprio_best(req->ioprio, next->ioprio);
-	if (blk_rq_cpu_valid(next))
-		req->cpu = next->cpu;
-
 	/*
 	 * ownership of bio passed from next to req, return 'next' for
 	 * the caller to free
@@ -863,16 +838,11 @@ 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)
 {
-	struct elevator_queue *e = q->elevator;
 	struct request *free;
 
-	if (!e->uses_mq && e->type->ops.sq.elevator_allow_rq_merge_fn)
-		if (!e->type->ops.sq.elevator_allow_rq_merge_fn(q, rq, next))
-			return 0;
-
 	free = attempt_merge(q, rq, next);
 	if (free) {
-		__blk_put_request(q, free);
+		blk_put_request(free);
 		return 1;
 	}
 
@@ -891,8 +861,8 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (bio_data_dir(bio) != rq_data_dir(rq))
 		return false;
 
-	/* must be same device and not a special request */
-	if (rq->rq_disk != bio->bi_disk || req_no_special_merge(rq))
+	/* must be same device */
+	if (rq->rq_disk != bio->bi_disk)
 		return false;
 
 	/* only merge integrity protected bio into ditto rq */
@@ -911,6 +881,9 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (rq->write_hint != bio->bi_write_hint)
 		return false;
 
+	if (rq->ioprio != bio_prio(bio))
+		return false;
+
 	return true;
 }
 

block/blk-mq-cpumap.c

@@ -14,9 +14,10 @@
 #include "blk.h"
 #include "blk-mq.h"
 
-static int cpu_to_queue_index(unsigned int nr_queues, const int cpu)
+static int cpu_to_queue_index(struct blk_mq_queue_map *qmap,
+			      unsigned int nr_queues, const int cpu)
 {
-	return cpu % nr_queues;
+	return qmap->queue_offset + (cpu % nr_queues);
 }
 
 static int get_first_sibling(unsigned int cpu)
@@ -30,10 +31,10 @@ static int get_first_sibling(unsigned int cpu)
 	return cpu;
 }
 
-int blk_mq_map_queues(struct blk_mq_tag_set *set)
+int blk_mq_map_queues(struct blk_mq_queue_map *qmap)
 {
-	unsigned int *map = set->mq_map;
-	unsigned int nr_queues = set->nr_hw_queues;
+	unsigned int *map = qmap->mq_map;
+	unsigned int nr_queues = qmap->nr_queues;
 	unsigned int cpu, first_sibling;
 
 	for_each_possible_cpu(cpu) {
@@ -44,11 +45,11 @@ int blk_mq_map_queues(struct blk_mq_tag_set *set)
 		 * performace optimizations.
 		 */
 		if (cpu < nr_queues) {
-			map[cpu] = cpu_to_queue_index(nr_queues, cpu);
+			map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
 		} else {
 			first_sibling = get_first_sibling(cpu);
 			if (first_sibling == cpu)
-				map[cpu] = cpu_to_queue_index(nr_queues, cpu);
+				map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
 			else
 				map[cpu] = map[first_sibling];
 		}
@@ -62,12 +63,12 @@ EXPORT_SYMBOL_GPL(blk_mq_map_queues);
  * We have no quick way of doing reverse lookups. This is only used at
  * queue init time, so runtime isn't important.
  */
-int blk_mq_hw_queue_to_node(unsigned int *mq_map, unsigned int index)
+int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int index)
 {
 	int i;
 
 	for_each_possible_cpu(i) {
-		if (index == mq_map[i])
+		if (index == qmap->mq_map[i])
 			return local_memory_node(cpu_to_node(i));
 	}
 

block/blk-mq-debugfs.h

@@ -31,6 +31,10 @@ void blk_mq_debugfs_unregister_sched(struct request_queue *q);
 int blk_mq_debugfs_register_sched_hctx(struct request_queue *q,
 				       struct blk_mq_hw_ctx *hctx);
 void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx);
+
+int blk_mq_debugfs_register_rqos(struct rq_qos *rqos);
+void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos);
+void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q);
 #else
 static inline int blk_mq_debugfs_register(struct request_queue *q)
 {
@@ -78,6 +82,19 @@ static inline int blk_mq_debugfs_register_sched_hctx(struct request_queue *q,
 static inline void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx)
 {
 }
+
+static inline int blk_mq_debugfs_register_rqos(struct rq_qos *rqos)
+{
+	return 0;
+}
+
+static inline void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos)
+{
+}
+
+static inline void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q)
+{
+}
 #endif
 
 #ifdef CONFIG_BLK_DEBUG_FS_ZONED

block/blk-mq-pci.c

@@ -31,26 +31,26 @@
  * that maps a queue to the CPUs that have irq affinity for the corresponding
  * vector.
  */
-int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev,
+int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev,
 			    int offset)
 {
 	const struct cpumask *mask;
 	unsigned int queue, cpu;
 
-	for (queue = 0; queue < set->nr_hw_queues; queue++) {
+	for (queue = 0; queue < qmap->nr_queues; queue++) {
 		mask = pci_irq_get_affinity(pdev, queue + offset);
 		if (!mask)
 			goto fallback;
 
 		for_each_cpu(cpu, mask)
-			set->mq_map[cpu] = queue;
+			qmap->mq_map[cpu] = qmap->queue_offset + queue;
 	}
 
 	return 0;
 
 fallback:
-	WARN_ON_ONCE(set->nr_hw_queues > 1);
-	blk_mq_clear_mq_map(set);
+	WARN_ON_ONCE(qmap->nr_queues > 1);
+	blk_mq_clear_mq_map(qmap);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);

block/blk-pm.h

@@ -21,7 +21,7 @@ static inline void blk_pm_mark_last_busy(struct request *rq)
 
 static inline void blk_pm_requeue_request(struct request *rq)
 {
-	lockdep_assert_held(rq->q->queue_lock);
+	lockdep_assert_held(&rq->q->queue_lock);
 
 	if (rq->q->dev && !(rq->rq_flags & RQF_PM))
 		rq->q->nr_pending--;
@@ -30,7 +30,7 @@ static inline void blk_pm_requeue_request(struct request *rq)
 static inline void blk_pm_add_request(struct request_queue *q,
 				      struct request *rq)
 {
-	lockdep_assert_held(q->queue_lock);
+	lockdep_assert_held(&q->queue_lock);
 
 	if (q->dev && !(rq->rq_flags & RQF_PM))
 		q->nr_pending++;
@@ -38,7 +38,7 @@ static inline void blk_pm_add_request(struct request_queue *q,
 
 static inline void blk_pm_put_request(struct request *rq)
 {
-	lockdep_assert_held(rq->q->queue_lock);
+	lockdep_assert_held(&rq->q->queue_lock);
 
 	if (rq->q->dev && !(rq->rq_flags & RQF_PM))
 		--rq->q->nr_pending;