Merge branch 'for-4.10/block' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "This is the main block pull request this series. Contrary to previous
  release, I've kept the core and driver changes in the same branch. We
  always ended up having dependencies between the two for obvious
  reasons, so makes more sense to keep them together. That said, I'll
  probably try and keep more topical branches going forward, especially
  for cycles that end up being as busy as this one.

  The major parts of this pull request is:

   - Improved support for O_DIRECT on block devices, with a small
     private implementation instead of using the pig that is
     fs/direct-io.c. From Christoph.

   - Request completion tracking in a scalable fashion. This is utilized
     by two components in this pull, the new hybrid polling and the
     writeback queue throttling code.

   - Improved support for polling with O_DIRECT, adding a hybrid mode
     that combines pure polling with an initial sleep. From me.

   - Support for automatic throttling of writeback queues on the block
     side. This uses feedback from the device completion latencies to
     scale the queue on the block side up or down. From me.

   - Support from SMR drives in the block layer and for SD. From Hannes
     and Shaun.

   - Multi-connection support for nbd. From Josef.

   - Cleanup of request and bio flags, so we have a clear split between
     which are bio (or rq) private, and which ones are shared. From
     Christoph.

   - A set of patches from Bart, that improve how we handle queue
     stopping and starting in blk-mq.

   - Support for WRITE_ZEROES from Chaitanya.

   - Lightnvm updates from Javier/Matias.

   - Supoort for FC for the nvme-over-fabrics code. From James Smart.

   - A bunch of fixes from a whole slew of people, too many to name
     here"

* 'for-4.10/block' of git://git.kernel.dk/linux-block: (182 commits)
  blk-stat: fix a few cases of missing batch flushing
  blk-flush: run the queue when inserting blk-mq flush
  elevator: make the rqhash helpers exported
  blk-mq: abstract out blk_mq_dispatch_rq_list() helper
  blk-mq: add blk_mq_start_stopped_hw_queue()
  block: improve handling of the magic discard payload
  blk-wbt: don't throttle discard or write zeroes
  nbd: use dev_err_ratelimited in io path
  nbd: reset the setup task for NBD_CLEAR_SOCK
  nvme-fabrics: Add FC LLDD loopback driver to test FC-NVME
  nvme-fabrics: Add target support for FC transport
  nvme-fabrics: Add host support for FC transport
  nvme-fabrics: Add FC transport LLDD api definitions
  nvme-fabrics: Add FC transport FC-NVME definitions
  nvme-fabrics: Add FC transport error codes to nvme.h
  Add type 0x28 NVME type code to scsi fc headers
  nvme-fabrics: patch target code in prep for FC transport support
  nvme-fabrics: set sqe.command_id in core not transports
  parser: add u64 number parser
  nvme-rdma: align to generic ib_event logging helper
  ...

30 files changed, 2835 insertions, 488 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 1d4d624..8bf114a 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -5,6 +5,7 @@ menuconfig BLOCK
        bool "Enable the block layer" if EXPERT
        default y
        select SBITMAP
+       select SRCU
        help
 	 Provide block layer support for the kernel.
 
@@ -89,6 +90,14 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
+config BLK_DEV_ZONED
+	bool "Zoned block device support"
+	---help---
+	Block layer zoned block device support. This option enables
+	support for ZAC/ZBC host-managed and host-aware zoned block devices.
+
+	Say yes here if you have a ZAC or ZBC storage device.
+
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
 	depends on BLK_CGROUP=y
@@ -112,6 +121,32 @@ config BLK_CMDLINE_PARSER
 
 	See Documentation/block/cmdline-partition.txt for more information.
 
+config BLK_WBT
+	bool "Enable support for block device writeback throttling"
+	default n
+	---help---
+	Enabling this option enables the block layer to throttle buffered
+	background writeback from the VM, making it more smooth and having
+	less impact on foreground operations. The throttling is done
+	dynamically on an algorithm loosely based on CoDel, factoring in
+	the realtime performance of the disk.
+
+config BLK_WBT_SQ
+	bool "Single queue writeback throttling"
+	default n
+	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
+	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.
+
 menu "Partition Types"
 
 source "block/partitions/Kconfig"
diff --git a/block/Makefile b/block/Makefile
index 36acdd7..a827f98 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
-			blk-lib.o blk-mq.o blk-mq-tag.o \
+			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o ioctl.o \
 			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
 			badblocks.o partitions/
@@ -23,3 +23,5 @@ obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
+obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
+obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 63f72f0..5384713 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -172,7 +172,7 @@ bool bio_integrity_enabled(struct bio *bio)
 {
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 
-	if (!bio_is_rw(bio))
+	if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE)
 		return false;
 
 	/* Already protected? */
diff --git a/block/bio.c b/block/bio.c
index db85c57..2b37502 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -270,11 +270,15 @@ static void bio_free(struct bio *bio)
 	}
 }
 
-void bio_init(struct bio *bio)
+void bio_init(struct bio *bio, struct bio_vec *table,
+	      unsigned short max_vecs)
 {
 	memset(bio, 0, sizeof(*bio));
 	atomic_set(&bio->__bi_remaining, 1);
 	atomic_set(&bio->__bi_cnt, 1);
+
+	bio->bi_io_vec = table;
+	bio->bi_max_vecs = max_vecs;
 }
 EXPORT_SYMBOL(bio_init);
 
@@ -480,7 +484,7 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		return NULL;
 
 	bio = p + front_pad;
-	bio_init(bio);
+	bio_init(bio, NULL, 0);
 
 	if (nr_iovecs > inline_vecs) {
 		unsigned long idx = 0;
@@ -670,6 +674,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 	switch (bio_op(bio)) {
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
+	case REQ_OP_WRITE_ZEROES:
 		break;
 	case REQ_OP_WRITE_SAME:
 		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
@@ -847,6 +852,55 @@ done:
 }
 EXPORT_SYMBOL(bio_add_page);
 
+/**
+ * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * @bio: bio to add pages to
+ * @iter: iov iterator describing the region to be mapped
+ *
+ * Pins as many pages from *iter and appends them to @bio's bvec array. The
+ * pages will have to be released using put_page() when done.
+ */
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
+	struct page **pages = (struct page **)bv;
+	size_t offset, diff;
+	ssize_t size;
+
+	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
+	if (unlikely(size <= 0))
+		return size ? size : -EFAULT;
+	nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
+
+	/*
+	 * Deep magic below:  We need to walk the pinned pages backwards
+	 * because we are abusing the space allocated for the bio_vecs
+	 * for the page array.  Because the bio_vecs are larger than the
+	 * page pointers by definition this will always work.  But it also
+	 * means we can't use bio_add_page, so any changes to it's semantics
+	 * need to be reflected here as well.
+	 */
+	bio->bi_iter.bi_size += size;
+	bio->bi_vcnt += nr_pages;
+
+	diff = (nr_pages * PAGE_SIZE - offset) - size;
+	while (nr_pages--) {
+		bv[nr_pages].bv_page = pages[nr_pages];
+		bv[nr_pages].bv_len = PAGE_SIZE;
+		bv[nr_pages].bv_offset = 0;
+	}
+
+	bv[0].bv_offset += offset;
+	bv[0].bv_len -= offset;
+	if (diff)
+		bv[bio->bi_vcnt - 1].bv_len -= diff;
+
+	iov_iter_advance(iter, size);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
+
 struct submit_bio_ret {
 	struct completion event;
 	int error;
@@ -1786,15 +1840,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	BUG_ON(sectors <= 0);
 	BUG_ON(sectors >= bio_sectors(bio));
 
-	/*
-	 * Discards need a mutable bio_vec to accommodate the payload
-	 * required by the DSM TRIM and UNMAP commands.
-	 */
-	if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
-		split = bio_clone_bioset(bio, gfp, bs);
-	else
-		split = bio_clone_fast(bio, gfp, bs);
-
+	split = bio_clone_fast(bio, gfp, bs);
 	if (!split)
 		return NULL;
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index b08ccbb..8ba0af7 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -185,7 +185,8 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 	}
 
 	wb_congested = wb_congested_get_create(&q->backing_dev_info,
-					       blkcg->css.id, GFP_NOWAIT);
+					       blkcg->css.id,
+					       GFP_NOWAIT | __GFP_NOWARN);
 	if (!wb_congested) {
 		ret = -ENOMEM;
 		goto err_put_css;
@@ -193,7 +194,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 
 	/* allocate */
 	if (!new_blkg) {
-		new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT);
+		new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN);
 		if (unlikely(!new_blkg)) {
 			ret = -ENOMEM;
 			goto err_put_congested;
@@ -1022,7 +1023,7 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 	}
 
 	spin_lock_init(&blkcg->lock);
-	INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT);
+	INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN);
 	INIT_HLIST_HEAD(&blkcg->blkg_list);
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&blkcg->cgwb_list);
@@ -1240,7 +1241,7 @@ pd_prealloc:
 		if (blkg->pd[pol->plid])
 			continue;
 
-		pd = pol->pd_alloc_fn(GFP_NOWAIT, q->node);
+		pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q->node);
 		if (!pd)
 			swap(pd, pd_prealloc);
 		if (!pd) {
diff --git a/block/blk-core.c b/block/blk-core.c
index 14d7c07..bd642a4 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -39,6 +39,7 @@
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-wbt.h"
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
@@ -145,13 +146,13 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 	if (error)
 		bio->bi_error = error;
 
-	if (unlikely(rq->cmd_flags & REQ_QUIET))
+	if (unlikely(rq->rq_flags & RQF_QUIET))
 		bio_set_flag(bio, BIO_QUIET);
 
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
-	if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
 		bio_endio(bio);
 }
 
@@ -882,6 +883,7 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 
 fail:
 	blk_free_flush_queue(q->fq);
+	wbt_exit(q);
 	return NULL;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -899,7 +901,7 @@ EXPORT_SYMBOL(blk_get_queue);
 
 static inline void blk_free_request(struct request_list *rl, struct request *rq)
 {
-	if (rq->cmd_flags & REQ_ELVPRIV) {
+	if (rq->rq_flags & RQF_ELVPRIV) {
 		elv_put_request(rl->q, rq);
 		if (rq->elv.icq)
 			put_io_context(rq->elv.icq->ioc);
@@ -961,14 +963,14 @@ static void __freed_request(struct request_list *rl, int sync)
  * A request has just been released.  Account for it, update the full and
  * congestion status, wake up any waiters.   Called under q->queue_lock.
  */
-static void freed_request(struct request_list *rl, int op, unsigned int flags)
+static void freed_request(struct request_list *rl, bool sync,
+		req_flags_t rq_flags)
 {
 	struct request_queue *q = rl->q;
-	int sync = rw_is_sync(op, flags);
 
 	q->nr_rqs[sync]--;
 	rl->count[sync]--;
-	if (flags & REQ_ELVPRIV)
+	if (rq_flags & RQF_ELVPRIV)
 		q->nr_rqs_elvpriv--;
 
 	__freed_request(rl, sync);
@@ -1056,8 +1058,7 @@ static struct io_context *rq_ioc(struct bio *bio)
 /**
  * __get_request - get a free request
  * @rl: request list to allocate from
- * @op: REQ_OP_READ/REQ_OP_WRITE
- * @op_flags: rq_flag_bits
+ * @op: operation and flags
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
@@ -1068,22 +1069,22 @@ static struct io_context *rq_ioc(struct bio *bio)
  * Returns ERR_PTR on failure, with @q->queue_lock held.
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
-static struct request *__get_request(struct request_list *rl, int op,
-				     int op_flags, struct bio *bio,
-				     gfp_t gfp_mask)
+static struct request *__get_request(struct request_list *rl, unsigned int op,
+		struct bio *bio, gfp_t gfp_mask)
 {
 	struct request_queue *q = rl->q;
 	struct request *rq;
 	struct elevator_type *et = q->elevator->type;
 	struct io_context *ioc = rq_ioc(bio);
 	struct io_cq *icq = NULL;
-	const bool is_sync = rw_is_sync(op, op_flags) != 0;
+	const bool is_sync = op_is_sync(op);
 	int may_queue;
+	req_flags_t rq_flags = RQF_ALLOCED;
 
 	if (unlikely(blk_queue_dying(q)))
 		return ERR_PTR(-ENODEV);
 
-	may_queue = elv_may_queue(q, op, op_flags);
+	may_queue = elv_may_queue(q, op);
 	if (may_queue == ELV_MQUEUE_NO)
 		goto rq_starved;
 
@@ -1127,7 +1128,7 @@ static struct request *__get_request(struct request_list *rl, int op,
 
 	/*
 	 * Decide whether the new request will be managed by elevator.  If
-	 * so, mark @op_flags and increment elvpriv.  Non-zero elvpriv will
+	 * so, mark @rq_flags and increment elvpriv.  Non-zero elvpriv will
 	 * prevent the current elevator from being destroyed until the new
 	 * request is freed.  This guarantees icq's won't be destroyed and
 	 * makes creating new ones safe.
@@ -1136,14 +1137,14 @@ static struct request *__get_request(struct request_list *rl, int op,
 	 * it will be created after releasing queue_lock.
 	 */
 	if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) {
-		op_flags |= REQ_ELVPRIV;
+		rq_flags |= RQF_ELVPRIV;
 		q->nr_rqs_elvpriv++;
 		if (et->icq_cache && ioc)
 			icq = ioc_lookup_icq(ioc, q);
 	}
 
 	if (blk_queue_io_stat(q))
-		op_flags |= REQ_IO_STAT;
+		rq_flags |= RQF_IO_STAT;
 	spin_unlock_irq(q->queue_lock);
 
 	/* allocate and init request */
@@ -1153,10 +1154,11 @@ static struct request *__get_request(struct request_list *rl, int op,
 
 	blk_rq_init(q, rq);
 	blk_rq_set_rl(rq, rl);
-	req_set_op_attrs(rq, op, op_flags | REQ_ALLOCED);
+	rq->cmd_flags = op;
+	rq->rq_flags = rq_flags;
 
 	/* init elvpriv */
-	if (op_flags & REQ_ELVPRIV) {
+	if (rq_flags & RQF_ELVPRIV) {
 		if (unlikely(et->icq_cache && !icq)) {
 			if (ioc)
 				icq = ioc_create_icq(ioc, q, gfp_mask);
@@ -1195,7 +1197,7 @@ fail_elvpriv:
 	printk_ratelimited(KERN_WARNING "%s: dev %s: request aux data allocation failed, iosched may be disturbed\n",
 			   __func__, dev_name(q->backing_dev_info.dev));
 
-	rq->cmd_flags &= ~REQ_ELVPRIV;
+	rq->rq_flags &= ~RQF_ELVPRIV;
 	rq->elv.icq = NULL;
 
 	spin_lock_irq(q->queue_lock);
@@ -1212,7 +1214,7 @@ fail_alloc:
 	 * queue, but this is pretty rare.
 	 */
 	spin_lock_irq(q->queue_lock);
-	freed_request(rl, op, op_flags);
+	freed_request(rl, is_sync, rq_flags);
 
 	/*
 	 * in the very unlikely event that allocation failed and no
@@ -1230,8 +1232,7 @@ rq_starved:
 /**
  * get_request - get a free request
  * @q: request_queue to allocate request from
- * @op: REQ_OP_READ/REQ_OP_WRITE
- * @op_flags: rq_flag_bits
+ * @op: operation and flags
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
@@ -1242,18 +1243,17 @@ rq_starved:
  * Returns ERR_PTR on failure, with @q->queue_lock held.
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
-static struct request *get_request(struct request_queue *q, int op,
-				   int op_flags, struct bio *bio,
-				   gfp_t gfp_mask)
+static struct request *get_request(struct request_queue *q, unsigned int op,
+		struct bio *bio, gfp_t gfp_mask)
 {
-	const bool is_sync = rw_is_sync(op, op_flags) != 0;
+	const bool is_sync = op_is_sync(op);
 	DEFINE_WAIT(wait);
 	struct request_list *rl;
 	struct request *rq;
 
 	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
 retry:
-	rq = __get_request(rl, op, op_flags, bio, gfp_mask);
+	rq = __get_request(rl, op, bio, gfp_mask);
 	if (!IS_ERR(rq))
 		return rq;
 
@@ -1295,7 +1295,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 	create_io_context(gfp_mask, q->node);
 
 	spin_lock_irq(q->queue_lock);
-	rq = get_request(q, rw, 0, NULL, gfp_mask);
+	rq = get_request(q, rw, NULL, gfp_mask);
 	if (IS_ERR(rq)) {
 		spin_unlock_irq(q->queue_lock);
 		return rq;
@@ -1346,8 +1346,9 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
 	blk_delete_timer(rq);
 	blk_clear_rq_complete(rq);
 	trace_block_rq_requeue(q, rq);
+	wbt_requeue(q->rq_wb, &rq->issue_stat);
 
-	if (rq->cmd_flags & REQ_QUEUED)
+	if (rq->rq_flags & RQF_QUEUED)
 		blk_queue_end_tag(q, rq);
 
 	BUG_ON(blk_queued_rq(rq));
@@ -1409,7 +1410,7 @@ EXPORT_SYMBOL_GPL(part_round_stats);
 #ifdef CONFIG_PM
 static void blk_pm_put_request(struct request *rq)
 {
-	if (rq->q->dev && !(rq->cmd_flags & REQ_PM) && !--rq->q->nr_pending)
+	if (rq->q->dev && !(rq->rq_flags & RQF_PM) && !--rq->q->nr_pending)
 		pm_runtime_mark_last_busy(rq->q->dev);
 }
 #else
@@ -1421,6 +1422,8 @@ static inline void blk_pm_put_request(struct request *rq) {}
  */
 void __blk_put_request(struct request_queue *q, struct request *req)
 {
+	req_flags_t rq_flags = req->rq_flags;
+
 	if (unlikely(!q))
 		return;
 
@@ -1436,20 +1439,21 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	/* this is a bio leak */
 	WARN_ON(req->bio != NULL);
 
+	wbt_done(q->rq_wb, &req->issue_stat);
+
 	/*
 	 * Request may not have originated from ll_rw_blk. if not,
 	 * it didn't come out of our reserved rq pools
 	 */
-	if (req->cmd_flags & REQ_ALLOCED) {
-		unsigned int flags = req->cmd_flags;
-		int op = req_op(req);
+	if (rq_flags & RQF_ALLOCED) {
 		struct request_list *rl = blk_rq_rl(req);
+		bool sync = op_is_sync(req->cmd_flags);
 
 		BUG_ON(!list_empty(&req->queuelist));
 		BUG_ON(ELV_ON_HASH(req));
 
 		blk_free_request(rl, req);
-		freed_request(rl, op, flags);
+		freed_request(rl, sync, rq_flags);
 		blk_put_rl(rl);
 	}
 }
@@ -1471,38 +1475,6 @@ void blk_put_request(struct request *req)
 }
 EXPORT_SYMBOL(blk_put_request);
 
-/**
- * blk_add_request_payload - add a payload to a request
- * @rq: request to update
- * @page: page backing the payload
- * @offset: offset in page
- * @len: length of the payload.
- *
- * This allows to later add a payload to an already submitted request by
- * a block driver.  The driver needs to take care of freeing the payload
- * itself.
- *
- * Note that this is a quite horrible hack and nothing but handling of
- * discard requests should ever use it.
- */
-void blk_add_request_payload(struct request *rq, struct page *page,
-		int offset, unsigned int len)
-{
-	struct bio *bio = rq->bio;
-
-	bio->bi_io_vec->bv_page = page;
-	bio->bi_io_vec->bv_offset = offset;
-	bio->bi_io_vec->bv_len = len;
-
-	bio->bi_iter.bi_size = len;
-	bio->bi_vcnt = 1;
-	bio->bi_phys_segments = 1;
-
-	rq->__data_len = rq->resid_len = len;
-	rq->nr_phys_segments = 1;
-}
-EXPORT_SYMBOL_GPL(blk_add_request_payload);
-
 bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 			    struct bio *bio)
 {
@@ -1649,8 +1621,6 @@ out:
 void init_request_from_bio(struct request *req, struct bio *bio)
 {
 	req->cmd_type = REQ_TYPE_FS;
-
-	req->cmd_flags |= bio->bi_opf & REQ_COMMON_MASK;
 	if (bio->bi_opf & REQ_RAHEAD)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
@@ -1662,11 +1632,11 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
-	const bool sync = !!(bio->bi_opf & REQ_SYNC);
 	struct blk_plug *plug;
-	int el_ret, rw_flags = 0, where = ELEVATOR_INSERT_SORT;
+	int el_ret, where = ELEVATOR_INSERT_SORT;
 	struct request *req;
 	unsigned int request_count = 0;
+	unsigned int wb_acct;
 
 	/*
 	 * low level driver can indicate that it wants pages above a
@@ -1719,30 +1689,22 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	}
 
 get_rq:
-	/*
-	 * This sync check and mask will be re-done in init_request_from_bio(),
-	 * but we need to set it earlier to expose the sync flag to the
-	 * rq allocator and io schedulers.
-	 */
-	if (sync)
-		rw_flags |= REQ_SYNC;
-
-	/*
-	 * Add in META/PRIO flags, if set, before we get to the IO scheduler
-	 */
-	rw_flags |= (bio->bi_opf & (REQ_META | REQ_PRIO));
+	wb_acct = wbt_wait(q->rq_wb, bio, q->queue_lock);
 
 	/*
 	 * Grab a free request. This is might sleep but can not fail.
 	 * Returns with the queue unlocked.
 	 */
-	req = get_request(q, bio_data_dir(bio), rw_flags, bio, GFP_NOIO);
+	req = get_request(q, bio->bi_opf, bio, GFP_NOIO);
 	if (IS_ERR(req)) {
+		__wbt_done(q->rq_wb, wb_acct);
 		bio->bi_error = PTR_ERR(req);
 		bio_endio(bio);
 		goto out_unlock;
 	}
 
+	wbt_track(&req->issue_stat, wb_acct);
+
 	/*
 	 * After dropping the lock and possibly sleeping here, our request
 	 * may now be mergeable after it had proven unmergeable (above).
@@ -1759,11 +1721,16 @@ get_rq:
 		/*
 		 * If this is the first request added after a plug, fire
 		 * of a plug trace.
+		 *
+		 * @request_count may become stale because of schedule
+		 * out, so check plug list again.
 		 */
-		if (!request_count)
+		if (!request_count || list_empty(&plug->list))
 			trace_block_plug(q);
 		else {
-			if (request_count >= BLK_MAX_REQUEST_COUNT) {
+			struct request *last = list_entry_rq(plug->list.prev);
+			if (request_count >= BLK_MAX_REQUEST_COUNT ||
+			    blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE) {
 				blk_flush_plug_list(plug, false);
 				trace_block_plug(q);
 			}
@@ -1788,7 +1755,12 @@ static inline void blk_partition_remap(struct bio *bio)
 {
 	struct block_device *bdev = bio->bi_bdev;
 
-	if (bio_sectors(bio) && bdev != bdev->bd_contains) {
+	/*
+	 * Zone reset does not include bi_size so bio_sectors() is always 0.
+	 * Include a test for the reset op code and perform the remap if needed.
+	 */
+	if (bdev != bdev->bd_contains &&
+	    (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)) {
 		struct hd_struct *p = bdev->bd_part;
 
 		bio->bi_iter.bi_sector += p->start_sect;
@@ -1942,6 +1914,15 @@ generic_make_request_checks(struct bio *bio)
 		if (!bdev_write_same(bio->bi_bdev))
 			goto not_supported;
 		break;
+	case REQ_OP_ZONE_REPORT:
+	case REQ_OP_ZONE_RESET:
+		if (!bdev_is_zoned(bio->bi_bdev))
+			goto not_supported;
+		break;
+	case REQ_OP_WRITE_ZEROES:
+		if (!bdev_write_zeroes_sectors(bio->bi_bdev))
+			goto not_supported;
+		break;
 	default:
 		break;
 	}
@@ -2210,7 +2191,7 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
 	unsigned int bytes = 0;
 	struct bio *bio;
 
-	if (!(rq->cmd_flags & REQ_MIXED_MERGE))
+	if (!(rq->rq_flags & RQF_MIXED_MERGE))
 		return blk_rq_bytes(rq);
 
 	/*
@@ -2253,7 +2234,7 @@ void blk_account_io_done(struct request *req)
 	 * normal IO on queueing nor completion.  Accounting the
 	 * containing request is enough.
 	 */
-	if (blk_do_io_stat(req) && !(req->cmd_flags & REQ_FLUSH_SEQ)) {
+	if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {
 		unsigned long duration = jiffies - req->start_time;
 		const int rw = rq_data_dir(req);
 		struct hd_struct *part;
@@ -2281,7 +2262,7 @@ static struct request *blk_pm_peek_request(struct request_queue *q,
 					   struct request *rq)
 {
 	if (q->dev && (q->rpm_status == RPM_SUSPENDED ||
-	    (q->rpm_status != RPM_ACTIVE && !(rq->cmd_flags & REQ_PM))))
+	    (q->rpm_status != RPM_ACTIVE && !(rq->rq_flags & RQF_PM))))
 		return NULL;
 	else
 		return rq;
@@ -2357,13 +2338,13 @@ struct request *blk_peek_request(struct request_queue *q)
 		if (!rq)
 			break;
 
-		if (!(rq->cmd_flags & REQ_STARTED)) {
+		if (!(rq->rq_flags & RQF_STARTED)) {
 			/*
 			 * This is the first time the device driver
 			 * sees this request (possibly after
 			 * requeueing).  Notify IO scheduler.
 			 */
-			if (rq->cmd_flags & REQ_SORTED)
+			if (rq->rq_flags & RQF_SORTED)
 				elv_activate_rq(q, rq);
 
 			/*
@@ -2371,7 +2352,7 @@ struct request *blk_peek_request(struct request_queue *q)
 			 * it, a request that has been delayed should
 			 * not be passed by new incoming requests
 			 */
-			rq->cmd_flags |= REQ_STARTED;
+			rq->rq_flags |= RQF_STARTED;
 			trace_block_rq_issue(q, rq);
 		}
 
@@ -2380,7 +2361,7 @@ struct request *blk_peek_request(struct request_queue *q)
 			q->boundary_rq = NULL;
 		}
 
-		if (rq->cmd_flags & REQ_DONTPREP)
+		if (rq->rq_flags & RQF_DONTPREP)
 			break;
 
 		if (q->dma_drain_size && blk_rq_bytes(rq)) {
@@ -2403,11 +2384,11 @@ struct request *blk_peek_request(struct request_queue *q)
 			/*
 			 * the request may have been (partially) prepped.
 			 * we need to keep this request in the front to
-			 * avoid resource deadlock.  REQ_STARTED will
+			 * avoid resource deadlock.  RQF_STARTED will
 			 * prevent other fs requests from passing this one.
 			 */
 			if (q->dma_drain_size && blk_rq_bytes(rq) &&
-			    !(rq->cmd_flags & REQ_DONTPREP)) {
+			    !(rq->rq_flags & RQF_DONTPREP)) {
 				/*
 				 * remove the space for the drain we added
 				 * so that we don't add it again
@@ -2420,7 +2401,7 @@ struct request *blk_peek_request(struct request_queue *q)
 		} else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) {
 			int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO;
 
-			rq->cmd_flags |= REQ_QUIET;
+			rq->rq_flags |= RQF_QUIET;
 			/*
 			 * Mark this request as started so we don't trigger
 			 * any debug logic in the end I/O path.
@@ -2475,6 +2456,12 @@ void blk_start_request(struct request *req)
 {
 	blk_dequeue_request(req);
 
+	if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {
+		blk_stat_set_issue_time(&req->issue_stat);
+		req->rq_flags |= RQF_STATS;
+		wbt_issue(req->q->rq_wb, &req->issue_stat);
+	}
+
 	/*
 	 * We are now handing the request to the hardware, initialize
 	 * resid_len to full count and add the timeout handler.
@@ -2557,7 +2544,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 		req->errors = 0;
 
 	if (error && req->cmd_type == REQ_TYPE_FS &&
-	    !(req->cmd_flags & REQ_QUIET)) {
+	    !(req->rq_flags & RQF_QUIET)) {
 		char *error_type;
 
 		switch (error) {
@@ -2623,6 +2610,8 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 		return false;
 	}
 
+	WARN_ON_ONCE(req->rq_flags & RQF_SPECIAL_PAYLOAD);
+
 	req->__data_len -= total_bytes;
 
 	/* update sector only for requests with clear definition of sector */
@@ -2630,7 +2619,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 		req->__sector += total_bytes >> 9;
 
 	/* mixed attributes always follow the first bio */
-	if (req->cmd_flags & REQ_MIXED_MERGE) {
+	if (req->rq_flags & RQF_MIXED_MERGE) {
 		req->cmd_flags &= ~REQ_FAILFAST_MASK;
 		req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK;
 	}
@@ -2683,7 +2672,7 @@ void blk_unprep_request(struct request *req)
 {
 	struct request_queue *q = req->q;
 
-	req->cmd_flags &= ~REQ_DONTPREP;
+	req->rq_flags &= ~RQF_DONTPREP;
 	if (q->unprep_rq_fn)
 		q->unprep_rq_fn(q, req);
 }
@@ -2694,8 +2683,13 @@ EXPORT_SYMBOL_GPL(blk_unprep_request);
  */
 void blk_finish_request(struct request *req, int error)
 {
-	if (req->cmd_flags & REQ_QUEUED)
-		blk_queue_end_tag(req->q, req);
+	struct request_queue *q = req->q;
+
+	if (req->rq_flags & RQF_STATS)
+		blk_stat_add(&q->rq_stats[rq_data_dir(req)], req);
+
+	if (req->rq_flags & RQF_QUEUED)
+		blk_queue_end_tag(q, req);
 
 	BUG_ON(blk_queued_rq(req));
 
@@ -2704,18 +2698,19 @@ void blk_finish_request(struct request *req, int error)
 
 	blk_delete_timer(req);
 
-	if (req->cmd_flags & REQ_DONTPREP)
+	if (req->rq_flags & RQF_DONTPREP)
 		blk_unprep_request(req);
 
 	blk_account_io_done(req);
 
-	if (req->end_io)
+	if (req->end_io) {
+		wbt_done(req->q->rq_wb, &req->issue_stat);
 		req->end_io(req, error);
-	else {
+	} else {
 		if (blk_bidi_rq(req))
 			__blk_put_request(req->next_rq->q, req->next_rq);
 
-		__blk_put_request(req->q, req);
+		__blk_put_request(q, req);
 	}
 }
 EXPORT_SYMBOL(blk_finish_request);
@@ -2939,8 +2934,6 @@ EXPORT_SYMBOL_GPL(__blk_end_request_err);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
-	req_set_op(rq, bio_op(bio));
-
 	if (bio_has_data(bio))
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
 
@@ -3024,8 +3017,7 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	req_set_op_attrs(dst, req_op(src),
-			 (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE);
+	dst->cmd_flags = src->cmd_flags | REQ_NOMERGE;
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
@@ -3303,52 +3295,6 @@ void blk_finish_plug(struct blk_plug *plug)
 }
 EXPORT_SYMBOL(blk_finish_plug);
 
-bool blk_poll(struct request_queue *q, blk_qc_t cookie)
-{
-	struct blk_plug *plug;
-	long state;
-	unsigned int queue_num;
-	struct blk_mq_hw_ctx *hctx;
-
-	if (!q->mq_ops || !q->mq_ops->poll || !blk_qc_t_valid(cookie) ||
-	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
-		return false;
-
-	queue_num = blk_qc_t_to_queue_num(cookie);
-	hctx = q->queue_hw_ctx[queue_num];
-	hctx->poll_considered++;
-
-	plug = current->plug;
-	if (plug)
-		blk_flush_plug_list(plug, false);
-
-	state = current->state;
-	while (!need_resched()) {
-		int ret;
-
-		hctx->poll_invoked++;
-
-		ret = q->mq_ops->poll(hctx, blk_qc_t_to_tag(cookie));
-		if (ret > 0) {
-			hctx->poll_success++;
-			set_current_state(TASK_RUNNING);
-			return true;
-		}
-
-		if (signal_pending_state(state, current))
-			set_current_state(TASK_RUNNING);
-
-		if (current->state == TASK_RUNNING)
-			return true;
-		if (ret < 0)
-			break;
-		cpu_relax();
-	}
-
-	return false;
-}
-EXPORT_SYMBOL_GPL(blk_poll);
-
 #ifdef CONFIG_PM
 /**
  * blk_pm_runtime_init - Block layer runtime PM initialization routine
@@ -3530,8 +3476,11 @@ EXPORT_SYMBOL(blk_set_runtime_active);
 
 int __init blk_dev_init(void)
 {
-	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
+	BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS));
+	BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *
 			FIELD_SIZEOF(struct request, cmd_flags));
+	BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *
+			FIELD_SIZEOF(struct bio, bi_opf));
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 7ea0432..3ecb00a 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -72,7 +72,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	spin_lock_irq(q->queue_lock);
 
 	if (unlikely(blk_queue_dying(q))) {
-		rq->cmd_flags |= REQ_QUIET; 
+		rq->rq_flags |= RQF_QUIET;
 		rq->errors = -ENXIO;
 		__blk_end_request_all(rq, rq->errors);
 		spin_unlock_irq(q->queue_lock);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 3c882cb..20b7c7a 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -56,7 +56,7 @@
  * Once while executing DATA and again after the whole sequence is
  * complete.  The first completion updates the contained bio but doesn't
  * finish it so that the bio submitter is notified only after the whole
- * sequence is complete.  This is implemented by testing REQ_FLUSH_SEQ in
+ * sequence is complete.  This is implemented by testing RQF_FLUSH_SEQ in
  * req_bio_endio().
  *
  * The above peculiarity requires that each FLUSH/FUA request has only one
@@ -127,17 +127,14 @@ static void blk_flush_restore_request(struct request *rq)
 	rq->bio = rq->biotail;
 
 	/* make @rq a normal request */
-	rq->cmd_flags &= ~REQ_FLUSH_SEQ;
+	rq->rq_flags &= ~RQF_FLUSH_SEQ;
 	rq->end_io = rq->flush.saved_end_io;
 }
 
 static bool blk_flush_queue_rq(struct request *rq, bool add_front)
 {
 	if (rq->q->mq_ops) {
-		struct request_queue *q = rq->q;
-
-		blk_mq_add_to_requeue_list(rq, add_front);
-		blk_mq_kick_requeue_list(q);
+		blk_mq_add_to_requeue_list(rq, add_front, true);
 		return false;
 	} else {
 		if (add_front)
@@ -330,7 +327,8 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	}
 
 	flush_rq->cmd_type = REQ_TYPE_FS;
-	req_set_op_attrs(flush_rq, REQ_OP_FLUSH, WRITE_FLUSH | REQ_FLUSH_SEQ);
+	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
+	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
 	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;
 
@@ -368,7 +366,7 @@ static void flush_data_end_io(struct request *rq, int error)
 	elv_completed_request(q, rq);
 
 	/* for avoiding double accounting */
-	rq->cmd_flags &= ~REQ_STARTED;
+	rq->rq_flags &= ~RQF_STARTED;
 
 	/*
 	 * After populating an empty queue, kick it to avoid stall.  Read
@@ -426,6 +424,13 @@ void blk_insert_flush(struct request *rq)
 		rq->cmd_flags &= ~REQ_FUA;
 
 	/*
+	 * REQ_PREFLUSH|REQ_FUA implies REQ_SYNC, so if we clear any
+	 * of those flags, we have to set REQ_SYNC to avoid skewing
+	 * the request accounting.
+	 */
+	rq->cmd_flags |= REQ_SYNC;
+
+	/*
 	 * An empty flush handed down from a stacking driver may
 	 * translate into nothing if the underlying device does not
 	 * advertise a write-back cache.  In this case, simply
@@ -449,7 +454,7 @@ void blk_insert_flush(struct request *rq)
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
 		if (q->mq_ops) {
-			blk_mq_insert_request(rq, false, false, true);
+			blk_mq_insert_request(rq, false, true, false);
 		} else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
@@ -461,7 +466,7 @@ void blk_insert_flush(struct request *rq)
 	 */
 	memset(&rq->flush, 0, sizeof(rq->flush));
 	INIT_LIST_HEAD(&rq->flush.list);
-	rq->cmd_flags |= REQ_FLUSH_SEQ;
+	rq->rq_flags |= RQF_FLUSH_SEQ;
 	rq->flush.saved_end_io = rq->end_io; /* Usually NULL */
 	if (q->mq_ops) {
 		rq->end_io = mq_flush_data_end_io;
@@ -513,7 +518,7 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 
 	bio = bio_alloc(gfp_mask, 0);
 	bio->bi_bdev = bdev;
-	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
+	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 
 	ret = submit_bio_wait(bio);
 
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 46fe924..ed89c8f 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -29,7 +29,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	struct request_queue *q = bdev_get_queue(bdev);
 	struct bio *bio = *biop;
 	unsigned int granularity;
-	enum req_op op;
+	unsigned int op;
 	int alignment;
 	sector_t bs_mask;
 
@@ -80,7 +80,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			req_sects = end_sect - sector;
 		}
 
-		bio = next_bio(bio, 1, gfp_mask);
+		bio = next_bio(bio, 0, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev = bdev;
 		bio_set_op_attrs(bio, op, 0);
@@ -137,24 +137,24 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 EXPORT_SYMBOL(blkdev_issue_discard);
 
 /**
- * blkdev_issue_write_same - queue a write same operation
+ * __blkdev_issue_write_same - generate number of bios with same page
  * @bdev:	target blockdev
  * @sector:	start sector
  * @nr_sects:	number of sectors to write
  * @gfp_mask:	memory allocation flags (for bio_alloc)
  * @page:	page containing data to write
+ * @biop:	pointer to anchor bio
  *
  * Description:
- *    Issue a write same request for the sectors in question.
+ *  Generate and issue number of bios(REQ_OP_WRITE_SAME) with same page.
  */
-int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
-			    sector_t nr_sects, gfp_t gfp_mask,
-			    struct page *page)
+static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, struct page *page,
+		struct bio **biop)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	unsigned int max_write_same_sectors;
-	struct bio *bio = NULL;
-	int ret = 0;
+	struct bio *bio = *biop;
 	sector_t bs_mask;
 
 	if (!q)
@@ -164,6 +164,9 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	if ((sector | nr_sects) & bs_mask)
 		return -EINVAL;
 
+	if (!bdev_write_same(bdev))
+		return -EOPNOTSUPP;
+
 	/* Ensure that max_write_same_sectors doesn't overflow bi_size */
 	max_write_same_sectors = UINT_MAX >> 9;
 
@@ -185,32 +188,112 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 			bio->bi_iter.bi_size = nr_sects << 9;
 			nr_sects = 0;
 		}
+		cond_resched();
 	}
 
-	if (bio) {
+	*biop = bio;
+	return 0;
+}
+
+/**
+ * blkdev_issue_write_same - queue a write same operation
+ * @bdev:	target blockdev
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to write
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @page:	page containing data
+ *
+ * Description:
+ *    Issue a write same request for the sectors in question.
+ */
+int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
+				sector_t nr_sects, gfp_t gfp_mask,
+				struct page *page)
+{
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret;
+
+	blk_start_plug(&plug);
+	ret = __blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask, page,
+			&bio);
+	if (ret == 0 && bio) {
 		ret = submit_bio_wait(bio);
 		bio_put(bio);
 	}
+	blk_finish_plug(&plug);
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_write_same);
 
 /**
- * blkdev_issue_zeroout - generate number of zero filed write bios
+ * __blkdev_issue_write_zeroes - generate number of bios with WRITE ZEROES
  * @bdev:	blockdev to issue
  * @sector:	start sector
  * @nr_sects:	number of sectors to write
  * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @biop:	pointer to anchor bio
  *
  * Description:
- *  Generate and issue number of bios with zerofiled pages.
+ *  Generate and issue number of bios(REQ_OP_WRITE_ZEROES) with zerofiled pages.
  */
+static int __blkdev_issue_write_zeroes(struct block_device *bdev,
+		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
+		struct bio **biop)
+{
+	struct bio *bio = *biop;
+	unsigned int max_write_zeroes_sectors;
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (!q)
+		return -ENXIO;
+
+	/* Ensure that max_write_zeroes_sectors doesn't overflow bi_size */
+	max_write_zeroes_sectors = bdev_write_zeroes_sectors(bdev);
+
+	if (max_write_zeroes_sectors == 0)
+		return -EOPNOTSUPP;
+
+	while (nr_sects) {
+		bio = next_bio(bio, 0, gfp_mask);
+		bio->bi_iter.bi_sector = sector;
+		bio->bi_bdev = bdev;
+		bio_set_op_attrs(bio, REQ_OP_WRITE_ZEROES, 0);
 
-static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-				  sector_t nr_sects, gfp_t gfp_mask)
+		if (nr_sects > max_write_zeroes_sectors) {
+			bio->bi_iter.bi_size = max_write_zeroes_sectors << 9;
+			nr_sects -= max_write_zeroes_sectors;
+			sector += max_write_zeroes_sectors;
+		} else {
+			bio->bi_iter.bi_size = nr_sects << 9;
+			nr_sects = 0;
+		}
+		cond_resched();
+	}
+
+	*biop = bio;
+	return 0;
+}
+
+/**
+ * __blkdev_issue_zeroout - generate number of zero filed write bios
+ * @bdev:	blockdev to issue
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to write
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @biop:	pointer to anchor bio
+ * @discard:	discard flag
+ *
+ * Description:
+ *  Generate and issue number of bios with zerofiled pages.
+ */
+int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
+		bool discard)
 {
 	int ret;
-	struct bio *bio = NULL;
+	int bi_size = 0;
+	struct bio *bio = *biop;
 	unsigned int sz;
 	sector_t bs_mask;
 
@@ -218,6 +301,24 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	if ((sector | nr_sects) & bs_mask)
 		return -EINVAL;
 
+	if (discard) {
+		ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
+				BLKDEV_DISCARD_ZERO, biop);
+		if (ret == 0 || (ret && ret != -EOPNOTSUPP))
+			goto out;
+	}
+
+	ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask,
+			biop);
+	if (ret == 0 || (ret && ret != -EOPNOTSUPP))
+		goto out;
+
+	ret = __blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
+			ZERO_PAGE(0), biop);
+	if (ret == 0 || (ret && ret != -EOPNOTSUPP))
+		goto out;
+
+	ret = 0;
 	while (nr_sects != 0) {
 		bio = next_bio(bio, min(nr_sects, (sector_t)BIO_MAX_PAGES),
 				gfp_mask);
@@ -227,21 +328,20 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 
 		while (nr_sects != 0) {
 			sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
-			ret = bio_add_page(bio, ZERO_PAGE(0), sz << 9, 0);
-			nr_sects -= ret >> 9;
-			sector += ret >> 9;
-			if (ret < (sz << 9))
+			bi_size = bio_add_page(bio, ZERO_PAGE(0), sz << 9, 0);
+			nr_sects -= bi_size >> 9;
+			sector += bi_size >> 9;
+			if (bi_size < (sz << 9))
 				break;
 		}
+		cond_resched();
 	}
 
-	if (bio) {
-		ret = submit_bio_wait(bio);
-		bio_put(bio);
-		return ret;
-	}
-	return 0;
+	*biop = bio;
+out:
+	return ret;
 }
+EXPORT_SYMBOL(__blkdev_issue_zeroout);
 
 /**
  * blkdev_issue_zeroout - zero-fill a block range
@@ -258,26 +358,27 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
  *  the discard request fail, if the discard flag is not set, or if
  *  discard_zeroes_data is not supported, this function will resort to
  *  zeroing the blocks manually, thus provisioning (allocating,
- *  anchoring) them. If the block device supports the WRITE SAME command
- *  blkdev_issue_zeroout() will use it to optimize the process of
+ *  anchoring) them. If the block device supports WRITE ZEROES or WRITE SAME
+ *  command(s), blkdev_issue_zeroout() will use it to optimize the process of
  *  clearing the block range. Otherwise the zeroing will be performed
  *  using regular WRITE calls.
  */
-
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			 sector_t nr_sects, gfp_t gfp_mask, bool discard)
 {
-	if (discard) {
-		if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
-				BLKDEV_DISCARD_ZERO))
-			return 0;
-	}
+	int ret;
+	struct bio *bio = NULL;
+	struct blk_plug plug;
 
-	if (bdev_write_same(bdev) &&
-	    blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
-				    ZERO_PAGE(0)) == 0)
-		return 0;
+	blk_start_plug(&plug);
+	ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask,
+			&bio, discard);
+	if (ret == 0 && bio) {
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
 
-	return __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask);
+	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_zeroout);
diff --git a/block/blk-map.c b/block/blk-map.c
index 27fd8d92..0acb664 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -16,6 +16,8 @@
 int blk_rq_append_bio(struct request *rq, struct bio *bio)
 {
 	if (!rq->bio) {
+		rq->cmd_flags &= REQ_OP_MASK;
+		rq->cmd_flags |= (bio->bi_opf & REQ_OP_MASK);
 		blk_rq_bio_prep(rq->q, rq, bio);
 	} else {
 		if (!ll_back_merge_fn(rq->q, rq, bio))
@@ -138,7 +140,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	} while (iov_iter_count(&i));
 
 	if (!bio_flagged(bio, BIO_USER_MAPPED))
-		rq->cmd_flags |= REQ_COPY_USER;
+		rq->rq_flags |= RQF_COPY_USER;
 	return 0;
 
 unmap_rq:
@@ -236,7 +238,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	if (do_copy)
-		rq->cmd_flags |= REQ_COPY_USER;
+		rq->rq_flags |= RQF_COPY_USER;
 
 	ret = blk_rq_append_bio(rq, bio);
 	if (unlikely(ret)) {
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 2642e5f..182398c 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -199,6 +199,10 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 	case REQ_OP_SECURE_ERASE:
 		split = blk_bio_discard_split(q, *bio, bs, &nsegs);
 		break;
+	case REQ_OP_WRITE_ZEROES:
+		split = NULL;
+		nsegs = (*bio)->bi_phys_segments;
+		break;
 	case REQ_OP_WRITE_SAME:
 		split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
 		break;
@@ -237,15 +241,14 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	if (!bio)
 		return 0;
 
-	/*
-	 * This should probably be returning 0, but blk_add_request_payload()
-	 * (Christoph!!!!)
-	 */
-	if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
-		return 1;
-
-	if (bio_op(bio) == REQ_OP_WRITE_SAME)
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+	case REQ_OP_WRITE_ZEROES:
+		return 0;
+	case REQ_OP_WRITE_SAME:
 		return 1;
+	}
 
 	fbio = bio;
 	cluster = blk_queue_cluster(q);
@@ -402,38 +405,21 @@ new_segment:
 	*bvprv = *bvec;
 }
 
+static inline int __blk_bvec_map_sg(struct request_queue *q, struct bio_vec bv,
+		struct scatterlist *sglist, struct scatterlist **sg)
+{
+	*sg = sglist;
+	sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
+	return 1;
+}
+
 static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 			     struct scatterlist *sglist,
 			     struct scatterlist **sg)
 {
 	struct bio_vec bvec, bvprv = { NULL };
 	struct bvec_iter iter;
-	int nsegs, cluster;
-
-	nsegs = 0;
-	cluster = blk_queue_cluster(q);
-
-	switch (bio_op(bio)) {
-	case REQ_OP_DISCARD:
-	case REQ_OP_SECURE_ERASE:
-		/*
-		 * This is a hack - drivers should be neither modifying the
-		 * biovec, nor relying on bi_vcnt - but because of
-		 * blk_add_request_payload(), a discard bio may or may not have
-		 * a payload we need to set up here (thank you Christoph) and
-		 * bi_vcnt is really the only way of telling if we need to.
-		 */
-		if (!bio->bi_vcnt)
-			return 0;
-		/* Fall through */
-	case REQ_OP_WRITE_SAME:
-		*sg = sglist;
-		bvec = bio_iovec(bio);
-		sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
-		return 1;
-	default:
-		break;
-	}
+	int cluster = blk_queue_cluster(q), nsegs = 0;
 
 	for_each_bio(bio)
 		bio_for_each_segment(bvec, bio, iter)
@@ -453,10 +439,14 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	struct scatterlist *sg = NULL;
 	int nsegs = 0;
 
-	if (rq->bio)
+	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+		nsegs = __blk_bvec_map_sg(q, rq->special_vec, sglist, &sg);
+	else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME)
+		nsegs = __blk_bvec_map_sg(q, bio_iovec(rq->bio), sglist, &sg);
+	else if (rq->bio)
 		nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg);
 
-	if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
+	if (unlikely(rq->rq_flags & RQF_COPY_USER) &&
 	    (blk_rq_bytes(rq) & q->dma_pad_mask)) {
 		unsigned int pad_len =
 			(q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1;
@@ -486,12 +476,19 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	 * Something must have been wrong if the figured number of
 	 * segment is bigger than number of req's physical segments
 	 */
-	WARN_ON(nsegs > rq->nr_phys_segments);
+	WARN_ON(nsegs > blk_rq_nr_phys_segments(rq));
 
 	return nsegs;
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
 
+static void req_set_nomerge(struct request_queue *q, struct request *req)
+{
+	req->cmd_flags |= REQ_NOMERGE;
+	if (req == q->last_merge)
+		q->last_merge = NULL;
+}
+
 static inline int ll_new_hw_segment(struct request_queue *q,
 				    struct request *req,
 				    struct bio *bio)
@@ -512,9 +509,7 @@ static inline int ll_new_hw_segment(struct request_queue *q,
 	return 1;
 
 no_merge:
-	req->cmd_flags |= REQ_NOMERGE;
-	if (req == q->last_merge)
-		q->last_merge = NULL;
+	req_set_nomerge(q, req);
 	return 0;
 }
 
@@ -528,9 +523,7 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
 	    blk_rq_get_max_sectors(req, blk_rq_pos(req))) {
-		req->cmd_flags |= REQ_NOMERGE;
-		if (req == q->last_merge)
-			q->last_merge = NULL;
+		req_set_nomerge(q, req);
 		return 0;
 	}
 	if (!bio_flagged(req->biotail, BIO_SEG_VALID))
@@ -552,9 +545,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
 	    blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) {
-		req->cmd_flags |= REQ_NOMERGE;
-		if (req == q->last_merge)
-			q->last_merge = NULL;
+		req_set_nomerge(q, req);
 		return 0;
 	}
 	if (!bio_flagged(bio, BIO_SEG_VALID))
@@ -634,7 +625,7 @@ void blk_rq_set_mixed_merge(struct request *rq)
 	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
 	struct bio *bio;
 
-	if (rq->cmd_flags & REQ_MIXED_MERGE)
+	if (rq->rq_flags & RQF_MIXED_MERGE)
 		return;
 
 	/*
@@ -647,7 +638,7 @@ void blk_rq_set_mixed_merge(struct request *rq)
 			     (bio->bi_opf & REQ_FAILFAST_MASK) != ff);
 		bio->bi_opf |= ff;
 	}
-	rq->cmd_flags |= REQ_MIXED_MERGE;
+	rq->rq_flags |= RQF_MIXED_MERGE;
 }
 
 static void blk_account_io_merge(struct request *req)
@@ -709,7 +700,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	 * makes sure that all involved bios have mixable attributes
 	 * set properly.
 	 */
-	if ((req->cmd_flags | next->cmd_flags) & REQ_MIXED_MERGE ||
+	if (((req->rq_flags | next->rq_flags) & RQF_MIXED_MERGE) ||
 	    (req->cmd_flags & REQ_FAILFAST_MASK) !=
 	    (next->cmd_flags & REQ_FAILFAST_MASK)) {
 		blk_rq_set_mixed_merge(req);
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 01fb455..eacd3af 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -259,6 +259,47 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 	return ret;
 }
 
+static void blk_mq_stat_clear(struct blk_mq_hw_ctx *hctx)
+{
+	struct blk_mq_ctx *ctx;
+	unsigned int i;
+
+	hctx_for_each_ctx(hctx, ctx, i) {
+		blk_stat_init(&ctx->stat[BLK_STAT_READ]);
+		blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
+	}
+}
+
+static ssize_t blk_mq_hw_sysfs_stat_store(struct blk_mq_hw_ctx *hctx,
+					  const char *page, size_t count)
+{
+	blk_mq_stat_clear(hctx);
+	return count;
+}
+
+static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre)
+{
+	return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n",
+			pre, (long long) stat->nr_samples,
+			(long long) stat->mean, (long long) stat->min,
+			(long long) stat->max);
+}
+
+static ssize_t blk_mq_hw_sysfs_stat_show(struct blk_mq_hw_ctx *hctx, char *page)
+{
+	struct blk_rq_stat stat[2];
+	ssize_t ret;
+
+	blk_stat_init(&stat[BLK_STAT_READ]);
+	blk_stat_init(&stat[BLK_STAT_WRITE]);
+
+	blk_hctx_stat_get(hctx, stat);
+
+	ret = print_stat(page, &stat[BLK_STAT_READ], "read :");
+	ret += print_stat(page + ret, &stat[BLK_STAT_WRITE], "write:");
+	return ret;
+}
+
 static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_dispatched = {
 	.attr = {.name = "dispatched", .mode = S_IRUGO },
 	.show = blk_mq_sysfs_dispatched_show,
@@ -317,6 +358,11 @@ static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_poll = {
 	.show = blk_mq_hw_sysfs_poll_show,
 	.store = blk_mq_hw_sysfs_poll_store,
 };
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_stat = {
+	.attr = {.name = "stats", .mode = S_IRUGO | S_IWUSR },
+	.show = blk_mq_hw_sysfs_stat_show,
+	.store = blk_mq_hw_sysfs_stat_store,
+};
 
 static struct attribute *default_hw_ctx_attrs[] = {
 	&blk_mq_hw_sysfs_queued.attr,
@@ -327,6 +373,7 @@ static struct attribute *default_hw_ctx_attrs[] = {
 	&blk_mq_hw_sysfs_cpus.attr,
 	&blk_mq_hw_sysfs_active.attr,
 	&blk_mq_hw_sysfs_poll.attr,
+	&blk_mq_hw_sysfs_stat.attr,
 	NULL,
 };
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f3d27a6..d79fdc1 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -30,6 +30,8 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
+#include "blk-stat.h"
+#include "blk-wbt.h"
 
 static DEFINE_MUTEX(all_q_mutex);
 static LIST_HEAD(all_q_list);
@@ -115,6 +117,33 @@ void blk_mq_unfreeze_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
 
+/**
+ * blk_mq_quiesce_queue() - wait until all ongoing queue_rq calls have finished
+ * @q: request queue.
+ *
+ * Note: this function does not prevent that the struct request end_io()
+ * callback function is invoked. Additionally, it is not prevented that
+ * new queue_rq() calls occur unless the queue has been stopped first.
+ */
+void blk_mq_quiesce_queue(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+	bool rcu = false;
+
+	blk_mq_stop_hw_queues(q);
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (hctx->flags & BLK_MQ_F_BLOCKING)
+			synchronize_srcu(&hctx->queue_rq_srcu);
+		else
+			rcu = true;
+	}
+	if (rcu)
+		synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
+
 void blk_mq_wake_waiters(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
@@ -139,17 +168,15 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 EXPORT_SYMBOL(blk_mq_can_queue);
 
 static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
-			       struct request *rq, int op,
-			       unsigned int op_flags)
+			       struct request *rq, unsigned int op)
 {
-	if (blk_queue_io_stat(q))
-		op_flags |= REQ_IO_STAT;
-
 	INIT_LIST_HEAD(&rq->queuelist);
 	/* csd/requeue_work/fifo_time is initialized before use */
 	rq->q = q;
 	rq->mq_ctx = ctx;
-	req_set_op_attrs(rq, op, op_flags);
+	rq->cmd_flags = op;
+	if (blk_queue_io_stat(q))
+		rq->rq_flags |= RQF_IO_STAT;
 	/* do not touch atomic flags, it needs atomic ops against the timer */
 	rq->cpu = -1;
 	INIT_HLIST_NODE(&rq->hash);
@@ -184,11 +211,11 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->end_io_data = NULL;
 	rq->next_rq = NULL;
 
-	ctx->rq_dispatched[rw_is_sync(op, op_flags)]++;
+	ctx->rq_dispatched[op_is_sync(op)]++;
 }
 
 static struct request *
-__blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags)
+__blk_mq_alloc_request(struct blk_mq_alloc_data *data, unsigned int op)
 {
 	struct request *rq;
 	unsigned int tag;
@@ -198,12 +225,12 @@ __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags)
 		rq = data->hctx->tags->rqs[tag];
 
 		if (blk_mq_tag_busy(data->hctx)) {
-			rq->cmd_flags = REQ_MQ_INFLIGHT;
+			rq->rq_flags = RQF_MQ_INFLIGHT;
 			atomic_inc(&data->hctx->nr_active);
 		}
 
 		rq->tag = tag;
-		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op, op_flags);
+		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op);
 		return rq;
 	}
 
@@ -226,7 +253,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 	ctx = blk_mq_get_ctx(q);
 	hctx = blk_mq_map_queue(q, ctx->cpu);
 	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
+	rq = __blk_mq_alloc_request(&alloc_data, rw);
 	blk_mq_put_ctx(ctx);
 
 	if (!rq) {
@@ -278,7 +305,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
 	ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask));
 
 	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
+	rq = __blk_mq_alloc_request(&alloc_data, rw);
 	if (!rq) {
 		ret = -EWOULDBLOCK;
 		goto out_queue_exit;
@@ -298,11 +325,14 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
 	const int tag = rq->tag;
 	struct request_queue *q = rq->q;
 
-	if (rq->cmd_flags & REQ_MQ_INFLIGHT)
+	if (rq->rq_flags & RQF_MQ_INFLIGHT)
 		atomic_dec(&hctx->nr_active);
-	rq->cmd_flags = 0;
+
+	wbt_done(q->rq_wb, &rq->issue_stat);
+	rq->rq_flags = 0;
 
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+	clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
 	blk_mq_put_tag(hctx, ctx, tag);
 	blk_queue_exit(q);
 }
@@ -328,6 +358,7 @@ inline void __blk_mq_end_request(struct request *rq, int error)
 	blk_account_io_done(rq);
 
 	if (rq->end_io) {
+		wbt_done(rq->q->rq_wb, &rq->issue_stat);
 		rq->end_io(rq, error);
 	} else {
 		if (unlikely(blk_bidi_rq(rq)))
@@ -378,10 +409,27 @@ static void blk_mq_ipi_complete_request(struct request *rq)
 	put_cpu();
 }
 
+static void blk_mq_stat_add(struct request *rq)
+{
+	if (rq->rq_flags & RQF_STATS) {
+		/*
+		 * We could rq->mq_ctx here, but there's less of a risk
+		 * of races if we have the completion event add the stats
+		 * to the local software queue.
+		 */
+		struct blk_mq_ctx *ctx;
+
+		ctx = __blk_mq_get_ctx(rq->q, raw_smp_processor_id());
+		blk_stat_add(&ctx->stat[rq_data_dir(rq)], rq);
+	}
+}
+
 static void __blk_mq_complete_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
+	blk_mq_stat_add(rq);
+
 	if (!q->softirq_done_fn)
 		blk_mq_end_request(rq, rq->errors);
 	else
@@ -425,6 +473,12 @@ void blk_mq_start_request(struct request *rq)
 	if (unlikely(blk_bidi_rq(rq)))
 		rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq);
 
+	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
+		blk_stat_set_issue_time(&rq->issue_stat);
+		rq->rq_flags |= RQF_STATS;
+		wbt_issue(q->rq_wb, &rq->issue_stat);
+	}
+
 	blk_add_timer(rq);
 
 	/*
@@ -460,6 +514,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 	struct request_queue *q = rq->q;
 
 	trace_block_rq_requeue(q, rq);
+	wbt_requeue(q->rq_wb, &rq->issue_stat);
 
 	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
 		if (q->dma_drain_size && blk_rq_bytes(rq))
@@ -467,12 +522,12 @@ static void __blk_mq_requeue_request(struct request *rq)
 	}
 }
 
-void blk_mq_requeue_request(struct request *rq)
+void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
 {
 	__blk_mq_requeue_request(rq);
 
 	BUG_ON(blk_queued_rq(rq));
-	blk_mq_add_to_requeue_list(rq, true);
+	blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
 }
 EXPORT_SYMBOL(blk_mq_requeue_request);
 
@@ -489,10 +544,10 @@ static void blk_mq_requeue_work(struct work_struct *work)
 	spin_unlock_irqrestore(&q->requeue_lock, flags);
 
 	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
-		if (!(rq->cmd_flags & REQ_SOFTBARRIER))
+		if (!(rq->rq_flags & RQF_SOFTBARRIER))
 			continue;
 
-		rq->cmd_flags &= ~REQ_SOFTBARRIER;
+		rq->rq_flags &= ~RQF_SOFTBARRIER;
 		list_del_init(&rq->queuelist);
 		blk_mq_insert_request(rq, true, false, false);
 	}
@@ -503,14 +558,11 @@ static void blk_mq_requeue_work(struct work_struct *work)
 		blk_mq_insert_request(rq, false, false, false);
 	}
 
-	/*
-	 * Use the start variant of queue running here, so that running
-	 * the requeue work will kick stopped queues.
-	 */
-	blk_mq_start_hw_queues(q);
+	blk_mq_run_hw_queues(q, false);
 }
 
-void blk_mq_add_to_requeue_list(struct request *rq, bool at_head)
+void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
+				bool kick_requeue_list)
 {
 	struct request_queue *q = rq->q;
 	unsigned long flags;
@@ -519,24 +571,21 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head)
 	 * We abuse this flag that is otherwise used by the I/O scheduler to
 	 * request head insertation from the workqueue.
 	 */
-	BUG_ON(rq->cmd_flags & REQ_SOFTBARRIER);
+	BUG_ON(rq->rq_flags & RQF_SOFTBARRIER);
 
 	spin_lock_irqsave(&q->requeue_lock, flags);
 	if (at_head) {
-		rq->cmd_flags |= REQ_SOFTBARRIER;
+		rq->rq_flags |= RQF_SOFTBARRIER;
 		list_add(&rq->queuelist, &q->requeue_list);
 	} else {
 		list_add_tail(&rq->queuelist, &q->requeue_list);
 	}
 	spin_unlock_irqrestore(&q->requeue_lock, flags);
-}
-EXPORT_SYMBOL(blk_mq_add_to_requeue_list);
 
-void blk_mq_cancel_requeue_work(struct request_queue *q)
-{
-	cancel_delayed_work_sync(&q->requeue_work);
+	if (kick_requeue_list)
+		blk_mq_kick_requeue_list(q);
 }
-EXPORT_SYMBOL_GPL(blk_mq_cancel_requeue_work);
+EXPORT_SYMBOL(blk_mq_add_to_requeue_list);
 
 void blk_mq_kick_requeue_list(struct request_queue *q)
 {
@@ -772,44 +821,13 @@ static inline unsigned int queued_to_index(unsigned int queued)
 	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
 }
 
-/*
- * Run this hardware queue, pulling any software queues mapped to it in.
- * Note that this function currently has various problems around ordering
- * of IO. In particular, we'd like FIFO behaviour on handling existing
- * items on the hctx->dispatch list. Ignore that for now.
- */
-static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
+bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 {
 	struct request_queue *q = hctx->queue;
 	struct request *rq;
-	LIST_HEAD(rq_list);
 	LIST_HEAD(driver_list);
 	struct list_head *dptr;
-	int queued;
-
-	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
-		return;
-
-	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
-		cpu_online(hctx->next_cpu));
-
-	hctx->run++;
-
-	/*
-	 * Touch any software queue that has pending entries.
-	 */
-	flush_busy_ctxs(hctx, &rq_list);
-
-	/*
-	 * If we have previous entries on our dispatch list, grab them
-	 * and stuff them at the front for more fair dispatch.
-	 */
-	if (!list_empty_careful(&hctx->dispatch)) {
-		spin_lock(&hctx->lock);
-		if (!list_empty(&hctx->dispatch))
-			list_splice_init(&hctx->dispatch, &rq_list);
-		spin_unlock(&hctx->lock);
-	}
+	int queued, ret = BLK_MQ_RQ_QUEUE_OK;
 
 	/*
 	 * Start off with dptr being NULL, so we start the first request
@@ -821,16 +839,15 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	 * Now process all the entries, sending them to the driver.
 	 */
 	queued = 0;
-	while (!list_empty(&rq_list)) {
+	while (!list_empty(list)) {
 		struct blk_mq_queue_data bd;
-		int ret;
 
-		rq = list_first_entry(&rq_list, struct request, queuelist);
+		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;
 		bd.list = dptr;
-		bd.last = list_empty(&rq_list);
+		bd.last = list_empty(list);
 
 		ret = q->mq_ops->queue_rq(hctx, &bd);
 		switch (ret) {
@@ -838,7 +855,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 			queued++;
 			break;
 		case BLK_MQ_RQ_QUEUE_BUSY:
-			list_add(&rq->queuelist, &rq_list);
+			list_add(&rq->queuelist, list);
 			__blk_mq_requeue_request(rq);
 			break;
 		default:
@@ -856,7 +873,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		 * We've done the first request. If we have more than 1
 		 * left in the list, set dptr to defer issue.
 		 */
-		if (!dptr && rq_list.next != rq_list.prev)
+		if (!dptr && list->next != list->prev)
 			dptr = &driver_list;
 	}
 
@@ -866,10 +883,11 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	 * Any items that need requeuing? Stuff them into hctx->dispatch,
 	 * that is where we will continue on next queue run.
 	 */
-	if (!list_empty(&rq_list)) {
+	if (!list_empty(list)) {
 		spin_lock(&hctx->lock);
-		list_splice(&rq_list, &hctx->dispatch);
+		list_splice(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
+
 		/*
 		 * the queue is expected stopped with BLK_MQ_RQ_QUEUE_BUSY, but
 		 * it's possible the queue is stopped and restarted again
@@ -881,6 +899,61 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		 **/
 		blk_mq_run_hw_queue(hctx, true);
 	}
+
+	return ret != BLK_MQ_RQ_QUEUE_BUSY;
+}
+
+/*
+ * Run this hardware queue, pulling any software queues mapped to it in.
+ * Note that this function currently has various problems around ordering
+ * of IO. In particular, we'd like FIFO behaviour on handling existing
+ * items on the hctx->dispatch list. Ignore that for now.
+ */
+static void blk_mq_process_rq_list(struct blk_mq_hw_ctx *hctx)
+{
+	LIST_HEAD(rq_list);
+	LIST_HEAD(driver_list);
+
+	if (unlikely(blk_mq_hctx_stopped(hctx)))
+		return;
+
+	hctx->run++;
+
+	/*
+	 * Touch any software queue that has pending entries.
+	 */
+	flush_busy_ctxs(hctx, &rq_list);
+
+	/*
+	 * If we have previous entries on our dispatch list, grab them
+	 * and stuff them at the front for more fair dispatch.
+	 */
+	if (!list_empty_careful(&hctx->dispatch)) {
+		spin_lock(&hctx->lock);
+		if (!list_empty(&hctx->dispatch))
+			list_splice_init(&hctx->dispatch, &rq_list);
+		spin_unlock(&hctx->lock);
+	}
+
+	blk_mq_dispatch_rq_list(hctx, &rq_list);
+}
+
+static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
+{
+	int srcu_idx;
+
+	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
+		cpu_online(hctx->next_cpu));
+
+	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
+		rcu_read_lock();
+		blk_mq_process_rq_list(hctx);
+		rcu_read_unlock();
+	} else {
+		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
+		blk_mq_process_rq_list(hctx);
+		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
+	}
 }
 
 /*
@@ -895,7 +968,7 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 		return WORK_CPU_UNBOUND;
 
 	if (--hctx->next_cpu_batch <= 0) {
-		int cpu = hctx->next_cpu, next_cpu;
+		int next_cpu;
 
 		next_cpu = cpumask_next(hctx->next_cpu, hctx->cpumask);
 		if (next_cpu >= nr_cpu_ids)
@@ -903,8 +976,6 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 
 		hctx->next_cpu = next_cpu;
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
-
-		return cpu;
 	}
 
 	return hctx->next_cpu;
@@ -912,8 +983,8 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
-	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state) ||
-	    !blk_mq_hw_queue_mapped(hctx)))
+	if (unlikely(blk_mq_hctx_stopped(hctx) ||
+		     !blk_mq_hw_queue_mapped(hctx)))
 		return;
 
 	if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
@@ -938,7 +1009,7 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if ((!blk_mq_hctx_has_pending(hctx) &&
 		    list_empty_careful(&hctx->dispatch)) ||
-		    test_bit(BLK_MQ_S_STOPPED, &hctx->state))
+		    blk_mq_hctx_stopped(hctx))
 			continue;
 
 		blk_mq_run_hw_queue(hctx, async);
@@ -946,6 +1017,26 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queues);
 
+/**
+ * blk_mq_queue_stopped() - check whether one or more hctxs have been stopped
+ * @q: request queue.
+ *
+ * The caller is responsible for serializing this function against
+ * blk_mq_{start,stop}_hw_queue().
+ */
+bool blk_mq_queue_stopped(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		if (blk_mq_hctx_stopped(hctx))
+			return true;
+
+	return false;
+}
+EXPORT_SYMBOL(blk_mq_queue_stopped);
+
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
 	cancel_work(&hctx->run_work);
@@ -982,18 +1073,23 @@ void blk_mq_start_hw_queues(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_mq_start_hw_queues);
 
+void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+{
+	if (!blk_mq_hctx_stopped(hctx))
+		return;
+
+	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+	blk_mq_run_hw_queue(hctx, async);
+}
+EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue);
+
 void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	queue_for_each_hw_ctx(q, hctx, i) {
-		if (!test_bit(BLK_MQ_S_STOPPED, &hctx->state))
-			continue;
-
-		clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
-		blk_mq_run_hw_queue(hctx, async);
-	}
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_start_stopped_hw_queue(hctx, async);
 }
 EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);
 
@@ -1155,7 +1251,7 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
 {
 	init_request_from_bio(rq, bio);
 
-	blk_account_io_start(rq, 1);
+	blk_account_io_start(rq, true);
 }
 
 static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx)
@@ -1190,40 +1286,27 @@ insert_rq:
 	}
 }
 
-struct blk_map_ctx {
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx;
-};
-
 static struct request *blk_mq_map_request(struct request_queue *q,
 					  struct bio *bio,
-					  struct blk_map_ctx *data)
+					  struct blk_mq_alloc_data *data)
 {
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct request *rq;
-	int op = bio_data_dir(bio);
-	int op_flags = 0;
-	struct blk_mq_alloc_data alloc_data;
 
 	blk_queue_enter_live(q);
 	ctx = blk_mq_get_ctx(q);
 	hctx = blk_mq_map_queue(q, ctx->cpu);
 
-	if (rw_is_sync(bio_op(bio), bio->bi_opf))
-		op_flags |= REQ_SYNC;
+	trace_block_getrq(q, bio, bio->bi_opf);
+	blk_mq_set_alloc_data(data, q, 0, ctx, hctx);
+	rq = __blk_mq_alloc_request(data, bio->bi_opf);
 
-	trace_block_getrq(q, bio, op);
-	blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);
-
-	data->hctx = alloc_data.hctx;
-	data->ctx = alloc_data.ctx;
 	data->hctx->queued++;
 	return rq;
 }
 
-static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)
+static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
 {
 	int ret;
 	struct request_queue *q = rq->q;
@@ -1235,6 +1318,9 @@ static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)
 	};
 	blk_qc_t new_cookie = blk_tag_to_qc_t(rq->tag, hctx->queue_num);
 
+	if (blk_mq_hctx_stopped(hctx))
+		goto insert;
+
 	/*
 	 * For OK queue, we are done. For error, kill it. Any other
 	 * error (busy), just add it to our list as we previously
@@ -1243,7 +1329,7 @@ static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)
 	ret = q->mq_ops->queue_rq(hctx, &bd);
 	if (ret == BLK_MQ_RQ_QUEUE_OK) {
 		*cookie = new_cookie;
-		return 0;
+		return;
 	}
 
 	__blk_mq_requeue_request(rq);
@@ -1252,10 +1338,11 @@ static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)
 		*cookie = BLK_QC_T_NONE;
 		rq->errors = -EIO;
 		blk_mq_end_request(rq, rq->errors);
-		return 0;
+		return;
 	}
 
-	return -1;
+insert:
+	blk_mq_insert_request(rq, false, true, true);
 }
 
 /*
@@ -1265,14 +1352,15 @@ static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)
  */
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf);
+	const int is_sync = op_is_sync(bio->bi_opf);
 	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
-	struct blk_map_ctx data;
+	struct blk_mq_alloc_data data;
 	struct request *rq;
-	unsigned int request_count = 0;
+	unsigned int request_count = 0, srcu_idx;
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
 	blk_qc_t cookie;
+	unsigned int wb_acct;
 
 	blk_queue_bounce(q, &bio);
 
@@ -1287,9 +1375,15 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
 		return BLK_QC_T_NONE;
 
+	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
+
 	rq = blk_mq_map_request(q, bio, &data);
-	if (unlikely(!rq))
+	if (unlikely(!rq)) {
+		__wbt_done(q->rq_wb, wb_acct);
 		return BLK_QC_T_NONE;
+	}
+
+	wbt_track(&rq->issue_stat, wb_acct);
 
 	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
 
@@ -1312,7 +1406,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_bio_to_request(rq, bio);
 
 		/*
-		 * We do limited pluging. If the bio can be merged, do that.
+		 * We do limited plugging. If the bio can be merged, do that.
 		 * Otherwise the existing request in the plug list will be
 		 * issued. So the plug list will have one request at most
 		 */
@@ -1332,9 +1426,16 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_put_ctx(data.ctx);
 		if (!old_rq)
 			goto done;
-		if (!blk_mq_direct_issue_request(old_rq, &cookie))
-			goto done;
-		blk_mq_insert_request(old_rq, false, true, true);
+
+		if (!(data.hctx->flags & BLK_MQ_F_BLOCKING)) {
+			rcu_read_lock();
+			blk_mq_try_issue_directly(old_rq, &cookie);
+			rcu_read_unlock();
+		} else {
+			srcu_idx = srcu_read_lock(&data.hctx->queue_rq_srcu);
+			blk_mq_try_issue_directly(old_rq, &cookie);
+			srcu_read_unlock(&data.hctx->queue_rq_srcu, srcu_idx);
+		}
 		goto done;
 	}
 
@@ -1359,13 +1460,14 @@ done:
  */
 static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf);
+	const int is_sync = op_is_sync(bio->bi_opf);
 	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
 	struct blk_plug *plug;
 	unsigned int request_count = 0;
-	struct blk_map_ctx data;
+	struct blk_mq_alloc_data data;
 	struct request *rq;
 	blk_qc_t cookie;
+	unsigned int wb_acct;
 
 	blk_queue_bounce(q, &bio);
 
@@ -1382,9 +1484,15 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	} else
 		request_count = blk_plug_queued_count(q);
 
+	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
+
 	rq = blk_mq_map_request(q, bio, &data);
-	if (unlikely(!rq))
+	if (unlikely(!rq)) {
+		__wbt_done(q->rq_wb, wb_acct);
 		return BLK_QC_T_NONE;
+	}
+
+	wbt_track(&rq->issue_stat, wb_acct);
 
 	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
 
@@ -1401,13 +1509,25 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	 */
 	plug = current->plug;
 	if (plug) {
+		struct request *last = NULL;
+
 		blk_mq_bio_to_request(rq, bio);
+
+		/*
+		 * @request_count may become stale because of schedule
+		 * out, so check the list again.
+		 */
+		if (list_empty(&plug->mq_list))
+			request_count = 0;
 		if (!request_count)
 			trace_block_plug(q);
+		else
+			last = list_entry_rq(plug->mq_list.prev);
 
 		blk_mq_put_ctx(data.ctx);
 
-		if (request_count >= BLK_MAX_REQUEST_COUNT) {
+		if (request_count >= BLK_MAX_REQUEST_COUNT || (last &&
+		    blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
 			blk_flush_plug_list(plug, false);
 			trace_block_plug(q);
 		}
@@ -1613,6 +1733,9 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
 
+	if (hctx->flags & BLK_MQ_F_BLOCKING)
+		cleanup_srcu_struct(&hctx->queue_rq_srcu);
+
 	blk_mq_remove_cpuhp(hctx);
 	blk_free_flush_queue(hctx->fq);
 	sbitmap_free(&hctx->ctx_map);
@@ -1693,6 +1816,9 @@ static int blk_mq_init_hctx(struct request_queue *q,
 				   flush_start_tag + hctx_idx, node))
 		goto free_fq;
 
+	if (hctx->flags & BLK_MQ_F_BLOCKING)
+		init_srcu_struct(&hctx->queue_rq_srcu);
+
 	return 0;
 
  free_fq:
@@ -1723,6 +1849,8 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 		spin_lock_init(&__ctx->lock);
 		INIT_LIST_HEAD(&__ctx->rq_list);
 		__ctx->queue = q;
+		blk_stat_init(&__ctx->stat[BLK_STAT_READ]);
+		blk_stat_init(&__ctx->stat[BLK_STAT_WRITE]);
 
 		/* If the cpu isn't online, the cpu is mapped to first hctx */
 		if (!cpu_online(i))
@@ -2018,6 +2146,11 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	 */
 	q->nr_requests = set->queue_depth;
 
+	/*
+	 * Default to classic polling
+	 */
+	q->poll_nsec = -1;
+
 	if (set->ops->complete)
 		blk_queue_softirq_done(q, set->ops->complete);
 
@@ -2053,6 +2186,8 @@ void blk_mq_free_queue(struct request_queue *q)
 	list_del_init(&q->all_q_node);
 	mutex_unlock(&all_q_mutex);
 
+	wbt_exit(q);
+
 	blk_mq_del_queue_tag_set(q);
 
 	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
@@ -2099,16 +2234,9 @@ static void blk_mq_queue_reinit_work(void)
 	 */
 	list_for_each_entry(q, &all_q_list, all_q_node)
 		blk_mq_freeze_queue_start(q);
-	list_for_each_entry(q, &all_q_list, all_q_node) {
+	list_for_each_entry(q, &all_q_list, all_q_node)
 		blk_mq_freeze_queue_wait(q);
 
-		/*
-		 * timeout handler can't touch hw queue during the
-		 * reinitialization
-		 */
-		del_timer_sync(&q->timeout);
-	}
-
 	list_for_each_entry(q, &all_q_list, all_q_node)
 		blk_mq_queue_reinit(q, &cpuhp_online_new);
 
@@ -2353,6 +2481,165 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 }
 EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
 
+static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
+				       struct blk_mq_hw_ctx *hctx,
+				       struct request *rq)
+{
+	struct blk_rq_stat stat[2];
+	unsigned long ret = 0;
+
+	/*
+	 * If stats collection isn't on, don't sleep but turn it on for
+	 * future users
+	 */
+	if (!blk_stat_enable(q))
+		return 0;
+
+	/*
+	 * We don't have to do this once per IO, should optimize this
+	 * to just use the current window of stats until it changes
+	 */
+	memset(&stat, 0, sizeof(stat));
+	blk_hctx_stat_get(hctx, stat);
+
+	/*
+	 * As an optimistic guess, use half of the mean service time
+	 * for this type of request. We can (and should) make this smarter.
+	 * For instance, if the completion latencies are tight, we can
+	 * get closer than just half the mean. This is especially
+	 * important on devices where the completion latencies are longer
+	 * than ~10 usec.
+	 */
+	if (req_op(rq) == REQ_OP_READ && stat[BLK_STAT_READ].nr_samples)
+		ret = (stat[BLK_STAT_READ].mean + 1) / 2;
+	else if (req_op(rq) == REQ_OP_WRITE && stat[BLK_STAT_WRITE].nr_samples)
+		ret = (stat[BLK_STAT_WRITE].mean + 1) / 2;
+
+	return ret;
+}
+
+static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
+				     struct blk_mq_hw_ctx *hctx,
+				     struct request *rq)
+{
+	struct hrtimer_sleeper hs;
+	enum hrtimer_mode mode;
+	unsigned int nsecs;
+	ktime_t kt;
+
+	if (test_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags))
+		return false;
+
+	/*
+	 * poll_nsec can be:
+	 *
+	 * -1:	don't ever hybrid sleep
+	 *  0:	use half of prev avg
+	 * >0:	use this specific value
+	 */
+	if (q->poll_nsec == -1)
+		return false;
+	else if (q->poll_nsec > 0)
+		nsecs = q->poll_nsec;
+	else
+		nsecs = blk_mq_poll_nsecs(q, hctx, rq);
+
+	if (!nsecs)
+		return false;
+
+	set_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
+
+	/*
+	 * This will be replaced with the stats tracking code, using
+	 * 'avg_completion_time / 2' as the pre-sleep target.
+	 */
+	kt = ktime_set(0, nsecs);
+
+	mode = HRTIMER_MODE_REL;
+	hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode);
+	hrtimer_set_expires(&hs.timer, kt);
+
+	hrtimer_init_sleeper(&hs, current);
+	do {
+		if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags))
+			break;
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		hrtimer_start_expires(&hs.timer, mode);
+		if (hs.task)
+			io_schedule();
+		hrtimer_cancel(&hs.timer);
+		mode = HRTIMER_MODE_ABS;
+	} while (hs.task && !signal_pending(current));
+
+	__set_current_state(TASK_RUNNING);
+	destroy_hrtimer_on_stack(&hs.timer);
+	return true;
+}
+
+static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq)
+{
+	struct request_queue *q = hctx->queue;
+	long state;
+
+	/*
+	 * If we sleep, have the caller restart the poll loop to reset
+	 * the state. Like for the other success return cases, the
+	 * caller is responsible for checking if the IO completed. If
+	 * the IO isn't complete, we'll get called again and will go
+	 * straight to the busy poll loop.
+	 */
+	if (blk_mq_poll_hybrid_sleep(q, hctx, rq))
+		return true;
+
+	hctx->poll_considered++;
+
+	state = current->state;
+	while (!need_resched()) {
+		int ret;
+
+		hctx->poll_invoked++;
+
+		ret = q->mq_ops->poll(hctx, rq->tag);
+		if (ret > 0) {
+			hctx->poll_success++;
+			set_current_state(TASK_RUNNING);
+			return true;
+		}
+
+		if (signal_pending_state(state, current))
+			set_current_state(TASK_RUNNING);
+
+		if (current->state == TASK_RUNNING)
+			return true;
+		if (ret < 0)
+			break;
+		cpu_relax();
+	}
+
+	return false;
+}
+
+bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_plug *plug;
+	struct request *rq;
+
+	if (!q->mq_ops || !q->mq_ops->poll || !blk_qc_t_valid(cookie) ||
+	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+		return false;
+
+	plug = current->plug;
+	if (plug)
+		blk_flush_plug_list(plug, false);
+
+	hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
+	rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
+
+	return __blk_mq_poll(hctx, rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_poll);
+
 void blk_mq_disable_hotplug(void)
 {
 	mutex_lock(&all_q_mutex);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index e5d2524..3a54dd3 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -1,6 +1,8 @@
 #ifndef INT_BLK_MQ_H
 #define INT_BLK_MQ_H
 
+#include "blk-stat.h"
+
 struct blk_mq_tag_set;
 
 struct blk_mq_ctx {
@@ -18,6 +20,7 @@ struct blk_mq_ctx {
 
 	/* incremented at completion time */
 	unsigned long		____cacheline_aligned_in_smp rq_completed[2];
+	struct blk_rq_stat	stat[2];
 
 	struct request_queue	*queue;
 	struct kobject		kobj;
@@ -28,6 +31,7 @@ void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
+bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *, struct list_head *);
 
 /*
  * CPU hotplug helpers
@@ -100,6 +104,11 @@ static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
 	data->hctx = hctx;
 }
 
+static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
+{
+	return test_bit(BLK_MQ_S_STOPPED, &hctx->state);
+}
+
 static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
 {
 	return hctx->nr_ctx && hctx->tags;
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 65f16cf..529e55f 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -13,6 +13,7 @@
 #include <linux/gfp.h>
 
 #include "blk.h"
+#include "blk-wbt.h"
 
 unsigned long blk_max_low_pfn;
 EXPORT_SYMBOL(blk_max_low_pfn);
@@ -95,6 +96,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->max_dev_sectors = 0;
 	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
+	lim->max_write_zeroes_sectors = 0;
 	lim->max_discard_sectors = 0;
 	lim->max_hw_discard_sectors = 0;
 	lim->discard_granularity = 0;
@@ -107,6 +109,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->io_opt = 0;
 	lim->misaligned = 0;
 	lim->cluster = 1;
+	lim->zoned = BLK_ZONED_NONE;
 }
 EXPORT_SYMBOL(blk_set_default_limits);
 
@@ -130,6 +133,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->max_sectors = UINT_MAX;
 	lim->max_dev_sectors = UINT_MAX;
 	lim->max_write_same_sectors = UINT_MAX;
+	lim->max_write_zeroes_sectors = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
 
@@ -299,6 +303,19 @@ void blk_queue_max_write_same_sectors(struct request_queue *q,
 EXPORT_SYMBOL(blk_queue_max_write_same_sectors);
 
 /**
+ * blk_queue_max_write_zeroes_sectors - set max sectors for a single
+ *                                      write zeroes
+ * @q:  the request queue for the device
+ * @max_write_zeroes_sectors: maximum number of sectors to write per command
+ **/
+void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
+		unsigned int max_write_zeroes_sectors)
+{
+	q->limits.max_write_zeroes_sectors = max_write_zeroes_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors);
+
+/**
  * blk_queue_max_segments - set max hw segments for a request for this queue
  * @q:  the request queue for the device
  * @max_segments:  max number of segments
@@ -526,6 +543,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
 	t->max_write_same_sectors = min(t->max_write_same_sectors,
 					b->max_write_same_sectors);
+	t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
+					b->max_write_zeroes_sectors);
 	t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
 
 	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
@@ -631,6 +650,10 @@ 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);
+
 	return ret;
 }
 EXPORT_SYMBOL(blk_stack_limits);
@@ -833,6 +856,19 @@ void blk_queue_flush_queueable(struct request_queue *q, bool queueable)
 EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
 
 /**
+ * blk_set_queue_depth - tell the block layer about the device queue depth
+ * @q:		the request queue for the device
+ * @depth:		queue depth
+ *
+ */
+void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
+{
+	q->queue_depth = depth;
+	wbt_set_queue_depth(q->rq_wb, depth);
+}
+EXPORT_SYMBOL(blk_set_queue_depth);
+
+/**
  * blk_queue_write_cache - configure queue's write cache
  * @q:		the request queue for the device
  * @wc:		write back cache on or off
@@ -852,6 +888,8 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 	else
 		queue_flag_clear(QUEUE_FLAG_FUA, q);
 	spin_unlock_irq(q->queue_lock);
+
+	wbt_set_write_cache(q->rq_wb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 }
 EXPORT_SYMBOL_GPL(blk_queue_write_cache);
 
diff --git a/block/blk-stat.c b/block/blk-stat.c
new file mode 100644
index 0000000..9b43efb
--- /dev/null
+++ b/block/blk-stat.c
@@ -0,0 +1,256 @@
+/*
+ * Block stat tracking code
+ *
+ * Copyright (C) 2016 Jens Axboe
+ */
+#include <linux/kernel.h>
+#include <linux/blk-mq.h>
+
+#include "blk-stat.h"
+#include "blk-mq.h"
+
+static void blk_stat_flush_batch(struct blk_rq_stat *stat)
+{
+	const s32 nr_batch = READ_ONCE(stat->nr_batch);
+	const s32 nr_samples = READ_ONCE(stat->nr_samples);
+
+	if (!nr_batch)
+		return;
+	if (!nr_samples)
+		stat->mean = div64_s64(stat->batch, nr_batch);
+	else {
+		stat->mean = div64_s64((stat->mean * nr_samples) +
+					stat->batch,
+					nr_batch + nr_samples);
+	}
+
+	stat->nr_samples += nr_batch;
+	stat->nr_batch = stat->batch = 0;
+}
+
+static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
+{
+	if (!src->nr_samples)
+		return;
+
+	blk_stat_flush_batch(src);
+
+	dst->min = min(dst->min, src->min);
+	dst->max = max(dst->max, src->max);
+
+	if (!dst->nr_samples)
+		dst->mean = src->mean;
+	else {
+		dst->mean = div64_s64((src->mean * src->nr_samples) +
+					(dst->mean * dst->nr_samples),
+					dst->nr_samples + src->nr_samples);
+	}
+	dst->nr_samples += src->nr_samples;
+}
+
+static void blk_mq_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	uint64_t latest = 0;
+	int i, j, nr;
+
+	blk_stat_init(&dst[BLK_STAT_READ]);
+	blk_stat_init(&dst[BLK_STAT_WRITE]);
+
+	nr = 0;
+	do {
+		uint64_t newest = 0;
+
+		queue_for_each_hw_ctx(q, hctx, i) {
+			hctx_for_each_ctx(hctx, ctx, j) {
+				blk_stat_flush_batch(&ctx->stat[BLK_STAT_READ]);
+				blk_stat_flush_batch(&ctx->stat[BLK_STAT_WRITE]);
+
+				if (!ctx->stat[BLK_STAT_READ].nr_samples &&
+				    !ctx->stat[BLK_STAT_WRITE].nr_samples)
+					continue;
+				if (ctx->stat[BLK_STAT_READ].time > newest)
+					newest = ctx->stat[BLK_STAT_READ].time;
+				if (ctx->stat[BLK_STAT_WRITE].time > newest)
+					newest = ctx->stat[BLK_STAT_WRITE].time;
+			}
+		}
+
+		/*
+		 * No samples
+		 */
+		if (!newest)
+			break;
+
+		if (newest > latest)
+			latest = newest;
+
+		queue_for_each_hw_ctx(q, hctx, i) {
+			hctx_for_each_ctx(hctx, ctx, j) {
+				if (ctx->stat[BLK_STAT_READ].time == newest) {
+					blk_stat_sum(&dst[BLK_STAT_READ],
+						     &ctx->stat[BLK_STAT_READ]);
+					nr++;
+				}
+				if (ctx->stat[BLK_STAT_WRITE].time == newest) {
+					blk_stat_sum(&dst[BLK_STAT_WRITE],
+						     &ctx->stat[BLK_STAT_WRITE]);
+					nr++;
+				}
+			}
+		}
+		/*
+		 * If we race on finding an entry, just loop back again.
+		 * Should be very rare.
+		 */
+	} while (!nr);
+
+	dst[BLK_STAT_READ].time = dst[BLK_STAT_WRITE].time = latest;
+}
+
+void blk_queue_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
+{
+	if (q->mq_ops)
+		blk_mq_stat_get(q, dst);
+	else {
+		blk_stat_flush_batch(&q->rq_stats[BLK_STAT_READ]);
+		blk_stat_flush_batch(&q->rq_stats[BLK_STAT_WRITE]);
+		memcpy(&dst[BLK_STAT_READ], &q->rq_stats[BLK_STAT_READ],
+				sizeof(struct blk_rq_stat));
+		memcpy(&dst[BLK_STAT_WRITE], &q->rq_stats[BLK_STAT_WRITE],
+				sizeof(struct blk_rq_stat));
+	}
+}
+
+void blk_hctx_stat_get(struct blk_mq_hw_ctx *hctx, struct blk_rq_stat *dst)
+{
+	struct blk_mq_ctx *ctx;
+	unsigned int i, nr;
+
+	nr = 0;
+	do {
+		uint64_t newest = 0;
+
+		hctx_for_each_ctx(hctx, ctx, i) {
+			blk_stat_flush_batch(&ctx->stat[BLK_STAT_READ]);
+			blk_stat_flush_batch(&ctx->stat[BLK_STAT_WRITE]);
+
+			if (!ctx->stat[BLK_STAT_READ].nr_samples &&
+			    !ctx->stat[BLK_STAT_WRITE].nr_samples)
+				continue;
+
+			if (ctx->stat[BLK_STAT_READ].time > newest)
+				newest = ctx->stat[BLK_STAT_READ].time;
+			if (ctx->stat[BLK_STAT_WRITE].time > newest)
+				newest = ctx->stat[BLK_STAT_WRITE].time;
+		}
+
+		if (!newest)
+			break;
+
+		hctx_for_each_ctx(hctx, ctx, i) {
+			if (ctx->stat[BLK_STAT_READ].time == newest) {
+				blk_stat_sum(&dst[BLK_STAT_READ],
+						&ctx->stat[BLK_STAT_READ]);
+				nr++;
+			}
+			if (ctx->stat[BLK_STAT_WRITE].time == newest) {
+				blk_stat_sum(&dst[BLK_STAT_WRITE],
+						&ctx->stat[BLK_STAT_WRITE]);
+				nr++;
+			}
+		}
+		/*
+		 * If we race on finding an entry, just loop back again.
+		 * Should be very rare, as the window is only updated
+		 * occasionally
+		 */
+	} while (!nr);
+}
+
+static void __blk_stat_init(struct blk_rq_stat *stat, s64 time_now)
+{
+	stat->min = -1ULL;
+	stat->max = stat->nr_samples = stat->mean = 0;
+	stat->batch = stat->nr_batch = 0;
+	stat->time = time_now & BLK_STAT_NSEC_MASK;
+}
+
+void blk_stat_init(struct blk_rq_stat *stat)
+{
+	__blk_stat_init(stat, ktime_to_ns(ktime_get()));
+}
+
+static bool __blk_stat_is_current(struct blk_rq_stat *stat, s64 now)
+{
+	return (now & BLK_STAT_NSEC_MASK) == (stat->time & BLK_STAT_NSEC_MASK);
+}
+
+bool blk_stat_is_current(struct blk_rq_stat *stat)
+{
+	return __blk_stat_is_current(stat, ktime_to_ns(ktime_get()));
+}
+
+void blk_stat_add(struct blk_rq_stat *stat, struct request *rq)
+{
+	s64 now, value;
+
+	now = __blk_stat_time(ktime_to_ns(ktime_get()));
+	if (now < blk_stat_time(&rq->issue_stat))
+		return;
+
+	if (!__blk_stat_is_current(stat, now))
+		__blk_stat_init(stat, now);
+
+	value = now - blk_stat_time(&rq->issue_stat);
+	if (value > stat->max)
+		stat->max = value;
+	if (value < stat->min)
+		stat->min = value;
+
+	if (stat->batch + value < stat->batch ||
+	    stat->nr_batch + 1 == BLK_RQ_STAT_BATCH)
+		blk_stat_flush_batch(stat);
+
+	stat->batch += value;
+	stat->nr_batch++;
+}
+
+void blk_stat_clear(struct request_queue *q)
+{
+	if (q->mq_ops) {
+		struct blk_mq_hw_ctx *hctx;
+		struct blk_mq_ctx *ctx;
+		int i, j;
+
+		queue_for_each_hw_ctx(q, hctx, i) {
+			hctx_for_each_ctx(hctx, ctx, j) {
+				blk_stat_init(&ctx->stat[BLK_STAT_READ]);
+				blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
+			}
+		}
+	} else {
+		blk_stat_init(&q->rq_stats[BLK_STAT_READ]);
+		blk_stat_init(&q->rq_stats[BLK_STAT_WRITE]);
+	}
+}
+
+void blk_stat_set_issue_time(struct blk_issue_stat *stat)
+{
+	stat->time = (stat->time & BLK_STAT_MASK) |
+			(ktime_to_ns(ktime_get()) & BLK_STAT_TIME_MASK);
+}
+
+/*
+ * Enable stat tracking, return whether it was enabled
+ */
+bool blk_stat_enable(struct request_queue *q)
+{
+	if (!test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
+		set_bit(QUEUE_FLAG_STATS, &q->queue_flags);
+		return false;
+	}
+
+	return true;
+}
diff --git a/block/blk-stat.h b/block/blk-stat.h
new file mode 100644
index 0000000..a2050a0
--- /dev/null
+++ b/block/blk-stat.h
@@ -0,0 +1,42 @@
+#ifndef BLK_STAT_H
+#define BLK_STAT_H
+
+/*
+ * ~0.13s window as a power-of-2 (2^27 nsecs)
+ */
+#define BLK_STAT_NSEC		134217728ULL
+#define BLK_STAT_NSEC_MASK	~(BLK_STAT_NSEC - 1)
+
+/*
+ * Upper 3 bits can be used elsewhere
+ */
+#define BLK_STAT_RES_BITS	3
+#define BLK_STAT_SHIFT		(64 - BLK_STAT_RES_BITS)
+#define BLK_STAT_TIME_MASK	((1ULL << BLK_STAT_SHIFT) - 1)
+#define BLK_STAT_MASK		~BLK_STAT_TIME_MASK
+
+enum {
+	BLK_STAT_READ	= 0,
+	BLK_STAT_WRITE,
+};
+
+void blk_stat_add(struct blk_rq_stat *, struct request *);
+void blk_hctx_stat_get(struct blk_mq_hw_ctx *, struct blk_rq_stat *);
+void blk_queue_stat_get(struct request_queue *, struct blk_rq_stat *);
+void blk_stat_clear(struct request_queue *);
+void blk_stat_init(struct blk_rq_stat *);
+bool blk_stat_is_current(struct blk_rq_stat *);
+void blk_stat_set_issue_time(struct blk_issue_stat *);
+bool blk_stat_enable(struct request_queue *);
+
+static inline u64 __blk_stat_time(u64 time)
+{
+	return time & BLK_STAT_TIME_MASK;
+}
+
+static inline u64 blk_stat_time(struct blk_issue_stat *stat)
+{
+	return __blk_stat_time(stat->time);
+}
+
+#endif
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index ea374e8..1dbce05 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -13,6 +13,7 @@
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-wbt.h"
 
 struct queue_sysfs_entry {
 	struct attribute attr;
@@ -41,6 +42,19 @@ queue_var_store(unsigned long *var, const char *page, size_t count)
 	return count;
 }
 
+static ssize_t queue_var_store64(s64 *var, const char *page)
+{
+	int err;
+	s64 v;
+
+	err = kstrtos64(page, 10, &v);
+	if (err < 0)
+		return err;
+
+	*var = v;
+	return 0;
+}
+
 static ssize_t queue_requests_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(q->nr_requests, (page));
@@ -130,6 +144,11 @@ static ssize_t queue_physical_block_size_show(struct request_queue *q, char *pag
 	return queue_var_show(queue_physical_block_size(q), page);
 }
 
+static ssize_t queue_chunk_sectors_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(q->limits.chunk_sectors, page);
+}
+
 static ssize_t queue_io_min_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(queue_io_min(q), page);
@@ -192,6 +211,11 @@ static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
 		(unsigned long long)q->limits.max_write_same_sectors << 9);
 }
 
+static ssize_t queue_write_zeroes_max_show(struct request_queue *q, char *page)
+{
+	return sprintf(page, "%llu\n",
+		(unsigned long long)q->limits.max_write_zeroes_sectors << 9);
+}
 
 static ssize_t
 queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
@@ -258,6 +282,18 @@ QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0);
 QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0);
 #undef QUEUE_SYSFS_BIT_FNS
 
+static ssize_t queue_zoned_show(struct request_queue *q, char *page)
+{
+	switch (blk_queue_zoned_model(q)) {
+	case BLK_ZONED_HA:
+		return sprintf(page, "host-aware\n");
+	case BLK_ZONED_HM:
+		return sprintf(page, "host-managed\n");
+	default:
+		return sprintf(page, "none\n");
+	}
+}
+
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
 {
 	return queue_var_show((blk_queue_nomerges(q) << 1) |
@@ -320,6 +356,38 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 	return ret;
 }
 
+static ssize_t queue_poll_delay_show(struct request_queue *q, char *page)
+{
+	int val;
+
+	if (q->poll_nsec == -1)
+		val = -1;
+	else
+		val = q->poll_nsec / 1000;
+
+	return sprintf(page, "%d\n", val);
+}
+
+static ssize_t queue_poll_delay_store(struct request_queue *q, const char *page,
+				size_t count)
+{
+	int err, val;
+
+	if (!q->mq_ops || !q->mq_ops->poll)
+		return -EINVAL;
+
+	err = kstrtoint(page, 10, &val);
+	if (err < 0)
+		return err;
+
+	if (val == -1)
+		q->poll_nsec = -1;
+	else
+		q->poll_nsec = val * 1000;
+
+	return count;
+}
+
 static ssize_t queue_poll_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(test_bit(QUEUE_FLAG_POLL, &q->queue_flags), page);
@@ -348,6 +416,50 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
 	return ret;
 }
 
+static ssize_t queue_wb_lat_show(struct request_queue *q, char *page)
+{
+	if (!q->rq_wb)
+		return -EINVAL;
+
+	return sprintf(page, "%llu\n", div_u64(q->rq_wb->min_lat_nsec, 1000));
+}
+
+static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
+				  size_t count)
+{
+	struct rq_wb *rwb;
+	ssize_t ret;
+	s64 val;
+
+	ret = queue_var_store64(&val, page);
+	if (ret < 0)
+		return ret;
+	if (val < -1)
+		return -EINVAL;
+
+	rwb = q->rq_wb;
+	if (!rwb) {
+		ret = wbt_init(q);
+		if (ret)
+			return ret;
+
+		rwb = q->rq_wb;
+		if (!rwb)
+			return -EINVAL;
+	}
+
+	if (val == -1)
+		rwb->min_lat_nsec = wbt_default_latency_nsec(q);
+	else if (val >= 0)
+		rwb->min_lat_nsec = val * 1000ULL;
+
+	if (rwb->enable_state == WBT_STATE_ON_DEFAULT)
+		rwb->enable_state = WBT_STATE_ON_MANUAL;
+
+	wbt_update_limits(rwb);
+	return count;
+}
+
 static ssize_t queue_wc_show(struct request_queue *q, char *page)
 {
 	if (test_bit(QUEUE_FLAG_WC, &q->queue_flags))
@@ -385,6 +497,26 @@ static ssize_t queue_dax_show(struct request_queue *q, char *page)
 	return queue_var_show(blk_queue_dax(q), page);
 }
 
+static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre)
+{
+	return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n",
+			pre, (long long) stat->nr_samples,
+			(long long) stat->mean, (long long) stat->min,
+			(long long) stat->max);
+}
+
+static ssize_t queue_stats_show(struct request_queue *q, char *page)
+{
+	struct blk_rq_stat stat[2];
+	ssize_t ret;
+
+	blk_queue_stat_get(q, stat);
+
+	ret = print_stat(page, &stat[BLK_STAT_READ], "read :");
+	ret += print_stat(page + ret, &stat[BLK_STAT_WRITE], "write:");
+	return ret;
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -444,6 +576,11 @@ static struct queue_sysfs_entry queue_physical_block_size_entry = {
 	.show = queue_physical_block_size_show,
 };
 
+static struct queue_sysfs_entry queue_chunk_sectors_entry = {
+	.attr = {.name = "chunk_sectors", .mode = S_IRUGO },
+	.show = queue_chunk_sectors_show,
+};
+
 static struct queue_sysfs_entry queue_io_min_entry = {
 	.attr = {.name = "minimum_io_size", .mode = S_IRUGO },
 	.show = queue_io_min_show,
@@ -480,12 +617,22 @@ static struct queue_sysfs_entry queue_write_same_max_entry = {
 	.show = queue_write_same_max_show,
 };
 
+static struct queue_sysfs_entry queue_write_zeroes_max_entry = {
+	.attr = {.name = "write_zeroes_max_bytes", .mode = S_IRUGO },
+	.show = queue_write_zeroes_max_show,
+};
+
 static struct queue_sysfs_entry queue_nonrot_entry = {
 	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_show_nonrot,
 	.store = queue_store_nonrot,
 };
 
+static struct queue_sysfs_entry queue_zoned_entry = {
+	.attr = {.name = "zoned", .mode = S_IRUGO },
+	.show = queue_zoned_show,
+};
+
 static struct queue_sysfs_entry queue_nomerges_entry = {
 	.attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_nomerges_show,
@@ -516,6 +663,12 @@ static struct queue_sysfs_entry queue_poll_entry = {
 	.store = queue_poll_store,
 };
 
+static struct queue_sysfs_entry queue_poll_delay_entry = {
+	.attr = {.name = "io_poll_delay", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_poll_delay_show,
+	.store = queue_poll_delay_store,
+};
+
 static struct queue_sysfs_entry queue_wc_entry = {
 	.attr = {.name = "write_cache", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_wc_show,
@@ -527,6 +680,17 @@ static struct queue_sysfs_entry queue_dax_entry = {
 	.show = queue_dax_show,
 };
 
+static struct queue_sysfs_entry queue_stats_entry = {
+	.attr = {.name = "stats", .mode = S_IRUGO },
+	.show = queue_stats_show,
+};
+
+static struct queue_sysfs_entry queue_wb_lat_entry = {
+	.attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_wb_lat_show,
+	.store = queue_wb_lat_store,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -539,6 +703,7 @@ static struct attribute *default_attrs[] = {
 	&queue_hw_sector_size_entry.attr,
 	&queue_logical_block_size_entry.attr,
 	&queue_physical_block_size_entry.attr,
+	&queue_chunk_sectors_entry.attr,
 	&queue_io_min_entry.attr,
 	&queue_io_opt_entry.attr,
 	&queue_discard_granularity_entry.attr,
@@ -546,7 +711,9 @@ static struct attribute *default_attrs[] = {
 	&queue_discard_max_hw_entry.attr,
 	&queue_discard_zeroes_data_entry.attr,
 	&queue_write_same_max_entry.attr,
+	&queue_write_zeroes_max_entry.attr,
 	&queue_nonrot_entry.attr,
+	&queue_zoned_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
 	&queue_iostats_entry.attr,
@@ -554,6 +721,9 @@ static struct attribute *default_attrs[] = {
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
 	&queue_dax_entry.attr,
+	&queue_stats_entry.attr,
+	&queue_wb_lat_entry.attr,
+	&queue_poll_delay_entry.attr,
 	NULL,
 };
 
@@ -628,6 +798,7 @@ static void blk_release_queue(struct kobject *kobj)
 	struct request_queue *q =
 		container_of(kobj, struct request_queue, kobj);
 
+	wbt_exit(q);
 	bdi_exit(&q->backing_dev_info);
 	blkcg_exit_queue(q);
 
@@ -668,6 +839,23 @@ struct kobj_type blk_queue_ktype = {
 	.release	= blk_release_queue,
 };
 
+static void blk_wb_init(struct request_queue *q)
+{
+#ifndef CONFIG_BLK_WBT_MQ
+	if (q->mq_ops)
+		return;
+#endif
+#ifndef CONFIG_BLK_WBT_SQ
+	if (q->request_fn)
+		return;
+#endif
+
+	/*
+	 * If this fails, we don't get throttling
+	 */
+	wbt_init(q);
+}
+
 int blk_register_queue(struct gendisk *disk)
 {
 	int ret;
@@ -707,6 +895,8 @@ int blk_register_queue(struct gendisk *disk)
 	if (q->mq_ops)
 		blk_mq_register_dev(dev, q);
 
+	blk_wb_init(q);
+
 	if (!q->request_fn)
 		return 0;
 
diff --git a/block/blk-tag.c b/block/blk-tag.c
index f0344e6..bae1dec 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -270,7 +270,7 @@ void blk_queue_end_tag(struct request_queue *q, struct request *rq)
 	BUG_ON(tag >= bqt->real_max_depth);
 
 	list_del_init(&rq->queuelist);
-	rq->cmd_flags &= ~REQ_QUEUED;
+	rq->rq_flags &= ~RQF_QUEUED;
 	rq->tag = -1;
 
 	if (unlikely(bqt->tag_index[tag] == NULL))
@@ -316,7 +316,7 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	unsigned max_depth;
 	int tag;
 
-	if (unlikely((rq->cmd_flags & REQ_QUEUED))) {
+	if (unlikely((rq->rq_flags & RQF_QUEUED))) {
 		printk(KERN_ERR
 		       "%s: request %p for device [%s] already tagged %d",
 		       __func__, rq,
@@ -371,7 +371,7 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	 */
 
 	bqt->next_tag = (tag + 1) % bqt->max_depth;
-	rq->cmd_flags |= REQ_QUEUED;
+	rq->rq_flags |= RQF_QUEUED;
 	rq->tag = tag;
 	bqt->tag_index[tag] = rq;
 	blk_start_request(rq);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index a3ea826..a6bb4fe 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -818,13 +818,13 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 	tg->io_disp[rw]++;
 
 	/*
-	 * REQ_THROTTLED is used to prevent the same bio to be throttled
+	 * BIO_THROTTLED is used to prevent the same bio to be throttled
 	 * more than once as a throttled bio will go through blk-throtl the
 	 * second time when it eventually gets issued.  Set it when a bio
 	 * is being charged to a tg.
 	 */
-	if (!(bio->bi_opf & REQ_THROTTLED))
-		bio->bi_opf |= REQ_THROTTLED;
+	if (!bio_flagged(bio, BIO_THROTTLED))
+		bio_set_flag(bio, BIO_THROTTLED);
 }
 
 /**
@@ -1401,7 +1401,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	/* see throtl_charge_bio() */
-	if ((bio->bi_opf & REQ_THROTTLED) || !tg->has_rules[rw])
+	if (bio_flagged(bio, BIO_THROTTLED) || !tg->has_rules[rw])
 		goto out;
 
 	spin_lock_irq(q->queue_lock);
@@ -1480,7 +1480,7 @@ out:
 	 * being issued.
 	 */
 	if (!throttled)
-		bio->bi_opf &= ~REQ_THROTTLED;
+		bio_clear_flag(bio, BIO_THROTTLED);
 	return throttled;
 }
 
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
new file mode 100644
index 0000000..6e82769
--- /dev/null
+++ b/block/blk-wbt.c
@@ -0,0 +1,750 @@
+/*
+ * buffered writeback throttling. loosely based on CoDel. We can't drop
+ * packets for IO scheduling, so the logic is something like this:
+ *
+ * - Monitor latencies in a defined window of time.
+ * - If the minimum latency in the above window exceeds some target, increment
+ *   scaling step and scale down queue depth by a factor of 2x. The monitoring
+ *   window is then shrunk to 100 / sqrt(scaling step + 1).
+ * - For any window where we don't have solid data on what the latencies
+ *   look like, retain status quo.
+ * - If latencies look good, decrement scaling step.
+ * - If we're only doing writes, allow the scaling step to go negative. This
+ *   will temporarily boost write performance, snapping back to a stable
+ *   scaling step of 0 if reads show up or the heavy writers finish. Unlike
+ *   positive scaling steps where we shrink the monitoring window, a negative
+ *   scaling step retains the default step==0 window size.
+ *
+ * Copyright (C) 2016 Jens Axboe
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/blk_types.h>
+#include <linux/slab.h>
+#include <linux/backing-dev.h>
+#include <linux/swap.h>
+
+#include "blk-wbt.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/wbt.h>
+
+enum {
+	/*
+	 * Default setting, we'll scale up (to 75% of QD max) or down (min 1)
+	 * from here depending on device stats
+	 */
+	RWB_DEF_DEPTH	= 16,
+
+	/*
+	 * 100msec window
+	 */
+	RWB_WINDOW_NSEC		= 100 * 1000 * 1000ULL,
+
+	/*
+	 * Disregard stats, if we don't meet this minimum
+	 */
+	RWB_MIN_WRITE_SAMPLES	= 3,
+
+	/*
+	 * If we have this number of consecutive windows with not enough
+	 * information to scale up or down, scale up.
+	 */
+	RWB_UNKNOWN_BUMP	= 5,
+};
+
+static inline bool rwb_enabled(struct rq_wb *rwb)
+{
+	return rwb && rwb->wb_normal != 0;
+}
+
+/*
+ * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
+ * false if 'v' + 1 would be bigger than 'below'.
+ */
+static bool atomic_inc_below(atomic_t *v, int below)
+{
+	int cur = atomic_read(v);
+
+	for (;;) {
+		int old;
+
+		if (cur >= below)
+			return false;
+		old = atomic_cmpxchg(v, cur, cur + 1);
+		if (old == cur)
+			break;
+		cur = old;
+	}
+
+	return true;
+}
+
+static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
+{
+	if (rwb_enabled(rwb)) {
+		const unsigned long cur = jiffies;
+
+		if (cur != *var)
+			*var = cur;
+	}
+}
+
+/*
+ * If a task was rate throttled in balance_dirty_pages() within the last
+ * second or so, use that to indicate a higher cleaning rate.
+ */
+static bool wb_recent_wait(struct rq_wb *rwb)
+{
+	struct bdi_writeback *wb = &rwb->queue->backing_dev_info.wb;
+
+	return time_before(jiffies, wb->dirty_sleep + HZ);
+}
+
+static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, bool is_kswapd)
+{
+	return &rwb->rq_wait[is_kswapd];
+}
+
+static void rwb_wake_all(struct rq_wb *rwb)
+{
+	int i;
+
+	for (i = 0; i < WBT_NUM_RWQ; i++) {
+		struct rq_wait *rqw = &rwb->rq_wait[i];
+
+		if (waitqueue_active(&rqw->wait))
+			wake_up_all(&rqw->wait);
+	}
+}
+
+void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
+{
+	struct rq_wait *rqw;
+	int inflight, limit;
+
+	if (!(wb_acct & WBT_TRACKED))
+		return;
+
+	rqw = get_rq_wait(rwb, wb_acct & WBT_KSWAPD);
+	inflight = atomic_dec_return(&rqw->inflight);
+
+	/*
+	 * wbt got disabled with IO in flight. Wake up any potential
+	 * waiters, we don't have to do more than that.
+	 */
+	if (unlikely(!rwb_enabled(rwb))) {
+		rwb_wake_all(rwb);
+		return;
+	}
+
+	/*
+	 * If the device does write back caching, drop further down
+	 * before we wake people up.
+	 */
+	if (rwb->wc && !wb_recent_wait(rwb))
+		limit = 0;
+	else
+		limit = rwb->wb_normal;
+
+	/*
+	 * Don't wake anyone up if we are above the normal limit.
+	 */
+	if (inflight && inflight >= limit)
+		return;
+
+	if (waitqueue_active(&rqw->wait)) {
+		int diff = limit - inflight;
+
+		if (!inflight || diff >= rwb->wb_background / 2)
+			wake_up_all(&rqw->wait);
+	}
+}
+
+/*
+ * Called on completion of a request. Note that it's also called when
+ * a request is merged, when the request gets freed.
+ */
+void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat)
+{
+	if (!rwb)
+		return;
+
+	if (!wbt_is_tracked(stat)) {
+		if (rwb->sync_cookie == stat) {
+			rwb->sync_issue = 0;
+			rwb->sync_cookie = NULL;
+		}
+
+		if (wbt_is_read(stat))
+			wb_timestamp(rwb, &rwb->last_comp);
+		wbt_clear_state(stat);
+	} else {
+		WARN_ON_ONCE(stat == rwb->sync_cookie);
+		__wbt_done(rwb, wbt_stat_to_mask(stat));
+		wbt_clear_state(stat);
+	}
+}
+
+/*
+ * Return true, if we can't increase the depth further by scaling
+ */
+static bool calc_wb_limits(struct rq_wb *rwb)
+{
+	unsigned int depth;
+	bool ret = false;
+
+	if (!rwb->min_lat_nsec) {
+		rwb->wb_max = rwb->wb_normal = rwb->wb_background = 0;
+		return false;
+	}
+
+	/*
+	 * For QD=1 devices, this is a special case. It's important for those
+	 * to have one request ready when one completes, so force a depth of
+	 * 2 for those devices. On the backend, it'll be a depth of 1 anyway,
+	 * since the device can't have more than that in flight. If we're
+	 * scaling down, then keep a setting of 1/1/1.
+	 */
+	if (rwb->queue_depth == 1) {
+		if (rwb->scale_step > 0)
+			rwb->wb_max = rwb->wb_normal = 1;
+		else {
+			rwb->wb_max = rwb->wb_normal = 2;
+			ret = true;
+		}
+		rwb->wb_background = 1;
+	} else {
+		/*
+		 * scale_step == 0 is our default state. If we have suffered
+		 * latency spikes, step will be > 0, and we shrink the
+		 * allowed write depths. If step is < 0, we're only doing
+		 * writes, and we allow a temporarily higher depth to
+		 * increase performance.
+		 */
+		depth = min_t(unsigned int, RWB_DEF_DEPTH, rwb->queue_depth);
+		if (rwb->scale_step > 0)
+			depth = 1 + ((depth - 1) >> min(31, rwb->scale_step));
+		else if (rwb->scale_step < 0) {
+			unsigned int maxd = 3 * rwb->queue_depth / 4;
+
+			depth = 1 + ((depth - 1) << -rwb->scale_step);
+			if (depth > maxd) {
+				depth = maxd;
+				ret = true;
+			}
+		}
+
+		/*
+		 * Set our max/normal/bg queue depths based on how far
+		 * we have scaled down (->scale_step).
+		 */
+		rwb->wb_max = depth;
+		rwb->wb_normal = (rwb->wb_max + 1) / 2;
+		rwb->wb_background = (rwb->wb_max + 3) / 4;
+	}
+
+	return ret;
+}
+
+static inline bool stat_sample_valid(struct blk_rq_stat *stat)
+{
+	/*
+	 * We need at least one read sample, and a minimum of
+	 * RWB_MIN_WRITE_SAMPLES. We require some write samples to know
+	 * that it's writes impacting us, and not just some sole read on
+	 * a device that is in a lower power state.
+	 */
+	return stat[BLK_STAT_READ].nr_samples >= 1 &&
+		stat[BLK_STAT_WRITE].nr_samples >= RWB_MIN_WRITE_SAMPLES;
+}
+
+static u64 rwb_sync_issue_lat(struct rq_wb *rwb)
+{
+	u64 now, issue = ACCESS_ONCE(rwb->sync_issue);
+
+	if (!issue || !rwb->sync_cookie)
+		return 0;
+
+	now = ktime_to_ns(ktime_get());
+	return now - issue;
+}
+
+enum {
+	LAT_OK = 1,
+	LAT_UNKNOWN,
+	LAT_UNKNOWN_WRITES,
+	LAT_EXCEEDED,
+};
+
+static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
+{
+	struct backing_dev_info *bdi = &rwb->queue->backing_dev_info;
+	u64 thislat;
+
+	/*
+	 * If our stored sync issue exceeds the window size, or it
+	 * exceeds our min target AND we haven't logged any entries,
+	 * flag the latency as exceeded. wbt works off completion latencies,
+	 * but for a flooded device, a single sync IO can take a long time
+	 * to complete after being issued. If this time exceeds our
+	 * monitoring window AND we didn't see any other completions in that
+	 * window, then count that sync IO as a violation of the latency.
+	 */
+	thislat = rwb_sync_issue_lat(rwb);
+	if (thislat > rwb->cur_win_nsec ||
+	    (thislat > rwb->min_lat_nsec && !stat[BLK_STAT_READ].nr_samples)) {
+		trace_wbt_lat(bdi, thislat);
+		return LAT_EXCEEDED;
+	}
+
+	/*
+	 * No read/write mix, if stat isn't valid
+	 */
+	if (!stat_sample_valid(stat)) {
+		/*
+		 * If we had writes in this stat window and the window is
+		 * current, we're only doing writes. If a task recently
+		 * waited or still has writes in flights, consider us doing
+		 * just writes as well.
+		 */
+		if ((stat[BLK_STAT_WRITE].nr_samples && blk_stat_is_current(stat)) ||
+		    wb_recent_wait(rwb) || wbt_inflight(rwb))
+			return LAT_UNKNOWN_WRITES;
+		return LAT_UNKNOWN;
+	}
+
+	/*
+	 * If the 'min' latency exceeds our target, step down.
+	 */
+	if (stat[BLK_STAT_READ].min > rwb->min_lat_nsec) {
+		trace_wbt_lat(bdi, stat[BLK_STAT_READ].min);
+		trace_wbt_stat(bdi, stat);
+		return LAT_EXCEEDED;
+	}
+
+	if (rwb->scale_step)
+		trace_wbt_stat(bdi, stat);
+
+	return LAT_OK;
+}
+
+static int latency_exceeded(struct rq_wb *rwb)
+{
+	struct blk_rq_stat stat[2];
+
+	blk_queue_stat_get(rwb->queue, stat);
+	return __latency_exceeded(rwb, stat);
+}
+
+static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
+{
+	struct backing_dev_info *bdi = &rwb->queue->backing_dev_info;
+
+	trace_wbt_step(bdi, msg, rwb->scale_step, rwb->cur_win_nsec,
+			rwb->wb_background, rwb->wb_normal, rwb->wb_max);
+}
+
+static void scale_up(struct rq_wb *rwb)
+{
+	/*
+	 * Hit max in previous round, stop here
+	 */
+	if (rwb->scaled_max)
+		return;
+
+	rwb->scale_step--;
+	rwb->unknown_cnt = 0;
+	blk_stat_clear(rwb->queue);
+
+	rwb->scaled_max = calc_wb_limits(rwb);
+
+	rwb_wake_all(rwb);
+
+	rwb_trace_step(rwb, "step up");
+}
+
+/*
+ * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
+ * had a latency violation.
+ */
+static void scale_down(struct rq_wb *rwb, bool hard_throttle)
+{
+	/*
+	 * Stop scaling down when we've hit the limit. This also prevents
+	 * ->scale_step from going to crazy values, if the device can't
+	 * keep up.
+	 */
+	if (rwb->wb_max == 1)
+		return;
+
+	if (rwb->scale_step < 0 && hard_throttle)
+		rwb->scale_step = 0;
+	else
+		rwb->scale_step++;
+
+	rwb->scaled_max = false;
+	rwb->unknown_cnt = 0;
+	blk_stat_clear(rwb->queue);
+	calc_wb_limits(rwb);
+	rwb_trace_step(rwb, "step down");
+}
+
+static void rwb_arm_timer(struct rq_wb *rwb)
+{
+	unsigned long expires;
+
+	if (rwb->scale_step > 0) {
+		/*
+		 * We should speed this up, using some variant of a fast
+		 * integer inverse square root calculation. Since we only do
+		 * this for every window expiration, it's not a huge deal,
+		 * though.
+		 */
+		rwb->cur_win_nsec = div_u64(rwb->win_nsec << 4,
+					int_sqrt((rwb->scale_step + 1) << 8));
+	} else {
+		/*
+		 * For step < 0, we don't want to increase/decrease the
+		 * window size.
+		 */
+		rwb->cur_win_nsec = rwb->win_nsec;
+	}
+
+	expires = jiffies + nsecs_to_jiffies(rwb->cur_win_nsec);
+	mod_timer(&rwb->window_timer, expires);
+}
+
+static void wb_timer_fn(unsigned long data)
+{
+	struct rq_wb *rwb = (struct rq_wb *) data;
+	unsigned int inflight = wbt_inflight(rwb);
+	int status;
+
+	status = latency_exceeded(rwb);
+
+	trace_wbt_timer(&rwb->queue->backing_dev_info, status, rwb->scale_step,
+			inflight);
+
+	/*
+	 * If we exceeded the latency target, step down. If we did not,
+	 * step one level up. If we don't know enough to say either exceeded
+	 * or ok, then don't do anything.
+	 */
+	switch (status) {
+	case LAT_EXCEEDED:
+		scale_down(rwb, true);
+		break;
+	case LAT_OK:
+		scale_up(rwb);
+		break;
+	case LAT_UNKNOWN_WRITES:
+		/*
+		 * We started a the center step, but don't have a valid
+		 * read/write sample, but we do have writes going on.
+		 * Allow step to go negative, to increase write perf.
+		 */
+		scale_up(rwb);
+		break;
+	case LAT_UNKNOWN:
+		if (++rwb->unknown_cnt < RWB_UNKNOWN_BUMP)
+			break;
+		/*
+		 * We get here when previously scaled reduced depth, and we
+		 * currently don't have a valid read/write sample. For that
+		 * case, slowly return to center state (step == 0).
+		 */
+		if (rwb->scale_step > 0)
+			scale_up(rwb);
+		else if (rwb->scale_step < 0)
+			scale_down(rwb, false);
+		break;
+	default:
+		break;
+	}
+
+	/*
+	 * Re-arm timer, if we have IO in flight
+	 */
+	if (rwb->scale_step || inflight)
+		rwb_arm_timer(rwb);
+}
+
+void wbt_update_limits(struct rq_wb *rwb)
+{
+	rwb->scale_step = 0;
+	rwb->scaled_max = false;
+	calc_wb_limits(rwb);
+
+	rwb_wake_all(rwb);
+}
+
+static bool close_io(struct rq_wb *rwb)
+{
+	const unsigned long now = jiffies;
+
+	return time_before(now, rwb->last_issue + HZ / 10) ||
+		time_before(now, rwb->last_comp + HZ / 10);
+}
+
+#define REQ_HIPRIO	(REQ_SYNC | REQ_META | REQ_PRIO)
+
+static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
+{
+	unsigned int limit;
+
+	/*
+	 * At this point we know it's a buffered write. If this is
+	 * kswapd trying to free memory, or REQ_SYNC is set, set, then
+	 * it's WB_SYNC_ALL writeback, and we'll use the max limit for
+	 * that. If the write is marked as a background write, then use
+	 * the idle limit, or go to normal if we haven't had competing
+	 * IO for a bit.
+	 */
+	if ((rw & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd())
+		limit = rwb->wb_max;
+	else if ((rw & REQ_BACKGROUND) || close_io(rwb)) {
+		/*
+		 * If less than 100ms since we completed unrelated IO,
+		 * limit us to half the depth for background writeback.
+		 */
+		limit = rwb->wb_background;
+	} else
+		limit = rwb->wb_normal;
+
+	return limit;
+}
+
+static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
+			     wait_queue_t *wait, unsigned long rw)
+{
+	/*
+	 * inc it here even if disabled, since we'll dec it at completion.
+	 * this only happens if the task was sleeping in __wbt_wait(),
+	 * and someone turned it off at the same time.
+	 */
+	if (!rwb_enabled(rwb)) {
+		atomic_inc(&rqw->inflight);
+		return true;
+	}
+
+	/*
+	 * If the waitqueue is already active and we are not the next
+	 * in line to be woken up, wait for our turn.
+	 */
+	if (waitqueue_active(&rqw->wait) &&
+	    rqw->wait.task_list.next != &wait->task_list)
+		return false;
+
+	return atomic_inc_below(&rqw->inflight, get_limit(rwb, rw));
+}
+
+/*
+ * Block if we will exceed our limit, or if we are currently waiting for
+ * the timer to kick off queuing again.
+ */
+static void __wbt_wait(struct rq_wb *rwb, unsigned long rw, spinlock_t *lock)
+{
+	struct rq_wait *rqw = get_rq_wait(rwb, current_is_kswapd());
+	DEFINE_WAIT(wait);
+
+	if (may_queue(rwb, rqw, &wait, rw))
+		return;
+
+	do {
+		prepare_to_wait_exclusive(&rqw->wait, &wait,
+						TASK_UNINTERRUPTIBLE);
+
+		if (may_queue(rwb, rqw, &wait, rw))
+			break;
+
+		if (lock)
+			spin_unlock_irq(lock);
+
+		io_schedule();
+
+		if (lock)
+			spin_lock_irq(lock);
+	} while (1);
+
+	finish_wait(&rqw->wait, &wait);
+}
+
+static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
+{
+	const int op = bio_op(bio);
+
+	/*
+	 * If not a WRITE, do nothing
+	 */
+	if (op != REQ_OP_WRITE)
+		return false;
+
+	/*
+	 * Don't throttle WRITE_ODIRECT
+	 */
+	if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) == (REQ_SYNC | REQ_IDLE))
+		return false;
+
+	return true;
+}
+
+/*
+ * Returns true if the IO request should be accounted, false if not.
+ * May sleep, if we have exceeded the writeback limits. Caller can pass
+ * in an irq held spinlock, if it holds one when calling this function.
+ * If we do sleep, we'll release and re-grab it.
+ */
+unsigned int wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
+{
+	unsigned int ret = 0;
+
+	if (!rwb_enabled(rwb))
+		return 0;
+
+	if (bio_op(bio) == REQ_OP_READ)
+		ret = WBT_READ;
+
+	if (!wbt_should_throttle(rwb, bio)) {
+		if (ret & WBT_READ)
+			wb_timestamp(rwb, &rwb->last_issue);
+		return ret;
+	}
+
+	__wbt_wait(rwb, bio->bi_opf, lock);
+
+	if (!timer_pending(&rwb->window_timer))
+		rwb_arm_timer(rwb);
+
+	if (current_is_kswapd())
+		ret |= WBT_KSWAPD;
+
+	return ret | WBT_TRACKED;
+}
+
+void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+{
+	if (!rwb_enabled(rwb))
+		return;
+
+	/*
+	 * Track sync issue, in case it takes a long time to complete. Allows
+	 * us to react quicker, if a sync IO takes a long time to complete.
+	 * Note that this is just a hint. 'stat' can go away when the
+	 * request completes, so it's important we never dereference it. We
+	 * only use the address to compare with, which is why we store the
+	 * sync_issue time locally.
+	 */
+	if (wbt_is_read(stat) && !rwb->sync_issue) {
+		rwb->sync_cookie = stat;
+		rwb->sync_issue = blk_stat_time(stat);
+	}
+}
+
+void wbt_requeue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+{
+	if (!rwb_enabled(rwb))
+		return;
+	if (stat == rwb->sync_cookie) {
+		rwb->sync_issue = 0;
+		rwb->sync_cookie = NULL;
+	}
+}
+
+void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
+{
+	if (rwb) {
+		rwb->queue_depth = depth;
+		wbt_update_limits(rwb);
+	}
+}
+
+void wbt_set_write_cache(struct rq_wb *rwb, bool write_cache_on)
+{
+	if (rwb)
+		rwb->wc = write_cache_on;
+}
+
+ /*
+ * Disable wbt, if enabled by default. Only called from CFQ, if we have
+ * cgroups enabled
+ */
+void wbt_disable_default(struct request_queue *q)
+{
+	struct rq_wb *rwb = q->rq_wb;
+
+	if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT) {
+		del_timer_sync(&rwb->window_timer);
+		rwb->win_nsec = rwb->min_lat_nsec = 0;
+		wbt_update_limits(rwb);
+	}
+}
+EXPORT_SYMBOL_GPL(wbt_disable_default);
+
+u64 wbt_default_latency_nsec(struct request_queue *q)
+{
+	/*
+	 * We default to 2msec for non-rotational storage, and 75msec
+	 * for rotational storage.
+	 */
+	if (blk_queue_nonrot(q))
+		return 2000000ULL;
+	else
+		return 75000000ULL;
+}
+
+int wbt_init(struct request_queue *q)
+{
+	struct rq_wb *rwb;
+	int i;
+
+	/*
+	 * For now, we depend on the stats window being larger than
+	 * our monitoring window. Ensure that this isn't inadvertently
+	 * violated.
+	 */
+	BUILD_BUG_ON(RWB_WINDOW_NSEC > BLK_STAT_NSEC);
+	BUILD_BUG_ON(WBT_NR_BITS > BLK_STAT_RES_BITS);
+
+	rwb = kzalloc(sizeof(*rwb), GFP_KERNEL);
+	if (!rwb)
+		return -ENOMEM;
+
+	for (i = 0; i < WBT_NUM_RWQ; i++) {
+		atomic_set(&rwb->rq_wait[i].inflight, 0);
+		init_waitqueue_head(&rwb->rq_wait[i].wait);
+	}
+
+	setup_timer(&rwb->window_timer, wb_timer_fn, (unsigned long) rwb);
+	rwb->wc = 1;
+	rwb->queue_depth = RWB_DEF_DEPTH;
+	rwb->last_comp = rwb->last_issue = jiffies;
+	rwb->queue = q;
+	rwb->win_nsec = RWB_WINDOW_NSEC;
+	rwb->enable_state = WBT_STATE_ON_DEFAULT;
+	wbt_update_limits(rwb);
+
+	/*
+	 * Assign rwb, and turn on stats tracking for this queue
+	 */
+	q->rq_wb = rwb;
+	blk_stat_enable(q);
+
+	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
+
+	wbt_set_queue_depth(rwb, blk_queue_depth(q));
+	wbt_set_write_cache(rwb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
+
+	return 0;
+}
+
+void wbt_exit(struct request_queue *q)
+{
+	struct rq_wb *rwb = q->rq_wb;
+
+	if (rwb) {
+		del_timer_sync(&rwb->window_timer);
+		q->rq_wb = NULL;
+		kfree(rwb);
+	}
+}
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
new file mode 100644
index 0000000..65f1de5
--- /dev/null
+++ b/block/blk-wbt.h
@@ -0,0 +1,171 @@
+#ifndef WB_THROTTLE_H
+#define WB_THROTTLE_H
+
+#include <linux/kernel.h>
+#include <linux/atomic.h>
+#include <linux/wait.h>
+#include <linux/timer.h>
+#include <linux/ktime.h>
+
+#include "blk-stat.h"
+
+enum wbt_flags {
+	WBT_TRACKED		= 1,	/* write, tracked for throttling */
+	WBT_READ		= 2,	/* read */
+	WBT_KSWAPD		= 4,	/* write, from kswapd */
+
+	WBT_NR_BITS		= 3,	/* number of bits */
+};
+
+enum {
+	WBT_NUM_RWQ		= 2,
+};
+
+/*
+ * Enable states. Either off, or on by default (done at init time),
+ * or on through manual setup in sysfs.
+ */
+enum {
+	WBT_STATE_ON_DEFAULT	= 1,
+	WBT_STATE_ON_MANUAL	= 2,
+};
+
+static inline void wbt_clear_state(struct blk_issue_stat *stat)
+{
+	stat->time &= BLK_STAT_TIME_MASK;
+}
+
+static inline enum wbt_flags wbt_stat_to_mask(struct blk_issue_stat *stat)
+{
+	return (stat->time & BLK_STAT_MASK) >> BLK_STAT_SHIFT;
+}
+
+static inline void wbt_track(struct blk_issue_stat *stat, enum wbt_flags wb_acct)
+{
+	stat->time |= ((u64) wb_acct) << BLK_STAT_SHIFT;
+}
+
+static inline bool wbt_is_tracked(struct blk_issue_stat *stat)
+{
+	return (stat->time >> BLK_STAT_SHIFT) & WBT_TRACKED;
+}
+
+static inline bool wbt_is_read(struct blk_issue_stat *stat)
+{
+	return (stat->time >> BLK_STAT_SHIFT) & WBT_READ;
+}
+
+struct rq_wait {
+	wait_queue_head_t wait;
+	atomic_t inflight;
+};
+
+struct rq_wb {
+	/*
+	 * Settings that govern how we throttle
+	 */
+	unsigned int wb_background;		/* background writeback */
+	unsigned int wb_normal;			/* normal writeback */
+	unsigned int wb_max;			/* max throughput writeback */
+	int scale_step;
+	bool scaled_max;
+
+	short enable_state;			/* WBT_STATE_* */
+
+	/*
+	 * Number of consecutive periods where we don't have enough
+	 * information to make a firm scale up/down decision.
+	 */
+	unsigned int unknown_cnt;
+
+	u64 win_nsec;				/* default window size */
+	u64 cur_win_nsec;			/* current window size */
+
+	struct timer_list window_timer;
+
+	s64 sync_issue;
+	void *sync_cookie;
+
+	unsigned int wc;
+	unsigned int queue_depth;
+
+	unsigned long last_issue;		/* last non-throttled issue */
+	unsigned long last_comp;		/* last non-throttled comp */
+	unsigned long min_lat_nsec;
+	struct request_queue *queue;
+	struct rq_wait rq_wait[WBT_NUM_RWQ];
+};
+
+static inline unsigned int wbt_inflight(struct rq_wb *rwb)
+{
+	unsigned int i, ret = 0;
+
+	for (i = 0; i < WBT_NUM_RWQ; i++)
+		ret += atomic_read(&rwb->rq_wait[i].inflight);
+
+	return ret;
+}
+
+#ifdef CONFIG_BLK_WBT
+
+void __wbt_done(struct rq_wb *, enum wbt_flags);
+void wbt_done(struct rq_wb *, struct blk_issue_stat *);
+enum wbt_flags wbt_wait(struct rq_wb *, struct bio *, spinlock_t *);
+int wbt_init(struct request_queue *);
+void wbt_exit(struct request_queue *);
+void wbt_update_limits(struct rq_wb *);
+void wbt_requeue(struct rq_wb *, struct blk_issue_stat *);
+void wbt_issue(struct rq_wb *, struct blk_issue_stat *);
+void wbt_disable_default(struct request_queue *);
+
+void wbt_set_queue_depth(struct rq_wb *, unsigned int);
+void wbt_set_write_cache(struct rq_wb *, bool);
+
+u64 wbt_default_latency_nsec(struct request_queue *);
+
+#else
+
+static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags)
+{
+}
+static inline void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat)
+{
+}
+static inline enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio,
+				      spinlock_t *lock)
+{
+	return 0;
+}
+static inline int wbt_init(struct request_queue *q)
+{
+	return -EINVAL;
+}
+static inline void wbt_exit(struct request_queue *q)
+{
+}
+static inline void wbt_update_limits(struct rq_wb *rwb)
+{
+}
+static inline void wbt_requeue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+{
+}
+static inline void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+{
+}
+static inline void wbt_disable_default(struct request_queue *q)
+{
+}
+static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
+{
+}
+static inline void wbt_set_write_cache(struct rq_wb *rwb, bool wc)
+{
+}
+static inline u64 wbt_default_latency_nsec(struct request_queue *q)
+{
+	return 0;
+}
+
+#endif /* CONFIG_BLK_WBT */
+
+#endif
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
new file mode 100644
index 0000000..472211f
--- /dev/null
+++ b/block/blk-zoned.c
@@ -0,0 +1,348 @@
+/*
+ * Zoned block device handling
+ *
+ * Copyright (c) 2015, Hannes Reinecke
+ * Copyright (c) 2015, SUSE Linux GmbH
+ *
+ * Copyright (c) 2016, Damien Le Moal
+ * Copyright (c) 2016, Western Digital
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/rbtree.h>
+#include <linux/blkdev.h>
+
+static inline sector_t blk_zone_start(struct request_queue *q,
+				      sector_t sector)
+{
+	sector_t zone_mask = blk_queue_zone_size(q) - 1;
+
+	return sector & ~zone_mask;
+}
+
+/*
+ * Check that a zone report belongs to the partition.
+ * If yes, fix its start sector and write pointer, copy it in the
+ * zone information array and return true. Return false otherwise.
+ */
+static bool blkdev_report_zone(struct block_device *bdev,
+			       struct blk_zone *rep,
+			       struct blk_zone *zone)
+{
+	sector_t offset = get_start_sect(bdev);
+
+	if (rep->start < offset)
+		return false;
+
+	rep->start -= offset;
+	if (rep->start + rep->len > bdev->bd_part->nr_sects)
+		return false;
+
+	if (rep->type == BLK_ZONE_TYPE_CONVENTIONAL)
+		rep->wp = rep->start + rep->len;
+	else
+		rep->wp -= offset;
+	memcpy(zone, rep, sizeof(struct blk_zone));
+
+	return true;
+}
+
+/**
+ * blkdev_report_zones - Get zones information
+ * @bdev:	Target block device
+ * @sector:	Sector from which to report zones
+ * @zones:	Array of zone structures where to return the zones information
+ * @nr_zones:	Number of zone structures in the zone array
+ * @gfp_mask:	Memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ *    Get zone information starting from the zone containing @sector.
+ *    The number of zone information reported may be less than the number
+ *    requested by @nr_zones. The number of zones actually reported is
+ *    returned in @nr_zones.
+ */
+int blkdev_report_zones(struct block_device *bdev,
+			sector_t sector,
+			struct blk_zone *zones,
+			unsigned int *nr_zones,
+			gfp_t gfp_mask)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+	struct blk_zone_report_hdr *hdr;
+	unsigned int nrz = *nr_zones;
+	struct page *page;
+	unsigned int nr_rep;
+	size_t rep_bytes;
+	unsigned int nr_pages;
+	struct bio *bio;
+	struct bio_vec *bv;
+	unsigned int i, n, nz;
+	unsigned int ofst;
+	void *addr;
+	int ret;
+
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -EOPNOTSUPP;
+
+	if (!nrz)
+		return 0;
+
+	if (sector > bdev->bd_part->nr_sects) {
+		*nr_zones = 0;
+		return 0;
+	}
+
+	/*
+	 * The zone report has a header. So make room for it in the
+	 * payload. Also make sure that the report fits in a single BIO
+	 * that will not be split down the stack.
+	 */
+	rep_bytes = sizeof(struct blk_zone_report_hdr) +
+		sizeof(struct blk_zone) * nrz;
+	rep_bytes = (rep_bytes + PAGE_SIZE - 1) & PAGE_MASK;
+	if (rep_bytes > (queue_max_sectors(q) << 9))
+		rep_bytes = queue_max_sectors(q) << 9;
+
+	nr_pages = min_t(unsigned int, BIO_MAX_PAGES,
+			 rep_bytes >> PAGE_SHIFT);
+	nr_pages = min_t(unsigned int, nr_pages,
+			 queue_max_segments(q));
+
+	bio = bio_alloc(gfp_mask, nr_pages);
+	if (!bio)
+		return -ENOMEM;
+
+	bio->bi_bdev = bdev;
+	bio->bi_iter.bi_sector = blk_zone_start(q, sector);
+	bio_set_op_attrs(bio, REQ_OP_ZONE_REPORT, 0);
+
+	for (i = 0; i < nr_pages; i++) {
+		page = alloc_page(gfp_mask);
+		if (!page) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		if (!bio_add_page(bio, page, PAGE_SIZE, 0)) {
+			__free_page(page);
+			break;
+		}
+	}
+
+	if (i == 0)
+		ret = -ENOMEM;
+	else
+		ret = submit_bio_wait(bio);
+	if (ret)
+		goto out;
+
+	/*
+	 * Process the report result: skip the header and go through the
+	 * reported zones to fixup and fixup the zone information for
+	 * partitions. At the same time, return the zone information into
+	 * the zone array.
+	 */
+	n = 0;
+	nz = 0;
+	nr_rep = 0;
+	bio_for_each_segment_all(bv, bio, i) {
+
+		if (!bv->bv_page)
+			break;
+
+		addr = kmap_atomic(bv->bv_page);
+
+		/* Get header in the first page */
+		ofst = 0;
+		if (!nr_rep) {
+			hdr = (struct blk_zone_report_hdr *) addr;
+			nr_rep = hdr->nr_zones;
+			ofst = sizeof(struct blk_zone_report_hdr);
+		}
+
+		/* Fixup and report zones */
+		while (ofst < bv->bv_len &&
+		       n < nr_rep && nz < nrz) {
+			if (blkdev_report_zone(bdev, addr + ofst, &zones[nz]))
+				nz++;
+			ofst += sizeof(struct blk_zone);
+			n++;
+		}
+
+		kunmap_atomic(addr);
+
+		if (n >= nr_rep || nz >= nrz)
+			break;
+
+	}
+
+	*nr_zones = nz;
+out:
+	bio_for_each_segment_all(bv, bio, i)
+		__free_page(bv->bv_page);
+	bio_put(bio);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_report_zones);
+
+/**
+ * blkdev_reset_zones - Reset zones write pointer
+ * @bdev:	Target block device
+ * @sector:	Start sector of the first zone to reset
+ * @nr_sectors:	Number of sectors, at least the length of one zone
+ * @gfp_mask:	Memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ *    Reset the write pointer of the zones contained in the range
+ *    @sector..@sector+@nr_sectors. Specifying the entire disk sector range
+ *    is valid, but the specified range should not contain conventional zones.
+ */
+int blkdev_reset_zones(struct block_device *bdev,
+		       sector_t sector, sector_t nr_sectors,
+		       gfp_t gfp_mask)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+	sector_t zone_sectors;
+	sector_t end_sector = sector + nr_sectors;
+	struct bio *bio;
+	int ret;
+
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -EOPNOTSUPP;
+
+	if (end_sector > bdev->bd_part->nr_sects)
+		/* Out of range */
+		return -EINVAL;
+
+	/* Check alignment (handle eventual smaller last zone) */
+	zone_sectors = blk_queue_zone_size(q);
+	if (sector & (zone_sectors - 1))
+		return -EINVAL;
+
+	if ((nr_sectors & (zone_sectors - 1)) &&
+	    end_sector != bdev->bd_part->nr_sects)
+		return -EINVAL;
+
+	while (sector < end_sector) {
+
+		bio = bio_alloc(gfp_mask, 0);
+		bio->bi_iter.bi_sector = sector;
+		bio->bi_bdev = bdev;
+		bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0);
+
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
+
+		if (ret)
+			return ret;
+
+		sector += zone_sectors;
+
+		/* This may take a while, so be nice to others */
+		cond_resched();
+
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blkdev_reset_zones);
+
+/**
+ * BLKREPORTZONE ioctl processing.
+ * Called from blkdev_ioctl.
+ */
+int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
+			      unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	struct request_queue *q;
+	struct blk_zone_report rep;
+	struct blk_zone *zones;
+	int ret;
+
+	if (!argp)
+		return -EINVAL;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -ENOTTY;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report)))
+		return -EFAULT;
+
+	if (!rep.nr_zones)
+		return -EINVAL;
+
+	zones = kcalloc(rep.nr_zones, sizeof(struct blk_zone), GFP_KERNEL);
+	if (!zones)
+		return -ENOMEM;
+
+	ret = blkdev_report_zones(bdev, rep.sector,
+				  zones, &rep.nr_zones,
+				  GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	if (rep.nr_zones) {
+		if (copy_to_user(argp + sizeof(struct blk_zone_report), zones,
+				 sizeof(struct blk_zone) * rep.nr_zones))
+			ret = -EFAULT;
+	}
+
+ out:
+	kfree(zones);
+
+	return ret;
+}
+
+/**
+ * BLKRESETZONE ioctl processing.
+ * Called from blkdev_ioctl.
+ */
+int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
+			     unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	struct request_queue *q;
+	struct blk_zone_range zrange;
+
+	if (!argp)
+		return -EINVAL;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -ENOTTY;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (!(mode & FMODE_WRITE))
+		return -EBADF;
+
+	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
+		return -EFAULT;
+
+	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
+				  GFP_KERNEL);
+}
diff --git a/block/blk.h b/block/blk.h
index 74444c4..041185e 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -111,6 +111,7 @@ void blk_account_io_done(struct request *req);
 enum rq_atomic_flags {
 	REQ_ATOM_COMPLETE = 0,
 	REQ_ATOM_STARTED,
+	REQ_ATOM_POLL_SLEPT,
 };
 
 /*
@@ -130,7 +131,7 @@ static inline void blk_clear_rq_complete(struct request *rq)
 /*
  * Internal elevator interface
  */
-#define ELV_ON_HASH(rq) ((rq)->cmd_flags & REQ_HASHED)
+#define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED)
 
 void blk_insert_flush(struct request *rq);
 
@@ -247,7 +248,7 @@ extern int blk_update_nr_requests(struct request_queue *, unsigned int);
 static inline int blk_do_io_stat(struct request *rq)
 {
 	return rq->rq_disk &&
-	       (rq->cmd_flags & REQ_IO_STAT) &&
+	       (rq->rq_flags & RQF_IO_STAT) &&
 		(rq->cmd_type == REQ_TYPE_FS);
 }
 
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 650f427..b2a61e3 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -161,6 +161,8 @@ failjob_rls_job:
  * Drivers/subsys should pass this to the queue init function.
  */
 void bsg_request_fn(struct request_queue *q)
+	__releases(q->queue_lock)
+	__acquires(q->queue_lock)
 {
 	struct device *dev = q->queuedata;
 	struct request *req;
diff --git a/block/bsg.c b/block/bsg.c
index d214e92..8a05a40 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -176,7 +176,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
  * Check if sg_io_v4 from user is allowed and valid
  */
 static int
-bsg_validate_sgv4_hdr(struct request_queue *q, struct sg_io_v4 *hdr, int *rw)
+bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw)
 {
 	int ret = 0;
 
@@ -226,7 +226,7 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 		hdr->dout_xfer_len, (unsigned long long) hdr->din_xferp,
 		hdr->din_xfer_len);
 
-	ret = bsg_validate_sgv4_hdr(q, hdr, &rw);
+	ret = bsg_validate_sgv4_hdr(hdr, &rw);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 5e24d88..c73a6fc 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -16,6 +16,7 @@
 #include <linux/blktrace_api.h>
 #include <linux/blk-cgroup.h>
 #include "blk.h"
+#include "blk-wbt.h"
 
 /*
  * tunables
@@ -667,10 +668,10 @@ static inline void cfqg_put(struct cfq_group *cfqg)
 } while (0)
 
 static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
-					    struct cfq_group *curr_cfqg, int op,
-					    int op_flags)
+					    struct cfq_group *curr_cfqg,
+					    unsigned int op)
 {
-	blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, 1);
+	blkg_rwstat_add(&cfqg->stats.queued, op, 1);
 	cfqg_stats_end_empty_time(&cfqg->stats);
 	cfqg_stats_set_start_group_wait_time(cfqg, curr_cfqg);
 }
@@ -684,30 +685,29 @@ static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
 #endif
 }
 
-static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op,
-					       int op_flags)
+static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg,
+					       unsigned int op)
 {
-	blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, -1);
+	blkg_rwstat_add(&cfqg->stats.queued, op, -1);
 }
 
-static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op,
-					       int op_flags)
+static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg,
+					       unsigned int op)
 {
-	blkg_rwstat_add(&cfqg->stats.merged, op, op_flags, 1);
+	blkg_rwstat_add(&cfqg->stats.merged, op, 1);
 }
 
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time, int op,
-			int op_flags)
+			uint64_t start_time, uint64_t io_start_time,
+			unsigned int op)
 {
 	struct cfqg_stats *stats = &cfqg->stats;
 	unsigned long long now = sched_clock();
 
 	if (time_after64(now, io_start_time))
-		blkg_rwstat_add(&stats->service_time, op, op_flags,
-				now - io_start_time);
+		blkg_rwstat_add(&stats->service_time, op, now - io_start_time);
 	if (time_after64(io_start_time, start_time))
-		blkg_rwstat_add(&stats->wait_time, op, op_flags,
+		blkg_rwstat_add(&stats->wait_time, op,
 				io_start_time - start_time);
 }
 
@@ -786,16 +786,16 @@ static inline void cfqg_put(struct cfq_group *cfqg) { }
 #define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0)
 
 static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
-			struct cfq_group *curr_cfqg, int op, int op_flags) { }
+			struct cfq_group *curr_cfqg, unsigned int op) { }
 static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
 			uint64_t time, unsigned long unaccounted_time) { }
-static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op,
-			int op_flags) { }
-static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op,
-			int op_flags) { }
+static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg,
+			unsigned int op) { }
+static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg,
+			unsigned int op) { }
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time, int op,
-			int op_flags) { }
+			uint64_t start_time, uint64_t io_start_time,
+			unsigned int op) { }
 
 #endif	/* CONFIG_CFQ_GROUP_IOSCHED */
 
@@ -913,15 +913,6 @@ static inline struct cfq_data *cic_to_cfqd(struct cfq_io_cq *cic)
 }
 
 /*
- * We regard a request as SYNC, if it's either a read or has the SYNC bit
- * set (in which case it could also be direct WRITE).
- */
-static inline bool cfq_bio_sync(struct bio *bio)
-{
-	return bio_data_dir(bio) == READ || (bio->bi_opf & REQ_SYNC);
-}
-
-/*
  * scheduler run of queue, if there are requests pending and no one in the
  * driver that will restart queueing
  */
@@ -1596,7 +1587,7 @@ static struct blkcg_policy_data *cfq_cpd_alloc(gfp_t gfp)
 {
 	struct cfq_group_data *cgd;
 
-	cgd = kzalloc(sizeof(*cgd), GFP_KERNEL);
+	cgd = kzalloc(sizeof(*cgd), gfp);
 	if (!cgd)
 		return NULL;
 	return &cgd->cpd;
@@ -2474,10 +2465,10 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
 {
 	elv_rb_del(&cfqq->sort_list, rq);
 	cfqq->queued[rq_is_sync(rq)]--;
-	cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags);
+	cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
 	cfq_add_rq_rb(rq);
 	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqq->cfqd->serving_group,
-				 req_op(rq), rq->cmd_flags);
+				 rq->cmd_flags);
 }
 
 static struct request *
@@ -2491,7 +2482,7 @@ cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio)
 	if (!cic)
 		return NULL;
 
-	cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
+	cfqq = cic_to_cfqq(cic, op_is_sync(bio->bi_opf));
 	if (cfqq)
 		return elv_rb_find(&cfqq->sort_list, bio_end_sector(bio));
 
@@ -2530,7 +2521,7 @@ static void cfq_remove_request(struct request *rq)
 	cfq_del_rq_rb(rq);
 
 	cfqq->cfqd->rq_queued--;
-	cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags);
+	cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
 	if (rq->cmd_flags & REQ_PRIO) {
 		WARN_ON(!cfqq->prio_pending);
 		cfqq->prio_pending--;
@@ -2565,7 +2556,7 @@ static void cfq_merged_request(struct request_queue *q, struct request *req,
 static void cfq_bio_merged(struct request_queue *q, struct request *req,
 				struct bio *bio)
 {
-	cfqg_stats_update_io_merged(RQ_CFQG(req), bio_op(bio), bio->bi_opf);
+	cfqg_stats_update_io_merged(RQ_CFQG(req), bio->bi_opf);
 }
 
 static void
@@ -2588,7 +2579,7 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	if (cfqq->next_rq == next)
 		cfqq->next_rq = rq;
 	cfq_remove_request(next);
-	cfqg_stats_update_io_merged(RQ_CFQG(rq), req_op(next), next->cmd_flags);
+	cfqg_stats_update_io_merged(RQ_CFQG(rq), next->cmd_flags);
 
 	cfqq = RQ_CFQQ(next);
 	/*
@@ -2605,13 +2596,14 @@ static int cfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 			       struct bio *bio)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
+	bool is_sync = op_is_sync(bio->bi_opf);
 	struct cfq_io_cq *cic;
 	struct cfq_queue *cfqq;
 
 	/*
 	 * Disallow merge of a sync bio into an async request.
 	 */
-	if (cfq_bio_sync(bio) && !rq_is_sync(rq))
+	if (is_sync && !rq_is_sync(rq))
 		return false;
 
 	/*
@@ -2622,7 +2614,7 @@ static int cfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 	if (!cic)
 		return false;
 
-	cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
+	cfqq = cic_to_cfqq(cic, is_sync);
 	return cfqq == RQ_CFQQ(rq);
 }
 
@@ -3771,9 +3763,11 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 	struct cfq_data *cfqd = cic_to_cfqd(cic);
 	struct cfq_queue *cfqq;
 	uint64_t serial_nr;
+	bool nonroot_cg;
 
 	rcu_read_lock();
 	serial_nr = bio_blkcg(bio)->css.serial_nr;
+	nonroot_cg = bio_blkcg(bio) != &blkcg_root;
 	rcu_read_unlock();
 
 	/*
@@ -3784,6 +3778,14 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 		return;
 
 	/*
+	 * If we have a non-root cgroup, we can depend on that to
+	 * do proper throttling of writes. Turn off wbt for that
+	 * case, if it was enabled by default.
+	 */
+	if (nonroot_cg)
+		wbt_disable_default(cfqd->queue);
+
+	/*
 	 * Drop reference to queues.  New queues will be assigned in new
 	 * group upon arrival of fresh requests.
 	 */
@@ -3854,7 +3856,8 @@ cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 			goto out;
 	}
 
-	cfqq = kmem_cache_alloc_node(cfq_pool, GFP_NOWAIT | __GFP_ZERO,
+	cfqq = kmem_cache_alloc_node(cfq_pool,
+				     GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN,
 				     cfqd->queue->node);
 	if (!cfqq) {
 		cfqq = &cfqd->oom_cfqq;
@@ -3923,6 +3926,12 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		cfqq->seek_history |= (sdist > CFQQ_SEEK_THR);
 }
 
+static inline bool req_noidle(struct request *req)
+{
+	return req_op(req) == REQ_OP_WRITE &&
+		(req->cmd_flags & (REQ_SYNC | REQ_IDLE)) == REQ_SYNC;
+}
+
 /*
  * Disable idle window if the process thinks too long or seeks so much that
  * it doesn't matter
@@ -3944,7 +3953,7 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	if (cfqq->queued[0] + cfqq->queued[1] >= 4)
 		cfq_mark_cfqq_deep(cfqq);
 
-	if (cfqq->next_rq && (cfqq->next_rq->cmd_flags & REQ_NOIDLE))
+	if (cfqq->next_rq && req_noidle(cfqq->next_rq))
 		enable_idle = 0;
 	else if (!atomic_read(&cic->icq.ioc->active_ref) ||
 		 !cfqd->cfq_slice_idle ||
@@ -4142,7 +4151,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 	rq->fifo_time = ktime_get_ns() + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
 	list_add_tail(&rq->queuelist, &cfqq->fifo);
 	cfq_add_rq_rb(rq);
-	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group, req_op(rq),
+	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group,
 				 rq->cmd_flags);
 	cfq_rq_enqueued(cfqd, cfqq, rq);
 }
@@ -4229,8 +4238,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	const int sync = rq_is_sync(rq);
 	u64 now = ktime_get_ns();
 
-	cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d",
-		     !!(rq->cmd_flags & REQ_NOIDLE));
+	cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", req_noidle(rq));
 
 	cfq_update_hw_tag(cfqd);
 
@@ -4240,8 +4248,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	cfqq->dispatched--;
 	(RQ_CFQG(rq))->dispatched--;
 	cfqg_stats_update_completion(cfqq->cfqg, rq_start_time_ns(rq),
-				     rq_io_start_time_ns(rq), req_op(rq),
-				     rq->cmd_flags);
+				     rq_io_start_time_ns(rq), rq->cmd_flags);
 
 	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
 
@@ -4319,14 +4326,14 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		cfq_schedule_dispatch(cfqd);
 }
 
-static void cfqq_boost_on_prio(struct cfq_queue *cfqq, int op_flags)
+static void cfqq_boost_on_prio(struct cfq_queue *cfqq, unsigned int op)
 {
 	/*
 	 * If REQ_PRIO is set, boost class and prio level, if it's below
 	 * BE/NORM. If prio is not set, restore the potentially boosted
 	 * class/prio level.
 	 */
-	if (!(op_flags & REQ_PRIO)) {
+	if (!(op & REQ_PRIO)) {
 		cfqq->ioprio_class = cfqq->org_ioprio_class;
 		cfqq->ioprio = cfqq->org_ioprio;
 	} else {
@@ -4347,7 +4354,7 @@ static inline int __cfq_may_queue(struct cfq_queue *cfqq)
 	return ELV_MQUEUE_MAY;
 }
 
-static int cfq_may_queue(struct request_queue *q, int op, int op_flags)
+static int cfq_may_queue(struct request_queue *q, unsigned int op)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct task_struct *tsk = current;
@@ -4364,10 +4371,10 @@ static int cfq_may_queue(struct request_queue *q, int op, int op_flags)
 	if (!cic)
 		return ELV_MQUEUE_MAY;
 
-	cfqq = cic_to_cfqq(cic, rw_is_sync(op, op_flags));
+	cfqq = cic_to_cfqq(cic, op_is_sync(op));
 	if (cfqq) {
 		cfq_init_prio_data(cfqq, cic);
-		cfqq_boost_on_prio(cfqq, op_flags);
+		cfqq_boost_on_prio(cfqq, op);
 
 		return __cfq_may_queue(cfqq);
 	}
diff --git a/block/elevator.c b/block/elevator.c
index f7d973a..40f0c04 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -245,31 +245,31 @@ EXPORT_SYMBOL(elevator_exit);
 static inline void __elv_rqhash_del(struct request *rq)
 {
 	hash_del(&rq->hash);
-	rq->cmd_flags &= ~REQ_HASHED;
+	rq->rq_flags &= ~RQF_HASHED;
 }
 
-static void elv_rqhash_del(struct request_queue *q, struct request *rq)
+void elv_rqhash_del(struct request_queue *q, struct request *rq)
 {
 	if (ELV_ON_HASH(rq))
 		__elv_rqhash_del(rq);
 }
 
-static void elv_rqhash_add(struct request_queue *q, struct request *rq)
+void elv_rqhash_add(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
 	BUG_ON(ELV_ON_HASH(rq));
 	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
-	rq->cmd_flags |= REQ_HASHED;
+	rq->rq_flags |= RQF_HASHED;
 }
 
-static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
+void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
 {
 	__elv_rqhash_del(rq);
 	elv_rqhash_add(q, rq);
 }
 
-static struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
+struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
 {
 	struct elevator_queue *e = q->elevator;
 	struct hlist_node *next;
@@ -352,7 +352,6 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 {
 	sector_t boundary;
 	struct list_head *entry;
-	int stop_flags;
 
 	if (q->last_merge == rq)
 		q->last_merge = NULL;
@@ -362,7 +361,6 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 	q->nr_sorted--;
 
 	boundary = q->end_sector;
-	stop_flags = REQ_SOFTBARRIER | REQ_STARTED;
 	list_for_each_prev(entry, &q->queue_head) {
 		struct request *pos = list_entry_rq(entry);
 
@@ -370,7 +368,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 			break;
 		if (rq_data_dir(rq) != rq_data_dir(pos))
 			break;
-		if (pos->cmd_flags & stop_flags)
+		if (pos->rq_flags & (RQF_STARTED | RQF_SOFTBARRIER))
 			break;
 		if (blk_rq_pos(rq) >= boundary) {
 			if (blk_rq_pos(pos) < boundary)
@@ -510,7 +508,7 @@ void elv_merge_requests(struct request_queue *q, struct request *rq,
 			     struct request *next)
 {
 	struct elevator_queue *e = q->elevator;
-	const int next_sorted = next->cmd_flags & REQ_SORTED;
+	const int next_sorted = next->rq_flags & RQF_SORTED;
 
 	if (next_sorted && e->type->ops.elevator_merge_req_fn)
 		e->type->ops.elevator_merge_req_fn(q, rq, next);
@@ -537,13 +535,13 @@ void elv_bio_merged(struct request_queue *q, struct request *rq,
 #ifdef CONFIG_PM
 static void blk_pm_requeue_request(struct request *rq)
 {
-	if (rq->q->dev && !(rq->cmd_flags & REQ_PM))
+	if (rq->q->dev && !(rq->rq_flags & RQF_PM))
 		rq->q->nr_pending--;
 }
 
 static void blk_pm_add_request(struct request_queue *q, struct request *rq)
 {
-	if (q->dev && !(rq->cmd_flags & REQ_PM) && q->nr_pending++ == 0 &&
+	if (q->dev && !(rq->rq_flags & RQF_PM) && q->nr_pending++ == 0 &&
 	    (q->rpm_status == RPM_SUSPENDED || q->rpm_status == RPM_SUSPENDING))
 		pm_request_resume(q->dev);
 }
@@ -563,11 +561,11 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
 	 */
 	if (blk_account_rq(rq)) {
 		q->in_flight[rq_is_sync(rq)]--;
-		if (rq->cmd_flags & REQ_SORTED)
+		if (rq->rq_flags & RQF_SORTED)
 			elv_deactivate_rq(q, rq);
 	}
 
-	rq->cmd_flags &= ~REQ_STARTED;
+	rq->rq_flags &= ~RQF_STARTED;
 
 	blk_pm_requeue_request(rq);
 
@@ -597,13 +595,13 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 
 	rq->q = q;
 
-	if (rq->cmd_flags & REQ_SOFTBARRIER) {
+	if (rq->rq_flags & RQF_SOFTBARRIER) {
 		/* barriers are scheduling boundary, update end_sector */
 		if (rq->cmd_type == REQ_TYPE_FS) {
 			q->end_sector = rq_end_sector(rq);
 			q->boundary_rq = rq;
 		}
-	} else if (!(rq->cmd_flags & REQ_ELVPRIV) &&
+	} else if (!(rq->rq_flags & RQF_ELVPRIV) &&
 		    (where == ELEVATOR_INSERT_SORT ||
 		     where == ELEVATOR_INSERT_SORT_MERGE))
 		where = ELEVATOR_INSERT_BACK;
@@ -611,12 +609,12 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 	switch (where) {
 	case ELEVATOR_INSERT_REQUEUE:
 	case ELEVATOR_INSERT_FRONT:
-		rq->cmd_flags |= REQ_SOFTBARRIER;
+		rq->rq_flags |= RQF_SOFTBARRIER;
 		list_add(&rq->queuelist, &q->queue_head);
 		break;
 
 	case ELEVATOR_INSERT_BACK:
-		rq->cmd_flags |= REQ_SOFTBARRIER;
+		rq->rq_flags |= RQF_SOFTBARRIER;
 		elv_drain_elevator(q);
 		list_add_tail(&rq->queuelist, &q->queue_head);
 		/*
@@ -642,7 +640,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 			break;
 	case ELEVATOR_INSERT_SORT:
 		BUG_ON(rq->cmd_type != REQ_TYPE_FS);
-		rq->cmd_flags |= REQ_SORTED;
+		rq->rq_flags |= RQF_SORTED;
 		q->nr_sorted++;
 		if (rq_mergeable(rq)) {
 			elv_rqhash_add(q, rq);
@@ -659,7 +657,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 		break;
 
 	case ELEVATOR_INSERT_FLUSH:
-		rq->cmd_flags |= REQ_SOFTBARRIER;
+		rq->rq_flags |= RQF_SOFTBARRIER;
 		blk_insert_flush(rq);
 		break;
 	default:
@@ -716,12 +714,12 @@ void elv_put_request(struct request_queue *q, struct request *rq)
 		e->type->ops.elevator_put_req_fn(rq);
 }
 
-int elv_may_queue(struct request_queue *q, int op, int op_flags)
+int elv_may_queue(struct request_queue *q, unsigned int op)
 {
 	struct elevator_queue *e = q->elevator;
 
 	if (e->type->ops.elevator_may_queue_fn)
-		return e->type->ops.elevator_may_queue_fn(q, op, op_flags);
+		return e->type->ops.elevator_may_queue_fn(q, op);
 
 	return ELV_MQUEUE_MAY;
 }
@@ -735,7 +733,7 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
 	 */
 	if (blk_account_rq(rq)) {
 		q->in_flight[rq_is_sync(rq)]--;
-		if ((rq->cmd_flags & REQ_SORTED) &&
+		if ((rq->rq_flags & RQF_SORTED) &&
 		    e->type->ops.elevator_completed_req_fn)
 			e->type->ops.elevator_completed_req_fn(q, rq);
 	}
diff --git a/block/ioctl.c b/block/ioctl.c
index 755119c..f856963 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -519,6 +519,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 				BLKDEV_DISCARD_SECURE);
 	case BLKZEROOUT:
 		return blk_ioctl_zeroout(bdev, mode, arg);
+	case BLKREPORTZONE:
+		return blkdev_report_zones_ioctl(bdev, mode, cmd, arg);
+	case BLKRESETZONE:
+		return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg);
 	case HDIO_GETGEO:
 		return blkdev_getgeo(bdev, argp);
 	case BLKRAGET:
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 71d9ed9..d7beb6b 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -430,6 +430,56 @@ static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
 	return 0;
 }
 
+static bool part_zone_aligned(struct gendisk *disk,
+			      struct block_device *bdev,
+			      sector_t from, sector_t size)
+{
+	unsigned int zone_size = bdev_zone_size(bdev);
+
+	/*
+	 * If this function is called, then the disk is a zoned block device
+	 * (host-aware or host-managed). This can be detected even if the
+	 * zoned block device support is disabled (CONFIG_BLK_DEV_ZONED not
+	 * set). In this case, however, only host-aware devices will be seen
+	 * as a block device is not created for host-managed devices. Without
+	 * zoned block device support, host-aware drives can still be used as
+	 * regular block devices (no zone operation) and their zone size will
+	 * be reported as 0. Allow this case.
+	 */
+	if (!zone_size)
+		return true;
+
+	/*
+	 * Check partition start and size alignement. If the drive has a
+	 * smaller last runt zone, ignore it and allow the partition to
+	 * use it. Check the zone size too: it should be a power of 2 number
+	 * of sectors.
+	 */
+	if (WARN_ON_ONCE(!is_power_of_2(zone_size))) {
+		u32 rem;
+
+		div_u64_rem(from, zone_size, &rem);
+		if (rem)
+			return false;
+		if ((from + size) < get_capacity(disk)) {
+			div_u64_rem(size, zone_size, &rem);
+			if (rem)
+				return false;
+		}
+
+	} else {
+
+		if (from & (zone_size - 1))
+			return false;
+		if ((from + size) < get_capacity(disk) &&
+		    (size & (zone_size - 1)))
+			return false;
+
+	}
+
+	return true;
+}
+
 int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
 {
 	struct parsed_partitions *state = NULL;
@@ -529,6 +579,21 @@ rescan:
 			}
 		}
 
+		/*
+		 * On a zoned block device, partitions should be aligned on the
+		 * device zone size (i.e. zone boundary crossing not allowed).
+		 * Otherwise, resetting the write pointer of the last zone of
+		 * one partition may impact the following partition.
+		 */
+		if (bdev_is_zoned(bdev) &&
+		    !part_zone_aligned(disk, bdev, from, size)) {
+			printk(KERN_WARNING
+			       "%s: p%d start %llu+%llu is not zone aligned\n",
+			       disk->disk_name, p, (unsigned long long) from,
+			       (unsigned long long) size);
+			continue;
+		}
+
 		part = add_partition(disk, p, from, size,
 				     state->parts[p].flags,
 				     &state->parts[p].info);