From 15bfd21fbc5d35834b9ea383dc458a1f0c9e3434 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Tue, 26 Jun 2018 09:14:58 -0600
Subject: block: Fix transfer when chunk sectors exceeds max

A device may have boundary restrictions where the number of sectors
between boundaries exceeds its max transfer size. In this case, we need
to cap the max size to the smaller of the two limits.

Reported-by: Jitendra Bhivare <jitendra.bhivare@broadcom.com>
Tested-by: Jitendra Bhivare <jitendra.bhivare@broadcom.com>
Cc: <stable@vger.kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9154570edf29..79226ca8f80f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1119,8 +1119,8 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q,
 	if (!q->limits.chunk_sectors)
 		return q->limits.max_sectors;
 
-	return q->limits.chunk_sectors -
-			(offset & (q->limits.chunk_sectors - 1));
+	return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors -
+			(offset & (q->limits.chunk_sectors - 1))));
 }
 
 static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
-- 
cgit v1.3-18-gd494


From 6b1d83d274486615cc341e410467a98fd9c27c0a Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:55:19 -0700
Subject: block: Remove bdev_nr_zones()

Remove this function since it has no callers. This function was
introduced in commit 6cc77e9cb080 ("block: introduce zoned block
devices zone write locking").

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Matias Bjorling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 79226ca8f80f..49a400afb146 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1639,15 +1639,6 @@ static inline unsigned int bdev_zone_sectors(struct block_device *bdev)
 	return 0;
 }
 
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return blk_queue_nr_zones(q);
-	return 0;
-}
-
 static inline int queue_dma_alignment(struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
-- 
cgit v1.3-18-gd494


From 7c8542b7982264226cf94102950343185869b584 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:55:20 -0700
Subject: block: Inline blk_queue_nr_zones()

Since the implementation of blk_queue_nr_zones() is trivial and since
it only has a single caller, inline this function.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Matias Bjorling <mb@lightnvm.io>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c | 2 +-
 include/linux/blkdev.h | 5 -----
 2 files changed, 1 insertion(+), 6 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 1c4532e92938..26e1f8e425a8 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -214,7 +214,7 @@ static int queue_zone_wlock_show(void *data, struct seq_file *m)
 	if (!q->seq_zones_wlock)
 		return 0;
 
-	for (i = 0; i < blk_queue_nr_zones(q); i++)
+	for (i = 0; i < q->nr_zones; i++)
 		if (test_bit(i, q->seq_zones_wlock))
 			seq_printf(m, "%u\n", i);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 49a400afb146..905daa7c647e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -800,11 +800,6 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
 	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
 
-static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
-{
-	return q->nr_zones;
-}
-
 static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 					     sector_t sector)
 {
-- 
cgit v1.3-18-gd494


From 6a5ac9846508ad7d1d23881d9d5add35f2e6ae71 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:55:21 -0700
Subject: block: Make struct request_queue smaller for CONFIG_BLK_DEV_ZONED=n

Exclude zoned block device members from struct request_queue for
CONFIG_BLK_DEV_ZONED == n. Avoid breaking the build by only building
the code that uses these struct request_queue members if
CONFIG_BLK_DEV_ZONED != n.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Matias Bjorling <mb@lightnvm.io>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/Kconfig                |  4 ++++
 block/Makefile               |  1 +
 block/blk-mq-debugfs-zoned.c | 24 ++++++++++++++++++++++++
 block/blk-mq-debugfs.c       | 15 ---------------
 block/blk-mq-debugfs.h       |  9 +++++++++
 include/linux/blkdev.h       |  6 ++++++
 6 files changed, 44 insertions(+), 15 deletions(-)
 create mode 100644 block/blk-mq-debugfs-zoned.c

(limited to 'include/linux/blkdev.h')

diff --git a/block/Kconfig b/block/Kconfig
index eb50fd4977c2..dfe7bc770fc9 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -177,6 +177,10 @@ config BLK_DEBUG_FS
 	Unless you are building a kernel for a tiny system, you should
 	say Y here.
 
+config BLK_DEBUG_FS_ZONED
+       bool
+       default BLK_DEBUG_FS && BLK_DEV_ZONED
+
 config BLK_SED_OPAL
 	bool "Logic for interfacing with Opal enabled SEDs"
 	---help---
diff --git a/block/Makefile b/block/Makefile
index 6a56303b9925..a8f94cdb75c3 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -34,4 +34,5 @@ obj-$(CONFIG_BLK_MQ_RDMA)	+= blk-mq-rdma.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
+obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
 obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
diff --git a/block/blk-mq-debugfs-zoned.c b/block/blk-mq-debugfs-zoned.c
new file mode 100644
index 000000000000..fb2c82c351e4
--- /dev/null
+++ b/block/blk-mq-debugfs-zoned.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Western Digital Corporation or its affiliates.
+ *
+ * This file is released under the GPL.
+ */
+
+#include <linux/blkdev.h>
+#include "blk-mq-debugfs.h"
+
+int queue_zone_wlock_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+	unsigned int i;
+
+	if (!q->seq_zones_wlock)
+		return 0;
+
+	for (i = 0; i < q->nr_zones; i++)
+		if (test_bit(i, q->seq_zones_wlock))
+			seq_printf(m, "%u\n", i);
+
+	return 0;
+}
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 26e1f8e425a8..7efe268e4447 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -206,21 +206,6 @@ static ssize_t queue_write_hint_store(void *data, const char __user *buf,
 	return count;
 }
 
-static int queue_zone_wlock_show(void *data, struct seq_file *m)
-{
-	struct request_queue *q = data;
-	unsigned int i;
-
-	if (!q->seq_zones_wlock)
-		return 0;
-
-	for (i = 0; i < q->nr_zones; i++)
-		if (test_bit(i, q->seq_zones_wlock))
-			seq_printf(m, "%u\n", i);
-
-	return 0;
-}
-
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
 	{ "poll_stat", 0400, queue_poll_stat_show },
 	{ "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops },
diff --git a/block/blk-mq-debugfs.h b/block/blk-mq-debugfs.h
index b9d366e57097..a9160be12be0 100644
--- a/block/blk-mq-debugfs.h
+++ b/block/blk-mq-debugfs.h
@@ -80,4 +80,13 @@ static inline void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hc
 }
 #endif
 
+#ifdef CONFIG_BLK_DEBUG_FS_ZONED
+int queue_zone_wlock_show(void *data, struct seq_file *m);
+#else
+static inline int queue_zone_wlock_show(void *data, struct seq_file *m)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 905daa7c647e..ca5a8b046894 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -592,6 +592,7 @@ struct request_queue {
 
 	struct queue_limits	limits;
 
+#ifdef CONFIG_BLK_DEV_ZONED
 	/*
 	 * Zoned block device information for request dispatch control.
 	 * nr_zones is the total number of zones of the device. This is always
@@ -612,6 +613,7 @@ struct request_queue {
 	unsigned int		nr_zones;
 	unsigned long		*seq_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 	/*
 	 * sg stuff
@@ -800,6 +802,7 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
 	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 					     sector_t sector)
 {
@@ -815,6 +818,7 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q,
 		return false;
 	return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap);
 }
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
 {
@@ -1065,6 +1069,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_rq_zone_no(struct request *rq)
 {
 	return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
@@ -1074,6 +1079,7 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
 {
 	return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
 }
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 /*
  * Some commands like WRITE SAME have a payload or data transfer size which
-- 
cgit v1.3-18-gd494


From 97889f9ac24f8d2fc8e703ea7f80c162bab10d4d Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 25 Jun 2018 19:31:48 +0800
Subject: blk-mq: remove synchronize_rcu() from blk_mq_del_queue_tag_set()

We have to remove synchronize_rcu() from blk_queue_cleanup(),
otherwise long delay can be caused during lun probe. For removing
it, we have to avoid to iterate the set->tag_list in IO path, eg,
blk_mq_sched_restart().

This patch reverts 5b79413946d (Revert "blk-mq: don't handle
TAG_SHARED in restart"). Given we have fixed enough IO hang issue,
and there isn't any reason to restart all queues in one tags any more,
see the following reasons:

1) blk-mq core can deal with shared-tags case well via blk_mq_get_driver_tag(),
which can wake up queues waiting for driver tag.

2) SCSI is a bit special because it may return BLK_STS_RESOURCE if queue,
target or host is ready, but SCSI built-in restart can cover all these well,
see scsi_end_request(), queue will be rerun after any request initiated from
this host/target is completed.

In my test on scsi_debug(8 luns), this patch may improve IOPS by 20% ~ 30%
when running I/O on these 8 luns concurrently.

Fixes: 705cda97ee3a ("blk-mq: Make it safe to use RCU to iterate over blk_mq_tag_set.tag_list")
Cc: Omar Sandoval <osandov@fb.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: linux-scsi@vger.kernel.org
Reported-by: Andrew Jones <drjones@redhat.com>
Tested-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-sched.c   | 85 +++-----------------------------------------------
 block/blk-mq.c         | 10 ++----
 include/linux/blkdev.h |  2 --
 3 files changed, 7 insertions(+), 90 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 56c493c6cd90..4e027f6108ae 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -59,29 +59,16 @@ static void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
 	if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
 		return;
 
-	if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
-		struct request_queue *q = hctx->queue;
-
-		if (!test_and_set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-			atomic_inc(&q->shared_hctx_restart);
-	} else
-		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+	set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 }
 
-static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 {
 	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-		return false;
-
-	if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
-		struct request_queue *q = hctx->queue;
-
-		if (test_and_clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-			atomic_dec(&q->shared_hctx_restart);
-	} else
-		clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+		return;
+	clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 
-	return blk_mq_run_hw_queue(hctx, true);
+	blk_mq_run_hw_queue(hctx, true);
 }
 
 /*
@@ -380,68 +367,6 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
 	return false;
 }
 
-/**
- * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
- * @pos:    loop cursor.
- * @skip:   the list element that will not be examined. Iteration starts at
- *          @skip->next.
- * @head:   head of the list to examine. This list must have at least one
- *          element, namely @skip.
- * @member: name of the list_head structure within typeof(*pos).
- */
-#define list_for_each_entry_rcu_rr(pos, skip, head, member)		\
-	for ((pos) = (skip);						\
-	     (pos = (pos)->member.next != (head) ? list_entry_rcu(	\
-			(pos)->member.next, typeof(*pos), member) :	\
-	      list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \
-	     (pos) != (skip); )
-
-/*
- * Called after a driver tag has been freed to check whether a hctx needs to
- * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware
- * queues in a round-robin fashion if the tag set of @hctx is shared with other
- * hardware queues.
- */
-void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
-{
-	struct blk_mq_tags *const tags = hctx->tags;
-	struct blk_mq_tag_set *const set = hctx->queue->tag_set;
-	struct request_queue *const queue = hctx->queue, *q;
-	struct blk_mq_hw_ctx *hctx2;
-	unsigned int i, j;
-
-	if (set->flags & BLK_MQ_F_TAG_SHARED) {
-		/*
-		 * If this is 0, then we know that no hardware queues
-		 * have RESTART marked. We're done.
-		 */
-		if (!atomic_read(&queue->shared_hctx_restart))
-			return;
-
-		rcu_read_lock();
-		list_for_each_entry_rcu_rr(q, queue, &set->tag_list,
-					   tag_set_list) {
-			queue_for_each_hw_ctx(q, hctx2, i)
-				if (hctx2->tags == tags &&
-				    blk_mq_sched_restart_hctx(hctx2))
-					goto done;
-		}
-		j = hctx->queue_num + 1;
-		for (i = 0; i < queue->nr_hw_queues; i++, j++) {
-			if (j == queue->nr_hw_queues)
-				j = 0;
-			hctx2 = queue->queue_hw_ctx[j];
-			if (hctx2->tags == tags &&
-			    blk_mq_sched_restart_hctx(hctx2))
-				break;
-		}
-done:
-		rcu_read_unlock();
-	} else {
-		blk_mq_sched_restart_hctx(hctx);
-	}
-}
-
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 				 bool run_queue, bool async)
 {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index df84281f6af6..7c6ff13171ef 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2335,15 +2335,10 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		if (shared) {
-			if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-				atomic_inc(&q->shared_hctx_restart);
+		if (shared)
 			hctx->flags |= BLK_MQ_F_TAG_SHARED;
-		} else {
-			if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-				atomic_dec(&q->shared_hctx_restart);
+		else
 			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
-		}
 	}
 }
 
@@ -2374,7 +2369,6 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 		blk_mq_update_tag_set_depth(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
-	synchronize_rcu();
 	INIT_LIST_HEAD(&q->tag_set_list);
 }
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ca5a8b046894..9d05646d5059 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -442,8 +442,6 @@ struct request_queue {
 	int			nr_rqs[2];	/* # allocated [a]sync rqs */
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
-	atomic_t		shared_hctx_restart;
-
 	struct blk_queue_stats	*stats;
 	struct rq_wb		*rq_wb;
 
-- 
cgit v1.3-18-gd494


From a79050434b45959f397042080fd1d70ffa9bd9df Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 09:32:35 -0600
Subject: blk-rq-qos: refactor out common elements of blk-wbt

blkcg-qos is going to do essentially what wbt does, only on a cgroup
basis.  Break out the common code that will be shared between blkcg-qos
and wbt into blk-rq-qos.* so they can both utilize the same
infrastructure.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/Makefile         |   2 +-
 block/blk-core.c       |  12 +-
 block/blk-mq.c         |  12 +-
 block/blk-rq-qos.c     | 178 +++++++++++++++++++++++++++
 block/blk-rq-qos.h     | 106 ++++++++++++++++
 block/blk-settings.c   |   4 +-
 block/blk-sysfs.c      |  22 ++--
 block/blk-wbt.c        | 326 ++++++++++++++++++++++---------------------------
 block/blk-wbt.h        |  63 ++++------
 include/linux/blkdev.h |   4 +-
 10 files changed, 478 insertions(+), 251 deletions(-)
 create mode 100644 block/blk-rq-qos.c
 create mode 100644 block/blk-rq-qos.h

(limited to 'include/linux/blkdev.h')

diff --git a/block/Makefile b/block/Makefile
index a8f94cdb75c3..57d0f47ab05f 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o partition-generic.o ioprio.o \
-			badblocks.o partitions/
+			badblocks.o partitions/ blk-rq-qos.o
 
 obj-$(CONFIG_BOUNCE)		+= bounce.o
 obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o
diff --git a/block/blk-core.c b/block/blk-core.c
index 2ff8e131a892..b33a73bcf2d0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1645,7 +1645,7 @@ 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);
+	rq_qos_requeue(q, rq);
 
 	if (rq->rq_flags & RQF_QUEUED)
 		blk_queue_end_tag(q, rq);
@@ -1752,7 +1752,7 @@ 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);
+	rq_qos_done(q, req);
 
 	/*
 	 * Request may not have originated from ll_rw_blk. if not,
@@ -2044,7 +2044,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	}
 
 get_rq:
-	wb_acct = wbt_wait(q->rq_wb, bio, q->queue_lock);
+	wb_acct = rq_qos_throttle(q, bio, q->queue_lock);
 
 	/*
 	 * Grab a free request. This is might sleep but can not fail.
@@ -2054,7 +2054,7 @@ get_rq:
 	req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO);
 	if (IS_ERR(req)) {
 		blk_queue_exit(q);
-		__wbt_done(q->rq_wb, wb_acct);
+		rq_qos_cleanup(q, wb_acct);
 		if (PTR_ERR(req) == -ENOMEM)
 			bio->bi_status = BLK_STS_RESOURCE;
 		else
@@ -2983,7 +2983,7 @@ void blk_start_request(struct request *req)
 		req->throtl_size = blk_rq_sectors(req);
 #endif
 		req->rq_flags |= RQF_STATS;
-		wbt_issue(req->q->rq_wb, req);
+		rq_qos_issue(req->q, req);
 	}
 
 	BUG_ON(blk_rq_is_complete(req));
@@ -3207,7 +3207,7 @@ void blk_finish_request(struct request *req, blk_status_t error)
 	blk_account_io_done(req, now);
 
 	if (req->end_io) {
-		wbt_done(req->q->rq_wb, req);
+		rq_qos_done(q, req);
 		req->end_io(req, error);
 	} else {
 		if (blk_bidi_rq(req))
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 850fdd02c385..ea2a226457fa 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -504,7 +504,7 @@ void blk_mq_free_request(struct request *rq)
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->backing_dev_info);
 
-	wbt_done(q->rq_wb, rq);
+	rq_qos_done(q, rq);
 
 	if (blk_rq_rl(rq))
 		blk_put_rl(blk_rq_rl(rq));
@@ -527,7 +527,7 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 	blk_account_io_done(rq, now);
 
 	if (rq->end_io) {
-		wbt_done(rq->q->rq_wb, rq);
+		rq_qos_done(rq->q, rq);
 		rq->end_io(rq, error);
 	} else {
 		if (unlikely(blk_bidi_rq(rq)))
@@ -641,7 +641,7 @@ void blk_mq_start_request(struct request *rq)
 		rq->throtl_size = blk_rq_sectors(rq);
 #endif
 		rq->rq_flags |= RQF_STATS;
-		wbt_issue(q->rq_wb, rq);
+		rq_qos_issue(q, rq);
 	}
 
 	WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);
@@ -667,7 +667,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 	blk_mq_put_driver_tag(rq);
 
 	trace_block_rq_requeue(q, rq);
-	wbt_requeue(q->rq_wb, rq);
+	rq_qos_requeue(q, rq);
 
 	if (blk_mq_request_started(rq)) {
 		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
@@ -1806,13 +1806,13 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	if (blk_mq_sched_bio_merge(q, bio))
 		return BLK_QC_T_NONE;
 
-	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
+	wb_acct = rq_qos_throttle(q, bio, NULL);
 
 	trace_block_getrq(q, bio, bio->bi_opf);
 
 	rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
-		__wbt_done(q->rq_wb, wb_acct);
+		rq_qos_cleanup(q, wb_acct);
 		if (bio->bi_opf & REQ_NOWAIT)
 			bio_wouldblock_error(bio);
 		return BLK_QC_T_NONE;
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
new file mode 100644
index 000000000000..d2f2af8aa10c
--- /dev/null
+++ b/block/blk-rq-qos.c
@@ -0,0 +1,178 @@
+#include "blk-rq-qos.h"
+
+#include "blk-wbt.h"
+
+/*
+ * 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;
+}
+
+bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit)
+{
+	return atomic_inc_below(&rq_wait->inflight, limit);
+}
+
+void rq_qos_cleanup(struct request_queue *q, enum wbt_flags wb_acct)
+{
+	struct rq_qos *rqos;
+
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->cleanup)
+			rqos->ops->cleanup(rqos, wb_acct);
+	}
+}
+
+void rq_qos_done(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->done)
+			rqos->ops->done(rqos, rq);
+	}
+}
+
+void rq_qos_issue(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->issue)
+			rqos->ops->issue(rqos, rq);
+	}
+}
+
+void rq_qos_requeue(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->requeue)
+			rqos->ops->requeue(rqos, rq);
+	}
+}
+
+enum wbt_flags rq_qos_throttle(struct request_queue *q, struct bio *bio,
+			       spinlock_t *lock)
+{
+	struct rq_qos *rqos;
+	enum wbt_flags flags = 0;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->throttle)
+			flags |= rqos->ops->throttle(rqos, bio, lock);
+	}
+	return flags;
+}
+
+/*
+ * Return true, if we can't increase the depth further by scaling
+ */
+bool rq_depth_calc_max_depth(struct rq_depth *rqd)
+{
+	unsigned int depth;
+	bool ret = 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 (rqd->queue_depth == 1) {
+		if (rqd->scale_step > 0)
+			rqd->max_depth = 1;
+		else {
+			rqd->max_depth = 2;
+			ret = true;
+		}
+	} 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, rqd->default_depth,
+			      rqd->queue_depth);
+		if (rqd->scale_step > 0)
+			depth = 1 + ((depth - 1) >> min(31, rqd->scale_step));
+		else if (rqd->scale_step < 0) {
+			unsigned int maxd = 3 * rqd->queue_depth / 4;
+
+			depth = 1 + ((depth - 1) << -rqd->scale_step);
+			if (depth > maxd) {
+				depth = maxd;
+				ret = true;
+			}
+		}
+
+		rqd->max_depth = depth;
+	}
+
+	return ret;
+}
+
+void rq_depth_scale_up(struct rq_depth *rqd)
+{
+	/*
+	 * Hit max in previous round, stop here
+	 */
+	if (rqd->scaled_max)
+		return;
+
+	rqd->scale_step--;
+
+	rqd->scaled_max = rq_depth_calc_max_depth(rqd);
+}
+
+/*
+ * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
+ * had a latency violation.
+ */
+void rq_depth_scale_down(struct rq_depth *rqd, 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 (rqd->max_depth == 1)
+		return;
+
+	if (rqd->scale_step < 0 && hard_throttle)
+		rqd->scale_step = 0;
+	else
+		rqd->scale_step++;
+
+	rqd->scaled_max = false;
+	rq_depth_calc_max_depth(rqd);
+}
+
+void rq_qos_exit(struct request_queue *q)
+{
+	while (q->rq_qos) {
+		struct rq_qos *rqos = q->rq_qos;
+		q->rq_qos = rqos->next;
+		rqos->ops->exit(rqos);
+	}
+}
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
new file mode 100644
index 000000000000..f9a39bd6ece3
--- /dev/null
+++ b/block/blk-rq-qos.h
@@ -0,0 +1,106 @@
+#ifndef RQ_QOS_H
+#define RQ_QOS_H
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/blk_types.h>
+#include <linux/atomic.h>
+#include <linux/wait.h>
+
+enum rq_qos_id {
+	RQ_QOS_WBT,
+	RQ_QOS_CGROUP,
+};
+
+struct rq_wait {
+	wait_queue_head_t wait;
+	atomic_t inflight;
+};
+
+struct rq_qos {
+	struct rq_qos_ops *ops;
+	struct request_queue *q;
+	enum rq_qos_id id;
+	struct rq_qos *next;
+};
+
+struct rq_qos_ops {
+	enum wbt_flags (*throttle)(struct rq_qos *, struct bio *,
+				   spinlock_t *);
+	void (*issue)(struct rq_qos *, struct request *);
+	void (*requeue)(struct rq_qos *, struct request *);
+	void (*done)(struct rq_qos *, struct request *);
+	void (*cleanup)(struct rq_qos *, enum wbt_flags);
+	void (*exit)(struct rq_qos *);
+};
+
+struct rq_depth {
+	unsigned int max_depth;
+
+	int scale_step;
+	bool scaled_max;
+
+	unsigned int queue_depth;
+	unsigned int default_depth;
+};
+
+static inline struct rq_qos *rq_qos_id(struct request_queue *q,
+				       enum rq_qos_id id)
+{
+	struct rq_qos *rqos;
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->id == id)
+			break;
+	}
+	return rqos;
+}
+
+static inline struct rq_qos *wbt_rq_qos(struct request_queue *q)
+{
+	return rq_qos_id(q, RQ_QOS_WBT);
+}
+
+static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q)
+{
+	return rq_qos_id(q, RQ_QOS_CGROUP);
+}
+
+static inline void rq_wait_init(struct rq_wait *rq_wait)
+{
+	atomic_set(&rq_wait->inflight, 0);
+	init_waitqueue_head(&rq_wait->wait);
+}
+
+static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
+{
+	rqos->next = q->rq_qos;
+	q->rq_qos = rqos;
+}
+
+static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
+{
+	struct rq_qos *cur, *prev = NULL;
+	for (cur = q->rq_qos; cur; cur = cur->next) {
+		if (cur == rqos) {
+			if (prev)
+				prev->next = rqos->next;
+			else
+				q->rq_qos = cur;
+			break;
+		}
+		prev = cur;
+	}
+}
+
+bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit);
+void rq_depth_scale_up(struct rq_depth *rqd);
+void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
+bool rq_depth_calc_max_depth(struct rq_depth *rqd);
+
+void rq_qos_cleanup(struct request_queue *, enum wbt_flags);
+void rq_qos_done(struct request_queue *, struct request *);
+void rq_qos_issue(struct request_queue *, struct request *);
+void rq_qos_requeue(struct request_queue *, struct request *);
+enum wbt_flags rq_qos_throttle(struct request_queue *, struct bio *, spinlock_t *);
+void rq_qos_exit(struct request_queue *);
+#endif
diff --git a/block/blk-settings.c b/block/blk-settings.c
index d1de71124656..053de87d1fda 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -875,7 +875,7 @@ EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
 void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 	q->queue_depth = depth;
-	wbt_set_queue_depth(q->rq_wb, depth);
+	wbt_set_queue_depth(q, depth);
 }
 EXPORT_SYMBOL(blk_set_queue_depth);
 
@@ -900,7 +900,7 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 		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));
+	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 }
 EXPORT_SYMBOL_GPL(blk_queue_write_cache);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 94987b1f69e1..49c29a5d06bb 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -422,16 +422,16 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
 
 static ssize_t queue_wb_lat_show(struct request_queue *q, char *page)
 {
-	if (!q->rq_wb)
+	if (!wbt_rq_qos(q))
 		return -EINVAL;
 
-	return sprintf(page, "%llu\n", div_u64(q->rq_wb->min_lat_nsec, 1000));
+	return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000));
 }
 
 static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 				  size_t count)
 {
-	struct rq_wb *rwb;
+	struct rq_qos *rqos;
 	ssize_t ret;
 	s64 val;
 
@@ -441,23 +441,21 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 	if (val < -1)
 		return -EINVAL;
 
-	rwb = q->rq_wb;
-	if (!rwb) {
+	rqos = wbt_rq_qos(q);
+	if (!rqos) {
 		ret = wbt_init(q);
 		if (ret)
 			return ret;
 	}
 
-	rwb = q->rq_wb;
 	if (val == -1)
-		rwb->min_lat_nsec = wbt_default_latency_nsec(q);
+		val = wbt_default_latency_nsec(q);
 	else if (val >= 0)
-		rwb->min_lat_nsec = val * 1000ULL;
+		val *= 1000ULL;
 
-	if (rwb->enable_state == WBT_STATE_ON_DEFAULT)
-		rwb->enable_state = WBT_STATE_ON_MANUAL;
+	wbt_set_min_lat(q, val);
 
-	wbt_update_limits(rwb);
+	wbt_update_limits(q);
 	return count;
 }
 
@@ -964,7 +962,7 @@ void blk_unregister_queue(struct gendisk *disk)
 	kobject_del(&q->kobj);
 	blk_trace_remove_sysfs(disk_to_dev(disk));
 
-	wbt_exit(q);
+	rq_qos_exit(q);
 
 	mutex_lock(&q->sysfs_lock);
 	if (q->request_fn || (q->mq_ops && q->elevator))
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 4f89b28fa652..6fe20fb823e4 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -25,6 +25,7 @@
 #include <linux/swap.h>
 
 #include "blk-wbt.h"
+#include "blk-rq-qos.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/wbt.h>
@@ -78,28 +79,6 @@ 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)) {
@@ -116,7 +95,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->queue->backing_dev_info->wb;
+	struct bdi_writeback *wb = &rwb->rqos.q->backing_dev_info->wb;
 
 	return time_before(jiffies, wb->dirty_sleep + HZ);
 }
@@ -144,8 +123,9 @@ static void rwb_wake_all(struct rq_wb *rwb)
 	}
 }
 
-void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
+static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct)
 {
+	struct rq_wb *rwb = RQWB(rqos);
 	struct rq_wait *rqw;
 	int inflight, limit;
 
@@ -194,10 +174,9 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
  * 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 request *rq)
+static void wbt_done(struct rq_qos *rqos, struct request *rq)
 {
-	if (!rwb)
-		return;
+	struct rq_wb *rwb = RQWB(rqos);
 
 	if (!wbt_is_tracked(rq)) {
 		if (rwb->sync_cookie == rq) {
@@ -209,72 +188,11 @@ void wbt_done(struct rq_wb *rwb, struct request *rq)
 			wb_timestamp(rwb, &rwb->last_comp);
 	} else {
 		WARN_ON_ONCE(rq == rwb->sync_cookie);
-		__wbt_done(rwb, wbt_flags(rq));
+		__wbt_done(rqos, wbt_flags(rq));
 	}
 	wbt_clear_state(rq);
 }
 
-/*
- * 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)
 {
 	/*
@@ -307,7 +225,8 @@ enum {
 
 static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 {
-	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info;
+	struct rq_depth *rqd = &rwb->rq_depth;
 	u64 thislat;
 
 	/*
@@ -351,7 +270,7 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 		return LAT_EXCEEDED;
 	}
 
-	if (rwb->scale_step)
+	if (rqd->scale_step)
 		trace_wbt_stat(bdi, stat);
 
 	return LAT_OK;
@@ -359,58 +278,48 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 
 static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
 {
-	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info;
+	struct rq_depth *rqd = &rwb->rq_depth;
 
-	trace_wbt_step(bdi, msg, rwb->scale_step, rwb->cur_win_nsec,
-			rwb->wb_background, rwb->wb_normal, rwb->wb_max);
+	trace_wbt_step(bdi, msg, rqd->scale_step, rwb->cur_win_nsec,
+			rwb->wb_background, rwb->wb_normal, rqd->max_depth);
 }
 
-static void scale_up(struct rq_wb *rwb)
+static void calc_wb_limits(struct rq_wb *rwb)
 {
-	/*
-	 * Hit max in previous round, stop here
-	 */
-	if (rwb->scaled_max)
-		return;
+	if (rwb->min_lat_nsec == 0) {
+		rwb->wb_normal = rwb->wb_background = 0;
+	} else if (rwb->rq_depth.max_depth <= 2) {
+		rwb->wb_normal = rwb->rq_depth.max_depth;
+		rwb->wb_background = 1;
+	} else {
+		rwb->wb_normal = (rwb->rq_depth.max_depth + 1) / 2;
+		rwb->wb_background = (rwb->rq_depth.max_depth + 3) / 4;
+	}
+}
 
-	rwb->scale_step--;
+static void scale_up(struct rq_wb *rwb)
+{
+	rq_depth_scale_up(&rwb->rq_depth);
+	calc_wb_limits(rwb);
 	rwb->unknown_cnt = 0;
-
-	rwb->scaled_max = calc_wb_limits(rwb);
-
-	rwb_wake_all(rwb);
-
-	rwb_trace_step(rwb, "step up");
+	rwb_trace_step(rwb, "scale 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;
+	rq_depth_scale_down(&rwb->rq_depth, hard_throttle);
 	calc_wb_limits(rwb);
-	rwb_trace_step(rwb, "step down");
+	rwb->unknown_cnt = 0;
+	rwb_wake_all(rwb);
+	rwb_trace_step(rwb, "scale down");
 }
 
 static void rwb_arm_timer(struct rq_wb *rwb)
 {
-	if (rwb->scale_step > 0) {
+	struct rq_depth *rqd = &rwb->rq_depth;
+
+	if (rqd->scale_step > 0) {
 		/*
 		 * We should speed this up, using some variant of a fast
 		 * integer inverse square root calculation. Since we only do
@@ -418,7 +327,7 @@ static void rwb_arm_timer(struct rq_wb *rwb)
 		 * though.
 		 */
 		rwb->cur_win_nsec = div_u64(rwb->win_nsec << 4,
-					int_sqrt((rwb->scale_step + 1) << 8));
+					int_sqrt((rqd->scale_step + 1) << 8));
 	} else {
 		/*
 		 * For step < 0, we don't want to increase/decrease the
@@ -433,12 +342,13 @@ static void rwb_arm_timer(struct rq_wb *rwb)
 static void wb_timer_fn(struct blk_stat_callback *cb)
 {
 	struct rq_wb *rwb = cb->data;
+	struct rq_depth *rqd = &rwb->rq_depth;
 	unsigned int inflight = wbt_inflight(rwb);
 	int status;
 
 	status = latency_exceeded(rwb, cb->stat);
 
-	trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step,
+	trace_wbt_timer(rwb->rqos.q->backing_dev_info, status, rqd->scale_step,
 			inflight);
 
 	/*
@@ -469,9 +379,9 @@ static void wb_timer_fn(struct blk_stat_callback *cb)
 		 * currently don't have a valid read/write sample. For that
 		 * case, slowly return to center state (step == 0).
 		 */
-		if (rwb->scale_step > 0)
+		if (rqd->scale_step > 0)
 			scale_up(rwb);
-		else if (rwb->scale_step < 0)
+		else if (rqd->scale_step < 0)
 			scale_down(rwb, false);
 		break;
 	default:
@@ -481,19 +391,50 @@ static void wb_timer_fn(struct blk_stat_callback *cb)
 	/*
 	 * Re-arm timer, if we have IO in flight
 	 */
-	if (rwb->scale_step || inflight)
+	if (rqd->scale_step || inflight)
 		rwb_arm_timer(rwb);
 }
 
-void wbt_update_limits(struct rq_wb *rwb)
+static void __wbt_update_limits(struct rq_wb *rwb)
 {
-	rwb->scale_step = 0;
-	rwb->scaled_max = false;
+	struct rq_depth *rqd = &rwb->rq_depth;
+
+	rqd->scale_step = 0;
+	rqd->scaled_max = false;
+
+	rq_depth_calc_max_depth(rqd);
 	calc_wb_limits(rwb);
 
 	rwb_wake_all(rwb);
 }
 
+void wbt_update_limits(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return;
+	__wbt_update_limits(RQWB(rqos));
+}
+
+u64 wbt_get_min_lat(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return 0;
+	return RQWB(rqos)->min_lat_nsec;
+}
+
+void wbt_set_min_lat(struct request_queue *q, u64 val)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return;
+	RQWB(rqos)->min_lat_nsec = val;
+	RQWB(rqos)->enable_state = WBT_STATE_ON_MANUAL;
+	__wbt_update_limits(RQWB(rqos));
+}
+
+
 static bool close_io(struct rq_wb *rwb)
 {
 	const unsigned long now = jiffies;
@@ -520,7 +461,7 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 	 * IO for a bit.
 	 */
 	if ((rw & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd())
-		limit = rwb->wb_max;
+		limit = rwb->rq_depth.max_depth;
 	else if ((rw & REQ_BACKGROUND) || close_io(rwb)) {
 		/*
 		 * If less than 100ms since we completed unrelated IO,
@@ -554,7 +495,7 @@ static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
 	    rqw->wait.head.next != &wait->entry)
 		return false;
 
-	return atomic_inc_below(&rqw->inflight, get_limit(rwb, rw));
+	return rq_wait_inc_below(rqw, get_limit(rwb, rw));
 }
 
 /*
@@ -614,8 +555,10 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
  * in an irq held spinlock, if it holds one when calling this function.
  * If we do sleep, we'll release and re-grab it.
  */
-enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
+static enum wbt_flags wbt_wait(struct rq_qos *rqos, struct bio *bio,
+			       spinlock_t *lock)
 {
+	struct rq_wb *rwb = RQWB(rqos);
 	enum wbt_flags ret = 0;
 
 	if (!rwb_enabled(rwb))
@@ -643,8 +586,10 @@ enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
 	return ret | WBT_TRACKED;
 }
 
-void wbt_issue(struct rq_wb *rwb, struct request *rq)
+void wbt_issue(struct rq_qos *rqos, struct request *rq)
 {
+	struct rq_wb *rwb = RQWB(rqos);
+
 	if (!rwb_enabled(rwb))
 		return;
 
@@ -661,8 +606,9 @@ void wbt_issue(struct rq_wb *rwb, struct request *rq)
 	}
 }
 
-void wbt_requeue(struct rq_wb *rwb, struct request *rq)
+void wbt_requeue(struct rq_qos *rqos, struct request *rq)
 {
+	struct rq_wb *rwb = RQWB(rqos);
 	if (!rwb_enabled(rwb))
 		return;
 	if (rq == rwb->sync_cookie) {
@@ -671,39 +617,30 @@ void wbt_requeue(struct rq_wb *rwb, struct request *rq)
 	}
 }
 
-void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
+void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
-	if (rwb) {
-		rwb->queue_depth = depth;
-		wbt_update_limits(rwb);
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (rqos) {
+		RQWB(rqos)->rq_depth.queue_depth = depth;
+		__wbt_update_limits(RQWB(rqos));
 	}
 }
 
-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.
- */
-void wbt_disable_default(struct request_queue *q)
+void wbt_set_write_cache(struct request_queue *q, bool write_cache_on)
 {
-	struct rq_wb *rwb = q->rq_wb;
-
-	if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT)
-		wbt_exit(q);
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (rqos)
+		RQWB(rqos)->wc = write_cache_on;
 }
-EXPORT_SYMBOL_GPL(wbt_disable_default);
 
 /*
  * Enable wbt if defaults are configured that way
  */
 void wbt_enable_default(struct request_queue *q)
 {
+	struct rq_qos *rqos = wbt_rq_qos(q);
 	/* Throttling already enabled? */
-	if (q->rq_wb)
+	if (rqos)
 		return;
 
 	/* Queue not registered? Maybe shutting down... */
@@ -741,6 +678,41 @@ static int wbt_data_dir(const struct request *rq)
 	return -1;
 }
 
+static void wbt_exit(struct rq_qos *rqos)
+{
+	struct rq_wb *rwb = RQWB(rqos);
+	struct request_queue *q = rqos->q;
+
+	blk_stat_remove_callback(q, rwb->cb);
+	blk_stat_free_callback(rwb->cb);
+	kfree(rwb);
+}
+
+/*
+ * Disable wbt, if enabled by default.
+ */
+void wbt_disable_default(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	struct rq_wb *rwb;
+	if (!rqos)
+		return;
+	rwb = RQWB(rqos);
+	if (rwb->enable_state == WBT_STATE_ON_DEFAULT)
+		rwb->wb_normal = 0;
+}
+EXPORT_SYMBOL_GPL(wbt_disable_default);
+
+
+static struct rq_qos_ops wbt_rqos_ops = {
+	.throttle = wbt_wait,
+	.issue = wbt_issue,
+	.requeue = wbt_requeue,
+	.done = wbt_done,
+	.cleanup = __wbt_done,
+	.exit = wbt_exit,
+};
+
 int wbt_init(struct request_queue *q)
 {
 	struct rq_wb *rwb;
@@ -756,39 +728,29 @@ int wbt_init(struct request_queue *q)
 		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);
-	}
+	for (i = 0; i < WBT_NUM_RWQ; i++)
+		rq_wait_init(&rwb->rq_wait[i]);
 
+	rwb->rqos.id = RQ_QOS_WBT;
+	rwb->rqos.ops = &wbt_rqos_ops;
+	rwb->rqos.q = q;
 	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);
+	rwb->wc = 1;
+	rwb->rq_depth.default_depth = RWB_DEF_DEPTH;
+	__wbt_update_limits(rwb);
 
 	/*
 	 * Assign rwb and add the stats callback.
 	 */
-	q->rq_wb = rwb;
+	rq_qos_add(q, &rwb->rqos);
 	blk_stat_add_callback(q, rwb->cb);
 
 	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));
+	wbt_set_queue_depth(q, blk_queue_depth(q));
+	wbt_set_write_cache(q, 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) {
-		blk_stat_remove_callback(q, rwb->cb);
-		blk_stat_free_callback(rwb->cb);
-		q->rq_wb = NULL;
-		kfree(rwb);
-	}
-}
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index 300df531d0a6..53b20a58c0a2 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -9,6 +9,7 @@
 #include <linux/ktime.h>
 
 #include "blk-stat.h"
+#include "blk-rq-qos.h"
 
 enum wbt_flags {
 	WBT_TRACKED		= 1,	/* write, tracked for throttling */
@@ -35,20 +36,12 @@ enum {
 	WBT_STATE_ON_MANUAL	= 2,
 };
 
-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_* */
 
@@ -67,15 +60,20 @@ struct rq_wb {
 	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_qos rqos;
 	struct rq_wait rq_wait[WBT_NUM_RWQ];
+	struct rq_depth rq_depth;
 };
 
+static inline struct rq_wb *RQWB(struct rq_qos *rqos)
+{
+	return container_of(rqos, struct rq_wb, rqos);
+}
+
 static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 {
 	unsigned int i, ret = 0;
@@ -86,6 +84,7 @@ static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 	return ret;
 }
 
+
 #ifdef CONFIG_BLK_WBT
 
 static inline void wbt_track(struct request *rq, enum wbt_flags flags)
@@ -93,19 +92,16 @@ static inline void wbt_track(struct request *rq, enum wbt_flags flags)
 	rq->wbt_flags |= flags;
 }
 
-void __wbt_done(struct rq_wb *, enum wbt_flags);
-void wbt_done(struct rq_wb *, struct request *);
-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 request *);
-void wbt_issue(struct rq_wb *, struct request *);
+void wbt_update_limits(struct request_queue *);
 void wbt_disable_default(struct request_queue *);
 void wbt_enable_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_get_min_lat(struct request_queue *q);
+void wbt_set_min_lat(struct request_queue *q, u64 val);
+
+void wbt_set_queue_depth(struct request_queue *, unsigned int);
+void wbt_set_write_cache(struct request_queue *, bool);
 
 u64 wbt_default_latency_nsec(struct request_queue *);
 
@@ -114,43 +110,30 @@ u64 wbt_default_latency_nsec(struct request_queue *);
 static inline void wbt_track(struct request *rq, enum wbt_flags flags)
 {
 }
-static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags)
-{
-}
-static inline void wbt_done(struct rq_wb *rwb, struct request *rq)
-{
-}
-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_update_limits(struct request_queue *q)
 {
 }
-static inline void wbt_requeue(struct rq_wb *rwb, struct request *rq)
+static inline void wbt_disable_default(struct request_queue *q)
 {
 }
-static inline void wbt_issue(struct rq_wb *rwb, struct request *rq)
+static inline void wbt_enable_default(struct request_queue *q)
 {
 }
-static inline void wbt_disable_default(struct request_queue *q)
+static inline void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 }
-static inline void wbt_enable_default(struct request_queue *q)
+static inline void wbt_set_write_cache(struct request_queue *q, bool wc)
 {
 }
-static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
+static inline u64 wbt_get_min_lat(struct request_queue *q)
 {
+	return 0;
 }
-static inline void wbt_set_write_cache(struct rq_wb *rwb, bool wc)
+static inline void wbt_set_min_lat(struct request_queue *q, u64 val)
 {
 }
 static inline u64 wbt_default_latency_nsec(struct request_queue *q)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9d05646d5059..137759862f07 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -42,7 +42,7 @@ struct bsg_job;
 struct blkcg_gq;
 struct blk_flush_queue;
 struct pr_ops;
-struct rq_wb;
+struct rq_qos;
 struct blk_queue_stats;
 struct blk_stat_callback;
 
@@ -443,7 +443,7 @@ struct request_queue {
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
 	struct blk_queue_stats	*stats;
-	struct rq_wb		*rq_wb;
+	struct rq_qos		*rq_qos;
 
 	/*
 	 * If blkcg is not used, @q->root_rl serves all requests.  If blkcg
-- 
cgit v1.3-18-gd494


From 05814a10370b3252fe2b0898b6adac3cdd531096 Mon Sep 17 00:00:00 2001
From: Vladimir Zapolskiy <vz@mleia.com>
Date: Fri, 13 Jul 2018 17:07:26 +0300
Subject: block: remove blkdev_entry_to_request() macro

Remove blkdev_entry_to_request() macro, which remained unused through
the observable history, also note that it repeats list_entry_rq() macro
verbatim.

Signed-off-by: Vladimir Zapolskiy <vz@mleia.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 137759862f07..1939ed95f936 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1436,8 +1436,6 @@ enum blk_default_limits {
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
 
-#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
-
 static inline unsigned long queue_segment_boundary(struct request_queue *q)
 {
 	return q->limits.seg_boundary_mask;
-- 
cgit v1.3-18-gd494


From 3f289dcb4b265416a57ca79cf4a324060bb09060 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 18 Jul 2018 04:47:36 -0700
Subject: block: make bdev_ops->rw_page() take a REQ_OP instead of bool

c11f0c0b5bb9 ("block/mm: make bdev_ops->rw_page() take a bool for
read/write") replaced @op with boolean @is_write, which limited the
amount of information going into ->rw_page() and more importantly
page_endio(), which removed the need to expose block internals to mm.

Unfortunately, we want to track discards separately and @is_write
isn't enough information.  This patch updates bdev_ops->rw_page() to
take REQ_OP instead but leaves page_endio() to take bool @is_write.
This allows the block part of operations to have enough information
while not leaking it to mm.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/brd.c           | 14 +++++++-------
 drivers/block/zram/zram_drv.c | 16 ++++++++--------
 drivers/nvdimm/btt.c          | 12 ++++++------
 drivers/nvdimm/pmem.c         | 13 ++++++-------
 fs/block_dev.c                |  6 ++++--
 fs/mpage.c                    |  4 ++--
 include/linux/blkdev.h        |  2 +-
 7 files changed, 34 insertions(+), 33 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index bb976598ee43..df8103dd40ac 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -254,20 +254,20 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
  * Process a single bvec of a bio.
  */
 static int brd_do_bvec(struct brd_device *brd, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
+			unsigned int len, unsigned int off, unsigned int op,
 			sector_t sector)
 {
 	void *mem;
 	int err = 0;
 
-	if (is_write) {
+	if (op_is_write(op)) {
 		err = copy_to_brd_setup(brd, sector, len);
 		if (err)
 			goto out;
 	}
 
 	mem = kmap_atomic(page);
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		copy_from_brd(mem + off, brd, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -296,7 +296,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 		int err;
 
 		err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
-					op_is_write(bio_op(bio)), sector);
+				  bio_op(bio), sector);
 		if (err)
 			goto io_error;
 		sector += len >> SECTOR_SHIFT;
@@ -310,15 +310,15 @@ io_error:
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	int err;
 
 	if (PageTransHuge(page))
 		return -ENOTSUPP;
-	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector);
-	page_endio(page, is_write, err);
+	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
+	page_endio(page, op_is_write(op), err);
 	return err;
 }
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 7436b2d27fa3..78c29044684a 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1274,17 +1274,17 @@ static void zram_bio_discard(struct zram *zram, u32 index,
  * Returns 1 if IO request was successfully submitted.
  */
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, bool is_write, struct bio *bio)
+			int offset, unsigned int op, struct bio *bio)
 {
 	unsigned long start_time = jiffies;
-	int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ;
+	int rw_acct = op_is_write(op) ? REQ_OP_WRITE : REQ_OP_READ;
 	struct request_queue *q = zram->disk->queue;
 	int ret;
 
 	generic_start_io_acct(q, rw_acct, bvec->bv_len >> SECTOR_SHIFT,
 			&zram->disk->part0);
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		atomic64_inc(&zram->stats.num_reads);
 		ret = zram_bvec_read(zram, bvec, index, offset, bio);
 		flush_dcache_page(bvec->bv_page);
@@ -1300,7 +1300,7 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 	zram_slot_unlock(zram, index);
 
 	if (unlikely(ret < 0)) {
-		if (!is_write)
+		if (!op_is_write(op))
 			atomic64_inc(&zram->stats.failed_reads);
 		else
 			atomic64_inc(&zram->stats.failed_writes);
@@ -1338,7 +1338,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 			bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset,
 							unwritten);
 			if (zram_bvec_rw(zram, &bv, index, offset,
-					op_is_write(bio_op(bio)), bio) < 0)
+					 bio_op(bio), bio) < 0)
 				goto out;
 
 			bv.bv_offset += bv.bv_len;
@@ -1390,7 +1390,7 @@ static void zram_slot_free_notify(struct block_device *bdev,
 }
 
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	int offset, ret;
 	u32 index;
@@ -1414,7 +1414,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_len = PAGE_SIZE;
 	bv.bv_offset = 0;
 
-	ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL);
+	ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL);
 out:
 	/*
 	 * If I/O fails, just return error(ie, non-zero) without
@@ -1429,7 +1429,7 @@ out:
 
 	switch (ret) {
 	case 0:
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 		break;
 	case 1:
 		ret = 0;
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 85de8053aa34..0360c015f658 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1423,11 +1423,11 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 
 static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
 			struct page *page, unsigned int len, unsigned int off,
-			bool is_write, sector_t sector)
+			unsigned int op, sector_t sector)
 {
 	int ret;
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		ret = btt_read_pg(btt, bip, page, off, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -1464,7 +1464,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 		}
 
 		err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
-				  op_is_write(bio_op(bio)), iter.bi_sector);
+				  bio_op(bio), iter.bi_sector);
 		if (err) {
 			dev_err(&btt->nd_btt->dev,
 					"io error in %s sector %lld, len %d,\n",
@@ -1483,16 +1483,16 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int btt_rw_page(struct block_device *bdev, sector_t sector,
-		struct page *page, bool is_write)
+		struct page *page, unsigned int op)
 {
 	struct btt *btt = bdev->bd_disk->private_data;
 	int rc;
 	unsigned int len;
 
 	len = hpage_nr_pages(page) * PAGE_SIZE;
-	rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector);
+	rc = btt_do_bvec(btt, NULL, page, len, 0, op, sector);
 	if (rc == 0)
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 
 	return rc;
 }
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 8b1fd7f1a224..dd17acd8fe68 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -120,7 +120,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 }
 
 static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
+			unsigned int len, unsigned int off, unsigned int op,
 			sector_t sector)
 {
 	blk_status_t rc = BLK_STS_OK;
@@ -131,7 +131,7 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		bad_pmem = true;
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		if (unlikely(bad_pmem))
 			rc = BLK_STS_IOERR;
 		else {
@@ -180,8 +180,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
 		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
-				bvec.bv_offset, op_is_write(bio_op(bio)),
-				iter.bi_sector);
+				bvec.bv_offset, bio_op(bio), iter.bi_sector);
 		if (rc) {
 			bio->bi_status = rc;
 			break;
@@ -198,13 +197,13 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int pmem_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	blk_status_t rc;
 
 	rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
-			  0, is_write, sector);
+			  0, op, sector);
 
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core
@@ -213,7 +212,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	 * caused by double completion.
 	 */
 	if (rc == 0)
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 
 	return blk_status_to_errno(rc);
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0dd87aaeb39a..496fb51a1e1a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -665,7 +665,8 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 	result = blk_queue_enter(bdev->bd_queue, 0);
 	if (result)
 		return result;
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, false);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_READ);
 	blk_queue_exit(bdev->bd_queue);
 	return result;
 }
@@ -703,7 +704,8 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 		return result;
 
 	set_page_writeback(page);
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_WRITE);
 	if (result) {
 		end_page_writeback(page);
 	} else {
diff --git a/fs/mpage.c b/fs/mpage.c
index b7e7f570733a..b73638db9866 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -51,8 +51,8 @@ static void mpage_end_io(struct bio *bio)
 
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
-		page_endio(page, op_is_write(bio_op(bio)),
-				blk_status_to_errno(bio->bi_status));
+		page_endio(page, bio_op(bio),
+			   blk_status_to_errno(bio->bi_status));
 	}
 
 	bio_put(bio);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1939ed95f936..331a6cb8805f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1943,7 +1943,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 struct block_device_operations {
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
-	int (*rw_page)(struct block_device *, sector_t, struct page *, bool);
+	int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	unsigned int (*check_events) (struct gendisk *disk,
-- 
cgit v1.3-18-gd494


From 359f642700f2ff05d9c94cd9216c97af7b8e9553 Mon Sep 17 00:00:00 2001
From: Greg Edwards <gedwards@ddn.com>
Date: Wed, 25 Jul 2018 10:22:58 -0400
Subject: block: move bio_integrity_{intervals,bytes} into blkdev.h

This allows bio_integrity_bytes() to be called from drivers instead of
open coding it.

Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Greg Edwards <gedwards@ddn.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio-integrity.c  | 22 ----------------------
 include/linux/blkdev.h | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 22 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index add7c7c85335..67b5fb861a51 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -159,28 +159,6 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_integrity_add_page);
 
-/**
- * bio_integrity_intervals - Return number of integrity intervals for a bio
- * @bi:		blk_integrity profile for device
- * @sectors:	Size of the bio in 512-byte sectors
- *
- * Description: The block layer calculates everything in 512 byte
- * sectors but integrity metadata is done in terms of the data integrity
- * interval size of the storage device.  Convert the block layer sectors
- * to the appropriate number of integrity intervals.
- */
-static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
-						   unsigned int sectors)
-{
-	return sectors >> (bi->interval_exp - 9);
-}
-
-static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
-					       unsigned int sectors)
-{
-	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
-}
-
 /**
  * bio_integrity_process - Process integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 331a6cb8805f..050d599f5ea9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1865,6 +1865,28 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 				bip_next->bip_vec[0].bv_offset);
 }
 
+/**
+ * bio_integrity_intervals - Return number of integrity intervals for a bio
+ * @bi:		blk_integrity profile for device
+ * @sectors:	Size of the bio in 512-byte sectors
+ *
+ * Description: The block layer calculates everything in 512 byte
+ * sectors but integrity metadata is done in terms of the data integrity
+ * interval size of the storage device.  Convert the block layer sectors
+ * to the appropriate number of integrity intervals.
+ */
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return sectors >> (bi->interval_exp - 9);
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
+}
+
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct bio;
@@ -1938,6 +1960,18 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 	return false;
 }
 
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return 0;
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return 0;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct block_device_operations {
-- 
cgit v1.3-18-gd494


From b1f4267cc5448d20ae0c515a74141e74365e78a3 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 9 Aug 2018 07:47:28 -0700
Subject: block: Remove two superfluous #include directives

Commit 12f5b9314545 ("blk-mq: Remove generation seqeunce") removed the
only seqcount_t and u64_stats_sync instances from <linux/blkdev.h> but
did not remove the corresponding #include directives. Since these
include directives are no longer needed, remove them.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Jianchao Wang <jianchao.w.wang@oracle.com>
Cc: Hannes Reinecke <hare@suse.com>,
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 050d599f5ea9..d6869e0e2b64 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -27,8 +27,6 @@
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
-#include <linux/seqlock.h>
-#include <linux/u64_stats_sync.h>
 
 struct module;
 struct scsi_ioctl_command;
-- 
cgit v1.3-18-gd494