Merge tag 'for-5.18/block-2022-03-18' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - BFQ cleanups and fixes (Yu, Zhang, Yahu, Paolo)

 - blk-rq-qos completion fix (Tejun)

 - blk-cgroup merge fix (Tejun)

 - Add offline error return value to distinguish it from an IO error on
   the device (Song)

 - IO stats fixes (Zhang, Christoph)

 - blkcg refcount fixes (Ming, Yu)

 - Fix for indefinite dispatch loop softlockup (Shin'ichiro)

 - blk-mq hardware queue management improvements (Ming)

 - sbitmap dead code removal (Ming, John)

 - Plugging merge improvements (me)

 - Show blk-crypto capabilities in sysfs (Eric)

 - Multiple delayed queue run improvement (David)

 - Block throttling fixes (Ming)

 - Start deprecating auto module loading based on dev_t (Christoph)

 - bio allocation improvements (Christoph, Chaitanya)

 - Get rid of bio_devname (Christoph)

 - bio clone improvements (Christoph)

 - Block plugging improvements (Christoph)

 - Get rid of genhd.h header (Christoph)

 - Ensure drivers use appropriate flush helpers (Christoph)

 - Refcounting improvements (Christoph)

 - Queue initialization and teardown improvements (Ming, Christoph)

 - Misc fixes/improvements (Barry, Chaitanya, Colin, Dan, Jiapeng,
   Lukas, Nian, Yang, Eric, Chengming)

* tag 'for-5.18/block-2022-03-18' of git://git.kernel.dk/linux-block: (127 commits)
  block: cancel all throttled bios in del_gendisk()
  block: let blkcg_gq grab request queue's refcnt
  block: avoid use-after-free on throttle data
  block: limit request dispatch loop duration
  block/bfq-iosched: Fix spelling mistake "tenative" -> "tentative"
  sr: simplify the local variable initialization in sr_block_open()
  block: don't merge across cgroup boundaries if blkcg is enabled
  block: fix rq-qos breakage from skipping rq_qos_done_bio()
  block: flush plug based on hardware and software queue order
  block: ensure plug merging checks the correct queue at least once
  block: move rq_qos_exit() into disk_release()
  block: do more work in elevator_exit
  block: move blk_exit_queue into disk_release
  block: move q_usage_counter release into blk_queue_release
  block: don't remove hctx debugfs dir from blk_mq_exit_queue
  block: move blkcg initialization/destroy into disk allocation/release handler
  sr: implement ->free_disk to simplify refcounting
  sd: implement ->free_disk to simplify refcounting
  sd: delay calling free_opal_dev
  sd: call sd_zbc_release_disk before releasing the scsi_device reference
  ...

47 files changed, 1430 insertions, 659 deletions

diff --git a/block/Kconfig b/block/Kconfig
index d5d4197b7ed2..7eb5d6d53b3f 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -26,6 +26,16 @@ menuconfig BLOCK
 
 if BLOCK
 
+config BLOCK_LEGACY_AUTOLOAD
+	bool "Legacy autoloading support"
+	default y
+	help
+	  Enable loading modules and creating block device instances based on
+	  accesses through their device special file.  This is a historic Linux
+	  feature and makes no sense in a udev world where device files are
+	  created on demand, but scripts that manually create device nodes and
+	  then call losetup might rely on this behavior.
+
 config BLK_RQ_ALLOC_TIME
 	bool
 
@@ -218,6 +228,9 @@ config BLK_PM
 config BLOCK_HOLDER_DEPRECATED
 	bool
 
+config BLK_MQ_STACKING
+	bool
+
 source "block/Kconfig.iosched"
 
 endif # BLOCK
diff --git a/block/Makefile b/block/Makefile
index f38eaa612929..3950ecbc5c26 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -36,6 +36,7 @@ obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
 obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
 obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
 obj-$(CONFIG_BLK_PM)		+= blk-pm.o
-obj-$(CONFIG_BLK_INLINE_ENCRYPTION)	+= blk-crypto.o blk-crypto-profile.o
+obj-$(CONFIG_BLK_INLINE_ENCRYPTION)	+= blk-crypto.o blk-crypto-profile.o \
+					   blk-crypto-sysfs.o
 obj-$(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK)	+= blk-crypto-fallback.o
 obj-$(CONFIG_BLOCK_HOLDER_DEPRECATED)	+= holder.o
diff --git a/block/bdev.c b/block/bdev.c
index 102837a37051..ce8de42a89be 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -678,7 +678,7 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode)
 	if (test_bit(GD_NEED_PART_SCAN, &disk->state))
 		bdev_disk_changed(disk, false);
 	bdev->bd_openers++;
-	return 0;;
+	return 0;
 }
 
 static void blkdev_put_whole(struct block_device *bdev, fmode_t mode)
@@ -733,12 +733,15 @@ struct block_device *blkdev_get_no_open(dev_t dev)
 	struct inode *inode;
 
 	inode = ilookup(blockdev_superblock, dev);
-	if (!inode) {
+	if (!inode && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) {
 		blk_request_module(dev);
 		inode = ilookup(blockdev_superblock, dev);
-		if (!inode)
-			return NULL;
+		if (inode)
+			pr_warn_ratelimited(
+"block device autoloading is deprecated and will be removed.\n");
 	}
+	if (!inode)
+		return NULL;
 
 	/* switch from the inode reference to a device mode one: */
 	bdev = &BDEV_I(inode)->bdev;
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 24a5c5329bcd..420eda2589c0 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -645,8 +645,22 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		   struct bfq_group *bfqg)
 {
 	struct bfq_entity *entity = &bfqq->entity;
+	struct bfq_group *old_parent = bfqq_group(bfqq);
 
 	/*
+	 * No point to move bfqq to the same group, which can happen when
+	 * root group is offlined
+	 */
+	if (old_parent == bfqg)
+		return;
+
+	/*
+	 * oom_bfqq is not allowed to move, oom_bfqq will hold ref to root_group
+	 * until elevator exit.
+	 */
+	if (bfqq == &bfqd->oom_bfqq)
+		return;
+	/*
 	 * Get extra reference to prevent bfqq from being freed in
 	 * next possible expire or deactivate.
 	 */
@@ -666,7 +680,7 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
 	else if (entity->on_st_or_in_serv)
 		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
-	bfqg_and_blkg_put(bfqq_group(bfqq));
+	bfqg_and_blkg_put(old_parent);
 
 	if (entity->parent &&
 	    entity->parent->last_bfqq_created == bfqq)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 36a66e97e3c2..29d2635a2a63 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -774,7 +774,7 @@ bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 	if (!bfqq->next_rq)
 		return;
 
-	bfqq->pos_root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+	bfqq->pos_root = &bfqq_group(bfqq)->rq_pos_tree;
 	__bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
 			blk_rq_pos(bfqq->next_rq), &parent, &p);
 	if (!__bfqq) {
@@ -2153,7 +2153,7 @@ static void bfq_check_waker(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfqq->waker_detection_started = now_ns;
 		bfq_bfqq_name(bfqq->tentative_waker_bfqq, waker_name,
 			      MAX_BFQQ_NAME_LENGTH);
-		bfq_log_bfqq(bfqd, bfqq, "set tenative waker %s", waker_name);
+		bfq_log_bfqq(bfqd, bfqq, "set tentative waker %s", waker_name);
 	} else /* Same tentative waker queue detected again */
 		bfqq->num_waker_detections++;
 
@@ -2669,7 +2669,7 @@ static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd,
 					 struct bfq_queue *bfqq,
 					 sector_t sector)
 {
-	struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+	struct rb_root *root = &bfqq_group(bfqq)->rq_pos_tree;
 	struct rb_node *parent, *node;
 	struct bfq_queue *__bfqq;
 
@@ -2782,6 +2782,15 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
 	 * are likely to increase the throughput.
 	 */
 	bfqq->new_bfqq = new_bfqq;
+	/*
+	 * The above assignment schedules the following redirections:
+	 * each time some I/O for bfqq arrives, the process that
+	 * generated that I/O is disassociated from bfqq and
+	 * associated with new_bfqq. Here we increases new_bfqq->ref
+	 * in advance, adding the number of processes that are
+	 * expected to be associated with new_bfqq as they happen to
+	 * issue I/O.
+	 */
 	new_bfqq->ref += process_refs;
 	return new_bfqq;
 }
@@ -2844,6 +2853,10 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 {
 	struct bfq_queue *in_service_bfqq, *new_bfqq;
 
+	/* if a merge has already been setup, then proceed with that first */
+	if (bfqq->new_bfqq)
+		return bfqq->new_bfqq;
+
 	/*
 	 * Check delayed stable merge for rotational or non-queueing
 	 * devs. For this branch to be executed, bfqq must not be
@@ -2945,9 +2958,6 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	if (bfq_too_late_for_merging(bfqq))
 		return NULL;
 
-	if (bfqq->new_bfqq)
-		return bfqq->new_bfqq;
-
 	if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq))
 		return NULL;
 
@@ -5181,7 +5191,7 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 	struct request *rq;
 	struct bfq_queue *in_serv_queue;
-	bool waiting_rq, idle_timer_disabled;
+	bool waiting_rq, idle_timer_disabled = false;
 
 	spin_lock_irq(&bfqd->lock);
 
@@ -5189,14 +5199,15 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	waiting_rq = in_serv_queue && bfq_bfqq_wait_request(in_serv_queue);
 
 	rq = __bfq_dispatch_request(hctx);
-
-	idle_timer_disabled =
-		waiting_rq && !bfq_bfqq_wait_request(in_serv_queue);
+	if (in_serv_queue == bfqd->in_service_queue) {
+		idle_timer_disabled =
+			waiting_rq && !bfq_bfqq_wait_request(in_serv_queue);
+	}
 
 	spin_unlock_irq(&bfqd->lock);
-
-	bfq_update_dispatch_stats(hctx->queue, rq, in_serv_queue,
-				  idle_timer_disabled);
+	bfq_update_dispatch_stats(hctx->queue, rq,
+			idle_timer_disabled ? in_serv_queue : NULL,
+				idle_timer_disabled);
 
 	return rq;
 }
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 07288b9da389..3b83e3d1c2e5 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -8,7 +8,6 @@
 
 #include <linux/blktrace_api.h>
 #include <linux/hrtimer.h>
-#include <linux/blk-cgroup.h>
 
 #include "blk-cgroup-rwstat.h"
 
@@ -1051,7 +1050,6 @@ extern struct blkcg_policy blkcg_policy_bfq;
 	for (parent = NULL; entity ; entity = parent)
 #endif /* CONFIG_BFQ_GROUP_IOSCHED */
 
-struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq);
 struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
 unsigned int bfq_tot_busy_queues(struct bfq_data *bfqd);
 struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity);
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index b74cc0da118e..f8eb340381cf 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -142,16 +142,6 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 
-struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
-{
-	struct bfq_entity *group_entity = bfqq->entity.parent;
-
-	if (!group_entity)
-		group_entity = &bfqq->bfqd->root_group->entity;
-
-	return container_of(group_entity, struct bfq_group, entity);
-}
-
 /*
  * Returns true if this budget changes may let next_in_service->parent
  * become the next_in_service entity for its parent entity.
@@ -230,11 +220,6 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 
 #else /* CONFIG_BFQ_GROUP_IOSCHED */
 
-struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
-{
-	return bfqq->bfqd->root_group;
-}
-
 static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
 {
 	return false;
@@ -519,7 +504,7 @@ unsigned short bfq_ioprio_to_weight(int ioprio)
 static unsigned short bfq_weight_to_ioprio(int weight)
 {
 	return max_t(int, 0,
-		     IOPRIO_NR_LEVELS * BFQ_WEIGHT_CONVERSION_COEFF - weight);
+		     IOPRIO_NR_LEVELS - weight / BFQ_WEIGHT_CONVERSION_COEFF);
 }
 
 static void bfq_get_entity(struct bfq_entity *entity)
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 0827b19820c5..6996e7bd66e9 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -420,7 +420,6 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 
 	return 0;
 }
-EXPORT_SYMBOL(bio_integrity_clone);
 
 int bioset_integrity_create(struct bio_set *bs, int pool_size)
 {
diff --git a/block/bio.c b/block/bio.c
index 4312a8085396..33979f306e9e 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -15,7 +15,6 @@
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
-#include <linux/blk-cgroup.h>
 #include <linux/highmem.h>
 #include <linux/sched/sysctl.h>
 #include <linux/blk-crypto.h>
@@ -24,6 +23,7 @@
 #include <trace/events/block.h>
 #include "blk.h"
 #include "blk-rq-qos.h"
+#include "blk-cgroup.h"
 
 struct bio_alloc_cache {
 	struct bio		*free_list;
@@ -249,12 +249,12 @@ static void bio_free(struct bio *bio)
  * they must remember to pair any call to bio_init() with bio_uninit()
  * when IO has completed, or when the bio is released.
  */
-void bio_init(struct bio *bio, struct bio_vec *table,
-	      unsigned short max_vecs)
+void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
+	      unsigned short max_vecs, unsigned int opf)
 {
 	bio->bi_next = NULL;
-	bio->bi_bdev = NULL;
-	bio->bi_opf = 0;
+	bio->bi_bdev = bdev;
+	bio->bi_opf = opf;
 	bio->bi_flags = 0;
 	bio->bi_ioprio = 0;
 	bio->bi_write_hint = 0;
@@ -268,6 +268,8 @@ void bio_init(struct bio *bio, struct bio_vec *table,
 #ifdef CONFIG_BLK_CGROUP
 	bio->bi_blkg = NULL;
 	bio->bi_issue.value = 0;
+	if (bdev)
+		bio_associate_blkg(bio);
 #ifdef CONFIG_BLK_CGROUP_IOCOST
 	bio->bi_iocost_cost = 0;
 #endif
@@ -293,6 +295,8 @@ EXPORT_SYMBOL(bio_init);
 /**
  * bio_reset - reinitialize a bio
  * @bio:	bio to reset
+ * @bdev:	block device to use the bio for
+ * @opf:	operation and flags for bio
  *
  * Description:
  *   After calling bio_reset(), @bio will be in the same state as a freshly
@@ -300,11 +304,15 @@ EXPORT_SYMBOL(bio_init);
  *   preserved are the ones that are initialized by bio_alloc_bioset(). See
  *   comment in struct bio.
  */
-void bio_reset(struct bio *bio)
+void bio_reset(struct bio *bio, struct block_device *bdev, unsigned int opf)
 {
 	bio_uninit(bio);
 	memset(bio, 0, BIO_RESET_BYTES);
 	atomic_set(&bio->__bi_remaining, 1);
+	bio->bi_bdev = bdev;
+	if (bio->bi_bdev)
+		bio_associate_blkg(bio);
+	bio->bi_opf = opf;
 }
 EXPORT_SYMBOL(bio_reset);
 
@@ -344,6 +352,20 @@ void bio_chain(struct bio *bio, struct bio *parent)
 }
 EXPORT_SYMBOL(bio_chain);
 
+struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
+		unsigned int nr_pages, unsigned int opf, gfp_t gfp)
+{
+	struct bio *new = bio_alloc(bdev, nr_pages, opf, gfp);
+
+	if (bio) {
+		bio_chain(bio, new);
+		submit_bio(bio);
+	}
+
+	return new;
+}
+EXPORT_SYMBOL_GPL(blk_next_bio);
+
 static void bio_alloc_rescue(struct work_struct *work)
 {
 	struct bio_set *bs = container_of(work, struct bio_set, rescue_work);
@@ -400,8 +422,10 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
 
 /**
  * bio_alloc_bioset - allocate a bio for I/O
+ * @bdev:	block device to allocate the bio for (can be %NULL)
+ * @nr_vecs:	number of bvecs to pre-allocate
+ * @opf:	operation and flags for bio
  * @gfp_mask:   the GFP_* mask given to the slab allocator
- * @nr_iovecs:	number of iovecs to pre-allocate
  * @bs:		the bio_set to allocate from.
  *
  * Allocate a bio from the mempools in @bs.
@@ -430,15 +454,16 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
  *
  * Returns: Pointer to new bio on success, NULL on failure.
  */
-struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned short nr_iovecs,
+struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
+			     unsigned int opf, gfp_t gfp_mask,
 			     struct bio_set *bs)
 {
 	gfp_t saved_gfp = gfp_mask;
 	struct bio *bio;
 	void *p;
 
-	/* should not use nobvec bioset for nr_iovecs > 0 */
-	if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_iovecs > 0))
+	/* should not use nobvec bioset for nr_vecs > 0 */
+	if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_vecs > 0))
 		return NULL;
 
 	/*
@@ -475,23 +500,23 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned short nr_iovecs,
 		return NULL;
 
 	bio = p + bs->front_pad;
-	if (nr_iovecs > BIO_INLINE_VECS) {
+	if (nr_vecs > BIO_INLINE_VECS) {
 		struct bio_vec *bvl = NULL;
 
-		bvl = bvec_alloc(&bs->bvec_pool, &nr_iovecs, gfp_mask);
+		bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask);
 		if (!bvl && gfp_mask != saved_gfp) {
 			punt_bios_to_rescuer(bs);
 			gfp_mask = saved_gfp;
-			bvl = bvec_alloc(&bs->bvec_pool, &nr_iovecs, gfp_mask);
+			bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask);
 		}
 		if (unlikely(!bvl))
 			goto err_free;
 
-		bio_init(bio, bvl, nr_iovecs);
-	} else if (nr_iovecs) {
-		bio_init(bio, bio->bi_inline_vecs, BIO_INLINE_VECS);
+		bio_init(bio, bdev, bvl, nr_vecs, opf);
+	} else if (nr_vecs) {
+		bio_init(bio, bdev, bio->bi_inline_vecs, BIO_INLINE_VECS, opf);
 	} else {
-		bio_init(bio, NULL, 0);
+		bio_init(bio, bdev, NULL, 0, opf);
 	}
 
 	bio->bi_pool = bs;
@@ -522,7 +547,8 @@ struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs)
 	bio = kmalloc(struct_size(bio, bi_inline_vecs, nr_iovecs), gfp_mask);
 	if (unlikely(!bio))
 		return NULL;
-	bio_init(bio, nr_iovecs ? bio->bi_inline_vecs : NULL, nr_iovecs);
+	bio_init(bio, NULL, nr_iovecs ? bio->bi_inline_vecs : NULL, nr_iovecs,
+		 0);
 	bio->bi_pool = NULL;
 	return bio;
 }
@@ -702,80 +728,84 @@ void bio_put(struct bio *bio)
 }
 EXPORT_SYMBOL(bio_put);
 
-/**
- * 	__bio_clone_fast - clone a bio that shares the original bio's biovec
- * 	@bio: destination bio
- * 	@bio_src: bio to clone
- *
- *	Clone a &bio. Caller will own the returned bio, but not
- *	the actual data it points to. Reference count of returned
- * 	bio will be one.
- *
- * 	Caller must ensure that @bio_src is not freed before @bio.
- */
-void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
+static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp)
 {
-	WARN_ON_ONCE(bio->bi_pool && bio->bi_max_vecs);
-
-	/*
-	 * most users will be overriding ->bi_bdev with a new target,
-	 * so we don't set nor calculate new physical/hw segment counts here
-	 */
-	bio->bi_bdev = bio_src->bi_bdev;
 	bio_set_flag(bio, BIO_CLONED);
 	if (bio_flagged(bio_src, BIO_THROTTLED))
 		bio_set_flag(bio, BIO_THROTTLED);
-	if (bio_flagged(bio_src, BIO_REMAPPED))
+	if (bio->bi_bdev == bio_src->bi_bdev &&
+	    bio_flagged(bio_src, BIO_REMAPPED))
 		bio_set_flag(bio, BIO_REMAPPED);
-	bio->bi_opf = bio_src->bi_opf;
 	bio->bi_ioprio = bio_src->bi_ioprio;
 	bio->bi_write_hint = bio_src->bi_write_hint;
 	bio->bi_iter = bio_src->bi_iter;
-	bio->bi_io_vec = bio_src->bi_io_vec;
 
 	bio_clone_blkg_association(bio, bio_src);
 	blkcg_bio_issue_init(bio);
+
+	if (bio_crypt_clone(bio, bio_src, gfp) < 0)
+		return -ENOMEM;
+	if (bio_integrity(bio_src) &&
+	    bio_integrity_clone(bio, bio_src, gfp) < 0)
+		return -ENOMEM;
+	return 0;
 }
-EXPORT_SYMBOL(__bio_clone_fast);
 
 /**
- *	bio_clone_fast - clone a bio that shares the original bio's biovec
- *	@bio: bio to clone
- *	@gfp_mask: allocation priority
- *	@bs: bio_set to allocate from
+ * bio_alloc_clone - clone a bio that shares the original bio's biovec
+ * @bdev: block_device to clone onto
+ * @bio_src: bio to clone from
+ * @gfp: allocation priority
+ * @bs: bio_set to allocate from
+ *
+ * Allocate a new bio that is a clone of @bio_src. The caller owns the returned
+ * bio, but not the actual data it points to.
  *
- * 	Like __bio_clone_fast, only also allocates the returned bio
+ * The caller must ensure that the return bio is not freed before @bio_src.
  */
-struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
+struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src,
+		gfp_t gfp, struct bio_set *bs)
 {
-	struct bio *b;
+	struct bio *bio;
 
-	b = bio_alloc_bioset(gfp_mask, 0, bs);
-	if (!b)
+	bio = bio_alloc_bioset(bdev, 0, bio_src->bi_opf, gfp, bs);
+	if (!bio)
 		return NULL;
 
-	__bio_clone_fast(b, bio);
-
-	if (bio_crypt_clone(b, bio, gfp_mask) < 0)
-		goto err_put;
-
-	if (bio_integrity(bio) &&
-	    bio_integrity_clone(b, bio, gfp_mask) < 0)
-		goto err_put;
-
-	return b;
+	if (__bio_clone(bio, bio_src, gfp) < 0) {
+		bio_put(bio);
+		return NULL;
+	}
+	bio->bi_io_vec = bio_src->bi_io_vec;
 
-err_put:
-	bio_put(b);
-	return NULL;
+	return bio;
 }
-EXPORT_SYMBOL(bio_clone_fast);
+EXPORT_SYMBOL(bio_alloc_clone);
 
-const char *bio_devname(struct bio *bio, char *buf)
+/**
+ * bio_init_clone - clone a bio that shares the original bio's biovec
+ * @bdev: block_device to clone onto
+ * @bio: bio to clone into
+ * @bio_src: bio to clone from
+ * @gfp: allocation priority
+ *
+ * Initialize a new bio in caller provided memory that is a clone of @bio_src.
+ * The caller owns the returned bio, but not the actual data it points to.
+ *
+ * The caller must ensure that @bio_src is not freed before @bio.
+ */
+int bio_init_clone(struct block_device *bdev, struct bio *bio,
+		struct bio *bio_src, gfp_t gfp)
 {
-	return bdevname(bio->bi_bdev, buf);
+	int ret;
+
+	bio_init(bio, bdev, bio_src->bi_io_vec, 0, bio_src->bi_opf);
+	ret = __bio_clone(bio, bio_src, gfp);
+	if (ret)
+		bio_uninit(bio);
+	return ret;
 }
-EXPORT_SYMBOL(bio_devname);
+EXPORT_SYMBOL(bio_init_clone);
 
 /**
  * bio_full - check if the bio is full
@@ -1054,7 +1084,7 @@ bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len,
 		   size_t off)
 {
 	if (len > UINT_MAX || off > UINT_MAX)
-		return 0;
+		return false;
 	return bio_add_page(bio, &folio->page, len, off) > 0;
 }
 
@@ -1486,8 +1516,7 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
-	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACKED))
-		rq_qos_done_bio(bdev_get_queue(bio->bi_bdev), bio);
+	rq_qos_done_bio(bio);
 
 	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
 		trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio);
@@ -1541,7 +1570,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND))
 		return NULL;
 
-	split = bio_clone_fast(bio, gfp, bs);
+	split = bio_alloc_clone(bio->bi_bdev, bio, gfp, bs);
 	if (!split)
 		return NULL;
 
@@ -1636,9 +1665,9 @@ EXPORT_SYMBOL(bioset_exit);
  *    Note that the bio must be embedded at the END of that structure always,
  *    or things will break badly.
  *    If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated
- *    for allocating iovecs.  This pool is not needed e.g. for bio_clone_fast().
- *    If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used to
- *    dispatch queued requests when the mempool runs out of space.
+ *    for allocating iovecs.  This pool is not needed e.g. for bio_init_clone().
+ *    If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used
+ *    to dispatch queued requests when the mempool runs out of space.
  *
  */
 int bioset_init(struct bio_set *bs,
@@ -1708,7 +1737,9 @@ EXPORT_SYMBOL(bioset_init_from_src);
 /**
  * bio_alloc_kiocb - Allocate a bio from bio_set based on kiocb
  * @kiocb:	kiocb describing the IO
+ * @bdev:	block device to allocate the bio for (can be %NULL)
  * @nr_vecs:	number of iovecs to pre-allocate
+ * @opf:	operation and flags for bio
  * @bs:		bio_set to allocate from
  *
  * Description:
@@ -1719,14 +1750,14 @@ EXPORT_SYMBOL(bioset_init_from_src);
  *    MUST be done from process context, not hard/soft IRQ.
  *
  */
-struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs,
-			    struct bio_set *bs)
+struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev,
+		unsigned short nr_vecs, unsigned int opf, struct bio_set *bs)
 {
 	struct bio_alloc_cache *cache;
 	struct bio *bio;
 
 	if (!(kiocb->ki_flags & IOCB_ALLOC_CACHE) || nr_vecs > BIO_INLINE_VECS)
-		return bio_alloc_bioset(GFP_KERNEL, nr_vecs, bs);
+		return bio_alloc_bioset(bdev, nr_vecs, opf, GFP_KERNEL, bs);
 
 	cache = per_cpu_ptr(bs->cache, get_cpu());
 	if (cache->free_list) {
@@ -1734,13 +1765,14 @@ struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs,
 		cache->free_list = bio->bi_next;
 		cache->nr--;
 		put_cpu();
-		bio_init(bio, nr_vecs ? bio->bi_inline_vecs : NULL, nr_vecs);
+		bio_init(bio, bdev, nr_vecs ? bio->bi_inline_vecs : NULL,
+			 nr_vecs, opf);
 		bio->bi_pool = bs;
 		bio_set_flag(bio, BIO_PERCPU_CACHE);
 		return bio;
 	}
 	put_cpu();
-	bio = bio_alloc_bioset(GFP_KERNEL, nr_vecs, bs);
+	bio = bio_alloc_bioset(bdev, nr_vecs, opf, GFP_KERNEL, bs);
 	bio_set_flag(bio, BIO_PERCPU_CACHE);
 	return bio;
 }
diff --git a/block/blk-cgroup-rwstat.h b/block/blk-cgroup-rwstat.h
index ee746919c41f..9f2723b34b75 100644
--- a/block/blk-cgroup-rwstat.h
+++ b/block/blk-cgroup-rwstat.h
@@ -6,7 +6,7 @@
 #ifndef _BLK_CGROUP_RWSTAT_H
 #define _BLK_CGROUP_RWSTAT_H
 
-#include <linux/blk-cgroup.h>
+#include "blk-cgroup.h"
 
 enum blkg_rwstat_type {
 	BLKG_RWSTAT_READ,
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 650f7e27989f..d53b0d69dd73 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -23,15 +23,14 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/slab.h>
-#include <linux/genhd.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
 #include <linux/ctype.h>
-#include <linux/blk-cgroup.h>
 #include <linux/tracehook.h>
 #include <linux/psi.h>
 #include <linux/part_stat.h>
 #include "blk.h"
+#include "blk-cgroup.h"
 #include "blk-ioprio.h"
 #include "blk-throttle.h"
 
@@ -83,6 +82,8 @@ static void blkg_free(struct blkcg_gq *blkg)
 		if (blkg->pd[i])
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
 
+	if (blkg->q)
+		blk_put_queue(blkg->q);
 	free_percpu(blkg->iostat_cpu);
 	percpu_ref_exit(&blkg->refcnt);
 	kfree(blkg);
@@ -168,6 +169,9 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	if (!blkg->iostat_cpu)
 		goto err_free;
 
+	if (!blk_get_queue(q))
+		goto err_free;
+
 	blkg->q = q;
 	INIT_LIST_HEAD(&blkg->q_node);
 	spin_lock_init(&blkg->async_bio_lock);
@@ -857,11 +861,11 @@ static void blkcg_fill_root_iostats(void)
 			blk_queue_root_blkg(bdev_get_queue(bdev));
 		struct blkg_iostat tmp;
 		int cpu;
+		unsigned long flags;
 
 		memset(&tmp, 0, sizeof(tmp));
 		for_each_possible_cpu(cpu) {
 			struct disk_stats *cpu_dkstats;
-			unsigned long flags;
 
 			cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu);
 			tmp.ios[BLKG_IOSTAT_READ] +=
@@ -877,11 +881,11 @@ static void blkcg_fill_root_iostats(void)
 				cpu_dkstats->sectors[STAT_WRITE] << 9;
 			tmp.bytes[BLKG_IOSTAT_DISCARD] +=
 				cpu_dkstats->sectors[STAT_DISCARD] << 9;
-
-			flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync);
-			blkg_iostat_set(&blkg->iostat.cur, &tmp);
-			u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
 		}
+
+		flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync);
+		blkg_iostat_set(&blkg->iostat.cur, &tmp);
+		u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
 	}
 }
 
@@ -1176,6 +1180,8 @@ int blkcg_init_queue(struct request_queue *q)
 	bool preloaded;
 	int ret;
 
+	INIT_LIST_HEAD(&q->blkg_list);
+
 	new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL);
 	if (!new_blkg)
 		return -ENOMEM;
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
new file mode 100644
index 000000000000..47e1e38390c9
--- /dev/null
+++ b/block/blk-cgroup.h
@@ -0,0 +1,494 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BLK_CGROUP_PRIVATE_H
+#define _BLK_CGROUP_PRIVATE_H
+/*
+ * block cgroup private header
+ *
+ * Based on ideas and code from CFQ, CFS and BFQ:
+ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
+ *
+ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
+ *		      Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
+ * 	              Nauman Rafique <nauman@google.com>
+ */
+
+#include <linux/blk-cgroup.h>
+#include <linux/blk-mq.h>
+
+/* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */
+#define BLKG_STAT_CPU_BATCH	(INT_MAX / 2)
+
+#ifdef CONFIG_BLK_CGROUP
+
+/*
+ * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a
+ * request_queue (q).  This is used by blkcg policies which need to track
+ * information per blkcg - q pair.
+ *
+ * There can be multiple active blkcg policies and each blkg:policy pair is
+ * represented by a blkg_policy_data which is allocated and freed by each
+ * policy's pd_alloc/free_fn() methods.  A policy can allocate private data
+ * area by allocating larger data structure which embeds blkg_policy_data
+ * at the beginning.
+ */
+struct blkg_policy_data {
+	/* the blkg and policy id this per-policy data belongs to */
+	struct blkcg_gq			*blkg;
+	int				plid;
+};
+
+/*
+ * Policies that need to keep per-blkcg data which is independent from any
+ * request_queue associated to it should implement cpd_alloc/free_fn()
+ * methods.  A policy can allocate private data area by allocating larger
+ * data structure which embeds blkcg_policy_data at the beginning.
+ * cpd_init() is invoked to let each policy handle per-blkcg data.
+ */
+struct blkcg_policy_data {
+	/* the blkcg and policy id this per-policy data belongs to */
+	struct blkcg			*blkcg;
+	int				plid;
+};
+
+typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
+typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd);
+typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd);
+typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd);
+typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp,
+				struct request_queue *q, struct blkcg *blkcg);
+typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd);
+typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
+typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
+typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
+typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);
+typedef bool (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd,
+				struct seq_file *s);
+
+struct blkcg_policy {
+	int				plid;
+	/* cgroup files for the policy */
+	struct cftype			*dfl_cftypes;
+	struct cftype			*legacy_cftypes;
+
+	/* operations */
+	blkcg_pol_alloc_cpd_fn		*cpd_alloc_fn;
+	blkcg_pol_init_cpd_fn		*cpd_init_fn;
+	blkcg_pol_free_cpd_fn		*cpd_free_fn;
+	blkcg_pol_bind_cpd_fn		*cpd_bind_fn;
+
+	blkcg_pol_alloc_pd_fn		*pd_alloc_fn;
+	blkcg_pol_init_pd_fn		*pd_init_fn;
+	blkcg_pol_online_pd_fn		*pd_online_fn;
+	blkcg_pol_offline_pd_fn		*pd_offline_fn;
+	blkcg_pol_free_pd_fn		*pd_free_fn;
+	blkcg_pol_reset_pd_stats_fn	*pd_reset_stats_fn;
+	blkcg_pol_stat_pd_fn		*pd_stat_fn;
+};
+
+extern struct blkcg blkcg_root;
+extern bool blkcg_debug_stats;
+
+struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
+				      struct request_queue *q, bool update_hint);
+int blkcg_init_queue(struct request_queue *q);
+void blkcg_exit_queue(struct request_queue *q);
+
+/* Blkio controller policy registration */
+int blkcg_policy_register(struct blkcg_policy *pol);
+void blkcg_policy_unregister(struct blkcg_policy *pol);
+int blkcg_activate_policy(struct request_queue *q,
+			  const struct blkcg_policy *pol);
+void blkcg_deactivate_policy(struct request_queue *q,
+			     const struct blkcg_policy *pol);
+
+const char *blkg_dev_name(struct blkcg_gq *blkg);
+void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
+		       u64 (*prfill)(struct seq_file *,
+				     struct blkg_policy_data *, int),
+		       const struct blkcg_policy *pol, int data,
+		       bool show_total);
+u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v);
+
+struct blkg_conf_ctx {
+	struct block_device		*bdev;
+	struct blkcg_gq			*blkg;
+	char				*body;
+};
+
+struct block_device *blkcg_conf_open_bdev(char **inputp);
+int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
+		   char *input, struct blkg_conf_ctx *ctx);
+void blkg_conf_finish(struct blkg_conf_ctx *ctx);
+
+/**
+ * blkcg_css - find the current css
+ *
+ * Find the css associated with either the kthread or the current task.
+ * This may return a dying css, so it is up to the caller to use tryget logic
+ * to confirm it is alive and well.
+ */
+static inline struct cgroup_subsys_state *blkcg_css(void)
+{
+	struct cgroup_subsys_state *css;
+
+	css = kthread_blkcg();
+	if (css)
+		return css;
+	return task_css(current, io_cgrp_id);
+}
+
+/**
+ * __bio_blkcg - internal, inconsistent version to get blkcg
+ *
+ * DO NOT USE.
+ * This function is inconsistent and consequently is dangerous to use.  The
+ * first part of the function returns a blkcg where a reference is owned by the
+ * bio.  This means it does not need to be rcu protected as it cannot go away
+ * with the bio owning a reference to it.  However, the latter potentially gets
+ * it from task_css().  This can race against task migration and the cgroup
+ * dying.  It is also semantically different as it must be called rcu protected
+ * and is susceptible to failure when trying to get a reference to it.
+ * Therefore, it is not ok to assume that *_get() will always succeed on the
+ * blkcg returned here.
+ */
+static inline struct blkcg *__bio_blkcg(struct bio *bio)
+{
+	if (bio && bio->bi_blkg)
+		return bio->bi_blkg->blkcg;
+	return css_to_blkcg(blkcg_css());
+}
+
+/**
+ * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg
+ * @return: true if this bio needs to be submitted with the root blkg context.
+ *
+ * In order to avoid priority inversions we sometimes need to issue a bio as if
+ * it were attached to the root blkg, and then backcharge to the actual owning
+ * blkg.  The idea is we do bio_blkcg() to look up the actual context for the
+ * bio and attach the appropriate blkg to the bio.  Then we call this helper and
+ * if it is true run with the root blkg for that queue and then do any
+ * backcharging to the originating cgroup once the io is complete.
+ */
+static inline bool bio_issue_as_root_blkg(struct bio *bio)
+{
+	return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0;
+}
+
+/**
+ * __blkg_lookup - internal version of blkg_lookup()
+ * @blkcg: blkcg of interest
+ * @q: request_queue of interest
+ * @update_hint: whether to update lookup hint with the result or not
+ *
+ * This is internal version and shouldn't be used by policy
+ * implementations.  Looks up blkgs for the @blkcg - @q pair regardless of
+ * @q's bypass state.  If @update_hint is %true, the caller should be
+ * holding @q->queue_lock and lookup hint is updated on success.
+ */
+static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg,
+					     struct request_queue *q,
+					     bool update_hint)
+{
+	struct blkcg_gq *blkg;
+
+	if (blkcg == &blkcg_root)
+		return q->root_blkg;
+
+	blkg = rcu_dereference(blkcg->blkg_hint);
+	if (blkg && blkg->q == q)
+		return blkg;
+
+	return blkg_lookup_slowpath(blkcg, q, update_hint);
+}
+
+/**
+ * blkg_lookup - lookup blkg for the specified blkcg - q pair
+ * @blkcg: blkcg of interest
+ * @q: request_queue of interest
+ *
+ * Lookup blkg for the @blkcg - @q pair.  This function should be called
+ * under RCU read lock.
+ */
+static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
+					   struct request_queue *q)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return __blkg_lookup(blkcg, q, false);
+}
+
+/**
+ * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair
+ * @q: request_queue of interest
+ *
+ * Lookup blkg for @q at the root level. See also blkg_lookup().
+ */
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
+{
+	return q->root_blkg;
+}
+
+/**
+ * blkg_to_pdata - get policy private data
+ * @blkg: blkg of interest
+ * @pol: policy of interest
+ *
+ * Return pointer to private data associated with the @blkg-@pol pair.
+ */
+static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
+						  struct blkcg_policy *pol)
+{
+	return blkg ? blkg->pd[pol->plid] : NULL;
+}
+
+static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg,
+						     struct blkcg_policy *pol)
+{
+	return blkcg ? blkcg->cpd[pol->plid] : NULL;
+}
+
+/**
+ * pdata_to_blkg - get blkg associated with policy private data
+ * @pd: policy private data of interest
+ *
+ * @pd is policy private data.  Determine the blkg it's associated with.
+ */
+static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd)
+{
+	return pd ? pd->blkg : NULL;
+}
+
+static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd)
+{
+	return cpd ? cpd->blkcg : NULL;
+}
+
+/**
+ * blkg_path - format cgroup path of blkg
+ * @blkg: blkg of interest
+ * @buf: target buffer
+ * @buflen: target buffer length
+ *
+ * Format the path of the cgroup of @blkg into @buf.
+ */
+static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
+{
+	return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
+}
+
+/**
+ * blkg_get - get a blkg reference
+ * @blkg: blkg to get
+ *
+ * The caller should be holding an existing reference.
+ */
+static inline void blkg_get(struct blkcg_gq *blkg)
+{
+	percpu_ref_get(&blkg->refcnt);
+}
+
+/**
+ * blkg_tryget - try and get a blkg reference
+ * @blkg: blkg to get
+ *
+ * This is for use when doing an RCU lookup of the blkg.  We may be in the midst
+ * of freeing this blkg, so we can only use it if the refcnt is not zero.
+ */
+static inline bool blkg_tryget(struct blkcg_gq *blkg)
+{
+	return blkg && percpu_ref_tryget(&blkg->refcnt);
+}
+
+/**
+ * blkg_put - put a blkg reference
+ * @blkg: blkg to put
+ */
+static inline void blkg_put(struct blkcg_gq *blkg)
+{
+	percpu_ref_put(&blkg->refcnt);
+}
+
+/**
+ * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants
+ * @d_blkg: loop cursor pointing to the current descendant
+ * @pos_css: used for iteration
+ * @p_blkg: target blkg to walk descendants of
+ *
+ * Walk @c_blkg through the descendants of @p_blkg.  Must be used with RCU
+ * read locked.  If called under either blkcg or queue lock, the iteration
+ * is guaranteed to include all and only online blkgs.  The caller may
+ * update @pos_css by calling css_rightmost_descendant() to skip subtree.
+ * @p_blkg is included in the iteration and the first node to be visited.
+ */
+#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg)		\
+	css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css)	\
+		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
+					      (p_blkg)->q, false)))
+
+/**
+ * blkg_for_each_descendant_post - post-order walk of a blkg's descendants
+ * @d_blkg: loop cursor pointing to the current descendant
+ * @pos_css: used for iteration
+ * @p_blkg: target blkg to walk descendants of
+ *
+ * Similar to blkg_for_each_descendant_pre() but performs post-order
+ * traversal instead.  Synchronization rules are the same.  @p_blkg is
+ * included in the iteration and the last node to be visited.
+ */
+#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg)		\
+	css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css)	\
+		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
+					      (p_blkg)->q, false)))
+
+bool __blkcg_punt_bio_submit(struct bio *bio);
+
+static inline bool blkcg_punt_bio_submit(struct bio *bio)
+{
+	if (bio->bi_opf & REQ_CGROUP_PUNT)
+		return __blkcg_punt_bio_submit(bio);
+	else
+		return false;
+}
+
+static inline void blkcg_bio_issue_init(struct bio *bio)
+{
+	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
+}
+
+static inline void blkcg_use_delay(struct blkcg_gq *blkg)
+{
+	if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0))
+		return;
+	if (atomic_add_return(1, &blkg->use_delay) == 1)
+		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
+}
+
+static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+
+	if (WARN_ON_ONCE(old < 0))
+		return 0;
+	if (old == 0)
+		return 0;
+
+	/*
+	 * We do this song and dance because we can race with somebody else
+	 * adding or removing delay.  If we just did an atomic_dec we'd end up
+	 * negative and we'd already be in trouble.  We need to subtract 1 and
+	 * then check to see if we were the last delay so we can drop the
+	 * congestion count on the cgroup.
+	 */
+	while (old) {
+		int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1);
+		if (cur == old)
+			break;
+		old = cur;
+	}
+
+	if (old == 0)
+		return 0;
+	if (old == 1)
+		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+	return 1;
+}
+
+/**
+ * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount
+ * @blkg: target blkg
+ * @delay: delay duration in nsecs
+ *
+ * When enabled with this function, the delay is not decayed and must be
+ * explicitly cleared with blkcg_clear_delay(). Must not be mixed with
+ * blkcg_[un]use_delay() and blkcg_add_delay() usages.
+ */
+static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay)
+{
+	int old = atomic_read(&blkg->use_delay);
+
+	/* We only want 1 person setting the congestion count for this blkg. */
+	if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old)
+		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
+
+	atomic64_set(&blkg->delay_nsec, delay);
+}
+
+/**
+ * blkcg_clear_delay - Disable allocator delay mechanism
+ * @blkg: target blkg
+ *
+ * Disable use_delay mechanism. See blkcg_set_delay().
+ */
+static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+
+	/* We only want 1 person clearing the congestion count for this blkg. */
+	if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old)
+		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+}
+
+/**
+ * blk_cgroup_mergeable - Determine whether to allow or disallow merges
+ * @rq: request to merge into
+ * @bio: bio to merge
+ *
+ * @bio and @rq should belong to the same cgroup and their issue_as_root should
+ * match. The latter is necessary as we don't want to throttle e.g. a metadata
+ * update because it happens to be next to a regular IO.
+ */
+static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio)
+{
+	return rq->bio->bi_blkg == bio->bi_blkg &&
+		bio_issue_as_root_blkg(rq->bio) == bio_issue_as_root_blkg(bio);
+}
+
+void blk_cgroup_bio_start(struct bio *bio);
+void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
+#else	/* CONFIG_BLK_CGROUP */
+
+struct blkg_policy_data {
+};
+
+struct blkcg_policy_data {
+};
+
+struct blkcg_policy {
+};
+
+#ifdef CONFIG_BLOCK
+
+static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
+{ return NULL; }
+static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
+static inline void blkcg_exit_queue(struct request_queue *q) { }
+static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
+static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { }
+static inline int blkcg_activate_policy(struct request_queue *q,
+					const struct blkcg_policy *pol) { return 0; }
+static inline void blkcg_deactivate_policy(struct request_queue *q,
+					   const struct blkcg_policy *pol) { }
+
+static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; }
+
+static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
+						  struct blkcg_policy *pol) { return NULL; }
+static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; }
+static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; }
+static inline void blkg_get(struct blkcg_gq *blkg) { }
+static inline void blkg_put(struct blkcg_gq *blkg) { }
+
+static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; }
+static inline void blkcg_bio_issue_init(struct bio *bio) { }
+static inline void blk_cgroup_bio_start(struct bio *bio) { }
+static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { return true; }
+
+#define blk_queue_for_each_rl(rl, q)	\
+	for ((rl) = &(q)->root_rl; (rl); (rl) = NULL)
+
+#endif	/* CONFIG_BLOCK */
+#endif	/* CONFIG_BLK_CGROUP */
+
+#endif /* _BLK_CGROUP_PRIVATE_H */
diff --git a/block/blk-core.c b/block/blk-core.c
index 779b4a1f66ac..9c14deab3af4 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -34,7 +34,6 @@
 #include <linux/delay.h>
 #include <linux/ratelimit.h>
 #include <linux/pm_runtime.h>
-#include <linux/blk-cgroup.h>
 #include <linux/t10-pi.h>
 #include <linux/debugfs.h>
 #include <linux/bpf.h>
@@ -49,6 +48,7 @@
 #include "blk.h"
 #include "blk-mq-sched.h"
 #include "blk-pm.h"
+#include "blk-cgroup.h"
 #include "blk-throttle.h"
 #include "blk-rq-qos.h"
 
@@ -165,6 +165,7 @@ static const struct {
 	[BLK_STS_RESOURCE]	= { -ENOMEM,	"kernel resource" },
 	[BLK_STS_DEV_RESOURCE]	= { -EBUSY,	"device resource" },
 	[BLK_STS_AGAIN]		= { -EAGAIN,	"nonblocking retry" },
+	[BLK_STS_OFFLINE]	= { -ENODEV,	"device offline" },
 
 	/* device mapper special case, should not leak out: */
 	[BLK_STS_DM_REQUEUE]	= { -EREMCHG, "dm internal retry" },
@@ -339,8 +340,6 @@ void blk_cleanup_queue(struct request_queue *q)
 		blk_mq_sched_free_rqs(q);
 	mutex_unlock(&q->sysfs_lock);
 
-	percpu_ref_exit(&q->q_usage_counter);
-
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);
 }
@@ -473,9 +472,6 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 	timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
 	INIT_WORK(&q->timeout_work, blk_timeout_work);
 	INIT_LIST_HEAD(&q->icq_list);
-#ifdef CONFIG_BLK_CGROUP
-	INIT_LIST_HEAD(&q->blkg_list);
-#endif
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
 
@@ -496,17 +492,12 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
 		goto fail_stats;
 
-	if (blkcg_init_queue(q))
-		goto fail_ref;
-
 	blk_queue_dma_alignment(q, 511);
 	blk_set_default_limits(&q->limits);
 	q->nr_requests = BLKDEV_DEFAULT_RQ;
 
 	return q;
 
-fail_ref:
-	percpu_ref_exit(&q->q_usage_counter);
 fail_stats:
 	blk_free_queue_stats(q->stats);
 fail_split:
@@ -540,17 +531,6 @@ bool blk_get_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_get_queue);
 
-static void handle_bad_sector(struct bio *bio, sector_t maxsector)
-{
-	char b[BDEVNAME_SIZE];
-
-	pr_info_ratelimited("%s: attempt to access beyond end of device\n"
-			    "%s: rw=%d, want=%llu, limit=%llu\n",
-			    current->comm,
-			    bio_devname(bio, b), bio->bi_opf,
-			    bio_end_sector(bio), maxsector);
-}
-
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 
 static DECLARE_FAULT_ATTR(fail_make_request);
@@ -580,14 +560,10 @@ late_initcall(fail_make_request_debugfs);
 static inline bool bio_check_ro(struct bio *bio)
 {
 	if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) {
-		char b[BDEVNAME_SIZE];
-
 		if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
 			return false;
-
-		WARN_ONCE(1,
-		       "Trying to write to read-only block-device %s (partno %d)\n",
-			bio_devname(bio, b), bio->bi_bdev->bd_partno);
+		pr_warn("Trying to write to read-only block-device %pg\n",
+			bio->bi_bdev);
 		/* Older lvm-tools actually trigger this */
 		return false;
 	}
@@ -616,7 +592,11 @@ static inline int bio_check_eod(struct bio *bio)
 	if (nr_sectors && maxsector &&
 	    (nr_sectors > maxsector ||
 	     bio->bi_iter.bi_sector > maxsector - nr_sectors)) {
-		handle_bad_sector(bio, maxsector);
+		pr_info_ratelimited("%s: attempt to access beyond end of device\n"
+				    "%pg: rw=%d, want=%llu, limit=%llu\n",
+				    current->comm,
+				    bio->bi_bdev, bio->bi_opf,
+				    bio_end_sector(bio), maxsector);
 		return -EIO;
 	}
 	return 0;
@@ -676,7 +656,123 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 	return BLK_STS_OK;
 }
 
-noinline_for_stack bool submit_bio_checks(struct bio *bio)
+static void __submit_bio(struct bio *bio)
+{
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+
+	if (unlikely(!blk_crypto_bio_prep(&bio)))
+		return;
+
+	if (!disk->fops->submit_bio) {
+		blk_mq_submit_bio(bio);
+	} else if (likely(bio_queue_enter(bio) == 0)) {
+		disk->fops->submit_bio(bio);
+		blk_queue_exit(disk->queue);
+	}
+}
+
+/*
+ * The loop in this function may be a bit non-obvious, and so deserves some
+ * explanation:
+ *
+ *  - Before entering the loop, bio->bi_next is NULL (as all callers ensure
+ *    that), so we have a list with a single bio.
+ *  - We pretend that we have just taken it off a longer list, so we assign
+ *    bio_list to a pointer to the bio_list_on_stack, thus initialising the
+ *    bio_list of new bios to be added.  ->submit_bio() may indeed add some more
+ *    bios through a recursive call to submit_bio_noacct.  If it did, we find a
+ *    non-NULL value in bio_list and re-enter the loop from the top.
+ *  - In this case we really did just take the bio of the top of the list (no
+ *    pretending) and so remove it from bio_list, and call into ->submit_bio()
+ *    again.
+ *
+ * bio_list_on_stack[0] contains bios submitted by the current ->submit_bio.
+ * bio_list_on_stack[1] contains bios that were submitted before the current
+ *	->submit_bio_bio, but that haven't been processed yet.
+ */
+static void __submit_bio_noacct(struct bio *bio)
+{
+	struct bio_list bio_list_on_stack[2];
+
+	BUG_ON(bio->bi_next);
+
+	bio_list_init(&bio_list_on_stack[0]);
+	current->bio_list = bio_list_on_stack;
+
+	do {
+		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+		struct bio_list lower, same;
+
+		/*
+		 * Create a fresh bio_list for all subordinate requests.
+		 */
+		bio_list_on_stack[1] = bio_list_on_stack[0];
+		bio_list_init(&bio_list_on_stack[0]);
+
+		__submit_bio(bio);
+
+		/*
+		 * Sort new bios into those for a lower level and those for the
+		 * same level.
+		 */
+		bio_list_init(&lower);
+		bio_list_init(&same);
+		while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
+			if (q == bdev_get_queue(bio->bi_bdev))
+				bio_list_add(&same, bio);
+			else
+				bio_list_add(&lower, bio);
+
+		/*
+		 * Now assemble so we handle the lowest level first.
+		 */
+		bio_list_merge(&bio_list_on_stack[0], &lower);
+		bio_list_merge(&bio_list_on_stack[0], &same);
+		bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
+	} while ((bio = bio_list_pop(&bio_list_on_stack[0])));
+
+	current->bio_list = NULL;
+}
+
+static void __submit_bio_noacct_mq(struct bio *bio)
+{
+	struct bio_list bio_list[2] = { };
+
+	current->bio_list = bio_list;
+
+	do {
+		__submit_bio(bio);
+	} while ((bio = bio_list_pop(&bio_list[0])));
+
+	current->bio_list = NULL;
+}
+
+void submit_bio_noacct_nocheck(struct bio *bio)
+{
+	/*
+	 * We only want one ->submit_bio to be active at a time, else stack
+	 * usage with stacked devices could be a problem.  Use current->bio_list
+	 * to collect a list of requests submited by a ->submit_bio method while
+	 * it is active, and then process them after it returned.
+	 */
+	if (current->bio_list)
+		bio_list_add(&current->bio_list[0], bio);
+	else if (!bio->bi_bdev->bd_disk->fops->submit_bio)
+		__submit_bio_noacct_mq(bio);
+	else
+		__submit_bio_noacct(bio);
+}
+
+/**
+ * submit_bio_noacct - re-submit a bio to the block device layer for I/O
+ * @bio:  The bio describing the location in memory and on the device.
+ *
+ * This is a version of submit_bio() that shall only be used for I/O that is
+ * resubmitted to lower level drivers by stacking block drivers.  All file
+ * systems and other upper level users of the block layer should use
+ * submit_bio() instead.
+ */
+void submit_bio_noacct(struct bio *bio)
 {
 	struct block_device *bdev = bio->bi_bdev;
 	struct request_queue *q = bdev_get_queue(bdev);
@@ -761,7 +857,7 @@ noinline_for_stack bool submit_bio_checks(struct bio *bio)
 	}
 
 	if (blk_throtl_bio(bio))
-		return false;
+		return;
 
 	blk_cgroup_bio_start(bio);
 	blkcg_bio_issue_init(bio);
@@ -773,138 +869,14 @@ noinline_for_stack bool submit_bio_checks(struct bio *bio)
 		 */
 		bio_set_flag(bio, BIO_TRACE_COMPLETION);
 	}
-	return true;
+	submit_bio_noacct_nocheck(bio);
+	return;
 
 not_supported:
 	status = BLK_STS_NOTSUPP;
 end_io:
 	bio->bi_status = status;
 	bio_endio(bio);
-	return false;
-}
-
-static void __submit_bio_fops(struct gendisk *disk, struct bio *bio)
-{
-	if (blk_crypto_bio_prep(&bio)) {
-		if (likely(bio_queue_enter(bio) == 0)) {
-			disk->fops->submit_bio(bio);
-			blk_queue_exit(disk->queue);
-		}
-	}
-}
-
-static void __submit_bio(struct bio *bio)
-{
-	struct gendisk *disk = bio->bi_bdev->bd_disk;
-
-	if (unlikely(!submit_bio_checks(bio)))
-		return;
-
-	if (!disk->fops->submit_bio)
-		blk_mq_submit_bio(bio);
-	else
-		__submit_bio_fops(disk, bio);
-}
-
-/*
- * The loop in this function may be a bit non-obvious, and so deserves some
- * explanation:
- *
- *  - Before entering the loop, bio->bi_next is NULL (as all callers ensure
- *    that), so we have a list with a single bio.
- *  - We pretend that we have just taken it off a longer list, so we assign
- *    bio_list to a pointer to the bio_list_on_stack, thus initialising the
- *    bio_list of new bios to be added.  ->submit_bio() may indeed add some more
- *    bios through a recursive call to submit_bio_noacct.  If it did, we find a
- *    non-NULL value in bio_list and re-enter the loop from the top.
- *  - In this case we really did just take the bio of the top of the list (no
- *    pretending) and so remove it from bio_list, and call into ->submit_bio()
- *    again.
- *
- * bio_list_on_stack[0] contains bios submitted by the current ->submit_bio.
- * bio_list_on_stack[1] contains bios that were submitted before the current
- *	->submit_bio_bio, but that haven't been processed yet.
- */
-static void __submit_bio_noacct(struct bio *bio)
-{
-	struct bio_list bio_list_on_stack[2];
-
-	BUG_ON(bio->bi_next);
-
-	bio_list_init(&bio_list_on_stack[0]);
-	current->bio_list = bio_list_on_stack;
-
-	do {
-		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-		struct bio_list lower, same;
-
-		/*
-		 * Create a fresh bio_list for all subordinate requests.
-		 */
-		bio_list_on_stack[1] = bio_list_on_stack[0];
-		bio_list_init(&bio_list_on_stack[0]);
-
-		__submit_bio(bio);
-
-		/*
-		 * Sort new bios into those for a lower level and those for the
-		 * same level.
-		 */
-		bio_list_init(&lower);
-		bio_list_init(&same);
-		while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
-			if (q == bdev_get_queue(bio->bi_bdev))
-				bio_list_add(&same, bio);
-			else
-				bio_list_add(&lower, bio);
-
-		/*
-		 * Now assemble so we handle the lowest level first.
-		 */
-		bio_list_merge(&bio_list_on_stack[0], &lower);
-		bio_list_merge(&bio_list_on_stack[0], &same);
-		bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
-	} while ((bio = bio_list_pop(&bio_list_on_stack[0])));
-
-	current->bio_list = NULL;
-}
-
-static void __submit_bio_noacct_mq(struct bio *bio)
-{
-	struct bio_list bio_list[2] = { };
-
-	current->bio_list = bio_list;
-
-	do {
-		__submit_bio(bio);
-	} while ((bio = bio_list_pop(&bio_list[0])));
-
-	current->bio_list = NULL;
-}
-
-/**
- * submit_bio_noacct - re-submit a bio to the block device layer for I/O
- * @bio:  The bio describing the location in memory and on the device.
- *
- * This is a version of submit_bio() that shall only be used for I/O that is
- * resubmitted to lower level drivers by stacking block drivers.  All file
- * systems and other upper level users of the block layer should use
- * submit_bio() instead.
- */
-void submit_bio_noacct(struct bio *bio)
-{
-	/*
-	 * We only want one ->submit_bio to be active at a time, else stack
-	 * usage with stacked devices could be a problem.  Use current->bio_list
-	 * to collect a list of requests submited by a ->submit_bio method while
-	 * it is active, and then process them after it returned.
-	 */
-	if (current->bio_list)
-		bio_list_add(&current->bio_list[0], bio);
-	else if (!bio->bi_bdev->bd_disk->fops->submit_bio)
-		__submit_bio_noacct_mq(bio);
-	else
-		__submit_bio_noacct(bio);
 }
 EXPORT_SYMBOL(submit_bio_noacct);
 
@@ -989,8 +961,7 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return 0;
 
-	if (current->plug)
-		blk_flush_plug(current->plug, false);
+	blk_flush_plug(current->plug, false);
 
 	if (blk_queue_enter(q, BLK_MQ_REQ_NOWAIT))
 		return 0;
@@ -1272,7 +1243,7 @@ struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data,
 }
 EXPORT_SYMBOL(blk_check_plugged);
 
-void blk_flush_plug(struct blk_plug *plug, bool from_schedule)
+void __blk_flush_plug(struct blk_plug *plug, bool from_schedule)
 {
 	if (!list_empty(&plug->cb_list))
 		flush_plug_callbacks(plug, from_schedule);
@@ -1301,7 +1272,7 @@ void blk_flush_plug(struct blk_plug *plug, bool from_schedule)
 void blk_finish_plug(struct blk_plug *plug)
 {
 	if (plug == current->plug) {
-		blk_flush_plug(plug, false);
+		__blk_flush_plug(plug, false);
 		current->plug = NULL;
 	}
 }
diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
index c87aba8584c6..18c8eafe20b9 100644
--- a/block/blk-crypto-fallback.c
+++ b/block/blk-crypto-fallback.c
@@ -10,7 +10,6 @@
 #define pr_fmt(fmt) "blk-crypto-fallback: " fmt
 
 #include <crypto/skcipher.h>
-#include <linux/blk-cgroup.h>
 #include <linux/blk-crypto.h>
 #include <linux/blk-crypto-profile.h>
 #include <linux/blkdev.h>
@@ -20,6 +19,7 @@
 #include <linux/random.h>
 #include <linux/scatterlist.h>
 
+#include "blk-cgroup.h"
 #include "blk-crypto-internal.h"
 
 static unsigned int num_prealloc_bounce_pg = 32;
diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h
index 2fb0d65a464c..e6818ffaddbf 100644
--- a/block/blk-crypto-internal.h
+++ b/block/blk-crypto-internal.h
@@ -11,6 +11,7 @@
 
 /* Represents a crypto mode supported by blk-crypto  */
 struct blk_crypto_mode {
+	const char *name; /* name of this mode, shown in sysfs */
 	const char *cipher_str; /* crypto API name (for fallback case) */
 	unsigned int keysize; /* key size in bytes */
 	unsigned int ivsize; /* iv size in bytes */
@@ -20,6 +21,10 @@ extern const struct blk_crypto_mode blk_crypto_modes[];
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 
+int blk_crypto_sysfs_register(struct request_queue *q);
+
+void blk_crypto_sysfs_unregister(struct request_queue *q);
+
 void bio_crypt_dun_increment(u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE],
 			     unsigned int inc);
 
@@ -62,6 +67,13 @@ static inline bool blk_crypto_rq_is_encrypted(struct request *rq)
 
 #else /* CONFIG_BLK_INLINE_ENCRYPTION */
 
+static inline int blk_crypto_sysfs_register(struct request_queue *q)
+{
+	return 0;
+}
+
+static inline void blk_crypto_sysfs_unregister(struct request_queue *q) { }
+
 static inline bool bio_crypt_rq_ctx_compatible(struct request *rq,
 					       struct bio *bio)
 {
diff --git a/block/blk-crypto-sysfs.c b/block/blk-crypto-sysfs.c
new file mode 100644
index 000000000000..fd93bd2f33b7
--- /dev/null
+++ b/block/blk-crypto-sysfs.c
@@ -0,0 +1,172 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2021 Google LLC
+ *
+ * sysfs support for blk-crypto.  This file contains the code which exports the
+ * crypto capabilities of devices via /sys/block/$disk/queue/crypto/.
+ */
+
+#include <linux/blk-crypto-profile.h>
+
+#include "blk-crypto-internal.h"
+
+struct blk_crypto_kobj {
+	struct kobject kobj;
+	struct blk_crypto_profile *profile;
+};
+
+struct blk_crypto_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct blk_crypto_profile *profile,
+			struct blk_crypto_attr *attr, char *page);
+};
+
+static struct blk_crypto_profile *kobj_to_crypto_profile(struct kobject *kobj)
+{
+	return container_of(kobj, struct blk_crypto_kobj, kobj)->profile;
+}
+
+static struct blk_crypto_attr *attr_to_crypto_attr(struct attribute *attr)
+{
+	return container_of(attr, struct blk_crypto_attr, attr);
+}
+
+static ssize_t max_dun_bits_show(struct blk_crypto_profile *profile,
+				 struct blk_crypto_attr *attr, char *page)
+{
+	return sysfs_emit(page, "%u\n", 8 * profile->max_dun_bytes_supported);
+}
+
+static ssize_t num_keyslots_show(struct blk_crypto_profile *profile,
+				 struct blk_crypto_attr *attr, char *page)
+{
+	return sysfs_emit(page, "%u\n", profile->num_slots);
+}
+
+#define BLK_CRYPTO_RO_ATTR(_name) \
+	static struct blk_crypto_attr _name##_attr = __ATTR_RO(_name)
+
+BLK_CRYPTO_RO_ATTR(max_dun_bits);
+BLK_CRYPTO_RO_ATTR(num_keyslots);
+
+static struct attribute *blk_crypto_attrs[] = {
+	&max_dun_bits_attr.attr,
+	&num_keyslots_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group blk_crypto_attr_group = {
+	.attrs = blk_crypto_attrs,
+};
+
+/*
+ * The encryption mode attributes.  To avoid hard-coding the list of encryption
+ * modes, these are initialized at boot time by blk_crypto_sysfs_init().
+ */
+static struct blk_crypto_attr __blk_crypto_mode_attrs[BLK_ENCRYPTION_MODE_MAX];
+static struct attribute *blk_crypto_mode_attrs[BLK_ENCRYPTION_MODE_MAX + 1];
+
+static umode_t blk_crypto_mode_is_visible(struct kobject *kobj,
+					  struct attribute *attr, int n)
+{
+	struct blk_crypto_profile *profile = kobj_to_crypto_profile(kobj);
+	struct blk_crypto_attr *a = attr_to_crypto_attr(attr);
+	int mode_num = a - __blk_crypto_mode_attrs;
+
+	if (profile->modes_supported[mode_num])
+		return 0444;
+	return 0;
+}
+
+static ssize_t blk_crypto_mode_show(struct blk_crypto_profile *profile,
+				    struct blk_crypto_attr *attr, char *page)
+{
+	int mode_num = attr - __blk_crypto_mode_attrs;
+
+	return sysfs_emit(page, "0x%x\n", profile->modes_supported[mode_num]);
+}
+
+static const struct attribute_group blk_crypto_modes_attr_group = {
+	.name = "modes",
+	.attrs = blk_crypto_mode_attrs,
+	.is_visible = blk_crypto_mode_is_visible,
+};
+
+static const struct attribute_group *blk_crypto_attr_groups[] = {
+	&blk_crypto_attr_group,
+	&blk_crypto_modes_attr_group,
+	NULL,
+};
+
+static ssize_t blk_crypto_attr_show(struct kobject *kobj,
+				    struct attribute *attr, char *page)
+{
+	struct blk_crypto_profile *profile = kobj_to_crypto_profile(kobj);
+	struct blk_crypto_attr *a = attr_to_crypto_attr(attr);
+
+	return a->show(profile, a, page);
+}
+
+static const struct sysfs_ops blk_crypto_attr_ops = {
+	.show = blk_crypto_attr_show,
+};
+
+static void blk_crypto_release(struct kobject *kobj)
+{
+	kfree(container_of(kobj, struct blk_crypto_kobj, kobj));
+}
+
+static struct kobj_type blk_crypto_ktype = {
+	.default_groups = blk_crypto_attr_groups,
+	.sysfs_ops	= &blk_crypto_attr_ops,
+	.release	= blk_crypto_release,
+};
+
+/*
+ * If the request_queue has a blk_crypto_profile, create the "crypto"
+ * subdirectory in sysfs (/sys/block/$disk/queue/crypto/).
+ */
+int blk_crypto_sysfs_register(struct request_queue *q)
+{
+	struct blk_crypto_kobj *obj;
+	int err;
+
+	if (!q->crypto_profile)
+		return 0;
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return -ENOMEM;
+	obj->profile = q->crypto_profile;
+
+	err = kobject_init_and_add(&obj->kobj, &blk_crypto_ktype, &q->kobj,
+				   "crypto");
+	if (err) {
+		kobject_put(&obj->kobj);
+		return err;
+	}
+	q->crypto_kobject = &obj->kobj;
+	return 0;
+}
+
+void blk_crypto_sysfs_unregister(struct request_queue *q)
+{
+	kobject_put(q->crypto_kobject);
+}
+
+static int __init blk_crypto_sysfs_init(void)
+{
+	int i;
+
+	BUILD_BUG_ON(BLK_ENCRYPTION_MODE_INVALID != 0);
+	for (i = 1; i < BLK_ENCRYPTION_MODE_MAX; i++) {
+		struct blk_crypto_attr *attr = &__blk_crypto_mode_attrs[i];
+
+		attr->attr.name = blk_crypto_modes[i].name;
+		attr->attr.mode = 0444;
+		attr->show = blk_crypto_mode_show;
+		blk_crypto_mode_attrs[i - 1] = &attr->attr;
+	}
+	return 0;
+}
+subsys_initcall(blk_crypto_sysfs_init);
diff --git a/block/blk-crypto.c b/block/blk-crypto.c
index ec9efeeeca91..a496aaef85ba 100644
--- a/block/blk-crypto.c
+++ b/block/blk-crypto.c
@@ -19,16 +19,19 @@
 
 const struct blk_crypto_mode blk_crypto_modes[] = {
 	[BLK_ENCRYPTION_MODE_AES_256_XTS] = {
+		.name = "AES-256-XTS",
 		.cipher_str = "xts(aes)",
 		.keysize = 64,
 		.ivsize = 16,
 	},
 	[BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV] = {
+		.name = "AES-128-CBC-ESSIV",
 		.cipher_str = "essiv(cbc(aes),sha256)",
 		.keysize = 16,
 		.ivsize = 16,
 	},
 	[BLK_ENCRYPTION_MODE_ADIANTUM] = {
+		.name = "Adiantum",
 		.cipher_str = "adiantum(xchacha12,aes)",
 		.keysize = 32,
 		.ivsize = 32,
@@ -111,7 +114,6 @@ int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask)
 	*dst->bi_crypt_context = *src->bi_crypt_context;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(__bio_crypt_clone);
 
 /* Increments @dun by @inc, treating @dun as a multi-limb integer. */
 void bio_crypt_dun_increment(u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE],
diff --git a/block/blk-flush.c b/block/blk-flush.c
index e4df894189ce..c68968724870 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -460,9 +460,7 @@ int blkdev_issue_flush(struct block_device *bdev)
 {
 	struct bio bio;
 
-	bio_init(&bio, NULL, 0);
-	bio_set_dev(&bio, bdev);
-	bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+	bio_init(&bio, bdev, NULL, 0, REQ_OP_WRITE | REQ_PREFLUSH);
 	return submit_bio_wait(&bio);
 }
 EXPORT_SYMBOL(blkdev_issue_flush);
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 769b64394298..70a0a3d680a3 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -178,12 +178,12 @@
 #include <linux/time64.h>
 #include <linux/parser.h>
 #include <linux/sched/signal.h>
-#include <linux/blk-cgroup.h>
 #include <asm/local.h>
 #include <asm/local64.h>
 #include "blk-rq-qos.h"
 #include "blk-stat.h"
 #include "blk-wbt.h"
+#include "blk-cgroup.h"
 
 #ifdef CONFIG_TRACEPOINTS
 
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 6593c7123b97..2f33932e72e3 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -74,9 +74,9 @@
 #include <linux/sched/signal.h>
 #include <trace/events/block.h>
 #include <linux/blk-mq.h>
-#include <linux/blk-cgroup.h>
 #include "blk-rq-qos.h"
 #include "blk-stat.h"
+#include "blk-cgroup.h"
 #include "blk.h"
 
 #define DEFAULT_SCALE_COOKIE 1000000U
@@ -598,7 +598,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
 	int inflight = 0;
 
 	blkg = bio->bi_blkg;
-	if (!blkg || !bio_flagged(bio, BIO_TRACKED))
+	if (!blkg || !bio_flagged(bio, BIO_QOS_THROTTLED))
 		return;
 
 	iolat = blkg_to_lat(bio->bi_blkg);
diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c
index 2e7f10e1c03f..79e797f5d194 100644
--- a/block/blk-ioprio.c
+++ b/block/blk-ioprio.c
@@ -12,11 +12,11 @@
  *   Documentation/admin-guide/cgroup-v2.rst.
  */
 
-#include <linux/blk-cgroup.h>
 #include <linux/blk-mq.h>
 #include <linux/blk_types.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include "blk-cgroup.h"
 #include "blk-ioprio.h"
 #include "blk-rq-qos.h"
 
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 9f09beadcbe3..fc6ea52e7482 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -10,19 +10,6 @@
 
 #include "blk.h"
 
-struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp)
-{
-	struct bio *new = bio_alloc(gfp, nr_pages);
-
-	if (bio) {
-		bio_chain(bio, new);
-		submit_bio(bio);
-	}
-
-	return new;
-}
-EXPORT_SYMBOL_GPL(blk_next_bio);
-
 int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, int flags,
 		struct bio **biop)
@@ -32,9 +19,6 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	unsigned int op;
 	sector_t bs_mask, part_offset = 0;
 
-	if (!q)
-		return -ENXIO;
-
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
@@ -95,11 +79,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 		WARN_ON_ONCE((req_sects << 9) > UINT_MAX);
 
-		bio = blk_next_bio(bio, 0, gfp_mask);
+		bio = blk_next_bio(bio, bdev, 0, op, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
-		bio_set_dev(bio, bdev);
-		bio_set_op_attrs(bio, op, 0);
-
 		bio->bi_iter.bi_size = req_sects << 9;
 		sector += req_sects;
 		nr_sects -= req_sects;
@@ -172,9 +153,6 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	struct bio *bio = *biop;
 	sector_t bs_mask;
 
-	if (!q)
-		return -ENXIO;
-
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
@@ -189,14 +167,12 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	max_write_same_sectors = bio_allowed_max_sectors(q);
 
 	while (nr_sects) {
-		bio = blk_next_bio(bio, 1, gfp_mask);
+		bio = blk_next_bio(bio, bdev, 1, REQ_OP_WRITE_SAME, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
-		bio_set_dev(bio, bdev);
 		bio->bi_vcnt = 1;
 		bio->bi_io_vec->bv_page = page;
 		bio->bi_io_vec->bv_offset = 0;
 		bio->bi_io_vec->bv_len = bdev_logical_block_size(bdev);
-		bio_set_op_attrs(bio, REQ_OP_WRITE_SAME, 0);
 
 		if (nr_sects > max_write_same_sectors) {
 			bio->bi_iter.bi_size = max_write_same_sectors << 9;
@@ -250,10 +226,6 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 {
 	struct bio *bio = *biop;
 	unsigned int max_write_zeroes_sectors;
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (!q)
-		return -ENXIO;
 
 	if (bdev_read_only(bdev))
 		return -EPERM;
@@ -265,10 +237,8 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 		return -EOPNOTSUPP;
 
 	while (nr_sects) {
-		bio = blk_next_bio(bio, 0, gfp_mask);
+		bio = blk_next_bio(bio, bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
-		bio_set_dev(bio, bdev);
-		bio->bi_opf = REQ_OP_WRITE_ZEROES;
 		if (flags & BLKDEV_ZERO_NOUNMAP)
 			bio->bi_opf |= REQ_NOUNMAP;
 
@@ -304,23 +274,17 @@ static int __blkdev_issue_zero_pages(struct block_device *bdev,
 		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
 		struct bio **biop)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
 	struct bio *bio = *biop;
 	int bi_size = 0;
 	unsigned int sz;
 
-	if (!q)
-		return -ENXIO;
-
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
 	while (nr_sects != 0) {
-		bio = blk_next_bio(bio, __blkdev_sectors_to_bio_pages(nr_sects),
-				   gfp_mask);
+		bio = blk_next_bio(bio, bdev, __blkdev_sectors_to_bio_pages(nr_sects),
+				   REQ_OP_WRITE, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
-		bio_set_dev(bio, bdev);
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 		while (nr_sects != 0) {
 			sz = min((sector_t) PAGE_SIZE, nr_sects << 9);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 4de34a332c9f..ea6968313b4a 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,6 +9,7 @@
 #include <linux/blk-integrity.h>
 #include <linux/scatterlist.h>
 #include <linux/part_stat.h>
+#include <linux/blk-cgroup.h>
 
 #include <trace/events/block.h>
 
@@ -368,8 +369,6 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
 		trace_block_split(split, (*bio)->bi_iter.bi_sector);
 		submit_bio_noacct(*bio);
 		*bio = split;
-
-		blk_throtl_charge_bio_split(*bio);
 	}
 }
 
@@ -600,6 +599,9 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
 static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
 		unsigned int nr_phys_segs)
 {
+	if (!blk_cgroup_mergeable(req, bio))
+		goto no_merge;
+
 	if (blk_integrity_merge_bio(req->q, req, bio) == false)
 		goto no_merge;
 
@@ -696,6 +698,9 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	if (total_phys_segments > blk_rq_get_max_segments(req))
 		return 0;
 
+	if (!blk_cgroup_mergeable(req, next->bio))
+		return 0;
+
 	if (blk_integrity_merge_rq(q, req, next) == false)
 		return 0;
 
@@ -904,6 +909,10 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (bio_data_dir(bio) != rq_data_dir(rq))
 		return false;
 
+	/* don't merge across cgroup boundaries */
+	if (!blk_cgroup_mergeable(rq, bio))
+		return false;
+
 	/* only merge integrity protected bio into ditto rq */
 	if (blk_integrity_merge_bio(rq->q, rq, bio) == false)
 		return false;
@@ -1089,12 +1098,20 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 	if (!plug || rq_list_empty(plug->mq_list))
 		return false;
 
-	/* check the previously added entry for a quick merge attempt */
-	rq = rq_list_peek(&plug->mq_list);
-	if (rq->q == q) {
-		if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
-				BIO_MERGE_OK)
-			return true;
+	rq_list_for_each(&plug->mq_list, rq) {
+		if (rq->q == q) {
+			if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
+			    BIO_MERGE_OK)
+				return true;
+			break;
+		}
+
+		/*
+		 * Only keep iterating plug list for merges if we have multiple
+		 * queues
+		 */
+		if (!plug->multiple_queues)
+			break;
 	}
 	return false;
 }
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 3a790eb4995c..e2880f6deb34 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -707,7 +707,7 @@ static void debugfs_create_files(struct dentry *parent, void *data,
 void blk_mq_debugfs_register(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	debugfs_create_files(q->debugfs_dir, q, blk_mq_debugfs_queue_attrs);
 
@@ -780,7 +780,7 @@ void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx)
 void blk_mq_debugfs_register_hctxs(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_debugfs_register_hctx(q, hctx);
@@ -789,7 +789,7 @@ void blk_mq_debugfs_register_hctxs(struct request_queue *q)
 void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_debugfs_unregister_hctx(hctx);
diff --git a/block/blk-mq-debugfs.h b/block/blk-mq-debugfs.h
index a68aa6041a10..69918f4170d6 100644
--- a/block/blk-mq-debugfs.h
+++ b/block/blk-mq-debugfs.h
@@ -6,6 +6,8 @@
 
 #include <linux/seq_file.h>
 
+struct blk_mq_hw_ctx;
+
 struct blk_mq_debugfs_attr {
 	const char *name;
 	umode_t mode;
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 55488ba97823..9e56a69422b6 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -180,11 +180,18 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
 
 static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
 {
+	unsigned long end = jiffies + HZ;
 	int ret;
 
 	do {
 		ret = __blk_mq_do_dispatch_sched(hctx);
-	} while (ret == 1);
+		if (ret != 1)
+			break;
+		if (need_resched() || time_is_before_jiffies(end)) {
+			blk_mq_delay_run_hw_queue(hctx, 0);
+			break;
+		}
+	} while (1);
 
 	return ret;
 }
@@ -515,7 +522,7 @@ static void blk_mq_exit_sched_shared_tags(struct request_queue *queue)
 static void blk_mq_sched_tags_teardown(struct request_queue *q, unsigned int flags)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (hctx->sched_tags) {
@@ -550,9 +557,10 @@ static int blk_mq_init_sched_shared_tags(struct request_queue *queue)
 
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 {
-	unsigned int i, flags = q->tag_set->flags;
+	unsigned int flags = q->tag_set->flags;
 	struct blk_mq_hw_ctx *hctx;
 	struct elevator_queue *eq;
+	unsigned long i;
 	int ret;
 
 	if (!e) {
@@ -618,7 +626,7 @@ err_free_map_and_rqs:
 void blk_mq_sched_free_rqs(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	if (blk_mq_is_shared_tags(q->tag_set->flags)) {
 		blk_mq_free_rqs(q->tag_set, q->sched_shared_tags,
@@ -635,7 +643,7 @@ void blk_mq_sched_free_rqs(struct request_queue *q)
 void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
 {
 	struct blk_mq_hw_ctx *hctx;
-	unsigned int i;
+	unsigned long i;
 	unsigned int flags = 0;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 674786574075..c08426975856 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -206,7 +206,7 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
 void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	lockdep_assert_held(&q->sysfs_dir_lock);
 
@@ -255,7 +255,8 @@ void blk_mq_sysfs_init(struct request_queue *q)
 int __blk_mq_register_dev(struct device *dev, struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int ret, i;
+	unsigned long i, j;
+	int ret;
 
 	WARN_ON_ONCE(!q->kobj.parent);
 	lockdep_assert_held(&q->sysfs_dir_lock);
@@ -278,8 +279,10 @@ out:
 	return ret;
 
 unreg:
-	while (--i >= 0)
-		blk_mq_unregister_hctx(q->queue_hw_ctx[i]);
+	queue_for_each_hw_ctx(q, hctx, j) {
+		if (j < i)
+			blk_mq_unregister_hctx(hctx);
+	}
 
 	kobject_uevent(q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(q->mq_kobj);
@@ -290,7 +293,7 @@ unreg:
 void blk_mq_sysfs_unregister(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	mutex_lock(&q->sysfs_dir_lock);
 	if (!q->mq_sysfs_init_done)
@@ -306,7 +309,8 @@ unlock:
 int blk_mq_sysfs_register(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i, ret = 0;
+	unsigned long i;
+	int ret = 0;
 
 	mutex_lock(&q->sysfs_dir_lock);
 	if (!q->mq_sysfs_init_done)
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 845f74e8dd7b..68ac23d0b640 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -107,7 +107,7 @@ static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
 		return BLK_MQ_NO_TAG;
 
 	if (data->shallow_depth)
-		return __sbitmap_queue_get_shallow(bt, data->shallow_depth);
+		return sbitmap_queue_get_shallow(bt, data->shallow_depth);
 	else
 		return __sbitmap_queue_get(bt);
 }
@@ -498,7 +498,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
 		void *priv)
 {
 	/*
-	 * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and queue_hw_ctx
+	 * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and hctx_table
 	 * while the queue is frozen. So we can use q_usage_counter to avoid
 	 * racing with it.
 	 */
@@ -515,7 +515,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
 		bt_for_each(NULL, q, btags, fn, priv, false);
 	} else {
 		struct blk_mq_hw_ctx *hctx;
-		int i;
+		unsigned long i;
 
 		queue_for_each_hw_ctx(q, hctx, i) {
 			struct blk_mq_tags *tags = hctx->tags;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 9a9185a0a2d1..8e659dc5fcf3 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -71,7 +71,8 @@ static int blk_mq_poll_stats_bkt(const struct request *rq)
 static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q,
 		blk_qc_t qc)
 {
-	return q->queue_hw_ctx[(qc & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT];
+	return xa_load(&q->hctx_table,
+			(qc & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT);
 }
 
 static inline struct request *blk_qc_to_rq(struct blk_mq_hw_ctx *hctx,
@@ -312,7 +313,7 @@ EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
 void blk_mq_wake_waiters(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	unsigned int i;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		if (blk_mq_hw_queue_mapped(hctx))
@@ -573,7 +574,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	 * If not tell the caller that it should skip this queue.
 	 */
 	ret = -EXDEV;
-	data.hctx = q->queue_hw_ctx[hctx_idx];
+	data.hctx = xa_load(&q->hctx_table, hctx_idx);
 	if (!blk_mq_hw_queue_mapped(data.hctx))
 		goto out_queue_exit;
 	cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
@@ -793,8 +794,10 @@ bool blk_update_request(struct request *req, blk_status_t error,
 #endif
 
 	if (unlikely(error && !blk_rq_is_passthrough(req) &&
-		     !(req->rq_flags & RQF_QUIET)))
+		     !(req->rq_flags & RQF_QUIET))) {
 		blk_print_req_error(req, error);
+		trace_block_rq_error(req, error, nr_bytes);
+	}
 
 	blk_account_io_completion(req, nr_bytes);
 
@@ -885,10 +888,15 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 
 static void __blk_account_io_start(struct request *rq)
 {
-	/* passthrough requests can hold bios that do not have ->bi_bdev set */
-	if (rq->bio && rq->bio->bi_bdev)
+	/*
+	 * All non-passthrough requests are created from a bio with one
+	 * exception: when a flush command that is part of a flush sequence
+	 * generated by the state machine in blk-flush.c is cloned onto the
+	 * lower device by dm-multipath we can get here without a bio.
+	 */
+	if (rq->bio)
 		rq->part = rq->bio->bi_bdev;
-	else if (rq->q->disk)
+	else
 		rq->part = rq->q->disk->part0;
 
 	part_stat_lock();
@@ -1444,7 +1452,7 @@ static void blk_mq_timeout_work(struct work_struct *work)
 		container_of(work, struct request_queue, timeout_work);
 	unsigned long next = 0;
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	/* A deadlock might occur if a request is stuck requiring a
 	 * timeout at the same time a queue freeze is waiting
@@ -2145,7 +2153,7 @@ static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q)
 void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 {
 	struct blk_mq_hw_ctx *hctx, *sq_hctx;
-	int i;
+	unsigned long i;
 
 	sq_hctx = NULL;
 	if (blk_mq_has_sqsched(q))
@@ -2173,7 +2181,7 @@ EXPORT_SYMBOL(blk_mq_run_hw_queues);
 void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
 {
 	struct blk_mq_hw_ctx *hctx, *sq_hctx;
-	int i;
+	unsigned long i;
 
 	sq_hctx = NULL;
 	if (blk_mq_has_sqsched(q))
@@ -2182,6 +2190,14 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
 		if (blk_mq_hctx_stopped(hctx))
 			continue;
 		/*
+		 * If there is already a run_work pending, leave the
+		 * pending delay untouched. Otherwise, a hctx can stall
+		 * if another hctx is re-delaying the other's work
+		 * before the work executes.
+		 */
+		if (delayed_work_pending(&hctx->run_work))
+			continue;
+		/*
 		 * Dispatch from this hctx either if there's no hctx preferred
 		 * by IO scheduler or if it has requests that bypass the
 		 * scheduler.
@@ -2203,7 +2219,7 @@ EXPORT_SYMBOL(blk_mq_delay_run_hw_queues);
 bool blk_mq_queue_stopped(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		if (blk_mq_hctx_stopped(hctx))
@@ -2242,7 +2258,7 @@ EXPORT_SYMBOL(blk_mq_stop_hw_queue);
 void blk_mq_stop_hw_queues(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_stop_hw_queue(hctx);
@@ -2260,7 +2276,7 @@ EXPORT_SYMBOL(blk_mq_start_hw_queue);
 void blk_mq_start_hw_queues(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_start_hw_queue(hctx);
@@ -2280,7 +2296,7 @@ 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;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_start_stopped_hw_queue(hctx, async);
@@ -2561,13 +2577,36 @@ static void __blk_mq_flush_plug_list(struct request_queue *q,
 	q->mq_ops->queue_rqs(&plug->mq_list);
 }
 
+static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
+{
+	struct blk_mq_hw_ctx *this_hctx = NULL;
+	struct blk_mq_ctx *this_ctx = NULL;
+	struct request *requeue_list = NULL;
+	unsigned int depth = 0;
+	LIST_HEAD(list);
+
+	do {
+		struct request *rq = rq_list_pop(&plug->mq_list);
+
+		if (!this_hctx) {
+			this_hctx = rq->mq_hctx;
+			this_ctx = rq->mq_ctx;
+		} else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) {
+			rq_list_add(&requeue_list, rq);
+			continue;
+		}
+		list_add_tail(&rq->queuelist, &list);
+		depth++;
+	} while (!rq_list_empty(plug->mq_list));
+
+	plug->mq_list = requeue_list;
+	trace_block_unplug(this_hctx->queue, depth, !from_sched);
+	blk_mq_sched_insert_requests(this_hctx, this_ctx, &list, from_sched);
+}
+
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 {
-	struct blk_mq_hw_ctx *this_hctx;
-	struct blk_mq_ctx *this_ctx;
 	struct request *rq;
-	unsigned int depth;
-	LIST_HEAD(list);
 
 	if (rq_list_empty(plug->mq_list))
 		return;
@@ -2603,35 +2642,9 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 			return;
 	}
 
-	this_hctx = NULL;
-	this_ctx = NULL;
-	depth = 0;
 	do {
-		rq = rq_list_pop(&plug->mq_list);
-
-		if (!this_hctx) {
-			this_hctx = rq->mq_hctx;
-			this_ctx = rq->mq_ctx;
-		} else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) {
-			trace_block_unplug(this_hctx->queue, depth,
-						!from_schedule);
-			blk_mq_sched_insert_requests(this_hctx, this_ctx,
-						&list, from_schedule);
-			depth = 0;
-			this_hctx = rq->mq_hctx;
-			this_ctx = rq->mq_ctx;
-
-		}
-
-		list_add(&rq->queuelist, &list);
-		depth++;
+		blk_mq_dispatch_plug_list(plug, from_schedule);
 	} while (!rq_list_empty(plug->mq_list));
-
-	if (!list_empty(&list)) {
-		trace_block_unplug(this_hctx->queue, depth, !from_schedule);
-		blk_mq_sched_insert_requests(this_hctx, this_ctx, &list,
-						from_schedule);
-	}
 }
 
 void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
@@ -2804,9 +2817,6 @@ void blk_mq_submit_bio(struct bio *bio)
 	unsigned int nr_segs = 1;
 	blk_status_t ret;
 
-	if (unlikely(!blk_crypto_bio_prep(&bio)))
-		return;
-
 	blk_queue_bounce(q, &bio);
 	if (blk_may_split(q, bio))
 		__blk_queue_split(q, &bio, &nr_segs);
@@ -2853,27 +2863,16 @@ void blk_mq_submit_bio(struct bio *bio)
 				blk_mq_try_issue_directly(rq->mq_hctx, rq));
 }
 
+#ifdef CONFIG_BLK_MQ_STACKING
 /**
- * blk_cloned_rq_check_limits - Helper function to check a cloned request
- *                              for the new queue limits
- * @q:  the queue
- * @rq: the request being checked
- *
- * Description:
- *    @rq may have been made based on weaker limitations of upper-level queues
- *    in request stacking drivers, and it may violate the limitation of @q.
- *    Since the block layer and the underlying device driver trust @rq
- *    after it is inserted to @q, it should be checked against @q before
- *    the insertion using this generic function.
- *
- *    Request stacking drivers like request-based dm may change the queue
- *    limits when retrying requests on other queues. Those requests need
- *    to be checked against the new queue limits again during dispatch.
+ * blk_insert_cloned_request - Helper for stacking drivers to submit a request
+ * @rq: the request being queued
  */
-static blk_status_t blk_cloned_rq_check_limits(struct request_queue *q,
-				      struct request *rq)
+blk_status_t blk_insert_cloned_request(struct request *rq)
 {
+	struct request_queue *q = rq->q;
 	unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq));
+	blk_status_t ret;
 
 	if (blk_rq_sectors(rq) > max_sectors) {
 		/*
@@ -2905,24 +2904,7 @@ static blk_status_t blk_cloned_rq_check_limits(struct request_queue *q,
 		return BLK_STS_IOERR;
 	}
 
-	return BLK_STS_OK;
-}
-
-/**
- * blk_insert_cloned_request - Helper for stacking drivers to submit a request
- * @q:  the queue to submit the request
- * @rq: the request being queued
- */
-blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq)
-{
-	blk_status_t ret;
-
-	ret = blk_cloned_rq_check_limits(q, rq);
-	if (ret != BLK_STS_OK)
-		return ret;
-
-	if (rq->q->disk &&
-	    should_fail_request(rq->q->disk->part0, blk_rq_bytes(rq)))
+	if (q->disk && should_fail_request(q->disk->part0, blk_rq_bytes(rq)))
 		return BLK_STS_IOERR;
 
 	if (blk_crypto_insert_cloned_request(rq))
@@ -2935,7 +2917,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 	 * bypass a potential scheduler on the bottom device for
 	 * insert.
 	 */
-	blk_mq_run_dispatch_ops(rq->q,
+	blk_mq_run_dispatch_ops(q,
 			ret = blk_mq_request_issue_directly(rq, true));
 	if (ret)
 		blk_account_io_done(rq, ktime_get_ns());
@@ -2990,10 +2972,10 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 		bs = &fs_bio_set;
 
 	__rq_for_each_bio(bio_src, rq_src) {
-		bio = bio_clone_fast(bio_src, gfp_mask, bs);
+		bio = bio_alloc_clone(rq->q->disk->part0, bio_src, gfp_mask,
+				      bs);
 		if (!bio)
 			goto free_and_out;
-		bio->bi_bdev = rq->q->disk->part0;
 
 		if (bio_ctr && bio_ctr(bio, bio_src, data))
 			goto free_and_out;
@@ -3030,6 +3012,7 @@ free_and_out:
 	return -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
+#endif /* CONFIG_BLK_MQ_STACKING */
 
 /*
  * Steal bios from a request and add them to a bio list.
@@ -3100,6 +3083,9 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 	struct blk_mq_tags *drv_tags;
 	struct page *page;
 
+	if (list_empty(&tags->page_list))
+		return;
+
 	if (blk_mq_is_shared_tags(set->flags))
 		drv_tags = set->shared_tags;
 	else
@@ -3142,15 +3128,41 @@ void blk_mq_free_rq_map(struct blk_mq_tags *tags)
 	blk_mq_free_tags(tags);
 }
 
+static enum hctx_type hctx_idx_to_type(struct blk_mq_tag_set *set,
+		unsigned int hctx_idx)
+{
+	int i;
+
+	for (i = 0; i < set->nr_maps; i++) {
+		unsigned int start = set->map[i].queue_offset;
+		unsigned int end = start + set->map[i].nr_queues;
+
+		if (hctx_idx >= start && hctx_idx < end)
+			break;
+	}
+
+	if (i >= set->nr_maps)
+		i = HCTX_TYPE_DEFAULT;
+
+	return i;
+}
+
+static int blk_mq_get_hctx_node(struct blk_mq_tag_set *set,
+		unsigned int hctx_idx)
+{
+	enum hctx_type type = hctx_idx_to_type(set, hctx_idx);
+
+	return blk_mq_hw_queue_to_node(&set->map[type], hctx_idx);
+}
+
 static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 					       unsigned int hctx_idx,
 					       unsigned int nr_tags,
 					       unsigned int reserved_tags)
 {
+	int node = blk_mq_get_hctx_node(set, hctx_idx);
 	struct blk_mq_tags *tags;
-	int node;
 
-	node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], hctx_idx);
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 
@@ -3199,10 +3211,9 @@ static int blk_mq_alloc_rqs(struct blk_mq_tag_set *set,
 			    unsigned int hctx_idx, unsigned int depth)
 {
 	unsigned int i, j, entries_per_page, max_order = 4;
+	int node = blk_mq_get_hctx_node(set, hctx_idx);
 	size_t rq_size, left;
-	int node;
 
-	node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], hctx_idx);
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 
@@ -3447,6 +3458,8 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 
 	blk_mq_remove_cpuhp(hctx);
 
+	xa_erase(&q->hctx_table, hctx_idx);
+
 	spin_lock(&q->unused_hctx_lock);
 	list_add(&hctx->hctx_list, &q->unused_hctx_list);
 	spin_unlock(&q->unused_hctx_lock);
@@ -3456,12 +3469,11 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
 		struct blk_mq_tag_set *set, int nr_queue)
 {
 	struct blk_mq_hw_ctx *hctx;
-	unsigned int i;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (i == nr_queue)
 			break;
-		blk_mq_debugfs_unregister_hctx(hctx);
 		blk_mq_exit_hctx(q, set, hctx, i);
 	}
 }
@@ -3486,8 +3498,15 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
 				hctx->numa_node))
 		goto exit_hctx;
+
+	if (xa_insert(&q->hctx_table, hctx_idx, hctx, GFP_KERNEL))
+		goto exit_flush_rq;
+
 	return 0;
 
+ exit_flush_rq:
+	if (set->ops->exit_request)
+		set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
  exit_hctx:
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
@@ -3647,7 +3666,8 @@ static void __blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
 
 static void blk_mq_map_swqueue(struct request_queue *q)
 {
-	unsigned int i, j, hctx_idx;
+	unsigned int j, hctx_idx;
+	unsigned long i;
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct blk_mq_tag_set *set = q->tag_set;
@@ -3754,7 +3774,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 static void queue_set_hctx_shared(struct request_queue *q, bool shared)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (shared) {
@@ -3854,7 +3874,7 @@ static int blk_mq_alloc_ctxs(struct request_queue *q)
 void blk_mq_release(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx, *next;
-	int i;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list));
@@ -3865,7 +3885,7 @@ void blk_mq_release(struct request_queue *q)
 		kobject_put(&hctx->kobj);
 	}
 
-	kfree(q->queue_hw_ctx);
+	xa_destroy(&q->hctx_table);
 
 	/*
 	 * release .mq_kobj and sw queue's kobject now because
@@ -3954,52 +3974,28 @@ static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
 static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 						struct request_queue *q)
 {
-	int i, j, end;
-	struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
-
-	if (q->nr_hw_queues < set->nr_hw_queues) {
-		struct blk_mq_hw_ctx **new_hctxs;
-
-		new_hctxs = kcalloc_node(set->nr_hw_queues,
-				       sizeof(*new_hctxs), GFP_KERNEL,
-				       set->numa_node);
-		if (!new_hctxs)
-			return;
-		if (hctxs)
-			memcpy(new_hctxs, hctxs, q->nr_hw_queues *
-			       sizeof(*hctxs));
-		q->queue_hw_ctx = new_hctxs;
-		kfree(hctxs);
-		hctxs = new_hctxs;
-	}
+	struct blk_mq_hw_ctx *hctx;
+	unsigned long i, j;
 
 	/* protect against switching io scheduler  */
 	mutex_lock(&q->sysfs_lock);
 	for (i = 0; i < set->nr_hw_queues; i++) {
-		int node;
-		struct blk_mq_hw_ctx *hctx;
+		int old_node;
+		int node = blk_mq_get_hctx_node(set, i);
+		struct blk_mq_hw_ctx *old_hctx = xa_load(&q->hctx_table, i);
 
-		node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], i);
-		/*
-		 * If the hw queue has been mapped to another numa node,
-		 * we need to realloc the hctx. If allocation fails, fallback
-		 * to use the previous one.
-		 */
-		if (hctxs[i] && (hctxs[i]->numa_node == node))
-			continue;
+		if (old_hctx) {
+			old_node = old_hctx->numa_node;
+			blk_mq_exit_hctx(q, set, old_hctx, i);
+		}
 
-		hctx = blk_mq_alloc_and_init_hctx(set, q, i, node);
-		if (hctx) {
-			if (hctxs[i])
-				blk_mq_exit_hctx(q, set, hctxs[i], i);
-			hctxs[i] = hctx;
-		} else {
-			if (hctxs[i])
-				pr_warn("Allocate new hctx on node %d fails,\
-						fallback to previous one on node %d\n",
-						node, hctxs[i]->numa_node);
-			else
+		if (!blk_mq_alloc_and_init_hctx(set, q, i, node)) {
+			if (!old_hctx)
 				break;
+			pr_warn("Allocate new hctx on node %d fails, fallback to previous one on node %d\n",
+					node, old_node);
+			hctx = blk_mq_alloc_and_init_hctx(set, q, i, old_node);
+			WARN_ON_ONCE(!hctx);
 		}
 	}
 	/*
@@ -4008,24 +4004,27 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	 */
 	if (i != set->nr_hw_queues) {
 		j = q->nr_hw_queues;
-		end = i;
 	} else {
 		j = i;
-		end = q->nr_hw_queues;
 		q->nr_hw_queues = set->nr_hw_queues;
 	}
 
-	for (; j < end; j++) {
-		struct blk_mq_hw_ctx *hctx = hctxs[j];
-
-		if (hctx) {
-			blk_mq_exit_hctx(q, set, hctx, j);
-			hctxs[j] = NULL;
-		}
-	}
+	xa_for_each_start(&q->hctx_table, j, hctx, j)
+		blk_mq_exit_hctx(q, set, hctx, j);
 	mutex_unlock(&q->sysfs_lock);
 }
 
+static void blk_mq_update_poll_flag(struct request_queue *q)
+{
+	struct blk_mq_tag_set *set = q->tag_set;
+
+	if (set->nr_maps > HCTX_TYPE_POLL &&
+	    set->map[HCTX_TYPE_POLL].nr_queues)
+		blk_queue_flag_set(QUEUE_FLAG_POLL, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_POLL, q);
+}
+
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q)
 {
@@ -4050,6 +4049,8 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	INIT_LIST_HEAD(&q->unused_hctx_list);
 	spin_lock_init(&q->unused_hctx_lock);
 
+	xa_init(&q->hctx_table);
+
 	blk_mq_realloc_hw_ctxs(set, q);
 	if (!q->nr_hw_queues)
 		goto err_hctxs;
@@ -4060,9 +4061,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	q->tag_set = set;
 
 	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
-	if (set->nr_maps > HCTX_TYPE_POLL &&
-	    set->map[HCTX_TYPE_POLL].nr_queues)
-		blk_queue_flag_set(QUEUE_FLAG_POLL, q);
+	blk_mq_update_poll_flag(q);
 
 	INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work);
 	INIT_LIST_HEAD(&q->requeue_list);
@@ -4081,7 +4080,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	return 0;
 
 err_hctxs:
-	kfree(q->queue_hw_ctx);
+	xa_destroy(&q->hctx_table);
 	q->nr_hw_queues = 0;
 	blk_mq_sysfs_deinit(q);
 err_poll:
@@ -4369,7 +4368,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 {
 	struct blk_mq_tag_set *set = q->tag_set;
 	struct blk_mq_hw_ctx *hctx;
-	int i, ret;
+	int ret;
+	unsigned long i;
 
 	if (!set)
 		return -EINVAL;
@@ -4528,6 +4528,7 @@ fallback:
 	blk_mq_update_queue_map(set);
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
+		blk_mq_update_poll_flag(q);
 		if (q->nr_hw_queues != set->nr_hw_queues) {
 			int i = prev_nr_hw_queues;
 
@@ -4744,7 +4745,7 @@ void blk_mq_cancel_work_sync(struct request_queue *q)
 {
 	if (queue_is_mq(q)) {
 		struct blk_mq_hw_ctx *hctx;
-		int i;
+		unsigned long i;
 
 		cancel_delayed_work_sync(&q->requeue_work);
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 948791ea2a3e..2615bd58bad3 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -83,7 +83,7 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *
 							  enum hctx_type type,
 							  unsigned int cpu)
 {
-	return q->queue_hw_ctx[q->tag_set->map[type].mq_map[cpu]];
+	return xa_load(&q->hctx_table, q->tag_set->map[type].mq_map[cpu]);
 }
 
 static inline enum hctx_type blk_mq_get_hctx_type(unsigned int flags)
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index 3cfbc8668cba..68267007da1c 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -177,20 +177,20 @@ static inline void rq_qos_requeue(struct request_queue *q, struct request *rq)
 		__rq_qos_requeue(q->rq_qos, rq);
 }
 
-static inline void rq_qos_done_bio(struct request_queue *q, struct bio *bio)
+static inline void rq_qos_done_bio(struct bio *bio)
 {
-	if (q->rq_qos)
-		__rq_qos_done_bio(q->rq_qos, bio);
+	if (bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) ||
+			     bio_flagged(bio, BIO_QOS_MERGED))) {
+		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+		if (q->rq_qos)
+			__rq_qos_done_bio(q->rq_qos, bio);
+	}
 }
 
 static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
 {
-	/*
-	 * BIO_TRACKED lets controllers know that a bio went through the
-	 * normal rq_qos path.
-	 */
 	if (q->rq_qos) {
-		bio_set_flag(bio, BIO_TRACKED);
+		bio_set_flag(bio, BIO_QOS_THROTTLED);
 		__rq_qos_throttle(q->rq_qos, bio);
 	}
 }
@@ -205,8 +205,10 @@ static inline void rq_qos_track(struct request_queue *q, struct request *rq,
 static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
 				struct bio *bio)
 {
-	if (q->rq_qos)
+	if (q->rq_qos) {
+		bio_set_flag(bio, BIO_QOS_MERGED);
 		__rq_qos_merge(q->rq_qos, rq, bio);
+	}
 }
 
 static inline void rq_qos_queue_depth_changed(struct request_queue *q)
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 9f32882ceb2f..85c4ba006671 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -10,7 +10,6 @@
 #include <linux/backing-dev.h>
 #include <linux/blktrace_api.h>
 #include <linux/blk-mq.h>
-#include <linux/blk-cgroup.h>
 #include <linux/debugfs.h>
 
 #include "blk.h"
@@ -18,6 +17,7 @@
 #include "blk-mq-debugfs.h"
 #include "blk-mq-sched.h"
 #include "blk-wbt.h"
+#include "blk-cgroup.h"
 #include "blk-throttle.h"
 
 struct queue_sysfs_entry {
@@ -739,27 +739,6 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head)
 	kmem_cache_free(blk_get_queue_kmem_cache(blk_queue_has_srcu(q)), q);
 }
 
-/* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */
-static void blk_exit_queue(struct request_queue *q)
-{
-	/*
-	 * Since the I/O scheduler exit code may access cgroup information,
-	 * perform I/O scheduler exit before disassociating from the block
-	 * cgroup controller.
-	 */
-	if (q->elevator) {
-		ioc_clear_queue(q);
-		elevator_exit(q);
-	}
-
-	/*
-	 * Remove all references to @q from the block cgroup controller before
-	 * restoring @q->queue_lock to avoid that restoring this pointer causes
-	 * e.g. blkcg_print_blkgs() to crash.
-	 */
-	blkcg_exit_queue(q);
-}
-
 /**
  * blk_release_queue - releases all allocated resources of the request_queue
  * @kobj: pointer to a kobject, whose container is a request_queue
@@ -787,12 +766,12 @@ static void blk_release_queue(struct kobject *kobj)
 
 	might_sleep();
 
+	percpu_ref_exit(&q->q_usage_counter);
+
 	if (q->poll_stat)
 		blk_stat_remove_callback(q, q->poll_cb);
 	blk_stat_free_callback(q->poll_cb);
 
-	blk_exit_queue(q);
-
 	blk_free_queue_stats(q->stats);
 	kfree(q->poll_stat);
 
@@ -880,6 +859,10 @@ int blk_register_queue(struct gendisk *disk)
 			goto put_dev;
 	}
 
+	ret = blk_crypto_sysfs_register(q);
+	if (ret)
+		goto put_dev;
+
 	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
 	wbt_enable_default(q);
 	blk_throtl_register_queue(q);
@@ -910,6 +893,7 @@ unlock:
 	return ret;
 
 put_dev:
+	elv_unregister_queue(q);
 	disk_unregister_independent_access_ranges(disk);
 	mutex_unlock(&q->sysfs_lock);
 	mutex_unlock(&q->sysfs_dir_lock);
@@ -954,16 +938,18 @@ void blk_unregister_queue(struct gendisk *disk)
 	 */
 	if (queue_is_mq(q))
 		blk_mq_unregister_dev(disk_to_dev(disk), q);
-
-	kobject_uevent(&q->kobj, KOBJ_REMOVE);
-	kobject_del(&q->kobj);
+	blk_crypto_sysfs_unregister(q);
 	blk_trace_remove_sysfs(disk_to_dev(disk));
 
 	mutex_lock(&q->sysfs_lock);
-	if (q->elevator)
-		elv_unregister_queue(q);
+	elv_unregister_queue(q);
 	disk_unregister_independent_access_ranges(disk);
 	mutex_unlock(&q->sysfs_lock);
+
+	/* Now that we've deleted all child objects, we can delete the queue. */
+	kobject_uevent(&q->kobj, KOBJ_REMOVE);
+	kobject_del(&q->kobj);
+
 	mutex_unlock(&q->sysfs_dir_lock);
 
 	kobject_put(&disk_to_dev(disk)->kobj);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 7c462c006b26..469c483719be 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -10,7 +10,6 @@
 #include <linux/blkdev.h>
 #include <linux/bio.h>
 #include <linux/blktrace_api.h>
-#include <linux/blk-cgroup.h>
 #include "blk.h"
 #include "blk-cgroup-rwstat.h"
 #include "blk-stat.h"
@@ -42,11 +41,6 @@
 /* A workqueue to queue throttle related work */
 static struct workqueue_struct *kthrotld_workqueue;
 
-enum tg_state_flags {
-	THROTL_TG_PENDING	= 1 << 0,	/* on parent's pending tree */
-	THROTL_TG_WAS_EMPTY	= 1 << 1,	/* bio_lists[] became non-empty */
-};
-
 #define rb_entry_tg(node)	rb_entry((node), struct throtl_grp, rb_node)
 
 /* We measure latency for request size from <= 4k to >= 1M */
@@ -426,12 +420,24 @@ static void tg_update_has_rules(struct throtl_grp *tg)
 	struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq);
 	struct throtl_data *td = tg->td;
 	int rw;
+	int has_iops_limit = 0;
+
+	for (rw = READ; rw <= WRITE; rw++) {
+		unsigned int iops_limit = tg_iops_limit(tg, rw);
 
-	for (rw = READ; rw <= WRITE; rw++)
 		tg->has_rules[rw] = (parent_tg && parent_tg->has_rules[rw]) ||
 			(td->limit_valid[td->limit_index] &&
 			 (tg_bps_limit(tg, rw) != U64_MAX ||
-			  tg_iops_limit(tg, rw) != UINT_MAX));
+			  iops_limit != UINT_MAX));
+
+		if (iops_limit != UINT_MAX)
+			has_iops_limit = 1;
+	}
+
+	if (has_iops_limit)
+		tg->flags |= THROTL_TG_HAS_IOPS_LIMIT;
+	else
+		tg->flags &= ~THROTL_TG_HAS_IOPS_LIMIT;
 }
 
 static void throtl_pd_online(struct blkg_policy_data *pd)
@@ -634,8 +640,6 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg,
 	tg->bytes_disp[rw] = 0;
 	tg->io_disp[rw] = 0;
 
-	atomic_set(&tg->io_split_cnt[rw], 0);
-
 	/*
 	 * Previous slice has expired. We must have trimmed it after last
 	 * bio dispatch. That means since start of last slice, we never used
@@ -659,8 +663,6 @@ static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
 	tg->slice_start[rw] = jiffies;
 	tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
 
-	atomic_set(&tg->io_split_cnt[rw], 0);
-
 	throtl_log(&tg->service_queue,
 		   "[%c] new slice start=%lu end=%lu jiffies=%lu",
 		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
@@ -808,7 +810,8 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
 	unsigned int bio_size = throtl_bio_data_size(bio);
 
-	if (bps_limit == U64_MAX) {
+	/* no need to throttle if this bio's bytes have been accounted */
+	if (bps_limit == U64_MAX || bio_flagged(bio, BIO_THROTTLED)) {
 		if (wait)
 			*wait = 0;
 		return true;
@@ -871,7 +874,8 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 	       bio != throtl_peek_queued(&tg->service_queue.queued[rw]));
 
 	/* If tg->bps = -1, then BW is unlimited */
-	if (bps_limit == U64_MAX && iops_limit == UINT_MAX) {
+	if ((bps_limit == U64_MAX && iops_limit == UINT_MAX) ||
+	    tg->flags & THROTL_TG_CANCELING) {
 		if (wait)
 			*wait = 0;
 		return true;
@@ -893,9 +897,6 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 				jiffies + tg->td->throtl_slice);
 	}
 
-	if (iops_limit != UINT_MAX)
-		tg->io_disp[rw] += atomic_xchg(&tg->io_split_cnt[rw], 0);
-
 	if (tg_with_in_bps_limit(tg, bio, bps_limit, &bps_wait) &&
 	    tg_with_in_iops_limit(tg, bio, iops_limit, &iops_wait)) {
 		if (wait)
@@ -920,9 +921,12 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 	unsigned int bio_size = throtl_bio_data_size(bio);
 
 	/* Charge the bio to the group */
-	tg->bytes_disp[rw] += bio_size;
+	if (!bio_flagged(bio, BIO_THROTTLED)) {
+		tg->bytes_disp[rw] += bio_size;
+		tg->last_bytes_disp[rw] += bio_size;
+	}
+
 	tg->io_disp[rw]++;
-	tg->last_bytes_disp[rw] += bio_size;
 	tg->last_io_disp[rw]++;
 
 	/*
@@ -1134,12 +1138,22 @@ static void throtl_pending_timer_fn(struct timer_list *t)
 	struct throtl_service_queue *sq = from_timer(sq, t, pending_timer);
 	struct throtl_grp *tg = sq_to_tg(sq);
 	struct throtl_data *td = sq_to_td(sq);
-	struct request_queue *q = td->queue;
 	struct throtl_service_queue *parent_sq;
+	struct request_queue *q;
 	bool dispatched;
 	int ret;
 
+	/* throtl_data may be gone, so figure out request queue by blkg */
+	if (tg)
+		q = tg->pd.blkg->q;
+	else
+		q = td->queue;
+
 	spin_lock_irq(&q->queue_lock);
+
+	if (!q->root_blkg)
+		goto out_unlock;
+
 	if (throtl_can_upgrade(td, NULL))
 		throtl_upgrade_state(td);
 
@@ -1219,7 +1233,7 @@ static void blk_throtl_dispatch_work_fn(struct work_struct *work)
 	if (!bio_list_empty(&bio_list_on_stack)) {
 		blk_start_plug(&plug);
 		while ((bio = bio_list_pop(&bio_list_on_stack)))
-			submit_bio_noacct(bio);
+			submit_bio_noacct_nocheck(bio);
 		blk_finish_plug(&plug);
 	}
 }
@@ -1763,6 +1777,39 @@ static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg)
 	return false;
 }
 
+void blk_throtl_cancel_bios(struct request_queue *q)
+{
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+
+	spin_lock_irq(&q->queue_lock);
+	/*
+	 * queue_lock is held, rcu lock is not needed here technically.
+	 * However, rcu lock is still held to emphasize that following
+	 * path need RCU protection and to prevent warning from lockdep.
+	 */
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+		struct throtl_service_queue *sq = &tg->service_queue;
+
+		/*
+		 * Set the flag to make sure throtl_pending_timer_fn() won't
+		 * stop until all throttled bios are dispatched.
+		 */
+		blkg_to_tg(blkg)->flags |= THROTL_TG_CANCELING;
+		/*
+		 * Update disptime after setting the above flag to make sure
+		 * throtl_select_dispatch() won't exit without dispatching.
+		 */
+		tg_update_disptime(tg);
+
+		throtl_schedule_pending_timer(sq, jiffies + 1);
+	}
+	rcu_read_unlock();
+	spin_unlock_irq(&q->queue_lock);
+}
+
 static bool throtl_can_upgrade(struct throtl_data *td,
 	struct throtl_grp *this_tg)
 {
@@ -1917,14 +1964,12 @@ static void throtl_downgrade_check(struct throtl_grp *tg)
 	}
 
 	if (tg->iops[READ][LIMIT_LOW]) {
-		tg->last_io_disp[READ] += atomic_xchg(&tg->last_io_split_cnt[READ], 0);
 		iops = tg->last_io_disp[READ] * HZ / elapsed_time;
 		if (iops >= tg->iops[READ][LIMIT_LOW])
 			tg->last_low_overflow_time[READ] = now;
 	}
 
 	if (tg->iops[WRITE][LIMIT_LOW]) {
-		tg->last_io_disp[WRITE] += atomic_xchg(&tg->last_io_split_cnt[WRITE], 0);
 		iops = tg->last_io_disp[WRITE] * HZ / elapsed_time;
 		if (iops >= tg->iops[WRITE][LIMIT_LOW])
 			tg->last_low_overflow_time[WRITE] = now;
@@ -2043,25 +2088,6 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td)
 }
 #endif
 
-void blk_throtl_charge_bio_split(struct bio *bio)
-{
-	struct blkcg_gq *blkg = bio->bi_blkg;
-	struct throtl_grp *parent = blkg_to_tg(blkg);
-	struct throtl_service_queue *parent_sq;
-	bool rw = bio_data_dir(bio);
-
-	do {
-		if (!parent->has_rules[rw])
-			break;
-
-		atomic_inc(&parent->io_split_cnt[rw]);
-		atomic_inc(&parent->last_io_split_cnt[rw]);
-
-		parent_sq = parent->service_queue.parent_sq;
-		parent = sq_to_tg(parent_sq);
-	} while (parent);
-}
-
 bool __blk_throtl_bio(struct bio *bio)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
diff --git a/block/blk-throttle.h b/block/blk-throttle.h
index 175f03abd9e4..c1b602996127 100644
--- a/block/blk-throttle.h
+++ b/block/blk-throttle.h
@@ -52,6 +52,13 @@ struct throtl_service_queue {
 	struct timer_list	pending_timer;	/* fires on first_pending_disptime */
 };
 
+enum tg_state_flags {
+	THROTL_TG_PENDING	= 1 << 0,	/* on parent's pending tree */
+	THROTL_TG_WAS_EMPTY	= 1 << 1,	/* bio_lists[] became non-empty */
+	THROTL_TG_HAS_IOPS_LIMIT = 1 << 2,	/* tg has iops limit */
+	THROTL_TG_CANCELING	= 1 << 3,	/* starts to cancel bio */
+};
+
 enum {
 	LIMIT_LOW,
 	LIMIT_MAX,
@@ -132,9 +139,6 @@ struct throtl_grp {
 	unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
 	unsigned long bio_cnt_reset_time;
 
-	atomic_t io_split_cnt[2];
-	atomic_t last_io_split_cnt[2];
-
 	struct blkg_rwstat stat_bytes;
 	struct blkg_rwstat stat_ios;
 };
@@ -158,20 +162,23 @@ static inline struct throtl_grp *blkg_to_tg(struct blkcg_gq *blkg)
 static inline int blk_throtl_init(struct request_queue *q) { return 0; }
 static inline void blk_throtl_exit(struct request_queue *q) { }
 static inline void blk_throtl_register_queue(struct request_queue *q) { }
-static inline void blk_throtl_charge_bio_split(struct bio *bio) { }
 static inline bool blk_throtl_bio(struct bio *bio) { return false; }
+static inline void blk_throtl_cancel_bios(struct request_queue *q) { }
 #else /* CONFIG_BLK_DEV_THROTTLING */
 int blk_throtl_init(struct request_queue *q);
 void blk_throtl_exit(struct request_queue *q);
 void blk_throtl_register_queue(struct request_queue *q);
-void blk_throtl_charge_bio_split(struct bio *bio);
 bool __blk_throtl_bio(struct bio *bio);
+void blk_throtl_cancel_bios(struct request_queue *q);
 static inline bool blk_throtl_bio(struct bio *bio)
 {
 	struct throtl_grp *tg = blkg_to_tg(bio->bi_blkg);
 
-	if (bio_flagged(bio, BIO_THROTTLED))
+	/* no need to throttle bps any more if the bio has been throttled */
+	if (bio_flagged(bio, BIO_THROTTLED) &&
+	    !(tg->flags & THROTL_TG_HAS_IOPS_LIMIT))
 		return false;
+
 	if (!tg->has_rules[bio_data_dir(bio)])
 		return false;
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 774ecc598bee..602bef54c813 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -215,9 +215,8 @@ static int blkdev_zone_reset_all_emulated(struct block_device *bdev,
 			continue;
 		}
 
-		bio = blk_next_bio(bio, 0, gfp_mask);
-		bio_set_dev(bio, bdev);
-		bio->bi_opf = REQ_OP_ZONE_RESET | REQ_SYNC;
+		bio = blk_next_bio(bio, bdev, 0, REQ_OP_ZONE_RESET | REQ_SYNC,
+				   gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
@@ -239,10 +238,7 @@ static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
 {
 	struct bio bio;
 
-	bio_init(&bio, NULL, 0);
-	bio_set_dev(&bio, bdev);
-	bio.bi_opf = REQ_OP_ZONE_RESET_ALL | REQ_SYNC;
-
+	bio_init(&bio, bdev, NULL, 0, REQ_OP_ZONE_RESET_ALL | REQ_SYNC);
 	return submit_bio_wait(&bio);
 }
 
@@ -306,9 +302,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 	}
 
 	while (sector < end_sector) {
-		bio = blk_next_bio(bio, 0, gfp_mask);
-		bio_set_dev(bio, bdev);
-		bio->bi_opf = op | REQ_SYNC;
+		bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
diff --git a/block/blk.h b/block/blk.h
index 8bd43b3ad33d..6f21859c7f0f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -46,7 +46,7 @@ void blk_freeze_queue(struct request_queue *q);
 void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic);
 void blk_queue_start_drain(struct request_queue *q);
 int __bio_queue_enter(struct request_queue *q, struct bio *bio);
-bool submit_bio_checks(struct bio *bio);
+void submit_bio_noacct_nocheck(struct bio *bio);
 
 static inline bool blk_try_enter_queue(struct request_queue *q, bool pm)
 {
@@ -325,7 +325,7 @@ int blk_dev_init(void);
  */
 static inline bool blk_do_io_stat(struct request *rq)
 {
-	return (rq->rq_flags & RQF_IO_STAT) && rq->q->disk;
+	return (rq->rq_flags & RQF_IO_STAT) && !blk_rq_is_passthrough(rq);
 }
 
 void update_io_ticks(struct block_device *part, unsigned long now, bool end);
@@ -406,8 +406,6 @@ extern int blk_iolatency_init(struct request_queue *q);
 static inline int blk_iolatency_init(struct request_queue *q) { return 0; }
 #endif
 
-struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp);
-
 #ifdef CONFIG_BLK_DEV_ZONED
 void blk_queue_free_zone_bitmaps(struct request_queue *q);
 void blk_queue_clear_zone_settings(struct request_queue *q);
@@ -426,6 +424,7 @@ int bdev_add_partition(struct gendisk *disk, int partno, sector_t start,
 int bdev_del_partition(struct gendisk *disk, int partno);
 int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start,
 		sector_t length);
+void blk_drop_partitions(struct gendisk *disk);
 
 int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
@@ -445,6 +444,9 @@ int disk_alloc_events(struct gendisk *disk);
 void disk_add_events(struct gendisk *disk);
 void disk_del_events(struct gendisk *disk);
 void disk_release_events(struct gendisk *disk);
+void disk_block_events(struct gendisk *disk);
+void disk_unblock_events(struct gendisk *disk);
+void disk_flush_events(struct gendisk *disk, unsigned int mask);
 extern struct device_attribute dev_attr_events;
 extern struct device_attribute dev_attr_events_async;
 extern struct device_attribute dev_attr_events_poll_msecs;
diff --git a/block/bounce.c b/block/bounce.c
index 7af1a72835b9..3d50d19cde72 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -14,7 +14,6 @@
 #include <linux/pagemap.h>
 #include <linux/mempool.h>
 #include <linux/blkdev.h>
-#include <linux/blk-cgroup.h>
 #include <linux/backing-dev.h>
 #include <linux/init.h>
 #include <linux/hash.h>
@@ -24,6 +23,7 @@
 
 #include <trace/events/block.h>
 #include "blk.h"
+#include "blk-cgroup.h"
 
 #define POOL_SIZE	64
 #define ISA_POOL_SIZE	16
@@ -162,15 +162,12 @@ static struct bio *bounce_clone_bio(struct bio *bio_src)
 	 *    that does not own the bio - reason being drivers don't use it for
 	 *    iterating over the biovec anymore, so expecting it to be kept up
 	 *    to date (i.e. for clones that share the parent biovec) is just
-	 *    asking for trouble and would force extra work on
-	 *    __bio_clone_fast() anyways.
+	 *    asking for trouble and would force extra work.
 	 */
-	bio = bio_alloc_bioset(GFP_NOIO, bio_segments(bio_src),
-			       &bounce_bio_set);
-	bio->bi_bdev		= bio_src->bi_bdev;
+	bio = bio_alloc_bioset(bio_src->bi_bdev, bio_segments(bio_src),
+			       bio_src->bi_opf, GFP_NOIO, &bounce_bio_set);
 	if (bio_flagged(bio_src, BIO_REMAPPED))
 		bio_set_flag(bio, BIO_REMAPPED);
-	bio->bi_opf		= bio_src->bi_opf;
 	bio->bi_ioprio		= bio_src->bi_ioprio;
 	bio->bi_write_hint	= bio_src->bi_write_hint;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
diff --git a/block/disk-events.c b/block/disk-events.c
index 8d5496e7592a..aee25a7e1ab7 100644
--- a/block/disk-events.c
+++ b/block/disk-events.c
@@ -4,7 +4,7 @@
  */
 #include <linux/export.h>
 #include <linux/moduleparam.h>
-#include <linux/genhd.h>
+#include <linux/blkdev.h>
 #include "blk.h"
 
 struct disk_events {
diff --git a/block/elevator.c b/block/elevator.c
index 482df2a350fc..c319765892bb 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -35,7 +35,6 @@
 #include <linux/hash.h>
 #include <linux/uaccess.h>
 #include <linux/pm_runtime.h>
-#include <linux/blk-cgroup.h>
 
 #include <trace/events/block.h>
 
@@ -44,6 +43,7 @@
 #include "blk-mq-sched.h"
 #include "blk-pm.h"
 #include "blk-wbt.h"
+#include "blk-cgroup.h"
 
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);
@@ -192,6 +192,9 @@ void elevator_exit(struct request_queue *q)
 {
 	struct elevator_queue *e = q->elevator;
 
+	ioc_clear_queue(q);
+	blk_mq_sched_free_rqs(q);
+
 	mutex_lock(&e->sysfs_lock);
 	blk_mq_exit_sched(q, e);
 	mutex_unlock(&e->sysfs_lock);
@@ -516,9 +519,11 @@ int elv_register_queue(struct request_queue *q, bool uevent)
 
 void elv_unregister_queue(struct request_queue *q)
 {
+	struct elevator_queue *e = q->elevator;
+
 	lockdep_assert_held(&q->sysfs_lock);
 
-	if (q) {
+	if (e && e->registered) {
 		struct elevator_queue *e = q->elevator;
 
 		kobject_uevent(&e->kobj, KOBJ_REMOVE);
@@ -591,11 +596,7 @@ int elevator_switch_mq(struct request_queue *q,
 	lockdep_assert_held(&q->sysfs_lock);
 
 	if (q->elevator) {
-		if (q->elevator->registered)
-			elv_unregister_queue(q);
-
-		ioc_clear_queue(q);
-		blk_mq_sched_free_rqs(q);
+		elv_unregister_queue(q);
 		elevator_exit(q);
 	}
 
@@ -606,7 +607,6 @@ int elevator_switch_mq(struct request_queue *q,
 	if (new_e) {
 		ret = elv_register_queue(q, true);
 		if (ret) {
-			blk_mq_sched_free_rqs(q);
 			elevator_exit(q);
 			goto out;
 		}
diff --git a/block/fops.c b/block/fops.c
index a18e7fbd97b8..7ccc4ff109ce 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -75,8 +75,13 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 			return -ENOMEM;
 	}
 
-	bio_init(&bio, vecs, nr_pages);
-	bio_set_dev(&bio, bdev);
+	if (iov_iter_rw(iter) == READ) {
+		bio_init(&bio, bdev, vecs, nr_pages, REQ_OP_READ);
+		if (iter_is_iovec(iter))
+			should_dirty = true;
+	} else {
+		bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb));
+	}
 	bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
 	bio.bi_write_hint = iocb->ki_hint;
 	bio.bi_private = current;
@@ -88,14 +93,9 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 		goto out;
 	ret = bio.bi_iter.bi_size;
 
-	if (iov_iter_rw(iter) == READ) {
-		bio.bi_opf = REQ_OP_READ;
-		if (iter_is_iovec(iter))
-			should_dirty = true;
-	} else {
-		bio.bi_opf = dio_bio_write_op(iocb);
+	if (iov_iter_rw(iter) == WRITE)
 		task_io_account_write(ret);
-	}
+
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		bio.bi_opf |= REQ_NOWAIT;
 	if (iocb->ki_flags & IOCB_HIPRI)
@@ -190,6 +190,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	struct blkdev_dio *dio;
 	struct bio *bio;
 	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
+	unsigned int opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
 	loff_t pos = iocb->ki_pos;
 	int ret = 0;
 
@@ -197,7 +198,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	    (bdev_logical_block_size(bdev) - 1))
 		return -EINVAL;
 
-	bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
+	bio = bio_alloc_kiocb(iocb, bdev, nr_pages, opf, &blkdev_dio_pool);
 
 	dio = container_of(bio, struct blkdev_dio, bio);
 	atomic_set(&dio->ref, 1);
@@ -223,7 +224,6 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	blk_start_plug(&plug);
 
 	for (;;) {
-		bio_set_dev(bio, bdev);
 		bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
 		bio->bi_write_hint = iocb->ki_hint;
 		bio->bi_private = dio;
@@ -238,11 +238,9 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		}
 
 		if (is_read) {
-			bio->bi_opf = REQ_OP_READ;
 			if (dio->flags & DIO_SHOULD_DIRTY)
 				bio_set_pages_dirty(bio);
 		} else {
-			bio->bi_opf = dio_bio_write_op(iocb);
 			task_io_account_write(bio->bi_iter.bi_size);
 		}
 		if (iocb->ki_flags & IOCB_NOWAIT)
@@ -258,7 +256,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		}
 		atomic_inc(&dio->ref);
 		submit_bio(bio);
-		bio = bio_alloc(GFP_KERNEL, nr_pages);
+		bio = bio_alloc(bdev, nr_pages, opf, GFP_KERNEL);
 	}
 
 	blk_finish_plug(&plug);
@@ -313,6 +311,8 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 					unsigned int nr_pages)
 {
 	struct block_device *bdev = iocb->ki_filp->private_data;
+	bool is_read = iov_iter_rw(iter) == READ;
+	unsigned int opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
 	struct blkdev_dio *dio;
 	struct bio *bio;
 	loff_t pos = iocb->ki_pos;
@@ -322,11 +322,10 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	    (bdev_logical_block_size(bdev) - 1))
 		return -EINVAL;
 
-	bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
+	bio = bio_alloc_kiocb(iocb, bdev, nr_pages, opf, &blkdev_dio_pool);
 	dio = container_of(bio, struct blkdev_dio, bio);
 	dio->flags = 0;
 	dio->iocb = iocb;
-	bio_set_dev(bio, bdev);
 	bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
 	bio->bi_write_hint = iocb->ki_hint;
 	bio->bi_end_io = blkdev_bio_end_io_async;
@@ -349,14 +348,12 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	}
 	dio->size = bio->bi_iter.bi_size;
 
-	if (iov_iter_rw(iter) == READ) {
-		bio->bi_opf = REQ_OP_READ;
+	if (is_read) {
 		if (iter_is_iovec(iter)) {
 			dio->flags |= DIO_SHOULD_DIRTY;
 			bio_set_pages_dirty(bio);
 		}
 	} else {
-		bio->bi_opf = dio_bio_write_op(iocb);
 		task_io_account_write(bio->bi_iter.bi_size);
 	}
 
diff --git a/block/genhd.c b/block/genhd.c
index 9eca1f7d35c9..37eb41ee4086 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -8,7 +8,6 @@
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/fs.h>
-#include <linux/genhd.h>
 #include <linux/kdev_t.h>
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
@@ -26,10 +25,12 @@
 #include <linux/pm_runtime.h>
 #include <linux/badblocks.h>
 #include <linux/part_stat.h>
+#include "blk-throttle.h"
 
 #include "blk.h"
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
+#include "blk-cgroup.h"
 
 static struct kobject *block_depr;
 
@@ -185,7 +186,9 @@ static struct blk_major_name {
 	struct blk_major_name *next;
 	int major;
 	char name[16];
+#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
 	void (*probe)(dev_t devt);
+#endif
 } *major_names[BLKDEV_MAJOR_HASH_SIZE];
 static DEFINE_MUTEX(major_names_lock);
 static DEFINE_SPINLOCK(major_names_spinlock);
@@ -275,7 +278,9 @@ int __register_blkdev(unsigned int major, const char *name,
 	}
 
 	p->major = major;
+#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
 	p->probe = probe;
+#endif
 	strlcpy(p->name, name, sizeof(p->name));
 	p->next = NULL;
 	index = major_to_index(major);
@@ -523,6 +528,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 
 	disk_update_readahead(disk);
 	disk_add_events(disk);
+	set_bit(GD_ADDED, &disk->state);
 	return 0;
 
 out_unregister_bdi:
@@ -636,7 +642,8 @@ void del_gendisk(struct gendisk *disk)
 
 	blk_mq_freeze_queue_wait(q);
 
-	rq_qos_exit(q);
+	blk_throtl_cancel_bios(disk->queue);
+
 	blk_sync_queue(q);
 	blk_flush_integrity();
 	/*
@@ -693,6 +700,7 @@ static ssize_t disk_badblocks_store(struct device *dev,
 	return badblocks_store(disk->bb, page, len, 0);
 }
 
+#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
 void blk_request_module(dev_t devt)
 {
 	unsigned int major = MAJOR(devt);
@@ -712,6 +720,7 @@ void blk_request_module(dev_t devt)
 		/* Make old-style 2.4 aliases work */
 		request_module("block-major-%d", MAJOR(devt));
 }
+#endif /* CONFIG_BLOCK_LEGACY_AUTOLOAD */
 
 /*
  * print a full list of all partitions - intended for places where the root
@@ -927,12 +936,17 @@ ssize_t part_stat_show(struct device *dev,
 	struct disk_stats stat;
 	unsigned int inflight;
 
-	part_stat_read_all(bdev, &stat);
 	if (queue_is_mq(q))
 		inflight = blk_mq_in_flight(q, bdev);
 	else
 		inflight = part_in_flight(bdev);
 
+	if (inflight) {
+		part_stat_lock();
+		update_io_ticks(bdev, jiffies, true);
+		part_stat_unlock();
+	}
+	part_stat_read_all(bdev, &stat);
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
 		"%8lu %8lu %8llu %8u "
@@ -1100,6 +1114,31 @@ static const struct attribute_group *disk_attr_groups[] = {
 	NULL
 };
 
+static void disk_release_mq(struct request_queue *q)
+{
+	blk_mq_cancel_work_sync(q);
+
+	/*
+	 * There can't be any non non-passthrough bios in flight here, but
+	 * requests stay around longer, including passthrough ones so we
+	 * still need to freeze the queue here.
+	 */
+	blk_mq_freeze_queue(q);
+
+	/*
+	 * Since the I/O scheduler exit code may access cgroup information,
+	 * perform I/O scheduler exit before disassociating from the block
+	 * cgroup controller.
+	 */
+	if (q->elevator) {
+		mutex_lock(&q->sysfs_lock);
+		elevator_exit(q);
+		mutex_unlock(&q->sysfs_lock);
+	}
+	rq_qos_exit(q);
+	__blk_mq_unfreeze_queue(q, true);
+}
+
 /**
  * disk_release - releases all allocated resources of the gendisk
  * @dev: the device representing this disk
@@ -1121,13 +1160,21 @@ static void disk_release(struct device *dev)
 	might_sleep();
 	WARN_ON_ONCE(disk_live(disk));
 
-	blk_mq_cancel_work_sync(disk->queue);
+	if (queue_is_mq(disk->queue))
+		disk_release_mq(disk->queue);
+
+	blkcg_exit_queue(disk->queue);
 
 	disk_release_events(disk);
 	kfree(disk->random);
 	xa_destroy(&disk->part_tbl);
+
 	disk->queue->disk = NULL;
 	blk_put_queue(disk->queue);
+
+	if (test_bit(GD_ADDED, &disk->state) && disk->fops->free_disk)
+		disk->fops->free_disk(disk);
+
 	iput(disk->part0->bd_inode);	/* frees the disk */
 }
 
@@ -1188,12 +1235,17 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 	xa_for_each(&gp->part_tbl, idx, hd) {
 		if (bdev_is_partition(hd) && !bdev_nr_sectors(hd))
 			continue;
-		part_stat_read_all(hd, &stat);
 		if (queue_is_mq(gp->queue))
 			inflight = blk_mq_in_flight(gp->queue, hd);
 		else
 			inflight = part_in_flight(hd);
 
+		if (inflight) {
+			part_stat_lock();
+			update_io_ticks(hd, jiffies, true);
+			part_stat_unlock();
+		}
+		part_stat_read_all(hd, &stat);
 		seq_printf(seqf, "%4d %7d %pg "
 			   "%lu %lu %lu %u "
 			   "%lu %lu %lu %u "
@@ -1322,6 +1374,9 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 	if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL))
 		goto out_destroy_part_tbl;
 
+	if (blkcg_init_queue(q))
+		goto out_erase_part0;
+
 	rand_initialize_disk(disk);
 	disk_to_dev(disk)->class = &block_class;
 	disk_to_dev(disk)->type = &disk_type;
@@ -1334,6 +1389,8 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 #endif
 	return disk;
 
+out_erase_part0:
+	xa_erase(&disk->part_tbl, 0);
 out_destroy_part_tbl:
 	xa_destroy(&disk->part_tbl);
 	disk->part0->bd_disk = NULL;
diff --git a/block/holder.c b/block/holder.c
index 27cddce1b446..8d750281a1cd 100644
--- a/block/holder.c
+++ b/block/holder.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#include <linux/genhd.h>
+#include <linux/blkdev.h>
 #include <linux/slab.h>
 
 struct bd_holder_disk {
diff --git a/block/partitions/check.h b/block/partitions/check.h
index d5b28e309d64..4ffa2359b1a3 100644
--- a/block/partitions/check.h
+++ b/block/partitions/check.h
@@ -1,7 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/pagemap.h>
 #include <linux/blkdev.h>
-#include <linux/genhd.h>
 #include "../blk.h"
 
 /*
diff --git a/block/partitions/core.c b/block/partitions/core.c
index c2a1635922b1..2ef8dfa1e5c8 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -8,7 +8,6 @@
 #include <linux/major.h>
 #include <linux/slab.h>
 #include <linux/ctype.h>
-#include <linux/genhd.h>
 #include <linux/vmalloc.h>
 #include <linux/blktrace_api.h>
 #include <linux/raid/detect.h>
diff --git a/block/partitions/efi.h b/block/partitions/efi.h
index 8cc2b88d0aa8..84b9f36b9e47 100644
--- a/block/partitions/efi.h
+++ b/block/partitions/efi.h
@@ -13,7 +13,6 @@
 
 #include <linux/types.h>
 #include <linux/fs.h>
-#include <linux/genhd.h>
 #include <linux/kernel.h>
 #include <linux/major.h>
 #include <linux/string.h>
diff --git a/block/partitions/ldm.h b/block/partitions/ldm.h
index 8693704dcf5e..0a747a0c782d 100644
--- a/block/partitions/ldm.h
+++ b/block/partitions/ldm.h
@@ -14,7 +14,6 @@
 
 #include <linux/types.h>
 #include <linux/list.h>
-#include <linux/genhd.h>
 #include <linux/fs.h>
 #include <asm/unaligned.h>
 #include <asm/byteorder.h>
diff --git a/block/sed-opal.c b/block/sed-opal.c
index daafadbb88ca..9700197000f2 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -13,7 +13,7 @@
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
-#include <linux/genhd.h>
+#include <linux/blkdev.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <uapi/linux/sed-opal.h>