diff --git a/block/bio.c b/block/bio.c
index 8bfdea58159b..9ef6cf3addb3 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -599,6 +599,8 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	bio->bi_disk = bio_src->bi_disk;
 	bio->bi_partno = bio_src->bi_partno;
 	bio_set_flag(bio, BIO_CLONED);
+	if (bio_flagged(bio_src, BIO_THROTTLED))
+		bio_set_flag(bio, BIO_THROTTLED);
 	bio->bi_opf = bio_src->bi_opf;
 	bio->bi_write_hint = bio_src->bi_write_hint;
 	bio->bi_iter = bio_src->bi_iter;
diff --git a/block/blk-map.c b/block/blk-map.c
index b21f8e86f120..d3a94719f03f 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -12,22 +12,29 @@
 #include "blk.h"
 
 /*
- * Append a bio to a passthrough request.  Only works can be merged into
- * the request based on the driver constraints.
+ * Append a bio to a passthrough request.  Only works if the bio can be merged
+ * into the request based on the driver constraints.
  */
-int blk_rq_append_bio(struct request *rq, struct bio *bio)
+int blk_rq_append_bio(struct request *rq, struct bio **bio)
 {
-	blk_queue_bounce(rq->q, &bio);
+	struct bio *orig_bio = *bio;
+
+	blk_queue_bounce(rq->q, bio);
 
 	if (!rq->bio) {
-		blk_rq_bio_prep(rq->q, rq, bio);
+		blk_rq_bio_prep(rq->q, rq, *bio);
 	} else {
-		if (!ll_back_merge_fn(rq->q, rq, bio))
+		if (!ll_back_merge_fn(rq->q, rq, *bio)) {
+			if (orig_bio != *bio) {
+				bio_put(*bio);
+				*bio = orig_bio;
+			}
 			return -EINVAL;
+		}
 
-		rq->biotail->bi_next = bio;
-		rq->biotail = bio;
-		rq->__data_len += bio->bi_iter.bi_size;
+		rq->biotail->bi_next = *bio;
+		rq->biotail = *bio;
+		rq->__data_len += (*bio)->bi_iter.bi_size;
 	}
 
 	return 0;
@@ -73,14 +80,12 @@ static int __blk_rq_map_user_iov(struct request *rq,
 	 * We link the bounce buffer in and could have to traverse it
 	 * later so we have to get a ref to prevent it from being freed
 	 */
-	ret = blk_rq_append_bio(rq, bio);
-	bio_get(bio);
+	ret = blk_rq_append_bio(rq, &bio);
 	if (ret) {
-		bio_endio(bio);
 		__blk_rq_unmap_user(orig_bio);
-		bio_put(bio);
 		return ret;
 	}
+	bio_get(bio);
 
 	return 0;
 }
@@ -213,7 +218,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	int reading = rq_data_dir(rq) == READ;
 	unsigned long addr = (unsigned long) kbuf;
 	int do_copy = 0;
-	struct bio *bio;
+	struct bio *bio, *orig_bio;
 	int ret;
 
 	if (len > (queue_max_hw_sectors(q) << 9))
@@ -236,10 +241,11 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (do_copy)
 		rq->rq_flags |= RQF_COPY_USER;
 
-	ret = blk_rq_append_bio(rq, bio);
+	orig_bio = bio;
+	ret = blk_rq_append_bio(rq, &bio);
 	if (unlikely(ret)) {
 		/* request is too big */
-		bio_put(bio);
+		bio_put(orig_bio);
 		return ret;
 	}
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 825bc29767e6..d19f416d6101 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2226,13 +2226,7 @@ again:
 out_unlock:
 	spin_unlock_irq(q->queue_lock);
 out:
-	/*
-	 * As multiple blk-throtls may stack in the same issue path, we
-	 * don't want bios to leave with the flag set.  Clear the flag if
-	 * being issued.
-	 */
-	if (!throttled)
-		bio_clear_flag(bio, BIO_THROTTLED);
+	bio_set_flag(bio, BIO_THROTTLED);
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 	if (throttled || !td->track_bio_latency)
diff --git a/block/bounce.c b/block/bounce.c
index fceb1a96480b..1d05c422c932 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -200,6 +200,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	unsigned i = 0;
 	bool bounce = false;
 	int sectors = 0;
+	bool passthrough = bio_is_passthrough(*bio_orig);
 
 	bio_for_each_segment(from, *bio_orig, iter) {
 		if (i++ < BIO_MAX_PAGES)
@@ -210,13 +211,14 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	if (!bounce)
 		return;
 
-	if (sectors < bio_sectors(*bio_orig)) {
+	if (!passthrough && sectors < bio_sectors(*bio_orig)) {
 		bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split);
 		bio_chain(bio, *bio_orig);
 		generic_make_request(*bio_orig);
 		*bio_orig = bio;
 	}
-	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, bounce_bio_set);
+	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL :
+			bounce_bio_set);
 
 	bio_for_each_segment_all(to, bio, i) {
 		struct page *page = to->bv_page;
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index b4df317c2916..f95c60774ce8 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -100,9 +100,13 @@ struct kyber_hctx_data {
 	unsigned int cur_domain;
 	unsigned int batching;
 	wait_queue_entry_t domain_wait[KYBER_NUM_DOMAINS];
+	struct sbq_wait_state *domain_ws[KYBER_NUM_DOMAINS];
 	atomic_t wait_index[KYBER_NUM_DOMAINS];
 };
 
+static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
+			     void *key);
+
 static int rq_sched_domain(const struct request *rq)
 {
 	unsigned int op = rq->cmd_flags;
@@ -385,6 +389,9 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 
 	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
 		INIT_LIST_HEAD(&khd->rqs[i]);
+		init_waitqueue_func_entry(&khd->domain_wait[i],
+					  kyber_domain_wake);
+		khd->domain_wait[i].private = hctx;
 		INIT_LIST_HEAD(&khd->domain_wait[i].entry);
 		atomic_set(&khd->wait_index[i], 0);
 	}
@@ -524,35 +531,39 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd,
 	int nr;
 
 	nr = __sbitmap_queue_get(domain_tokens);
-	if (nr >= 0)
-		return nr;
 
 	/*
 	 * If we failed to get a domain token, make sure the hardware queue is
 	 * run when one becomes available. Note that this is serialized on
 	 * khd->lock, but we still need to be careful about the waker.
 	 */
-	if (list_empty_careful(&wait->entry)) {
-		init_waitqueue_func_entry(wait, kyber_domain_wake);
-		wait->private = hctx;
+	if (nr < 0 && list_empty_careful(&wait->entry)) {
 		ws = sbq_wait_ptr(domain_tokens,
 				  &khd->wait_index[sched_domain]);
+		khd->domain_ws[sched_domain] = ws;
 		add_wait_queue(&ws->wait, wait);
 
 		/*
 		 * Try again in case a token was freed before we got on the wait
-		 * queue. The waker may have already removed the entry from the
-		 * wait queue, but list_del_init() is okay with that.
+		 * queue.
 		 */
 		nr = __sbitmap_queue_get(domain_tokens);
-		if (nr >= 0) {
-			unsigned long flags;
-
-			spin_lock_irqsave(&ws->wait.lock, flags);
-			list_del_init(&wait->entry);
-			spin_unlock_irqrestore(&ws->wait.lock, flags);
-		}
 	}
+
+	/*
+	 * If we got a token while we were on the wait queue, remove ourselves
+	 * from the wait queue to ensure that all wake ups make forward
+	 * progress. It's possible that the waker already deleted the entry
+	 * between the !list_empty_careful() check and us grabbing the lock, but
+	 * list_del_init() is okay with that.
+	 */
+	if (nr >= 0 && !list_empty_careful(&wait->entry)) {
+		ws = khd->domain_ws[sched_domain];
+		spin_lock_irq(&ws->wait.lock);
+		list_del_init(&wait->entry);
+		spin_unlock_irq(&ws->wait.lock);
+	}
+
 	return nr;
 }
 
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index ccb9975a97fa..ad0477ae820f 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -35,13 +35,13 @@ static inline u64 mb_per_tick(int mbps)
 struct nullb_cmd {
 	struct list_head list;
 	struct llist_node ll_list;
-	call_single_data_t csd;
+	struct __call_single_data csd;
 	struct request *rq;
 	struct bio *bio;
 	unsigned int tag;
+	blk_status_t error;
 	struct nullb_queue *nq;
 	struct hrtimer timer;
-	blk_status_t error;
 };
 
 struct nullb_queue {
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f837d666cbd4..1e46e60b8f10 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1287,7 +1287,7 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl,
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
 
-	queue->limits.discard_alignment = size;
+	queue->limits.discard_alignment = 0;
 	queue->limits.discard_granularity = size;
 
 	blk_queue_max_discard_sectors(queue, UINT_MAX);
@@ -1705,7 +1705,8 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
 		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
 		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
 	}
-	if (ctrl->quirks & NVME_QUIRK_STRIPE_SIZE)
+	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
+	    is_power_of_2(ctrl->max_hw_sectors))
 		blk_queue_chunk_sectors(q, ctrl->max_hw_sectors);
 	blk_queue_virt_boundary(q, ctrl->page_size - 1);
 	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
@@ -2869,7 +2870,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
 	nvme_set_queue_limits(ctrl, ns->queue);
-	nvme_setup_streams_ns(ctrl, ns);
 
 	id = nvme_identify_ns(ctrl, nsid);
 	if (!id)
@@ -2880,6 +2880,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	if (nvme_init_ns_head(ns, nsid, id, &new))
 		goto out_free_id;
+	nvme_setup_streams_ns(ctrl, ns);
 	
 #ifdef CONFIG_NVME_MULTIPATH
 	/*
@@ -2965,8 +2966,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		return;
 
 	if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
-		if (blk_get_integrity(ns->disk))
-			blk_integrity_unregister(ns->disk);
 		nvme_mpath_remove_disk_links(ns);
 		sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_id_attr_group);
@@ -2974,6 +2973,8 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 			nvme_nvm_unregister_sysfs(ns);
 		del_gendisk(ns->disk);
 		blk_cleanup_queue(ns->queue);
+		if (blk_get_integrity(ns->disk))
+			blk_integrity_unregister(ns->disk);
 	}
 
 	mutex_lock(&ns->ctrl->subsys->lock);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 0a8af4daef89..794e66e4aa20 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -3221,7 +3221,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 		/* initiate nvme ctrl ref counting teardown */
 		nvme_uninit_ctrl(&ctrl->ctrl);
-		nvme_put_ctrl(&ctrl->ctrl);
 
 		/* Remove core ctrl ref. */
 		nvme_put_ctrl(&ctrl->ctrl);
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index a4f28b7e4c65..e18877177f1b 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -1576,7 +1576,9 @@ static struct request *_make_request(struct request_queue *q, bool has_write,
 		return req;
 
 	for_each_bio(bio) {
-		ret = blk_rq_append_bio(req, bio);
+		struct bio *bounce_bio = bio;
+
+		ret = blk_rq_append_bio(req, &bounce_bio);
 		if (ret)
 			return ERR_PTR(ret);
 	}
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 7c69b4a9694d..0d99b242e82e 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -920,7 +920,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 					" %d i: %d bio: %p, allocating another"
 					" bio\n", bio->bi_vcnt, i, bio);
 
-				rc = blk_rq_append_bio(req, bio);
+				rc = blk_rq_append_bio(req, &bio);
 				if (rc) {
 					pr_err("pSCSI: failed to append bio\n");
 					goto fail;
@@ -938,7 +938,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	}
 
 	if (bio) {
-		rc = blk_rq_append_bio(req, bio);
+		rc = blk_rq_append_bio(req, &bio);
 		if (rc) {
 			pr_err("pSCSI: failed to append bio\n");
 			goto fail;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 82f0c8fd7be8..23d29b39f71e 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -492,6 +492,8 @@ extern unsigned int bvec_nr_vecs(unsigned short idx);
 
 #define bio_set_dev(bio, bdev) 			\
 do {						\
+	if ((bio)->bi_disk != (bdev)->bd_disk)	\
+		bio_clear_flag(bio, BIO_THROTTLED);\
 	(bio)->bi_disk = (bdev)->bd_disk;	\
 	(bio)->bi_partno = (bdev)->bd_partno;	\
 } while (0)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index a1e628e032da..9e7d8bd776d2 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -50,8 +50,6 @@ struct blk_issue_stat {
 struct bio {
 	struct bio		*bi_next;	/* request queue link */
 	struct gendisk		*bi_disk;
-	u8			bi_partno;
-	blk_status_t		bi_status;
 	unsigned int		bi_opf;		/* bottom bits req flags,
 						 * top bits REQ_OP. Use
 						 * accessors.
@@ -59,8 +57,8 @@ struct bio {
 	unsigned short		bi_flags;	/* status, etc and bvec pool number */
 	unsigned short		bi_ioprio;
 	unsigned short		bi_write_hint;
-
-	struct bvec_iter	bi_iter;
+	blk_status_t		bi_status;
+	u8			bi_partno;
 
 	/* Number of segments in this BIO after
 	 * physical address coalescing is performed.
@@ -74,8 +72,9 @@ struct bio {
 	unsigned int		bi_seg_front_size;
 	unsigned int		bi_seg_back_size;
 
-	atomic_t		__bi_remaining;
+	struct bvec_iter	bi_iter;
 
+	atomic_t		__bi_remaining;
 	bio_end_io_t		*bi_end_io;
 
 	void			*bi_private;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8089ca17db9a..0ce8a372d506 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -135,7 +135,7 @@ typedef __u32 __bitwise req_flags_t;
 struct request {
 	struct list_head queuelist;
 	union {
-		call_single_data_t csd;
+		struct __call_single_data csd;
 		u64 fifo_time;
 	};
 
@@ -241,14 +241,24 @@ struct request {
 	struct request *next_rq;
 };
 
+static inline bool blk_op_is_scsi(unsigned int op)
+{
+	return op == REQ_OP_SCSI_IN || op == REQ_OP_SCSI_OUT;
+}
+
+static inline bool blk_op_is_private(unsigned int op)
+{
+	return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
+}
+
 static inline bool blk_rq_is_scsi(struct request *rq)
 {
-	return req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT;
+	return blk_op_is_scsi(req_op(rq));
 }
 
 static inline bool blk_rq_is_private(struct request *rq)
 {
-	return req_op(rq) == REQ_OP_DRV_IN || req_op(rq) == REQ_OP_DRV_OUT;
+	return blk_op_is_private(req_op(rq));
 }
 
 static inline bool blk_rq_is_passthrough(struct request *rq)
@@ -256,6 +266,13 @@ static inline bool blk_rq_is_passthrough(struct request *rq)
 	return blk_rq_is_scsi(rq) || blk_rq_is_private(rq);
 }
 
+static inline bool bio_is_passthrough(struct bio *bio)
+{
+	unsigned op = bio_op(bio);
+
+	return blk_op_is_scsi(op) || blk_op_is_private(op);
+}
+
 static inline unsigned short req_get_ioprio(struct request *req)
 {
 	return req->ioprio;
@@ -948,7 +965,7 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 extern void blk_rq_unprep_clone(struct request *rq);
 extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
-extern int blk_rq_append_bio(struct request *rq, struct bio *bio);
+extern int blk_rq_append_bio(struct request *rq, struct bio **bio);
 extern void blk_delay_queue(struct request_queue *, unsigned long);
 extern void blk_queue_split(struct request_queue *, struct bio **);
 extern void blk_recount_segments(struct request_queue *, struct bio *);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 84b2dc76f140..b5f940ce0143 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -882,13 +882,10 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args)
 	if (IS_ERR(dev))
 		return PTR_ERR(dev);
 
-	if (bdi_debug_register(bdi, dev_name(dev))) {
-		device_destroy(bdi_class, dev->devt);
-		return -ENOMEM;
-	}
 	cgwb_bdi_register(bdi);
 	bdi->dev = dev;
 
+	bdi_debug_register(bdi, dev_name(dev));
 	set_bit(WB_registered, &bdi->wb.state);
 
 	spin_lock_bh(&bdi_lock);