Merge tag 'for-6.10/block-20240511' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - Add a partscan attribute in sysfs, fixing an issue with systemd
   relying on an internal interface that went away.

 - Attempt #2 at making long running discards interruptible. The
   previous attempt went into 6.9, but we ended up mostly reverting it
   as it had issues.

 - Remove old ida_simple API in bcache

 - Support for zoned write plugging, greatly improving the performance
   on zoned devices.

 - Remove the old throttle low interface, which has been experimental
   since 2017 and never made it beyond that and isn't being used.

 - Remove page->index debugging checks in brd, as it hasn't caught
   anything and prepares us for removing in struct page.

 - MD pull request from Song

 - Don't schedule block workers on isolated CPUs

* tag 'for-6.10/block-20240511' of git://git.kernel.dk/linux: (84 commits)
  blk-throttle: delay initialization until configuration
  blk-throttle: remove CONFIG_BLK_DEV_THROTTLING_LOW
  block: fix that util can be greater than 100%
  block: support to account io_ticks precisely
  block: add plug while submitting IO
  bcache: fix variable length array abuse in btree_iter
  bcache: Remove usage of the deprecated ida_simple_xx() API
  md: Revert "md: Fix overflow in is_mddev_idle"
  blk-lib: check for kill signal in ioctl BLKDISCARD
  block: add a bio_await_chain helper
  block: add a blk_alloc_discard_bio helper
  block: add a bio_chain_and_submit helper
  block: move discard checks into the ioctl handler
  block: remove the discard_granularity check in __blkdev_issue_discard
  block/ioctl: prefer different overflow check
  null_blk: Fix the WARNING: modpost: missing MODULE_DESCRIPTION()
  block: fix and simplify blkdevparts= cmdline parsing
  block: refine the EOF check in blkdev_iomap_begin
  block: add a partscan sysfs attribute for disks
  block: add a disk_has_partscan helper
  ...

29 files changed, 1959 insertions, 1641 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 1de4682d48cc..dc12af58dbae 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -100,7 +100,6 @@ config BLK_DEV_WRITE_MOUNTED
 
 config BLK_DEV_ZONED
 	bool "Zoned block device support"
-	select MQ_IOSCHED_DEADLINE
 	help
 	Block layer zoned block device support. This option enables
 	support for ZAC/ZBC/ZNS host-managed and host-aware zoned block
@@ -120,17 +119,6 @@ config BLK_DEV_THROTTLING
 
 	See Documentation/admin-guide/cgroup-v1/blkio-controller.rst for more information.
 
-config BLK_DEV_THROTTLING_LOW
-	bool "Block throttling .low limit interface support (EXPERIMENTAL)"
-	depends on BLK_DEV_THROTTLING
-	help
-	Add .low limit interface for block throttling. The low limit is a best
-	effort limit to prioritize cgroups. Depending on the setting, the limit
-	can be used to protect cgroups in terms of bandwidth/iops and better
-	utilize disk resource.
-
-	Note, this is an experimental interface and could be changed someday.
-
 config BLK_WBT
 	bool "Enable support for block device writeback throttling"
 	help
@@ -198,10 +186,6 @@ config BLK_DEBUG_FS
 	Unless you are building a kernel for a tiny system, you should
 	say Y here.
 
-config BLK_DEBUG_FS_ZONED
-       bool
-       default BLK_DEBUG_FS && BLK_DEV_ZONED
-
 config BLK_SED_OPAL
 	bool "Logic for interfacing with Opal enabled SEDs"
 	depends on KEYS
diff --git a/block/Makefile b/block/Makefile
index 46ada9dc8bbf..168150b9c510 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -33,7 +33,6 @@ obj-$(CONFIG_BLK_MQ_VIRTIO)	+= blk-mq-virtio.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
-obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
 obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
 obj-$(CONFIG_BLK_PM)		+= blk-pm.o
 obj-$(CONFIG_BLK_INLINE_ENCRYPTION)	+= blk-crypto.o blk-crypto-profile.o \
diff --git a/block/bio.c b/block/bio.c
index d24420ed1c4c..53f608028c78 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -345,18 +345,29 @@ 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, blk_opf_t opf, gfp_t gfp)
+/**
+ * bio_chain_and_submit - submit a bio after chaining it to another one
+ * @prev: bio to chain and submit
+ * @new: bio to chain to
+ *
+ * If @prev is non-NULL, chain it to @new and submit it.
+ *
+ * Return: @new.
+ */
+struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new)
 {
-	struct bio *new = bio_alloc(bdev, nr_pages, opf, gfp);
-
-	if (bio) {
-		bio_chain(bio, new);
-		submit_bio(bio);
+	if (prev) {
+		bio_chain(prev, new);
+		submit_bio(prev);
 	}
-
 	return new;
 }
+
+struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
+		unsigned int nr_pages, blk_opf_t opf, gfp_t gfp)
+{
+	return bio_chain_and_submit(bio, bio_alloc(bdev, nr_pages, opf, gfp));
+}
 EXPORT_SYMBOL_GPL(blk_next_bio);
 
 static void bio_alloc_rescue(struct work_struct *work)
@@ -1384,6 +1395,26 @@ int submit_bio_wait(struct bio *bio)
 }
 EXPORT_SYMBOL(submit_bio_wait);
 
+static void bio_wait_end_io(struct bio *bio)
+{
+	complete(bio->bi_private);
+	bio_put(bio);
+}
+
+/*
+ * bio_await_chain - ends @bio and waits for every chained bio to complete
+ */
+void bio_await_chain(struct bio *bio)
+{
+	DECLARE_COMPLETION_ONSTACK_MAP(done,
+			bio->bi_bdev->bd_disk->lockdep_map);
+
+	bio->bi_private = &done;
+	bio->bi_end_io = bio_wait_end_io;
+	bio_endio(bio);
+	blk_wait_io(&done);
+}
+
 void __bio_advance(struct bio *bio, unsigned bytes)
 {
 	if (bio_integrity(bio))
@@ -1576,6 +1607,8 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
+	blk_zone_bio_endio(bio);
+
 	rq_qos_done_bio(bio);
 
 	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
@@ -1596,7 +1629,6 @@ again:
 		goto again;
 	}
 
-	blk_throtl_bio_endio(bio);
 	/* release cgroup info */
 	bio_uninit(bio);
 	if (bio->bi_end_io)
diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c
index 3304e841df7c..a55fb0c53558 100644
--- a/block/blk-cgroup-rwstat.c
+++ b/block/blk-cgroup-rwstat.c
@@ -9,25 +9,19 @@ int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp)
 {
 	int i, ret;
 
-	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
-		ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp);
-		if (ret) {
-			while (--i >= 0)
-				percpu_counter_destroy(&rwstat->cpu_cnt[i]);
-			return ret;
-		}
+	ret = percpu_counter_init_many(rwstat->cpu_cnt, 0, gfp, BLKG_RWSTAT_NR);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
 		atomic64_set(&rwstat->aux_cnt[i], 0);
-	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blkg_rwstat_init);
 
 void blkg_rwstat_exit(struct blkg_rwstat *rwstat)
 {
-	int i;
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		percpu_counter_destroy(&rwstat->cpu_cnt[i]);
+	percpu_counter_destroy_many(rwstat->cpu_cnt, BLKG_RWSTAT_NR);
 }
 EXPORT_SYMBOL_GPL(blkg_rwstat_exit);
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 059467086b13..4b1a35ab0ea4 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -218,8 +218,7 @@ static void blkg_async_bio_workfn(struct work_struct *work)
 
 	/* as long as there are pending bios, @blkg can't go away */
 	spin_lock(&blkg->async_bio_lock);
-	bio_list_merge(&bios, &blkg->async_bios);
-	bio_list_init(&blkg->async_bios);
+	bio_list_merge_init(&bios, &blkg->async_bios);
 	spin_unlock(&blkg->async_bio_lock);
 
 	/* start plug only when bio_list contains at least 2 bios */
@@ -1444,14 +1443,8 @@ int blkcg_init_disk(struct gendisk *disk)
 	if (ret)
 		goto err_destroy_all;
 
-	ret = blk_throtl_init(disk);
-	if (ret)
-		goto err_ioprio_exit;
-
 	return 0;
 
-err_ioprio_exit:
-	blk_ioprio_exit(disk);
 err_destroy_all:
 	blkg_destroy_all(disk);
 	return ret;
diff --git a/block/blk-core.c b/block/blk-core.c
index b795ac177281..01186333c88e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -591,8 +591,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 		return BLK_STS_NOTSUPP;
 
 	/* The bio sector must point to the start of a sequential zone */
-	if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector) ||
-	    !bio_zone_is_seq(bio))
+	if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector))
 		return BLK_STS_IOERR;
 
 	/*
@@ -604,7 +603,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 		return BLK_STS_IOERR;
 
 	/* Make sure the BIO is small enough and will not get split */
-	if (nr_sectors > q->limits.max_zone_append_sectors)
+	if (nr_sectors > queue_max_zone_append_sectors(q))
 		return BLK_STS_IOERR;
 
 	bio->bi_opf |= REQ_NOMERGE;
@@ -649,11 +648,13 @@ static void __submit_bio(struct bio *bio)
 static void __submit_bio_noacct(struct bio *bio)
 {
 	struct bio_list bio_list_on_stack[2];
+	struct blk_plug plug;
 
 	BUG_ON(bio->bi_next);
 
 	bio_list_init(&bio_list_on_stack[0]);
 	current->bio_list = bio_list_on_stack;
+	blk_start_plug(&plug);
 
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
@@ -687,19 +688,23 @@ static void __submit_bio_noacct(struct bio *bio)
 		bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
 	} while ((bio = bio_list_pop(&bio_list_on_stack[0])));
 
+	blk_finish_plug(&plug);
 	current->bio_list = NULL;
 }
 
 static void __submit_bio_noacct_mq(struct bio *bio)
 {
 	struct bio_list bio_list[2] = { };
+	struct blk_plug plug;
 
 	current->bio_list = bio_list;
+	blk_start_plug(&plug);
 
 	do {
 		__submit_bio(bio);
 	} while ((bio = bio_list_pop(&bio_list[0])));
 
+	blk_finish_plug(&plug);
 	current->bio_list = NULL;
 }
 
@@ -910,12 +915,6 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return 0;
 
-	/*
-	 * As the requests that require a zone lock are not plugged in the
-	 * first place, directly accessing the plug instead of using
-	 * blk_mq_plug() should not have any consequences during flushing for
-	 * zoned devices.
-	 */
 	blk_flush_plug(current->plug, false);
 
 	/*
@@ -987,10 +986,11 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end)
 	unsigned long stamp;
 again:
 	stamp = READ_ONCE(part->bd_stamp);
-	if (unlikely(time_after(now, stamp))) {
-		if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now)))
-			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
-	}
+	if (unlikely(time_after(now, stamp)) &&
+	    likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) &&
+	    (end || part_in_flight(part)))
+		__part_stat_add(part, io_ticks, now - stamp);
+
 	if (part->bd_partno) {
 		part = bdev_whole(part);
 		goto again;
diff --git a/block/blk-flush.c b/block/blk-flush.c
index b0f314f4bc14..c17cf8ed8113 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -130,6 +130,8 @@ static void blk_flush_restore_request(struct request *rq)
 	 * original @rq->bio.  Restore it.
 	 */
 	rq->bio = rq->biotail;
+	if (rq->bio)
+		rq->__sector = rq->bio->bi_iter.bi_sector;
 
 	/* make @rq a normal request */
 	rq->rq_flags &= ~RQF_FLUSH_SEQ;
diff --git a/block/blk-lib.c b/block/blk-lib.c
index a6954eafb8c8..442da9dad042 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -35,51 +35,39 @@ static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
 	return round_down(UINT_MAX, discard_granularity) >> SECTOR_SHIFT;
 }
 
-int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
+struct bio *blk_alloc_discard_bio(struct block_device *bdev,
+		sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask)
 {
-	struct bio *bio = *biop;
-	sector_t bs_mask;
-
-	if (bdev_read_only(bdev))
-		return -EPERM;
-	if (!bdev_max_discard_sectors(bdev))
-		return -EOPNOTSUPP;
-
-	/* In case the discard granularity isn't set by buggy device driver */
-	if (WARN_ON_ONCE(!bdev_discard_granularity(bdev))) {
-		pr_err_ratelimited("%pg: Error: discard_granularity is 0.\n",
-				   bdev);
-		return -EOPNOTSUPP;
-	}
-
-	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
-	if ((sector | nr_sects) & bs_mask)
-		return -EINVAL;
+	sector_t bio_sects = min(*nr_sects, bio_discard_limit(bdev, *sector));
+	struct bio *bio;
 
-	if (!nr_sects)
-		return -EINVAL;
+	if (!bio_sects)
+		return NULL;
 
-	while (nr_sects) {
-		sector_t req_sects =
-			min(nr_sects, bio_discard_limit(bdev, sector));
+	bio = bio_alloc(bdev, 0, REQ_OP_DISCARD, gfp_mask);
+	if (!bio)
+		return NULL;
+	bio->bi_iter.bi_sector = *sector;
+	bio->bi_iter.bi_size = bio_sects << SECTOR_SHIFT;
+	*sector += bio_sects;
+	*nr_sects -= bio_sects;
+	/*
+	 * We can loop for a long time in here if someone does full device
+	 * discards (like mkfs).  Be nice and allow us to schedule out to avoid
+	 * softlocking if preempt is disabled.
+	 */
+	cond_resched();
+	return bio;
+}
 
-		bio = blk_next_bio(bio, bdev, 0, REQ_OP_DISCARD, gfp_mask);
-		bio->bi_iter.bi_sector = sector;
-		bio->bi_iter.bi_size = req_sects << 9;
-		sector += req_sects;
-		nr_sects -= req_sects;
-
-		/*
-		 * We can loop for a long time in here, if someone does
-		 * full device discards (like mkfs). Be nice and allow
-		 * us to schedule out to avoid softlocking if preempt
-		 * is disabled.
-		 */
-		cond_resched();
-	}
+int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
+{
+	struct bio *bio;
 
-	*biop = bio;
+	while ((bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects,
+			gfp_mask)))
+		*biop = bio_chain_and_submit(*biop, bio);
 	return 0;
 }
 EXPORT_SYMBOL(__blkdev_issue_discard);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 4e3483a16b75..8534c35e0497 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -377,6 +377,7 @@ struct bio *__bio_split_to_limits(struct bio *bio,
 		blkcg_bio_issue_init(split);
 		bio_chain(split, bio);
 		trace_block_split(split, bio->bi_iter.bi_sector);
+		WARN_ON_ONCE(bio_zone_write_plugging(bio));
 		submit_bio_noacct(bio);
 		return split;
 	}
@@ -779,6 +780,8 @@ static void blk_account_io_merge_request(struct request *req)
 	if (blk_do_io_stat(req)) {
 		part_stat_lock();
 		part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
+		part_stat_local_dec(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }
@@ -972,13 +975,7 @@ static void blk_account_io_merge_bio(struct request *req)
 	part_stat_unlock();
 }
 
-enum bio_merge_status {
-	BIO_MERGE_OK,
-	BIO_MERGE_NONE,
-	BIO_MERGE_FAILED,
-};
-
-static enum bio_merge_status bio_attempt_back_merge(struct request *req,
+enum bio_merge_status bio_attempt_back_merge(struct request *req,
 		struct bio *bio, unsigned int nr_segs)
 {
 	const blk_opf_t ff = bio_failfast(bio);
@@ -994,6 +991,9 @@ static enum bio_merge_status bio_attempt_back_merge(struct request *req,
 
 	blk_update_mixed_merge(req, bio, false);
 
+	if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING)
+		blk_zone_write_plug_bio_merged(bio);
+
 	req->biotail->bi_next = bio;
 	req->biotail = bio;
 	req->__data_len += bio->bi_iter.bi_size;
@@ -1009,6 +1009,14 @@ static enum bio_merge_status bio_attempt_front_merge(struct request *req,
 {
 	const blk_opf_t ff = bio_failfast(bio);
 
+	/*
+	 * A front merge for writes to sequential zones of a zoned block device
+	 * can happen only if the user submitted writes out of order. Do not
+	 * merge such write to let it fail.
+	 */
+	if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING)
+		return BIO_MERGE_FAILED;
+
 	if (!ll_front_merge_fn(req, bio, nr_segs))
 		return BIO_MERGE_FAILED;
 
@@ -1107,10 +1115,9 @@ static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs)
 {
-	struct blk_plug *plug;
+	struct blk_plug *plug = current->plug;
 	struct request *rq;
 
-	plug = blk_mq_plug(bio);
 	if (!plug || rq_list_empty(plug->mq_list))
 		return false;
 
diff --git a/block/blk-mq-debugfs-zoned.c b/block/blk-mq-debugfs-zoned.c
deleted file mode 100644
index a77b099c34b7..000000000000
--- a/block/blk-mq-debugfs-zoned.c
+++ /dev/null
@@ -1,22 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2017 Western Digital Corporation or its affiliates.
- */
-
-#include <linux/blkdev.h>
-#include "blk-mq-debugfs.h"
-
-int queue_zone_wlock_show(void *data, struct seq_file *m)
-{
-	struct request_queue *q = data;
-	unsigned int i;
-
-	if (!q->disk->seq_zones_wlock)
-		return 0;
-
-	for (i = 0; i < q->disk->nr_zones; i++)
-		if (test_bit(i, q->disk->seq_zones_wlock))
-			seq_printf(m, "%u\n", i);
-
-	return 0;
-}
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 94668e72ab09..770c0c2b72fa 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -160,7 +160,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
 	{ "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops },
 	{ "pm_only", 0600, queue_pm_only_show, NULL },
 	{ "state", 0600, queue_state_show, queue_state_write },
-	{ "zone_wlock", 0400, queue_zone_wlock_show, NULL },
+	{ "zone_wplugs", 0400, queue_zone_wplugs_show, NULL },
 	{ },
 };
 
@@ -256,7 +256,6 @@ static const char *const rqf_name[] = {
 	RQF_NAME(HASHED),
 	RQF_NAME(STATS),
 	RQF_NAME(SPECIAL_PAYLOAD),
-	RQF_NAME(ZONE_WRITE_LOCKED),
 	RQF_NAME(TIMED_OUT),
 	RQF_NAME(RESV),
 };
diff --git a/block/blk-mq-debugfs.h b/block/blk-mq-debugfs.h
index 9c7d4b6117d4..c80e453e3014 100644
--- a/block/blk-mq-debugfs.h
+++ b/block/blk-mq-debugfs.h
@@ -83,10 +83,10 @@ static inline void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos)
 }
 #endif
 
-#ifdef CONFIG_BLK_DEBUG_FS_ZONED
-int queue_zone_wlock_show(void *data, struct seq_file *m);
+#if defined(CONFIG_BLK_DEV_ZONED) && defined(CONFIG_BLK_DEBUG_FS)
+int queue_zone_wplugs_show(void *data, struct seq_file *m);
 #else
-static inline int queue_zone_wlock_show(void *data, struct seq_file *m)
+static inline int queue_zone_wplugs_show(void *data, struct seq_file *m)
 {
 	return 0;
 }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 32afb87efbd0..8e01e4b32e10 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -28,6 +28,7 @@
 #include <linux/prefetch.h>
 #include <linux/blk-crypto.h>
 #include <linux/part_stat.h>
+#include <linux/sched/isolation.h>
 
 #include <trace/events/block.h>
 
@@ -690,6 +691,8 @@ static void blk_mq_finish_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
+	blk_zone_finish_request(rq);
+
 	if (rq->rq_flags & RQF_USE_SCHED) {
 		q->elevator->type->ops.finish_request(rq);
 		/*
@@ -761,31 +764,6 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 }
 EXPORT_SYMBOL(blk_dump_rq_flags);
 
-static void req_bio_endio(struct request *rq, struct bio *bio,
-			  unsigned int nbytes, blk_status_t error)
-{
-	if (unlikely(error)) {
-		bio->bi_status = error;
-	} else if (req_op(rq) == REQ_OP_ZONE_APPEND) {
-		/*
-		 * Partial zone append completions cannot be supported as the
-		 * BIO fragments may end up not being written sequentially.
-		 */
-		if (bio->bi_iter.bi_size != nbytes)
-			bio->bi_status = BLK_STS_IOERR;
-		else
-			bio->bi_iter.bi_sector = rq->__sector;
-	}
-
-	bio_advance(bio, nbytes);
-
-	if (unlikely(rq->rq_flags & RQF_QUIET))
-		bio_set_flag(bio, BIO_QUIET);
-	/* don't actually finish bio if it's part of flush sequence */
-	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
-		bio_endio(bio);
-}
-
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (req->part && blk_do_io_stat(req)) {
@@ -845,8 +823,7 @@ static void blk_complete_request(struct request *req)
 		/* Completion has already been traced */
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
 
-		if (req_op(req) == REQ_OP_ZONE_APPEND)
-			bio->bi_iter.bi_sector = req->__sector;
+		blk_zone_update_request_bio(req, bio);
 
 		if (!is_flush)
 			bio_endio(bio);
@@ -889,6 +866,8 @@ static void blk_complete_request(struct request *req)
 bool blk_update_request(struct request *req, blk_status_t error,
 		unsigned int nr_bytes)
 {
+	bool is_flush = req->rq_flags & RQF_FLUSH_SEQ;
+	bool quiet = req->rq_flags & RQF_QUIET;
 	int total_bytes;
 
 	trace_block_rq_complete(req, error, nr_bytes);
@@ -909,9 +888,8 @@ bool blk_update_request(struct request *req, blk_status_t error,
 	if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req))
 		__blk_crypto_rq_put_keyslot(req);
 
-	if (unlikely(error && !blk_rq_is_passthrough(req) &&
-		     !(req->rq_flags & RQF_QUIET)) &&
-		     !test_bit(GD_DEAD, &req->q->disk->state)) {
+	if (unlikely(error && !blk_rq_is_passthrough(req) && !quiet) &&
+	    !test_bit(GD_DEAD, &req->q->disk->state)) {
 		blk_print_req_error(req, error);
 		trace_block_rq_error(req, error, nr_bytes);
 	}
@@ -923,12 +901,33 @@ bool blk_update_request(struct request *req, blk_status_t error,
 		struct bio *bio = req->bio;
 		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
 
-		if (bio_bytes == bio->bi_iter.bi_size)
+		if (unlikely(error))
+			bio->bi_status = error;
+
+		if (bio_bytes == bio->bi_iter.bi_size) {
 			req->bio = bio->bi_next;
+		} else if (bio_is_zone_append(bio) && error == BLK_STS_OK) {
+			/*
+			 * Partial zone append completions cannot be supported
+			 * as the BIO fragments may end up not being written
+			 * sequentially.
+			 */
+			bio->bi_status = BLK_STS_IOERR;
+		}
 
 		/* Completion has already been traced */
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
-		req_bio_endio(req, bio, bio_bytes, error);
+		if (unlikely(quiet))
+			bio_set_flag(bio, BIO_QUIET);
+
+		bio_advance(bio, bio_bytes);
+
+		/* Don't actually finish bio if it's part of flush sequence */
+		if (!bio->bi_iter.bi_size) {
+			blk_zone_update_request_bio(req, bio);
+			if (!is_flush)
+				bio_endio(bio);
+		}
 
 		total_bytes += bio_bytes;
 		nr_bytes -= bio_bytes;
@@ -997,6 +996,8 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 		update_io_ticks(req->part, jiffies, true);
 		part_stat_inc(req->part, ios[sgrp]);
 		part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
+		part_stat_local_dec(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }
@@ -1019,6 +1020,8 @@ static inline void blk_account_io_start(struct request *req)
 
 		part_stat_lock();
 		update_io_ticks(req->part, jiffies, false);
+		part_stat_local_inc(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }
@@ -1330,11 +1333,6 @@ void blk_execute_rq_nowait(struct request *rq, bool at_head)
 
 	blk_account_io_start(rq);
 
-	/*
-	 * As plugging can be enabled for passthrough requests on a zoned
-	 * device, directly accessing the plug instead of using blk_mq_plug()
-	 * should not have any consequences.
-	 */
 	if (current->plug && !at_head) {
 		blk_add_rq_to_plug(current->plug, rq);
 		return;
@@ -1921,19 +1919,6 @@ static void blk_mq_handle_dev_resource(struct request *rq,
 	__blk_mq_requeue_request(rq);
 }
 
-static void blk_mq_handle_zone_resource(struct request *rq,
-					struct list_head *zone_list)
-{
-	/*
-	 * If we end up here it is because we cannot dispatch a request to a
-	 * specific zone due to LLD level zone-write locking or other zone
-	 * related resource not being available. In this case, set the request
-	 * aside in zone_list for retrying it later.
-	 */
-	list_add(&rq->queuelist, zone_list);
-	__blk_mq_requeue_request(rq);
-}
-
 enum prep_dispatch {
 	PREP_DISPATCH_OK,
 	PREP_DISPATCH_NO_TAG,
@@ -2019,7 +2004,6 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 	struct request *rq;
 	int queued;
 	blk_status_t ret = BLK_STS_OK;
-	LIST_HEAD(zone_list);
 	bool needs_resource = false;
 
 	if (list_empty(list))
@@ -2061,23 +2045,11 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 		case BLK_STS_DEV_RESOURCE:
 			blk_mq_handle_dev_resource(rq, list);
 			goto out;
-		case BLK_STS_ZONE_RESOURCE:
-			/*
-			 * Move the request to zone_list and keep going through
-			 * the dispatch list to find more requests the drive can
-			 * accept.
-			 */
-			blk_mq_handle_zone_resource(rq, &zone_list);
-			needs_resource = true;
-			break;
 		default:
 			blk_mq_end_request(rq, ret);
 		}
 	} while (!list_empty(list));
 out:
-	if (!list_empty(&zone_list))
-		list_splice_tail_init(&zone_list, list);
-
 	/* If we didn't flush the entire list, we could have told the driver
 	 * there was more coming, but that turned out to be a lie.
 	 */
@@ -2164,6 +2136,15 @@ static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
 }
 
 /*
+ * ->next_cpu is always calculated from hctx->cpumask, so simply use
+ * it for speeding up the check
+ */
+static bool blk_mq_hctx_empty_cpumask(struct blk_mq_hw_ctx *hctx)
+{
+        return hctx->next_cpu >= nr_cpu_ids;
+}
+
+/*
  * It'd be great if the workqueue API had a way to pass
  * in a mask and had some smarts for more clever placement.
  * For now we just round-robin here, switching for every
@@ -2174,7 +2155,8 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 	bool tried = false;
 	int next_cpu = hctx->next_cpu;
 
-	if (hctx->queue->nr_hw_queues == 1)
+	/* Switch to unbound if no allowable CPUs in this hctx */
+	if (hctx->queue->nr_hw_queues == 1 || blk_mq_hctx_empty_cpumask(hctx))
 		return WORK_CPU_UNBOUND;
 
 	if (--hctx->next_cpu_batch <= 0) {
@@ -2948,22 +2930,37 @@ static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 void blk_mq_submit_bio(struct bio *bio)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	struct blk_plug *plug = blk_mq_plug(bio);
+	struct blk_plug *plug = current->plug;
 	const int is_sync = op_is_sync(bio->bi_opf);
 	struct blk_mq_hw_ctx *hctx;
 	unsigned int nr_segs = 1;
 	struct request *rq;
 	blk_status_t ret;
 
+	/*
+	 * If the plug has a cached request for this queue, try to use it.
+	 */
+	rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf);
+
+	/*
+	 * A BIO that was released from a zone write plug has already been
+	 * through the preparation in this function, already holds a reference
+	 * on the queue usage counter, and is the only write BIO in-flight for
+	 * the target zone. Go straight to preparing a request for it.
+	 */
+	if (bio_zone_write_plugging(bio)) {
+		nr_segs = bio->__bi_nr_segments;
+		if (rq)
+			blk_queue_exit(q);
+		goto new_request;
+	}
+
 	bio = blk_queue_bounce(bio, q);