for-6.10/block-20240511

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAmY/YgsQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpvi0EACwnFRtYioizBH0x7QUHTBcIr0IhACd5gfz
 bm+uwlDUtf6G6lupHdJT9gOVB2z2z1m2Pz//8RuUVWw3Eqw2+rfgG8iJd+yo7IaV
 DpX3WaM4NnBvB7FKOKHlMPvGuf7KgbZ3uPm3x8cbrn/axMmkZ6ljxTixJ3p5t4+s
 xRsef/lVdG71DkXIFgTKATB86yNRJNlRQTbL+sZW22vdXdtfyBbOgR1sBuFfp7Hd
 g/uocZM/z0ahM6JH/5R2IX2ttKXMIBZLA8HRkJdvYqg022cj4js2YyRCPU3N6jQN
 MtN4TpJV5I++8l6SPQOOhaDNrK/6zFtDQpwG0YBiKKj3nQDgVbWWb8ejYTIUv4MP
 SrEto4MVBEqg5N65VwYYhIf45rmueFyJp6z0Vqv6Owur5nuww/YIFknmoMa/WDMd
 V8dIU3zL72FZDbPjIBjxHeqAGz9OgzEVafled7pi0Xbw6wqiB4kZihlMGXlD+WBy
 Yd6xo8PX4i5+d2LLKKPxpW1X0eJlKYJ/4dnYCoFN8LmXSiPJnMx2pYrV+NqMxy4X
 Thr8lxswLQC7j9YBBuIeDl8NB9N5FZZLvaC6I25QKq045M2ckJ+VrounsQb3vGwJ
 72nlxxBZL8wz3sasgX9Pc1Cez9AqYbM+UZahq8ezPY5y3Jh0QfRw/MOk1ZaDNC8V
 CNOHBH0E+Q==
 =HnjE
 -----END PGP SIGNATURE-----

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
  ...

Documentation/ABI/stable/sysfs-block

@@ -101,6 +101,16 @@ Description:
 		devices that support receiving integrity metadata.
 
 
+What:		/sys/block/<disk>/partscan
+Date:		May 2024
+Contact:	Christoph Hellwig <hch@lst.de>
+Description:
+		The /sys/block/<disk>/partscan files reports if partition
+		scanning is enabled for the disk.  It returns "1" if partition
+		scanning is enabled, or "0" if not.  The value type is a 32-bit
+		unsigned integer, but only "0" and "1" are valid values.
+
+
 What:		/sys/block/<disk>/<partition>/alignment_offset
 Date:		April 2009
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
@@ -584,18 +594,6 @@ Description:
 		the data.  If no such restriction exists, this file will contain
 		'0'.  This file is writable for testing purposes.
 
-
-What:		/sys/block/<disk>/queue/throttle_sample_time
-Date:		March 2017
-Contact:	linux-block@vger.kernel.org
-Description:
-		[RW] This is the time window that blk-throttle samples data, in
-		millisecond.  blk-throttle makes decision based on the
-		samplings. Lower time means cgroups have more smooth throughput,
-		but higher CPU overhead. This exists only when
-		CONFIG_BLK_DEV_THROTTLING_LOW is enabled.
-
-
 What:		/sys/block/<disk>/queue/virt_boundary_mask
 Date:		April 2021
 Contact:	linux-block@vger.kernel.org

arch/loongarch/configs/loongson3_defconfig

@@ -76,7 +76,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_BLK_DEV_ZONED=y
 CONFIG_BLK_DEV_THROTTLING=y
-CONFIG_BLK_DEV_THROTTLING_LOW=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
 CONFIG_BLK_CGROUP_FC_APPID=y

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

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 \

block/bio.c

@@ -345,17 +345,28 @@ void bio_chain(struct bio *bio, struct bio *parent)
 }
 EXPORT_SYMBOL(bio_chain);
 
+/**
+ * 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)
+{
+	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)
 {
-	struct bio *new = bio_alloc(bdev, nr_pages, opf, gfp);
+	return bio_chain_and_submit(bio, bio_alloc(bdev, nr_pages, opf, gfp));
-
-	if (bio) {
-		bio_chain(bio, new);
-		submit_bio(bio);
-	}
-
-	return new;
 }
 EXPORT_SYMBOL_GPL(blk_next_bio);
 
@@ -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)

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_many(rwstat->cpu_cnt, 0, gfp, BLKG_RWSTAT_NR);
-		ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp);
+	if (ret)
-		if (ret) {
+		return ret;
-			while (--i >= 0)
+
-				percpu_counter_destroy(&rwstat->cpu_cnt[i]);
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-			return ret;
-		}
 		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;
+	percpu_counter_destroy_many(rwstat->cpu_cnt, BLKG_RWSTAT_NR);
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		percpu_counter_destroy(&rwstat->cpu_cnt[i]);
 }
 EXPORT_SYMBOL_GPL(blkg_rwstat_exit);
 

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_merge_init(&bios, &blkg->async_bios);
-	bio_list_init(&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;

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) ||
+	if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector))
-	    !bio_zone_is_seq(bio))
 		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 (unlikely(time_after(now, stamp)) &&
-		if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now)))
+	    likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) &&
-			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
+	    (end || part_in_flight(part)))
-	}
+		__part_stat_add(part, io_ticks, now - stamp);
+
 	if (part->bd_partno) {
 		part = bdev_whole(part);
 		goto again;

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;

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;
 }
 
+struct bio *blk_alloc_discard_bio(struct block_device *bdev,
+		sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask)
+{
+	sector_t bio_sects = min(*nr_sects, bio_discard_limit(bdev, *sector));
+	struct bio *bio;
+
+	if (!bio_sects)
+		return NULL;
+
+	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;
+}
+
 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;
+	struct bio *bio;
-	sector_t bs_mask;
 
-	if (bdev_read_only(bdev))
+	while ((bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects,
-		return -EPERM;
+			gfp_mask)))
-	if (!bdev_max_discard_sectors(bdev))
+		*biop = bio_chain_and_submit(*biop, bio);
-		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;
-
-	if (!nr_sects)
-		return -EINVAL;
-
-	while (nr_sects) {
-		sector_t req_sects =
-			min(nr_sects, bio_discard_limit(bdev, sector));
-
-		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();
-	}
-
-	*biop = bio;
 	return 0;
 }
 EXPORT_SYMBOL(__blkdev_issue_discard);

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 {
+enum bio_merge_status bio_attempt_back_merge(struct request *req,
-	BIO_MERGE_OK,
-	BIO_MERGE_NONE,
-	BIO_MERGE_FAILED,
-};
-
-static 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;
 

block/blk-mq-debugfs-zoned.c

@@ -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;
-}

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),
 };

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
+#if defined(CONFIG_BLK_DEV_ZONED) && defined(CONFIG_BLK_DEBUG_FS)
-int queue_zone_wlock_show(void *data, struct seq_file *m);
+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;
 }

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)
+		blk_zone_update_request_bio(req, bio);
-			bio->bi_iter.bi_sector = req->__sector;
 
 		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) &&
+	if (unlikely(error && !blk_rq_is_passthrough(req) && !quiet) &&
-		     !(req->rq_flags & RQF_QUIET)) &&
+	    !test_bit(GD_DEAD, &req->q->disk->state)) {
-		     !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.
 	 */
@@ -2163,6 +2135,15 @@ static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
 	return cpu;
 }
 
+/*
+ * ->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.
@@ -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);
 
 	/*
-	 * If the plug has a cached request for this queue, try use it.
-	 *
 	 * The cached request already holds a q_usage_counter reference and we
 	 * don't have to acquire a new one if we use it.
 	 */
-	rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf);
 	if (!rq) {
 		if (unlikely(bio_queue_enter(bio)))
 			return;
@@ -2980,6 +2977,10 @@ void blk_mq_submit_bio(struct bio *bio)
 	if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
 		goto queue_exit;
 
+	if (blk_queue_is_zoned(q) && blk_zone_plug_bio(bio, nr_segs))
+		goto queue_exit;
+
+new_request:
 	if (!rq) {
 		rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
 		if (unlikely(!rq))
@@ -3002,6 +3003,9 @@ void blk_mq_submit_bio(struct bio *bio)
 		return;
 	}
 
+	if (bio_zone_write_plugging(bio))
+		blk_zone_write_plug_init_request(rq);
+
 	if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq))
 		return;
 
@@ -3483,14 +3487,30 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
 	return data.has_rq;
 }
 
-static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu,
+static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
-		struct blk_mq_hw_ctx *hctx)
+		unsigned int this_cpu)
 {
-	if (cpumask_first_and(hctx->cpumask, cpu_online_mask) != cpu)
+	enum hctx_type type = hctx->type;
-		return false;
+	int cpu;
-	if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids)
+
-		return false;
+	/*
-	return true;
+	 * hctx->cpumask has to rule out isolated CPUs, but userspace still
+	 * might submit IOs on these isolated CPUs, so use the queue map to
+	 * check if all CPUs mapped to this hctx are offline
+	 */
+	for_each_online_cpu(cpu) {
+		struct blk_mq_hw_ctx *h = blk_mq_map_queue_type(hctx->queue,
+				type, cpu);
+
+		if (h != hctx)
+			continue;
+
+		/* this hctx has at least one online CPU */
+		if (this_cpu != cpu)
+			return true;
+	}
+
+	return false;
 }
 
 static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
@@ -3498,8 +3518,7 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
 	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
 			struct blk_mq_hw_ctx, cpuhp_online);
 
-	if (!cpumask_test_cpu(cpu, hctx->cpumask) ||
+	if (blk_mq_hctx_has_online_cpu(hctx, cpu))
-	    !blk_mq_last_cpu_in_hctx(cpu, hctx))
 		return 0;
 
 	/*
@@ -3907,6 +3926,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {
+		int cpu;
+
 		/*
 		 * If no software queues are mapped to this hardware queue,
 		 * disable it and free the request entries.
@@ -3933,6 +3954,15 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		 */
 		sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx);
 
+		/*
+		 * Rule out isolated CPUs from hctx->cpumask to avoid
+		 * running block kworker on isolated CPUs
+		 */
+		for_each_cpu(cpu, hctx->cpumask) {
+			if (cpu_is_isolated(cpu))
+				cpumask_clear_cpu(cpu, hctx->cpumask);
+		}
+
 		/*
 		 * Initialize batch roundrobin counts
 		 */

block/blk-mq.h

@@ -365,37 +365,6 @@ static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
 		qmap->mq_map[cpu] = 0;
 }
 
-/*
- * blk_mq_plug() - Get caller context plug
- * @bio : the bio being submitted by the caller context
- *
- * Plugging, by design, may delay the insertion of BIOs into the elevator in
- * order to increase BIO merging opportunities. This however can cause BIO
- * insertion order to change from the order in which submit_bio() is being
- * executed in the case of multiple contexts concurrently issuing BIOs to a
- * device, even if these context are synchronized to tightly control BIO issuing
- * order. While this is not a problem with regular block devices, this ordering
- * change can cause write BIO failures with zoned block devices as these
- * require sequential write patterns to zones. Prevent this from happening by
- * ignoring the plug state of a BIO issuing context if it is for a zoned block
- * device and the BIO to plug is a write operation.
- *
- * Return current->plug if the bio can be plugged and NULL otherwise
- */
-static inline struct blk_plug *blk_mq_plug( struct bio *bio)
-{
-	/* Zoned block device write operation case: do not plug the BIO */
-	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-	    bdev_op_is_zoned_write(bio->bi_bdev, bio_op(bio)))
-		return NULL;
-
-	/*
-	 * For regular block devices or read operations, use the context plug
-	 * which may be NULL if blk_start_plug() was not executed.
-	 */
-	return current->plug;
-}
-
 /* Free all requests on the list */
 static inline void blk_mq_free_requests(struct list_head *list)
 {

block/blk-settings.c

@@ -411,24 +411,32 @@ EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors);
  * blk_queue_max_zone_append_sectors - set max sectors for a single zone append
  * @q:  the request queue for the device
  * @max_zone_append_sectors: maximum number of sectors to write per command
+ *
+ * Sets the maximum number of sectors allowed for zone append commands. If
+ * Specifying 0 for @max_zone_append_sectors indicates that the queue does
+ * not natively support zone append operations and that the block layer must
+ * emulate these operations using regular writes.
  **/
 void blk_queue_max_zone_append_sectors(struct request_queue *q,
 		unsigned int max_zone_append_sectors)
 {
-	unsigned int max_sectors;
+	unsigned int max_sectors = 0;
 
 	if (WARN_ON(!blk_queue_is_zoned(q)))
 		return;
 
-	max_sectors = min(q->limits.max_hw_sectors, max_zone_append_sectors);
+	if (max_zone_append_sectors) {
-	max_sectors = min(q->limits.chunk_sectors, max_sectors);
+		max_sectors = min(q->limits.max_hw_sectors,
+				  max_zone_append_sectors);
+		max_sectors = min(q->limits.chunk_sectors, max_sectors);
 
-	/*
+		/*
-	 * Signal eventual driver bugs resulting in the max_zone_append sectors limit
+		 * Signal eventual driver bugs resulting in the max_zone_append
-	 * being 0 due to a 0 argument, the chunk_sectors limit (zone size) not set,
+		 * sectors limit being 0 due to the chunk_sectors limit (zone
-	 * or the max_hw_sectors limit not set.
+		 * size) not set or the max_hw_sectors limit not set.
-	 */
+		 */
-	WARN_ON(!max_sectors);
+		WARN_ON_ONCE(!max_sectors);
+	}
 
 	q->limits.max_zone_append_sectors = max_sectors;
 }
@@ -755,8 +763,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
 	t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
 					b->max_write_zeroes_sectors);
-	t->max_zone_append_sectors = min(t->max_zone_append_sectors,
+	t->max_zone_append_sectors = min(queue_limits_max_zone_append_sectors(t),
-					b->max_zone_append_sectors);
+					 queue_limits_max_zone_append_sectors(b));
 	t->bounce = max(t->bounce, b->bounce);
 
 	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
@@ -1043,22 +1051,6 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 }
 EXPORT_SYMBOL_GPL(blk_queue_write_cache);
 
-/**
- * blk_queue_required_elevator_features - Set a queue required elevator features
- * @q:		the request queue for the target device
- * @features:	Required elevator features OR'ed together
- *
- * Tell the block layer that for the device controlled through @q, only the
- * only elevators that can be used are those that implement at least the set of
- * features specified by @features.
- */
-void blk_queue_required_elevator_features(struct request_queue *q,
-					  unsigned int features)
-{
-	q->required_elevator_features = features;
-}
-EXPORT_SYMBOL_GPL(blk_queue_required_elevator_features);
-
 /**
  * blk_queue_can_use_dma_map_merging - configure queue for merging segments.
  * @q:		the request queue for the device

block/blk-stat.c

@@ -57,9 +57,6 @@ void blk_stat_add(struct request *rq, u64 now)
 
 	value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0;
 
-	if (req_op(rq) == REQ_OP_READ || req_op(rq) == REQ_OP_WRITE)
-		blk_throtl_stat_add(rq, value);
-
 	rcu_read_lock();
 	cpu = get_cpu();
 	list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {

block/blk-sysfs.c

@@ -224,7 +224,7 @@ static ssize_t queue_zone_write_granularity_show(struct request_queue *q,
 
 static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page)
 {
-	unsigned long long max_sectors = q->limits.max_zone_append_sectors;
+	unsigned long long max_sectors = queue_max_zone_append_sectors(q);
 
 	return sprintf(page, "%llu\n", max_sectors << SECTOR_SHIFT);
 }
@@ -516,10 +516,6 @@ QUEUE_RW_ENTRY(queue_io_timeout, "io_timeout");
 QUEUE_RO_ENTRY(queue_virt_boundary_mask, "virt_boundary_mask");
 QUEUE_RO_ENTRY(queue_dma_alignment, "dma_alignment");
 
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-QUEUE_RW_ENTRY(blk_throtl_sample_time, "throttle_sample_time");
-#endif
-
 /* legacy alias for logical_block_size: */
 static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 	.attr = {.name = "hw_sector_size", .mode = 0444 },
@@ -640,9 +636,6 @@ static struct attribute *queue_attrs[] = {
 	&queue_fua_entry.attr,
 	&queue_dax_entry.attr,
 	&queue_poll_delay_entry.attr,
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	&blk_throtl_sample_time_entry.attr,
-#endif
 	&queue_virt_boundary_mask_entry.attr,
 	&queue_dma_alignment_entry.attr,
 	NULL,
@@ -814,7 +807,6 @@ int blk_register_queue(struct gendisk *disk)
 
 	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
 	wbt_enable_default(disk);
-	blk_throtl_register(disk);
 
 	/* Now everything is ready and send out KOBJ_ADD uevent */
 	kobject_uevent(&disk->queue_kobj, KOBJ_ADD);

block/blk-throttle.h

@@ -58,12 +58,6 @@ enum tg_state_flags {
 	THROTL_TG_CANCELING	= 1 << 2,	/* starts to cancel bio */
 };
 
-enum {
-	LIMIT_LOW,
-	LIMIT_MAX,
-	LIMIT_CNT,
-};
-
 struct throtl_grp {
 	/* must be the first member */
 	struct blkg_policy_data pd;
@@ -102,14 +96,14 @@ struct throtl_grp {
 	bool has_rules_iops[2];
 
 	/* internally used bytes per second rate limits */
-	uint64_t bps[2][LIMIT_CNT];
+	uint64_t bps[2];
 	/* user configured bps limits */
-	uint64_t bps_conf[2][LIMIT_CNT];
+	uint64_t bps_conf[2];
 
 	/* internally used IOPS limits */
-	unsigned int iops[2][LIMIT_CNT];
+	unsigned int iops[2];
 	/* user configured IOPS limits */
-	unsigned int iops_conf[2][LIMIT_CNT];
+	unsigned int iops_conf[2];
 
 	/* Number of bytes dispatched in current slice */
 	uint64_t bytes_disp[2];
@@ -132,22 +126,10 @@ struct throtl_grp {
 
 	unsigned long last_check_time;
 
-	unsigned long latency_target; /* us */
-	unsigned long latency_target_conf; /* us */
 	/* When did we start a new slice */
 	unsigned long slice_start[2];
 	unsigned long slice_end[2];
 
-	unsigned long last_finish_time; /* ns / 1024 */
-	unsigned long checked_last_finish_time; /* ns / 1024 */
-	unsigned long avg_idletime; /* ns / 1024 */
-	unsigned long idletime_threshold; /* us */
-	unsigned long idletime_threshold_conf; /* us */
-
-	unsigned int bio_cnt; /* total bios */
-	unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
-	unsigned long bio_cnt_reset_time;
-
 	struct blkg_rwstat stat_bytes;
 	struct blkg_rwstat stat_ios;
 };
@@ -168,23 +150,33 @@ static inline struct throtl_grp *blkg_to_tg(struct blkcg_gq *blkg)
  * Internal throttling interface
  */
 #ifndef CONFIG_BLK_DEV_THROTTLING
-static inline int blk_throtl_init(struct gendisk *disk) { return 0; }
 static inline void blk_throtl_exit(struct gendisk *disk) { }
-static inline void blk_throtl_register(struct gendisk *disk) { }
 static inline bool blk_throtl_bio(struct bio *bio) { return false; }
 static inline void blk_throtl_cancel_bios(struct gendisk *disk) { }
 #else /* CONFIG_BLK_DEV_THROTTLING */
-int blk_throtl_init(struct gendisk *disk);
 void blk_throtl_exit(struct gendisk *disk);
-void blk_throtl_register(struct gendisk *disk);
 bool __blk_throtl_bio(struct bio *bio);
 void blk_throtl_cancel_bios(struct gendisk *disk);
 
+static inline bool blk_throtl_activated(struct request_queue *q)
+{
+	return q->td != NULL;
+}
+
 static inline bool blk_should_throtl(struct bio *bio)
 {
-	struct throtl_grp *tg = blkg_to_tg(bio->bi_blkg);
+	struct throtl_grp *tg;
 	int rw = bio_data_dir(bio);
 
+	/*
+	 * This is called under bio_queue_enter(), and it's synchronized with
+	 * the activation of blk-throtl, which is protected by
+	 * blk_mq_freeze_queue().
+	 */
+	if (!blk_throtl_activated(bio->bi_bdev->bd_queue))
+		return false;
+
+	tg = blkg_to_tg(bio->bi_blkg);
 	if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) {
 		if (!bio_flagged(bio, BIO_CGROUP_ACCT)) {
 			bio_set_flag(bio, BIO_CGROUP_ACCT);

block/blk.h

@@ -38,6 +38,7 @@ 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);
 void submit_bio_noacct_nocheck(struct bio *bio);
+void bio_await_chain(struct bio *bio);
 
 static inline bool blk_try_enter_queue(struct request_queue *q, bool pm)
 {
@@ -269,6 +270,14 @@ static inline void bio_integrity_free(struct bio *bio)
 unsigned long blk_rq_timeout(unsigned long timeout);
 void blk_add_timer(struct request *req);
 
+enum bio_merge_status {
+	BIO_MERGE_OK,
+	BIO_MERGE_NONE,
+	BIO_MERGE_FAILED,
+};
+
+enum bio_merge_status bio_attempt_back_merge(struct request *req,
+		struct bio *bio, unsigned int nr_segs);
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs);
 bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
@@ -357,6 +366,7 @@ static inline bool blk_do_io_stat(struct request *rq)
 }
 
 void update_io_ticks(struct block_device *part, unsigned long now, bool end);
+unsigned int part_in_flight(struct block_device *part);
 
 static inline void req_set_nomerge(struct request_queue *q, struct request *req)
 {
@@ -378,17 +388,6 @@ static inline void ioc_clear_queue(struct request_queue *q)
 }
 #endif /* CONFIG_BLK_ICQ */
 
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
-extern ssize_t blk_throtl_sample_time_store(struct request_queue *q,
-	const char *page, size_t count);
-extern void blk_throtl_bio_endio(struct bio *bio);
-extern void blk_throtl_stat_add(struct request *rq, u64 time);
-#else
-static inline void blk_throtl_bio_endio(struct bio *bio) { }
-static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
-#endif
-
 struct bio *__blk_queue_bounce(struct bio *bio, struct request_queue *q);
 
 static inline bool blk_queue_may_bounce(struct request_queue *q)
@@ -407,13 +406,85 @@ static inline struct bio *blk_queue_bounce(struct bio *bio,
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
-void disk_free_zone_bitmaps(struct gendisk *disk);
+void disk_init_zone_resources(struct gendisk *disk);
+void disk_free_zone_resources(struct gendisk *disk);
+static inline bool bio_zone_write_plugging(struct bio *bio)
+{
+	return bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING);
+}
+static inline bool bio_is_zone_append(struct bio *bio)
+{
+	return bio_op(bio) == REQ_OP_ZONE_APPEND ||
+		bio_flagged(bio, BIO_EMULATES_ZONE_APPEND);
+}
+void blk_zone_write_plug_bio_merged(struct bio *bio);
+void blk_zone_write_plug_init_request(struct request *rq);
+static inline void blk_zone_update_request_bio(struct request *rq,
+					       struct bio *bio)
+{
+	/*
+	 * For zone append requests, the request sector indicates the location
+	 * at which the BIO data was written. Return this value to the BIO
+	 * issuer through the BIO iter sector.
+	 * For plugged zone writes, which include emulated zone append, we need
+	 * the original BIO sector so that blk_zone_write_plug_bio_endio() can
+	 * lookup the zone write plug.
+	 */
+	if (req_op(rq) == REQ_OP_ZONE_APPEND || bio_zone_write_plugging(bio))
+		bio->bi_iter.bi_sector = rq->__sector;
+}
+void blk_zone_write_plug_bio_endio(struct bio *bio);
+static inline void blk_zone_bio_endio(struct bio *bio)
+{
+	/*
+	 * For write BIOs to zoned devices, signal the completion of the BIO so
+	 * that the next write BIO can be submitted by zone write plugging.
+	 */
+	if (bio_zone_write_plugging(bio))
+		blk_zone_write_plug_bio_endio(bio);
+}
+
+void blk_zone_write_plug_finish_request(struct request *rq);
+static inline void blk_zone_finish_request(struct request *rq)
+{
+	if (rq->rq_flags & RQF_ZONE_WRITE_PLUGGING)
+		blk_zone_write_plug_finish_request(rq);
+}
 int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd,
 		unsigned long arg);
 int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		unsigned int cmd, unsigned long arg);
 #else /* CONFIG_BLK_DEV_ZONED */
-static inline void disk_free_zone_bitmaps(struct gendisk *disk) {}
+static inline void disk_init_zone_resources(struct gendisk *disk)
+{
+}
+static inline void disk_free_zone_resources(struct gendisk *disk)
+{
+}
+static inline bool bio_zone_write_plugging(struct bio *bio)
+{
+	return false;
+}
+static inline bool bio_is_zone_append(struct bio *bio)
+{
+	return false;
+}
+static inline void blk_zone_write_plug_bio_merged(struct bio *bio)
+{
+}
+static inline void blk_zone_write_plug_init_request(struct request *rq)
+{
+}
+static inline void blk_zone_update_request_bio(struct request *rq,
+					       struct bio *bio)
+{
+}
+static inline void blk_zone_bio_endio(struct bio *bio)
+{
+}
+static inline void blk_zone_finish_request(struct request *rq)
+{
+}
 static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
 		unsigned int cmd, unsigned long arg)
 {

block/elevator.c

@@ -83,13 +83,6 @@ bool elv_bio_merge_ok(struct request *rq, struct bio *bio)
 }
 EXPORT_SYMBOL(elv_bio_merge_ok);
 
-static inline bool elv_support_features(struct request_queue *q,
-		const struct elevator_type *e)
-{
-	return (q->required_elevator_features & e->elevator_features) ==
-		q->required_elevator_features;
-}
-
 /**
  * elevator_match - Check whether @e's name or alias matches @name
  * @e: Scheduler to test
@@ -120,7 +113,7 @@ static struct elevator_type *elevator_find_get(struct request_queue *q,
 
 	spin_lock(&elv_list_lock);
 	e = __elevator_find(name);
-	if (e && (!elv_support_features(q, e) || !elevator_tryget(e)))
+	if (e && (!elevator_tryget(e)))
 		e = NULL;
 	spin_unlock(&elv_list_lock);
 	return e;
@@ -580,34 +573,8 @@ static struct elevator_type *elevator_get_default(struct request_queue *q)
 }
 
 /*
- * Get the first elevator providing the features required by the request queue.
+ * Use the default elevator settings. If the chosen elevator initialization
- * Default to "none" if no matching elevator is found.
+ * fails, fall back to the "none" elevator (no elevator).
- */
-static struct elevator_type *elevator_get_by_features(struct request_queue *q)
-{
-	struct elevator_type *e, *found = NULL;
-
-	spin_lock(&elv_list_lock);
-
-	list_for_each_entry(e, &elv_list, list) {
-		if (elv_support_features(q, e)) {
-			found = e;
-			break;
-		}
-	}
-
-	if (found && !elevator_tryget(found))
-		found = NULL;
-
-	spin_unlock(&elv_list_lock);
-	return found;
-}
-
-/*
- * For a device queue that has no required features, use the default elevator
- * settings. Otherwise, use the first elevator available matching the required
- * features. If no suitable elevator is find or if the chosen elevator
- * initialization fails, fall back to the "none" elevator (no elevator).
  */
 void elevator_init_mq(struct request_queue *q)
 {
@@ -622,10 +589,7 @@ void elevator_init_mq(struct request_queue *q)
 	if (unlikely(q->elevator))
 		return;
 
-	if (!q->required_elevator_features)
+	e = elevator_get_default(q);
-		e = elevator_get_default(q);
-	else
-		e = elevator_get_by_features(q);
 	if (!e)
 		return;
 
@@ -781,7 +745,7 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name)
 	list_for_each_entry(e, &elv_list, list) {
 		if (e == cur)
 			len += sprintf(name+len, "[%s] ", e->elevator_name);
-		else if (elv_support_features(q, e))
+		else
 			len += sprintf(name+len, "%s ", e->elevator_name);
 	}
 	spin_unlock(&elv_list_lock);

block/elevator.h

@@ -74,7 +74,6 @@ struct elevator_type
 	struct elv_fs_entry *elevator_attrs;
 	const char *elevator_name;
 	const char *elevator_alias;
-	const unsigned int elevator_features;
 	struct module *elevator_owner;
 #ifdef CONFIG_BLK_DEBUG_FS
 	const struct blk_mq_debugfs_attr *queue_debugfs_attrs;

block/fops.c

@@ -44,18 +44,15 @@ static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
 #define DIO_INLINE_BIO_VECS 4
 
 static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
-		struct iov_iter *iter, unsigned int nr_pages)
+		struct iov_iter *iter, struct block_device *bdev,
+		unsigned int nr_pages)
 {
-	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs;
 	loff_t pos = iocb->ki_pos;
 	bool should_dirty = false;
 	struct bio bio;
 	ssize_t ret;
 
-	if (blkdev_dio_unaligned(bdev, pos, iter))
-		return -EINVAL;
-
 	if (nr_pages <= DIO_INLINE_BIO_VECS)
 		vecs = inline_vecs;
 	else {
@@ -161,9 +158,8 @@ static void blkdev_bio_end_io(struct bio *bio)
 }
 
 static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
-		unsigned int nr_pages)
+		struct block_device *bdev, unsigned int nr_pages)
 {
-	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	struct blk_plug plug;
 	struct blkdev_dio *dio;
 	struct bio *bio;
@@ -172,9 +168,6 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	loff_t pos = iocb->ki_pos;
 	int ret = 0;
 
-	if (blkdev_dio_unaligned(bdev, pos, iter))
-		return -EINVAL;
-
 	if (iocb->ki_flags & IOCB_ALLOC_CACHE)
 		opf |= REQ_ALLOC_CACHE;
 	bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL,
@@ -302,9 +295,9 @@ static void blkdev_bio_end_io_async(struct bio *bio)
 
 static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 					struct iov_iter *iter,
+					struct block_device *bdev,
 					unsigned int nr_pages)
 {
-	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	bool is_read = iov_iter_rw(iter) == READ;
 	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
 	struct blkdev_dio *dio;
@@ -312,9 +305,6 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	loff_t pos = iocb->ki_pos;
 	int ret = 0;
 
-	if (blkdev_dio_unaligned(bdev, pos, iter))
-		return -EINVAL;
-
 	if (iocb->ki_flags & IOCB_ALLOC_CACHE)
 		opf |= REQ_ALLOC_CACHE;
 	bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL,
@@ -368,18 +358,23 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 
 static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
+	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	unsigned int nr_pages;
 
 	if (!iov_iter_count(iter))
 		return 0;
 
+	if (blkdev_dio_unaligned(bdev, iocb->ki_pos, iter))
+		return -EINVAL;
+
 	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
 	if (likely(nr_pages <= BIO_MAX_VECS)) {
 		if (is_sync_kiocb(iocb))
-			return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
+			return __blkdev_direct_IO_simple(iocb, iter, bdev,
-		return __blkdev_direct_IO_async(iocb, iter, nr_pages);
+							nr_pages);
+		return __blkdev_direct_IO_async(iocb, iter, bdev, nr_pages);
 	}
-	return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
+	return __blkdev_direct_IO(iocb, iter, bdev, bio_max_segs(nr_pages));
 }
 
 static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
@@ -390,7 +385,7 @@ static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 
 	iomap->bdev = bdev;
 	iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev));
-	if (iomap->offset >= isize)
+	if (offset >= isize)
 		return -EIO;
 	iomap->type = IOMAP_MAPPED;
 	iomap->addr = iomap->offset;

block/genhd.c

@@ -118,7 +118,7 @@ static void part_stat_read_all(struct block_device *part,
 	}
 }
 
-static unsigned int part_in_flight(struct block_device *part)
+unsigned int part_in_flight(struct block_device *part)
 {
 	unsigned int inflight = 0;
 	int cpu;
@@ -345,9 +345,7 @@ int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode)
 	struct file *file;
 	int ret = 0;
 
-	if (disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN))
+	if (!disk_has_partscan(disk))
-		return -EINVAL;
-	if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
 		return -EINVAL;
 	if (disk->open_partitions)
 		return -EBUSY;
@@ -503,8 +501,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 			goto out_unregister_bdi;
 
 		/* Make sure the first partition scan will be proceed */
-		if (get_capacity(disk) && !(disk->flags & GENHD_FL_NO_PART) &&
+		if (get_capacity(disk) && disk_has_partscan(disk))
-		    !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
 			set_bit(GD_NEED_PART_SCAN, &disk->state);
 
 		bdev_add(disk->part0, ddev->devt);
@@ -954,15 +951,10 @@ ssize_t part_stat_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
 	struct block_device *bdev = dev_to_bdev(dev);
-	struct request_queue *q = bdev_get_queue(bdev);
 	struct disk_stats stat;
 	unsigned int inflight;
 
-	if (queue_is_mq(q))
+	inflight = part_in_flight(bdev);
-		inflight = blk_mq_in_flight(q, bdev);
-	else
-		inflight = part_in_flight(bdev);
-
 	if (inflight) {
 		part_stat_lock();
 		update_io_ticks(bdev, jiffies, true);
@@ -1047,6 +1039,12 @@ static ssize_t diskseq_show(struct device *dev,
 	return sprintf(buf, "%llu\n", disk->diskseq);
 }
 
+static ssize_t partscan_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", disk_has_partscan(dev_to_disk(dev)));
+}
+
 static DEVICE_ATTR(range, 0444, disk_range_show, NULL);
 static DEVICE_ATTR(ext_range, 0444, disk_ext_range_show, NULL);
 static DEVICE_ATTR(removable, 0444, disk_removable_show, NULL);
@@ -1060,6 +1058,7 @@ static DEVICE_ATTR(stat, 0444, part_stat_show, NULL);
 static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL);
 static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store);
 static DEVICE_ATTR(diskseq, 0444, diskseq_show, NULL);
+static DEVICE_ATTR(partscan, 0444, partscan_show, NULL);
 
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 ssize_t part_fail_show(struct device *dev,
@@ -1106,6 +1105,7 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_events_async.attr,
 	&dev_attr_events_poll_msecs.attr,
 	&dev_attr_diskseq.attr,
+	&dev_attr_partscan.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
 #endif
@@ -1182,7 +1182,7 @@ static void disk_release(struct device *dev)
 
 	disk_release_events(disk);
 	kfree(disk->random);
-	disk_free_zone_bitmaps(disk);
+	disk_free_zone_resources(disk);
 	xa_destroy(&disk->part_tbl);
 
 	disk->queue->disk = NULL;
@@ -1251,11 +1251,8 @@ 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;
-		if (queue_is_mq(gp->queue))
-			inflight = blk_mq_in_flight(gp->queue, hd);
-		else
-			inflight = part_in_flight(hd);
 
+		inflight = part_in_flight(hd);
 		if (inflight) {
 			part_stat_lock();
 			update_io_ticks(hd, jiffies, true);
@@ -1364,6 +1361,7 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 	if (blkcg_init_disk(disk))
 		goto out_erase_part0;
 
+	disk_init_zone_resources(disk);
 	rand_initialize_disk(disk);
 	disk_to_dev(disk)->class = &block_class;
 	disk_to_dev(disk)->type = &disk_type;

block/ioctl.c

@@ -33,7 +33,7 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 	if (op == BLKPG_DEL_PARTITION)
 		return bdev_del_partition(disk, p.pno);
 
-	if (p.start < 0 || p.length <= 0 || p.start + p.length < 0)
+	if (p.start < 0 || p.length <= 0 || LLONG_MAX - p.length < p.start)
 		return -EINVAL;
 	/* Check that the partition is aligned to the block size */
 	if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev)))
@@ -95,9 +95,12 @@ static int compat_blkpg_ioctl(struct block_device *bdev,
 static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 		unsigned long arg)
 {
-	uint64_t range[2];
+	unsigned int bs_mask = bdev_logical_block_size(bdev) - 1;
-	uint64_t start, len, end;
 	struct inode *inode = bdev->bd_inode;
+	uint64_t range[2], start, len, end;
+	struct bio *prev = NULL, *bio;
+	sector_t sector, nr_sects;
+	struct blk_plug plug;
 	int err;
 
 	if (!(mode & BLK_OPEN_WRITE))
@@ -105,6 +108,8 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 
 	if (!bdev_max_discard_sectors(bdev))
 		return -EOPNOTSUPP;
+	if (bdev_read_only(bdev))
+		return -EPERM;
 
 	if (copy_from_user(range, (void __user *)arg, sizeof(range)))
 		return -EFAULT;
@@ -112,9 +117,9 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 	start = range[0];
 	len = range[1];
 
-	if (start & 511)
+	if (!len)
 		return -EINVAL;
-	if (len & 511)
+	if ((start | len) & bs_mask)
 		return -EINVAL;
 
 	if (check_add_overflow(start, len, &end) ||
@@ -125,7 +130,32 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
 	if (err)
 		goto fail;
-	err = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL);
+
+	sector = start >> SECTOR_SHIFT;
+	nr_sects = len >> SECTOR_SHIFT;
+
+	blk_start_plug(&plug);
+	while (1) {
+		if (fatal_signal_pending(current)) {
+			if (prev)
+				bio_await_chain(prev);
+			err = -EINTR;
+			goto out_unplug;
+		}
+		bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects,
+				GFP_KERNEL);
+		if (!bio)
+			break;
+		prev = bio_chain_and_submit(prev, bio);
+	}
+	if (prev) {
+		err = submit_bio_wait(prev);
+		if (err == -EOPNOTSUPP)
+			err = 0;
+		bio_put(prev);
+	}
+out_unplug:
+	blk_finish_plug(&plug);
 fail:
 	filemap_invalidate_unlock(inode->i_mapping);
 	return err;

block/mq-deadline.c

@@ -102,7 +102,6 @@ struct deadline_data {
 	int prio_aging_expire;
 
 	spinlock_t lock;
-	spinlock_t zone_lock;
 };
 
 /* Maps an I/O priority class to a deadline scheduler priority. */
@@ -129,36 +128,7 @@ static u8 dd_rq_ioclass(struct request *rq)
 }
 
 /*
- * get the request before `rq' in sector-sorted order
+ * Return the first request for which blk_rq_pos() >= @pos.
- */
-static inline struct request *
-deadline_earlier_request(struct request *rq)
-{
-	struct rb_node *node = rb_prev(&rq->rb_node);
-
-	if (node)
-		return rb_entry_rq(node);
-
-	return NULL;
-}
-
-/*
- * get the request after `rq' in sector-sorted order
- */
-static inline struct request *
-deadline_latter_request(struct request *rq)
-{
-	struct rb_node *node = rb_next(&rq->rb_node);
-
-	if (node)
-		return rb_entry_rq(node);
-
-	return NULL;
-}
-
-/*
- * Return the first request for which blk_rq_pos() >= @pos. For zoned devices,
- * return the first request after the start of the zone containing @pos.
  */
 static inline struct request *deadline_from_pos(struct dd_per_prio *per_prio,
 				enum dd_data_dir data_dir, sector_t pos)
@@ -170,14 +140,6 @@ static inline struct request *deadline_from_pos(struct dd_per_prio *per_prio,
 		return NULL;
 
 	rq = rb_entry_rq(node);
-	/*
-	 * A zoned write may have been requeued with a starting position that
-	 * is below that of the most recently dispatched request. Hence, for
-	 * zoned writes, start searching from the start of a zone.
-	 */
-	if (blk_rq_is_seq_zoned_write(rq))
-		pos = round_down(pos, rq->q->limits.chunk_sectors);
-
 	while (node) {
 		rq = rb_entry_rq(node);
 		if (blk_rq_pos(rq) >= pos) {
@@ -308,36 +270,6 @@ static inline bool deadline_check_fifo(struct dd_per_prio *per_prio,
 	return time_is_before_eq_jiffies((unsigned long)rq->fifo_time);
 }
 
-/*
- * Check if rq has a sequential request preceding it.
- */
-static bool deadline_is_seq_write(struct deadline_data *dd, struct request *rq)
-{
-	struct request *prev = deadline_earlier_request(rq);
-
-	if (!prev)
-		return false;
-
-	return blk_rq_pos(prev) + blk_rq_sectors(prev) == blk_rq_pos(rq);
-}
-
-/*
- * Skip all write requests that are sequential from @rq, even if we cross
- * a zone boundary.
- */
-static struct request *deadline_skip_seq_writes(struct deadline_data *dd,
-						struct request *rq)
-{
-	sector_t pos = blk_rq_pos(rq);
-
-	do {
-		pos += blk_rq_sectors(rq);
-		rq = deadline_latter_request(rq);
-	} while (rq && blk_rq_pos(rq) == pos);
-
-	return rq;
-}
-
 /*
  * For the specified data direction, return the next request to
  * dispatch using arrival ordered lists.
@@ -346,40 +278,10 @@ static struct request *
 deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
 		      enum dd_data_dir data_dir)
 {
-	struct request *rq, *rb_rq, *next;
-	unsigned long flags;
-
 	if (list_empty(&per_prio->fifo_list[data_dir]))
 		return NULL;
 
-	rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next);
+	return rq_entry_fifo(per_prio->fifo_list[data_dir].next);
-	if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q))
-		return rq;
-
-	/*
-	 * Look for a write request that can be dispatched, that is one with
-	 * an unlocked target zone. For some HDDs, breaking a sequential
-	 * write stream can lead to lower throughput, so make sure to preserve
-	 * sequential write streams, even if that stream crosses into the next
-	 * zones and these zones are unlocked.
-	 */
-	spin_lock_irqsave(&dd->zone_lock, flags);
-	list_for_each_entry_safe(rq, next, &per_prio->fifo_list[DD_WRITE],
-				 queuelist) {
-		/* Check whether a prior request exists for the same zone. */
-		rb_rq = deadline_from_pos(per_prio, data_dir, blk_rq_pos(rq));
-		if (rb_rq && blk_rq_pos(rb_rq) < blk_rq_pos(rq))
-			rq = rb_rq;
-		if (blk_req_can_dispatch_to_zone(rq) &&
-		    (blk_queue_nonrot(rq->q) ||
-		     !deadline_is_seq_write(dd, rq)))
-			goto out;
-	}
-	rq = NULL;
-out:
-	spin_unlock_irqrestore(&dd->zone_lock, flags);
-
-	return rq;
 }
 
 /*
@@ -390,36 +292,8 @@ static struct request *
 deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
 		      enum dd_data_dir data_dir)
 {
-	struct request *rq;
+	return deadline_from_pos(per_prio, data_dir,
-	unsigned long flags;
+				 per_prio->latest_pos[data_dir]);
-
-	rq = deadline_from_pos(per_prio, data_dir,
-			       per_prio->latest_pos[data_dir]);
-	if (!rq)
-		return NULL;
-
-	if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q))
-		return rq;
-
-	/*
-	 * Look for a write request that can be dispatched, that is one with
-	 * an unlocked target zone. For some HDDs, breaking a sequential
-	 * write stream can lead to lower throughput, so make sure to preserve
-	 * sequential write streams, even if that stream crosses into the next
-	 * zones and these zones are unlocked.
-	 */
-	spin_lock_irqsave(&dd->zone_lock, flags);
-	while (rq) {
-		if (blk_req_can_dispatch_to_zone(rq))
-			break;
-		if (blk_queue_nonrot(rq->q))
-			rq = deadline_latter_request(rq);
-		else
-			rq = deadline_skip_seq_writes(dd, rq);
-	}
-	spin_unlock_irqrestore(&dd->zone_lock, flags);
-
-	return rq;
 }
 
 /*
@@ -525,10 +399,6 @@ dispatch_find_request:
 		rq = next_rq;
 	}
 
-	/*
-	 * For a zoned block device, if we only have writes queued and none of
-	 * them can be dispatched, rq will be NULL.
-	 */
 	if (!rq)
 		return NULL;
 
@@ -549,10 +419,6 @@ done:
 	prio = ioprio_class_to_prio[ioprio_class];
 	dd->per_prio[prio].latest_pos[data_dir] = blk_rq_pos(rq);
 	dd->per_prio[prio].stats.dispatched++;
-	/*
-	 * If the request needs its target zone locked, do it.
-	 */
-	blk_req_zone_write_lock(rq);
 	rq->rq_flags |= RQF_STARTED;
 	return rq;
 }
@@ -722,7 +588,6 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e)
 	dd->fifo_batch = fifo_batch;
 	dd->prio_aging_expire = prio_aging_expire;
 	spin_lock_init(&dd->lock);
-	spin_lock_init(&dd->zone_lock);
 
 	/* We dispatch from request queue wide instead of hw queue */
 	blk_queue_flag_set(QUEUE_FLAG_SQ_SCHED, q);
@@ -804,12 +669,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	lockdep_assert_held(&dd->lock);
 
-	/*
-	 * This may be a requeue of a write request that has locked its
-	 * target zone. If it is the case, this releases the zone lock.
-	 */
-	blk_req_zone_write_unlock(rq);
-
 	prio = ioprio_class_to_prio[ioprio_class];
 	per_prio = &dd->per_prio[prio];
 	if (!rq->elv.priv[0]) {
@@ -841,18 +700,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		 */
 		rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
 		insert_before = &per_prio->fifo_list[data_dir];
-#ifdef CONFIG_BLK_DEV_ZONED
-		/*
-		 * Insert zoned writes such that requests are sorted by
-		 * position per zone.
-		 */
-		if (blk_rq_is_seq_zoned_write(rq)) {
-			struct request *rq2 = deadline_latter_request(rq);
-
-			if (rq2 && blk_rq_zone_no(rq2) == blk_rq_zone_no(rq))
-				insert_before = &rq2->queuelist;
-		}
-#endif
 		list_add_tail(&rq->queuelist, insert_before);
 	}
 }
@@ -887,33 +734,8 @@ static void dd_prepare_request(struct request *rq)
 	rq->elv.priv[0] = NULL;
 }
 
-static bool dd_has_write_work(struct blk_mq_hw_ctx *hctx)
-{
-	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
-	enum dd_prio p;
-
-	for (p = 0; p <= DD_PRIO_MAX; p++)
-		if (!list_empty_careful(&dd->per_prio[p].fifo_list[DD_WRITE]))
-			return true;
-
-	return false;
-}
-
 /*
  * Callback from inside blk_mq_free_request().
- *
- * For zoned block devices, write unlock the target zone of
- * completed write requests. Do this while holding the zone lock
- * spinlock so that the zone is never unlocked while deadline_fifo_request()
- * or deadline_next_request() are executing. This function is called for
- * all requests, whether or not these requests complete successfully.
- *
- * For a zoned block device, __dd_dispatch_request() may have stopped
- * dispatching requests if all the queued requests are write requests directed
- * at zones that are already locked due to on-going write requests. To ensure
- * write request dispatch progress in this case, mark the queue as needing a
- * restart to ensure that the queue is run again after completion of the
- * request and zones being unlocked.
  */
 static void dd_finish_request(struct request *rq)
 {
@@ -928,21 +750,8 @@ static void dd_finish_request(struct request *rq)
 	 * called dd_insert_requests(). Skip requests that bypassed I/O
 	 * scheduling. See also blk_mq_request_bypass_insert().
 	 */
-	if (!rq->elv.priv[0])
+	if (rq->elv.priv[0])
-		return;
+		atomic_inc(&per_prio->stats.completed);
-
-	atomic_inc(&per_prio->stats.completed);
-
-	if (blk_queue_is_zoned(q)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&dd->zone_lock, flags);
-		blk_req_zone_write_unlock(rq);
-		spin_unlock_irqrestore(&dd->zone_lock, flags);
-
-		if (dd_has_write_work(rq->mq_hctx))
-			blk_mq_sched_mark_restart_hctx(rq->mq_hctx);
-	}
 }
 
 static bool dd_has_work_for_prio(struct dd_per_prio *per_prio)
@@ -1266,7 +1075,6 @@ static struct elevator_type mq_deadline = {
 	.elevator_attrs = deadline_attrs,
 	.elevator_name = "mq-deadline",
 	.elevator_alias = "deadline",
-	.elevator_features = ELEVATOR_F_ZBD_SEQ_WRITE,
 	.elevator_owner = THIS_MODULE,
 };
 MODULE_ALIAS("mq-deadline-iosched");

block/partitions/cmdline.c

@@ -70,8 +70,8 @@ static int parse_subpart(struct cmdline_subpart **subpart, char *partdef)
 	}
 
 	if (*partdef == '(') {
-		int length;
+		partdef++;
-		char *next = strchr(++partdef, ')');
+		char *next = strsep(&partdef, ")");
 
 		if (!next) {
 			pr_warn("cmdline partition format is invalid.");
@@ -79,11 +79,7 @@ static int parse_subpart(struct cmdline_subpart **subpart, char *partdef)
 			goto fail;
 		}
 
-		length = min_t(int, next - partdef,
+		strscpy(new_subpart->name, next, sizeof(new_subpart->name));
-			       sizeof(new_subpart->name) - 1);
-		strscpy(new_subpart->name, partdef, length);
-
-		partdef = ++next;
 	} else
 		new_subpart->name[0] = '\0';
 
@@ -117,14 +113,12 @@ static void free_subpart(struct cmdline_parts *parts)
 	}
 }
 
-static int parse_parts(struct cmdline_parts **parts, const char *bdevdef)
+static int parse_parts(struct cmdline_parts **parts, char *bdevdef)
 {
 	int ret = -EINVAL;
 	char *next;
-	int length;
 	struct cmdline_subpart **next_subpart;
 	struct cmdline_parts *newparts;
-	char buf[BDEVNAME_SIZE + 32 + 4];
 
 	*parts = NULL;
 
@@ -132,28 +126,19 @@ static int parse_parts(struct cmdline_parts **parts, const char *bdevdef)
 	if (!newparts)
 		return -ENOMEM;
 
-	next = strchr(bdevdef, ':');
+	next = strsep(&bdevdef, ":");
 	if (!next) {
 		pr_warn("cmdline partition has no block device.");
 		goto fail;
 	}
 
-	length = min_t(int, next - bdevdef, sizeof(newparts->name) - 1);
+	strscpy(newparts->name, next, sizeof(newparts->name));
-	strscpy(newparts->name, bdevdef, length);
 	newparts->nr_subparts = 0;
 
 	next_subpart = &newparts->subpart;
 
-	while (next && *(++next)) {
+	while ((next = strsep(&bdevdef, ","))) {
-		bdevdef = next;
+		ret = parse_subpart(next_subpart, next);
-		next = strchr(bdevdef, ',');
-
-		length = (!next) ? (sizeof(buf) - 1) :
-			min_t(int, next - bdevdef, sizeof(buf) - 1);
-
-		strscpy(buf, bdevdef, length);
-
-		ret = parse_subpart(next_subpart, buf);
 		if (ret)
 			goto fail;
 
@@ -199,24 +184,17 @@ static int cmdline_parts_parse(struct cmdline_parts **parts,
 
 	*parts = NULL;
 
-	next = pbuf = buf = kstrdup(cmdline, GFP_KERNEL);
+	pbuf = buf = kstrdup(cmdline, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
 	next_parts = parts;
 
-	while (next && *pbuf) {
+	while ((next = strsep(&pbuf, ";"))) {
-		next = strchr(pbuf, ';');
+		ret = parse_parts(next_parts, next);
-		if (next)
-			*next = '\0';
-
-		ret = parse_parts(next_parts, pbuf);
 		if (ret)
 			goto fail;
 
-		if (next)
-			pbuf = ++next;
-
 		next_parts = &(*next_parts)->next_parts;
 	}
 
@@ -250,7 +228,6 @@ static struct cmdline_parts *bdev_parts;
 static int add_part(int slot, struct cmdline_subpart *subpart,
 		struct parsed_partitions *state)
 {
-	int label_min;
 	struct partition_meta_info *info;
 	char tmp[sizeof(info->volname) + 4];
 
@@ -262,9 +239,7 @@ static int add_part(int slot, struct cmdline_subpart *subpart,
 
 	info = &state->parts[slot].info;
 
-	label_min = min_t(int, sizeof(info->volname) - 1,
+	strscpy(info->volname, subpart->name, sizeof(info->volname));
-			  sizeof(subpart->name));
-	strscpy(info->volname, subpart->name, label_min);
 
 	snprintf(tmp, sizeof(tmp), "(%s)", info->volname);
 	strlcat(state->pp_buf, tmp, PAGE_SIZE);

block/partitions/core.c

@@ -573,10 +573,7 @@ static int blk_add_partitions(struct gendisk *disk)
 	struct parsed_partitions *state;
 	int ret = -EAGAIN, p;
 
-	if (disk->flags & GENHD_FL_NO_PART)
+	if (!disk_has_partscan(disk))
-		return 0;
-
-	if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
 		return 0;
 
 	state = check_partition(disk);

drivers/block/brd.c

@@ -29,10 +29,7 @@
 
 /*
  * Each block ramdisk device has a xarray brd_pages of pages that stores
- * the pages containing the block device's contents. A brd page's ->index is
+ * the pages containing the block device's contents.
- * its offset in PAGE_SIZE units. This is similar to, but in no way connected
- * with, the kernel's pagecache or buffer cache (which sit above our block
- * device).
  */
 struct brd_device {
 	int			brd_number;
@@ -51,15 +48,7 @@ struct brd_device {
  */
 static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
 {
-	pgoff_t idx;
+	return xa_load(&brd->brd_pages, sector >> PAGE_SECTORS_SHIFT);
-	struct page *page;
-
-	idx = sector >> PAGE_SECTORS_SHIFT; /* sector to page index */
-	page = xa_load(&brd->brd_pages, idx);
-
-	BUG_ON(page && page->index != idx);
-
-	return page;
 }
 
 /*
@@ -67,8 +56,8 @@ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
  */
 static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp)
 {
-	pgoff_t idx;
+	pgoff_t idx = sector >> PAGE_SECTORS_SHIFT;
-	struct page *page, *cur;
+	struct page *page;
 	int ret = 0;
 
 	page = brd_lookup_page(brd, sector);
@@ -80,23 +69,16 @@ static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp)
 		return -ENOMEM;
 
 	xa_lock(&brd->brd_pages);
-
+	ret = __xa_insert(&brd->brd_pages, idx, page, gfp);
-	idx = sector >> PAGE_SECTORS_SHIFT;
+	if (!ret)
-	page->index = idx;
-
-	cur = __xa_cmpxchg(&brd->brd_pages, idx, NULL, page, gfp);
-
-	if (unlikely(cur)) {
-		__free_page(page);
-		ret = xa_err(cur);
-		if (!ret && (cur->index != idx))
-			ret = -EIO;
-	} else {
 		brd->brd_nr_pages++;
-	}
-
 	xa_unlock(&brd->brd_pages);
 
+	if (ret < 0) {
+		__free_page(page);
+		if (ret == -EBUSY)
+			ret = 0;
+	}
 	return ret;
 }
 

drivers/block/null_blk/main.c

@@ -225,6 +225,10 @@ static unsigned long g_cache_size;
 module_param_named(cache_size, g_cache_size, ulong, 0444);
 MODULE_PARM_DESC(mbps, "Cache size in MiB for memory-backed device. Default: 0 (none)");
 
+static bool g_fua = true;
+module_param_named(fua, g_fua, bool, 0444);
+MODULE_PARM_DESC(zoned, "Enable/disable FUA support when cache_size is used. Default: true");
+
 static unsigned int g_mbps;
 module_param_named(mbps, g_mbps, uint, 0444);
 MODULE_PARM_DESC(mbps, "Limit maximum bandwidth (in MiB/s). Default: 0 (no limit)");
@@ -253,6 +257,11 @@ static unsigned int g_zone_max_active;
 module_param_named(zone_max_active, g_zone_max_active, uint, 0444);
 MODULE_PARM_DESC(zone_max_active, "Maximum number of active zones when block device is zoned. Default: 0 (no limit)");
 
+static int g_zone_append_max_sectors = INT_MAX;
+module_param_named(zone_append_max_sectors, g_zone_append_max_sectors, int, 0444);
+MODULE_PARM_DESC(zone_append_max_sectors,
+		 "Maximum size of a zone append command (in 512B sectors). Specify 0 for zone append emulation");
+
 static struct nullb_device *null_alloc_dev(void);
 static void null_free_dev(struct nullb_device *dev);
 static void null_del_dev(struct nullb *nullb);
@@ -436,10 +445,12 @@ NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
 NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
+NULLB_DEVICE_ATTR(zone_append_max_sectors, uint, NULL);
 NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
 NULLB_DEVICE_ATTR(no_sched, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tags, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL);
+NULLB_DEVICE_ATTR(fua, bool, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -580,12 +591,14 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_zone_nr_conv,
 	&nullb_device_attr_zone_max_open,
 	&nullb_device_attr_zone_max_active,
+	&nullb_device_attr_zone_append_max_sectors,
 	&nullb_device_attr_zone_readonly,
 	&nullb_device_attr_zone_offline,
 	&nullb_device_attr_virt_boundary,
 	&nullb_device_attr_no_sched,
 	&nullb_device_attr_shared_tags,
 	&nullb_device_attr_shared_tag_bitmap,
+	&nullb_device_attr_fua,
 	NULL,
 };
 
@@ -664,14 +677,14 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
 	return snprintf(page, PAGE_SIZE,
-			"badblocks,blocking,blocksize,cache_size,"
+			"badblocks,blocking,blocksize,cache_size,fua,"
 			"completion_nsec,discard,home_node,hw_queue_depth,"
 			"irqmode,max_sectors,mbps,memory_backed,no_sched,"
 			"poll_queues,power,queue_mode,shared_tag_bitmap,"
 			"shared_tags,size,submit_queues,use_per_node_hctx,"
 			"virt_boundary,zoned,zone_capacity,zone_max_active,"
 			"zone_max_open,zone_nr_conv,zone_offline,zone_readonly,"
-			"zone_size\n");
+			"zone_size,zone_append_max_sectors\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -751,10 +764,13 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->zone_nr_conv = g_zone_nr_conv;
 	dev->zone_max_open = g_zone_max_open;
 	dev->zone_max_active = g_zone_max_active;
+	dev->zone_append_max_sectors = g_zone_append_max_sectors;
 	dev->virt_boundary = g_virt_boundary;
 	dev->no_sched = g_no_sched;
 	dev->shared_tags = g_shared_tags;
 	dev->shared_tag_bitmap = g_shared_tag_bitmap;
+	dev->fua = g_fua;
+
 	return dev;
 }
 
@@ -1151,7 +1167,7 @@ blk_status_t null_handle_discard(struct nullb_device *dev,
 	return BLK_STS_OK;
 }
 
-static int null_handle_flush(struct nullb *nullb)
+static blk_status_t null_handle_flush(struct nullb *nullb)
 {
 	int err;
 
@@ -1168,7 +1184,7 @@ static int null_handle_flush(struct nullb *nullb)
 
 	WARN_ON(!radix_tree_empty(&nullb->dev->cache));
 	spin_unlock_irq(&nullb->lock);
-	return err;
+	return errno_to_blk_status(err);
 }
 
 static int null_transfer(struct nullb *nullb, struct page *page,
@@ -1206,7 +1222,7 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 {
 	struct request *rq = blk_mq_rq_from_pdu(cmd);
 	struct nullb *nullb = cmd->nq->dev->nullb;
-	int err;
+	int err = 0;
 	unsigned int len;
 	sector_t sector = blk_rq_pos(rq);
 	struct req_iterator iter;
@@ -1218,15 +1234,13 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
 				     op_is_write(req_op(rq)), sector,
 				     rq->cmd_flags & REQ_FUA);
-		if (err) {
+		if (err)
-			spin_unlock_irq(&nullb->lock);
+			break;
-			return err;
-		}
 		sector += len >> SECTOR_SHIFT;
 	}
 	spin_unlock_irq(&nullb->lock);
 
-	return 0;
+	return errno_to_blk_status(err);
 }
 
 static inline blk_status_t null_handle_throttled(struct nullb_cmd *cmd)
@@ -1273,8 +1287,8 @@ static inline blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd,
 
 	if (op == REQ_OP_DISCARD)
 		return null_handle_discard(dev, sector, nr_sectors);
-	return errno_to_blk_status(null_handle_rq(cmd));
 
+	return null_handle_rq(cmd);
 }
 
 static void nullb_zero_read_cmd_buffer(struct nullb_cmd *cmd)
@@ -1343,7 +1357,7 @@ static void null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
 	blk_status_t sts;
 
 	if (op == REQ_OP_FLUSH) {
-		cmd->error = errno_to_blk_status(null_handle_flush(nullb));
+		cmd->error = null_handle_flush(nullb);
 		goto out;
 	}
 
@@ -1912,7 +1926,7 @@ static int null_add_dev(struct nullb_device *dev)
 
 	if (dev->cache_size > 0) {
 		set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
-		blk_queue_write_cache(nullb->q, true, true);
+		blk_queue_write_cache(nullb->q, true, dev->fua);
 	}
 
 	nullb->q->queuedata = nullb;
@@ -2113,10 +2127,13 @@ static void __exit null_exit(void)
 
 	if (tag_set.ops)
 		blk_mq_free_tag_set(&tag_set);
+
+	mutex_destroy(&lock);
 }
 
 module_init(null_init);
 module_exit(null_exit);
 
 MODULE_AUTHOR("Jens Axboe <axboe@kernel.dk>");
+MODULE_DESCRIPTION("multi queue aware block test driver");
 MODULE_LICENSE("GPL");

drivers/block/null_blk/null_blk.h

@@ -82,6 +82,7 @@ struct nullb_device {
 	unsigned int zone_nr_conv; /* number of conventional zones */
 	unsigned int zone_max_open; /* max number of open zones */
 	unsigned int zone_max_active; /* max number of active zones */
+	unsigned int zone_append_max_sectors; /* Max sectors per zone append command */
 	unsigned int submit_queues; /* number of submission queues */
 	unsigned int prev_submit_queues; /* number of submission queues before change */
 	unsigned int poll_queues; /* number of IOPOLL submission queues */
@@ -104,6 +105,7 @@ struct nullb_device {
 	bool no_sched; /* no IO scheduler for the device */
 	bool shared_tags; /* share tag set between devices for blk-mq */
 	bool shared_tag_bitmap; /* use hostwide shared tags */
+	bool fua; /* Support FUA */
 };
 
 struct nullb {

drivers/block/null_blk/zoned.c

@@ -9,6 +9,8 @@
 #undef pr_fmt
 #define pr_fmt(fmt)	"null_blk: " fmt
 
+#define NULL_ZONE_INVALID_WP	((sector_t)-1)
+
 static inline sector_t mb_to_sects(unsigned long mb)
 {
 	return ((sector_t)mb * SZ_1M) >> SECTOR_SHIFT;
@@ -19,18 +21,6 @@ static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
 	return sect >> ilog2(dev->zone_size_sects);
 }
 
-static inline void null_lock_zone_res(struct nullb_device *dev)
-{
-	if (dev->need_zone_res_mgmt)
-		spin_lock_irq(&dev->zone_res_lock);
-}
-
-static inline void null_unlock_zone_res(struct nullb_device *dev)
-{
-	if (dev->need_zone_res_mgmt)
-		spin_unlock_irq(&dev->zone_res_lock);
-}
-
 static inline void null_init_zone_lock(struct nullb_device *dev,
 				       struct nullb_zone *zone)
 {
@@ -103,6 +93,11 @@ int null_init_zoned_dev(struct nullb_device *dev,
 			dev->zone_nr_conv);
 	}
 
+	dev->zone_append_max_sectors =
+		min(ALIGN_DOWN(dev->zone_append_max_sectors,
+			       dev->blocksize >> SECTOR_SHIFT),
+		    zone_capacity_sects);
+
 	/* Max active zones has to be < nbr of seq zones in order to be enforceable */
 	if (dev->zone_max_active >= dev->nr_zones - dev->zone_nr_conv) {
 		dev->zone_max_active = 0;
@@ -154,7 +149,7 @@ int null_init_zoned_dev(struct nullb_device *dev,
 
 	lim->zoned = true;
 	lim->chunk_sectors = dev->zone_size_sects;
-	lim->max_zone_append_sectors = dev->zone_size_sects;
+	lim->max_zone_append_sectors = dev->zone_append_max_sectors;
 	lim->max_open_zones = dev->zone_max_open;
 	lim->max_active_zones = dev->zone_max_active;
 	return 0;
@@ -163,11 +158,16 @@ int null_init_zoned_dev(struct nullb_device *dev,
 int null_register_zoned_dev(struct nullb *nullb)
 {
 	struct request_queue *q = nullb->q;
+	struct gendisk *disk = nullb->disk;
 
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
-	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
+	disk->nr_zones = bdev_nr_zones(disk->part0);
-	nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0);
+
-	return blk_revalidate_disk_zones(nullb->disk, NULL);
+	pr_info("%s: using %s zone append\n",
+		disk->disk_name,
+		queue_emulates_zone_append(q) ? "emulated" : "native");
+
+	return blk_revalidate_disk_zones(disk);
 }
 
 void null_free_zoned_dev(struct nullb_device *dev)
@@ -241,35 +241,6 @@ size_t null_zone_valid_read_len(struct nullb *nullb,
 	return (zone->wp - sector) << SECTOR_SHIFT;
 }
 
-static blk_status_t __null_close_zone(struct nullb_device *dev,
-				      struct nullb_zone *zone)
-{
-	switch (zone->cond) {
-	case BLK_ZONE_COND_CLOSED:
-		/* close operation on closed is not an error */
-		return BLK_STS_OK;
-	case BLK_ZONE_COND_IMP_OPEN:
-		dev->nr_zones_imp_open--;
-		break;
-	case BLK_ZONE_COND_EXP_OPEN:
-		dev->nr_zones_exp_open--;
-		break;
-	case BLK_ZONE_COND_EMPTY:
-	case BLK_ZONE_COND_FULL:
-	default:
-		return BLK_STS_IOERR;
-	}
-
-	if (zone->wp == zone->start) {
-		zone->cond = BLK_ZONE_COND_EMPTY;
-	} else {
-		zone->cond = BLK_ZONE_COND_CLOSED;
-		dev->nr_zones_closed++;
-	}
-
-	return BLK_STS_OK;
-}
-
 static void null_close_imp_open_zone(struct nullb_device *dev)
 {
 	struct nullb_zone *zone;
@@ -286,7 +257,13 @@ static void null_close_imp_open_zone(struct nullb_device *dev)
 			zno = dev->zone_nr_conv;
 
 		if (zone->cond == BLK_ZONE_COND_IMP_OPEN) {
-			__null_close_zone(dev, zone);
+			dev->nr_zones_imp_open--;
+			if (zone->wp == zone->start) {
+				zone->cond = BLK_ZONE_COND_EMPTY;
+			} else {
+				zone->cond = BLK_ZONE_COND_CLOSED;
+				dev->nr_zones_closed++;
+			}
 			dev->imp_close_zone_no = zno;
 			return;
 		}
@@ -374,73 +351,73 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 
 	null_lock_zone(dev, zone);
 
-	if (zone->cond == BLK_ZONE_COND_FULL ||
-	    zone->cond == BLK_ZONE_COND_READONLY ||
-	    zone->cond == BLK_ZONE_COND_OFFLINE) {
-		/* Cannot write to the zone */
-		ret = BLK_STS_IOERR;
-		goto unlock;
-	}
-
 	/*
-	 * Regular writes must be at the write pointer position.
+	 * Regular writes must be at the write pointer position. Zone append
-	 * Zone append writes are automatically issued at the write
+	 * writes are automatically issued at the write pointer and the position
-	 * pointer and the position returned using the request or BIO
+	 * returned using the request sector. Note that we do not check the zone
-	 * sector.
+	 * condition because for FULL, READONLY and OFFLINE zones, the sector
+	 * check against the zone write pointer will always result in failing
+	 * the command.
 	 */
 	if (append) {
+		if (WARN_ON_ONCE(!dev->zone_append_max_sectors) ||
+		    zone->wp == NULL_ZONE_INVALID_WP) {
+			ret = BLK_STS_IOERR;
+			goto unlock_zone;
+		}
 		sector = zone->wp;
 		blk_mq_rq_from_pdu(cmd)->__sector = sector;
-	} else if (sector != zone->wp) {
-		ret = BLK_STS_IOERR;
-		goto unlock;
 	}
 
-	if (zone->wp + nr_sectors > zone->start + zone->capacity) {
+	if (sector != zone->wp ||
+	    zone->wp + nr_sectors > zone->start + zone->capacity) {
 		ret = BLK_STS_IOERR;
-		goto unlock;
+		goto unlock_zone;
 	}
 
 	if (zone->cond == BLK_ZONE_COND_CLOSED ||
 	    zone->cond == BLK_ZONE_COND_EMPTY) {
-		null_lock_zone_res(dev);
+		if (dev->need_zone_res_mgmt) {
+			spin_lock(&dev->zone_res_lock);
 
-		ret = null_check_zone_resources(dev, zone);
+			ret = null_check_zone_resources(dev, zone);
-		if (ret != BLK_STS_OK) {
+			if (ret != BLK_STS_OK) {
-			null_unlock_zone_res(dev);
+				spin_unlock(&dev->zone_res_lock);
-			goto unlock;
+				goto unlock_zone;
-		}
+			}
-		if (zone->cond == BLK_ZONE_COND_CLOSED) {
+			if (zone->cond == BLK_ZONE_COND_CLOSED) {
-			dev->nr_zones_closed--;
+				dev->nr_zones_closed--;
-			dev->nr_zones_imp_open++;
+				dev->nr_zones_imp_open++;
-		} else if (zone->cond == BLK_ZONE_COND_EMPTY) {
+			} else if (zone->cond == BLK_ZONE_COND_EMPTY) {
-			dev->nr_zones_imp_open++;
+				dev->nr_zones_imp_open++;
+			}
+
+			spin_unlock(&dev->zone_res_lock);
 		}
 
-		if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
+		zone->cond = BLK_ZONE_COND_IMP_OPEN;
-			zone->cond = BLK_ZONE_COND_IMP_OPEN;
-
-		null_unlock_zone_res(dev);
 	}
 
 	ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
 	if (ret != BLK_STS_OK)
-		goto unlock;
+		goto unlock_zone;
 
 	zone->wp += nr_sectors;
 	if (zone->wp == zone->start + zone->capacity) {
-		null_lock_zone_res(dev);
+		if (dev->need_zone_res_mgmt) {
-		if (zone->cond == BLK_ZONE_COND_EXP_OPEN)
+			spin_lock(&dev->zone_res_lock);
-			dev->nr_zones_exp_open--;
+			if (zone->cond == BLK_ZONE_COND_EXP_OPEN)
-		else if (zone->cond == BLK_ZONE_COND_IMP_OPEN)
+				dev->nr_zones_exp_open--;
-			dev->nr_zones_imp_open--;
+			else if (zone->cond == BLK_ZONE_COND_IMP_OPEN)
+				dev->nr_zones_imp_open--;
+			spin_unlock(&dev->zone_res_lock);
+		}
 		zone->cond = BLK_ZONE_COND_FULL;
-		null_unlock_zone_res(dev);
 	}
 
 	ret = BLK_STS_OK;
 
-unlock:
+unlock_zone:
 	null_unlock_zone(dev, zone);
 
 	return ret;
@@ -454,54 +431,100 @@ static blk_status_t null_open_zone(struct nullb_device *dev,
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
-	null_lock_zone_res(dev);
-
 	switch (zone->cond) {
 	case BLK_ZONE_COND_EXP_OPEN:
-		/* open operation on exp open is not an error */
+		/* Open operation on exp open is not an error */
-		goto unlock;
+		return BLK_STS_OK;
 	case BLK_ZONE_COND_EMPTY:
-		ret = null_check_zone_resources(dev, zone);
-		if (ret != BLK_STS_OK)
-			goto unlock;
-		break;
 	case BLK_ZONE_COND_IMP_OPEN:
-		dev->nr_zones_imp_open--;
-		break;
 	case BLK_ZONE_COND_CLOSED:
-		ret = null_check_zone_resources(dev, zone);
-		if (ret != BLK_STS_OK)
-			goto unlock;
-		dev->nr_zones_closed--;
 		break;
 	case BLK_ZONE_COND_FULL:
 	default:
-		ret = BLK_STS_IOERR;
+		return BLK_STS_IOERR;
-		goto unlock;
+	}
+
+	if (dev->need_zone_res_mgmt) {
+		spin_lock(&dev->zone_res_lock);
+
+		switch (zone->cond) {
+		case BLK_ZONE_COND_EMPTY:
+			ret = null_check_zone_resources(dev, zone);
+			if (ret != BLK_STS_OK) {
+				spin_unlock(&dev->zone_res_lock);
+				return ret;
+			}
+			break;
+		case BLK_ZONE_COND_IMP_OPEN:
+			dev->nr_zones_imp_open--;
+			break;
+		case BLK_ZONE_COND_CLOSED:
+			ret = null_check_zone_resources(dev, zone);
+			if (ret != BLK_STS_OK) {
+				spin_unlock(&dev->zone_res_lock);
+				return ret;
+			}
+			dev->nr_zones_closed--;
+			break;
+		default:
+			break;
+		}
+
+		dev->nr_zones_exp_open++;
+
+		spin_unlock(&dev->zone_res_lock);
 	}
 
 	zone->cond = BLK_ZONE_COND_EXP_OPEN;
-	dev->nr_zones_exp_open++;
 
-unlock:
+	return BLK_STS_OK;
-	null_unlock_zone_res(dev);
-
-	return ret;
 }
 
 static blk_status_t null_close_zone(struct nullb_device *dev,
 				    struct nullb_zone *zone)
 {
-	blk_status_t ret;
-
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
-	null_lock_zone_res(dev);
+	switch (zone->cond) {
-	ret = __null_close_zone(dev, zone);
+	case BLK_ZONE_COND_CLOSED:
-	null_unlock_zone_res(dev);
+		/* close operation on closed is not an error */
+		return BLK_STS_OK;
+	case BLK_ZONE_COND_IMP_OPEN:
+	case BLK_ZONE_COND_EXP_OPEN:
+		break;
+	case BLK_ZONE_COND_EMPTY:
+	case BLK_ZONE_COND_FULL:
+	default:
+		return BLK_STS_IOERR;
+	}
 
-	return ret;
+	if (dev->need_zone_res_mgmt) {
+		spin_lock(&dev->zone_res_lock);
+
+		switch (zone->cond) {
+		case BLK_ZONE_COND_IMP_OPEN:
+			dev->nr_zones_imp_open--;
+			break;
+		case BLK_ZONE_COND_EXP_OPEN:
+			dev->nr_zones_exp_open--;
+			break;
+		default:
+			break;
+		}
+
+		if (zone->wp > zone->start)
+			dev->nr_zones_closed++;
+
+		spin_unlock(&dev->zone_res_lock);
+	}
+
+	if (zone->wp == zone->start)
+		zone->cond = BLK_ZONE_COND_EMPTY;
+	else
+		zone->cond = BLK_ZONE_COND_CLOSED;
+
+	return BLK_STS_OK;
 }
 
 static blk_status_t null_finish_zone(struct nullb_device *dev,
@@ -512,41 +535,47 @@ static blk_status_t null_finish_zone(struct nullb_device *dev,
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
-	null_lock_zone_res(dev);
+	if (dev->need_zone_res_mgmt) {
+		spin_lock(&dev->zone_res_lock);
 
-	switch (zone->cond) {
+		switch (zone->cond) {
-	case BLK_ZONE_COND_FULL:
+		case BLK_ZONE_COND_FULL:
-		/* finish operation on full is not an error */
+			/* Finish operation on full is not an error */
-		goto unlock;
+			spin_unlock(&dev->zone_res_lock);
-	case BLK_ZONE_COND_EMPTY:
+			return BLK_STS_OK;
-		ret = null_check_zone_resources(dev, zone);
+		case BLK_ZONE_COND_EMPTY:
-		if (ret != BLK_STS_OK)
+			ret = null_check_zone_resources(dev, zone);
-			goto unlock;
+			if (ret != BLK_STS_OK) {
-		break;
+				spin_unlock(&dev->zone_res_lock);
-	case BLK_ZONE_COND_IMP_OPEN:
+				return ret;
-		dev->nr_zones_imp_open--;
+			}
-		break;
+			break;
-	case BLK_ZONE_COND_EXP_OPEN:
+		case BLK_ZONE_COND_IMP_OPEN:
-		dev->nr_zones_exp_open--;
+			dev->nr_zones_imp_open--;
-		break;
+			break;
-	case BLK_ZONE_COND_CLOSED:
+		case BLK_ZONE_COND_EXP_OPEN:
-		ret = null_check_zone_resources(dev, zone);
+			dev->nr_zones_exp_open--;
-		if (ret != BLK_STS_OK)
+			break;
-			goto unlock;
+		case BLK_ZONE_COND_CLOSED:
-		dev->nr_zones_closed--;
+			ret = null_check_zone_resources(dev, zone);
-		break;
+			if (ret != BLK_STS_OK) {
-	default:
+				spin_unlock(&dev->zone_res_lock);
-		ret = BLK_STS_IOERR;
+				return ret;
-		goto unlock;
+			}
+			dev->nr_zones_closed--;
+			break;
+		default:
+			spin_unlock(&dev->zone_res_lock);
+			return BLK_STS_IOERR;
+		}
+
+		spin_unlock(&dev->zone_res_lock);
 	}
 
 	zone->cond = BLK_ZONE_COND_FULL;
 	zone->wp = zone->start + zone->len;
 
-unlock:
+	return BLK_STS_OK;
-	null_unlock_zone_res(dev);
-
-	return ret;
 }
 
 static blk_status_t null_reset_zone(struct nullb_device *dev,
@@ -555,34 +584,33 @@ static blk_status_t null_reset_zone(struct nullb_device *dev,
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
-	null_lock_zone_res(dev);
+	if (dev->need_zone_res_mgmt) {
+		spin_lock(&dev->zone_res_lock);
 
-	switch (zone->cond) {
+		switch (zone->cond) {
-	case BLK_ZONE_COND_EMPTY:
+		case BLK_ZONE_COND_IMP_OPEN:
-		/* reset operation on empty is not an error */
+			dev->nr_zones_imp_open--;
-		null_unlock_zone_res(dev);
+			break;
-		return BLK_STS_OK;
+		case BLK_ZONE_COND_EXP_OPEN:
-	case BLK_ZONE_COND_IMP_OPEN:
+			dev->nr_zones_exp_open--;
-		dev->nr_zones_imp_open--;
+			break;
-		break;
+		case BLK_ZONE_COND_CLOSED:
-	case BLK_ZONE_COND_EXP_OPEN:
+			dev->nr_zones_closed--;
-		dev->nr_zones_exp_open--;
+			break;
-		break;
+		case BLK_ZONE_COND_EMPTY:
-	case BLK_ZONE_COND_CLOSED:
+		case BLK_ZONE_COND_FULL:
-		dev->nr_zones_closed--;
+			break;
-		break;
+		default:
-	case BLK_ZONE_COND_FULL:
+			spin_unlock(&dev->zone_res_lock);
-		break;
+			return BLK_STS_IOERR;
-	default:
+		}
-		null_unlock_zone_res(dev);
+
-		return BLK_STS_IOERR;
+		spin_unlock(&dev->zone_res_lock);
 	}
 
 	zone->cond = BLK_ZONE_COND_EMPTY;
 	zone->wp = zone->start;
 
-	null_unlock_zone_res(dev);
-
 	if (dev->memory_backed)
 		return null_handle_discard(dev, zone->start, zone->len);
 
@@ -711,7 +739,7 @@ static void null_set_zone_cond(struct nullb_device *dev,
 		    zone->cond != BLK_ZONE_COND_OFFLINE)
 			null_finish_zone(dev, zone);
 		zone->cond = cond;
-		zone->wp = (sector_t)-1;
+		zone->wp = NULL_ZONE_INVALID_WP;
 	}
 
 	null_unlock_zone(dev, zone);

drivers/block/ublk_drv.c

@@ -221,7 +221,7 @@ static int ublk_get_nr_zones(const struct ublk_device *ub)
 
 static int ublk_revalidate_disk_zones(struct ublk_device *ub)
 {
-	return blk_revalidate_disk_zones(ub->ub_disk, NULL);
+	return blk_revalidate_disk_zones(ub->ub_disk);
 }
 
 static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
@@ -249,8 +249,7 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
-	blk_queue_required_elevator_features(ub->ub_disk->queue,
+
-					     ELEVATOR_F_ZBD_SEQ_WRITE);
 	ub->ub_disk->nr_zones = ublk_get_nr_zones(ub);
 }
 

drivers/block/virtio_blk.c

@@ -1543,7 +1543,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	 */
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && lim.zoned) {
 		blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, vblk->disk->queue);
-		err = blk_revalidate_disk_zones(vblk->disk, NULL);
+		err = blk_revalidate_disk_zones(vblk->disk);
 		if (err)
 			goto out_cleanup_disk;
 	}

drivers/md/bcache/bset.c

@@ -54,7 +54,7 @@ void bch_dump_bucket(struct btree_keys *b)
 int __bch_count_data(struct btree_keys *b)
 {
 	unsigned int ret = 0;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k;
 
 	if (b->ops->is_extents)
@@ -67,7 +67,7 @@ void __bch_check_keys(struct btree_keys *b, const char *fmt, ...)
 {
 	va_list args;
 	struct bkey *k, *p = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	const char *err;
 
 	for_each_key(b, k, &iter) {
@@ -879,7 +879,7 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	unsigned int status = BTREE_INSERT_STATUS_NO_INSERT;
 	struct bset *i = bset_tree_last(b)->data;
 	struct bkey *m, *prev = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey preceding_key_on_stack = ZERO_KEY;
 	struct bkey *preceding_key_p = &preceding_key_on_stack;
 
@@ -895,9 +895,9 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	else
 		preceding_key(k, &preceding_key_p);
 
-	m = bch_btree_iter_init(b, &iter, preceding_key_p);
+	m = bch_btree_iter_stack_init(b, &iter, preceding_key_p);
 
-	if (b->ops->insert_fixup(b, k, &iter, replace_key))
+	if (b->ops->insert_fixup(b, k, &iter.iter, replace_key))
 		return status;
 
 	status = BTREE_INSERT_STATUS_INSERT;
@@ -1100,33 +1100,33 @@ void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 				 btree_iter_cmp));
 }
 
-static struct bkey *__bch_btree_iter_init(struct btree_keys *b,
+static struct bkey *__bch_btree_iter_stack_init(struct btree_keys *b,
-					  struct btree_iter *iter,
+						struct btree_iter_stack *iter,
-					  struct bkey *search,
+						struct bkey *search,
-					  struct bset_tree *start)
+						struct bset_tree *start)
 {
 	struct bkey *ret = NULL;
 
-	iter->size = ARRAY_SIZE(iter->data);
+	iter->iter.size = ARRAY_SIZE(iter->stack_data);
-	iter->used = 0;
+	iter->iter.used = 0;
 
 #ifdef CONFIG_BCACHE_DEBUG
-	iter->b = b;
+	iter->iter.b = b;
 #endif
 
 	for (; start <= bset_tree_last(b); start++) {
 		ret = bch_bset_search(b, start, search);
-		bch_btree_iter_push(iter, ret, bset_bkey_last(start->data));
+		bch_btree_iter_push(&iter->iter, ret, bset_bkey_last(start->data));
 	}
 
 	return ret;
 }
 
-struct bkey *bch_btree_iter_init(struct btree_keys *b,
+struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
-				 struct btree_iter *iter,
+				 struct btree_iter_stack *iter,
 				 struct bkey *search)
 {
-	return __bch_btree_iter_init(b, iter, search, b->set);
+	return __bch_btree_iter_stack_init(b, iter, search, b->set);
 }
 
 static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
@@ -1293,10 +1293,10 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 			    struct bset_sort_state *state)
 {
 	size_t order = b->page_order, keys = 0;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	int oldsize = bch_count_data(b);
 
-	__bch_btree_iter_init(b, &iter, NULL, &b->set[start]);
+	__bch_btree_iter_stack_init(b, &iter, NULL, &b->set[start]);
 
 	if (start) {
 		unsigned int i;
@@ -1307,7 +1307,7 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 		order = get_order(__set_bytes(b->set->data, keys));
 	}
 
-	__btree_sort(b, &iter, start, order, false, state);
+	__btree_sort(b, &iter.iter, start, order, false, state);
 
 	EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize);
 }
@@ -1323,11 +1323,11 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new,
 			 struct bset_sort_state *state)
 {
 	uint64_t start_time = local_clock();
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
-	bch_btree_iter_init(b, &iter, NULL);
+	bch_btree_iter_stack_init(b, &iter, NULL);
 
-	btree_mergesort(b, new->set->data, &iter, false, true);
+	btree_mergesort(b, new->set->data, &iter.iter, false, true);
 
 	bch_time_stats_update(&state->time, start_time);
 

drivers/md/bcache/bset.h

@@ -321,7 +321,14 @@ struct btree_iter {
 #endif
 	struct btree_iter_set {
 		struct bkey *k, *end;
-	} data[MAX_BSETS];
+	} data[];
+};
+
+/* Fixed-size btree_iter that can be allocated on the stack */
+
+struct btree_iter_stack {
+	struct btree_iter iter;
+	struct btree_iter_set stack_data[MAX_BSETS];
 };
 
 typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k);
@@ -333,9 +340,9 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
 
 void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 			 struct bkey *end);
-struct bkey *bch_btree_iter_init(struct btree_keys *b,
+struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
-				 struct btree_iter *iter,
+				       struct btree_iter_stack *iter,
-				 struct bkey *search);
+				       struct bkey *search);
 
 struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
 			       const struct bkey *search);
@@ -350,13 +357,14 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b,
 	return search ? __bch_bset_search(b, t, search) : t->data->start;
 }
 
-#define for_each_key_filter(b, k, iter, filter)				\
+#define for_each_key_filter(b, k, stack_iter, filter)                      \
-	for (bch_btree_iter_init((b), (iter), NULL);			\
+	for (bch_btree_iter_stack_init((b), (stack_iter), NULL);           \
-	     ((k) = bch_btree_iter_next_filter((iter), (b), filter));)
+	     ((k) = bch_btree_iter_next_filter(&((stack_iter)->iter), (b), \
+					       filter));)
 
-#define for_each_key(b, k, iter)					\
+#define for_each_key(b, k, stack_iter)                           \
-	for (bch_btree_iter_init((b), (iter), NULL);			\
+	for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \
-	     ((k) = bch_btree_iter_next(iter));)
+	     ((k) = bch_btree_iter_next(&((stack_iter)->iter)));)
 
 /* Sorting */
 

drivers/md/bcache/btree.c

@@ -1309,7 +1309,7 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc)
 	uint8_t stale = 0;
 	unsigned int keys = 0, good_keys = 0;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bset_tree *t;
 
 	gc->nodes++;
@@ -1570,7 +1570,7 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op,
 static unsigned int btree_gc_count_keys(struct btree *b)
 {
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	unsigned int ret = 0;
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad)
@@ -1611,17 +1611,18 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 	int ret = 0;
 	bool should_rewrite;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct gc_merge_info r[GC_MERGE_NODES];
 	struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1;
 
-	bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done);
+	bch_btree_iter_stack_init(&b->keys, &iter, &b->c->gc_done);
 
 	for (i = r; i < r + ARRAY_SIZE(r); i++)
 		i->b = ERR_PTR(-EINTR);
 
 	while (1) {
-		k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad);
+		k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+					       bch_ptr_bad);
 		if (k) {
 			r->b = bch_btree_node_get(b->c, op, k, b->level - 1,
 						  true, b);
@@ -1911,7 +1912,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 {
 	int ret = 0;
 	struct bkey *k, *p = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid)
 		bch_initial_mark_key(b->c, b->level, k);
@@ -1919,10 +1920,10 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 	bch_initial_mark_key(b->c, b->level + 1, &b->key);
 
 	if (b->level) {
-		bch_btree_iter_init(&b->keys, &iter, NULL);
+		bch_btree_iter_stack_init(&b->keys, &iter, NULL);
 
 		do {
-			k = bch_btree_iter_next_filter(&iter, &b->keys,
+			k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
 						       bch_ptr_bad);
 			if (k) {
 				btree_node_prefetch(b, k);
@@ -1950,7 +1951,7 @@ static int bch_btree_check_thread(void *arg)
 	struct btree_check_info *info = arg;
 	struct btree_check_state *check_state = info->state;
 	struct cache_set *c = check_state->c;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k, *p;
 	int cur_idx, prev_idx, skip_nr;
 
@@ -1959,8 +1960,8 @@ static int bch_btree_check_thread(void *arg)
 	ret = 0;
 
 	/* root node keys are checked before thread created */
-	bch_btree_iter_init(&c->root->keys, &iter, NULL);
+	bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
-	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+	k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
 	BUG_ON(!k);
 
 	p = k;
@@ -1978,7 +1979,7 @@ static int bch_btree_check_thread(void *arg)
 		skip_nr = cur_idx - prev_idx;
 
 		while (skip_nr) {
-			k = bch_btree_iter_next_filter(&iter,
+			k = bch_btree_iter_next_filter(&iter.iter,
 						       &c->root->keys,
 						       bch_ptr_bad);
 			if (k)
@@ -2051,7 +2052,7 @@ int bch_btree_check(struct cache_set *c)
 	int ret = 0;
 	int i;
 	struct bkey *k = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct btree_check_state check_state;
 
 	/* check and mark root node keys */
@@ -2547,11 +2548,11 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op,
 
 	if (b->level) {
 		struct bkey *k;
-		struct btree_iter iter;
+		struct btree_iter_stack iter;
 
-		bch_btree_iter_init(&b->keys, &iter, from);
+		bch_btree_iter_stack_init(&b->keys, &iter, from);
 
-		while ((k = bch_btree_iter_next_filter(&iter, &b->keys,
+		while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
 						       bch_ptr_bad))) {
 			ret = bcache_btree(map_nodes_recurse, k, b,
 				    op, from, fn, flags);
@@ -2580,11 +2581,12 @@ int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
 {
 	int ret = MAP_CONTINUE;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
-	bch_btree_iter_init(&b->keys, &iter, from);
+	bch_btree_iter_stack_init(&b->keys, &iter, from);
 
-	while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) {
+	while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+					       bch_ptr_bad))) {
 		ret = !b->level
 			? fn(op, b, k)
 			: bcache_btree(map_keys_recurse, k,

drivers/md/bcache/super.c

@@ -881,8 +881,8 @@ static void bcache_device_free(struct bcache_device *d)
 		bcache_device_detach(d);
 
 	if (disk) {
-		ida_simple_remove(&bcache_device_idx,
+		ida_free(&bcache_device_idx,
-				  first_minor_to_idx(disk->first_minor));
+			 first_minor_to_idx(disk->first_minor));
 		put_disk(disk);
 	}
 
@@ -940,8 +940,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	if (!d->full_dirty_stripes)
 		goto out_free_stripe_sectors_dirty;
 
-	idx = ida_simple_get(&bcache_device_idx, 0,
+	idx = ida_alloc_max(&bcache_device_idx, BCACHE_DEVICE_IDX_MAX - 1,
-				BCACHE_DEVICE_IDX_MAX, GFP_KERNEL);
+			    GFP_KERNEL);
 	if (idx < 0)
 		goto out_free_full_dirty_stripes;
 
@@ -986,7 +986,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 out_bioset_exit:
 	bioset_exit(&d->bio_split);
 out_ida_remove:
-	ida_simple_remove(&bcache_device_idx, idx);
+	ida_free(&bcache_device_idx, idx);
 out_free_full_dirty_stripes:
 	kvfree(d->full_dirty_stripes);
 out_free_stripe_sectors_dirty:
@@ -1914,8 +1914,9 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	INIT_LIST_HEAD(&c->btree_cache_freed);
 	INIT_LIST_HEAD(&c->data_buckets);
 
-	iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size + 1) *
+	iter_size = sizeof(struct btree_iter) +
-		sizeof(struct btree_iter_set);
+		    ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
+			    sizeof(struct btree_iter_set);
 
 	c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL);
 	if (!c->devices)

drivers/md/bcache/sysfs.c

@@ -660,7 +660,7 @@ static unsigned int bch_root_usage(struct cache_set *c)
 	unsigned int bytes = 0;
 	struct bkey *k;
 	struct btree *b;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
 	goto lock_root;
 

drivers/md/bcache/writeback.c

@@ -908,15 +908,15 @@ static int bch_dirty_init_thread(void *arg)
 	struct dirty_init_thrd_info *info = arg;
 	struct bch_dirty_init_state *state = info->state;
 	struct cache_set *c = state->c;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k, *p;
 	int cur_idx, prev_idx, skip_nr;
 
 	k = p = NULL;
 	prev_idx = 0;
 
-	bch_btree_iter_init(&c->root->keys, &iter, NULL);
+	bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
-	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+	k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
 	BUG_ON(!k);
 
 	p = k;
@@ -930,7 +930,7 @@ static int bch_dirty_init_thread(void *arg)
 		skip_nr = cur_idx - prev_idx;
 
 		while (skip_nr) {
-			k = bch_btree_iter_next_filter(&iter,
+			k = bch_btree_iter_next_filter(&iter.iter,
 						       &c->root->keys,
 						       bch_ptr_bad);
 			if (k)
@@ -979,7 +979,7 @@ void bch_sectors_dirty_init(struct bcache_device *d)
 	int i;
 	struct btree *b = NULL;
 	struct bkey *k = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct sectors_dirty_init op;
 	struct cache_set *c = d->c;
 	struct bch_dirty_init_state state;

drivers/md/dm-bio-prison-v2.c

@@ -321,8 +321,7 @@ static bool __unlock(struct dm_bio_prison_v2 *prison,
 {
 	BUG_ON(!cell->exclusive_lock);
 
-	bio_list_merge(bios, &cell->bios);
+	bio_list_merge_init(bios, &cell->bios);
-	bio_list_init(&cell->bios);
 
 	if (cell->shared_count) {
 		cell->exclusive_lock = false;

drivers/md/dm-cache-target.c

@@ -115,8 +115,7 @@ static void __commit(struct work_struct *_ws)
 	 */
 	spin_lock_irq(&b->lock);
 	list_splice_init(&b->work_items, &work_items);
-	bio_list_merge(&bios, &b->bios);
+	bio_list_merge_init(&bios, &b->bios);
-	bio_list_init(&b->bios);
 	b->commit_scheduled = false;
 	spin_unlock_irq(&b->lock);
 
@@ -565,8 +564,7 @@ static void defer_bio(struct cache *cache, struct bio *bio)
 static void defer_bios(struct cache *cache, struct bio_list *bios)
 {
 	spin_lock_irq(&cache->lock);
-	bio_list_merge(&cache->deferred_bios, bios);
+	bio_list_merge_init(&cache->deferred_bios, bios);
-	bio_list_init(bios);
 	spin_unlock_irq(&cache->lock);
 
 	wake_deferred_bio_worker(cache);
@@ -1816,8 +1814,7 @@ static void process_deferred_bios(struct work_struct *ws)
 	bio_list_init(&bios);
 
 	spin_lock_irq(&cache->lock);
-	bio_list_merge(&bios, &cache->deferred_bios);
+	bio_list_merge_init(&bios, &cache->deferred_bios);
-	bio_list_init(&cache->deferred_bios);
 	spin_unlock_irq(&cache->lock);
 
 	while ((bio = bio_list_pop(&bios))) {
@@ -1847,8 +1844,7 @@ static void requeue_deferred_bios(struct cache *cache)
 	struct bio_list bios;
 
 	bio_list_init(&bios);
-	bio_list_merge(&bios, &cache->deferred_bios);
+	bio_list_merge_init(&bios, &cache->deferred_bios);
-	bio_list_init(&cache->deferred_bios);
 
 	while ((bio = bio_list_pop(&bios))) {
 		bio->bi_status = BLK_STS_DM_REQUEUE;

drivers/md/dm-clone-target.c

@@ -1181,8 +1181,7 @@ static void process_deferred_discards(struct clone *clone)
 	struct bio_list discards = BIO_EMPTY_LIST;
 
 	spin_lock_irq(&clone->lock);
-	bio_list_merge(&discards, &clone->deferred_discard_bios);
+	bio_list_merge_init(&discards, &clone->deferred_discard_bios);
-	bio_list_init(&clone->deferred_discard_bios);
 	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&discards))
@@ -1215,8 +1214,7 @@ static void process_deferred_bios(struct clone *clone)
 	struct bio_list bios = BIO_EMPTY_LIST;
 
 	spin_lock_irq(&clone->lock);
-	bio_list_merge(&bios, &clone->deferred_bios);
+	bio_list_merge_init(&bios, &clone->deferred_bios);
-	bio_list_init(&clone->deferred_bios);
 	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&bios))
@@ -1237,11 +1235,9 @@ static void process_deferred_flush_bios(struct clone *clone)
 	 * before issuing them or signaling their completion.
 	 */
 	spin_lock_irq(&clone->lock);
-	bio_list_merge(&bios, &clone->deferred_flush_bios);
+	bio_list_merge_init(&bios, &clone->deferred_flush_bios);
-	bio_list_init(&clone->deferred_flush_bios);
+	bio_list_merge_init(&bio_completions,
-
+			    &clone->deferred_flush_completions);
-	bio_list_merge(&bio_completions, &clone->deferred_flush_completions);
-	bio_list_init(&clone->deferred_flush_completions);
 	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) &&

drivers/md/dm-core.h

@@ -140,7 +140,7 @@ struct mapped_device {
 
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int nr_zones;
-	unsigned int *zwp_offset;
+	void *zone_revalidate_map;
 #endif
 
 #ifdef CONFIG_IMA

drivers/md/dm-era-target.c

@@ -1272,8 +1272,7 @@ static void process_deferred_bios(struct era *era)
 	bio_list_init(&marked_bios);
 
 	spin_lock(&era->deferred_lock);
-	bio_list_merge(&deferred_bios, &era->deferred_bios);
+	bio_list_merge_init(&deferred_bios, &era->deferred_bios);
-	bio_list_init(&era->deferred_bios);
 	spin_unlock(&era->deferred_lock);
 
 	if (bio_list_empty(&deferred_bios))

drivers/md/dm-mpath.c

@@ -704,8 +704,7 @@ static void process_queued_bios(struct work_struct *work)
 		return;
 	}
 
-	bio_list_merge(&bios, &m->queued_bios);
+	bio_list_merge_init(&bios, &m->queued_bios);
-	bio_list_init(&m->queued_bios);
 
 	spin_unlock_irqrestore(&m->lock, flags);
 

drivers/md/dm-table.c

@@ -2042,7 +2042,8 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 		r = dm_set_zones_restrictions(t, q);
 		if (r)
 			return r;
-		if (!static_key_enabled(&zoned_enabled.key))
+		if (blk_queue_is_zoned(q) &&
+		    !static_key_enabled(&zoned_enabled.key))
 			static_branch_enable(&zoned_enabled);
 	}
 

drivers/md/dm-thin.c

@@ -592,12 +592,6 @@ struct dm_thin_endio_hook {
 	struct dm_bio_prison_cell *cell;
 };
 
-static void __merge_bio_list(struct bio_list *bios, struct bio_list *master)
-{
-	bio_list_merge(bios, master);
-	bio_list_init(master);
-}
-
 static void error_bio_list(struct bio_list *bios, blk_status_t error)
 {
 	struct bio *bio;
@@ -616,7 +610,7 @@ static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master,
 	bio_list_init(&bios);
 
 	spin_lock_irq(&tc->lock);
-	__merge_bio_list(&bios, master);
+	bio_list_merge_init(&bios, master);
 	spin_unlock_irq(&tc->lock);
 
 	error_bio_list(&bios, error);
@@ -645,8 +639,8 @@ static void requeue_io(struct thin_c *tc)
 	bio_list_init(&bios);
 
 	spin_lock_irq(&tc->lock);
-	__merge_bio_list(&bios, &tc->deferred_bio_list);
+	bio_list_merge_init(&bios, &tc->deferred_bio_list);
-	__merge_bio_list(&bios, &tc->retry_on_resume_list);
+	bio_list_merge_init(&bios, &tc->retry_on_resume_list);
 	spin_unlock_irq(&tc->lock);
 
 	error_bio_list(&bios, BLK_STS_DM_REQUEUE);

drivers/md/dm-vdo/data-vio.c

@@ -604,8 +604,7 @@ static void assign_discard_permit(struct limiter *limiter)
 
 static void get_waiters(struct limiter *limiter)
 {
-	bio_list_merge(&limiter->waiters, &limiter->new_waiters);
+	bio_list_merge_init(&limiter->waiters, &limiter->new_waiters);
-	bio_list_init(&limiter->new_waiters);
 }
 
 static inline struct data_vio *get_available_data_vio(struct data_vio_pool *pool)

drivers/md/dm-vdo/flush.c

@@ -369,8 +369,7 @@ void vdo_dump_flusher(const struct flusher *flusher)
 static void initialize_flush(struct vdo_flush *flush, struct vdo *vdo)
 {
 	bio_list_init(&flush->bios);
-	bio_list_merge(&flush->bios, &vdo->flusher->waiting_flush_bios);
+	bio_list_merge_init(&flush->bios, &vdo->flusher->waiting_flush_bios);
-	bio_list_init(&vdo->flusher->waiting_flush_bios);
 }
 
 static void launch_flush(struct vdo_flush *flush)

drivers/md/dm-zone.c

@@ -60,16 +60,23 @@ int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 	struct dm_table *map;
 	int srcu_idx, ret;
 
-	if (dm_suspended_md(md))
+	if (!md->zone_revalidate_map) {
-		return -EAGAIN;
+		/* Regular user context */
+		if (dm_suspended_md(md))
+			return -EAGAIN;
 
-	map = dm_get_live_table(md, &srcu_idx);
+		map = dm_get_live_table(md, &srcu_idx);
-	if (!map)
+		if (!map)
-		return -EIO;
+			return -EIO;
+	} else {
+		/* Zone revalidation during __bind() */
+		map = md->zone_revalidate_map;
+	}
 
 	ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb, data);
 
-	dm_put_live_table(md, srcu_idx);
+	if (!md->zone_revalidate_map)
+		dm_put_live_table(md, srcu_idx);
 
 	return ret;
 }
@@ -138,80 +145,47 @@ bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
 	}
 }
 
-void dm_cleanup_zoned_dev(struct mapped_device *md)
+/*
+ * Count conventional zones of a mapped zoned device. If the device
+ * only has conventional zones, do not expose it as zoned.
+ */
+static int dm_check_zoned_cb(struct blk_zone *zone, unsigned int idx,
+			     void *data)
 {
-	if (md->disk) {
+	unsigned int *nr_conv_zones = data;
-		bitmap_free(md->disk->conv_zones_bitmap);
-		md->disk->conv_zones_bitmap = NULL;
-		bitmap_free(md->disk->seq_zones_wlock);
-		md->disk->seq_zones_wlock = NULL;
-	}
 
-	kvfree(md->zwp_offset);
+	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
-	md->zwp_offset = NULL;
+		(*nr_conv_zones)++;
-	md->nr_zones = 0;
+
+	return 0;
 }
 
-static unsigned int dm_get_zone_wp_offset(struct blk_zone *zone)
+static int dm_check_zoned(struct mapped_device *md, struct dm_table *t)
 {
-	switch (zone->cond) {
-	case BLK_ZONE_COND_IMP_OPEN:
-	case BLK_ZONE_COND_EXP_OPEN:
-	case BLK_ZONE_COND_CLOSED:
-		return zone->wp - zone->start;
-	case BLK_ZONE_COND_FULL:
-		return zone->len;
-	case BLK_ZONE_COND_EMPTY:
-	case BLK_ZONE_COND_NOT_WP:
-	case BLK_ZONE_COND_OFFLINE:
-	case BLK_ZONE_COND_READONLY:
-	default:
-		/*
-		 * Conventional, offline and read-only zones do not have a valid
-		 * write pointer. Use 0 as for an empty zone.
-		 */
-		return 0;
-	}
-}
-
-static int dm_zone_revalidate_cb(struct blk_zone *zone, unsigned int idx,
-				 void *data)
-{
-	struct mapped_device *md = data;
 	struct gendisk *disk = md->disk;
+	unsigned int nr_conv_zones = 0;
+	int ret;
 
-	switch (zone->type) {
+	/* Count conventional zones */
-	case BLK_ZONE_TYPE_CONVENTIONAL:
+	md->zone_revalidate_map = t;
-		if (!disk->conv_zones_bitmap) {
+	ret = dm_blk_report_zones(disk, 0, UINT_MAX,
-			disk->conv_zones_bitmap = bitmap_zalloc(disk->nr_zones,
+				  dm_check_zoned_cb, &nr_conv_zones);
-								GFP_NOIO);
+	md->zone_revalidate_map = NULL;
-			if (!disk->conv_zones_bitmap)
+	if (ret < 0) {
-				return -ENOMEM;
+		DMERR("Check zoned failed %d", ret);
-		}
+		return ret;
-		set_bit(idx, disk->conv_zones_bitmap);
+	}
-		break;
-	case BLK_ZONE_TYPE_SEQWRITE_REQ:
-	case BLK_ZONE_TYPE_SEQWRITE_PREF:
-		if (!disk->seq_zones_wlock) {
-			disk->seq_zones_wlock = bitmap_zalloc(disk->nr_zones,
-							      GFP_NOIO);
-			if (!disk->seq_zones_wlock)
-				return -ENOMEM;
-		}
-		if (!md->zwp_offset) {
-			md->zwp_offset =
-				kvcalloc(disk->nr_zones, sizeof(unsigned int),
-					 GFP_KERNEL);
-			if (!md->zwp_offset)
-				return -ENOMEM;
-		}
-		md->zwp_offset[idx] = dm_get_zone_wp_offset(zone);
 
-		break;
+	/*
-	default:
+	 * If we only have conventional zones, expose the mapped device as
-		DMERR("Invalid zone type 0x%x at sectors %llu",
+	 * a regular device.
-		      (int)zone->type, zone->start);
+	 */
-		return -ENODEV;
+	if (nr_conv_zones >= ret) {
+		disk->queue->limits.max_open_zones = 0;
+		disk->queue->limits.max_active_zones = 0;
+		disk->queue->limits.zoned = false;
+		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
+		disk->nr_zones = 0;
 	}
 
 	return 0;
@@ -226,41 +200,32 @@ static int dm_zone_revalidate_cb(struct blk_zone *zone, unsigned int idx,
 static int dm_revalidate_zones(struct mapped_device *md, struct dm_table *t)
 {
 	struct gendisk *disk = md->disk;
-	unsigned int noio_flag;
 	int ret;
 
-	/*
+	/* Revalidate only if something changed. */
-	 * Check if something changed. If yes, cleanup the current resources
-	 * and reallocate everything.
-	 */
 	if (!disk->nr_zones || disk->nr_zones != md->nr_zones)
-		dm_cleanup_zoned_dev(md);
+		md->nr_zones = 0;
+
 	if (md->nr_zones)
 		return 0;
 
 	/*
-	 * Scan all zones to initialize everything. Ensure that all vmalloc
+	 * Our table is not live yet. So the call to dm_get_live_table()
-	 * operations in this context are done as if GFP_NOIO was specified.
+	 * in dm_blk_report_zones() will fail. Set a temporary pointer to
+	 * our table for dm_blk_report_zones() to use directly.
 	 */
-	noio_flag = memalloc_noio_save();
+	md->zone_revalidate_map = t;
-	ret = dm_blk_do_report_zones(md, t, 0, disk->nr_zones,
+	ret = blk_revalidate_disk_zones(disk);
-				     dm_zone_revalidate_cb, md);
+	md->zone_revalidate_map = NULL;
-	memalloc_noio_restore(noio_flag);
+
-	if (ret < 0)
+	if (ret) {
-		goto err;
+		DMERR("Revalidate zones failed %d", ret);
-	if (ret != disk->nr_zones) {
+		return ret;
-		ret = -EIO;
-		goto err;
 	}
 
 	md->nr_zones = disk->nr_zones;
 
 	return 0;
-
-err:
-	DMERR("Revalidate zones failed %d", ret);
-	dm_cleanup_zoned_dev(md);
-	return ret;
 }
 
 static int device_not_zone_append_capable(struct dm_target *ti,
@@ -289,296 +254,42 @@ static bool dm_table_supports_zone_append(struct dm_table *t)
 int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q)
 {
 	struct mapped_device *md = t->md;
+	int ret;
 
 	/*
-	 * For a zoned target, the number of zones should be updated for the
+	 * Check if zone append is natively supported, and if not, set the
-	 * correct value to be exposed in sysfs queue/nr_zones.
+	 * mapped device queue as needing zone append emulation.
 	 */
 	WARN_ON_ONCE(queue_is_mq(q));
-	md->disk->nr_zones = bdev_nr_zones(md->disk->part0);
-
-	/* Check if zone append is natively supported */
 	if (dm_table_supports_zone_append(t)) {
 		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
-		dm_cleanup_zoned_dev(md);
+	} else {
-		return 0;
+		set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
+		blk_queue_max_zone_append_sectors(q, 0);
 	}
 
-	/*
-	 * Mark the mapped device as needing zone append emulation and
-	 * initialize the emulation resources once the capacity is set.
-	 */
-	set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
 	if (!get_capacity(md->disk))
 		return 0;
 
+	/*
+	 * Check that the mapped device will indeed be zoned, that is, that it
+	 * has sequential write required zones.
+	 */
+	ret = dm_check_zoned(md, t);
+	if (ret)
+		return ret;
+	if (!blk_queue_is_zoned(q))
+		return 0;
+
+	if (!md->disk->nr_zones) {
+		DMINFO("%s using %s zone append",
+		       md->disk->disk_name,
+		       queue_emulates_zone_append(q) ? "emulated" : "native");
+	}
+
 	return dm_revalidate_zones(md, t);
 }
 
-static int dm_update_zone_wp_offset_cb(struct blk_zone *zone, unsigned int idx,
-				       void *data)
-{
-	unsigned int *wp_offset = data;
-
-	*wp_offset = dm_get_zone_wp_offset(zone);
-
-	return 0;
-}
-
-static int dm_update_zone_wp_offset(struct mapped_device *md, unsigned int zno,
-				    unsigned int *wp_ofst)
-{
-	sector_t sector = zno * bdev_zone_sectors(md->disk->part0);
-	unsigned int noio_flag;
-	struct dm_table *t;
-	int srcu_idx, ret;
-
-	t = dm_get_live_table(md, &srcu_idx);
-	if (!t)
-		return -EIO;
-
-	/*
-	 * Ensure that all memory allocations in this context are done as if
-	 * GFP_NOIO was specified.
-	 */
-	noio_flag = memalloc_noio_save();
-	ret = dm_blk_do_report_zones(md, t, sector, 1,
-				     dm_update_zone_wp_offset_cb, wp_ofst);
-	memalloc_noio_restore(noio_flag);
-
-	dm_put_live_table(md, srcu_idx);
-
-	if (ret != 1)
-		return -EIO;
-
-	return 0;
-}
-
-struct orig_bio_details {
-	enum req_op op;
-	unsigned int nr_sectors;
-};
-
-/*
- * First phase of BIO mapping for targets with zone append emulation:
- * check all BIO that change a zone writer pointer and change zone
- * append operations into regular write operations.
- */
-static bool dm_zone_map_bio_begin(struct mapped_device *md,
-				  unsigned int zno, struct bio *clone)
-{
-	sector_t zsectors = bdev_zone_sectors(md->disk->part0);
-	unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]);
-
-	/*
-	 * If the target zone is in an error state, recover by inspecting the
-	 * zone to get its current write pointer position. Note that since the
-	 * target zone is already locked, a BIO issuing context should never
-	 * see the zone write in the DM_ZONE_UPDATING_WP_OFST state.
-	 */
-	if (zwp_offset == DM_ZONE_INVALID_WP_OFST) {
-		if (dm_update_zone_wp_offset(md, zno, &zwp_offset))
-			return false;
-		WRITE_ONCE(md->zwp_offset[zno], zwp_offset);
-	}
-
-	switch (bio_op(clone)) {
-	case REQ_OP_ZONE_RESET:
-	case REQ_OP_ZONE_FINISH:
-		return true;
-	case REQ_OP_WRITE_ZEROES:
-	case REQ_OP_WRITE:
-		/* Writes must be aligned to the zone write pointer */
-		if ((clone->bi_iter.bi_sector & (zsectors - 1)) != zwp_offset)
-			return false;
-		break;
-	case REQ_OP_ZONE_APPEND:
-		/*
-		 * Change zone append operations into a non-mergeable regular
-		 * writes directed at the current write pointer position of the
-		 * target zone.
-		 */
-		clone->bi_opf = REQ_OP_WRITE | REQ_NOMERGE |
-			(clone->bi_opf & (~REQ_OP_MASK));
-		clone->bi_iter.bi_sector += zwp_offset;
-		break;
-	default:
-		DMWARN_LIMIT("Invalid BIO operation");
-		return false;
-	}
-
-	/* Cannot write to a full zone */
-	if (zwp_offset >= zsectors)
-		return false;
-
-	return true;
-}
-
-/*
- * Second phase of BIO mapping for targets with zone append emulation:
- * update the zone write pointer offset array to account for the additional
- * data written to a zone. Note that at this point, the remapped clone BIO
- * may already have completed, so we do not touch it.
- */
-static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, unsigned int zno,
-					struct orig_bio_details *orig_bio_details,
-					unsigned int nr_sectors)
-{
-	unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]);
-
-	/* The clone BIO may already have been completed and failed */
-	if (zwp_offset == DM_ZONE_INVALID_WP_OFST)
-		return BLK_STS_IOERR;
-
-	/* Update the zone wp offset */
-	switch (orig_bio_details->op) {
-	case REQ_OP_ZONE_RESET:
-		WRITE_ONCE(md->zwp_offset[zno], 0);
-		return BLK_STS_OK;
-	case REQ_OP_ZONE_FINISH:
-		WRITE_ONCE(md->zwp_offset[zno],
-			   bdev_zone_sectors(md->disk->part0));
-		return BLK_STS_OK;
-	case REQ_OP_WRITE_ZEROES:
-	case REQ_OP_WRITE:
-		WRITE_ONCE(md->zwp_offset[zno], zwp_offset + nr_sectors);
-		return BLK_STS_OK;
-	case REQ_OP_ZONE_APPEND:
-		/*
-		 * Check that the target did not truncate the write operation
-		 * emulating a zone append.
-		 */
-		if (nr_sectors != orig_bio_details->nr_sectors) {
-			DMWARN_LIMIT("Truncated write for zone append");
-			return BLK_STS_IOERR;
-		}
-		WRITE_ONCE(md->zwp_offset[zno], zwp_offset + nr_sectors);
-		return BLK_STS_OK;
-	default:
-		DMWARN_LIMIT("Invalid BIO operation");
-		return BLK_STS_IOERR;
-	}
-}
-
-static inline void dm_zone_lock(struct gendisk *disk, unsigned int zno,
-				struct bio *clone)
-{
-	if (WARN_ON_ONCE(bio_flagged(clone, BIO_ZONE_WRITE_LOCKED)))
-		return;
-
-	wait_on_bit_lock_io(disk->seq_zones_wlock, zno, TASK_UNINTERRUPTIBLE);
-	bio_set_flag(clone, BIO_ZONE_WRITE_LOCKED);
-}
-
-static inline void dm_zone_unlock(struct gendisk *disk, unsigned int zno,
-				  struct bio *clone)
-{
-	if (!bio_flagged(clone, BIO_ZONE_WRITE_LOCKED))
-		return;
-
-	WARN_ON_ONCE(!test_bit(zno, disk->seq_zones_wlock));
-	clear_bit_unlock(zno, disk->seq_zones_wlock);
-	smp_mb__after_atomic();
-	wake_up_bit(disk->seq_zones_wlock, zno);
-
-	bio_clear_flag(clone, BIO_ZONE_WRITE_LOCKED);
-}
-
-static bool dm_need_zone_wp_tracking(struct bio *bio)
-{
-	/*
-	 * Special processing is not needed for operations that do not need the
-	 * zone write lock, that is, all operations that target conventional
-	 * zones and all operations that do not modify directly a sequential
-	 * zone write pointer.
-	 */
-	if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
-		return false;
-	switch (bio_op(bio)) {
-	case REQ_OP_WRITE_ZEROES:
-	case REQ_OP_WRITE:
-	case REQ_OP_ZONE_RESET:
-	case REQ_OP_ZONE_FINISH:
-	case REQ_OP_ZONE_APPEND:
-		return bio_zone_is_seq(bio);
-	default:
-		return false;
-	}
-}
-
-/*
- * Special IO mapping for targets needing zone append emulation.
- */
-int dm_zone_map_bio(struct dm_target_io *tio)
-{
-	struct dm_io *io = tio->io;
-	struct dm_target *ti = tio->ti;
-	struct mapped_device *md = io->md;
-	struct bio *clone = &tio->clone;
-	struct orig_bio_details orig_bio_details;
-	unsigned int zno;
-	blk_status_t sts;
-	int r;
-
-	/*
-	 * IOs that do not change a zone write pointer do not need
-	 * any additional special processing.
-	 */
-	if (!dm_need_zone_wp_tracking(clone))
-		return ti->type->map(ti, clone);
-
-	/* Lock the target zone */
-	zno = bio_zone_no(clone);
-	dm_zone_lock(md->disk, zno, clone);
-
-	orig_bio_details.nr_sectors = bio_sectors(clone);
-	orig_bio_details.op = bio_op(clone);
-
-	/*
-	 * Check that the bio and the target zone write pointer offset are
-	 * both valid, and if the bio is a zone append, remap it to a write.
-	 */
-	if (!dm_zone_map_bio_begin(md, zno, clone)) {
-		dm_zone_unlock(md->disk, zno, clone);
-		return DM_MAPIO_KILL;
-	}
-
-	/* Let the target do its work */
-	r = ti->type->map(ti, clone);
-	switch (r) {
-	case DM_MAPIO_SUBMITTED:
-		/*
-		 * The target submitted the clone BIO. The target zone will
-		 * be unlocked on completion of the clone.
-		 */
-		sts = dm_zone_map_bio_end(md, zno, &orig_bio_details,
-					  *tio->len_ptr);
-		break;
-	case DM_MAPIO_REMAPPED:
-		/*
-		 * The target only remapped the clone BIO. In case of error,
-		 * unlock the target zone here as the clone will not be
-		 * submitted.
-		 */
-		sts = dm_zone_map_bio_end(md, zno, &orig_bio_details,
-					  *tio->len_ptr);
-		if (sts != BLK_STS_OK)
-			dm_zone_unlock(md->disk, zno, clone);
-		break;
-	case DM_MAPIO_REQUEUE:
-	case DM_MAPIO_KILL:
-	default:
-		dm_zone_unlock(md->disk, zno, clone);
-		sts = BLK_STS_IOERR;
-		break;
-	}
-
-	if (sts != BLK_STS_OK)
-		return DM_MAPIO_KILL;
-
-	return r;
-}
-
 /*
  * IO completion callback called from clone_endio().
  */
@@ -587,61 +298,17 @@ void dm_zone_endio(struct dm_io *io, struct bio *clone)
 	struct mapped_device *md = io->md;
 	struct gendisk *disk = md->disk;
 	struct bio *orig_bio = io->orig_bio;
-	unsigned int zwp_offset;
-	unsigned int zno;
 
 	/*
-	 * For targets that do not emulate zone append, we only need to
+	 * Get the offset within the zone of the written sector
-	 * handle native zone-append bios.
+	 * and add that to the original bio sector position.
 	 */
-	if (!dm_emulate_zone_append(md)) {
+	if (clone->bi_status == BLK_STS_OK &&
-		/*
+	    bio_op(clone) == REQ_OP_ZONE_APPEND) {
-		 * Get the offset within the zone of the written sector
+		sector_t mask = bdev_zone_sectors(disk->part0) - 1;
-		 * and add that to the original bio sector position.
-		 */
-		if (clone->bi_status == BLK_STS_OK &&
-		    bio_op(clone) == REQ_OP_ZONE_APPEND) {
-			sector_t mask =
-				(sector_t)bdev_zone_sectors(disk->part0) - 1;
 
-			orig_bio->bi_iter.bi_sector +=
+		orig_bio->bi_iter.bi_sector += clone->bi_iter.bi_sector & mask;
-				clone->bi_iter.bi_sector & mask;
-		}
-
-		return;
 	}
 
-	/*
+	return;
-	 * For targets that do emulate zone append, if the clone BIO does not
-	 * own the target zone write lock, we have nothing to do.
-	 */
-	if (!bio_flagged(clone, BIO_ZONE_WRITE_LOCKED))
-		return;
-
-	zno = bio_zone_no(orig_bio);
-
-	if (clone->bi_status != BLK_STS_OK) {
-		/*
-		 * BIOs that modify a zone write pointer may leave the zone
-		 * in an unknown state in case of failure (e.g. the write
-		 * pointer was only partially advanced). In this case, set
-		 * the target zone write pointer as invalid unless it is
-		 * already being updated.
-		 */
-		WRITE_ONCE(md->zwp_offset[zno], DM_ZONE_INVALID_WP_OFST);
-	} else if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) {
-		/*
-		 * Get the written sector for zone append operation that were
-		 * emulated using regular write operations.
-		 */
-		zwp_offset = READ_ONCE(md->zwp_offset[zno]);
-		if (WARN_ON_ONCE(zwp_offset < bio_sectors(orig_bio)))
-			WRITE_ONCE(md->zwp_offset[zno],
-				   DM_ZONE_INVALID_WP_OFST);
-		else
-			orig_bio->bi_iter.bi_sector +=
-				zwp_offset - bio_sectors(orig_bio);
-	}
-
-	dm_zone_unlock(disk, zno, clone);
 }

drivers/md/dm.c

@@ -1428,25 +1428,12 @@ static void __map_bio(struct bio *clone)
 		down(&md->swap_bios_semaphore);
 	}
 
-	if (static_branch_unlikely(&zoned_enabled)) {
+	if (likely(ti->type->map == linear_map))
-		/*
+		r = linear_map(ti, clone);
-		 * Check if the IO needs a special mapping due to zone append
+	else if (ti->type->map == stripe_map)
-		 * emulation on zoned target. In this case, dm_zone_map_bio()
+		r = stripe_map(ti, clone);
-		 * calls the target map operation.
+	else
-		 */
+		r = ti->type->map(ti, clone);
-		if (unlikely(dm_emulate_zone_append(md)))
-			r = dm_zone_map_bio(tio);
-		else
-			goto do_map;
-	} else {
-do_map:
-		if (likely(ti->type->map == linear_map))
-			r = linear_map(ti, clone);
-		else if (ti->type->map == stripe_map)
-			r = stripe_map(ti, clone);
-		else
-			r = ti->type->map(ti, clone);
-	}
 
 	switch (r) {
 	case DM_MAPIO_SUBMITTED:
@@ -1774,6 +1761,33 @@ static void init_clone_info(struct clone_info *ci, struct dm_io *io,
 		ci->sector_count = 0;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
+					   struct bio *bio)
+{
+	/*
+	 * For mapped device that need zone append emulation, we must
+	 * split any large BIO that straddles zone boundaries.
+	 */
+	return dm_emulate_zone_append(md) && bio_straddles_zones(bio) &&
+		!bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING);
+}
+static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
+{
+	return dm_emulate_zone_append(md) && blk_zone_plug_bio(bio, 0);
+}
+#else
+static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
+					   struct bio *bio)
+{
+	return false;
+}
+static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
+{
+	return false;
+}
+#endif
+
 /*
  * Entry point to split a bio into clones and submit them to the targets.
  */
@@ -1783,19 +1797,32 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 	struct clone_info ci;
 	struct dm_io *io;
 	blk_status_t error = BLK_STS_OK;
-	bool is_abnormal;
+	bool is_abnormal, need_split;
 
-	is_abnormal = is_abnormal_io(bio);
+	need_split = is_abnormal = is_abnormal_io(bio);
-	if (unlikely(is_abnormal)) {
+	if (static_branch_unlikely(&zoned_enabled))
+		need_split = is_abnormal || dm_zone_bio_needs_split(md, bio);
+
+	if (unlikely(need_split)) {
 		/*
 		 * Use bio_split_to_limits() for abnormal IO (e.g. discard, etc)
 		 * otherwise associated queue_limits won't be imposed.
+		 * Also split the BIO for mapped devices needing zone append
+		 * emulation to ensure that the BIO does not cross zone
+		 * boundaries.
 		 */
 		bio = bio_split_to_limits(bio);
 		if (!bio)
 			return;
 	}
 
+	/*
+	 * Use the block layer zone write plugging for mapped devices that
+	 * need zone append emulation (e.g. dm-crypt).
+	 */
+	if (static_branch_unlikely(&zoned_enabled) && dm_zone_plug_bio(md, bio))
+		return;
+
 	/* Only support nowait for normal IO */
 	if (unlikely(bio->bi_opf & REQ_NOWAIT) && !is_abnormal) {
 		io = alloc_io(md, bio, GFP_NOWAIT);
@@ -2016,7 +2043,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
 		md->dax_dev = NULL;
 	}
 
-	dm_cleanup_zoned_dev(md);
 	if (md->disk) {
 		spin_lock(&_minor_lock);
 		md->disk->private_data = NULL;

drivers/md/dm.h

@@ -104,13 +104,11 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
 int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q);
 void dm_zone_endio(struct dm_io *io, struct bio *clone);
 #ifdef CONFIG_BLK_DEV_ZONED
-void dm_cleanup_zoned_dev(struct mapped_device *md);
 int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data);
 bool dm_is_zone_write(struct mapped_device *md, struct bio *bio);
 int dm_zone_map_bio(struct dm_target_io *io);
 #else
-static inline void dm_cleanup_zoned_dev(struct mapped_device *md) {}
 #define dm_blk_report_zones	NULL
 static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
 {

drivers/md/md-bitmap.c

@@ -1424,7 +1424,7 @@ __acquires(bitmap->lock)
 	sector_t chunk = offset >> bitmap->chunkshift;
 	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
 	unsigned long pageoff = (chunk & PAGE_COUNTER_MASK) << COUNTER_BYTE_SHIFT;
-	sector_t csize;
+	sector_t csize = ((sector_t)1) << bitmap->chunkshift;
 	int err;
 
 	if (page >= bitmap->pages) {
@@ -1433,6 +1433,7 @@ __acquires(bitmap->lock)
 		 * End-of-device while looking for a whole page or
 		 * user set a huge number to sysfs bitmap_set_bits.
 		 */
+		*blocks = csize - (offset & (csize - 1));
 		return NULL;
 	}
 	err = md_bitmap_checkpage(bitmap, page, create, 0);
@@ -1441,8 +1442,7 @@ __acquires(bitmap->lock)
 	    bitmap->bp[page].map == NULL)
 		csize = ((sector_t)1) << (bitmap->chunkshift +
 					  PAGE_COUNTER_SHIFT);
-	else
+
-		csize = ((sector_t)1) << bitmap->chunkshift;
 	*blocks = csize - (offset & (csize - 1));
 
 	if (err < 0)

drivers/md/md.c

@@ -8087,7 +8087,8 @@ void md_wakeup_thread(struct md_thread __rcu *thread)
 	if (t) {
 		pr_debug("md: waking up MD thread %s.\n", t->tsk->comm);
 		set_bit(THREAD_WAKEUP, &t->flags);
-		wake_up(&t->wqueue);
+		if (wq_has_sleeper(&t->wqueue))
+			wake_up(&t->wqueue);
 	}
 	rcu_read_unlock();
 }
@@ -8582,6 +8583,10 @@ static int is_mddev_idle(struct mddev *mddev, int init)
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_disk;
+
+		if (!init && !blk_queue_io_stat(disk->queue))
+			continue;
+
 		curr_events = (int)part_stat_read_accum(disk->part0, sectors) -
 			      atomic_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats

drivers/md/md.h

@@ -621,7 +621,8 @@ extern void mddev_unlock(struct mddev *mddev);
 
 static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors)
 {
-	atomic_add(nr_sectors, &bdev->bd_disk->sync_io);
+	if (blk_queue_io_stat(bdev->bd_disk->queue))
+		atomic_add(nr_sectors, &bdev->bd_disk->sync_io);
 }
 
 static inline void md_sync_acct_bio(struct bio *bio, unsigned long nr_sectors)

drivers/md/raid5.c

@@ -36,7 +36,6 @@
  */
 
 #include <linux/blkdev.h>
-#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
@@ -6734,6 +6733,9 @@ static void raid5d(struct md_thread *thread)
 		int batch_size, released;
 		unsigned int offset;
 
+		if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
+			break;
+
 		released = release_stripe_list(conf, conf->temp_inactive_list);
 		if (released)
 			clear_bit(R5_DID_ALLOC, &conf->cache_state);
@@ -6770,18 +6772,7 @@ static void raid5d(struct md_thread *thread)
 			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
 			spin_lock_irq(&conf->device_lock);
-
-			/*
-			 * Waiting on MD_SB_CHANGE_PENDING below may deadlock
-			 * seeing md_check_recovery() is needed to clear
-			 * the flag when using mdmon.
-			 */
-			continue;
 		}
-
-		wait_event_lock_irq(mddev->sb_wait,
-			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
-			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);
 

drivers/nvme/host/core.c

@@ -2132,7 +2132,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
 	if (blk_queue_is_zoned(ns->queue)) {
-		ret = blk_revalidate_disk_zones(ns->disk, NULL);
+		ret = blk_revalidate_disk_zones(ns->disk);
 		if (ret && !nvme_first_scan(ns->disk))
 			goto out;
 	}

drivers/nvme/target/zns.c

@@ -52,14 +52,10 @@ bool nvmet_bdev_zns_enable(struct nvmet_ns *ns)
 	if (get_capacity(bd_disk) & (bdev_zone_sectors(ns->bdev) - 1))
 		return false;
 	/*
-	 * ZNS does not define a conventional zone type. If the underlying
+	 * ZNS does not define a conventional zone type. Use report zones
-	 * device has a bitmap set indicating the existence of conventional
+	 * to detect if the device has conventional zones and reject it if
-	 * zones, reject the device. Otherwise, use report zones to detect if
+	 * it does.
-	 * the device has conventional zones.
 	 */
-	if (ns->bdev->bd_disk->conv_zones_bitmap)
-		return false;
-
 	ret = blkdev_report_zones(ns->bdev, 0, bdev_nr_zones(ns->bdev),
 				  validate_conv_zones_cb, NULL);
 	if (ret < 0)

drivers/scsi/scsi_lib.c

@@ -1869,7 +1869,6 @@ out_put_budget:
 	case BLK_STS_OK:
 		break;
 	case BLK_STS_RESOURCE:
-	case BLK_STS_ZONE_RESOURCE:
 		if (scsi_device_blocked(sdev))
 			ret = BLK_STS_DEV_RESOURCE;
 		break;

drivers/scsi/sd.c

@@ -1260,12 +1260,6 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 		}
 	}
 
-	if (req_op(rq) == REQ_OP_ZONE_APPEND) {
-		ret = sd_zbc_prepare_zone_append(cmd, &lba, nr_blocks);
-		if (ret)
-			goto fail;
-	}
-
 	fua = rq->cmd_flags & REQ_FUA ? 0x8 : 0;
 	dix = scsi_prot_sg_count(cmd);
 	dif = scsi_host_dif_capable(cmd->device->host, sdkp->protection_type);
@@ -1348,7 +1342,6 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
 		return sd_setup_flush_cmnd(cmd);
 	case REQ_OP_READ:
 	case REQ_OP_WRITE:
-	case REQ_OP_ZONE_APPEND:
 		return sd_setup_read_write_cmnd(cmd);
 	case REQ_OP_ZONE_RESET:
 		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER,
@@ -3981,7 +3974,6 @@ static void scsi_disk_release(struct device *dev)
 	struct scsi_disk *sdkp = to_scsi_disk(dev);
 
 	ida_free(&sd_index_ida, sdkp->index);
-	sd_zbc_free_zone_info(sdkp);
 	put_device(&sdkp->device->sdev_gendev);
 	free_opal_dev(sdkp->opal_dev);
 

drivers/scsi/sd.h

@@ -104,12 +104,6 @@ struct scsi_disk {
 	 * between zone starting LBAs is constant.
 	 */
 	u32		zone_starting_lba_gran;
-	u32		*zones_wp_offset;
-	spinlock_t	zones_wp_offset_lock;
-	u32		*rev_wp_offset;
-	struct mutex	rev_mutex;
-	struct work_struct zone_wp_offset_work;
-	char		*zone_wp_update_buf;
 #endif
 	atomic_t	openers;
 	sector_t	capacity;	/* size in logical blocks */
@@ -245,7 +239,6 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp)
 
 #ifdef CONFIG_BLK_DEV_ZONED
 
-void sd_zbc_free_zone_info(struct scsi_disk *sdkp);
 int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE]);
 int sd_zbc_revalidate_zones(struct scsi_disk *sdkp);
 blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
@@ -255,13 +248,8 @@ unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data);
 
-blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
-				        unsigned int nr_blocks);
-
 #else /* CONFIG_BLK_DEV_ZONED */
 
-static inline void sd_zbc_free_zone_info(struct scsi_disk *sdkp) {}
-
 static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE])
 {
 	return 0;
@@ -285,13 +273,6 @@ static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd,
 	return good_bytes;
 }
 
-static inline blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd,
-						      sector_t *lba,
-						      unsigned int nr_blocks)
-{
-	return BLK_STS_TARGET;
-}
-
 #define sd_zbc_report_zones NULL
 
 #endif /* CONFIG_BLK_DEV_ZONED */

drivers/scsi/sd_zbc.c

@@ -23,36 +23,6 @@
 #define CREATE_TRACE_POINTS
 #include "sd_trace.h"
 
-/**
- * sd_zbc_get_zone_wp_offset - Get zone write pointer offset.
- * @zone: Zone for which to return the write pointer offset.
- *
- * Return: offset of the write pointer from the start of the zone.
- */
-static unsigned int sd_zbc_get_zone_wp_offset(struct blk_zone *zone)
-{
-	if (zone->type == ZBC_ZONE_TYPE_CONV)
-		return 0;
-
-	switch (zone->cond) {
-	case BLK_ZONE_COND_IMP_OPEN:
-	case BLK_ZONE_COND_EXP_OPEN:
-	case BLK_ZONE_COND_CLOSED:
-		return zone->wp - zone->start;
-	case BLK_ZONE_COND_FULL:
-		return zone->len;
-	case BLK_ZONE_COND_EMPTY:
-	case BLK_ZONE_COND_OFFLINE:
-	case BLK_ZONE_COND_READONLY:
-	default:
-		/*
-		 * Offline and read-only zones do not have a valid
-		 * write pointer. Use 0 as for an empty zone.
-		 */
-		return 0;
-	}
-}
-
 /* Whether or not a SCSI zone descriptor describes a gap zone. */
 static bool sd_zbc_is_gap_zone(const u8 buf[64])
 {
@@ -121,9 +91,6 @@ static int sd_zbc_parse_report(struct scsi_disk *sdkp, const u8 buf[64],
 	if (ret)
 		return ret;
 
-	if (sdkp->rev_wp_offset)
-		sdkp->rev_wp_offset[idx] = sd_zbc_get_zone_wp_offset(&zone);
-
 	return 0;
 }
 
@@ -347,123 +314,6 @@ static blk_status_t sd_zbc_cmnd_checks(struct scsi_cmnd *cmd)
 	return BLK_STS_OK;
 }
 
-#define SD_ZBC_INVALID_WP_OFST	(~0u)
-#define SD_ZBC_UPDATING_WP_OFST	(SD_ZBC_INVALID_WP_OFST - 1)
-
-static int sd_zbc_update_wp_offset_cb(struct blk_zone *zone, unsigned int idx,
-				    void *data)
-{
-	struct scsi_disk *sdkp = data;
-
-	lockdep_assert_held(&sdkp->zones_wp_offset_lock);
-
-	sdkp->zones_wp_offset[idx] = sd_zbc_get_zone_wp_offset(zone);
-
-	return 0;
-}
-
-/*
- * An attempt to append a zone triggered an invalid write pointer error.
- * Reread the write pointer of the zone(s) in which the append failed.
- */
-static void sd_zbc_update_wp_offset_workfn(struct work_struct *work)
-{
-	struct scsi_disk *sdkp;
-	unsigned long flags;
-	sector_t zno;
-	int ret;
-
-	sdkp = container_of(work, struct scsi_disk, zone_wp_offset_work);
-
-	spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
-	for (zno = 0; zno < sdkp->zone_info.nr_zones; zno++) {
-		if (sdkp->zones_wp_offset[zno] != SD_ZBC_UPDATING_WP_OFST)
-			continue;
-
-		spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
-		ret = sd_zbc_do_report_zones(sdkp, sdkp->zone_wp_update_buf,
-					     SD_BUF_SIZE,
-					     zno * sdkp->zone_info.zone_blocks, true);
-		spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
-		if (!ret)
-			sd_zbc_parse_report(sdkp, sdkp->zone_wp_update_buf + 64,
-					    zno, sd_zbc_update_wp_offset_cb,
-					    sdkp);
-	}
-	spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
-
-	scsi_device_put(sdkp->device);
-}
-
-/**
- * sd_zbc_prepare_zone_append() - Prepare an emulated ZONE_APPEND command.
- * @cmd: the command to setup
- * @lba: the LBA to patch
- * @nr_blocks: the number of LBAs to be written
- *
- * Called from sd_setup_read_write_cmnd() for REQ_OP_ZONE_APPEND.
- * @sd_zbc_prepare_zone_append() handles the necessary zone wrote locking and
- * patching of the lba for an emulated ZONE_APPEND command.
- *
- * In case the cached write pointer offset is %SD_ZBC_INVALID_WP_OFST it will
- * schedule a REPORT ZONES command and return BLK_STS_IOERR.
- */
-blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
-					unsigned int nr_blocks)
-{
-	struct request *rq = scsi_cmd_to_rq(cmd);
-	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
-	unsigned int wp_offset, zno = blk_rq_zone_no(rq);
-	unsigned long flags;
-	blk_status_t ret;
-
-	ret = sd_zbc_cmnd_checks(cmd);
-	if (ret != BLK_STS_OK)
-		return ret;
-
-	if (!blk_rq_zone_is_seq(rq))
-		return BLK_STS_IOERR;
-
-	/* Unlock of the write lock will happen in sd_zbc_complete() */
-	if (!blk_req_zone_write_trylock(rq))
-		return BLK_STS_ZONE_RESOURCE;
-
-	spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
-	wp_offset = sdkp->zones_wp_offset[zno];
-	switch (wp_offset) {
-	case SD_ZBC_INVALID_WP_OFST:
-		/*
-		 * We are about to schedule work to update a zone write pointer
-		 * offset, which will cause the zone append command to be
-		 * requeued. So make sure that the scsi device does not go away
-		 * while the work is being processed.
-		 */
-		if (scsi_device_get(sdkp->device)) {
-			ret = BLK_STS_IOERR;
-			break;
-		}
-		sdkp->zones_wp_offset[zno] = SD_ZBC_UPDATING_WP_OFST;
-		schedule_work(&sdkp->zone_wp_offset_work);
-		fallthrough;
-	case SD_ZBC_UPDATING_WP_OFST:
-		ret = BLK_STS_DEV_RESOURCE;
-		break;
-	default:
-		wp_offset = sectors_to_logical(sdkp->device, wp_offset);
-		if (wp_offset + nr_blocks > sdkp->zone_info.zone_blocks) {
-			ret = BLK_STS_IOERR;
-			break;
-		}
-
-		trace_scsi_prepare_zone_append(cmd, *lba, wp_offset);
-		*lba += wp_offset;
-	}
-	spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
-	if (ret)
-		blk_req_zone_write_unlock(rq);
-	return ret;
-}
-
 /**
  * sd_zbc_setup_zone_mgmt_cmnd - Prepare a zone ZBC_OUT command. The operations
  *			can be RESET WRITE POINTER, OPEN, CLOSE or FINISH.
@@ -504,96 +354,6 @@ blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
 	return BLK_STS_OK;
 }
 
-static bool sd_zbc_need_zone_wp_update(struct request *rq)
-{
-	switch (req_op(rq)) {
-	case REQ_OP_ZONE_APPEND:
-	case REQ_OP_ZONE_FINISH:
-	case REQ_OP_ZONE_RESET:
-	case REQ_OP_ZONE_RESET_ALL:
-		return true;
-	case REQ_OP_WRITE:
-	case REQ_OP_WRITE_ZEROES:
-		return blk_rq_zone_is_seq(rq);
-	default:
-		return false;
-	}
-}
-
-/**
- * sd_zbc_zone_wp_update - Update cached zone write pointer upon cmd completion
- * @cmd: Completed command
- * @good_bytes: Command reply bytes
- *
- * Called from sd_zbc_complete() to handle the update of the cached zone write
- * pointer value in case an update is needed.
- */
-static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd,
-					  unsigned int good_bytes)
-{
-	int result = cmd->result;
-	struct request *rq = scsi_cmd_to_rq(cmd);
-	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
-	unsigned int zno = blk_rq_zone_no(rq);
-	enum req_op op = req_op(rq);
-	unsigned long flags;
-
-	/*
-	 * If we got an error for a command that needs updating the write
-	 * pointer offset cache, we must mark the zone wp offset entry as
-	 * invalid to force an update from disk the next time a zone append
-	 * command is issued.
-	 */
-	spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
-
-	if (result && op != REQ_OP_ZONE_RESET_ALL) {
-		if (op == REQ_OP_ZONE_APPEND) {
-			/* Force complete completion (no retry) */
-			good_bytes = 0;
-			scsi_set_resid(cmd, blk_rq_bytes(rq));
-		}
-
-		/*
-		 * Force an update of the zone write pointer offset on
-		 * the next zone append access.
-		 */
-		if (sdkp->zones_wp_offset[zno] != SD_ZBC_UPDATING_WP_OFST)
-			sdkp->zones_wp_offset[zno] = SD_ZBC_INVALID_WP_OFST;
-		goto unlock_wp_offset;
-	}
-
-	switch (op) {
-	case REQ_OP_ZONE_APPEND:
-		trace_scsi_zone_wp_update(cmd, rq->__sector,
-				  sdkp->zones_wp_offset[zno], good_bytes);
-		rq->__sector += sdkp->zones_wp_offset[zno];
-		fallthrough;
-	case REQ_OP_WRITE_ZEROES:
-	case REQ_OP_WRITE:
-		if (sdkp->zones_wp_offset[zno] < sd_zbc_zone_sectors(sdkp))
-			sdkp->zones_wp_offset[zno] +=
-						good_bytes >> SECTOR_SHIFT;
-		break;
-	case REQ_OP_ZONE_RESET:
-		sdkp->zones_wp_offset[zno] = 0;
-		break;
-	case REQ_OP_ZONE_FINISH:
-		sdkp->zones_wp_offset[zno] = sd_zbc_zone_sectors(sdkp);
-		break;
-	case REQ_OP_ZONE_RESET_ALL:
-		memset(sdkp->zones_wp_offset, 0,
-		       sdkp->zone_info.nr_zones * sizeof(unsigned int));
-		break;
-	default:
-		break;
-	}
-
-unlock_wp_offset:
-	spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
-
-	return good_bytes;
-}
-
 /**
  * sd_zbc_complete - ZBC command post processing.
  * @cmd: Completed command
@@ -619,11 +379,7 @@ unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 		 * so be quiet about the error.
 		 */
 		rq->rq_flags |= RQF_QUIET;
-	} else if (sd_zbc_need_zone_wp_update(rq))
+	}
-		good_bytes = sd_zbc_zone_wp_update(cmd, good_bytes);
-
-	if (req_op(rq) == REQ_OP_ZONE_APPEND)
-		blk_req_zone_write_unlock(rq);
 
 	return good_bytes;
 }
@@ -780,46 +536,6 @@ static void sd_zbc_print_zones(struct scsi_disk *sdkp)
 			  sdkp->zone_info.zone_blocks);
 }
 
-static int sd_zbc_init_disk(struct scsi_disk *sdkp)
-{
-	sdkp->zones_wp_offset = NULL;
-	spin_lock_init(&sdkp->zones_wp_offset_lock);
-	sdkp->rev_wp_offset = NULL;
-	mutex_init(&sdkp->rev_mutex);
-	INIT_WORK(&sdkp->zone_wp_offset_work, sd_zbc_update_wp_offset_workfn);
-	sdkp->zone_wp_update_buf = kzalloc(SD_BUF_SIZE, GFP_KERNEL);
-	if (!sdkp->zone_wp_update_buf)
-		return -ENOMEM;
-
-	return 0;
-}
-
-void sd_zbc_free_zone_info(struct scsi_disk *sdkp)
-{
-	if (!sdkp->zone_wp_update_buf)
-		return;
-
-	/* Serialize against revalidate zones */
-	mutex_lock(&sdkp->rev_mutex);
-
-	kvfree(sdkp->zones_wp_offset);
-	sdkp->zones_wp_offset = NULL;
-	kfree(sdkp->zone_wp_update_buf);
-	sdkp->zone_wp_update_buf = NULL;
-
-	sdkp->early_zone_info = (struct zoned_disk_info){ };
-	sdkp->zone_info = (struct zoned_disk_info){ };
-
-	mutex_unlock(&sdkp->rev_mutex);
-}
-
-static void sd_zbc_revalidate_zones_cb(struct gendisk *disk)
-{
-	struct scsi_disk *sdkp = scsi_disk(disk);
-
-	swap(sdkp->zones_wp_offset, sdkp->rev_wp_offset);
-}
-
 /*
  * Call blk_revalidate_disk_zones() if any of the zoned disk properties have
  * changed that make it necessary to call that function. Called by
@@ -831,18 +547,8 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp)
 	struct request_queue *q = disk->queue;
 	u32 zone_blocks = sdkp->early_zone_info.zone_blocks;
 	unsigned int nr_zones = sdkp->early_zone_info.nr_zones;
-	int ret = 0;
 	unsigned int flags;
-
+	int ret;
-	/*
-	 * For all zoned disks, initialize zone append emulation data if not
-	 * already done.
-	 */
-	if (sd_is_zoned(sdkp) && !sdkp->zone_wp_update_buf) {
-		ret = sd_zbc_init_disk(sdkp);
-		if (ret)
-			return ret;
-	}
 
 	/*
 	 * There is nothing to do for regular disks, including host-aware disks
@@ -851,50 +557,32 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp)
 	if (!blk_queue_is_zoned(q))
 		return 0;
 
-	/*
-	 * Make sure revalidate zones are serialized to ensure exclusive
-	 * updates of the scsi disk data.
-	 */
-	mutex_lock(&sdkp->rev_mutex);
-
 	if (sdkp->zone_info.zone_blocks == zone_blocks &&
 	    sdkp->zone_info.nr_zones == nr_zones &&
 	    disk->nr_zones == nr_zones)
-		goto unlock;
+		return 0;
 
-	flags = memalloc_noio_save();
 	sdkp->zone_info.zone_blocks = zone_blocks;
 	sdkp->zone_info.nr_zones = nr_zones;
-	sdkp->rev_wp_offset = kvcalloc(nr_zones, sizeof(u32), GFP_KERNEL);
-	if (!sdkp->rev_wp_offset) {
-		ret = -ENOMEM;
-		memalloc_noio_restore(flags);
-		goto unlock;
-	}
 
 	blk_queue_chunk_sectors(q,
 			logical_to_sectors(sdkp->device, zone_blocks));
-	blk_queue_max_zone_append_sectors(q,
-			q->limits.max_segments << PAGE_SECTORS_SHIFT);
 
-	ret = blk_revalidate_disk_zones(disk, sd_zbc_revalidate_zones_cb);
+	/* Enable block layer zone append emulation */
+	blk_queue_max_zone_append_sectors(q, 0);
 
+	flags = memalloc_noio_save();
+	ret = blk_revalidate_disk_zones(disk);
 	memalloc_noio_restore(flags);
-	kvfree(sdkp->rev_wp_offset);
-	sdkp->rev_wp_offset = NULL;
-
 	if (ret) {
 		sdkp->zone_info = (struct zoned_disk_info){ };
 		sdkp->capacity = 0;
-		goto unlock;
+		return ret;
 	}
 
 	sd_zbc_print_zones(sdkp);
 
-unlock:
+	return 0;
-	mutex_unlock(&sdkp->rev_mutex);
-
-	return ret;
 }
 
 /**
@@ -917,10 +605,8 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE])
 	if (!sd_is_zoned(sdkp)) {
 		/*
 		 * Device managed or normal SCSI disk, no special handling
-		 * required. Nevertheless, free the disk zone information in
+		 * required.
-		 * case the device type changed.
 		 */
-		sd_zbc_free_zone_info(sdkp);
 		return 0;
 	}
 
@@ -941,7 +627,6 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE])
 
 	/* The drive satisfies the kernel restrictions: set it up */
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
-	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
 	if (sdkp->zones_max_open == U32_MAX)
 		disk_set_max_open_zones(disk, 0);
 	else

fs/btrfs/raid56.c

@@ -331,12 +331,11 @@ static void steal_rbio(struct btrfs_raid_bio *src, struct btrfs_raid_bio *dest)
 static void merge_rbio(struct btrfs_raid_bio *dest,
 		       struct btrfs_raid_bio *victim)
 {
-	bio_list_merge(&dest->bio_list, &victim->bio_list);
+	bio_list_merge_init(&dest->bio_list, &victim->bio_list);
 	dest->bio_list_bytes += victim->bio_list_bytes;
 	/* Also inherit the bitmaps from @victim. */
 	bitmap_or(&dest->dbitmap, &victim->dbitmap, &dest->dbitmap,
 		  dest->stripe_nsectors);
-	bio_list_init(&victim->bio_list);
 }
 
 /*

include/linux/bio.h

@@ -615,6 +615,13 @@ static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2)
 	bl->tail = bl2->tail;
 }
 
+static inline void bio_list_merge_init(struct bio_list *bl,
+		struct bio_list *bl2)
+{
+	bio_list_merge(bl, bl2);
+	bio_list_init(bl2);
+}
+
 static inline void bio_list_merge_head(struct bio_list *bl,
 				       struct bio_list *bl2)
 {
@@ -824,5 +831,9 @@ static inline void bio_clear_polled(struct bio *bio)
 
 struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
 		unsigned int nr_pages, blk_opf_t opf, gfp_t gfp);
+struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new);
+
+struct bio *blk_alloc_discard_bio(struct block_device *bdev,
+		sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask);
 
 #endif /* __LINUX_BIO_H */

include/linux/blk-mq.h

@@ -54,8 +54,8 @@ typedef __u32 __bitwise req_flags_t;
 /* Look at ->special_vec for the actual data payload instead of the
    bio chain. */
 #define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
-/* The per-zone write lock is held for this request */
+/* The request completion needs to be signaled to zone write pluging. */
-#define RQF_ZONE_WRITE_LOCKED	((__force req_flags_t)(1 << 19))
+#define RQF_ZONE_WRITE_PLUGGING	((__force req_flags_t)(1 << 20))
 /* ->timeout has been called, don't expire again */
 #define RQF_TIMED_OUT		((__force req_flags_t)(1 << 21))
 #define RQF_RESV		((__force req_flags_t)(1 << 23))
@@ -1150,85 +1150,4 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 }
 void blk_dump_rq_flags(struct request *, char *);
 
-#ifdef CONFIG_BLK_DEV_ZONED
-static inline unsigned int blk_rq_zone_no(struct request *rq)
-{
-	return disk_zone_no(rq->q->disk, blk_rq_pos(rq));
-}
-
-static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
-{
-	return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq));
-}
-
-/**
- * blk_rq_is_seq_zoned_write() - Check if @rq requires write serialization.
- * @rq: Request to examine.
- *
- * Note: REQ_OP_ZONE_APPEND requests do not require serialization.
- */
-static inline bool blk_rq_is_seq_zoned_write(struct request *rq)
-{
-	return op_needs_zoned_write_locking(req_op(rq)) &&
-		blk_rq_zone_is_seq(rq);
-}
-
-bool blk_req_needs_zone_write_lock(struct request *rq);
-bool blk_req_zone_write_trylock(struct request *rq);
-void __blk_req_zone_write_lock(struct request *rq);
-void __blk_req_zone_write_unlock(struct request *rq);
-
-static inline void blk_req_zone_write_lock(struct request *rq)
-{
-	if (blk_req_needs_zone_write_lock(rq))
-		__blk_req_zone_write_lock(rq);
-}
-
-static inline void blk_req_zone_write_unlock(struct request *rq)
-{
-	if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED)
-		__blk_req_zone_write_unlock(rq);
-}
-
-static inline bool blk_req_zone_is_write_locked(struct request *rq)
-{
-	return rq->q->disk->seq_zones_wlock &&
-		test_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock);
-}
-
-static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
-{
-	if (!blk_req_needs_zone_write_lock(rq))
-		return true;
-	return !blk_req_zone_is_write_locked(rq);
-}
-#else /* CONFIG_BLK_DEV_ZONED */
-static inline bool blk_rq_is_seq_zoned_write(struct request *rq)
-{
-	return false;
-}
-
-static inline bool blk_req_needs_zone_write_lock(struct request *rq)
-{
-	return false;
-}
-
-static inline void blk_req_zone_write_lock(struct request *rq)
-{
-}
-
-static inline void blk_req_zone_write_unlock(struct request *rq)
-{
-}
-static inline bool blk_req_zone_is_write_locked(struct request *rq)
-{
-	return false;
-}
-
-static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
-{
-	return true;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
-
 #endif /* BLK_MQ_H */

include/linux/blk_types.h

@@ -130,18 +130,6 @@ typedef u16 blk_short_t;
  */
 #define BLK_STS_DEV_RESOURCE	((__force blk_status_t)13)
 
-/*
- * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone
- * related resources are unavailable, but the driver can guarantee the queue
- * will be rerun in the future once the resources become available again.
- *
- * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references
- * a zone specific resource and IO to a different zone on the same device could
- * still be served. Examples of that are zones that are write-locked, but a read
- * to the same zone could be served.
- */
-#define BLK_STS_ZONE_RESOURCE	((__force blk_status_t)14)
-
 /*
  * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion
  * path if the device returns a status indicating that too many zone resources
@@ -149,7 +137,7 @@ typedef u16 blk_short_t;
  * after the number of open zones decreases below the device's limits, which is
  * reported in the request_queue's max_open_zones.
  */
-#define BLK_STS_ZONE_OPEN_RESOURCE	((__force blk_status_t)15)
+#define BLK_STS_ZONE_OPEN_RESOURCE	((__force blk_status_t)14)
 
 /*
  * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion
@@ -158,20 +146,20 @@ typedef u16 blk_short_t;
  * after the number of active zones decreases below the device's limits, which
  * is reported in the request_queue's max_active_zones.
  */
-#define BLK_STS_ZONE_ACTIVE_RESOURCE	((__force blk_status_t)16)
+#define BLK_STS_ZONE_ACTIVE_RESOURCE	((__force blk_status_t)15)
 
 /*
  * BLK_STS_OFFLINE is returned from the driver when the target device is offline
  * or is being taken offline. This could help differentiate the case where a
  * device is intentionally being shut down from a real I/O error.
  */
-#define BLK_STS_OFFLINE		((__force blk_status_t)17)
+#define BLK_STS_OFFLINE		((__force blk_status_t)16)
 
 /*
  * BLK_STS_DURATION_LIMIT is returned from the driver when the target device
  * aborted the command because it exceeded one of its Command Duration Limits.
  */
-#define BLK_STS_DURATION_LIMIT	((__force blk_status_t)18)
+#define BLK_STS_DURATION_LIMIT	((__force blk_status_t)17)
 
 /**
  * blk_path_error - returns true if error may be path related
@@ -228,7 +216,12 @@ struct bio {
 
 	struct bvec_iter	bi_iter;
 
-	blk_qc_t		bi_cookie;
+	union {
+		/* for polled bios: */
+		blk_qc_t		bi_cookie;
+		/* for plugged zoned writes only: */
+		unsigned int		__bi_nr_segments;
+	};
 	bio_end_io_t		*bi_end_io;
 	void			*bi_private;
 #ifdef CONFIG_BLK_CGROUP
@@ -298,7 +291,8 @@ enum {
 	BIO_QOS_THROTTLED,	/* bio went through rq_qos throttle path */
 	BIO_QOS_MERGED,		/* but went through rq_qos merge path */
 	BIO_REMAPPED,
-	BIO_ZONE_WRITE_LOCKED,	/* Owns a zoned device zone write lock */
+	BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */
+	BIO_EMULATES_ZONE_APPEND, /* bio emulates a zone append operation */
 	BIO_FLAG_LAST
 };
 

include/linux/blkdev.h

@@ -179,22 +179,21 @@ struct gendisk {
 
 #ifdef CONFIG_BLK_DEV_ZONED
 	/*
-	 * Zoned block device information for request dispatch control.
+	 * Zoned block device information. Reads of this information must be
-	 * nr_zones is the total number of zones of the device. This is always
+	 * protected with blk_queue_enter() / blk_queue_exit(). Modifying this
-	 * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones
+	 * information is only allowed while no requests are being processed.
-	 * bits which indicates if a zone is conventional (bit set) or
+	 * See also blk_mq_freeze_queue() and blk_mq_unfreeze_queue().
-	 * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones
-	 * bits which indicates if a zone is write locked, that is, if a write
-	 * request targeting the zone was dispatched.
-	 *
-	 * Reads of this information must be protected with blk_queue_enter() /
-	 * blk_queue_exit(). Modifying this information is only allowed while
-	 * no requests are being processed. See also blk_mq_freeze_queue() and
-	 * blk_mq_unfreeze_queue().
 	 */
 	unsigned int		nr_zones;
+	unsigned int		zone_capacity;
 	unsigned long		*conv_zones_bitmap;
-	unsigned long		*seq_zones_wlock;
+	unsigned int            zone_wplugs_hash_bits;
+	spinlock_t              zone_wplugs_lock;
+	struct mempool_s	*zone_wplugs_pool;
+	struct hlist_head       *zone_wplugs_hash;
+	struct list_head        zone_wplugs_err_list;
+	struct work_struct	zone_wplugs_work;
+	struct workqueue_struct *zone_wplugs_wq;
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 #if IS_ENABLED(CONFIG_CDROM)
@@ -233,6 +232,19 @@ static inline unsigned int disk_openers(struct gendisk *disk)
 	return atomic_read(&disk->part0->bd_openers);
 }
 
+/**
+ * disk_has_partscan - return %true if partition scanning is enabled on a disk
+ * @disk: disk to check
+ *
+ * Returns %true if partitions scanning is enabled for @disk, or %false if
+ * partition scanning is disabled either permanently or temporarily.
+ */
+static inline bool disk_has_partscan(struct gendisk *disk)
+{
+	return !(disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN)) &&
+		!test_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
+}
+
 /*
  * The gendisk is refcounted by the part0 block_device, and the bd_device
  * therein is also used for device model presentation in sysfs.
@@ -331,8 +343,7 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data);
 int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 		sector_t sectors, sector_t nr_sectors);
-int blk_revalidate_disk_zones(struct gendisk *disk,
+int blk_revalidate_disk_zones(struct gendisk *disk);
-		void (*update_driver_data)(struct gendisk *disk));
 
 /*
  * Independent access ranges: struct blk_independent_access_range describes
@@ -449,8 +460,6 @@ struct request_queue {
 
 	atomic_t		nr_active_requests_shared_tags;
 
-	unsigned int		required_elevator_features;
-
 	struct blk_mq_tags	*sched_shared_tags;
 
 	struct list_head	icq_list;
@@ -633,15 +642,6 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 	return sector >> ilog2(disk->queue->limits.chunk_sectors);
 }
 
-static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
-{
-	if (!blk_queue_is_zoned(disk->queue))
-		return false;
-	if (!disk->conv_zones_bitmap)
-		return true;
-	return !test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap);
-}
-
 static inline void disk_set_max_open_zones(struct gendisk *disk,
 		unsigned int max_open_zones)
 {
@@ -664,6 +664,7 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 	return bdev->bd_disk->queue->limits.max_active_zones;
 }
 
+bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline unsigned int bdev_nr_zones(struct block_device *bdev)
 {
@@ -674,10 +675,6 @@ static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return 0;
 }
-static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
-{
-	return false;
-}
 static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 {
 	return 0;
@@ -691,6 +688,10 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 {
 	return 0;
 }
+static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
+{
+	return false;
+}
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline unsigned int blk_queue_depth(struct request_queue *q)
@@ -855,9 +856,11 @@ static inline unsigned int bio_zone_no(struct bio *bio)
 	return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
 }
 
-static inline unsigned int bio_zone_is_seq(struct bio *bio)
+static inline bool bio_straddles_zones(struct bio *bio)
 {
-	return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
+	return bio_sectors(bio) &&
+		bio_zone_no(bio) !=
+		disk_zone_no(bio->bi_bdev->bd_disk, bio_end_sector(bio) - 1);
 }
 
 /*
@@ -942,14 +945,6 @@ disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges);
 void disk_set_independent_access_ranges(struct gendisk *disk,
 				struct blk_independent_access_ranges *iars);
 
-/*
- * Elevator features for blk_queue_required_elevator_features:
- */
-/* Supports zoned block devices sequential write constraint */
-#define ELEVATOR_F_ZBD_SEQ_WRITE	(1U << 0)
-
-extern void blk_queue_required_elevator_features(struct request_queue *q,
-						 unsigned int features);
 extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 					      struct device *dev);
 
@@ -1156,12 +1151,29 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 	return q->limits.max_segment_size;
 }
 
-static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
+static inline unsigned int queue_limits_max_zone_append_sectors(struct queue_limits *l)
 {
+	unsigned int max_sectors = min(l->chunk_sectors, l->max_hw_sectors);
 
-	const struct queue_limits *l = &q->limits;
+	return min_not_zero(l->max_zone_append_sectors, max_sectors);
+}
 
-	return min(l->max_zone_append_sectors, l->max_sectors);
+static inline unsigned int queue_max_zone_append_sectors(struct request_queue *q)
+{
+	if (!blk_queue_is_zoned(q))
+		return 0;
+
+	return queue_limits_max_zone_append_sectors(&q->limits);
+}
+
+static inline bool queue_emulates_zone_append(struct request_queue *q)
+{
+	return blk_queue_is_zoned(q) && !q->limits.max_zone_append_sectors;
+}
+
+static inline bool bdev_emulates_zone_append(struct block_device *bdev)
+{
+	return queue_emulates_zone_append(bdev_get_queue(bdev));
 }
 
 static inline unsigned int
@@ -1303,18 +1315,6 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec)
 	return disk_zone_no(bdev->bd_disk, sec);
 }
 
-/* Whether write serialization is required for @op on zoned devices. */
-static inline bool op_needs_zoned_write_locking(enum req_op op)
-{
-	return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES;
-}
-
-static inline bool bdev_op_is_zoned_write(struct block_device *bdev,
-					  enum req_op op)
-{
-	return bdev_is_zoned(bdev) && op_needs_zoned_write_locking(op);
-}
-
 static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
@@ -1330,6 +1330,12 @@ static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev,
 	return sector & (bdev_zone_sectors(bdev) - 1);
 }
 
+static inline sector_t bio_offset_from_zone_start(struct bio *bio)
+{
+	return bdev_offset_from_zone_start(bio->bi_bdev,
+					   bio->bi_iter.bi_sector);
+}
+
 static inline bool bdev_is_zone_start(struct block_device *bdev,
 				      sector_t sector)
 {

lib/sbitmap.c

@@ -494,18 +494,18 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
 		struct sbitmap_word *map = &sb->map[index];
 		unsigned long get_mask;
 		unsigned int map_depth = __map_depth(sb, index);
+		unsigned long val;
 
 		sbitmap_deferred_clear(map);
-		if (map->word == (1UL << (map_depth - 1)) - 1)
+		val = READ_ONCE(map->word);
+		if (val == (1UL << (map_depth - 1)) - 1)
 			goto next;
 
-		nr = find_first_zero_bit(&map->word, map_depth);
+		nr = find_first_zero_bit(&val, map_depth);
 		if (nr + nr_tags <= map_depth) {
 			atomic_long_t *ptr = (atomic_long_t *) &map->word;
-			unsigned long val;
 
 			get_mask = ((1UL << nr_tags) - 1) << nr;
-			val = READ_ONCE(map->word);
 			while (!atomic_long_try_cmpxchg(ptr, &val,
 							  get_mask | val))
 				;