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

@@ -345,18 +345,29 @@ void bio_chain(struct bio *bio, struct bio *parent)
 }
 EXPORT_SYMBOL(bio_chain);
 
-struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
-		unsigned int nr_pages, blk_opf_t opf, gfp_t gfp)
+/**
+ * bio_chain_and_submit - submit a bio after chaining it to another one
+ * @prev: bio to chain and submit
+ * @new: bio to chain to
+ *
+ * If @prev is non-NULL, chain it to @new and submit it.
+ *
+ * Return: @new.
+ */
+struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new)
 {
-	struct bio *new = bio_alloc(bdev, nr_pages, opf, gfp);
-
-	if (bio) {
-		bio_chain(bio, new);
-		submit_bio(bio);
+	if (prev) {
+		bio_chain(prev, new);
+		submit_bio(prev);
 	}
-
 	return new;
 }
+
+struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
+		unsigned int nr_pages, blk_opf_t opf, gfp_t gfp)
+{
+	return bio_chain_and_submit(bio, bio_alloc(bdev, nr_pages, opf, gfp));
+}
 EXPORT_SYMBOL_GPL(blk_next_bio);
 
 static void bio_alloc_rescue(struct work_struct *work)
@@ -1384,6 +1395,26 @@ int submit_bio_wait(struct bio *bio)
 }
 EXPORT_SYMBOL(submit_bio_wait);
 
+static void bio_wait_end_io(struct bio *bio)
+{
+	complete(bio->bi_private);
+	bio_put(bio);
+}
+
+/*
+ * bio_await_chain - ends @bio and waits for every chained bio to complete
+ */
+void bio_await_chain(struct bio *bio)
+{
+	DECLARE_COMPLETION_ONSTACK_MAP(done,
+			bio->bi_bdev->bd_disk->lockdep_map);
+
+	bio->bi_private = &done;
+	bio->bi_end_io = bio_wait_end_io;
+	bio_endio(bio);
+	blk_wait_io(&done);
+}
+
 void __bio_advance(struct bio *bio, unsigned bytes)
 {
 	if (bio_integrity(bio))
@@ -1576,6 +1607,8 @@ void bio_endio(struct bio *bio)
 	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 @@ void bio_endio(struct bio *bio)
 		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(&rwstat->cpu_cnt[i], 0, gfp);
-		if (ret) {
-			while (--i >= 0)
-				percpu_counter_destroy(&rwstat->cpu_cnt[i]);
-			return ret;
-		}
+	ret = percpu_counter_init_many(rwstat->cpu_cnt, 0, gfp, BLKG_RWSTAT_NR);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
 		atomic64_set(&rwstat->aux_cnt[i], 0);
-	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blkg_rwstat_init);
 
 void blkg_rwstat_exit(struct blkg_rwstat *rwstat)
 {
-	int i;
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		percpu_counter_destroy(&rwstat->cpu_cnt[i]);
+	percpu_counter_destroy_many(rwstat->cpu_cnt, BLKG_RWSTAT_NR);
 }
 EXPORT_SYMBOL_GPL(blkg_rwstat_exit);
 

block/blk-cgroup.c

@@ -218,8 +218,7 @@ static void blkg_async_bio_workfn(struct work_struct *work)
 
 	/* as long as there are pending bios, @blkg can't go away */
 	spin_lock(&blkg->async_bio_lock);
-	bio_list_merge(&bios, &blkg->async_bios);
-	bio_list_init(&blkg->async_bios);
+	bio_list_merge_init(&bios, &blkg->async_bios);
 	spin_unlock(&blkg->async_bio_lock);
 
 	/* start plug only when bio_list contains at least 2 bios */
@@ -1444,14 +1443,8 @@ int blkcg_init_disk(struct gendisk *disk)
 	if (ret)
 		goto err_destroy_all;
 
-	ret = blk_throtl_init(disk);
-	if (ret)
-		goto err_ioprio_exit;
-
 	return 0;
 
-err_ioprio_exit:
-	blk_ioprio_exit(disk);
 err_destroy_all:
 	blkg_destroy_all(disk);
 	return ret;

block/blk-core.c

@@ -591,8 +591,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 		return BLK_STS_NOTSUPP;
 
 	/* The bio sector must point to the start of a sequential zone */
-	if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector) ||
-	    !bio_zone_is_seq(bio))
+	if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector))
 		return BLK_STS_IOERR;
 
 	/*
@@ -604,7 +603,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 		return BLK_STS_IOERR;
 
 	/* Make sure the BIO is small enough and will not get split */
-	if (nr_sectors > q->limits.max_zone_append_sectors)
+	if (nr_sectors > queue_max_zone_append_sectors(q))
 		return BLK_STS_IOERR;
 
 	bio->bi_opf |= REQ_NOMERGE;
@@ -649,11 +648,13 @@ static void __submit_bio(struct bio *bio)
 static void __submit_bio_noacct(struct bio *bio)
 {
 	struct bio_list bio_list_on_stack[2];
+	struct blk_plug plug;
 
 	BUG_ON(bio->bi_next);
 
 	bio_list_init(&bio_list_on_stack[0]);
 	current->bio_list = bio_list_on_stack;
+	blk_start_plug(&plug);
 
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
@@ -687,19 +688,23 @@ static void __submit_bio_noacct(struct bio *bio)
 		bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
 	} while ((bio = bio_list_pop(&bio_list_on_stack[0])));
 
+	blk_finish_plug(&plug);
 	current->bio_list = NULL;
 }
 
 static void __submit_bio_noacct_mq(struct bio *bio)
 {
 	struct bio_list bio_list[2] = { };
+	struct blk_plug plug;
 
 	current->bio_list = bio_list;
+	blk_start_plug(&plug);
 
 	do {
 		__submit_bio(bio);
 	} while ((bio = bio_list_pop(&bio_list[0])));
 
+	blk_finish_plug(&plug);
 	current->bio_list = NULL;
 }
 
@@ -910,12 +915,6 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return 0;
 
-	/*
-	 * As the requests that require a zone lock are not plugged in the
-	 * first place, directly accessing the plug instead of using
-	 * blk_mq_plug() should not have any consequences during flushing for
-	 * zoned devices.
-	 */
 	blk_flush_plug(current->plug, false);
 
 	/*
@@ -987,10 +986,11 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end)
 	unsigned long stamp;
 again:
 	stamp = READ_ONCE(part->bd_stamp);
-	if (unlikely(time_after(now, stamp))) {
-		if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now)))
-			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
-	}
+	if (unlikely(time_after(now, stamp)) &&
+	    likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) &&
+	    (end || part_in_flight(part)))
+		__part_stat_add(part, io_ticks, now - stamp);
+
 	if (part->bd_partno) {
 		part = bdev_whole(part);
 		goto again;

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;
 }
 
-int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
+struct bio *blk_alloc_discard_bio(struct block_device *bdev,
+		sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask)
 {
-	struct bio *bio = *biop;
-	sector_t bs_mask;
-
-	if (bdev_read_only(bdev))
-		return -EPERM;
-	if (!bdev_max_discard_sectors(bdev))
-		return -EOPNOTSUPP;
-
-	/* In case the discard granularity isn't set by buggy device driver */
-	if (WARN_ON_ONCE(!bdev_discard_granularity(bdev))) {
-		pr_err_ratelimited("%pg: Error: discard_granularity is 0.\n",
-				   bdev);
-		return -EOPNOTSUPP;
-	}
-
-	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
-	if ((sector | nr_sects) & bs_mask)
-		return -EINVAL;
+	sector_t bio_sects = min(*nr_sects, bio_discard_limit(bdev, *sector));
+	struct bio *bio;
 
-	if (!nr_sects)
-		return -EINVAL;
+	if (!bio_sects)
+		return NULL;
 
-	while (nr_sects) {
-		sector_t req_sects =
-			min(nr_sects, bio_discard_limit(bdev, sector));
+	bio = bio_alloc(bdev, 0, REQ_OP_DISCARD, gfp_mask);
+	if (!bio)
+		return NULL;
+	bio->bi_iter.bi_sector = *sector;
+	bio->bi_iter.bi_size = bio_sects << SECTOR_SHIFT;
+	*sector += bio_sects;
+	*nr_sects -= bio_sects;
+	/*
+	 * We can loop for a long time in here if someone does full device
+	 * discards (like mkfs).  Be nice and allow us to schedule out to avoid
+	 * softlocking if preempt is disabled.
+	 */
+	cond_resched();
+	return bio;
+}
 
-		bio = blk_next_bio(bio, bdev, 0, REQ_OP_DISCARD, gfp_mask);
-		bio->bi_iter.bi_sector = sector;
-		bio->bi_iter.bi_size = req_sects << 9;
-		sector += req_sects;
-		nr_sects -= req_sects;
-
-		/*
-		 * We can loop for a long time in here, if someone does
-		 * full device discards (like mkfs). Be nice and allow
-		 * us to schedule out to avoid softlocking if preempt
-		 * is disabled.
-		 */
-		cond_resched();
-	}
+int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
+{
+	struct bio *bio;
 
-	*biop = bio;
+	while ((bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects,
+			gfp_mask)))
+		*biop = bio_chain_and_submit(*biop, bio);
 	return 0;
 }
 EXPORT_SYMBOL(__blkdev_issue_discard);

block/blk-merge.c

@@ -377,6 +377,7 @@ struct bio *__bio_split_to_limits(struct bio *bio,
 		blkcg_bio_issue_init(split);
 		bio_chain(split, bio);
 		trace_block_split(split, bio->bi_iter.bi_sector);
+		WARN_ON_ONCE(bio_zone_write_plugging(bio));
 		submit_bio_noacct(bio);
 		return split;
 	}
@@ -779,6 +780,8 @@ static void blk_account_io_merge_request(struct request *req)
 	if (blk_do_io_stat(req)) {
 		part_stat_lock();
 		part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
+		part_stat_local_dec(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }
@@ -972,13 +975,7 @@ static void blk_account_io_merge_bio(struct request *req)
 	part_stat_unlock();
 }
 
-enum bio_merge_status {
-	BIO_MERGE_OK,
-	BIO_MERGE_NONE,
-	BIO_MERGE_FAILED,
-};
-
-static enum bio_merge_status bio_attempt_back_merge(struct request *req,
+enum bio_merge_status bio_attempt_back_merge(struct request *req,
 		struct bio *bio, unsigned int nr_segs)
 {
 	const blk_opf_t ff = bio_failfast(bio);
@@ -994,6 +991,9 @@ static enum bio_merge_status bio_attempt_back_merge(struct request *req,
 
 	blk_update_mixed_merge(req, bio, false);
 
+	if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING)
+		blk_zone_write_plug_bio_merged(bio);
+
 	req->biotail->bi_next = bio;
 	req->biotail = bio;
 	req->__data_len += bio->bi_iter.bi_size;
@@ -1009,6 +1009,14 @@ static enum bio_merge_status bio_attempt_front_merge(struct request *req,
 {
 	const blk_opf_t ff = bio_failfast(bio);
 
+	/*
+	 * A front merge for writes to sequential zones of a zoned block device
+	 * can happen only if the user submitted writes out of order. Do not
+	 * merge such write to let it fail.
+	 */
+	if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING)
+		return BIO_MERGE_FAILED;
+
 	if (!ll_front_merge_fn(req, bio, nr_segs))
 		return BIO_MERGE_FAILED;
 
@@ -1107,10 +1115,9 @@ static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs)
 {
-	struct blk_plug *plug;
+	struct blk_plug *plug = current->plug;
 	struct request *rq;
 
-	plug = blk_mq_plug(bio);
 	if (!plug || rq_list_empty(plug->mq_list))
 		return false;
 

block/blk-mq-debugfs-zoned.c

-// 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
-int queue_zone_wlock_show(void *data, struct seq_file *m);
+#if defined(CONFIG_BLK_DEV_ZONED) && defined(CONFIG_BLK_DEBUG_FS)
+int queue_zone_wplugs_show(void *data, struct seq_file *m);
 #else
-static inline int queue_zone_wlock_show(void *data, struct seq_file *m)
+static inline int queue_zone_wplugs_show(void *data, struct seq_file *m)
 {
 	return 0;
 }

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);
-	max_sectors = min(q->limits.chunk_sectors, max_sectors);
+	if (max_zone_append_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
-	 * being 0 due to a 0 argument, the chunk_sectors limit (zone size) not set,
-	 * or the max_hw_sectors limit not set.
-	 */
-	WARN_ON(!max_sectors);
+		/*
+		 * Signal eventual driver bugs resulting in the max_zone_append
+		 * sectors limit being 0 due to the chunk_sectors limit (zone
+		 * size) not set or the max_hw_sectors limit not set.
+		 */
+		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,
-					b->max_zone_append_sectors);
+	t->max_zone_append_sectors = min(queue_limits_max_zone_append_sectors(t),
+					 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.
- * Default to "none" if no matching elevator is found.
- */
-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).
+ * Use the default elevator settings. 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);
-	else
-		e = elevator_get_by_features(q);
+	e = elevator_get_default(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_async(iocb, iter, nr_pages);
+			return __blkdev_direct_IO_simple(iocb, iter, bdev,
+							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))
-		return -EINVAL;
-	if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
+	if (!disk_has_partscan(disk))
 		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) &&
-		    !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
+		if (get_capacity(disk) && disk_has_partscan(disk))
 			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 = blk_mq_in_flight(q, bdev);
-	else
-		inflight = part_in_flight(bdev);
-
+	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];
-	uint64_t start, len, end;
+	unsigned int bs_mask = bdev_logical_block_size(bdev) - 1;
 	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
- */
-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.
+ * Return the first request for which blk_rq_pos() >= @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);
-	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;
+	return rq_entry_fifo(per_prio->fifo_list[data_dir].next);
 }
 
 /*
@@ -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;
-	unsigned long flags;
-
-	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;
+	return deadline_from_pos(per_prio, data_dir,
+				 per_prio->latest_pos[data_dir]);
 }
 
 /*
@@ -525,10 +399,6 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd,
 		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 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd,
 	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])
-		return;
-
-	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);
-	}
+	if (rq->elv.priv[0])
+		atomic_inc(&per_prio->stats.completed);
 }
 
 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;
-		char *next = strchr(++partdef, ')');
+		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,
-			       sizeof(new_subpart->name) - 1);
-		strscpy(new_subpart->name, partdef, length);
-
-		partdef = ++next;
+		strscpy(new_subpart->name, next, sizeof(new_subpart->name));
 	} 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, bdevdef, length);
+	strscpy(newparts->name, next, sizeof(newparts->name));
 	newparts->nr_subparts = 0;
 
 	next_subpart = &newparts->subpart;
 
-	while (next && *(++next)) {
-		bdevdef = 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);
+	while ((next = strsep(&bdevdef, ","))) {
+		ret = parse_subpart(next_subpart, next);
 		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) {
-		next = strchr(pbuf, ';');
-		if (next)
-			*next = '\0';
-
-		ret = parse_parts(next_parts, pbuf);
+	while ((next = strsep(&pbuf, ";"))) {
+		ret = parse_parts(next_parts, next);
 		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,
-			  sizeof(subpart->name));
-	strscpy(info->volname, subpart->name, label_min);
+	strscpy(info->volname, subpart->name, sizeof(info->volname));
 
 	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)
-		return 0;
-
-	if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
+	if (!disk_has_partscan(disk))
 		return 0;
 
 	state = check_partition(disk);

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 {