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
  ...

72 files changed, 2555 insertions, 2949 deletions

diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block
index 1fe9a553c37b..831f19a32e08 100644
--- a/Documentation/ABI/stable/sysfs-block
+++ b/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
diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index f18c2ba871ef..fc0d89d4c1c5 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/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
diff --git a/block/Kconfig b/block/Kconfig
index 1de4682d48cc..dc12af58dbae 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -100,7 +100,6 @@ config BLK_DEV_WRITE_MOUNTED
 
 config BLK_DEV_ZONED
 	bool "Zoned block device support"
-	select MQ_IOSCHED_DEADLINE
 	help
 	Block layer zoned block device support. This option enables
 	support for ZAC/ZBC/ZNS host-managed and host-aware zoned block
@@ -120,17 +119,6 @@ config BLK_DEV_THROTTLING
 
 	See Documentation/admin-guide/cgroup-v1/blkio-controller.rst for more information.
 
-config BLK_DEV_THROTTLING_LOW
-	bool "Block throttling .low limit interface support (EXPERIMENTAL)"
-	depends on BLK_DEV_THROTTLING
-	help
-	Add .low limit interface for block throttling. The low limit is a best
-	effort limit to prioritize cgroups. Depending on the setting, the limit
-	can be used to protect cgroups in terms of bandwidth/iops and better
-	utilize disk resource.
-
-	Note, this is an experimental interface and could be changed someday.
-
 config BLK_WBT
 	bool "Enable support for block device writeback throttling"
 	help
@@ -198,10 +186,6 @@ config BLK_DEBUG_FS
 	Unless you are building a kernel for a tiny system, you should
 	say Y here.
 
-config BLK_DEBUG_FS_ZONED
-       bool
-       default BLK_DEBUG_FS && BLK_DEV_ZONED
-
 config BLK_SED_OPAL
 	bool "Logic for interfacing with Opal enabled SEDs"
 	depends on KEYS
diff --git a/block/Makefile b/block/Makefile
index 46ada9dc8bbf..168150b9c510 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -33,7 +33,6 @@ obj-$(CONFIG_BLK_MQ_VIRTIO)	+= blk-mq-virtio.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
-obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
 obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
 obj-$(CONFIG_BLK_PM)		+= blk-pm.o
 obj-$(CONFIG_BLK_INLINE_ENCRYPTION)	+= blk-crypto.o blk-crypto-profile.o \
diff --git a/block/bio.c b/block/bio.c
index d24420ed1c4c..53f608028c78 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -345,18 +345,29 @@ void bio_chain(struct bio *bio, struct bio *parent)
 }
 EXPORT_SYMBOL(bio_chain);
 
-struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
-		unsigned int nr_pages, blk_opf_t opf, gfp_t gfp)
+/**
+ * bio_chain_and_submit - submit a bio after chaining it to another one
+ * @prev: bio to chain and submit
+ * @new: bio to chain to
+ *
+ * If @prev is non-NULL, chain it to @new and submit it.
+ *
+ * Return: @new.
+ */
+struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new)
 {
-	struct bio *new = bio_alloc(bdev, nr_pages, opf, gfp);
-
-	if (bio) {
-		bio_chain(bio, new);
-		submit_bio(bio);
+	if (prev) {
+		bio_chain(prev, new);
+		submit_bio(prev);
 	}
-
 	return new;
 }
+
+struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
+		unsigned int nr_pages, blk_opf_t opf, gfp_t gfp)
+{
+	return bio_chain_and_submit(bio, bio_alloc(bdev, nr_pages, opf, gfp));
+}
 EXPORT_SYMBOL_GPL(blk_next_bio);
 
 static void bio_alloc_rescue(struct work_struct *work)
@@ -1384,6 +1395,26 @@ int submit_bio_wait(struct bio *bio)
 }
 EXPORT_SYMBOL(submit_bio_wait);
 
+static void bio_wait_end_io(struct bio *bio)
+{
+	complete(bio->bi_private);
+	bio_put(bio);
+}
+
+/*
+ * bio_await_chain - ends @bio and waits for every chained bio to complete
+ */
+void bio_await_chain(struct bio *bio)
+{
+	DECLARE_COMPLETION_ONSTACK_MAP(done,
+			bio->bi_bdev->bd_disk->lockdep_map);
+
+	bio->bi_private = &done;
+	bio->bi_end_io = bio_wait_end_io;
+	bio_endio(bio);
+	blk_wait_io(&done);
+}
+
 void __bio_advance(struct bio *bio, unsigned bytes)
 {
 	if (bio_integrity(bio))
@@ -1576,6 +1607,8 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
+	blk_zone_bio_endio(bio);
+
 	rq_qos_done_bio(bio);
 
 	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
@@ -1596,7 +1629,6 @@ again:
 		goto again;
 	}
 
-	blk_throtl_bio_endio(bio);
 	/* release cgroup info */
 	bio_uninit(bio);
 	if (bio->bi_end_io)
diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c
index 3304e841df7c..a55fb0c53558 100644
--- a/block/blk-cgroup-rwstat.c
+++ b/block/blk-cgroup-rwstat.c
@@ -9,25 +9,19 @@ int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp)
 {
 	int i, ret;
 
-	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
-		ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp);
-		if (ret) {
-			while (--i >= 0)
-				percpu_counter_destroy(&rwstat->cpu_cnt[i]);
-			return ret;
-		}
+	ret = percpu_counter_init_many(rwstat->cpu_cnt, 0, gfp, BLKG_RWSTAT_NR);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
 		atomic64_set(&rwstat->aux_cnt[i], 0);
-	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blkg_rwstat_init);
 
 void blkg_rwstat_exit(struct blkg_rwstat *rwstat)
 {
-	int i;
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		percpu_counter_destroy(&rwstat->cpu_cnt[i]);
+	percpu_counter_destroy_many(rwstat->cpu_cnt, BLKG_RWSTAT_NR);
 }
 EXPORT_SYMBOL_GPL(blkg_rwstat_exit);
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 059467086b13..4b1a35ab0ea4 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -218,8 +218,7 @@ static void blkg_async_bio_workfn(struct work_struct *work)
 
 	/* as long as there are pending bios, @blkg can't go away */
 	spin_lock(&blkg->async_bio_lock);
-	bio_list_merge(&bios, &blkg->async_bios);
-	bio_list_init(&blkg->async_bios);
+	bio_list_merge_init(&bios, &blkg->async_bios);
 	spin_unlock(&blkg->async_bio_lock);
 
 	/* start plug only when bio_list contains at least 2 bios */
@@ -1444,14 +1443,8 @@ int blkcg_init_disk(struct gendisk *disk)
 	if (ret)
 		goto err_destroy_all;
 
-	ret = blk_throtl_init(disk);
-	if (ret)
-		goto err_ioprio_exit;
-
 	return 0;
 
-err_ioprio_exit:
-	blk_ioprio_exit(disk);
 err_destroy_all:
 	blkg_destroy_all(disk);
 	return ret;
diff --git a/block/blk-core.c b/block/blk-core.c
index b795ac177281..01186333c88e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -591,8 +591,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 		return BLK_STS_NOTSUPP;
 
 	/* The bio sector must point to the start of a sequential zone */
-	if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector) ||
-	    !bio_zone_is_seq(bio))
+	if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector))
 		return BLK_STS_IOERR;
 
 	/*
@@ -604,7 +603,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 		return BLK_STS_IOERR;
 
 	/* Make sure the BIO is small enough and will not get split */
-	if (nr_sectors > q->limits.max_zone_append_sectors)
+	if (nr_sectors > queue_max_zone_append_sectors(q))
 		return BLK_STS_IOERR;
 
 	bio->bi_opf |= REQ_NOMERGE;
@@ -649,11 +648,13 @@ static void __submit_bio(struct bio *bio)
 static void __submit_bio_noacct(struct bio *bio)
 {
 	struct bio_list bio_list_on_stack[2];
+	struct blk_plug plug;
 
 	BUG_ON(bio->bi_next);
 
 	bio_list_init(&bio_list_on_stack[0]);
 	current->bio_list = bio_list_on_stack;
+	blk_start_plug(&plug);
 
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
@@ -687,19 +688,23 @@ static void __submit_bio_noacct(struct bio *bio)
 		bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
 	} while ((bio = bio_list_pop(&bio_list_on_stack[0])));
 
+	blk_finish_plug(&plug);
 	current->bio_list = NULL;
 }
 
 static void __submit_bio_noacct_mq(struct bio *bio)
 {
 	struct bio_list bio_list[2] = { };
+	struct blk_plug plug;
 
 	current->bio_list = bio_list;
+	blk_start_plug(&plug);
 
 	do {
 		__submit_bio(bio);
 	} while ((bio = bio_list_pop(&bio_list[0])));
 
+	blk_finish_plug(&plug);
 	current->bio_list = NULL;
 }
 
@@ -910,12 +915,6 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return 0;
 
-	/*
-	 * As the requests that require a zone lock are not plugged in the
-	 * first place, directly accessing the plug instead of using
-	 * blk_mq_plug() should not have any consequences during flushing for
-	 * zoned devices.
-	 */
 	blk_flush_plug(current->plug, false);
 
 	/*
@@ -987,10 +986,11 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end)
 	unsigned long stamp;
 again:
 	stamp = READ_ONCE(part->bd_stamp);
-	if (unlikely(time_after(now, stamp))) {
-		if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now)))
-			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
-	}
+	if (unlikely(time_after(now, stamp)) &&
+	    likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) &&
+	    (end || part_in_flight(part)))
+		__part_stat_add(part, io_ticks, now - stamp);
+
 	if (part->bd_partno) {
 		part = bdev_whole(part);
 		goto again;
diff --git a/block/blk-flush.c b/block/blk-flush.c
index b0f314f4bc14..c17cf8ed8113 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -130,6 +130,8 @@ static void blk_flush_restore_request(struct request *rq)
 	 * original @rq->bio.  Restore it.
 	 */
 	rq->bio = rq->biotail;
+	if (rq->bio)
+		rq->__sector = rq->bio->bi_iter.bi_sector;
 
 	/* make @rq a normal request */
 	rq->rq_flags &= ~RQF_FLUSH_SEQ;
diff --git a/block/blk-lib.c b/block/blk-lib.c
index a6954eafb8c8..442da9dad042 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -35,51 +35,39 @@ static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
 	return round_down(UINT_MAX, discard_granularity) >> SECTOR_SHIFT;
 }
 
-int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
+struct bio *blk_alloc_discard_bio(struct block_device *bdev,
+		sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask)
 {
-	struct bio *bio = *biop;
-	sector_t bs_mask;
-
-	if (bdev_read_only(bdev))
-		return -EPERM;
-	if (!bdev_max_discard_sectors(bdev))
-		return -EOPNOTSUPP;
-
-	/* In case the discard granularity isn't set by buggy device driver */
-	if (WARN_ON_ONCE(!bdev_discard_granularity(bdev))) {
-		pr_err_ratelimited("%pg: Error: discard_granularity is 0.\n",
-				   bdev);
-		return -EOPNOTSUPP;
-	}
-
-	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
-	if ((sector | nr_sects) & bs_mask)
-		return -EINVAL;
+	sector_t bio_sects = min(*nr_sects, bio_discard_limit(bdev, *sector));
+	struct bio *bio;
 
-	if (!nr_sects)
-		return -EINVAL;
+	if (!bio_sects)
+		return NULL;
 
-	while (nr_sects) {
-		sector_t req_sects =
-			min(nr_sects, bio_discard_limit(bdev, sector));
+	bio = bio_alloc(bdev, 0, REQ_OP_DISCARD, gfp_mask);
+	if (!bio)
+		return NULL;
+	bio->bi_iter.bi_sector = *sector;
+	bio->bi_iter.bi_size = bio_sects << SECTOR_SHIFT;
+	*sector += bio_sects;
+	*nr_sects -= bio_sects;
+	/*
+	 * We can loop for a long time in here if someone does full device
+	 * discards (like mkfs).  Be nice and allow us to schedule out to avoid
+	 * softlocking if preempt is disabled.
+	 */
+	cond_resched();
+	return bio;
+}
 
-		bio = blk_next_bio(bio, bdev, 0, REQ_OP_DISCARD, gfp_mask);
-		bio->bi_iter.bi_sector = sector;
-		bio->bi_iter.bi_size = req_sects << 9;
-		sector += req_sects;
-		nr_sects -= req_sects;
-
-		/*
-		 * We can loop for a long time in here, if someone does
-		 * full device discards (like mkfs). Be nice and allow
-		 * us to schedule out to avoid softlocking if preempt
-		 * is disabled.
-		 */
-		cond_resched();
-	}
+int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
+{
+	struct bio *bio;
 
-	*biop = bio;
+	while ((bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects,
+			gfp_mask)))
+		*biop = bio_chain_and_submi