From fa8555630b32da7c239a1e01e9eb1bb040be59ac Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 17 Dec 2024 13:03:09 -0800
Subject: [PATCH 01/16] blk-zoned: Improve the queue reference count strategy
 documentation

For the blk_queue_exit() calls, document where the corresponding code can
be found that increases q->q_usage_counter.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241217210310.645966-4-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 954724a2e3c6..7876a6458022 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -582,6 +582,7 @@ static inline void blk_zone_wplug_bio_io_error(struct blk_zone_wplug *zwplug,
 	bio_clear_flag(bio, BIO_ZONE_WRITE_PLUGGING);
 	bio_io_error(bio);
 	disk_put_zone_wplug(zwplug);
+	/* Drop the reference taken by disk_zone_wplug_add_bio(() */
 	blk_queue_exit(q);
 }
 
@@ -893,10 +894,7 @@ void blk_zone_write_plug_init_request(struct request *req)
 			break;
 		}
 
-		/*
-		 * Drop the extra reference on the queue usage we got when
-		 * plugging the BIO and advance the write pointer offset.
-		 */
+		/* Drop the reference taken by disk_zone_wplug_add_bio(). */
 		blk_queue_exit(q);
 		zwplug->wp_offset += bio_sectors(bio);
 
-- 
2.51.0


From cb01ecb79943367f9903b1f1ffb4afb6a3f4d715 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 17 Dec 2024 13:03:10 -0800
Subject: [PATCH 02/16] blk-zoned: Split queue_zone_wplugs_show()

Reduce the indentation level of the code in queue_zone_wplugs_show() by
moving the body of the loop in that function into a new function.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241217210310.645966-5-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c | 44 ++++++++++++++++++++++++--------------------
 1 file changed, 24 insertions(+), 20 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 7876a6458022..4b0be40a8ea7 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1774,37 +1774,41 @@ int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector,
 EXPORT_SYMBOL_GPL(blk_zone_issue_zeroout);
 
 #ifdef CONFIG_BLK_DEBUG_FS
+static void queue_zone_wplug_show(struct blk_zone_wplug *zwplug,
+				  struct seq_file *m)
+{
+	unsigned int zwp_wp_offset, zwp_flags;
+	unsigned int zwp_zone_no, zwp_ref;
+	unsigned int zwp_bio_list_size;
+	unsigned long flags;
+
+	spin_lock_irqsave(&zwplug->lock, flags);
+	zwp_zone_no = zwplug->zone_no;
+	zwp_flags = zwplug->flags;
+	zwp_ref = refcount_read(&zwplug->ref);
+	zwp_wp_offset = zwplug->wp_offset;
+	zwp_bio_list_size = bio_list_size(&zwplug->bio_list);
+	spin_unlock_irqrestore(&zwplug->lock, flags);
+
+	seq_printf(m, "%u 0x%x %u %u %u\n", zwp_zone_no, zwp_flags, zwp_ref,
+		   zwp_wp_offset, zwp_bio_list_size);
+}
 
 int queue_zone_wplugs_show(void *data, struct seq_file *m)
 {
 	struct request_queue *q = data;
 	struct gendisk *disk = q->disk;
 	struct blk_zone_wplug *zwplug;
-	unsigned int zwp_wp_offset, zwp_flags;
-	unsigned int zwp_zone_no, zwp_ref;
-	unsigned int zwp_bio_list_size, i;
-	unsigned long flags;
+	unsigned int i;
 
 	if (!disk->zone_wplugs_hash)
 		return 0;
 
 	rcu_read_lock();
-	for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++) {
-		hlist_for_each_entry_rcu(zwplug,
-					 &disk->zone_wplugs_hash[i], node) {
-			spin_lock_irqsave(&zwplug->lock, flags);
-			zwp_zone_no = zwplug->zone_no;
-			zwp_flags = zwplug->flags;
-			zwp_ref = refcount_read(&zwplug->ref);
-			zwp_wp_offset = zwplug->wp_offset;
-			zwp_bio_list_size = bio_list_size(&zwplug->bio_list);
-			spin_unlock_irqrestore(&zwplug->lock, flags);
-
-			seq_printf(m, "%u 0x%x %u %u %u\n",
-				   zwp_zone_no, zwp_flags, zwp_ref,
-				   zwp_wp_offset, zwp_bio_list_size);
-		}
-	}
+	for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++)
+		hlist_for_each_entry_rcu(zwplug, &disk->zone_wplugs_hash[i],
+					 node)
+			queue_zone_wplug_show(zwplug, m);
 	rcu_read_unlock();
 
 	return 0;
-- 
2.51.0


From 044792cda05a97ae1da330771ec2140ae86439ec Mon Sep 17 00:00:00 2001
From: =?utf8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Thu, 2 Jan 2025 13:01:31 +0100
Subject: [PATCH 03/16] elevator: Enable const sysfs attributes
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

The elevator core does not need to modify the sysfs attributes added by
the elevators. Reflect this in the types, so the attributes can be moved
into read-only memory.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20250102-sysfs-const-attr-elevator-v1-1-9837d2058c60@weissschuh.net
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/elevator.c | 8 ++++----
 block/elevator.h | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/block/elevator.c b/block/elevator.c
index a26b96662620..be6e994256ac 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -405,12 +405,12 @@ struct request *elv_former_request(struct request_queue *q, struct request *rq)
 	return NULL;
 }
 
-#define to_elv(atr) container_of((atr), struct elv_fs_entry, attr)
+#define to_elv(atr) container_of_const((atr), struct elv_fs_entry, attr)
 
 static ssize_t
 elv_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 {
-	struct elv_fs_entry *entry = to_elv(attr);
+	const struct elv_fs_entry *entry = to_elv(attr);
 	struct elevator_queue *e;
 	ssize_t error;
 
@@ -428,7 +428,7 @@ static ssize_t
 elv_attr_store(struct kobject *kobj, struct attribute *attr,
 	       const char *page, size_t length)
 {
-	struct elv_fs_entry *entry = to_elv(attr);
+	const struct elv_fs_entry *entry = to_elv(attr);
 	struct elevator_queue *e;
 	ssize_t error;
 
@@ -461,7 +461,7 @@ int elv_register_queue(struct request_queue *q, bool uevent)
 
 	error = kobject_add(&e->kobj, &q->disk->queue_kobj, "iosched");
 	if (!error) {
-		struct elv_fs_entry *attr = e->type->elevator_attrs;
+		const struct elv_fs_entry *attr = e->type->elevator_attrs;
 		if (attr) {
 			while (attr->attr.name) {
 				if (sysfs_create_file(&e->kobj, &attr->attr))
diff --git a/block/elevator.h b/block/elevator.h
index dbf357ef4fab..e526662c5dbb 100644
--- a/block/elevator.h
+++ b/block/elevator.h
@@ -71,7 +71,7 @@ struct elevator_type
 
 	size_t icq_size;	/* see iocontext.h */
 	size_t icq_align;	/* ditto */
-	struct elv_fs_entry *elevator_attrs;
+	const struct elv_fs_entry *elevator_attrs;
 	const char *elevator_name;
 	const char *elevator_alias;
 	struct module *elevator_owner;
-- 
2.51.0


From 8686e1dedac7190d2f148b23e4f1ac69d2e37d6b Mon Sep 17 00:00:00 2001
From: =?utf8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Thu, 2 Jan 2025 13:01:32 +0100
Subject: [PATCH 04/16] block: mq-deadline: Constify sysfs attributes
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

The elevator core now allows instances of 'struct elv_fs_entry' to be
moved into read-only memory. Make use of that to protect them against
accidental or malicious modifications.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20250102-sysfs-const-attr-elevator-v1-2-9837d2058c60@weissschuh.net
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/mq-deadline.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 5528347b5fcf..754f6b7415cd 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -834,7 +834,7 @@ STORE_INT(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX);
 #define DD_ATTR(name) \
 	__ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store)
 
-static struct elv_fs_entry deadline_attrs[] = {
+static const struct elv_fs_entry deadline_attrs[] = {
 	DD_ATTR(read_expire),
 	DD_ATTR(write_expire),
 	DD_ATTR(writes_starved),
-- 
2.51.0


From c40f9f6ac59f949b6cbf10903fa2aae76efffa20 Mon Sep 17 00:00:00 2001
From: =?utf8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Thu, 2 Jan 2025 13:01:33 +0100
Subject: [PATCH 05/16] block, bfq: constify sysfs attributes
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

The elevator core now allows instances of 'struct elv_fs_entry' to be
moved into read-only memory. Make use of that to protect them against
accidental or malicious modifications.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20250102-sysfs-const-attr-elevator-v1-3-9837d2058c60@weissschuh.net
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-iosched.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 95dd7b795935..068c63e95738 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -7614,7 +7614,7 @@ static ssize_t bfq_low_latency_store(struct elevator_queue *e,
 #define BFQ_ATTR(name) \
 	__ATTR(name, 0644, bfq_##name##_show, bfq_##name##_store)
 
-static struct elv_fs_entry bfq_attrs[] = {
+static const struct elv_fs_entry bfq_attrs[] = {
 	BFQ_ATTR(fifo_expire_sync),
 	BFQ_ATTR(fifo_expire_async),
 	BFQ_ATTR(back_seek_max),
-- 
2.51.0


From 00aab2f236f25f3dc3c88eee1b8ccb0cbcae3f99 Mon Sep 17 00:00:00 2001
From: =?utf8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Thu, 2 Jan 2025 13:01:34 +0100
Subject: [PATCH 06/16] kyber: constify sysfs attributes
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

The elevator core now allows instances of 'struct elv_fs_entry' to be
moved into read-only memory. Make use of that to protect them against
accidental or malicious modifications.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20250102-sysfs-const-attr-elevator-v1-4-9837d2058c60@weissschuh.net
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/kyber-iosched.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index 4155594aefc6..dc31f2dfa414 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -889,7 +889,7 @@ KYBER_LAT_SHOW_STORE(KYBER_WRITE, write);
 #undef KYBER_LAT_SHOW_STORE
 
 #define KYBER_LAT_ATTR(op) __ATTR(op##_lat_nsec, 0644, kyber_##op##_lat_show, kyber_##op##_lat_store)
-static struct elv_fs_entry kyber_sched_attrs[] = {
+static const struct elv_fs_entry kyber_sched_attrs[] = {
 	KYBER_LAT_ATTR(read),
 	KYBER_LAT_ATTR(write),
 	__ATTR_NULL
-- 
2.51.0


From 457ef47c08d2979f3e59ce66267485c3faed70c8 Mon Sep 17 00:00:00 2001
From: Yang Erkun <yangerkun@huawei.com>
Date: Mon, 9 Dec 2024 19:04:35 +0800
Subject: [PATCH 07/16] block: retry call probe after request_module in
 blk_request_module

Set kernel config:

 CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_LOOP_MIN_COUNT=0

Do latter:

 mknod loop0 b 7 0
 exec 4<> loop0

Before commit e418de3abcda ("block: switch gendisk lookup to a simple
xarray"), lookup_gendisk will first use base_probe to load module loop,
and then the retry will call loop_probe to prepare the loop disk. Finally
open for this disk will success. However, after this commit, we lose the
retry logic, and open will fail with ENXIO. Block device autoloading is
deprecated and will be removed soon, but maybe we should keep open success
until we really remove it. So, give a retry to fix it.

Fixes: e418de3abcda ("block: switch gendisk lookup to a simple xarray")
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Yang Erkun <yangerkun@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20241209110435.3670985-1-yangerkun@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/block/genhd.c b/block/genhd.c
index 5678194b6b1a..5da3c9a64e64 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -797,7 +797,7 @@ static ssize_t disk_badblocks_store(struct device *dev,
 }
 
 #ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
-void blk_request_module(dev_t devt)
+static bool blk_probe_dev(dev_t devt)
 {
 	unsigned int major = MAJOR(devt);
 	struct blk_major_name **n;
@@ -807,14 +807,26 @@ void blk_request_module(dev_t devt)
 		if ((*n)->major == major && (*n)->probe) {
 			(*n)->probe(devt);
 			mutex_unlock(&major_names_lock);
-			return;
+			return true;
 		}
 	}
 	mutex_unlock(&major_names_lock);
+	return false;
+}
+
+void blk_request_module(dev_t devt)
+{
+	int error;
+
+	if (blk_probe_dev(devt))
+		return;
 
-	if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0)
-		/* Make old-style 2.4 aliases work */
-		request_module("block-major-%d", MAJOR(devt));
+	error = request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt));
+	/* Make old-style 2.4 aliases work */
+	if (error > 0)
+		error = request_module("block-major-%d", MAJOR(devt));
+	if (!error)
+		blk_probe_dev(devt);
 }
 #endif /* CONFIG_BLOCK_LEGACY_AUTOLOAD */
 
-- 
2.51.0


From c2398e6d5f16e15598d3a37e17107fea477e3f91 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 3 Jan 2025 09:51:25 +0100
Subject: [PATCH 08/16] ps3disk: Do not use dev->bounce_size before it is set

dev->bounce_size is only initialized after it is used to set the queue
limits.  Fix this by using BOUNCE_SIZE instead.

Fixes: a7f18b74dbe17162 ("ps3disk: pass queue_limits to blk_mq_alloc_disk")
Reported-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Closes: https://lore.kernel.org/39256db9-3d73-4e86-a49b-300dfd670212@gmail.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/06988f959ea6885b8bd7fb3b9059dd54bc6bbad7.1735894216.git.geert+renesas@glider.be
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ps3disk.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 68fed46c463e..dc9e4a14b885 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -384,9 +384,9 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	unsigned int devidx;
 	struct queue_limits lim = {
 		.logical_block_size	= dev->blk_size,
-		.max_hw_sectors		= dev->bounce_size >> 9,
+		.max_hw_sectors		= BOUNCE_SIZE >> 9,
 		.max_segments		= -1,
-		.max_segment_size	= dev->bounce_size,
+		.max_segment_size	= BOUNCE_SIZE,
 		.dma_alignment		= dev->blk_size - 1,
 		.features		= BLK_FEAT_WRITE_CACHE |
 					  BLK_FEAT_ROTATIONAL,
-- 
2.51.0


From 6aeb4f836480617be472de767c4cb09c1060a067 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 3 Jan 2025 08:33:57 +0100
Subject: [PATCH 09/16] block: remove bio_add_pc_page

Lift bio_split_rw_at into blk_rq_append_bio so that it validates the
hardware limits.  With this all passthrough callers can simply add
bio_add_page to build the bio and delay checking for exceeding of limits
to this point instead of doing it for each page.

While this looks like adding a new expensive loop over all bio_vecs,
blk_rq_append_bio is already doing that just to counter the number of
segments.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Link: https://lore.kernel.org/r/20250103073417.459715-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c                        | 107 ++------------------------
 block/blk-map.c                    | 118 +++++++----------------------
 block/blk.h                        |   8 --
 drivers/nvme/target/passthru.c     |  18 +++--
 drivers/nvme/target/zns.c          |   3 +-
 drivers/target/target_core_pscsi.c |   6 +-
 include/linux/bio.h                |   2 -
 7 files changed, 48 insertions(+), 214 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index d5bdc31d88d3..4e1a27d312c9 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -946,8 +946,11 @@ static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page,
 
 /*
  * Try to merge a page into a segment, while obeying the hardware segment
- * size limit.  This is not for normal read/write bios, but for passthrough
- * or Zone Append operations that we can't split.
+ * size limit.
+ *
+ * This is kept around for the integrity metadata, which is still tries
+ * to build the initial bio to the hardware limit and doesn't have proper
+ * helpers to split.  Hopefully this will go away soon.
  */
 bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,
 		struct page *page, unsigned len, unsigned offset,
@@ -964,106 +967,6 @@ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,
 	return bvec_try_merge_page(bv, page, len, offset, same_page);
 }
 
-/**
- * bio_add_hw_page - attempt to add a page to a bio with hw constraints
- * @q: the target queue
- * @bio: destination bio
- * @page: page to add
- * @len: vec entry length
- * @offset: vec entry offset
- * @max_sectors: maximum number of sectors that can be added
- * @same_page: return if the segment has been merged inside the same page
- *
- * Add a page to a bio while respecting the hardware max_sectors, max_segment
- * and gap limitations.
- */
-int bio_add_hw_page(struct request_queue *q, struct bio *bio,
-		struct page *page, unsigned int len, unsigned int offset,
-		unsigned int max_sectors, bool *same_page)
-{
-	unsigned int max_size = max_sectors << SECTOR_SHIFT;
-
-	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
-		return 0;
-
-	len = min3(len, max_size, queue_max_segment_size(q));
-	if (len > max_size - bio->bi_iter.bi_size)
-		return 0;
-
-	if (bio->bi_vcnt > 0) {
-		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
-
-		if (bvec_try_merge_hw_page(q, bv, page, len, offset,
-				same_page)) {
-			bio->bi_iter.bi_size += len;
-			return len;
-		}
-
-		if (bio->bi_vcnt >=
-		    min(bio->bi_max_vecs, queue_max_segments(q)))
-			return 0;
-
-		/*
-		 * If the queue doesn't support SG gaps and adding this segment
-		 * would create a gap, disallow it.
-		 */
-		if (bvec_gap_to_prev(&q->limits, bv, offset))
-			return 0;
-	}
-
-	bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, offset);
-	bio->bi_vcnt++;
-	bio->bi_iter.bi_size += len;
-	return len;
-}
-
-/**
- * bio_add_hw_folio - attempt to add a folio to a bio with hw constraints
- * @q: the target queue
- * @bio: destination bio
- * @folio: folio to add
- * @len: vec entry length
- * @offset: vec entry offset in the folio
- * @max_sectors: maximum number of sectors that can be added
- * @same_page: return if the segment has been merged inside the same folio
- *
- * Add a folio to a bio while respecting the hardware max_sectors, max_segment
- * and gap limitations.
- */
-int bio_add_hw_folio(struct request_queue *q, struct bio *bio,
-		struct folio *folio, size_t len, size_t offset,
-		unsigned int max_sectors, bool *same_page)
-{
-	if (len > UINT_MAX || offset > UINT_MAX)
-		return 0;
-	return bio_add_hw_page(q, bio, folio_page(folio, 0), len, offset,
-			       max_sectors, same_page);
-}
-
-/**
- * bio_add_pc_page	- attempt to add page to passthrough bio
- * @q: the target queue
- * @bio: destination bio
- * @page: page to add
- * @len: vec entry length
- * @offset: vec entry offset
- *
- * Attempt to add a page to the bio_vec maplist. This can fail for a
- * number of reasons, such as the bio being full or target block device
- * limitations. The target block device must allow bio's up to PAGE_SIZE,
- * so it is always possible to add a single page to an empty bio.
- *
- * This should only be used by passthrough bios.
- */
-int bio_add_pc_page(struct request_queue *q, struct bio *bio,
-		struct page *page, unsigned int len, unsigned int offset)
-{
-	bool same_page = false;
-	return bio_add_hw_page(q, bio, page, len, offset,
-			queue_max_hw_sectors(q), &same_page);
-}
-EXPORT_SYMBOL(bio_add_pc_page);
-
 /**
  * __bio_add_page - add page(s) to a bio in a new segment
  * @bio: destination bio
diff --git a/block/blk-map.c b/block/blk-map.c
index 894009b2d881..67a2da3b7ed9 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -189,7 +189,7 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
 			}
 		}
 
-		if (bio_add_pc_page(rq->q, bio, page, bytes, offset) < bytes) {
+		if (bio_add_page(bio, page, bytes, offset) < bytes) {
 			if (!map_data)
 				__free_page(page);
 			break;
@@ -272,86 +272,27 @@ static struct bio *blk_rq_map_bio_alloc(struct request *rq,
 static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 		gfp_t gfp_mask)
 {
-	iov_iter_extraction_t extraction_flags = 0;
-	unsigned int max_sectors = queue_max_hw_sectors(rq->q);
 	unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS);
 	struct bio *bio;
 	int ret;
-	int j;
 
 	if (!iov_iter_count(iter))
 		return -EINVAL;
 
 	bio = blk_rq_map_bio_alloc(rq, nr_vecs, gfp_mask);
-	if (bio == NULL)
+	if (!bio)
 		return -ENOMEM;
-
-	if (blk_queue_pci_p2pdma(rq->q))
-		extraction_flags |= ITER_ALLOW_P2PDMA;
-	if (iov_iter_extract_will_pin(iter))
-		bio_set_flag(bio, BIO_PAGE_PINNED);
-
-	while (iov_iter_count(iter)) {
-		struct page *stack_pages[UIO_FASTIOV];
-		struct page **pages = stack_pages;
-		ssize_t bytes;
-		size_t offs;
-		int npages;
-
-		if (nr_vecs > ARRAY_SIZE(stack_pages))
-			pages = NULL;
-
-		bytes = iov_iter_extract_pages(iter, &pages, LONG_MAX,
-					       nr_vecs, extraction_flags, &offs);
-		if (unlikely(bytes <= 0)) {
-			ret = bytes ? bytes : -EFAULT;
-			goto out_unmap;
-		}
-
-		npages = DIV_ROUND_UP(offs + bytes, PAGE_SIZE);
-
-		if (unlikely(offs & queue_dma_alignment(rq->q)))
-			j = 0;
-		else {
-			for (j = 0; j < npages; j++) {
-				struct page *page = pages[j];
-				unsigned int n = PAGE_SIZE - offs;
-				bool same_page = false;
-
-				if (n > bytes)
-					n = bytes;
-
-				if (!bio_add_hw_page(rq->q, bio, page, n, offs,
-						     max_sectors, &same_page))
-					break;
-
-				if (same_page)
-					bio_release_page(bio, page);
-				bytes -= n;
-				offs = 0;
-			}
-		}
-		/*
-		 * release the pages we didn't map into the bio, if any
-		 */
-		while (j < npages)
-			bio_release_page(bio, pages[j++]);
-		if (pages != stack_pages)
-			kvfree(pages);
-		/* couldn't stuff something into bio? */
-		if (bytes) {
-			iov_iter_revert(iter, bytes);
-			break;
-		}
-	}
-
+	ret = bio_iov_iter_get_pages(bio, iter);
+	if (ret)
+		goto out_put;
 	ret = blk_rq_append_bio(rq, bio);
 	if (ret)
-		goto out_unmap;
+		goto out_release;
 	return 0;
 
- out_unmap:
+out_release:
 	bio_release_pages(bio, false);
+out_put:
 	blk_mq_map_bio_put(bio);
 	return ret;
 }
@@ -422,8 +363,7 @@ static struct bio *bio_map_kern(struct request_queue *q, void *data,
 			page = virt_to_page(data);
 		else
 			page = vmalloc_to_page(data);
-		if (bio_add_pc_page(q, bio, page, bytes,
-				    offset) < bytes) {
+		if (bio_add_page(bio, page, bytes, offset) < bytes) {
 			/* we don't support partial mappings */
 			bio_uninit(bio);
 			kfree(bio);
@@ -507,7 +447,7 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data,
 		if (!reading)
 			memcpy(page_address(page), p, bytes);
 
-		if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes)
+		if (bio_add_page(bio, page, bytes, 0) < bytes)
 			break;
 
 		len -= bytes;
@@ -536,12 +476,19 @@ cleanup:
  */
 int blk_rq_append_bio(struct request *rq, struct bio *bio)
 {
-	struct bvec_iter iter;
-	struct bio_vec bv;
+	const struct queue_limits *lim = &rq->q->limits;
+	unsigned int max_bytes = lim->max_hw_sectors << SECTOR_SHIFT;
 	unsigned int nr_segs = 0;
+	int ret;
 
-	bio_for_each_bvec(bv, bio, iter)
-		nr_segs++;
+	/* check that the data layout matches the hardware restrictions */
+	ret = bio_split_rw_at(bio, lim, &nr_segs, max_bytes);
+	if (ret) {
+		/* if we would have to split the bio, copy instead */
+		if (ret > 0)
+			ret = -EREMOTEIO;
+		return ret;
+	}
 
 	if (!rq->bio) {
 		blk_rq_bio_prep(rq, bio, nr_segs);
@@ -561,9 +508,7 @@ EXPORT_SYMBOL(blk_rq_append_bio);
 /* Prepare bio for passthrough IO given ITER_BVEC iter */
 static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter)
 {
-	const struct queue_limits *lim = &rq->q->limits;
-	unsigned int max_bytes = lim->max_hw_sectors << SECTOR_SHIFT;
-	unsigned int nsegs;
+	unsigned int max_bytes = rq->q->limits.max_hw_sectors << SECTOR_SHIFT;
 	struct bio *bio;
 	int ret;
 
@@ -576,18 +521,10 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter)
 		return -ENOMEM;
 	bio_iov_bvec_set(bio, iter);
 
-	/* check that the data layout matches the hardware restrictions */
-	ret = bio_split_rw_at(bio, lim, &nsegs, max_bytes);
-	if (ret) {
-		/* if we would have to split the bio, copy instead */
-		if (ret > 0)
-			ret = -EREMOTEIO;
+	ret = blk_rq_append_bio(rq, bio);
+	if (ret)
 		blk_mq_map_bio_put(bio);
-		return ret;
-	}
-
-	blk_rq_bio_prep(rq, bio, nsegs);
-	return 0;
+	return ret;
 }
 
 /**
@@ -644,8 +581,11 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 			ret = bio_copy_user_iov(rq, map_data, &i, gfp_mask);
 		else
 			ret = bio_map_user_iov(rq, &i, gfp_mask);
-		if (ret)
+		if (ret) {
+			if (ret == -EREMOTEIO)
+				ret = -EINVAL;
 			goto unmap_rq;
+		}
 		if (!bio)
 			bio = rq->bio;
 	} while (iov_iter_count(&i));
diff --git a/block/blk.h b/block/blk.h
index cbf6a676ffe9..4904b86d5fec 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -556,14 +556,6 @@ void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors);
 struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 		struct lock_class_key *lkclass);
 
-int bio_add_hw_page(struct request_queue *q, struct bio *bio,
-		struct page *page, unsigned int len, unsigned int offset,
-		unsigned int max_sectors, bool *same_page);
-
-int bio_add_hw_folio(struct request_queue *q, struct bio *bio,
-		struct folio *folio, size_t len, size_t offset,
-		unsigned int max_sectors, bool *same_page);
-
 /*
  * Clean up a page appropriately, where the page may be pinned, may have a
  * ref taken on it or neither.
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 30b21936b0c6..26e2907ce8bb 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -261,6 +261,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
 {
 	struct scatterlist *sg;
 	struct bio *bio;
+	int ret = -EINVAL;
 	int i;
 
 	if (req->sg_cnt > BIO_MAX_VECS)
@@ -277,16 +278,19 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
 	}
 
 	for_each_sg(req->sg, sg, req->sg_cnt, i) {
-		if (bio_add_pc_page(rq->q, bio, sg_page(sg), sg->length,
-				    sg->offset) < sg->length) {
-			nvmet_req_bio_put(req, bio);
-			return -EINVAL;
-		}
+		if (bio_add_page(bio, sg_page(sg), sg->length, sg->offset) <
+				sg->length)
+			goto out_bio_put;
 	}
 
-	blk_rq_bio_prep(rq, bio, req->sg_cnt);
-
+	ret = blk_rq_append_bio(rq, bio);
+	if (ret)
+		goto out_bio_put;
 	return 0;
+
+out_bio_put:
+	nvmet_req_bio_put(req, bio);
+	return ret;
 }
 
 static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c
index 3aef35b05111..29a60fabfcc8 100644
--- a/drivers/nvme/target/zns.c
+++ b/drivers/nvme/target/zns.c
@@ -586,8 +586,7 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req)
 	for_each_sg(req->sg, sg, req->sg_cnt, sg_cnt) {
 		unsigned int len = sg->length;
 
-		if (bio_add_pc_page(bdev_get_queue(bio->bi_bdev), bio,
-				sg_page(sg), len, sg->offset) != len) {
+		if (bio_add_page(bio, sg_page(sg), len, sg->offset) != len) {
 			status = NVME_SC_INTERNAL;
 			goto out_put_bio;
 		}
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 287ac5b0495f..f991cf759836 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -823,7 +823,6 @@ static sense_reason_t
 pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		struct request *req)
 {
-	struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev);
 	struct bio *bio = NULL;
 	struct page *page;
 	struct scatterlist *sg;
@@ -871,12 +870,11 @@ new_bio:
 					(rw) ? "rw" : "r", nr_vecs);
 			}
 
-			pr_debug("PSCSI: Calling bio_add_pc_page() i: %d"
+			pr_debug("PSCSI: Calling bio_add_page() i: %d"
 				" bio: %p page: %p len: %d off: %d\n", i, bio,
 				page, len, off);
 
-			rc = bio_add_pc_page(pdv->pdv_sd->request_queue,
-					bio, page, bytes, off);
+			rc = bio_add_page(bio, page, bytes, off);
 			pr_debug("PSCSI: bio->bi_vcnt: %d nr_vecs: %d\n",
 				bio_segments(bio), nr_vecs);
 			if (rc != bytes) {
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 1eec59699100..4b79bf50f4f0 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -413,8 +413,6 @@ int __must_check bio_add_page(struct bio *bio, struct page *page, unsigned len,
 			      unsigned off);
 bool __must_check bio_add_folio(struct bio *bio, struct folio *folio,
 				size_t len, size_t off);
-extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
-			   unsigned int, unsigned int);
 void __bio_add_page(struct bio *bio, struct page *page,
 		unsigned int len, unsigned int off);
 void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len,
-- 
2.51.0


From 02ee5d69e3baf2796ba75b928fcbc9cf7884c5e9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 3 Jan 2025 08:33:58 +0100
Subject: [PATCH 10/16] block: remove blk_rq_bio_prep

There is not real point in a helper just to assign three values to four
fields, especially when the surrounding code is working on the
neighbor fields directly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Link: https://lore.kernel.org/r/20250103073417.459715-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-map.c        | 10 ++++++----
 block/blk-mq.c         |  4 +++-
 include/linux/blk-mq.h |  8 --------
 3 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/block/blk-map.c b/block/blk-map.c
index 67a2da3b7ed9..d2f22744b3d1 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -490,17 +490,19 @@ int blk_rq_append_bio(struct request *rq, struct bio *bio)
 		return ret;
 	}
 
-	if (!rq->bio) {
-		blk_rq_bio_prep(rq, bio, nr_segs);
-	} else {
+	if (rq->bio) {
 		if (!ll_back_merge_fn(rq, bio, nr_segs))
 			return -EINVAL;
 		rq->biotail->bi_next = bio;
 		rq->biotail = bio;
-		rq->__data_len += (bio)->bi_iter.bi_size;
+		rq->__data_len += bio->bi_iter.bi_size;
 		bio_crypt_free_ctx(bio);
+		return 0;
 	}
 
+	rq->nr_phys_segments = nr_segs;
+	rq->bio = rq->biotail = bio;
+	rq->__data_len = bio->bi_iter.bi_size;
 	return 0;
 }
 EXPORT_SYMBOL(blk_rq_append_bio);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index fca2ec64a06b..17f10683d640 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2658,8 +2658,10 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 	if (bio->bi_opf & REQ_RAHEAD)
 		rq->cmd_flags |= REQ_FAILFAST_MASK;
 
+	rq->bio = rq->biotail = bio;
 	rq->__sector = bio->bi_iter.bi_sector;
-	blk_rq_bio_prep(rq, bio, nr_segs);
+	rq->__data_len = bio->bi_iter.bi_size;
+	rq->nr_phys_segments = nr_segs;
 	if (bio_integrity(bio))
 		rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q,
 								      bio);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 7f6c482ebf54..6340293511c9 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -978,14 +978,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq)
 		rq->q->mq_ops->cleanup_rq(rq);
 }
 
-static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
-		unsigned int nr_segs)
-{
-	rq->nr_phys_segments = nr_segs;
-	rq->__data_len = bio->bi_iter.bi_size;
-	rq->bio = rq->biotail = bio;
-}
-
 void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
 		struct lock_class_key *key);
 
-- 
2.51.0


From 2caca8fc7aad9ea9a6ea3ed26ed146b1e5f06fab Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 6 Jan 2025 09:14:37 +0100
Subject: [PATCH 11/16] block: use page_to_phys in bvec_phys

Use page_to_phys instead of open coding it now that it is available in an
architecture independent way.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250106081437.798213-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/bvec.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index f41c7f0ef91e..ba8f52d48b94 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -286,12 +286,7 @@ static inline void *bvec_virt(struct bio_vec *bvec)
  */
 static inline phys_addr_t bvec_phys(const struct bio_vec *bvec)
 {
-	/*
-	 * Note this open codes page_to_phys because page_to_phys is defined in
-	 * <asm/io.h>, which we don't want to pull in here.  If it ever moves to
-	 * a sensible place we should start using it.
-	 */
-	return PFN_PHYS(page_to_pfn(bvec->bv_page)) + bvec->bv_offset;
+	return page_to_phys(bvec->bv_page) + bvec->bv_offset;
 }
 
 #endif /* __LINUX_BVEC_H */
-- 
2.51.0


From b7175e24d6acf79d9f3af9ce9d3d50de1fa748ec Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 6 Jan 2025 09:15:29 +0100
Subject: [PATCH 12/16] block: add a dma mapping iterator

blk_rq_map_sg is maze of nested loops.  Untangle it by creating an
iterator that returns [paddr,len] tuples for DMA mapping, and then
implement the DMA logic on top of this.  This not only removes code
at the source level, but also generates nicer binary code:

$ size block/blk-merge.o.*
   text	   data	    bss	    dec	    hex	filename
  10001	    432	      0	  10433	   28c1	block/blk-merge.o.new
  10317	    468	      0	  10785	   2a21	block/blk-merge.o.old

Last but not least it will be used as a building block for a new
DMA mapping helper that doesn't rely on struct scatterlist.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250106081609.798289-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c | 177 ++++++++++++++++++----------------------------
 1 file changed, 70 insertions(+), 107 deletions(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index e01383c6e534..15cd231d560c 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -473,137 +473,100 @@ unsigned int blk_recalc_rq_segments(struct request *rq)
 	return nr_phys_segs;
 }
 
-static inline struct scatterlist *blk_next_sg(struct scatterlist **sg,
-		struct scatterlist *sglist)
-{
-	if (!*sg)
-		return sglist;
+struct phys_vec {
+	phys_addr_t	paddr;
+	u32		len;
+};
 
-	/*
-	 * If the driver previously mapped a shorter list, we could see a
-	 * termination bit prematurely unless it fully inits the sg table
-	 * on each mapping. We KNOW that there must be more entries here
-	 * or the driver would be buggy, so force clear the termination bit
-	 * to avoid doing a full sg_init_table() in drivers for each command.
-	 */
-	sg_unmark_end(*sg);
-	return sg_next(*sg);
-}
-
-static unsigned blk_bvec_map_sg(struct request_queue *q,
-		struct bio_vec *bvec, struct scatterlist *sglist,
-		struct scatterlist **sg)
+static bool blk_map_iter_next(struct request *req,
+		struct req_iterator *iter, struct phys_vec *vec)
 {
-	unsigned nbytes = bvec->bv_len;
-	unsigned nsegs = 0, total = 0;
-
-	while (nbytes > 0) {
-		unsigned offset = bvec->bv_offset + total;
-		unsigned len = get_max_segment_size(&q->limits,
-				bvec_phys(bvec) + total, nbytes);
-		struct page *page = bvec->bv_page;
-
-		/*
-		 * Unfortunately a fair number of drivers barf on scatterlists
-		 * that have an offset larger than PAGE_SIZE, despite other
-		 * subsystems dealing with that invariant just fine.  For now
-		 * stick to the legacy format where we never present those from
-		 * the block layer, but the code below should be removed once
-		 * these offenders (mostly MMC/SD drivers) are fixed.
-		 */
-		page += (offset >> PAGE_SHIFT);
-		offset &= ~PAGE_MASK;
-
-		*sg = blk_next_sg(sg, sglist);
-		sg_set_page(*sg, page, len, offset);
+	unsigned int max_size;
+	struct bio_vec bv;
 
-		total += len;
-		nbytes -= len;
-		nsegs++;
+	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
+		if (!iter->bio)
+			return false;
+		vec->paddr = bvec_phys(&req->special_vec);
+		vec->len = req->special_vec.bv_len;
+		iter->bio = NULL;
+		return true;
 	}
 
-	return nsegs;
-}
-
-static inline int __blk_bvec_map_sg(struct bio_vec bv,
-		struct scatterlist *sglist, struct scatterlist **sg)
-{
-	*sg = blk_next_sg(sg, sglist);
-	sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
-	return 1;
-}
-
-/* only try to merge bvecs into one sg if they are from two bios */
-static inline bool
-__blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec,
-			   struct bio_vec *bvprv, struct scatterlist **sg)
-{
-
-	int nbytes = bvec->bv_len;
-
-	if (!*sg)
+	if (!iter->iter.bi_size)
 		return false;
 
-	if ((*sg)->length + nbytes > queue_max_segment_size(q))
-		return false;
+	bv = mp_bvec_iter_bvec(iter->bio->bi_io_vec, iter->iter);
+	vec->paddr = bvec_phys(&bv);
+	max_size = get_max_segment_size(&req->q->limits, vec->paddr, UINT_MAX);
+	bv.bv_len = min(bv.bv_len, max_size);
+	bio_advance_iter_single(iter->bio, &iter->iter, bv.bv_len);
 
-	if (!biovec_phys_mergeable(q, bvprv, bvec))
-		return false;
+	/*
+	 * If we are entirely done with this bi_io_vec entry, check if the next
+	 * one could be merged into it.  This typically happens when moving to
+	 * the next bio, but some callers also don't pack bvecs tight.
+	 */
+	while (!iter->iter.bi_size || !iter->iter.bi_bvec_done) {
+		struct bio_vec next;
+
+		if (!iter->iter.bi_size) {
+			if (!iter->bio->bi_next)
+				break;
+			iter->bio = iter->bio->bi_next;
+			iter->iter = iter->bio->bi_iter;
+		}
 
-	(*sg)->length += nbytes;
+		next = mp_bvec_iter_bvec(iter->bio->bi_io_vec, iter->iter);
+		if (bv.bv_len + next.bv_len > max_size ||
+		    !biovec_phys_mergeable(req->q, &bv, &next))
+			break;
+
+		bv.bv_len += next.bv_len;
+		bio_advance_iter_single(iter->bio, &iter->iter, next.bv_len);
+	}
 
+	vec->len = bv.bv_len;
 	return true;
 }
 
-static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
-			     struct scatterlist *sglist,
-			     struct scatterlist **sg)
+static inline struct scatterlist *blk_next_sg(struct scatterlist **sg,
+		struct scatterlist *sglist)
 {
-	struct bio_vec bvec, bvprv = { NULL };
-	struct bvec_iter iter;
-	int nsegs = 0;
-	bool new_bio = false;
-
-	for_each_bio(bio) {
-		bio_for_each_bvec(bvec, bio, iter) {
-			/*
-			 * Only try to merge bvecs from two bios given we
-			 * have done bio internal merge when adding pages
-			 * to bio
-			 */
-			if (new_bio &&
-			    __blk_segment_map_sg_merge(q, &bvec, &bvprv, sg))
-				goto next_bvec;
-
-			if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE)
-				nsegs += __blk_bvec_map_sg(bvec, sglist, sg);
-			else
-				nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg);
- next_bvec:
-			new_bio = false;
-		}
-		if (likely(bio->bi_iter.bi_size)) {
-			bvprv = bvec;
-			new_bio = true;
-		}
-	}
+	if (!*sg)
+		return sglist;
 
-	return nsegs;
+	/*
+	 * If the driver previously mapped a shorter list, we could see a
+	 * termination bit prematurely unless it fully inits the sg table
+	 * on each mapping. We KNOW that there must be more entries here
+	 * or the driver would be buggy, so force clear the termination bit
+	 * to avoid doing a full sg_init_table() in drivers for each command.
+	 */
+	sg_unmark_end(*sg);
+	return sg_next(*sg);
 }
 
 /*
- * map a request to scatterlist, return number of sg entries setup. Caller
- * must make sure sg can hold rq->nr_phys_segments entries
+ * Map a request to scatterlist, return number of sg entries setup. Caller
+ * must make sure sg can hold rq->nr_phys_segments entries.
  */
 int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
 		struct scatterlist *sglist, struct scatterlist **last_sg)
 {
+	struct req_iterator iter = {
+		.bio	= rq->bio,
+		.iter	= rq->bio->bi_iter,
+	};
+	struct phys_vec vec;
 	int nsegs = 0;
 
-	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
-		nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, last_sg);
-	else if (rq->bio)
-		nsegs = __blk_bios_map_sg(q, rq->bio, sglist, last_sg);
+	while (blk_map_iter_next(rq, &iter, &vec)) {
+		*last_sg = blk_next_sg(last_sg, sglist);
+		sg_set_page(*last_sg, phys_to_page(vec.paddr), vec.len,
+				offset_in_page(vec.paddr));
+		nsegs++;
+	}
 
 	if (*last_sg)
 		sg_mark_end(*last_sg);
-- 
2.51.0


From 6783811569aef24b949992bd5c4e6eaac02a0c30 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 6 Jan 2025 09:35:08 +0100
Subject: [PATCH 13/16] block: better split mq vs non-mq code in
 add_disk_fwnode

Add a big conditional for blk-mq vs not mq at the beginning of
add_disk_fwnode so that elevator_init_mq is only called for blk-mq disks,
and add checks that the right methods or set or not set based on the
queue type.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250106083531.799976-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/block/genhd.c b/block/genhd.c
index 5da3c9a64e64..befb7a516bcf 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -400,21 +400,23 @@ int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk,
 	struct device *ddev = disk_to_dev(disk);
 	int ret;
 
-	/* Only makes sense for bio-based to set ->poll_bio */
-	if (queue_is_mq(disk->queue) && disk->fops->poll_bio)
-		return -EINVAL;
-
-	/*
-	 * The disk queue should now be all set with enough information about
-	 * the device for the elevator code to pick an adequate default
-	 * elevator if one is needed, that is, for devices requesting queue
-	 * registration.
-	 */
-	elevator_init_mq(disk->queue);
+	if (queue_is_mq(disk->queue)) {
+		/*
+		 * ->submit_bio and ->poll_bio are bypassed for blk-mq drivers.
+		 */
+		if (disk->fops->submit_bio || disk->fops->poll_bio)
+			return -EINVAL;
 
-	/* Mark bdev as having a submit_bio, if needed */
-	if (disk->fops->submit_bio)
+		/*
+		 * Initialize the I/O scheduler code and pick a default one if
+		 * needed.
+		 */
+		elevator_init_mq(disk->queue);
+	} else {
+		if (!disk->fops->submit_bio)
+			return -EINVAL;
 		bdev_set_flag(disk->part0, BD_HAS_SUBMIT_BIO);
+	}
 
 	/*
 	 * If the driver provides an explicit major number it also must provide
-- 
2.51.0


From 68ed45122249083bf45593ed635474282583352c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 6 Jan 2025 09:35:09 +0100
Subject: [PATCH 14/16] block: remove blk_mq_init_bitmaps

The little work done in blk_mq_init_bitmaps is easier done in the only
caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20250106083531.799976-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-tag.c | 38 ++++++++++++--------------------------
 block/blk-mq.h     |  3 ---
 2 files changed, 12 insertions(+), 29 deletions(-)

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 2cafcf11ee8b..ab4a66791a20 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -544,30 +544,12 @@ static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,
 				       node);
 }
 
-int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags,
-			struct sbitmap_queue *breserved_tags,
-			unsigned int queue_depth, unsigned int reserved,
-			int node, int alloc_policy)
-{
-	unsigned int depth = queue_depth - reserved;
-	bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR;
-
-	if (bt_alloc(bitmap_tags, depth, round_robin, node))
-		return -ENOMEM;
-	if (bt_alloc(breserved_tags, reserved, round_robin, node))
-		goto free_bitmap_tags;
-
-	return 0;
-
-free_bitmap_tags:
-	sbitmap_queue_free(bitmap_tags);
-	return -ENOMEM;
-}
-
 struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 				     unsigned int reserved_tags,
 				     int node, int alloc_policy)
 {
+	unsigned int depth = total_tags - reserved_tags;
+	bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR;
 	struct blk_mq_tags *tags;
 
 	if (total_tags > BLK_MQ_TAG_MAX) {
@@ -582,14 +564,18 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 	spin_lock_init(&tags->lock);
+	if (bt_alloc(&tags->bitmap_tags, depth, round_robin, node))
+		goto out_free_tags;
+	if (bt_alloc(&tags->breserved_tags, reserved_tags, round_robin, node))
+		goto out_free_bitmap_tags;
 
-	if (blk_mq_init_bitmaps(&tags->bitmap_tags, &tags->breserved_tags,
-				total_tags, reserved_tags, node,
-				alloc_policy) < 0) {
-		kfree(tags);
-		return NULL;
-	}
 	return tags;
+
+out_free_bitmap_tags:
+	sbitmap_queue_free(&tags->bitmap_tags);
+out_free_tags:
+	kfree(tags);
+	return NULL;
 }
 
 void blk_mq_free_tags(struct blk_mq_tags *tags)
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 89a20fffa4b1..3bb9ea80f9b6 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -165,9 +165,6 @@ struct blk_mq_alloc_data {
 struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
 		unsigned int reserved_tags, int node, int alloc_policy);
 void blk_mq_free_tags(struct blk_mq_tags *tags);
-int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags,
-		struct sbitmap_queue *breserved_tags, unsigned int queue_depth,
-		unsigned int reserved, int node, int alloc_policy);
 
 unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
 unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags,
-- 
2.51.0


From e7602bb4f3a1234df8b75728ac3260bcb8242612 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 6 Jan 2025 09:35:10 +0100
Subject: [PATCH 15/16] block: remove BLK_MQ_F_NO_SCHED

The only queues that really can't support a scheduler are those that
do not have a gendisk associated with them, and thus can't be used for
non-passthrough commands.  In addition to those null_blk can optionally
set the flag, which is a bad odd.  Replace the null_blk usage with
BLK_MQ_F_NO_SCHED_BY_DEFAULT to keep the expected semantics and then
remove BLK_MQ_F_NO_SCHED as the non-disk queues never call into
elevator_init_mq or blk_register_queue which adds the sysfs attributes.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250106083531.799976-4-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c        |  1 -
 block/bsg-lib.c               |  2 +-
 block/elevator.c              | 20 --------------------
 drivers/block/null_blk/main.c |  4 ++--
 drivers/nvme/host/apple.c     |  1 -
 drivers/nvme/host/core.c      |  1 -
 drivers/ufs/core/ufshcd.c     |  1 -
 include/linux/blk-mq.h        |  2 --
 8 files changed, 3 insertions(+), 29 deletions(-)

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 4b6b20ccdb53..64b3c333aa47 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -185,7 +185,6 @@ static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(STACKING),
 	HCTX_FLAG_NAME(TAG_HCTX_SHARED),
 	HCTX_FLAG_NAME(BLOCKING),
-	HCTX_FLAG_NAME(NO_SCHED),
 	HCTX_FLAG_NAME(NO_SCHED_BY_DEFAULT),
 };
 #undef HCTX_FLAG_NAME
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 32da4a4429ce..93523d8f8195 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -381,7 +381,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 	set->queue_depth = 128;
 	set->numa_node = NUMA_NO_NODE;
 	set->cmd_size = sizeof(struct bsg_job) + dd_job_size;
-	set->flags = BLK_MQ_F_NO_SCHED | BLK_MQ_F_BLOCKING;
+	set->flags = BLK_MQ_F_BLOCKING;
 	if (blk_mq_alloc_tag_set(set))
 		goto out_tag_set;
 
diff --git a/block/elevator.c b/block/elevator.c
index be6e994256ac..b81216c48b6b 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -547,14 +547,6 @@ void elv_unregister(struct elevator_type *e)
 }
 EXPORT_SYMBOL_GPL(elv_unregister);
 
-static inline bool elv_support_iosched(struct request_queue *q)
-{
-	if (!queue_is_mq(q) ||
-	    (q->tag_set->flags & BLK_MQ_F_NO_SCHED))
-		return false;
-	return true;
-}
-
 /*
  * For single queue devices, default to using mq-deadline. If we have multiple
  * queues or mq-deadline is not available, default to "none".
@@ -580,9 +572,6 @@ void elevator_init_mq(struct request_queue *q)
 	struct elevator_type *e;
 	int err;
 
-	if (!elv_support_iosched(q))
-		return;
-
 	WARN_ON_ONCE(blk_queue_registered(q));
 
 	if (unlikely(q->elevator))
@@ -714,9 +703,6 @@ void elv_iosched_load_module(struct gendisk *disk, const char *buf,
 	struct elevator_type *found;
 	const char *name;
 
-	if (!elv_support_iosched(disk->queue))
-		return;
-
 	strscpy(elevator_name, buf, sizeof(elevator_name));
 	name = strstrip(elevator_name);
 
@@ -734,9 +720,6 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 	char elevator_name[ELV_NAME_MAX];
 	int ret;
 
-	if (!elv_support_iosched(disk->queue))
-		return count;
-
 	strscpy(elevator_name, buf, sizeof(elevator_name));
 	ret = elevator_change(disk->queue, strstrip(elevator_name));
 	if (!ret)
@@ -751,9 +734,6 @@ ssize_t elv_iosched_show(struct gendisk *disk, char *name)
 	struct elevator_type *cur = NULL, *e;
 	int len = 0;
 
-	if (!elv_support_iosched(q))
-		return sprintf(name, "none\n");
-
 	if (!q->elevator) {
 		len += sprintf(name+len, "[none] ");
 	} else {
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 178e62cd9a9f..d94ef37480bd 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1792,7 +1792,7 @@ static int null_init_global_tag_set(void)
 	tag_set.queue_depth = g_hw_queue_depth;
 	tag_set.numa_node = g_home_node;
 	if (g_no_sched)
-		tag_set.flags |= BLK_MQ_F_NO_SCHED;
+		tag_set.flags |= BLK_MQ_F_NO_SCHED_BY_DEFAULT;
 	if (g_shared_tag_bitmap)
 		tag_set.flags |= BLK_MQ_F_TAG_HCTX_SHARED;
 	if (g_blocking)
@@ -1817,7 +1817,7 @@ static int null_setup_tagset(struct nullb *nullb)
 	nullb->tag_set->queue_depth = nullb->dev->hw_queue_depth;
 	nullb->tag_set->numa_node = nullb->dev->home_node;
 	if (nullb->dev->no_sched)
-		nullb->tag_set->flags |= BLK_MQ_F_NO_SCHED;
+		nullb->tag_set->flags |= BLK_MQ_F_NO_SCHED_BY_DEFAULT;
 	if (nullb->dev->shared_tag_bitmap)
 		nullb->tag_set->flags |= BLK_MQ_F_TAG_HCTX_SHARED;
 	if (nullb->dev->blocking)
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index 83c60468542c..1de11b722f04 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -1251,7 +1251,6 @@ static int apple_nvme_alloc_tagsets(struct apple_nvme *anv)
 	anv->admin_tagset.timeout = NVME_ADMIN_TIMEOUT;
 	anv->admin_tagset.numa_node = NUMA_NO_NODE;
 	anv->admin_tagset.cmd_size = sizeof(struct apple_nvme_iod);
-	anv->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
 	anv->admin_tagset.driver_data = &anv->adminq;
 
 	ret = blk_mq_alloc_tag_set(&anv->admin_tagset);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 42283d268500..c2250ddef5a2 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4564,7 +4564,6 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 		/* Reserved for fabric connect and keep alive */
 		set->reserved_tags = 2;
 	set->numa_node = ctrl->numa_node;
-	set->flags = BLK_MQ_F_NO_SCHED;
 	if (ctrl->ops->flags & NVME_F_BLOCKING)
 		set->flags |= BLK_MQ_F_BLOCKING;
 	set->cmd_size = cmd_size;
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 8a01e4393159..fd53c9f402c3 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -10412,7 +10412,6 @@ static int ufshcd_add_scsi_host(struct ufs_hba *hba)
 		.nr_hw_queues	= 1,
 		.queue_depth	= hba->nutmrs,
 		.ops		= &ufshcd_tmf_ops,
-		.flags		= BLK_MQ_F_NO_SCHED,
 	};
 	err = blk_mq_alloc_tag_set(&hba->tmf_tag_set);
 	if (err < 0)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 6340293511c9..f2ff0ffa0535 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -676,8 +676,6 @@ enum {
 	BLK_MQ_F_STACKING	= 1 << 2,
 	BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3,
 	BLK_MQ_F_BLOCKING	= 1 << 4,
-	/* Do not allow an I/O scheduler to be configured. */
-	BLK_MQ_F_NO_SCHED	= 1 << 5,
 
 	/*
 	 * Select 'none' during queue registration in case of a single hwq
-- 
2.51.0


From ce32496ec1abe866225f2e2005ceda68cf4c7bf4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 6 Jan 2025 09:35:11 +0100
Subject: [PATCH 16/16] block: simplify tag allocation policy selection

Use a plain BLK_MQ_F_* flag to select the round robin tag selection
instead of overlaying an enum with just two possible values into the
flags space.

Doing so allows adding a BLK_MQ_F_MAX sentinel for simplified overflow
checking in the messy debugfs helpers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20250106083531.799976-5-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c                 | 25 ++++---------------------
 block/blk-mq-tag.c                     |  5 ++---
 block/blk-mq.c                         |  3 +--
 block/blk-mq.h                         |  2 +-
 drivers/ata/ahci.h                     |  2 +-
 drivers/ata/pata_macio.c               |  2 +-
 drivers/ata/sata_mv.c                  |  2 +-
 drivers/ata/sata_nv.c                  |  4 ++--
 drivers/ata/sata_sil24.c               |  1 -
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c |  2 +-
 drivers/scsi/scsi_lib.c                |  4 ++--
 include/linux/blk-mq.h                 | 22 +++++++---------------
 include/linux/libata.h                 |  4 ++--
 include/scsi/scsi_host.h               |  6 ++++--
 14 files changed, 29 insertions(+), 55 deletions(-)

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 64b3c333aa47..adf5f0697b6b 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -172,19 +172,13 @@ static int hctx_state_show(void *data, struct seq_file *m)
 	return 0;
 }
 
-#define BLK_TAG_ALLOC_NAME(name) [BLK_TAG_ALLOC_##name] = #name
-static const char *const alloc_policy_name[] = {
-	BLK_TAG_ALLOC_NAME(FIFO),
-	BLK_TAG_ALLOC_NAME(RR),
-};
-#undef BLK_TAG_ALLOC_NAME
-
 #define HCTX_FLAG_NAME(name) [ilog2(BLK_MQ_F_##name)] = #name
 static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(TAG_QUEUE_SHARED),
 	HCTX_FLAG_NAME(STACKING),
 	HCTX_FLAG_NAME(TAG_HCTX_SHARED),
 	HCTX_FLAG_NAME(BLOCKING),
+	HCTX_FLAG_NAME(TAG_RR),
 	HCTX_FLAG_NAME(NO_SCHED_BY_DEFAULT),
 };
 #undef HCTX_FLAG_NAME
@@ -192,22 +186,11 @@ static const char *const hctx_flag_name[] = {
 static int hctx_flags_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
-	const int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(hctx->flags);
 
-	BUILD_BUG_ON(ARRAY_SIZE(hctx_flag_name) !=
-			BLK_MQ_F_ALLOC_POLICY_START_BIT);
-	BUILD_BUG_ON(ARRAY_SIZE(alloc_policy_name) != BLK_TAG_ALLOC_MAX);
+	BUILD_BUG_ON(ARRAY_SIZE(hctx_flag_name) != ilog2(BLK_MQ_F_MAX));
 
-	seq_puts(m, "alloc_policy=");
-	if (alloc_policy < ARRAY_SIZE(alloc_policy_name) &&
-	    alloc_policy_name[alloc_policy])
-		seq_puts(m, alloc_policy_name[alloc_policy]);
-	else
-		seq_printf(m, "%d", alloc_policy);
-	seq_puts(m, " ");
-	blk_flags_show(m,
-		       hctx->flags ^ BLK_ALLOC_POLICY_TO_MQ_FLAG(alloc_policy),
-		       hctx_flag_name, ARRAY_SIZE(hctx_flag_name));
+	blk_flags_show(m, hctx->flags, hctx_flag_name,
+			ARRAY_SIZE(hctx_flag_name));
 	seq_puts(m, "\n");
 	return 0;
 }
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index ab4a66791a20..b9f417d980b4 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -545,11 +545,10 @@ static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,
 }
 
 struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
-				     unsigned int reserved_tags,
-				     int node, int alloc_policy)
+		unsigned int reserved_tags, unsigned int flags, int node)
 {
 	unsigned int depth = total_tags - reserved_tags;
-	bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR;
+	bool round_robin = flags & BLK_MQ_F_TAG_RR;
 	struct blk_mq_tags *tags;
 
 	if (total_tags > BLK_MQ_TAG_MAX) {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 17f10683d640..2e6132f778fd 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3476,8 +3476,7 @@ static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 
-	tags = blk_mq_init_tags(nr_tags, reserved_tags, node,
-				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
+	tags = blk_mq_init_tags(nr_tags, reserved_tags, set->flags, node);
 	if (!tags)
 		return NULL;
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 3bb9ea80f9b6..c872bbbe6411 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -163,7 +163,7 @@ struct blk_mq_alloc_data {
 };
 
 struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
-		unsigned int reserved_tags, int node, int alloc_policy);
+		unsigned int reserved_tags, unsigned int flags, int node);
 void blk_mq_free_tags(struct blk_mq_tags *tags);
 
 unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 8f40f75ba08c..06781bdde0d2 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -396,7 +396,7 @@ extern const struct attribute_group *ahci_sdev_groups[];
 	.shost_groups		= ahci_shost_groups,			\
 	.sdev_groups		= ahci_sdev_groups,			\
 	.change_queue_depth     = ata_scsi_change_queue_depth,		\
-	.tag_alloc_policy       = BLK_TAG_ALLOC_RR,             	\
+	.tag_alloc_policy_rr	= true,					\
 	.device_configure	= ata_scsi_device_configure
 
 extern struct ata_port_operations ahci_ops;
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index f2f36e55a1f4..4b01bb6880b0 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -935,7 +935,7 @@ static const struct scsi_host_template pata_macio_sht = {
 	.device_configure	= pata_macio_device_configure,
 	.sdev_groups		= ata_common_sdev_groups,
 	.can_queue		= ATA_DEF_QUEUE,
-	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,
+	.tag_alloc_policy_rr	= true,
 };
 
 static struct ata_port_operations pata_macio_ops = {
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index b8f363370e1a..21c72650f9cc 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -672,7 +672,7 @@ static const struct scsi_host_template mv6_sht = {
 	.dma_boundary		= MV_DMA_BOUNDARY,
 	.sdev_groups		= ata_ncq_sdev_groups,
 	.change_queue_depth	= ata_scsi_change_queue_depth,
-	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,
+	.tag_alloc_policy_rr	= true,
 	.device_configure	= ata_scsi_device_configure
 };
 
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 36d99043ef50..823cce5ea1e9 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -385,7 +385,7 @@ static const struct scsi_host_template nv_adma_sht = {
 	.device_configure	= nv_adma_device_configure,
 	.sdev_groups		= ata_ncq_sdev_groups,
 	.change_queue_depth     = ata_scsi_change_queue_depth,
-	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,
+	.tag_alloc_policy_rr	= true,
 };
 
 static const struct scsi_host_template nv_swncq_sht = {
@@ -396,7 +396,7 @@ static const struct scsi_host_template nv_swncq_sht = {
 	.device_configure	= nv_swncq_device_configure,
 	.sdev_groups		= ata_ncq_sdev_groups,
 	.change_queue_depth     = ata_scsi_change_queue_depth,
-	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,
+	.tag_alloc_policy_rr	= true,
 };
 
 /*
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index 72c03cbdaff4..935b13e79dec 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -378,7 +378,6 @@ static const struct scsi_host_template sil24_sht = {
 	.can_queue		= SIL24_MAX_CMDS,
 	.sg_tablesize		= SIL24_MAX_SGE,
 	.dma_boundary		= ATA_DMA_BOUNDARY,
-	.tag_alloc_policy	= BLK_TAG_ALLOC_FIFO,
 	.sdev_groups		= ata_ncq_sdev_groups,
 	.change_queue_depth	= ata_scsi_change_queue_depth,
 	.device_configure	= ata_scsi_device_configure
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 79129c977704..35501d0aa655 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -3345,7 +3345,7 @@ static const struct scsi_host_template sht_v3_hw = {
 	.slave_alloc		= hisi_sas_slave_alloc,
 	.shost_groups		= host_v3_hw_groups,
 	.sdev_groups		= sdev_groups_v3_hw,
-	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,
+	.tag_alloc_policy_rr	= true,
 	.host_reset             = hisi_sas_host_reset,
 	.host_tagset		= 1,
 	.mq_poll		= queue_complete_v3_hw,
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 5cf124e13097..51c496ca9380 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2065,8 +2065,8 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
 	tag_set->queue_depth = shost->can_queue;
 	tag_set->cmd_size = cmd_size;
 	tag_set->numa_node = dev_to_node(shost->dma_dev);
-	tag_set->flags |=
-		BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy);
+	if (shost->hostt->tag_alloc_policy_rr)
+		tag_set->flags |= BLK_MQ_F_TAG_RR;
 	if (shost->queuecommand_may_block)
 		tag_set->flags |= BLK_MQ_F_BLOCKING;
 	tag_set->driver_data = shost;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index f2ff0ffa0535..a0a9007cc1e3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -296,13 +296,6 @@ enum blk_eh_timer_return {
 	BLK_EH_RESET_TIMER,
 };
 
-/* Keep alloc_policy_name[] in sync with the definitions below */
-enum {
-	BLK_TAG_ALLOC_FIFO,	/* allocate starting from 0 */
-	BLK_TAG_ALLOC_RR,	/* allocate starting from last allocated tag */
-	BLK_TAG_ALLOC_MAX
-};
-
 /**
  * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware
  * block device
@@ -677,20 +670,19 @@ enum {
 	BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3,
 	BLK_MQ_F_BLOCKING	= 1 << 4,
 
+	/*
+	 * Alloc tags on a round-robin base instead of the first available one.
+	 */
+	BLK_MQ_F_TAG_RR		= 1 << 5,
+
 	/*
 	 * Select 'none' during queue registration in case of a single hwq
 	 * or shared hwqs instead of 'mq-deadline'.
 	 */
 	BLK_MQ_F_NO_SCHED_BY_DEFAULT	= 1 << 6,
-	BLK_MQ_F_ALLOC_POLICY_START_BIT = 7,
-	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
+
+	BLK_MQ_F_MAX = 1 << 7,
 };
-#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \
-	((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \
-		((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1))
-#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \
-	((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
-		<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
 
 #define BLK_MQ_MAX_DEPTH	(10240)
 #define BLK_MQ_NO_HCTX_IDX	(-1U)
diff --git a/include/linux/libata.h b/include/linux/libata.h
index c1a85d46eba6..be5183d75736 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1467,13 +1467,13 @@ extern const struct attribute_group *ata_common_sdev_groups[];
 #define ATA_SUBBASE_SHT(drv_name)				\
 	__ATA_BASE_SHT(drv_name),				\
 	.can_queue		= ATA_DEF_QUEUE,		\
-	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,		\
+	.tag_alloc_policy_rr	= true,				\
 	.device_configure	= ata_scsi_device_configure
 
 #define ATA_SUBBASE_SHT_QD(drv_name, drv_qd)			\
 	__ATA_BASE_SHT(drv_name),				\
 	.can_queue		= drv_qd,			\
-	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,		\
+	.tag_alloc_policy_rr	= true,				\
 	.device_configure	= ata_scsi_device_configure
 
 #define ATA_BASE_SHT(drv_name)					\
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 2b4ab0369ffb..02823d6af37d 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -438,8 +438,10 @@ struct scsi_host_template {
 	 */
 	short cmd_per_lun;
 
-	/* If use block layer to manage tags, this is tag allocation policy */
-	int tag_alloc_policy;
+	/*
+	 * Allocate tags starting from last allocated tag.
+	 */
+	bool tag_alloc_policy_rr : 1;
 
 	/*
 	 * Track QUEUE_FULL events and reduce queue depth on demand.
-- 
2.51.0