block: Allow zero value of max_zone_append_sectors queue limit

In preparation for adding a generic zone append emulation using zone
write plugging, allow device drivers supporting zoned block device to
set a the max_zone_append_sectors queue limit of a device to 0 to
indicate the lack of native support for zone append operations and that
the block layer should emulate these operations using regular write
operations.

blk_queue_max_zone_append_sectors() is modified to allow passing 0 as
the max_zone_append_sectors argument. The function
queue_max_zone_append_sectors() is also modified to ensure that the
minimum of the max_hw_sectors and chunk_sectors limit is used whenever
the max_zone_append_sectors limit is 0. This minimum is consistent with
the value set for the max_zone_append_sectors limit by the function
blk_validate_zoned_limits() when limits for a queue are validated.

The helper functions queue_emulates_zone_append() and
bdev_emulates_zone_append() are added to test if a queue (or block
device) emulates zone append operations.

In order for blk_revalidate_disk_zones() to accept zoned block devices
relying on zone append emulation, the direct check to the
max_zone_append_sectors queue limit of the disk is replaced by a check
using the value returned by queue_max_zone_append_sectors(). Similarly,
queue_zone_append_max_show() is modified to use the same accessor so
that the sysfs attribute advertizes the non-zero limit that will be
used, regardless if it is for native or emulated commands.

For stacking drivers, a top device should not need to care if the
underlying devices have native or emulated zone append operations.
blk_stack_limits() is thus modified to set the top device
max_zone_append_sectors limit using the new accessor
queue_limits_max_zone_append_sectors(). queue_max_zone_append_sectors()
is modified to use this function as well. Stacking drivers that require
zone append emulation, e.g. dm-crypt, can still request this feature by
calling blk_queue_max_zone_append_sectors() with a 0 limit.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: Hans Holmberg <hans.holmberg@wdc.com>
Tested-by: Dennis Maisenbacher <dennis.maisenbacher@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20240408014128.205141-10-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

5 files changed, 42 insertions, 17 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index a16b5abdbbf5..3bf28149e104 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -602,7 +602,7 @@ 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;
diff --git a/block/blk-settings.c b/block/blk-settings.c
index cdbaef159c4b..c0197e1e7485 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -412,24 +412,32 @@ 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;
 }
@@ -756,8 +764,8 @@ 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,
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 8c8f69d8ba48..e3ed5a921aff 100644
--- a/block/blk-sysfs.c
+++ b/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);
 }
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 4b21a1ec00d4..fcc1284b7c19 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1692,7 +1692,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 		return -ENODEV;
 	}
 
-	if (!q->limits.max_zone_append_sectors) {
+	if (!queue_max_zone_append_sectors(q)) {
 		pr_warn("%s: Invalid 0 maximum zone append limit\n",
 			disk->disk_name);
 		return -ENODEV;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 348b57ca0425..46613bf6a402 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1173,12 +1173,29 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 	return q->limits.max_segment_size;
 }
 
-static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
+static inline unsigned int queue_limits_max_zone_append_sectors(struct queue_limits *l)
 {
+	unsigned int max_sectors = min(l->chunk_sectors, l->max_hw_sectors);
 
-	const struct queue_limits *l = &q->limits;
+	return min_not_zero(l->max_zone_append_sectors, max_sectors);
+}
+
+static inline unsigned int queue_max_zone_append_sectors(struct request_queue *q)
+{
+	if (!blk_queue_is_zoned(q))
+		return 0;
 
-	return min(l->max_zone_append_sectors, l->max_sectors);
+	return queue_limits_max_zone_append_sectors(&q->limits);
+}
+
+static inline bool queue_emulates_zone_append(struct request_queue *q)
+{
+	return blk_queue_is_zoned(q) && !q->limits.max_zone_append_sectors;
+}
+
+static inline bool bdev_emulates_zone_append(struct block_device *bdev)
+{
+	return queue_emulates_zone_append(bdev_get_queue(bdev));
 }
 
 static inline unsigned int