dm: Use the block layer zone append emulation

For targets requiring zone append operation emulation with regular
writes (e.g. dm-crypt), we can use the block layer emulation provided by
zone write plugging. Remove DM implemented zone append emulation and
enable the block layer one.

This is done by setting the max_zone_append_sectors limit of the
mapped device queue to 0 for mapped devices that have a target table
that cannot support native zone append operations (e.g. dm-crypt).
Such mapped devices are flagged with the DMF_EMULATE_ZONE_APPEND flag.
dm_split_and_process_bio() is modified to execute
blk_zone_write_plug_bio() for such device to let the block layer
transform zone append operations into regular writes.  This is done
after ensuring that the submitted BIO is split if it straddles zone
boundaries. Both changes are implemented unsing the inline helpers
dm_zone_write_plug_bio() and dm_zone_bio_needs_split() respectively.

dm_revalidate_zones() is also modified to use the block layer provided
function blk_revalidate_disk_zones() so that all zone resources needed
for zone append emulation are initialized by the block layer without DM
core needing to do anything. Since the device table is not yet live when
dm_revalidate_zones() is executed, enabling the use of
blk_revalidate_disk_zones() requires adding a pointer to the device
table in struct mapped_device. This avoids errors in
dm_blk_report_zones() trying to get the table with dm_get_live_table().
The mapped device table pointer is set to the table passed as argument
to dm_revalidate_zones() before calling blk_revalidate_disk_zones() and
reset to NULL after this function returns to restore the live table
handling for user call of report zones.

All the code related to zone append emulation is removed from
dm-zone.c. This leads to simplifications of the functions __map_bio()
and dm_zone_endio(). This later function now only needs to deal with
completions of real zone append operations for targets that support it.
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
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/20240408014128.205141-13-dlemoal@kernel.orgSigned-off-by: Jens Axboe <axboe@kernel.dk>

drivers/md/dm-core.h

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

drivers/md/dm.c

@@ -1422,25 +1422,12 @@ static void __map_bio(struct bio *clone)
 		down(&md->swap_bios_semaphore);
 	}
 
-	if (static_branch_unlikely(&zoned_enabled)) {
-		/*
-		 * Check if the IO needs a special mapping due to zone append
-		 * emulation on zoned target. In this case, dm_zone_map_bio()
-		 * calls the target map operation.
-		 */
-		if (unlikely(dm_emulate_zone_append(md)))
-			r = dm_zone_map_bio(tio);
-		else
-			goto do_map;
-	} else {
-do_map:
-		if (likely(ti->type->map == linear_map))
-			r = linear_map(ti, clone);
-		else if (ti->type->map == stripe_map)
-			r = stripe_map(ti, clone);
-		else
-			r = ti->type->map(ti, clone);
-	}
+	if (likely(ti->type->map == linear_map))
+		r = linear_map(ti, clone);
+	else if (ti->type->map == stripe_map)
+		r = stripe_map(ti, clone);
+	else
+		r = ti->type->map(ti, clone);
 
 	switch (r) {
 	case DM_MAPIO_SUBMITTED:
@@ -1768,6 +1755,33 @@ static void init_clone_info(struct clone_info *ci, struct dm_io *io,
 		ci->sector_count = 0;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
+					   struct bio *bio)
+{
+	/*
+	 * For mapped device that need zone append emulation, we must
+	 * split any large BIO that straddles zone boundaries.
+	 */
+	return dm_emulate_zone_append(md) && bio_straddles_zones(bio) &&
+		!bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING);
+}
+static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
+{
+	return dm_emulate_zone_append(md) && blk_zone_plug_bio(bio, 0);
+}
+#else
+static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
+					   struct bio *bio)
+{
+	return false;
+}
+static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
+{
+	return false;
+}
+#endif
+
 /*
  * Entry point to split a bio into clones and submit them to the targets.
  */
@@ -1777,19 +1791,32 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 	struct clone_info ci;
 	struct dm_io *io;
 	blk_status_t error = BLK_STS_OK;
-	bool is_abnormal;
+	bool is_abnormal, need_split;
+
+	need_split = is_abnormal = is_abnormal_io(bio);
+	if (static_branch_unlikely(&zoned_enabled))
+		need_split = is_abnormal || dm_zone_bio_needs_split(md, bio);
 
-	is_abnormal = is_abnormal_io(bio);
-	if (unlikely(is_abnormal)) {
+	if (unlikely(need_split)) {
 		/*
 		 * Use bio_split_to_limits() for abnormal IO (e.g. discard, etc)
 		 * otherwise associated queue_limits won't be imposed.
+		 * Also split the BIO for mapped devices needing zone append
+		 * emulation to ensure that the BIO does not cross zone
+		 * boundaries.
 		 */
 		bio = bio_split_to_limits(bio);
 		if (!bio)
 			return;
 	}
 
+	/*
+	 * Use the block layer zone write plugging for mapped devices that
+	 * need zone append emulation (e.g. dm-crypt).
+	 */
+	if (static_branch_unlikely(&zoned_enabled) && dm_zone_plug_bio(md, bio))
+		return;
+
 	/* Only support nowait for normal IO */
 	if (unlikely(bio->bi_opf & REQ_NOWAIT) && !is_abnormal) {
 		io = alloc_io(md, bio, GFP_NOWAIT);
@@ -2010,7 +2037,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
 		md->dax_dev = NULL;
 	}
 
-	dm_cleanup_zoned_dev(md);
 	if (md->disk) {
 		spin_lock(&_minor_lock);
 		md->disk->private_data = NULL;

drivers/md/dm.h

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