null_blk: Introduce zone_append_max_sectors attribute

Add the zone_append_max_sectors configfs attribute and module parameter
to allow configuring the maximum number of 512B sectors of zone append
operations. This attribute is meaningful only for zoned null block
devices.

If not specified, the default is unchanged and the zoned device max
append sectors limit is set to the device max sectors limit.
If a non 0 value is used for this attribute, which is the default,
then native support for zone append operations is enabled.
Setting a 0 value disables native zone append operations support to
instead use the block layer emulation.

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: Chaitanya Kulkarni <kch@nvidia.com>
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/20240408014128.205141-17-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: damien-lemoal

drivers/block/null_blk/main.c

@@ -253,6 +253,11 @@ static unsigned int g_zone_max_active;
 module_param_named(zone_max_active, g_zone_max_active, uint, 0444);
 MODULE_PARM_DESC(zone_max_active, "Maximum number of active zones when block device is zoned. Default: 0 (no limit)");
 
+static int g_zone_append_max_sectors = INT_MAX;
+module_param_named(zone_append_max_sectors, g_zone_append_max_sectors, int, 0444);
+MODULE_PARM_DESC(zone_append_max_sectors,
+		 "Maximum size of a zone append command (in 512B sectors). Specify 0 for zone append emulation");
+
 static struct nullb_device *null_alloc_dev(void);
 static void null_free_dev(struct nullb_device *dev);
 static void null_del_dev(struct nullb *nullb);
@@ -436,6 +441,7 @@ NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
 NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
+NULLB_DEVICE_ATTR(zone_append_max_sectors, uint, NULL);
 NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
 NULLB_DEVICE_ATTR(no_sched, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tags, bool, NULL);
@@ -580,6 +586,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_zone_nr_conv,
 	&nullb_device_attr_zone_max_open,
 	&nullb_device_attr_zone_max_active,
+	&nullb_device_attr_zone_append_max_sectors,
 	&nullb_device_attr_zone_readonly,
 	&nullb_device_attr_zone_offline,
 	&nullb_device_attr_virt_boundary,
@@ -671,7 +678,7 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page)
 			"shared_tags,size,submit_queues,use_per_node_hctx,"
 			"virt_boundary,zoned,zone_capacity,zone_max_active,"
 			"zone_max_open,zone_nr_conv,zone_offline,zone_readonly,"
-			"zone_size\n");
+			"zone_size,zone_append_max_sectors\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -751,6 +758,7 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->zone_nr_conv = g_zone_nr_conv;
 	dev->zone_max_open = g_zone_max_open;
 	dev->zone_max_active = g_zone_max_active;
+	dev->zone_append_max_sectors = g_zone_append_max_sectors;
 	dev->virt_boundary = g_virt_boundary;
 	dev->no_sched = g_no_sched;
 	dev->shared_tags = g_shared_tags;

drivers/block/null_blk/null_blk.h

@@ -82,6 +82,7 @@ struct nullb_device {
 	unsigned int zone_nr_conv; /* number of conventional zones */
 	unsigned int zone_max_open; /* max number of open zones */
 	unsigned int zone_max_active; /* max number of active zones */
+	unsigned int zone_append_max_sectors; /* Max sectors per zone append command */
 	unsigned int submit_queues; /* number of submission queues */
 	unsigned int prev_submit_queues; /* number of submission queues before change */
 	unsigned int poll_queues; /* number of IOPOLL submission queues */

drivers/block/null_blk/zoned.c

@@ -103,6 +103,11 @@ int null_init_zoned_dev(struct nullb_device *dev,
 			dev->zone_nr_conv);
 	}
 
+	dev->zone_append_max_sectors =
+		min(ALIGN_DOWN(dev->zone_append_max_sectors,
+			       dev->blocksize >> SECTOR_SHIFT),
+		    zone_capacity_sects);
+
 	/* Max active zones has to be < nbr of seq zones in order to be enforceable */
 	if (dev->zone_max_active >= dev->nr_zones - dev->zone_nr_conv) {
 		dev->zone_max_active = 0;
@@ -154,7 +159,7 @@ int null_init_zoned_dev(struct nullb_device *dev,
 
 	lim->zoned = true;
 	lim->chunk_sectors = dev->zone_size_sects;
-	lim->max_zone_append_sectors = dev->zone_size_sects;
+	lim->max_zone_append_sectors = dev->zone_append_max_sectors;
 	lim->max_open_zones = dev->zone_max_open;
 	lim->max_active_zones = dev->zone_max_active;
 	return 0;
@@ -163,10 +168,16 @@ int null_init_zoned_dev(struct nullb_device *dev,
 int null_register_zoned_dev(struct nullb *nullb)
 {
 	struct request_queue *q = nullb->q;
+	struct gendisk *disk = nullb->disk;
 
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
-	nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0);
-	return blk_revalidate_disk_zones(nullb->disk, NULL);
+	disk->nr_zones = bdev_nr_zones(disk->part0);
+
+	pr_info("%s: using %s zone append\n",
+		disk->disk_name,
+		queue_emulates_zone_append(q) ? "emulated" : "native");
+
+	return blk_revalidate_disk_zones(disk, NULL);
 }
 
 void null_free_zoned_dev(struct nullb_device *dev)
@@ -365,6 +376,9 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 
 	trace_nullb_zone_op(cmd, zno, zone->cond);
 
+	if (WARN_ON_ONCE(append && !dev->zone_append_max_sectors))
+		return BLK_STS_IOERR;
+
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) {
 		if (append)
 			return BLK_STS_IOERR;