block: add max_open_zones to blk-sysfs

Add a new max_open_zones definition in the sysfs documentation.
This definition will be common for all devices utilizing the zoned block
device support in the kernel.

Export max open zones according to this new definition for NVMe Zoned
Namespace devices, ZAC ATA devices (which are treated as SCSI devices by
the kernel), and ZBC SCSI devices.

Add the new max_open_zones member to struct request_queue, rather
than as a queue limit, since this property cannot be split across stacking
drivers.

Signed-off-by: Niklas Cassel <[email protected]>
Reviewed-by: Javier González <[email protected]>
Reviewed-by: Damien Le Moal <[email protected]>
Reviewed-by: Johannes Thumshirn <[email protected]>
Reviewed-by: Martin K. Petersen <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>

Documentation/ABI/testing/sysfs-block

@@ -273,6 +273,15 @@ Description:
 		device ("host-aware" or "host-managed" zone model). For regular
 		block devices, the value is always 0.
 
+What:		/sys/block/<disk>/queue/max_open_zones
+Date:		July 2020
+Contact:	Niklas Cassel <[email protected]>
+Description:
+		For zoned block devices (zoned attribute indicating
+		"host-managed" or "host-aware"), the sum of zones belonging to
+		any of the zone states: EXPLICIT OPEN or IMPLICIT OPEN,
+		is limited by this value. If this value is 0, there is no limit.
+
 What:		/sys/block/<disk>/queue/chunk_sectors
 Date:		September 2016
 Contact:	Hannes Reinecke <[email protected]>

Documentation/block/queue-sysfs.rst

@@ -117,6 +117,13 @@ Maximum number of elements in a DMA scatter/gather list with integrity
 data that will be submitted by the block layer core to the associated
 block driver.
 
+max_open_zones (RO)
+-------------------
+For zoned block devices (zoned attribute indicating "host-managed" or
+"host-aware"), the sum of zones belonging to any of the zone states:
+EXPLICIT OPEN or IMPLICIT OPEN, is limited by this value.
+If this value is 0, there is no limit.
+
 max_sectors_kb (RW)
 -------------------
 This is the maximum number of kilobytes that the block layer will allow

block/blk-sysfs.c

@@ -306,6 +306,11 @@ static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
 	return queue_var_show(blk_queue_nr_zones(q), page);
 }
 
+static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_max_open_zones(q), page);
+}
+
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
 {
 	return queue_var_show((blk_queue_nomerges(q) << 1) |
@@ -668,6 +673,11 @@ static struct queue_sysfs_entry queue_nr_zones_entry = {
 	.show = queue_nr_zones_show,
 };
 
+static struct queue_sysfs_entry queue_max_open_zones_entry = {
+	.attr = {.name = "max_open_zones", .mode = 0444 },
+	.show = queue_max_open_zones_show,
+};
+
 static struct queue_sysfs_entry queue_nomerges_entry = {
 	.attr = {.name = "nomerges", .mode = 0644 },
 	.show = queue_nomerges_show,
@@ -766,6 +776,7 @@ static struct attribute *queue_attrs[] = {
 	&queue_nonrot_entry.attr,
 	&queue_zoned_entry.attr,
 	&queue_nr_zones_entry.attr,
+	&queue_max_open_zones_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
 	&queue_iostats_entry.attr,
@@ -793,6 +804,10 @@ static umode_t queue_attr_visible(struct kobject *kobj, struct attribute *attr,
 		(!q->mq_ops || !q->mq_ops->timeout))
 			return 0;
 
+	if (attr == &queue_max_open_zones_entry.attr &&
+	    !blk_queue_is_zoned(q))
+		return 0;
+
 	return attr->mode;
 }
 

drivers/nvme/host/zns.c

@@ -96,6 +96,7 @@ int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
 
 	q->limits.zoned = BLK_ZONED_HM;
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
+	blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1);
 free_data:
 	kfree(id);
 	return status;

drivers/scsi/sd_zbc.c

@@ -717,6 +717,10 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 	/* The drive satisfies the kernel restrictions: set it up */
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
+	if (sdkp->zones_max_open == U32_MAX)
+		blk_queue_max_open_zones(q, 0);
+	else
+		blk_queue_max_open_zones(q, sdkp->zones_max_open);
 	nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
 
 	/* READ16/WRITE16 is mandatory for ZBC disks */

include/linux/blkdev.h

@@ -513,6 +513,7 @@ struct request_queue {
 	unsigned int		nr_zones;
 	unsigned long		*conv_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
+	unsigned int		max_open_zones;
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 	/*
@@ -722,6 +723,17 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q,
 		return true;
 	return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap);
 }
+
+static inline void blk_queue_max_open_zones(struct request_queue *q,
+		unsigned int max_open_zones)
+{
+	q->max_open_zones = max_open_zones;
+}
+
+static inline unsigned int queue_max_open_zones(const struct request_queue *q)
+{
+	return q->max_open_zones;
+}
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
 {
@@ -737,6 +749,10 @@ static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 {
 	return 0;
 }
+static inline unsigned int queue_max_open_zones(const struct request_queue *q)
+{
+	return 0;
+}
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
@@ -1519,6 +1535,15 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 	return 0;
 }
 
+static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return queue_max_open_zones(q);
+	return 0;
+}
+
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;