On 2020/06/29 8:01, Matias Bjorling wrote:
> The NVMe Zoned Namespace Command Set adds support for associating
> data to a zone through the Zone Descriptor Extension feature.
>
> The Zone Descriptor Extension size is fixed to a multiple of 64
> bytes. A value of zero communicates the feature is not available.
> A value larger than zero communites the feature is available, and
> the specified Zone Descriptor Extension size in bytes.
>
> The Zone Descriptor Extension feature is only available in the
> NVMe Zoned Namespaces Command Set. Devices that supports ZAC/ZBC
> therefore reports this value as zero, where as the NVMe device
> driver reports the Zone Descriptor Extension size from the
> specific device.
>
> Signed-off-by: Matias Bjørling <matias.bjorling@xxxxxxx>
> ---
> Documentation/block/queue-sysfs.rst | 6 ++++++
> block/blk-sysfs.c | 15 ++++++++++++++-
> drivers/nvme/host/zns.c | 1 +
> drivers/scsi/sd_zbc.c | 1 +
> include/linux/blkdev.h | 22 ++++++++++++++++++++++
> 5 files changed, 44 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst
> index f261a5c84170..c4fa195c87b4 100644
> --- a/Documentation/block/queue-sysfs.rst
> +++ b/Documentation/block/queue-sysfs.rst
> @@ -265,4 +265,10 @@ devices are described in the ZBC (Zoned Block Commands) and ZAC
> do not support zone commands, they will be treated as regular block devices
> and zoned will report "none".
>
> +zone_desc_ext_bytes (RO)
> +-------------------------
> +This indicates the zone description extension (ZDE) size, in bytes, of a zoned
> +block device. A value of '0' means that zone description extension is not
> +supported.
> +
> Jens Axboe <jens.axboe@xxxxxxxxxx>, February 2009
> diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
> index 624bb4d85fc7..0c99454823b7 100644
> --- a/block/blk-sysfs.c
> +++ b/block/blk-sysfs.c
> @@ -315,6 +315,12 @@ static ssize_t queue_max_active_zones_show(struct request_queue *q, char *page)
> return queue_var_show(queue_max_active_zones(q), page);
> }
>
> +static ssize_t queue_zone_desc_ext_bytes_show(struct request_queue *q,
> + char *page)
> +{
> + return queue_var_show(queue_zone_desc_ext_bytes(q), page);
> +}
> +
> static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
> {
> return queue_var_show((blk_queue_nomerges(q) << 1) |
> @@ -687,6 +693,11 @@ static struct queue_sysfs_entry queue_max_active_zones_entry = {
> .show = queue_max_active_zones_show,
> };
>
> +static struct queue_sysfs_entry queue_zone_desc_ext_bytes_entry = {
> + .attr = {.name = "zone_desc_ext_bytes", .mode = 0444 },
> + .show = queue_zone_desc_ext_bytes_show,
> +};
> +
> static struct queue_sysfs_entry queue_nomerges_entry = {
> .attr = {.name = "nomerges", .mode = 0644 },
> .show = queue_nomerges_show,
> @@ -787,6 +798,7 @@ static struct attribute *queue_attrs[] = {
> &queue_nr_zones_entry.attr,
> &queue_max_open_zones_entry.attr,
> &queue_max_active_zones_entry.attr,
Which tree is this patch based on ? Not I have seen any patch introducing max
active zones.
> + &queue_zone_desc_ext_bytes_entry.attr,
> &queue_nomerges_entry.attr,
> &queue_rq_affinity_entry.attr,
> &queue_iostats_entry.attr,
> @@ -815,7 +827,8 @@ static umode_t queue_attr_visible(struct kobject *kobj, struct attribute *attr,
> return 0;
>
> if ((attr == &queue_max_open_zones_entry.attr ||
> - attr == &queue_max_active_zones_entry.attr) &&
> + attr == &queue_max_active_zones_entry.attr ||
> + attr == &queue_zone_desc_ext_bytes_entry.attr) &&
> !blk_queue_is_zoned(q))
> return 0;
>
> diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
> index 502070763266..5792d953a8f3 100644
> --- a/drivers/nvme/host/zns.c
> +++ b/drivers/nvme/host/zns.c
> @@ -84,6 +84,7 @@ int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
> blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
> blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1);
> blk_queue_max_active_zones(q, le32_to_cpu(id->mar) + 1);
> + blk_queue_zone_desc_ext_bytes(q, id->lbafe[lbaf].zdes << 6);
> free_data:
> kfree(id);
> return status;
> diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
> index d8b2c49d645b..a4b6d6cf5457 100644
> --- a/drivers/scsi/sd_zbc.c
> +++ b/drivers/scsi/sd_zbc.c
> @@ -722,6 +722,7 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
> else
> blk_queue_max_open_zones(q, sdkp->zones_max_open);
> blk_queue_max_active_zones(q, 0);
> + blk_queue_zone_desc_ext_bytes(q, 0);
> nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
>
> /* READ16/WRITE16 is mandatory for ZBC disks */
> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
> index 3776140f8f20..2ed55055f68d 100644
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -522,6 +522,7 @@ struct request_queue {
> unsigned long *seq_zones_wlock;
> unsigned int max_open_zones;
> unsigned int max_active_zones;
> + unsigned int zone_desc_ext_bytes;
Why is this not a queue limit ? This may need to be to be gracefully handled by
device mapper for a target device using multiple zoned drives.
> #endif /* CONFIG_BLK_DEV_ZONED */
>
> /*
> @@ -753,6 +754,18 @@ static inline unsigned int queue_max_active_zones(const struct request_queue *q)
> {
> return q->max_active_zones;
> }
> +
> +static inline void blk_queue_zone_desc_ext_bytes(struct request_queue *q,
> + unsigned int zone_desc_ext_bytes)
> +{
> + q->zone_desc_ext_bytes = zone_desc_ext_bytes;
> +}
> +
> +static inline unsigned int queue_zone_desc_ext_bytes(
> + const struct request_queue *q)
> +{
> + return q->zone_desc_ext_bytes;
> +}
> #else /* CONFIG_BLK_DEV_ZONED */
> static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
> {
> @@ -784,6 +797,15 @@ static inline unsigned int queue_max_active_zones(const struct request_queue *q)
> {
> return 0;
> }
> +static inline void blk_queue_zone_desc_ext_bytes(struct request_queue *q,
> + unsigned int zone_desc_ext_bytes)
> +{
> +}
> +static inline unsigned int queue_zone_desc_ext_bytes(
> + const struct request_queue *q)
> +{
> + return 0;
> +}
> #endif /* CONFIG_BLK_DEV_ZONED */
>
> static inline bool rq_is_sync(struct request *rq)
>
--
Damien Le Moal
Western Digital Research
