On 11/15/23 06:16, Bart Van Assche wrote:
> Many but not all storage controllers require serialization of zoned writes.
> Introduce two new request queue limit member variables related to write
> serialization. 'driver_preserves_write_order' allows block drivers to
> indicate that the order of write commands is preserved and hence that
> serialization of writes per zone is not required. 'use_zone_write_lock' is
> set by disk_set_zoned() if and only if the block device has zones and if
> the block driver does not preserve the order of write requests.
>
> Reviewed-by: Damien Le Moal <dlemoal@xxxxxxxxxx>
> Reviewed-by: Hannes Reinecke <hare@xxxxxxx>
> Reviewed-by: Nitesh Shetty <nj.shetty@xxxxxxxxxxx>
> Cc: Christoph Hellwig <hch@xxxxxx>
> Cc: Ming Lei <ming.lei@xxxxxxxxxx>
> Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
> ---
> block/blk-settings.c | 15 +++++++++++++++
> block/blk-zoned.c | 1 +
> include/linux/blkdev.h | 10 ++++++++++
> 3 files changed, 26 insertions(+)
>
> diff --git a/block/blk-settings.c b/block/blk-settings.c
> index 0046b447268f..4c776c08f190 100644
> --- a/block/blk-settings.c
> +++ b/block/blk-settings.c
> @@ -56,6 +56,8 @@ void blk_set_default_limits(struct queue_limits *lim)
> lim->alignment_offset = 0;
> lim->io_opt = 0;
> lim->misaligned = 0;
> + lim->driver_preserves_write_order = false;
> + lim->use_zone_write_lock = false;
> lim->zoned = BLK_ZONED_NONE;
> lim->zone_write_granularity = 0;
> lim->dma_alignment = 511;
> @@ -82,6 +84,8 @@ void blk_set_stacking_limits(struct queue_limits *lim)
> lim->max_dev_sectors = UINT_MAX;
> lim->max_write_zeroes_sectors = UINT_MAX;
> lim->max_zone_append_sectors = UINT_MAX;
> + /* Request-based stacking drivers do not reorder requests. */
Rereading this patch, I do not think this statement is correct. I seriously
doubt that multipath will preserve write command order in all cases...
> + lim->driver_preserves_write_order = true;
... so it is likely much safer to set the default to "false" as that is the
default for all requests in general.
> }
> EXPORT_SYMBOL(blk_set_stacking_limits);
>
> @@ -685,6 +689,10 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
> b->max_secure_erase_sectors);
> t->zone_write_granularity = max(t->zone_write_granularity,
> b->zone_write_granularity);
> + t->driver_preserves_write_order = t->driver_preserves_write_order &&
> + b->driver_preserves_write_order;
> + t->use_zone_write_lock = t->use_zone_write_lock ||
> + b->use_zone_write_lock;
Very minor nit: splitting the line after the equal would make this more readable.
> t->zoned = max(t->zoned, b->zoned);
> return ret;
> }
> @@ -949,6 +957,13 @@ void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
> }
>
> q->limits.zoned = model;
> + /*
> + * Use the zone write lock only for zoned block devices and only if
> + * the block driver does not preserve the order of write commands.
> + */
> + q->limits.use_zone_write_lock = model != BLK_ZONED_NONE &&
> + !q->limits.driver_preserves_write_order;
> +
> if (model != BLK_ZONED_NONE) {
> /*
> * Set the zone write granularity to the device logical block
> diff --git a/block/blk-zoned.c b/block/blk-zoned.c
> index 619ee41a51cc..112620985bff 100644
> --- a/block/blk-zoned.c
> +++ b/block/blk-zoned.c
> @@ -631,6 +631,7 @@ void disk_clear_zone_settings(struct gendisk *disk)
> q->limits.chunk_sectors = 0;
> q->limits.zone_write_granularity = 0;
> q->limits.max_zone_append_sectors = 0;
> + q->limits.use_zone_write_lock = false;
>
> blk_mq_unfreeze_queue(q);
> }
> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
> index 51fa7ffdee83..2d452f5a36c8 100644
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -316,6 +316,16 @@ struct queue_limits {
> unsigned char misaligned;
> unsigned char discard_misaligned;
> unsigned char raid_partial_stripes_expensive;
> + /*
> + * Whether or not the block driver preserves the order of write
> + * requests. Set by the block driver.
> + */
> + bool driver_preserves_write_order;
> + /*
> + * Whether or not zone write locking should be used. Set by
> + * disk_set_zoned().
> + */
> + bool use_zone_write_lock;
> enum blk_zoned_model zoned;
>
> /*
--
Damien Le Moal
Western Digital Research
