On 7/9/25 7:06 AM, Bart Van Assche wrote:
> Some storage controllers preserve the request order per hardware queue.
> Some but not all device mapper drivers preserve the bio order. Introduce
> the request queue limit member variable 'driver_preserves_write_order' to
> allow block drivers and device mapper drivers to indicate that the order
> of write commands is preserved per hardware queue and hence that
> serialization of writes per zone is not required if all pending writes are
> submitted to the same hardware queue.
>
> Cc: Damien Le Moal <dlemoal@xxxxxxxxxx>
> Cc: Hannes Reinecke <hare@xxxxxxx>
> Cc: 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 | 2 ++
> include/linux/blkdev.h | 5 +++++
> 2 files changed, 7 insertions(+)
>
> diff --git a/block/blk-settings.c b/block/blk-settings.c
> index a000daafbfb4..bceb9a9cb5ba 100644
> --- a/block/blk-settings.c
> +++ b/block/blk-settings.c
> @@ -814,6 +814,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
> }
> t->max_secure_erase_sectors = min_not_zero(t->max_secure_erase_sectors,
> b->max_secure_erase_sectors);
> + t->driver_preserves_write_order = t->driver_preserves_write_order &&
> + b->driver_preserves_write_order;
See blk_stack_limits() and the section:
/*
* Some feaures need to be supported both by the stacking driver and all
* underlying devices. The stacking driver sets these flags before
* stacking the limits, and this will clear the flags if any of the
* underlying devices does not support it.
*/
if (!(b->features & BLK_FEAT_NOWAIT))
t->features &= ~BLK_FEAT_NOWAIT;
if (!(b->features & BLK_FEAT_POLL))
t->features &= ~BLK_FEAT_POLL;
And make driver_preserves_write_order a feature instead of treating it
specially. Also, the name "driver_preserves_write_order" is not great. The
driver may be preserving write order, but the hardware not (e.g. libata and AHCI).
> t->zone_write_granularity = max(t->zone_write_granularity,
> b->zone_write_granularity);
> if (!(t->features & BLK_FEAT_ZONED)) {
> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
> index 5f14c20c8bc0..4dec1d91b7f2 100644
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -413,6 +413,11 @@ struct queue_limits {
>
> unsigned int max_open_zones;
> unsigned int max_active_zones;
> + /*
> + * Whether or not the block driver preserves the order of write
> + * requests per hardware queue. Set by the block driver.
> + */
> + bool driver_preserves_write_order;
>
> /*
> * Drivers that set dma_alignment to less than 511 must be prepared to
--
Damien Le Moal
Western Digital Research
