On 6/13/23 05:33, Bart Van Assche wrote:
> Add support for configuring the maximum segment size.
>
> Add support for segments smaller than the page size.
>
> This patch enables testing segments smaller than the page size with a
> driver that does not call blk_rq_map_sg().
>
> Reviewed-by: Chaitanya Kulkarni <kch@xxxxxxxxxx>
> Reviewed-by: Luis Chamberlain <mcgrof@xxxxxxxxxx>
> Cc: Christoph Hellwig <hch@xxxxxx>
> Cc: Ming Lei <ming.lei@xxxxxxxxxx>
> Cc: Damien Le Moal <damien.lemoal@xxxxxxxxxxxxxxxxxx>
> Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
> ---
> drivers/block/null_blk/main.c | 19 ++++++++++++++++---
> drivers/block/null_blk/null_blk.h | 1 +
> 2 files changed, 17 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
> index b3fedafe301e..9c9098f1bd52 100644
> --- a/drivers/block/null_blk/main.c
> +++ b/drivers/block/null_blk/main.c
> @@ -157,6 +157,10 @@ static int g_max_sectors;
> module_param_named(max_sectors, g_max_sectors, int, 0444);
> MODULE_PARM_DESC(max_sectors, "Maximum size of a command (in 512B sectors)");
>
> +static unsigned int g_max_segment_size = BLK_MAX_SEGMENT_SIZE;
> +module_param_named(max_segment_size, g_max_segment_size, int, 0444);
> +MODULE_PARM_DESC(max_segment_size, "Maximum size of a segment in bytes");
> +
> static unsigned int nr_devices = 1;
> module_param(nr_devices, uint, 0444);
> MODULE_PARM_DESC(nr_devices, "Number of devices to register");
> @@ -409,6 +413,7 @@ NULLB_DEVICE_ATTR(home_node, uint, NULL);
> NULLB_DEVICE_ATTR(queue_mode, uint, NULL);
> NULLB_DEVICE_ATTR(blocksize, uint, NULL);
> NULLB_DEVICE_ATTR(max_sectors, uint, NULL);
> +NULLB_DEVICE_ATTR(max_segment_size, uint, NULL);
> NULLB_DEVICE_ATTR(irqmode, uint, NULL);
> NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL);
> NULLB_DEVICE_ATTR(index, uint, NULL);
> @@ -550,6 +555,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
> &nullb_device_attr_queue_mode,
> &nullb_device_attr_blocksize,
> &nullb_device_attr_max_sectors,
> + &nullb_device_attr_max_segment_size,
> &nullb_device_attr_irqmode,
> &nullb_device_attr_hw_queue_depth,
> &nullb_device_attr_index,
> @@ -652,7 +658,8 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page)
> return snprintf(page, PAGE_SIZE,
> "badblocks,blocking,blocksize,cache_size,"
> "completion_nsec,discard,home_node,hw_queue_depth,"
> - "irqmode,max_sectors,mbps,memory_backed,no_sched,"
> + "irqmode,max_sectors,max_segment_size,mbps,"
> + "memory_backed,no_sched,"
> "poll_queues,power,queue_mode,shared_tag_bitmap,size,"
> "submit_queues,use_per_node_hctx,virt_boundary,zoned,"
> "zone_capacity,zone_max_active,zone_max_open,"
> @@ -722,6 +729,7 @@ static struct nullb_device *null_alloc_dev(void)
> dev->queue_mode = g_queue_mode;
> dev->blocksize = g_bs;
> dev->max_sectors = g_max_sectors;
> + dev->max_segment_size = g_max_segment_size;
> dev->irqmode = g_irqmode;
> dev->hw_queue_depth = g_hw_queue_depth;
> dev->blocking = g_blocking;
> @@ -1248,6 +1256,8 @@ static int null_transfer(struct nullb *nullb, struct page *page,
> unsigned int valid_len = len;
> int err = 0;
>
> + WARN_ONCE(len > dev->max_segment_size, "%u > %u\n", len,
> + dev->max_segment_size);
> if (!is_write) {
> if (dev->zoned)
> valid_len = null_zone_valid_read_len(nullb,
> @@ -1283,7 +1293,8 @@ static int null_handle_rq(struct nullb_cmd *cmd)
>
> spin_lock_irq(&nullb->lock);
> rq_for_each_segment(bvec, rq, iter) {
> - len = bvec.bv_len;
> + len = min(bvec.bv_len, nullb->dev->max_segment_size);
> + bvec.bv_len = len;
I am still confused by this change... Why is it necessary ? If max_segment_size
is set correctly, how can we ever get a BIO with a bvec length exceeding that
maximum ? If that is the case, aren't we missing a bio_split() somewhere ?
> err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
> op_is_write(req_op(rq)), sector,
> rq->cmd_flags & REQ_FUA);
> @@ -1310,7 +1321,8 @@ static int null_handle_bio(struct nullb_cmd *cmd)
>
> spin_lock_irq(&nullb->lock);
> bio_for_each_segment(bvec, bio, iter) {
> - len = bvec.bv_len;
> + len = min(bvec.bv_len, nullb->dev->max_segment_size);
> + bvec.bv_len = len;
> err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
> op_is_write(bio_op(bio)), sector,
> bio->bi_opf & REQ_FUA);
> @@ -2161,6 +2173,7 @@ static int null_add_dev(struct nullb_device *dev)
> dev->max_sectors = queue_max_hw_sectors(nullb->q);
> dev->max_sectors = min(dev->max_sectors, BLK_DEF_MAX_SECTORS);
> blk_queue_max_hw_sectors(nullb->q, dev->max_sectors);
> + blk_queue_max_segment_size(nullb->q, dev->max_segment_size);
>
> if (dev->virt_boundary)
> blk_queue_virt_boundary(nullb->q, PAGE_SIZE - 1);
> diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
> index 929f659dd255..7bf80b0035f5 100644
> --- a/drivers/block/null_blk/null_blk.h
> +++ b/drivers/block/null_blk/null_blk.h
> @@ -107,6 +107,7 @@ struct nullb_device {
> unsigned int queue_mode; /* block interface */
> unsigned int blocksize; /* block size */
> unsigned int max_sectors; /* Max sectors per command */
> + unsigned int max_segment_size; /* Max size of a single DMA segment. */
> unsigned int irqmode; /* IRQ completion handler */
> unsigned int hw_queue_depth; /* queue depth */
> unsigned int index; /* index of the disk, only valid with a disk */
--
Damien Le Moal
Western Digital Research
