On 10/06/2025 07.06, Christoph Hellwig wrote:
> Add a new blk_rq_dma_map / blk_rq_dma_unmap pair that does away with
> the wasteful scatterlist structure. Instead it uses the mapping iterator
> to either add segments to the IOVA for IOMMU operations, or just maps
> them one by one for the direct mapping. For the IOMMU case instead of
> a scatterlist with an entry for each segment, only a single [dma_addr,len]
> pair needs to be stored for processing a request, and for the direct
> mapping the per-segment allocation shrinks from
> [page,offset,len,dma_addr,dma_len] to just [dma_addr,len].
>
> One big difference to the scatterlist API, which could be considered
> downside, is that the IOVA collapsing only works when the driver sets
> a virt_boundary that matches the IOMMU granule. For NVMe this is done
> already so it works perfectly.
>
> Signed-off-by: Christoph Hellwig <hch@xxxxxx>
> ---
> block/blk-mq-dma.c | 162 +++++++++++++++++++++++++++++++++++++
> include/linux/blk-mq-dma.h | 63 +++++++++++++++
> 2 files changed, 225 insertions(+)
> create mode 100644 include/linux/blk-mq-dma.h
>
> diff --git a/block/blk-mq-dma.c b/block/blk-mq-dma.c
> index 82bae475dfa4..37f8fba077e6 100644
> --- a/block/blk-mq-dma.c
> +++ b/block/blk-mq-dma.c
> +static bool blk_rq_dma_map_iova(struct request *req, struct device *dma_dev,
> + struct dma_iova_state *state, struct blk_dma_iter *iter,
> + struct phys_vec *vec)
> +{
> + enum dma_data_direction dir = rq_dma_dir(req);
> + unsigned int mapped = 0;
> + int error = 0;
error does not need to be initialized.
> +/**
> + * blk_rq_dma_map_iter_start - map the first DMA segment for a request
> + * @req: request to map
> + * @dma_dev: device to map to
> + * @state: DMA IOVA state
> + * @iter: block layer DMA iterator
> + *
> + * Start DMA mapping @req to @dma_dev. @state and @iter are provided by the
> + * caller and don't need to be initialized. @state needs to be stored for use
> + * at unmap time, @iter is only needed at map time.
> + *
> + * Returns %false if there is no segment to map, including due to an error, or
> + * %true ft it did map a segment.
> + *
> + * If a segment was mapped, the DMA address for it is returned in @iter.addr and
> + * the length in @iter.len. If no segment was mapped the status code is
> + * returned in @iter.status.
> + *
> + * The caller can call blk_rq_dma_map_coalesce() to check if further segments
> + * need to be mapped after this, or go straight to blk_rq_dma_map_iter_next()
> + * to try to map the following segments.
> + */
> +bool blk_rq_dma_map_iter_start(struct request *req, struct device *dma_dev,
> + struct dma_iova_state *state, struct blk_dma_iter *iter)
> +{
> + unsigned int total_len = blk_rq_payload_bytes(req);
> + struct phys_vec vec;
> +
> + iter->iter.bio = req->bio;
> + iter->iter.iter = req->bio->bi_iter;
> + memset(&iter->p2pdma, 0, sizeof(iter->p2pdma));
> + iter->status = BLK_STS_OK;
> +
> + /*
> + * Grab the first segment ASAP because we'll need it to check for P2P
> + * transfers.
> + */
> + if (!blk_map_iter_next(req, &iter->iter, &vec))
> + return false;
> +
> + if (IS_ENABLED(CONFIG_PCI_P2PDMA) && (req->cmd_flags & REQ_P2PDMA)) {
> + switch (pci_p2pdma_state(&iter->p2pdma, dma_dev,
> + phys_to_page(vec.paddr))) {
> + case PCI_P2PDMA_MAP_BUS_ADDR:
> + return blk_dma_map_bus(req, dma_dev, iter, &vec);
> + case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
> + /*
> + * P2P transfers through the host bridge are treated the
> + * same as non-P2P transfers below and during unmap.
> + */
> + req->cmd_flags &= ~REQ_P2PDMA;
> + break;
> + default:
> + iter->status = BLK_STS_INVAL;
> + return false;
> + }
> + }
> +
> + if (blk_can_dma_map_iova(req, dma_dev) &&
> + dma_iova_try_alloc(dma_dev, state, vec.paddr, total_len))
> + return blk_rq_dma_map_iova(req, dma_dev, state, iter, &vec);
> + return blk_dma_map_direct(req, dma_dev, iter, &vec);
> +}
> +EXPORT_SYMBOL_GPL(blk_rq_dma_map_iter_start);
> +
...
> diff --git a/include/linux/blk-mq-dma.h b/include/linux/blk-mq-dma.h
> new file mode 100644
> index 000000000000..c26a01aeae00
> --- /dev/null
> +++ b/include/linux/blk-mq-dma.h
> @@ -0,0 +1,63 @@
> +/* SPDX-License-Identifier: GPL-2.0-only */
> +#ifndef BLK_MQ_DMA_H
> +#define BLK_MQ_DMA_H
> +
> +#include <linux/blk-mq.h>
> +#include <linux/pci-p2pdma.h>
> +
> +struct blk_dma_iter {
> + /* Output address range for this iteration */
> + dma_addr_t addr;
> + u32 len;
> +
> + /* Status code. Only valid when blk_rq_dma_map_iter_* returned false */
> + blk_status_t status;
This comment does not match with blk_rq_dma_map_iter_start(). It returns false
and status is BLK_STS_INVAL.
