diff options
| author | Leon Romanovsky <leonro@nvidia.com> | 2025-11-14 11:07:04 +0200 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2025-11-14 05:09:56 -0700 |
| commit | 37f0c7a8df7ad719a68fa1c2dbf066cfebc391a7 (patch) | |
| tree | 4512b28a5e01e2d581381a7f75fce083be3e906b /block | |
| parent | 61d43b1731e0bc122a0f78df42ce424db5b14a19 (diff) | |
block-dma: properly take MMIO path
In commit eadaa8b255f3 ("dma-mapping: introduce new DMA attribute to
indicate MMIO memory"), DMA_ATTR_MMIO attribute was added to describe
MMIO addresses, which require to avoid any memory cache flushing, as
an outcome of the discussion pointed in Link tag below.
In case of PCI_P2PDMA_MAP_THRU_HOST_BRIDGE transfer, blk-mq-dm logic
treated this as regular page and relied on "struct page" DMA flow.
That flow performs CPU cache flushing, which shouldn't be done here,
and doesn't set IOMMU_MMIO flag in DMA-IOMMU case.
As a solution, let's encode peer-to-peer transaction type in NVMe IOD
flags variable and provide it to blk-mq-dma API.
Link: https://lore.kernel.org/all/f912c446-1ae9-4390-9c11-00dce7bf0fd3@arm.com/
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block')
| -rw-r--r-- | block/blk-mq-dma.c | 18 |
1 files changed, 12 insertions, 6 deletions
diff --git a/block/blk-mq-dma.c b/block/blk-mq-dma.c index cebfead826ee..e9108ccaf4b0 100644 --- a/block/blk-mq-dma.c +++ b/block/blk-mq-dma.c @@ -92,8 +92,13 @@ static bool blk_dma_map_bus(struct blk_dma_iter *iter, struct phys_vec *vec) static bool blk_dma_map_direct(struct request *req, struct device *dma_dev, struct blk_dma_iter *iter, struct phys_vec *vec) { + unsigned int attrs = 0; + + if (iter->p2pdma.map == PCI_P2PDMA_MAP_THRU_HOST_BRIDGE) + attrs |= DMA_ATTR_MMIO; + iter->addr = dma_map_phys(dma_dev, vec->paddr, vec->len, - rq_dma_dir(req), 0); + rq_dma_dir(req), attrs); if (dma_mapping_error(dma_dev, iter->addr)) { iter->status = BLK_STS_RESOURCE; return false; @@ -108,14 +113,18 @@ static bool blk_rq_dma_map_iova(struct request *req, struct device *dma_dev, { enum dma_data_direction dir = rq_dma_dir(req); unsigned int mapped = 0; + unsigned int attrs = 0; int error; iter->addr = state->addr; iter->len = dma_iova_size(state); + if (iter->p2pdma.map == PCI_P2PDMA_MAP_THRU_HOST_BRIDGE) + attrs |= DMA_ATTR_MMIO; + do { error = dma_iova_link(dma_dev, state, vec->paddr, mapped, - vec->len, dir, 0); + vec->len, dir, attrs); if (error) break; mapped += vec->len; @@ -162,6 +171,7 @@ static bool blk_dma_map_iter_start(struct request *req, struct device *dma_dev, memset(&iter->p2pdma, 0, sizeof(iter->p2pdma)); iter->status = BLK_STS_OK; + iter->p2pdma.map = PCI_P2PDMA_MAP_NONE; /* * Grab the first segment ASAP because we'll need it to check for P2P @@ -173,10 +183,6 @@ static bool blk_dma_map_iter_start(struct request *req, struct device *dma_dev, switch (pci_p2pdma_state(&iter->p2pdma, dma_dev, phys_to_page(vec.paddr))) { case PCI_P2PDMA_MAP_BUS_ADDR: - if (iter->iter.is_integrity) - bio_integrity(req->bio)->bip_flags |= BIP_P2P_DMA; - else - req->cmd_flags |= REQ_P2PDMA; return blk_dma_map_bus(iter, &vec); case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: /* |