On 02.09.2025 16:48, Leon Romanovsky wrote:
> From: Leon Romanovsky <leo...@nvidia.com>
>
> Convert the DMA direct mapping functions to accept physical addresses
> directly instead of page+offset parameters. The functions were already
> operating on physical addresses internally, so this change eliminates
> the redundant page-to-physical conversion at the API boundary.
>
> The functions dma_direct_map_page() and dma_direct_unmap_page() are
> renamed to dma_direct_map_phys() and dma_direct_unmap_phys() respectively,
> with their calling convention changed from (struct page *page,
> unsigned long offset) to (phys_addr_t phys).
>
> Architecture-specific functions arch_dma_map_page_direct() and
> arch_dma_unmap_page_direct() are similarly renamed to
> arch_dma_map_phys_direct() and arch_dma_unmap_phys_direct().
>
> The is_pci_p2pdma_page() checks are replaced with DMA_ATTR_MMIO checks
> to allow integration with dma_direct_map_resource and dma_direct_map_phys()
> is extended to support MMIO path either.
>
> Reviewed-by: Jason Gunthorpe <j...@nvidia.com>
> Signed-off-by: Leon Romanovsky <leo...@nvidia.com>
> ---
> arch/powerpc/kernel/dma-iommu.c | 4 +--
> include/linux/dma-map-ops.h | 8 ++---
> kernel/dma/direct.c | 6 ++--
> kernel/dma/direct.h | 57 +++++++++++++++++++++------------
> kernel/dma/mapping.c | 8 ++---
> 5 files changed, 49 insertions(+), 34 deletions(-)
>
> diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
> index 4d64a5db50f3..0359ab72cd3b 100644
> --- a/arch/powerpc/kernel/dma-iommu.c
> +++ b/arch/powerpc/kernel/dma-iommu.c
> @@ -14,7 +14,7 @@
> #define can_map_direct(dev, addr) \
> ((dev)->bus_dma_limit >= phys_to_dma((dev), (addr)))
>
> -bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr)
> +bool arch_dma_map_phys_direct(struct device *dev, phys_addr_t addr)
> {
> if (likely(!dev->bus_dma_limit))
> return false;
> @@ -24,7 +24,7 @@ bool arch_dma_map_page_direct(struct device *dev,
> phys_addr_t addr)
>
> #define is_direct_handle(dev, h) ((h) >= (dev)->archdata.dma_offset)
>
> -bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle)
> +bool arch_dma_unmap_phys_direct(struct device *dev, dma_addr_t dma_handle)
> {
> if (likely(!dev->bus_dma_limit))
> return false;
> diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
> index f48e5fb88bd5..71f5b3025415 100644
> --- a/include/linux/dma-map-ops.h
> +++ b/include/linux/dma-map-ops.h
> @@ -392,15 +392,15 @@ void *arch_dma_set_uncached(void *addr, size_t size);
> void arch_dma_clear_uncached(void *addr, size_t size);
>
> #ifdef CONFIG_ARCH_HAS_DMA_MAP_DIRECT
> -bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr);
> -bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle);
> +bool arch_dma_map_phys_direct(struct device *dev, phys_addr_t addr);
> +bool arch_dma_unmap_phys_direct(struct device *dev, dma_addr_t dma_handle);
> bool arch_dma_map_sg_direct(struct device *dev, struct scatterlist *sg,
> int nents);
> bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
> int nents);
> #else
> -#define arch_dma_map_page_direct(d, a) (false)
> -#define arch_dma_unmap_page_direct(d, a) (false)
> +#define arch_dma_map_phys_direct(d, a) (false)
> +#define arch_dma_unmap_phys_direct(d, a) (false)
> #define arch_dma_map_sg_direct(d, s, n) (false)
> #define arch_dma_unmap_sg_direct(d, s, n) (false)
> #endif
> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> index 24c359d9c879..fa75e3070073 100644
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -453,7 +453,7 @@ void dma_direct_unmap_sg(struct device *dev, struct
> scatterlist *sgl,
> if (sg_dma_is_bus_address(sg))
> sg_dma_unmark_bus_address(sg);
> else
> - dma_direct_unmap_page(dev, sg->dma_address,
> + dma_direct_unmap_phys(dev, sg->dma_address,
> sg_dma_len(sg), dir, attrs);
> }
> }
> @@ -476,8 +476,8 @@ int dma_direct_map_sg(struct device *dev, struct
> scatterlist *sgl, int nents,
> */
> break;
> case PCI_P2PDMA_MAP_NONE:
> - sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
> - sg->offset, sg->length, dir, attrs);
> + sg->dma_address = dma_direct_map_phys(dev, sg_phys(sg),
> + sg->length, dir, attrs);
> if (sg->dma_address == DMA_MAPPING_ERROR) {
> ret = -EIO;
> goto out_unmap;
> diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
> index d2c0b7e632fc..3f4792910604 100644
> --- a/kernel/dma/direct.h
> +++ b/kernel/dma/direct.h
> @@ -80,42 +80,57 @@ static inline void dma_direct_sync_single_for_cpu(struct
> device *dev,
> arch_dma_mark_clean(paddr, size);
> }
>
> -static inline dma_addr_t dma_direct_map_page(struct device *dev,
> - struct page *page, unsigned long offset, size_t size,
> - enum dma_data_direction dir, unsigned long attrs)
> +static inline dma_addr_t dma_direct_map_phys(struct device *dev,
> + phys_addr_t phys, size_t size, enum dma_data_direction dir,
> + unsigned long attrs)
> {
> - phys_addr_t phys = page_to_phys(page) + offset;
> - dma_addr_t dma_addr = phys_to_dma(dev, phys);
> + dma_addr_t dma_addr;
>
> if (is_swiotlb_force_bounce(dev)) {
> - if (is_pci_p2pdma_page(page))
> - return DMA_MAPPING_ERROR;
> + if (attrs & DMA_ATTR_MMIO)
> + goto err_overflow;
> +
> return swiotlb_map(dev, phys, size, dir, attrs);
> }
>
> - if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
> - dma_kmalloc_needs_bounce(dev, size, dir)) {
> - if (is_pci_p2pdma_page(page))
> - return DMA_MAPPING_ERROR;
> - if (is_swiotlb_active(dev))
> - return swiotlb_map(dev, phys, size, dir, attrs);
> -
> - dev_WARN_ONCE(dev, 1,
> - "DMA addr %pad+%zu overflow (mask %llx, bus limit
> %llx).\n",
> - &dma_addr, size, *dev->dma_mask,
> dev->bus_dma_limit);
> - return DMA_MAPPING_ERROR;
> + if (attrs & DMA_ATTR_MMIO) {
> + dma_addr = phys;
> + if (unlikely(dma_capable(dev, dma_addr, size, false)))
"!dma_capable(dev, dma_addr, size, false)" in the above line.
It took me a while to find this after noticing that this patchset breaks
booting some of me test systems.
> + goto err_overflow;
> + } else {
> + dma_addr = phys_to_dma(dev, phys);
> + if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
> + dma_kmalloc_needs_bounce(dev, size, dir)) {
> + if (is_swiotlb_active(dev))
> + return swiotlb_map(dev, phys, size, dir, attrs);
> +
> + goto err_overflow;
> + }
> }
>
> - if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> + if (!dev_is_dma_coherent(dev) &&
> + !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
> arch_sync_dma_for_device(phys, size, dir);
> return dma_addr;
> +
> +err_overflow:
> + dev_WARN_ONCE(
> + dev, 1,
> + "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
> + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
> + return DMA_MAPPING_ERROR;
> }
>
> -static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
> +static inline void dma_direct_unmap_phys(struct device *dev, dma_addr_t addr,
> size_t size, enum dma_data_direction dir, unsigned long attrs)
> {
> - phys_addr_t phys = dma_to_phys(dev, addr);
> + phys_addr_t phys;
> +
> + if (attrs & DMA_ATTR_MMIO)
> + /* nothing to do: uncached and no swiotlb */
> + return;
>
> + phys = dma_to_phys(dev, addr);
> if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> dma_direct_sync_single_for_cpu(dev, addr, size, dir);
>
> diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
> index 58482536db9b..80481a873340 100644
> --- a/kernel/dma/mapping.c
> +++ b/kernel/dma/mapping.c
> @@ -166,8 +166,8 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct
> page *page,
> return DMA_MAPPING_ERROR;
>
> if (dma_map_direct(dev, ops) ||
> - arch_dma_map_page_direct(dev, phys + size))
> - addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
> + arch_dma_map_phys_direct(dev, phys + size))
> + addr = dma_direct_map_phys(dev, phys, size, dir, attrs);
> else if (use_dma_iommu(dev))
> addr = iommu_dma_map_phys(dev, phys, size, dir, attrs);
> else
> @@ -187,8 +187,8 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t
> addr, size_t size,
>
> BUG_ON(!valid_dma_direction(dir));
> if (dma_map_direct(dev, ops) ||
> - arch_dma_unmap_page_direct(dev, addr + size))
> - dma_direct_unmap_page(dev, addr, size, dir, attrs);
> + arch_dma_unmap_phys_direct(dev, addr + size))
> + dma_direct_unmap_phys(dev, addr, size, dir, attrs);
> else if (use_dma_iommu(dev))
> iommu_dma_unmap_phys(dev, addr, size, dir, attrs);
> else
Best regards
--
Marek Szyprowski, PhD
Samsung R&D Institute Poland
