search for: dma_attr_skip_cpu_sync

...43e03b5293d0 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -126,7 +126,7 @@ static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) { - if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __dma_page_cpu_to_dev(page, offset, size, dir); return pfn_to_dma(dev, page_to_pfn(page)) + offset; } @@ -155,7 +155,7 @@ static dma_addr_t arm_coherent_dma_map_page(struct device *dev, struct page *pag static void arm_dma_unmap_page(...

DMA_ATTR_SKIP_CPU_SYNC should only be used when the driver manually performs dma cache maintainance operations using the dma_sync_* calls. Nouveau doesn't do that, and generally just assumes DMA is coherent. Use plain dma_map_page which doesn't make this code correct but at least a little less wrong and simpler...

...+ buf->size, buf->attrs); if (ret < 0) { dev_err(buf->dev, "failed to get scatterlist from DMA API\n"); kfree(sgt); @@ -426,15 +426,12 @@ static void vb2_dc_put_userptr(void *buf_priv) struct page **pages; if (sgt) { - DEFINE_DMA_ATTRS(attrs); - - dma_set_attr(DMA_ATTR_SKIP_CPU_SYNC, &attrs); /* * No need to sync to CPU, it's already synced to the CPU * since the finish() memop will have been called before this. */ dma_unmap_sg_attrs(buf->dev, sgt->sgl, sgt->orig_nents, - buf->dma_dir, &attrs); + buf->dma_dir, DMA_ATTR_S...

...v, + __phys_to_dma(dev, io_tlb_start), + phys, org_size, aligned_size, dir, attrs); + + if (phys == DMA_MAPPING_ERROR) + return DMA_MAPPING_ERROR; + + /* Cleanup the padding area. */ + void *padding_start = phys_to_virt(phys); + size_t padding_size = aligned_size; + + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && + (dir == DMA_TO_DEVICE || + dir == DMA_BIDIRECTIONAL)) { + padding_start += org_size; + padding_size -= org_size; + } - iova = iommu_dma_alloc_iova(domain, size, dma_mask, dev); + memset(padding_start, 0, padding_size); + } +#endif + + iova = iommu_dma_alloc_iova(dom...

On Fri, May 19, 2023 at 01:49:46PM +0100, Andrew Cooper wrote: > > The alternative would be to finally merge swiotlb-xen into swiotlb, in > > which case we might be able to do this later. Let me see what I can > > do there. > > If that is an option, it would be great to reduce the special-cashing. I think it's doable, and I've been wanting it for a while. I just

Hi, This is third approach (complete this time) for replacing struct dma_attrs with unsigned long. The main patch (2/45) doing the change is split into many subpatches for easier review (3-43). They should be squashed together when applying. *Important:* Patchset is *only* build tested on allyesconfigs: ARM, ARM64, i386, x86_64 and powerpc. Please provide reviewes and tests for other

...v); if (!merge_boundary || merge_boundary > chunk_size - 1) { /* can't coalesce */ return -EINVAL; } nents = DIV_ROUND_UP(total_size, chunk_size); sg = sgl_alloc(); for_each_sgl() { sg->page = __alloc_pages(get_order(chunk_size)) sg->len = chunk_size; } dma_map_sg(sg, DMA_ATTR_SKIP_CPU_SYNC); // you are guaranteed to get a single dma_addr out } Of course this still uses the scatterlist structure with its annoying mix of input and output parametes, so I'd rather not expose it as an official API at the DMA layer.

...ason they start at 2, not 1? > +#define DMA_ATTR_WEAK_ORDERING (1UL << 2) > +#define DMA_ATTR_WRITE_COMBINE (1UL << 3) > +#define DMA_ATTR_NON_CONSISTENT (1UL << 4) > +#define DMA_ATTR_NO_KERNEL_MAPPING (1UL << 5) > +#define DMA_ATTR_SKIP_CPU_SYNC (1UL << 6) > +#define DMA_ATTR_FORCE_CONTIGUOUS (1UL << 7) > +#define DMA_ATTR_ALLOC_SINGLE_PAGES (1UL << 8) Gr{oetje,eeting}s, Geert -- Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert at linux-m68k.org In pers...

...a_map_page(struct device *dev, struct page *page, int prot = dma_info_to_prot(dir, coherent, attrs); dma_addr_t dma_handle; - dma_handle = __iommu_dma_map(dev, phys, size, prot); + dma_handle = __iommu_dma_map(dev, phys, size, prot, dma_get_mask(dev)); if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && dma_handle != DMA_MAPPING_ERROR) arch_sync_dma_for_device(dev, phys, size, dir); @@ -938,7 +938,8 @@ static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs) { return __iommu_dma_map(dev,...

.../nvif/os.h +++ b/lib/include/nvif/os.h @@ -683,6 +683,37 @@ dma_free_coherent(struct device *dev, size_t sz, void *vaddr, dma_addr_t bus) { } +enum dma_attr { + DMA_ATTR_WRITE_BARRIER, + DMA_ATTR_WEAK_ORDERING, + DMA_ATTR_WRITE_COMBINE, + DMA_ATTR_NON_CONSISTENT, + DMA_ATTR_NO_KERNEL_MAPPING, + DMA_ATTR_SKIP_CPU_SYNC, + DMA_ATTR_FORCE_CONTIGUOUS, + DMA_ATTR_MAX, +}; + +struct dma_attrs { +}; + +static inline void init_dma_attrs(struct dma_attrs *attrs) {} +static inline void dma_set_attr(enum dma_attr attr, struct dma_attrs *attrs) {} + +static inline void * +dma_alloc_attrs(struct device *dev, size_t sz, dma_a...

.../nvif/os.h +++ b/lib/include/nvif/os.h @@ -683,6 +683,37 @@ dma_free_coherent(struct device *dev, size_t sz, void *vaddr, dma_addr_t bus) { } +enum dma_attr { + DMA_ATTR_WRITE_BARRIER, + DMA_ATTR_WEAK_ORDERING, + DMA_ATTR_WRITE_COMBINE, + DMA_ATTR_NON_CONSISTENT, + DMA_ATTR_NO_KERNEL_MAPPING, + DMA_ATTR_SKIP_CPU_SYNC, + DMA_ATTR_FORCE_CONTIGUOUS, + DMA_ATTR_MAX, +}; + +struct dma_attrs { +}; + +static inline void init_dma_attrs(struct dma_attrs *attrs) {} +static inline void dma_set_attr(enum dma_attr attr, struct dma_attrs *attrs) {} + +static inline void * +dma_alloc_attrs(struct device *dev, size_t sz, dma_a...

...} > > > nents = DIV_ROUND_UP(total_size, chunk_size); > sg = sgl_alloc(); > for_each_sgl() { > sg->page = __alloc_pages(get_order(chunk_size)) > sg->len = chunk_size; > } > dma_map_sg(sg, DMA_ATTR_SKIP_CPU_SYNC); > // you are guaranteed to get a single dma_addr out > } > > Of course this still uses the scatterlist structure with its annoying > mix of input and output parametes, so I'd rather not expose it as > an official API at the DMA layer. The problem with the above open...

...| !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) { > - dst_pfns[i] = MIGRATE_PFN_ERROR; > - __free_page(dpage); > - continue; > - } > - > - fault->dma[fault->npages] = > - dma_map_page_attrs(dev, dpage, 0, PAGE_SIZE, > - PCI_DMA_BIDIRECTIONAL, > - DMA_ATTR_SKIP_CPU_SYNC); > - if (dma_mapping_error(dev, fault->dma[fault->npages])) { > - dst_pfns[i] = MIGRATE_PFN_ERROR; > - __free_page(dpage); > - continue; > - } > - > - ret = copy(drm, 1, NOUVEAU_APER_HOST, > - fault->dma[fault->npages++], > - NOUVEAU_APER_VRAM,...

...ate_pfn_to_page(src_pfns[i]); - if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) { - dst_pfns[i] = MIGRATE_PFN_ERROR; - __free_page(dpage); - continue; - } - - fault->dma[fault->npages] = - dma_map_page_attrs(dev, dpage, 0, PAGE_SIZE, - PCI_DMA_BIDIRECTIONAL, - DMA_ATTR_SKIP_CPU_SYNC); - if (dma_mapping_error(dev, fault->dma[fault->npages])) { - dst_pfns[i] = MIGRATE_PFN_ERROR; - __free_page(dpage); - continue; - } + *dma_addr = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, *dma_addr)) + goto error_free_page; - ret = c...

...ate_pfn_to_page(src_pfns[i]); - if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) { - dst_pfns[i] = MIGRATE_PFN_ERROR; - __free_page(dpage); - continue; - } - - fault->dma[fault->npages] = - dma_map_page_attrs(dev, dpage, 0, PAGE_SIZE, - PCI_DMA_BIDIRECTIONAL, - DMA_ATTR_SKIP_CPU_SYNC); - if (dma_mapping_error(dev, fault->dma[fault->npages])) { - dst_pfns[i] = MIGRATE_PFN_ERROR; - __free_page(dpage); - continue; - } - - ret = copy(drm, 1, NOUVEAU_APER_HOST, - fault->dma[fault->npages++], - NOUVEAU_APER_VRAM, - nouveau_dmem_page_addr(spage)); - if (...

...s an attribute associated with a DMA - * mapping. The semantics of each attribute should be defined in - * Documentation/DMA-attributes.txt. - */ -enum dma_attr { - DMA_ATTR_WRITE_BARRIER, - DMA_ATTR_WEAK_ORDERING, - DMA_ATTR_WRITE_COMBINE, - DMA_ATTR_NON_CONSISTENT, - DMA_ATTR_NO_KERNEL_MAPPING, - DMA_ATTR_SKIP_CPU_SYNC, - DMA_ATTR_FORCE_CONTIGUOUS, - DMA_ATTR_ALLOC_SINGLE_PAGES, - DMA_ATTR_MAX, -}; - -#define __DMA_ATTRS_LONGS BITS_TO_LONGS(DMA_ATTR_MAX) - -/** - * struct dma_attrs - an opaque container for DMA attributes - * @flags - bitmask representing a collection of enum dma_attr - */ -struct dma_attrs { - u...

...| !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) { > - dst_pfns[i] = MIGRATE_PFN_ERROR; > - __free_page(dpage); > - continue; > - } > - > - fault->dma[fault->npages] = > - dma_map_page_attrs(dev, dpage, 0, PAGE_SIZE, > - PCI_DMA_BIDIRECTIONAL, > - DMA_ATTR_SKIP_CPU_SYNC); > - if (dma_mapping_error(dev, fault->dma[fault->npages])) { > - dst_pfns[i] = MIGRATE_PFN_ERROR; > - __free_page(dpage); > - continue; > - } > + *dma_addr = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); > + if (dma_mapping_error(dev, *dma_addr)) &g...

...device *dev, size_t sz, void *vaddr, dma_addr_t bus) > { > } > > +enum dma_attr { > + DMA_ATTR_WRITE_BARRIER, > + DMA_ATTR_WEAK_ORDERING, > + DMA_ATTR_WRITE_COMBINE, > + DMA_ATTR_NON_CONSISTENT, > + DMA_ATTR_NO_KERNEL_MAPPING, > + DMA_ATTR_SKIP_CPU_SYNC, > + DMA_ATTR_FORCE_CONTIGUOUS, > + DMA_ATTR_MAX, > +}; > + > +struct dma_attrs { > +}; > + > +static inline void init_dma_attrs(struct dma_attrs *attrs) {} > +static inline void dma_set_attr(enum dma_attr attr, struct dma_attrs *attrs) {} > + > +static...

...page(src_pfns[i]); - if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) { - nouveau_dmem_page_free_locked(drm, dpage); - dst_pfns[i] = 0; - continue; - } - - migrate->dma[migrate->dma_nr] = - dma_map_page_attrs(dev, spage, 0, PAGE_SIZE, - PCI_DMA_BIDIRECTIONAL, - DMA_ATTR_SKIP_CPU_SYNC); - if (dma_mapping_error(dev, migrate->dma[migrate->dma_nr])) { - nouveau_dmem_page_free_locked(drm, dpage); - dst_pfns[i] = 0; - continue; - } - - ret = copy(drm, 1, NOUVEAU_APER_VRAM, - nouveau_dmem_page_addr(dpage), - NOUVEAU_APER_HOST, - migrate->dma[migrate->dma_...

...const struct dma_map_ops *ops = get_dma_ops(dev); + struct page *page; + + page = dma_alloc_contiguous(dev, size, gfp); + if (!page) + page = alloc_pages_node(dev_to_node(dev), gfp, get_order(size)); + if (!page) + return NULL; + + *dma_handle = ops->map_page(dev, page, 0, size, dir, + DMA_ATTR_SKIP_CPU_SYNC); + if (*dma_handle == DMA_MAPPING_ERROR) { + dma_free_contiguous(dev, page, size); + return NULL; + } + + memset(page_address(page), 0, size); + return page; +} + +void dma_common_free_pages(struct device *dev, size_t size, struct page *page, + dma_addr_t dma_handle, enum dma_data_direction dir...