diff options
Diffstat (limited to 'arch/arm/mm/dma-mapping.c')
-rw-r--r-- | arch/arm/mm/dma-mapping.c | 793 |
1 files changed, 123 insertions, 670 deletions
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index e822af0d9219..f68db05eba29 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -15,9 +15,7 @@ #include <linux/init.h> #include <linux/device.h> #include <linux/dma-direct.h> -#include <linux/dma-mapping.h> -#include <linux/dma-noncoherent.h> -#include <linux/dma-contiguous.h> +#include <linux/dma-map-ops.h> #include <linux/highmem.h> #include <linux/memblock.h> #include <linux/slab.h> @@ -27,7 +25,7 @@ #include <linux/sizes.h> #include <linux/cma.h> -#include <asm/memory.h> +#include <asm/page.h> #include <asm/highmem.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> @@ -35,8 +33,7 @@ #include <asm/dma-iommu.h> #include <asm/mach/map.h> #include <asm/system_info.h> -#include <asm/dma-contiguous.h> -#include <xen/swiotlb-xen.h> +#include <asm/xen/xen-ops.h> #include "dma.h" #include "mm.h" @@ -106,161 +103,6 @@ static struct arm_dma_buffer *arm_dma_buffer_find(void *virt) * before transfers and delay cache invalidation until transfer completion. * */ -static void __dma_page_cpu_to_dev(struct page *, unsigned long, - size_t, enum dma_data_direction); -static void __dma_page_dev_to_cpu(struct page *, unsigned long, - size_t, enum dma_data_direction); - -/** - * arm_dma_map_page - map a portion of a page for streaming DMA - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @page: page that buffer resides in - * @offset: offset into page for start of buffer - * @size: size of buffer to map - * @dir: DMA transfer direction - * - * Ensure that any data held in the cache is appropriately discarded - * or written back. - * - * The device owns this memory once this call has completed. The CPU - * can regain ownership by calling dma_unmap_page(). - */ -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 ((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; -} - -static dma_addr_t arm_coherent_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - return pfn_to_dma(dev, page_to_pfn(page)) + offset; -} - -/** - * arm_dma_unmap_page - unmap a buffer previously mapped through dma_map_page() - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @handle: DMA address of buffer - * @size: size of buffer (same as passed to dma_map_page) - * @dir: DMA transfer direction (same as passed to dma_map_page) - * - * Unmap a page streaming mode DMA translation. The handle and size - * must match what was provided in the previous dma_map_page() call. - * All other usages are undefined. - * - * After this call, reads by the CPU to the buffer are guaranteed to see - * whatever the device wrote there. - */ -static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)), - handle & ~PAGE_MASK, size, dir); -} - -static void arm_dma_sync_single_for_cpu(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - unsigned int offset = handle & (PAGE_SIZE - 1); - struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); - __dma_page_dev_to_cpu(page, offset, size, dir); -} - -static void arm_dma_sync_single_for_device(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - unsigned int offset = handle & (PAGE_SIZE - 1); - struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); - __dma_page_cpu_to_dev(page, offset, size, dir); -} - -const struct dma_map_ops arm_dma_ops = { - .alloc = arm_dma_alloc, - .free = arm_dma_free, - .mmap = arm_dma_mmap, - .get_sgtable = arm_dma_get_sgtable, - .map_page = arm_dma_map_page, - .unmap_page = arm_dma_unmap_page, - .map_sg = arm_dma_map_sg, - .unmap_sg = arm_dma_unmap_sg, - .map_resource = dma_direct_map_resource, - .sync_single_for_cpu = arm_dma_sync_single_for_cpu, - .sync_single_for_device = arm_dma_sync_single_for_device, - .sync_sg_for_cpu = arm_dma_sync_sg_for_cpu, - .sync_sg_for_device = arm_dma_sync_sg_for_device, - .dma_supported = arm_dma_supported, - .get_required_mask = dma_direct_get_required_mask, -}; -EXPORT_SYMBOL(arm_dma_ops); - -static void *arm_coherent_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs); -static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs); -static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs); - -const struct dma_map_ops arm_coherent_dma_ops = { - .alloc = arm_coherent_dma_alloc, - .free = arm_coherent_dma_free, - .mmap = arm_coherent_dma_mmap, - .get_sgtable = arm_dma_get_sgtable, - .map_page = arm_coherent_dma_map_page, - .map_sg = arm_dma_map_sg, - .map_resource = dma_direct_map_resource, - .dma_supported = arm_dma_supported, - .get_required_mask = dma_direct_get_required_mask, -}; -EXPORT_SYMBOL(arm_coherent_dma_ops); - -static int __dma_supported(struct device *dev, u64 mask, bool warn) -{ - unsigned long max_dma_pfn = min(max_pfn, arm_dma_pfn_limit); - - /* - * Translate the device's DMA mask to a PFN limit. This - * PFN number includes the page which we can DMA to. - */ - if (dma_to_pfn(dev, mask) < max_dma_pfn) { - if (warn) - dev_warn(dev, "Coherent DMA mask %#llx (pfn %#lx-%#lx) covers a smaller range of system memory than the DMA zone pfn 0x0-%#lx\n", - mask, - dma_to_pfn(dev, 0), dma_to_pfn(dev, mask) + 1, - max_dma_pfn + 1); - return 0; - } - - return 1; -} - -static u64 get_coherent_dma_mask(struct device *dev) -{ - u64 mask = (u64)DMA_BIT_MASK(32); - - if (dev) { - mask = dev->coherent_dma_mask; - - /* - * Sanity check the DMA mask - it must be non-zero, and - * must be able to be satisfied by a DMA allocation. - */ - if (mask == 0) { - dev_warn(dev, "coherent DMA mask is unset\n"); - return 0; - } - - if (!__dma_supported(dev, mask, true)) - return 0; - } - - return mask; -} static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag) { @@ -406,6 +248,7 @@ out: */ postcore_initcall(atomic_pool_init); +#ifdef CONFIG_CMA_AREAS struct dma_contig_early_reserve { phys_addr_t base; unsigned long size; @@ -415,12 +258,14 @@ static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS] __initdata; static int dma_mmu_remap_num __initdata; +#ifdef CONFIG_DMA_CMA void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { dma_mmu_remap[dma_mmu_remap_num].base = base; dma_mmu_remap[dma_mmu_remap_num].size = size; dma_mmu_remap_num++; } +#endif void __init dma_contiguous_remap(void) { @@ -460,10 +305,11 @@ void __init dma_contiguous_remap(void) iotable_init(&map, 1); } } +#endif static int __dma_update_pte(pte_t *pte, unsigned long addr, void *data) { - struct page *page = virt_to_page(addr); + struct page *page = virt_to_page((void *)addr); pgprot_t prot = *(pgprot_t *)data; set_pte_ext(pte, mk_pte(page, prot), 0); @@ -688,7 +534,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, pgprot_t prot, bool is_coherent, unsigned long attrs, const void *caller) { - u64 mask = get_coherent_dma_mask(dev); + u64 mask = min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit); struct page *page = NULL; void *addr; bool allowblock, cma; @@ -712,9 +558,6 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, } #endif - if (!mask) - return NULL; - buf = kzalloc(sizeof(*buf), gfp & ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM)); if (!buf) @@ -723,19 +566,11 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, if (mask < 0xffffffffULL) gfp |= GFP_DMA; - /* - * Following is a work-around (a.k.a. hack) to prevent pages - * with __GFP_COMP being passed to split_page() which cannot - * handle them. The real problem is that this flag probably - * should be 0 on ARM as it is not supported on this - * platform; see CONFIG_HUGETLBFS. - */ - gfp &= ~(__GFP_COMP); args.gfp = gfp; *handle = DMA_MAPPING_ERROR; allowblock = gfpflags_allow_blocking(gfp); - cma = allowblock ? dev_get_cma_area(dev) : false; + cma = allowblock ? dev_get_cma_area(dev) : NULL; if (cma) buf->allocator = &cma_allocator; @@ -751,7 +586,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, if (page) { unsigned long flags; - *handle = pfn_to_dma(dev, page_to_pfn(page)); + *handle = phys_to_dma(dev, page_to_phys(page)); buf->virt = args.want_vaddr ? addr : page; spin_lock_irqsave(&arm_dma_bufs_lock, flags); @@ -765,74 +600,13 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, } /* - * Allocate DMA-coherent memory space and return both the kernel remapped - * virtual and bus address for that space. - */ -void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, - gfp_t gfp, unsigned long attrs) -{ - pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); - - return __dma_alloc(dev, size, handle, gfp, prot, false, - attrs, __builtin_return_address(0)); -} - -static void *arm_coherent_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs) -{ - return __dma_alloc(dev, size, handle, gfp, PAGE_KERNEL, true, - attrs, __builtin_return_address(0)); -} - -static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - int ret = -ENXIO; - unsigned long nr_vma_pages = vma_pages(vma); - unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; - unsigned long pfn = dma_to_pfn(dev, dma_addr); - unsigned long off = vma->vm_pgoff; - - if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) - return ret; - - if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) { - ret = remap_pfn_range(vma, vma->vm_start, - pfn + off, - vma->vm_end - vma->vm_start, - vma->vm_page_prot); - } - - return ret; -} - -/* - * Create userspace mapping for the DMA-coherent memory. - */ -static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); -} - -int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); - return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); -} - -/* * Free a buffer as defined by the above mapping. */ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, unsigned long attrs, bool is_coherent) { - struct page *page = pfn_to_page(dma_to_pfn(dev, handle)); + struct page *page = phys_to_page(dma_to_phys(dev, handle)); struct arm_dma_buffer *buf; struct arm_dma_free_args args = { .dev = dev, @@ -850,40 +624,6 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, kfree(buf); } -void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs) -{ - __arm_dma_free(dev, size, cpu_addr, handle, attrs, false); -} - -static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs) -{ - __arm_dma_free(dev, size, cpu_addr, handle, attrs, true); -} - -int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t handle, size_t size, - unsigned long attrs) -{ - unsigned long pfn = dma_to_pfn(dev, handle); - struct page *page; - int ret; - - /* If the PFN is not valid, we do not have a struct page */ - if (!pfn_valid(pfn)) - return -ENXIO; - - page = pfn_to_page(pfn); - - ret = sg_alloc_table(sgt, 1, GFP_KERNEL); - if (unlikely(ret)) - return ret; - - sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); - return 0; -} - static void dma_cache_maint_page(struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, void (*op)(const void *, size_t, int)) @@ -933,8 +673,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, /* * Make an area consistent for devices. - * Note: Drivers should NOT use this function directly, as it will break - * platforms with CONFIG_DMABOUNCE. + * Note: Drivers should NOT use this function directly. * Use the driver DMA support - see dma-mapping.h (dma_sync_*) */ static void __dma_page_cpu_to_dev(struct page *page, unsigned long off, @@ -970,146 +709,23 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off, * Mark the D-cache clean for these pages to avoid extra flushing. */ if (dir != DMA_TO_DEVICE && size >= PAGE_SIZE) { - unsigned long pfn; - size_t left = size; - - pfn = page_to_pfn(page) + off / PAGE_SIZE; - off %= PAGE_SIZE; - if (off) { - pfn++; - left -= PAGE_SIZE - off; - } - while (left >= PAGE_SIZE) { - page = pfn_to_page(pfn++); - set_bit(PG_dcache_clean, &page->flags); - left -= PAGE_SIZE; - } - } -} + struct folio *folio = pfn_folio(paddr / PAGE_SIZE); + size_t offset = offset_in_folio(folio, paddr); -/** - * arm_dma_map_sg - map a set of SG buffers for streaming mode DMA - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @sg: list of buffers - * @nents: number of buffers to map - * @dir: DMA transfer direction - * - * Map a set of buffers described by scatterlist in streaming mode for DMA. - * This is the scatter-gather version of the dma_map_single interface. - * Here the scatter gather list elements are each tagged with the - * appropriate dma address and length. They are obtained via - * sg_dma_{address,length}. - * - * Device ownership issues as mentioned for dma_map_single are the same - * here. - */ -int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - struct scatterlist *s; - int i, j; + for (;;) { + size_t sz = folio_size(folio) - offset; - for_each_sg(sg, s, nents, i) { -#ifdef CONFIG_NEED_SG_DMA_LENGTH - s->dma_length = s->length; -#endif - s->dma_address = ops->map_page(dev, sg_page(s), s->offset, - s->length, dir, attrs); - if (dma_mapping_error(dev, s->dma_address)) - goto bad_mapping; + if (size < sz) + break; + if (!offset) + set_bit(PG_dcache_clean, &folio->flags); + offset = 0; + size -= sz; + if (!size) + break; + folio = folio_next(folio); + } } - return nents; - - bad_mapping: - for_each_sg(sg, s, i, j) - ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs); - return 0; -} - -/** - * arm_dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @sg: list of buffers - * @nents: number of buffers to unmap (same as was passed to dma_map_sg) - * @dir: DMA transfer direction (same as was passed to dma_map_sg) - * - * Unmap a set of streaming mode DMA translations. Again, CPU access - * rules concerning calls here are the same as for dma_unmap_single(). - */ -void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - struct scatterlist *s; - - int i; - - for_each_sg(sg, s, nents, i) - ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs); -} - -/** - * arm_dma_sync_sg_for_cpu - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @sg: list of buffers - * @nents: number of buffers to map (returned from dma_map_sg) - * @dir: DMA transfer direction (same as was passed to dma_map_sg) - */ -void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - struct scatterlist *s; - int i; - - for_each_sg(sg, s, nents, i) - ops->sync_single_for_cpu(dev, sg_dma_address(s), s->length, - dir); -} - -/** - * arm_dma_sync_sg_for_device - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @sg: list of buffers - * @nents: number of buffers to map (returned from dma_map_sg) - * @dir: DMA transfer direction (same as was passed to dma_map_sg) - */ -void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - struct scatterlist *s; - int i; - - for_each_sg(sg, s, nents, i) - ops->sync_single_for_device(dev, sg_dma_address(s), s->length, - dir); -} - -/* - * Return whether the given device DMA address mask can be supported - * properly. For example, if your device can only drive the low 24-bits - * during bus mastering, then you would pass 0x00ffffff as the mask - * to this function. - */ -int arm_dma_supported(struct device *dev, u64 mask) -{ - return __dma_supported(dev, mask, false); -} - -static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent) -{ - /* - * When CONFIG_ARM_LPAE is set, physical address can extend above - * 32-bits, which then can't be addressed by devices that only support - * 32-bit DMA. - * Use the generic dma-direct / swiotlb ops code in that case, as that - * handles bounce buffering for us. - */ - if (IS_ENABLED(CONFIG_ARM_LPAE)) - return NULL; - return coherent ? &arm_coherent_dma_ops : &arm_dma_ops; } #ifdef CONFIG_ARM_DMA_USE_IOMMU @@ -1243,10 +859,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, int i = 0; int order_idx = 0; - if (array_size <= PAGE_SIZE) - pages = kzalloc(array_size, GFP_KERNEL); - else - pages = vzalloc(array_size); + pages = kvzalloc(array_size, GFP_KERNEL); if (!pages) return NULL; @@ -1372,7 +985,8 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size, len = (j - i) << PAGE_SHIFT; ret = iommu_map(mapping->domain, iova, phys, len, - __dma_info_to_prot(DMA_BIDIRECTIONAL, attrs)); + __dma_info_to_prot(DMA_BIDIRECTIONAL, attrs), + GFP_KERNEL); if (ret < 0) goto fail; iova += len; @@ -1458,13 +1072,13 @@ static void __iommu_free_atomic(struct device *dev, void *cpu_addr, __free_from_pool(cpu_addr, size); } -static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs, - int coherent_flag) +static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *handle, gfp_t gfp, unsigned long attrs) { pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); struct page **pages; void *addr = NULL; + int coherent_flag = dev->dma_coherent ? COHERENT : NORMAL; *handle = DMA_MAPPING_ERROR; size = PAGE_ALIGN(size); @@ -1473,15 +1087,6 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size, return __iommu_alloc_simple(dev, size, gfp, handle, coherent_flag, attrs); - /* - * Following is a work-around (a.k.a. hack) to prevent pages - * with __GFP_COMP being passed to split_page() which cannot - * handle them. The real problem is that this flag probably - * should be 0 on ARM as it is not supported on this - * platform; see CONFIG_HUGETLBFS. - */ - gfp &= ~(__GFP_COMP); - pages = __iommu_alloc_buffer(dev, size, gfp, attrs, coherent_flag); if (!pages) return NULL; @@ -1507,19 +1112,7 @@ err_buffer: return NULL; } -static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs) -{ - return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, NORMAL); -} - -static void *arm_coherent_iommu_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs) -{ - return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, COHERENT); -} - -static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, +static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { @@ -1533,35 +1126,24 @@ static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma if (vma->vm_pgoff >= nr_pages) return -ENXIO; + if (!dev->dma_coherent) + vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); + err = vm_map_pages(vma, pages, nr_pages); if (err) pr_err("Remapping memory failed: %d\n", err); return err; } -static int arm_iommu_mmap_attrs(struct device *dev, - struct vm_area_struct *vma, void *cpu_addr, - dma_addr_t dma_addr, size_t size, unsigned long attrs) -{ - vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); - - return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs); -} - -static int arm_coherent_iommu_mmap_attrs(struct device *dev, - struct vm_area_struct *vma, void *cpu_addr, - dma_addr_t dma_addr, size_t size, unsigned long attrs) -{ - return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs); -} /* * free a page as defined by the above mapping. * Must not be called with IRQs disabled. */ -static void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs, int coherent_flag) +static void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, unsigned long attrs) { + int coherent_flag = dev->dma_coherent ? COHERENT : NORMAL; struct page **pages; size = PAGE_ALIGN(size); @@ -1583,19 +1165,6 @@ static void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_ad __iommu_free_buffer(dev, pages, size, attrs); } -static void arm_iommu_free_attrs(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t handle, - unsigned long attrs) -{ - __arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, NORMAL); -} - -static void arm_coherent_iommu_free_attrs(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t handle, unsigned long attrs) -{ - __arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, COHERENT); -} - static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) @@ -1615,8 +1184,7 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt, */ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, size_t size, dma_addr_t *handle, - enum dma_data_direction dir, unsigned long attrs, - bool is_coherent) + enum dma_data_direction dir, unsigned long attrs) { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t iova, iova_base; @@ -1636,12 +1204,13 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, phys_addr_t phys = page_to_phys(sg_page(s)); unsigned int len = PAGE_ALIGN(s->offset + s->length); - if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) + if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); prot = __dma_info_to_prot(dir, attrs); - ret = iommu_map(mapping->domain, iova, phys, len, prot); + ret = iommu_map(mapping->domain, iova, phys, len, prot, + GFP_KERNEL); if (ret < 0) goto fail; count += len >> PAGE_SHIFT; @@ -1656,12 +1225,23 @@ fail: return ret; } -static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs, - bool is_coherent) +/** + * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to map + * @dir: DMA transfer direction + * + * Map a set of buffers described by scatterlist in streaming mode for DMA. + * The scatter gather list elements are merged together (if possible) and + * tagged with the appropriate dma address and length. They are obtained via + * sg_dma_{address,length}. + */ +static int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, unsigned long attrs) { struct scatterlist *s = sg, *dma = sg, *start = sg; - int i, count = 0; + int i, count = 0, ret; unsigned int offset = s->offset; unsigned int size = s->offset + s->length; unsigned int max = dma_get_max_seg_size(dev); @@ -1669,12 +1249,12 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, for (i = 1; i < nents; i++) { s = sg_next(s); - s->dma_address = DMA_MAPPING_ERROR; s->dma_length = 0; if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) { - if (__map_sg_chunk(dev, start, size, &dma->dma_address, - dir, attrs, is_coherent) < 0) + ret = __map_sg_chunk(dev, start, size, + &dma->dma_address, dir, attrs); + if (ret < 0) goto bad_mapping; dma->dma_address += offset; @@ -1687,8 +1267,8 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, } size += s->length; } - if (__map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs, - is_coherent) < 0) + ret = __map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs); + if (ret < 0) goto bad_mapping; dma->dma_address += offset; @@ -1699,48 +1279,25 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, bad_mapping: for_each_sg(sg, s, count, i) __iommu_remove_mapping(dev, sg_dma_address(s), sg_dma_len(s)); - return 0; -} - -/** - * arm_coherent_iommu_map_sg - map a set of SG buffers for streaming mode DMA - * @dev: valid struct device pointer - * @sg: list of buffers - * @nents: number of buffers to map - * @dir: DMA transfer direction - * - * Map a set of i/o coherent buffers described by scatterlist in streaming - * mode for DMA. The scatter gather list elements are merged together (if - * possible) and tagged with the appropriate dma address and length. They are - * obtained via sg_dma_{address,length}. - */ -static int arm_coherent_iommu_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ - return __iommu_map_sg(dev, sg, nents, dir, attrs, true); + if (ret == -ENOMEM) + return ret; + return -EINVAL; } /** - * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA + * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg * @dev: valid struct device pointer * @sg: list of buffers - * @nents: number of buffers to map - * @dir: DMA transfer direction + * @nents: number of buffers to unmap (same as was passed to dma_map_sg) + * @dir: DMA transfer direction (same as was passed to dma_map_sg) * - * Map a set of buffers described by scatterlist in streaming mode for DMA. - * The scatter gather list elements are merged together (if possible) and - * tagged with the appropriate dma address and length. They are obtained via - * sg_dma_{address,length}. + * Unmap a set of streaming mode DMA translations. Again, CPU access + * rules concerning calls here are the same as for dma_unmap_single(). */ -static int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ - return __iommu_map_sg(dev, sg, nents, dir, attrs, false); -} - -static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - unsigned long attrs, bool is_coherent) +static void arm_iommu_unmap_sg(struct device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction dir, + unsigned long attrs) { struct scatterlist *s; int i; @@ -1749,48 +1306,13 @@ static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg, if (sg_dma_len(s)) __iommu_remove_mapping(dev, sg_dma_address(s), sg_dma_len(s)); - if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) + if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) __dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir); } } /** - * arm_coherent_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg - * @dev: valid struct device pointer - * @sg: list of buffers - * @nents: number of buffers to unmap (same as was passed to dma_map_sg) - * @dir: DMA transfer direction (same as was passed to dma_map_sg) - * - * Unmap a set of streaming mode DMA translations. Again, CPU access - * rules concerning calls here are the same as for dma_unmap_single(). - */ -static void arm_coherent_iommu_unmap_sg(struct device *dev, - struct scatterlist *sg, int nents, enum dma_data_direction dir, - unsigned long attrs) -{ - __iommu_unmap_sg(dev, sg, nents, dir, attrs, true); -} - -/** - * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg - * @dev: valid struct device pointer - * @sg: list of buffers - * @nents: number of buffers to unmap (same as was passed to dma_map_sg) - * @dir: DMA transfer direction (same as was passed to dma_map_sg) - * - * Unmap a set of streaming mode DMA translations. Again, CPU access - * rules concerning calls here are the same as for dma_unmap_single(). - */ -static void arm_iommu_unmap_sg(struct device *dev, - struct scatterlist *sg, int nents, - enum dma_data_direction dir, - unsigned long attrs) -{ - __iommu_unmap_sg(dev, sg, nents, dir, attrs, false); -} - -/** * arm_iommu_sync_sg_for_cpu * @dev: valid struct device pointer * @sg: list of buffers @@ -1804,6 +1326,9 @@ static void arm_iommu_sync_sg_for_cpu(struct device *dev, struct scatterlist *s; int i; + if (dev->dma_coherent) + return; + for_each_sg(sg, s, nents, i) __dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir); @@ -1823,22 +1348,24 @@ static void arm_iommu_sync_sg_for_device(struct device *dev, struct scatterlist *s; int i; + if (dev->dma_coherent) + return; + for_each_sg(sg, s, nents, i) __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); } - /** - * arm_coherent_iommu_map_page + * arm_iommu_map_page * @dev: valid struct device pointer * @page: page that buffer resides in * @offset: offset into page for start of buffer * @size: size of buffer to map * @dir: DMA transfer direction * - * Coherent IOMMU aware version of arm_dma_map_page() + * IOMMU aware version of arm_dma_map_page() */ -static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *page, +static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) { @@ -1846,13 +1373,17 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p dma_addr_t dma_addr; int ret, prot, len = PAGE_ALIGN(size + offset); + if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + __dma_page_cpu_to_dev(page, offset, size, dir); + dma_addr = __alloc_iova(mapping, len); if (dma_addr == DMA_MAPPING_ERROR) return dma_addr; prot = __dma_info_to_prot(dir, attrs); - ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot); + ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, + prot, GFP_KERNEL); if (ret < 0) goto fail; @@ -1863,50 +1394,6 @@ fail: } /** - * arm_iommu_map_page - * @dev: valid struct device pointer - * @page: page that buffer resides in - * @offset: offset into page for start of buffer - * @size: size of buffer to map - * @dir: DMA transfer direction - * - * IOMMU aware version of arm_dma_map_page() - */ -static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - __dma_page_cpu_to_dev(page, offset, size, dir); - - return arm_coherent_iommu_map_page(dev, page, offset, size, dir, attrs); -} - -/** - * arm_coherent_iommu_unmap_page - * @dev: valid struct device pointer - * @handle: DMA address of buffer - * @size: size of buffer (same as passed to dma_map_page) - * @dir: DMA transfer direction (same as passed to dma_map_page) - * - * Coherent IOMMU aware version of arm_dma_unmap_page() - */ -static void arm_coherent_iommu_unmap_page(struct device *dev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); - dma_addr_t iova = handle & PAGE_MASK; - int offset = handle & ~PAGE_MASK; - int len = PAGE_ALIGN(size + offset); - - if (!iova) - return; - - iommu_unmap(mapping->domain, iova, len); - __free_iova(mapping, iova, len); -} - -/** * arm_iommu_unmap_page * @dev: valid struct device pointer * @handle: DMA address of buffer @@ -1920,15 +1407,17 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle, { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t iova = handle & PAGE_MASK; - struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + struct page *page; int offset = handle & ~PAGE_MASK; int len = PAGE_ALIGN(size + offset); if (!iova) return; - if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) + if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { + page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); __dma_page_dev_to_cpu(page, offset, size, dir); + } iommu_unmap(mapping->domain, iova, len); __free_iova(mapping, iova, len); @@ -1958,7 +1447,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev, prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO; - ret = iommu_map(mapping->domain, dma_addr, addr, len, prot); + ret = iommu_map(mapping->domain, dma_addr, addr, len, prot, GFP_KERNEL); if (ret < 0) goto fail; @@ -1996,12 +1485,13 @@ static void arm_iommu_sync_single_for_cpu(struct device *dev, { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t iova = handle & PAGE_MASK; - struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + struct page *page; unsigned int offset = handle & ~PAGE_MASK; - if (!iova) + if (dev->dma_coherent || !iova) return; + page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); __dma_page_dev_to_cpu(page, offset, size, dir); } @@ -2010,12 +1500,13 @@ static void arm_iommu_sync_single_for_device(struct device *dev, { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t iova = handle & PAGE_MASK; - struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + struct page *page; unsigned int offset = handle & ~PAGE_MASK; - if (!iova) + if (dev->dma_coherent || !iova) return; + page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); __dma_page_cpu_to_dev(page, offset, size, dir); } @@ -2037,26 +1528,6 @@ static const struct dma_map_ops iommu_ops = { .map_resource = arm_iommu_map_resource, .unmap_resource = arm_iommu_unmap_resource, - - .dma_supported = arm_dma_supported, -}; - -static const struct dma_map_ops iommu_coherent_ops = { - .alloc = arm_coherent_iommu_alloc_attrs, - .free = arm_coherent_iommu_free_attrs, - .mmap = arm_coherent_iommu_mmap_attrs, - .get_sgtable = arm_iommu_get_sgtable, - - .map_page = arm_coherent_iommu_map_page, - .unmap_page = arm_coherent_iommu_unmap_page, - - .map_sg = arm_coherent_iommu_map_sg, - .unmap_sg = arm_coherent_iommu_unmap_sg, - - .map_resource = arm_iommu_map_resource, - .unmap_resource = arm_iommu_unmap_resource, - - .dma_supported = arm_dma_supported, }; /** @@ -2073,7 +1544,7 @@ static const struct dma_map_ops iommu_coherent_ops = { * arm_iommu_attach_device function. */ struct dma_iommu_mapping * -arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size) +arm_iommu_create_mapping(const struct bus_type *bus, dma_addr_t base, u64 size) { unsigned int bits = size >> PAGE_SHIFT; unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long); @@ -2232,40 +1703,32 @@ void arm_iommu_detach_device(struct device *dev) iommu_detach_device(mapping->domain, dev); kref_put(&mapping->kref, release_iommu_mapping); to_dma_iommu_mapping(dev) = NULL; - set_dma_ops(dev, arm_get_dma_map_ops(dev->archdata.dma_coherent)); + set_dma_ops(dev, NULL); pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev)); } EXPORT_SYMBOL_GPL(arm_iommu_detach_device); -static const struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent) -{ - return coherent ? &iommu_coherent_ops : &iommu_ops; -} - -static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu) +static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, + bool coherent) { struct dma_iommu_mapping *mapping; - if (!iommu) - return false; - mapping = arm_iommu_create_mapping(dev->bus, dma_base, size); if (IS_ERR(mapping)) { pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n", size, dev_name(dev)); - return false; + return; } if (__arm_iommu_attach_device(dev, mapping)) { pr_warn("Failed to attached device %s to IOMMU_mapping\n", dev_name(dev)); arm_iommu_release_mapping(mapping); - return false; + return; } - return true; + set_dma_ops(dev, &iommu_ops); } static void arm_teardown_iommu_dma_ops(struct device *dev) @@ -2281,27 +1744,26 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) #else -static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu) +static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, + bool coherent) { - return false; } static void arm_teardown_iommu_dma_ops(struct device *dev) { } -#define arm_get_iommu_dma_map_ops arm_get_dma_map_ops - #endif /* CONFIG_ARM_DMA_USE_IOMMU */ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - const struct iommu_ops *iommu, bool coherent) + bool coherent) { - const struct dma_map_ops *dma_ops; - - dev->archdata.dma_coherent = coherent; -#ifdef CONFIG_SWIOTLB - dev->dma_coherent = coherent; -#endif + /* + * Due to legacy code that sets the ->dma_coherent flag from a bus + * notifier we can't just assign coherent to the ->dma_coherent flag + * here, but instead have to make sure we only set but never clear it + * for now. + */ + if (coherent) + dev->dma_coherent = true; /* * Don't override the dma_ops if they have already been set. Ideally @@ -2311,17 +1773,10 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, if (dev->dma_ops) return; - if (arm_setup_iommu_dma_ops(dev, dma_base, size, iommu)) - dma_ops = arm_get_iommu_dma_map_ops(coherent); - else - dma_ops = arm_get_dma_map_ops(coherent); + if (device_iommu_mapped(dev)) + arm_setup_iommu_dma_ops(dev, dma_base, size, coherent); - set_dma_ops(dev, dma_ops); - -#ifdef CONFIG_XEN - if (xen_initial_domain()) - dev->dma_ops = &xen_swiotlb_dma_ops; -#endif + xen_setup_dma_ops(dev); dev->archdata.dma_ops_setup = true; } @@ -2335,7 +1790,6 @@ void arch_teardown_dma_ops(struct device *dev) set_dma_ops(dev, NULL); } -#ifdef CONFIG_SWIOTLB void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { @@ -2363,4 +1817,3 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, { __arm_dma_free(dev, size, cpu_addr, dma_handle, attrs, false); } -#endif /* CONFIG_SWIOTLB */ |