--- zzzz-none-000/linux-3.10.107/arch/arm/mm/dma-mapping.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/arm/mm/dma-mapping.c 2021-02-04 17:41:59.000000000 +0000 @@ -9,8 +9,10 @@ * * DMA uncached mapping support. */ +#include #include #include +#include #include #include #include @@ -25,6 +27,8 @@ #include #include #include +#include +#include #include #include @@ -35,7 +39,9 @@ #include #include #include +#include +#include "dma.h" #include "mm.h" /* @@ -145,11 +151,14 @@ dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs); static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, struct dma_attrs *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, + struct dma_attrs *attrs); struct dma_map_ops arm_coherent_dma_ops = { .alloc = arm_coherent_dma_alloc, .free = arm_coherent_dma_free, - .mmap = arm_dma_mmap, + .mmap = arm_coherent_dma_mmap, .get_sgtable = arm_dma_get_sgtable, .map_page = arm_coherent_dma_map_page, .map_sg = arm_dma_map_sg, @@ -157,9 +166,47 @@ }; EXPORT_SYMBOL(arm_coherent_dma_ops); +static int __dma_supported(struct device *dev, u64 mask, bool warn) +{ + unsigned long max_dma_pfn; + + /* + * If the mask allows for more memory than we can address, + * and we actually have that much memory, then we must + * indicate that DMA to this device is not supported. + */ + if (sizeof(mask) != sizeof(dma_addr_t) && + mask > (dma_addr_t)~0 && + dma_to_pfn(dev, ~0) < max_pfn - 1) { + if (warn) { + dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n", + mask); + dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n"); + } + return 0; + } + + 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)arm_dma_limit; + u64 mask = (u64)DMA_BIT_MASK(32); if (dev) { mask = dev->coherent_dma_mask; @@ -173,18 +220,15 @@ return 0; } - if ((~mask) & (u64)arm_dma_limit) { - dev_warn(dev, "coherent DMA mask %#llx is smaller " - "than system GFP_DMA mask %#llx\n", - mask, (u64)arm_dma_limit); + if (!__dma_supported(dev, mask, true)) return 0; - } } return mask; } -static void __dma_clear_buffer(struct page *page, size_t size) +static void __dma_clear_buffer(struct page *page, size_t size, + struct dma_attrs *attrs) { /* * Ensure that the allocated pages are zeroed, and that any data @@ -195,7 +239,8 @@ phys_addr_t end = base + size; while (size > 0) { void *ptr = kmap_atomic(page); - memset(ptr, 0, PAGE_SIZE); + if (!dma_get_attr(DMA_ATTR_SKIP_ZEROING, attrs)) + memset(ptr, 0, PAGE_SIZE); dmac_flush_range(ptr, ptr + PAGE_SIZE); kunmap_atomic(ptr); page++; @@ -204,7 +249,8 @@ outer_flush_range(base, end); } else { void *ptr = page_address(page); - memset(ptr, 0, size); + if (!dma_get_attr(DMA_ATTR_SKIP_ZEROING, attrs)) + memset(ptr, 0, size); dmac_flush_range(ptr, ptr + size); outer_flush_range(__pa(ptr), __pa(ptr) + size); } @@ -230,7 +276,7 @@ for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++) __free_page(p); - __dma_clear_buffer(page, size); + __dma_clear_buffer(page, size, NULL); return page; } @@ -249,73 +295,43 @@ } #ifdef CONFIG_MMU -#ifdef CONFIG_HUGETLB_PAGE -#error ARM Coherent DMA allocator does not (yet) support huge TLB -#endif static void *__alloc_from_contiguous(struct device *dev, size_t size, pgprot_t prot, struct page **ret_page, - const void *caller); + const void *caller, bool want_vaddr, + struct dma_attrs *attrs); static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp, pgprot_t prot, struct page **ret_page, - const void *caller); + const void *caller, bool want_vaddr); static void * __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot, const void *caller) { - struct vm_struct *area; - unsigned long addr; - /* * DMA allocation can be mapped to user space, so lets * set VM_USERMAP flags too. */ - area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP, - caller); - if (!area) - return NULL; - addr = (unsigned long)area->addr; - area->phys_addr = __pfn_to_phys(page_to_pfn(page)); - - if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) { - vunmap((void *)addr); - return NULL; - } - return (void *)addr; + return dma_common_contiguous_remap(page, size, + VM_ARM_DMA_CONSISTENT | VM_USERMAP, + prot, caller); } static void __dma_free_remap(void *cpu_addr, size_t size) { - unsigned int flags = VM_ARM_DMA_CONSISTENT | VM_USERMAP; - struct vm_struct *area = find_vm_area(cpu_addr); - if (!area || (area->flags & flags) != flags) { - WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); - return; - } - unmap_kernel_range((unsigned long)cpu_addr, size); - vunmap(cpu_addr); + dma_common_free_remap(cpu_addr, size, + VM_ARM_DMA_CONSISTENT | VM_USERMAP); } #define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K +static struct gen_pool *atomic_pool; -struct dma_pool { - size_t size; - spinlock_t lock; - unsigned long *bitmap; - unsigned long nr_pages; - void *vaddr; - struct page **pages; -}; - -static struct dma_pool atomic_pool = { - .size = DEFAULT_DMA_COHERENT_POOL_SIZE, -}; +static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE; static int __init early_coherent_pool(char *p) { - atomic_pool.size = memparse(p, &p); + atomic_pool_size = memparse(p, &p); return 0; } early_param("coherent_pool", early_coherent_pool); @@ -325,14 +341,14 @@ /* * Catch any attempt to set the pool size too late. */ - BUG_ON(atomic_pool.vaddr); + BUG_ON(atomic_pool); /* * Set architecture specific coherent pool size only if * it has not been changed by kernel command line parameter. */ - if (atomic_pool.size == DEFAULT_DMA_COHERENT_POOL_SIZE) - atomic_pool.size = size; + if (atomic_pool_size == DEFAULT_DMA_COHERENT_POOL_SIZE) + atomic_pool_size = size; } /* @@ -340,52 +356,44 @@ */ static int __init atomic_pool_init(void) { - struct dma_pool *pool = &atomic_pool; - pgprot_t prot = pgprot_dmacoherent(pgprot_kernel); + pgprot_t prot = pgprot_dmacoherent(PAGE_KERNEL); gfp_t gfp = GFP_KERNEL | GFP_DMA; - unsigned long nr_pages = pool->size >> PAGE_SHIFT; - unsigned long *bitmap; struct page *page; - struct page **pages; void *ptr; - int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long); - - bitmap = kzalloc(bitmap_size, GFP_KERNEL); - if (!bitmap) - goto no_bitmap; - pages = kzalloc(nr_pages * sizeof(struct page *), GFP_KERNEL); - if (!pages) - goto no_pages; - - if (IS_ENABLED(CONFIG_CMA)) - ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page, - atomic_pool_init); + atomic_pool = gen_pool_create(PAGE_SHIFT, -1); + if (!atomic_pool) + goto out; + + if (dev_get_cma_area(NULL)) + ptr = __alloc_from_contiguous(NULL, atomic_pool_size, prot, + &page, atomic_pool_init, true, NULL); else - ptr = __alloc_remap_buffer(NULL, pool->size, gfp, prot, &page, - atomic_pool_init); + ptr = __alloc_remap_buffer(NULL, atomic_pool_size, gfp, prot, + &page, atomic_pool_init, true); if (ptr) { - int i; + int ret; - for (i = 0; i < nr_pages; i++) - pages[i] = page + i; - - spin_lock_init(&pool->lock); - pool->vaddr = ptr; - pool->pages = pages; - pool->bitmap = bitmap; - pool->nr_pages = nr_pages; - pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n", - (unsigned)pool->size / 1024); + ret = gen_pool_add_virt(atomic_pool, (unsigned long)ptr, + page_to_phys(page), + atomic_pool_size, -1); + if (ret) + goto destroy_genpool; + + gen_pool_set_algo(atomic_pool, + gen_pool_first_fit_order_align, + (void *)PAGE_SHIFT); + pr_info("DMA: preallocated %zd KiB pool for atomic coherent allocations\n", + atomic_pool_size / 1024); return 0; } - kfree(pages); -no_pages: - kfree(bitmap); -no_bitmap: - pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n", - (unsigned)pool->size / 1024); +destroy_genpool: + gen_pool_destroy(atomic_pool); + atomic_pool = NULL; +out: + pr_err("DMA: failed to allocate %zx KiB pool for atomic coherent allocation\n", + atomic_pool_size / 1024); return -ENOMEM; } /* @@ -464,19 +472,20 @@ unsigned end = start + size; apply_to_page_range(&init_mm, start, size, __dma_update_pte, &prot); - dsb(); flush_tlb_kernel_range(start, end); } static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp, pgprot_t prot, struct page **ret_page, - const void *caller) + const void *caller, bool want_vaddr) { struct page *page; - void *ptr; + void *ptr = NULL; page = __dma_alloc_buffer(dev, size, gfp); if (!page) return NULL; + if (!want_vaddr) + goto out; ptr = __dma_alloc_remap(page, size, gfp, prot, caller); if (!ptr) { @@ -484,100 +493,70 @@ return NULL; } + out: *ret_page = page; return ptr; } static void *__alloc_from_pool(size_t size, struct page **ret_page) { - struct dma_pool *pool = &atomic_pool; - unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; - unsigned int pageno; - unsigned long flags; + unsigned long val; void *ptr = NULL; - unsigned long align_mask; - if (!pool->vaddr) { + if (!atomic_pool) { WARN(1, "coherent pool not initialised!\n"); return NULL; } - /* - * Align the region allocation - allocations from pool are rather - * small, so align them to their order in pages, minimum is a page - * size. This helps reduce fragmentation of the DMA space. - */ - align_mask = (1 << get_order(size)) - 1; + val = gen_pool_alloc(atomic_pool, size); + if (val) { + phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val); - spin_lock_irqsave(&pool->lock, flags); - pageno = bitmap_find_next_zero_area(pool->bitmap, pool->nr_pages, - 0, count, align_mask); - if (pageno < pool->nr_pages) { - bitmap_set(pool->bitmap, pageno, count); - ptr = pool->vaddr + PAGE_SIZE * pageno; - *ret_page = pool->pages[pageno]; - } else { - pr_err_once("ERROR: %u KiB atomic DMA coherent pool is too small!\n" - "Please increase it with coherent_pool= kernel parameter!\n", - (unsigned)pool->size / 1024); + *ret_page = phys_to_page(phys); + ptr = (void *)val; } - spin_unlock_irqrestore(&pool->lock, flags); return ptr; } static bool __in_atomic_pool(void *start, size_t size) { - struct dma_pool *pool = &atomic_pool; - void *end = start + size; - void *pool_start = pool->vaddr; - void *pool_end = pool->vaddr + pool->size; - - if (start < pool_start || start >= pool_end) - return false; - - if (end <= pool_end) - return true; - - WARN(1, "Wrong coherent size(%p-%p) from atomic pool(%p-%p)\n", - start, end - 1, pool_start, pool_end - 1); - - return false; + return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); } static int __free_from_pool(void *start, size_t size) { - struct dma_pool *pool = &atomic_pool; - unsigned long pageno, count; - unsigned long flags; - if (!__in_atomic_pool(start, size)) return 0; - pageno = (start - pool->vaddr) >> PAGE_SHIFT; - count = size >> PAGE_SHIFT; - - spin_lock_irqsave(&pool->lock, flags); - bitmap_clear(pool->bitmap, pageno, count); - spin_unlock_irqrestore(&pool->lock, flags); + gen_pool_free(atomic_pool, (unsigned long)start, size); return 1; } static void *__alloc_from_contiguous(struct device *dev, size_t size, pgprot_t prot, struct page **ret_page, - const void *caller) + const void *caller, bool want_vaddr, + struct dma_attrs *attrs) { unsigned long order = get_order(size); size_t count = size >> PAGE_SHIFT; struct page *page; - void *ptr; + void *ptr = NULL; page = dma_alloc_from_contiguous(dev, count, order); if (!page) return NULL; - __dma_clear_buffer(page, size); + /* + * skip completely if we neither need to zero nor sync. + */ + if (!(dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs) && + dma_get_attr(DMA_ATTR_SKIP_ZEROING, attrs))) + __dma_clear_buffer(page, size, attrs); + + if (!want_vaddr) + goto out; if (PageHighMem(page)) { ptr = __dma_alloc_remap(page, size, GFP_KERNEL, prot, caller); @@ -589,17 +568,21 @@ __dma_remap(page, size, prot); ptr = page_address(page); } + + out: *ret_page = page; return ptr; } static void __free_from_contiguous(struct device *dev, struct page *page, - void *cpu_addr, size_t size) + void *cpu_addr, size_t size, bool want_vaddr) { - if (PageHighMem(page)) - __dma_free_remap(cpu_addr, size); - else - __dma_remap(page, size, pgprot_kernel); + if (want_vaddr) { + if (PageHighMem(page)) + __dma_free_remap(cpu_addr, size); + else + __dma_remap(page, size, PAGE_KERNEL); + } dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); } @@ -617,12 +600,12 @@ #define nommu() 1 -#define __get_dma_pgprot(attrs, prot) __pgprot(0) -#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c) NULL +#define __get_dma_pgprot(attrs, prot) __pgprot(0) +#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c, wv) NULL #define __alloc_from_pool(size, ret_page) NULL -#define __alloc_from_contiguous(dev, size, prot, ret, c) NULL +#define __alloc_from_contiguous(dev, size, prot, ret, c, wv, a) NULL #define __free_from_pool(cpu_addr, size) 0 -#define __free_from_contiguous(dev, page, cpu_addr, size) do { } while (0) +#define __free_from_contiguous(dev, page, cpu_addr, size, wv) do { } while (0) #define __dma_free_remap(cpu_addr, size) do { } while (0) #endif /* CONFIG_MMU */ @@ -642,11 +625,13 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, - gfp_t gfp, pgprot_t prot, bool is_coherent, const void *caller) + gfp_t gfp, pgprot_t prot, bool is_coherent, + struct dma_attrs *attrs, const void *caller) { u64 mask = get_coherent_dma_mask(dev); struct page *page = NULL; void *addr; + bool want_vaddr; #ifdef CONFIG_DMA_API_DEBUG u64 limit = (mask + 1) & ~mask; @@ -674,20 +659,25 @@ *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); + want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs); - if (is_coherent || nommu()) + if (nommu()) addr = __alloc_simple_buffer(dev, size, gfp, &page); - else if (!(gfp & __GFP_WAIT)) + else if (dev_get_cma_area(dev) && (gfp & __GFP_DIRECT_RECLAIM)) + addr = __alloc_from_contiguous(dev, size, prot, &page, + caller, want_vaddr, attrs); + else if (is_coherent) + addr = __alloc_simple_buffer(dev, size, gfp, &page); + else if (!gfpflags_allow_blocking(gfp)) addr = __alloc_from_pool(size, &page); - else if (!IS_ENABLED(CONFIG_CMA)) - addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller); else - addr = __alloc_from_contiguous(dev, size, prot, &page, caller); + addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, + caller, want_vaddr); - if (addr) + if (page) *handle = pfn_to_dma(dev, page_to_pfn(page)); - return addr; + return want_vaddr ? addr : page; } /* @@ -697,33 +687,20 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) { - pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); - void *memory; - - if (dma_alloc_from_coherent(dev, size, handle, &memory)) - return memory; + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); return __dma_alloc(dev, size, handle, gfp, prot, false, - __builtin_return_address(0)); + attrs, __builtin_return_address(0)); } static void *arm_coherent_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) { - pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); - void *memory; - - if (dma_alloc_from_coherent(dev, size, handle, &memory)) - return memory; - - return __dma_alloc(dev, size, handle, gfp, prot, true, - __builtin_return_address(0)); + return __dma_alloc(dev, size, handle, gfp, PAGE_KERNEL, true, + attrs, __builtin_return_address(0)); } -/* - * Create userspace mapping for the DMA-coherent memory. - */ -int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, +static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs) { @@ -734,8 +711,6 @@ unsigned long pfn = dma_to_pfn(dev, dma_addr); unsigned long off = vma->vm_pgoff; - vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); - if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret)) return ret; @@ -751,6 +726,26 @@ } /* + * 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, + struct dma_attrs *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, + struct dma_attrs *attrs) +{ +#ifdef CONFIG_MMU + vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); +#endif /* CONFIG_MMU */ + 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, @@ -758,25 +753,24 @@ bool is_coherent) { struct page *page = pfn_to_page(dma_to_pfn(dev, handle)); - - if (dma_release_from_coherent(dev, get_order(size), cpu_addr)) - return; + bool want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs); size = PAGE_ALIGN(size); - if (is_coherent || nommu()) { + if (nommu()) { __dma_free_buffer(page, size); - } else if (__free_from_pool(cpu_addr, size)) { + } else if (!is_coherent && __free_from_pool(cpu_addr, size)) { return; - } else if (!IS_ENABLED(CONFIG_CMA)) { - __dma_free_remap(cpu_addr, size); + } else if (!dev_get_cma_area(dev)) { + if (want_vaddr && !is_coherent) + __dma_free_remap(cpu_addr, size); __dma_free_buffer(page, size); } else { /* * Non-atomic allocations cannot be freed with IRQs disabled */ WARN_ON(irqs_disabled()); - __free_from_contiguous(dev, page, cpu_addr, size); + __free_from_contiguous(dev, page, cpu_addr, size, want_vaddr); } } @@ -863,7 +857,7 @@ static void __dma_page_cpu_to_dev(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { - unsigned long paddr; + phys_addr_t paddr; dma_cache_maint_page(page, off, size, dir, dmac_map_area); @@ -879,20 +873,35 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { - unsigned long paddr = page_to_phys(page) + off; + phys_addr_t paddr = page_to_phys(page) + off; /* FIXME: non-speculating: not required */ - /* don't bother invalidating if DMA to device */ - if (dir != DMA_TO_DEVICE) + /* in any case, don't bother invalidating if DMA to device */ + if (dir != DMA_TO_DEVICE) { outer_inv_range(paddr, paddr + size); - dma_cache_maint_page(page, off, size, dir, dmac_unmap_area); + dma_cache_maint_page(page, off, size, dir, dmac_unmap_area); + } /* - * Mark the D-cache clean for this page to avoid extra flushing. + * Mark the D-cache clean for these pages to avoid extra flushing. */ - if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE) - set_bit(PG_dcache_clean, &page->flags); + 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; + } + } } /** @@ -914,7 +923,7 @@ int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, struct dma_attrs *attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; int i, j; @@ -948,7 +957,7 @@ void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, struct dma_attrs *attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; int i; @@ -967,7 +976,7 @@ void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; int i; @@ -986,7 +995,7 @@ void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; int i; @@ -1003,9 +1012,7 @@ */ int dma_supported(struct device *dev, u64 mask) { - if (mask < (u64)arm_dma_limit) - return 0; - return 1; + return __dma_supported(dev, mask, false); } EXPORT_SYMBOL(dma_supported); @@ -1032,51 +1039,104 @@ /* IOMMU */ +static int extend_iommu_mapping(struct dma_iommu_mapping *mapping); + static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping, size_t size) { unsigned int order = get_order(size); unsigned int align = 0; unsigned int count, start; + size_t mapping_size = mapping->bits << PAGE_SHIFT; unsigned long flags; + dma_addr_t iova; + int i; if (order > CONFIG_ARM_DMA_IOMMU_ALIGNMENT) order = CONFIG_ARM_DMA_IOMMU_ALIGNMENT; - count = ((PAGE_ALIGN(size) >> PAGE_SHIFT) + - (1 << mapping->order) - 1) >> mapping->order; - - if (order > mapping->order) - align = (1 << (order - mapping->order)) - 1; + count = PAGE_ALIGN(size) >> PAGE_SHIFT; + align = (1 << order) - 1; spin_lock_irqsave(&mapping->lock, flags); - start = bitmap_find_next_zero_area(mapping->bitmap, mapping->bits, 0, - count, align); - if (start > mapping->bits) { - spin_unlock_irqrestore(&mapping->lock, flags); - return DMA_ERROR_CODE; + for (i = 0; i < mapping->nr_bitmaps; i++) { + start = bitmap_find_next_zero_area(mapping->bitmaps[i], + mapping->bits, 0, count, align); + + if (start > mapping->bits) + continue; + + bitmap_set(mapping->bitmaps[i], start, count); + break; } - bitmap_set(mapping->bitmap, start, count); + /* + * No unused range found. Try to extend the existing mapping + * and perform a second attempt to reserve an IO virtual + * address range of size bytes. + */ + if (i == mapping->nr_bitmaps) { + if (extend_iommu_mapping(mapping)) { + spin_unlock_irqrestore(&mapping->lock, flags); + return DMA_ERROR_CODE; + } + + start = bitmap_find_next_zero_area(mapping->bitmaps[i], + mapping->bits, 0, count, align); + + if (start > mapping->bits) { + spin_unlock_irqrestore(&mapping->lock, flags); + return DMA_ERROR_CODE; + } + + bitmap_set(mapping->bitmaps[i], start, count); + } spin_unlock_irqrestore(&mapping->lock, flags); - return mapping->base + (start << (mapping->order + PAGE_SHIFT)); + iova = mapping->base + (mapping_size * i); + iova += start << PAGE_SHIFT; + + return iova; } static inline void __free_iova(struct dma_iommu_mapping *mapping, dma_addr_t addr, size_t size) { - unsigned int start = (addr - mapping->base) >> - (mapping->order + PAGE_SHIFT); - unsigned int count = ((size >> PAGE_SHIFT) + - (1 << mapping->order) - 1) >> mapping->order; + unsigned int start, count; + size_t mapping_size = mapping->bits << PAGE_SHIFT; unsigned long flags; + dma_addr_t bitmap_base; + u32 bitmap_index; + + if (!size) + return; + + bitmap_index = (u32) (addr - mapping->base) / (u32) mapping_size; + BUG_ON(addr < mapping->base || bitmap_index > mapping->extensions); + + bitmap_base = mapping->base + mapping_size * bitmap_index; + + start = (addr - bitmap_base) >> PAGE_SHIFT; + + if (addr + size > bitmap_base + mapping_size) { + /* + * The address range to be freed reaches into the iova + * range of the next bitmap. This should not happen as + * we don't allow this in __alloc_iova (at the + * moment). + */ + BUG(); + } else + count = size >> PAGE_SHIFT; spin_lock_irqsave(&mapping->lock, flags); - bitmap_clear(mapping->bitmap, start, count); + bitmap_clear(mapping->bitmaps[bitmap_index], start, count); spin_unlock_irqrestore(&mapping->lock, flags); } +/* We'll try 2M, 1M, 64K, and finally 4K; array must end with 0! */ +static const int iommu_order_array[] = { 9, 8, 4, 0 }; + static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, gfp_t gfp, struct dma_attrs *attrs) { @@ -1084,9 +1144,10 @@ int count = size >> PAGE_SHIFT; int array_size = count * sizeof(struct page *); int i = 0; + int order_idx = 0; if (array_size <= PAGE_SIZE) - pages = kzalloc(array_size, gfp); + pages = kzalloc(array_size, GFP_KERNEL); else pages = vzalloc(array_size); if (!pages) @@ -1101,7 +1162,7 @@ if (!page) goto error; - __dma_clear_buffer(page, size); + __dma_clear_buffer(page, size, NULL); for (i = 0; i < count; i++) pages[i] = page + i; @@ -1109,19 +1170,40 @@ return pages; } + /* Go straight to 4K chunks if caller says it's OK. */ + if (dma_get_attr(DMA_ATTR_ALLOC_SINGLE_PAGES, attrs)) + order_idx = ARRAY_SIZE(iommu_order_array) - 1; + /* * IOMMU can map any pages, so himem can also be used here */ gfp |= __GFP_NOWARN | __GFP_HIGHMEM; while (count) { - int j, order = __fls(count); + int j, order; - pages[i] = alloc_pages(gfp, order); - while (!pages[i] && order) - pages[i] = alloc_pages(gfp, --order); - if (!pages[i]) - goto error; + order = iommu_order_array[order_idx]; + + /* Drop down when we get small */ + if (__fls(count) < order) { + order_idx++; + continue; + } + + if (order) { + /* See if it's easy to allocate a high-order chunk */ + pages[i] = alloc_pages(gfp | __GFP_NORETRY, order); + + /* Go down a notch at first sign of pressure */ + if (!pages[i]) { + order_idx++; + continue; + } + } else { + pages[i] = alloc_pages(gfp, 0); + if (!pages[i]) + goto error; + } if (order) { split_page(pages[i], order); @@ -1130,7 +1212,7 @@ pages[i + j] = pages[i] + j; } - __dma_clear_buffer(pages[i], PAGE_SIZE << order); + __dma_clear_buffer(pages[i], PAGE_SIZE << order, NULL); i += 1 << order; count -= 1 << order; } @@ -1176,30 +1258,8 @@ __iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot, const void *caller) { - unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; - struct vm_struct *area; - unsigned long p; - - area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP, - caller); - if (!area) - return NULL; - - area->pages = pages; - area->nr_pages = nr_pages; - p = (unsigned long)area->addr; - - for (i = 0; i < nr_pages; i++) { - phys_addr_t phys = __pfn_to_phys(page_to_pfn(pages[i])); - if (ioremap_page_range(p, p + PAGE_SIZE, phys, prot)) - goto err; - p += PAGE_SIZE; - } - return area->addr; -err: - unmap_kernel_range((unsigned long)area->addr, size); - vunmap(area->addr); - return NULL; + return dma_common_pages_remap(pages, size, + VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller); } /* @@ -1208,10 +1268,10 @@ static dma_addr_t __iommu_create_mapping(struct device *dev, struct page **pages, size_t size) { - struct dma_iommu_mapping *mapping = dev->archdata.mapping; + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; dma_addr_t dma_addr, iova; - int i, ret = DMA_ERROR_CODE; + int i; dma_addr = __alloc_iova(mapping, size); if (dma_addr == DMA_ERROR_CODE) @@ -1219,6 +1279,8 @@ iova = dma_addr; for (i = 0; i < count; ) { + int ret; + unsigned int next_pfn = page_to_pfn(pages[i]) + 1; phys_addr_t phys = page_to_phys(pages[i]); unsigned int len, j; @@ -1228,7 +1290,8 @@ break; len = (j - i) << PAGE_SHIFT; - ret = iommu_map(mapping->domain, iova, phys, len, 0); + ret = iommu_map(mapping->domain, iova, phys, len, + IOMMU_READ|IOMMU_WRITE); if (ret < 0) goto fail; iova += len; @@ -1243,7 +1306,7 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t size) { - struct dma_iommu_mapping *mapping = dev->archdata.mapping; + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); /* * add optional in-page offset from iova to size and align @@ -1259,11 +1322,13 @@ static struct page **__atomic_get_pages(void *addr) { - struct dma_pool *pool = &atomic_pool; - struct page **pages = pool->pages; - int offs = (addr - pool->vaddr) >> PAGE_SHIFT; + struct page *page; + phys_addr_t phys; - return pages + offs; + phys = gen_pool_virt_to_phys(atomic_pool, (unsigned long)addr); + page = phys_to_page(phys); + + return (struct page **)page; } static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs) @@ -1313,16 +1378,25 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) { - pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); struct page **pages; void *addr = NULL; *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); - if (!(gfp & __GFP_WAIT)) + if (!gfpflags_allow_blocking(gfp)) return __iommu_alloc_atomic(dev, size, handle); + /* + * 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); if (!pages) return NULL; @@ -1388,22 +1462,23 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs) { - struct page **pages = __iommu_get_pages(cpu_addr, attrs); + struct page **pages; size = PAGE_ALIGN(size); - if (!pages) { - WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); + if (__in_atomic_pool(cpu_addr, size)) { + __iommu_free_atomic(dev, cpu_addr, handle, size); return; } - if (__in_atomic_pool(cpu_addr, size)) { - __iommu_free_atomic(dev, cpu_addr, handle, size); + pages = __iommu_get_pages(cpu_addr, attrs); + if (!pages) { + WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); return; } if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) { - unmap_kernel_range((unsigned long)cpu_addr, size); - vunmap(cpu_addr); + dma_common_free_remap(cpu_addr, size, + VM_ARM_DMA_CONSISTENT | VM_USERMAP); } __iommu_remove_mapping(dev, handle, size); @@ -1424,6 +1499,27 @@ GFP_KERNEL); } +static int __dma_direction_to_prot(enum dma_data_direction dir) +{ + int prot; + + switch (dir) { + case DMA_BIDIRECTIONAL: + prot = IOMMU_READ | IOMMU_WRITE; + break; + case DMA_TO_DEVICE: + prot = IOMMU_READ | IOMMU_WRITE; + break; + case DMA_FROM_DEVICE: + prot = IOMMU_WRITE | IOMMU_READ; + break; + default: + prot = 0; + } + + return prot; +} + /* * Map a part of the scatter-gather list into contiguous io address space */ @@ -1432,11 +1528,12 @@ enum dma_data_direction dir, struct dma_attrs *attrs, bool is_coherent) { - struct dma_iommu_mapping *mapping = dev->archdata.mapping; + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t iova, iova_base; int ret = 0; unsigned int count; struct scatterlist *s; + int prot; size = PAGE_ALIGN(size); *handle = DMA_ERROR_CODE; @@ -1453,7 +1550,9 @@ !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); - ret = iommu_map(mapping->domain, iova, phys, len, 0); + prot = __dma_direction_to_prot(dir); + + ret = iommu_map(mapping->domain, iova, phys, len, prot); if (ret < 0) goto fail; count += len >> PAGE_SHIFT; @@ -1650,15 +1749,17 @@ unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - struct dma_iommu_mapping *mapping = dev->archdata.mapping; + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t dma_addr; - int ret, len = PAGE_ALIGN(size + offset); + int ret, prot, len = PAGE_ALIGN(size + offset); dma_addr = __alloc_iova(mapping, len); if (dma_addr == DMA_ERROR_CODE) return dma_addr; - ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, 0); + prot = __dma_direction_to_prot(dir); + + ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot); if (ret < 0) goto fail; @@ -1701,7 +1802,7 @@ size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - struct dma_iommu_mapping *mapping = dev->archdata.mapping; + 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); @@ -1726,7 +1827,7 @@ size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - struct dma_iommu_mapping *mapping = dev->archdata.mapping; + 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)); int offset = handle & ~PAGE_MASK; @@ -1745,7 +1846,7 @@ static void arm_iommu_sync_single_for_cpu(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { - struct dma_iommu_mapping *mapping = dev->archdata.mapping; + 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)); unsigned int offset = handle & ~PAGE_MASK; @@ -1759,7 +1860,7 @@ static void arm_iommu_sync_single_for_device(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { - struct dma_iommu_mapping *mapping = dev->archdata.mapping; + 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)); unsigned int offset = handle & ~PAGE_MASK; @@ -1770,7 +1871,7 @@ __dma_page_cpu_to_dev(page, offset, size, dir); } -struct dma_map_ops iommu_ops = { +const struct dma_map_ops iommu_ops = { .alloc = arm_iommu_alloc_attrs, .free = arm_iommu_free_attrs, .mmap = arm_iommu_mmap_attrs, @@ -1789,7 +1890,7 @@ .set_dma_mask = arm_dma_set_mask, }; -struct dma_map_ops iommu_coherent_ops = { +const struct dma_map_ops iommu_coherent_ops = { .alloc = arm_iommu_alloc_attrs, .free = arm_iommu_free_attrs, .mmap = arm_iommu_mmap_attrs, @@ -1808,8 +1909,7 @@ * arm_iommu_create_mapping * @bus: pointer to the bus holding the client device (for IOMMU calls) * @base: start address of the valid IO address space - * @size: size of the valid IO address space - * @order: accuracy of the IO addresses allocations + * @size: maximum size of the valid IO address space * * Creates a mapping structure which holds information about used/unused * IO address ranges, which is required to perform memory allocation and @@ -1819,38 +1919,64 @@ * arm_iommu_attach_device function. */ struct dma_iommu_mapping * -arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size, - int order) +arm_iommu_create_mapping(struct device *dev, struct bus_type *bus, + dma_addr_t base, u64 size) { - unsigned int count = size >> (PAGE_SHIFT + order); - unsigned int bitmap_size = BITS_TO_LONGS(count) * sizeof(long); + unsigned int bits = size >> PAGE_SHIFT; + unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long); struct dma_iommu_mapping *mapping; + int extensions = 1; int err = -ENOMEM; + struct iommu_domain *domain; + + domain = iommu_get_domain_for_dev(dev); + if (domain->handler_token) + return (struct dma_iommu_mapping *)domain->handler_token; - if (!count) + /* currently only 32-bit DMA address space is supported */ + if (size > DMA_BIT_MASK(32) + 1) + return ERR_PTR(-ERANGE); + + if (!bitmap_size) return ERR_PTR(-EINVAL); + if (bitmap_size > PAGE_SIZE) { + extensions = bitmap_size / PAGE_SIZE; + bitmap_size = PAGE_SIZE; + } + mapping = kzalloc(sizeof(struct dma_iommu_mapping), GFP_KERNEL); if (!mapping) goto err; - mapping->bitmap = kzalloc(bitmap_size, GFP_KERNEL); - if (!mapping->bitmap) + mapping->bitmap_size = bitmap_size; + mapping->bitmaps = kzalloc(extensions * sizeof(unsigned long *), + GFP_KERNEL); + if (!mapping->bitmaps) goto err2; + mapping->bitmaps[0] = kzalloc(bitmap_size, GFP_KERNEL); + if (!mapping->bitmaps[0]) + goto err3; + + mapping->nr_bitmaps = 1; + mapping->extensions = extensions; mapping->base = base; mapping->bits = BITS_PER_BYTE * bitmap_size; - mapping->order = order; + mapping->size = size; + spin_lock_init(&mapping->lock); mapping->domain = iommu_domain_alloc(bus); if (!mapping->domain) - goto err3; + goto err4; kref_init(&mapping->kref); return mapping; +err4: + kfree(mapping->bitmaps[0]); err3: - kfree(mapping->bitmap); + kfree(mapping->bitmaps); err2: kfree(mapping); err: @@ -1860,14 +1986,35 @@ static void release_iommu_mapping(struct kref *kref) { + int i; struct dma_iommu_mapping *mapping = container_of(kref, struct dma_iommu_mapping, kref); iommu_domain_free(mapping->domain); - kfree(mapping->bitmap); + for (i = 0; i < mapping->nr_bitmaps; i++) + kfree(mapping->bitmaps[i]); + kfree(mapping->bitmaps); kfree(mapping); } +static int extend_iommu_mapping(struct dma_iommu_mapping *mapping) +{ + int next_bitmap; + + if (mapping->nr_bitmaps >= mapping->extensions) + return -EINVAL; + + next_bitmap = mapping->nr_bitmaps; + mapping->bitmaps[next_bitmap] = kzalloc(mapping->bitmap_size, + GFP_ATOMIC); + if (!mapping->bitmaps[next_bitmap]) + return -ENOMEM; + + mapping->nr_bitmaps++; + + return 0; +} + void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping) { if (mapping) @@ -1875,43 +2022,71 @@ } EXPORT_SYMBOL_GPL(arm_iommu_release_mapping); +/* fast mapping is always true for now */ +static bool fast = true; + +static int __arm_iommu_attach_device(struct device *dev, + struct dma_iommu_mapping *mapping) +{ + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + int err; + + if (fast && !domain->handler_token) { + /* detach the existing and attach to fast mapping domain */ + iommu_detach_device(mapping->domain, dev); + err = fast_smmu_attach_device(dev, mapping); + if (err) + return err; + err = iommu_dma_init_domain(domain, mapping->base, + mapping->size); + if (err) + /* Detach the domain? */ + return err; + dev->archdata.dma_ops = &fast_smmu_dma_ops; + } else if (domain->handler_token) { + dev->archdata.dma_ops = &fast_smmu_dma_ops; + dev->archdata.mapping = domain->handler_token; + mapping = domain->handler_token; + kref_get(&mapping->kref); + } else { + err = iommu_attach_device(mapping->domain, dev); + if (err) + return err; + } + + pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev)); + return 0; +} + /** * arm_iommu_attach_device * @dev: valid struct device pointer * @mapping: io address space mapping structure (returned from * arm_iommu_create_mapping) * - * Attaches specified io address space mapping to the provided device, - * this replaces the dma operations (dma_map_ops pointer) with the - * IOMMU aware version. More than one client might be attached to - * the same io address space mapping. + * Attaches specified io address space mapping to the provided device. + * This replaces the dma operations (dma_map_ops pointer) with the + * IOMMU aware version. + * + * More than one client might be attached to the same io address space + * mapping. */ int arm_iommu_attach_device(struct device *dev, struct dma_iommu_mapping *mapping) { int err; - err = iommu_attach_device(mapping->domain, dev); + err = __arm_iommu_attach_device(dev, mapping); if (err) return err; - kref_get(&mapping->kref); - dev->archdata.mapping = mapping; + /* TODO: Should this be removed when fast DMA mapping is enabled? */ set_dma_ops(dev, &iommu_ops); - - pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev)); return 0; } EXPORT_SYMBOL_GPL(arm_iommu_attach_device); -/** - * arm_iommu_detach_device - * @dev: valid struct device pointer - * - * Detaches the provided device from a previously attached map. - * This voids the dma operations (dma_map_ops pointer) - */ -void arm_iommu_detach_device(struct device *dev) +static void __arm_iommu_detach_device(struct device *dev) { struct dma_iommu_mapping *mapping; @@ -1923,11 +2098,109 @@ iommu_detach_device(mapping->domain, dev); kref_put(&mapping->kref, release_iommu_mapping); - mapping = NULL; - set_dma_ops(dev, NULL); + to_dma_iommu_mapping(dev) = NULL; pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev)); } + +/** + * arm_iommu_detach_device + * @dev: valid struct device pointer + * + * Detaches the provided device from a previously attached map. + * This voids the dma operations (dma_map_ops pointer) + */ +void arm_iommu_detach_device(struct device *dev) +{ + __arm_iommu_detach_device(dev); + set_dma_ops(dev, NULL); +} EXPORT_SYMBOL_GPL(arm_iommu_detach_device); -#endif +static const struct dma_map_ops *arm_get_iommu_dma_map_ops(struct device *dev, + bool coherent) +{ + /* If fast DMA mapping is enabled, dma_ops is updated with + * fast_smmu_dma_ops in __arm_iommu_attach_device(), use the same + */ + if (fast) + return dev->archdata.dma_ops; + + 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) +{ + struct dma_iommu_mapping *mapping; + + if (!iommu) + return false; + + mapping = arm_iommu_create_mapping(dev, 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; + } + + 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 true; +} + +static void arm_teardown_iommu_dma_ops(struct device *dev) +{ + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); + + if (!mapping) + return; + + __arm_iommu_detach_device(dev); + arm_iommu_release_mapping(mapping); +} + +#else + +static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu) +{ + 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 */ + +static struct dma_map_ops *arm_get_dma_map_ops(struct device *dev, + bool coherent) +{ + return coherent ? &arm_coherent_dma_ops : &arm_dma_ops; +} + +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent) +{ + const struct dma_map_ops *dma_ops; + + dev->archdata.dma_coherent = coherent; + if (arm_setup_iommu_dma_ops(dev, dma_base, size, iommu)) + dma_ops = arm_get_iommu_dma_map_ops(dev, coherent); + else + dma_ops = arm_get_dma_map_ops(dev, coherent); + + set_dma_ops(dev, dma_ops); +} +EXPORT_SYMBOL(arch_setup_dma_ops); + +void arch_teardown_dma_ops(struct device *dev) +{ + arm_teardown_iommu_dma_ops(dev); +}