From f0edfea8ef93ed6cc5f747c46c85c8e53e0798a0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Aug 2018 10:31:08 +0200 Subject: dma-mapping: move the remap helpers to a separate file The dma remap code only makes sense for not cache coherent architectures (or possibly the corner case of highmem CMA allocations) and currently is only used by arm, arm64, csky and xtensa. Split it out into a separate file with a separate Kconfig symbol, which gets the right copyright notice given that this code was written by Laura Abbott working for Code Aurora at that point. Signed-off-by: Christoph Hellwig Acked-by: Laura Abbott Reviewed-by: Robin Murphy --- arch/arm64/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/arm64') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 787d7850e064..5d065acb6d10 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -82,6 +82,7 @@ config ARM64 select CRC32 select DCACHE_WORD_ACCESS select DMA_DIRECT_OPS + select DMA_REMAP select EDAC_SUPPORT select FRAME_POINTER select GENERIC_ALLOCATOR -- cgit v1.2.3-70-g09d2 From 0c3b3171ceccb8830c2bb5adff1b4e9b204c1450 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 4 Nov 2018 20:29:28 +0100 Subject: dma-mapping: move the arm64 noncoherent alloc/free support to common code The arm64 codebase to implement coherent dma allocation for architectures with non-coherent DMA is a good start for a generic implementation, given that is uses the generic remap helpers, provides the atomic pool for allocations that can't sleep and still is realtively simple and well tested. Move it to kernel/dma and allow architectures to opt into it using a config symbol. Architectures just need to provide a new arch_dma_prep_coherent helper to writeback an invalidate the caches for any memory that gets remapped for uncached access. Signed-off-by: Christoph Hellwig Reviewed-by: Will Deacon Reviewed-by: Robin Murphy --- arch/arm64/Kconfig | 2 +- arch/arm64/mm/dma-mapping.c | 184 +++------------------------------------- include/linux/dma-mapping.h | 5 ++ include/linux/dma-noncoherent.h | 2 + kernel/dma/Kconfig | 5 ++ kernel/dma/remap.c | 158 +++++++++++++++++++++++++++++++++- 6 files changed, 180 insertions(+), 176 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 5d065acb6d10..2e645ea693ea 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -82,7 +82,7 @@ config ARM64 select CRC32 select DCACHE_WORD_ACCESS select DMA_DIRECT_OPS - select DMA_REMAP + select DMA_DIRECT_REMAP select EDAC_SUPPORT select FRAME_POINTER select GENERIC_ALLOCATOR diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index a3ac26284845..e2e7e5d0f94e 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -33,113 +33,6 @@ #include -static struct gen_pool *atomic_pool __ro_after_init; - -#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K -static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE; - -static int __init early_coherent_pool(char *p) -{ - atomic_pool_size = memparse(p, &p); - return 0; -} -early_param("coherent_pool", early_coherent_pool); - -static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) -{ - unsigned long val; - void *ptr = NULL; - - if (!atomic_pool) { - WARN(1, "coherent pool not initialised!\n"); - return NULL; - } - - val = gen_pool_alloc(atomic_pool, size); - if (val) { - phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val); - - *ret_page = phys_to_page(phys); - ptr = (void *)val; - memset(ptr, 0, size); - } - - return ptr; -} - -static bool __in_atomic_pool(void *start, size_t size) -{ - return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); -} - -static int __free_from_pool(void *start, size_t size) -{ - if (!__in_atomic_pool(start, size)) - return 0; - - gen_pool_free(atomic_pool, (unsigned long)start, size); - - return 1; -} - -void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t flags, unsigned long attrs) -{ - struct page *page; - void *ptr, *coherent_ptr; - pgprot_t prot = pgprot_writecombine(PAGE_KERNEL); - - size = PAGE_ALIGN(size); - - if (!gfpflags_allow_blocking(flags)) { - struct page *page = NULL; - void *addr = __alloc_from_pool(size, &page, flags); - - if (addr) - *dma_handle = phys_to_dma(dev, page_to_phys(page)); - - return addr; - } - - ptr = dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); - if (!ptr) - goto no_mem; - - /* remove any dirty cache lines on the kernel alias */ - __dma_flush_area(ptr, size); - - /* create a coherent mapping */ - page = virt_to_page(ptr); - coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP, - prot, __builtin_return_address(0)); - if (!coherent_ptr) - goto no_map; - - return coherent_ptr; - -no_map: - dma_direct_free_pages(dev, size, ptr, *dma_handle, attrs); -no_mem: - return NULL; -} - -void arch_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) -{ - if (!__free_from_pool(vaddr, PAGE_ALIGN(size))) { - void *kaddr = phys_to_virt(dma_to_phys(dev, dma_handle)); - - vunmap(vaddr); - dma_direct_free_pages(dev, size, kaddr, dma_handle, attrs); - } -} - -long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, - dma_addr_t dma_addr) -{ - return __phys_to_pfn(dma_to_phys(dev, dma_addr)); -} - pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) { @@ -160,6 +53,11 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, __dma_unmap_area(phys_to_virt(paddr), size, dir); } +void arch_dma_prep_coherent(struct page *page, size_t size) +{ + __dma_flush_area(page_address(page), size); +} + #ifdef CONFIG_IOMMU_DMA static int __swiotlb_get_sgtable_page(struct sg_table *sgt, struct page *page, size_t size) @@ -191,67 +89,6 @@ static int __swiotlb_mmap_pfn(struct vm_area_struct *vma, } #endif /* CONFIG_IOMMU_DMA */ -static int __init atomic_pool_init(void) -{ - pgprot_t prot = __pgprot(PROT_NORMAL_NC); - unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT; - struct page *page; - void *addr; - unsigned int pool_size_order = get_order(atomic_pool_size); - - if (dev_get_cma_area(NULL)) - page = dma_alloc_from_contiguous(NULL, nr_pages, - pool_size_order, false); - else - page = alloc_pages(GFP_DMA32, pool_size_order); - - if (page) { - int ret; - void *page_addr = page_address(page); - - memset(page_addr, 0, atomic_pool_size); - __dma_flush_area(page_addr, atomic_pool_size); - - atomic_pool = gen_pool_create(PAGE_SHIFT, -1); - if (!atomic_pool) - goto free_page; - - addr = dma_common_contiguous_remap(page, atomic_pool_size, - VM_USERMAP, prot, atomic_pool_init); - - if (!addr) - goto destroy_genpool; - - ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr, - page_to_phys(page), - atomic_pool_size, -1); - if (ret) - goto remove_mapping; - - gen_pool_set_algo(atomic_pool, - gen_pool_first_fit_order_align, - NULL); - - pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n", - atomic_pool_size / 1024); - return 0; - } - goto out; - -remove_mapping: - dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP); -destroy_genpool: - gen_pool_destroy(atomic_pool); - atomic_pool = NULL; -free_page: - if (!dma_release_from_contiguous(NULL, page, nr_pages)) - __free_pages(page, pool_size_order); -out: - pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n", - atomic_pool_size / 1024); - return -ENOMEM; -} - /******************************************** * The following APIs are for dummy DMA ops * ********************************************/ @@ -350,8 +187,7 @@ static int __init arm64_dma_init(void) TAINT_CPU_OUT_OF_SPEC, "ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)", ARCH_DMA_MINALIGN, cache_line_size()); - - return atomic_pool_init(); + return dma_atomic_pool_init(GFP_DMA32, __pgprot(PROT_NORMAL_NC)); } arch_initcall(arm64_dma_init); @@ -397,7 +233,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, page = alloc_pages(gfp, get_order(size)); addr = page ? page_address(page) : NULL; } else { - addr = __alloc_from_pool(size, &page, gfp); + addr = dma_alloc_from_pool(size, &page, gfp); } if (!addr) return NULL; @@ -407,7 +243,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, if (coherent) __free_pages(page, get_order(size)); else - __free_from_pool(addr, size); + dma_free_from_pool(addr, size); addr = NULL; } } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { @@ -471,9 +307,9 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, * coherent devices. * Hence how dodgy the below logic looks... */ - if (__in_atomic_pool(cpu_addr, size)) { + if (dma_in_atomic_pool(cpu_addr, size)) { iommu_dma_unmap_page(dev, handle, iosize, 0, 0); - __free_from_pool(cpu_addr, size); + dma_free_from_pool(cpu_addr, size); } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { struct page *page = vmalloc_to_page(cpu_addr); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 0f81c713f6e9..1a0edcde7d14 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -455,6 +455,11 @@ void *dma_common_pages_remap(struct page **pages, size_t size, const void *caller); void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags); +int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot); +bool dma_in_atomic_pool(void *start, size_t size); +void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags); +bool dma_free_from_pool(void *start, size_t size); + /** * dma_mmap_attrs - map a coherent DMA allocation into user space * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 9051b055beec..306557331d7d 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -69,4 +69,6 @@ static inline void arch_sync_dma_for_cpu_all(struct device *dev) } #endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */ +void arch_dma_prep_coherent(struct page *page, size_t size); + #endif /* _LINUX_DMA_NONCOHERENT_H */ diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index c92e08173ed8..41c3b1df70eb 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -55,3 +55,8 @@ config SWIOTLB config DMA_REMAP depends on MMU bool + +config DMA_DIRECT_REMAP + bool + depends on DMA_DIRECT_OPS + select DMA_REMAP diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index a15c393ea4e5..b32bb08f96ae 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -1,8 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (C) 2012 ARM Ltd. * Copyright (c) 2014 The Linux Foundation */ -#include +#include +#include +#include +#include +#include #include #include @@ -86,3 +91,154 @@ void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags) unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size)); vunmap(cpu_addr); } + +#ifdef CONFIG_DMA_DIRECT_REMAP +static struct gen_pool *atomic_pool __ro_after_init; + +#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K +static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE; + +static int __init early_coherent_pool(char *p) +{ + atomic_pool_size = memparse(p, &p); + return 0; +} +early_param("coherent_pool", early_coherent_pool); + +int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot) +{ + unsigned int pool_size_order = get_order(atomic_pool_size); + unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT; + struct page *page; + void *addr; + int ret; + + if (dev_get_cma_area(NULL)) + page = dma_alloc_from_contiguous(NULL, nr_pages, + pool_size_order, false); + else + page = alloc_pages(gfp, pool_size_order); + if (!page) + goto out; + + memset(page_address(page), 0, atomic_pool_size); + arch_dma_prep_coherent(page, atomic_pool_size); + + atomic_pool = gen_pool_create(PAGE_SHIFT, -1); + if (!atomic_pool) + goto free_page; + + addr = dma_common_contiguous_remap(page, atomic_pool_size, VM_USERMAP, + prot, __builtin_return_address(0)); + if (!addr) + goto destroy_genpool; + + ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr, + page_to_phys(page), atomic_pool_size, -1); + if (ret) + goto remove_mapping; + gen_pool_set_algo(atomic_pool, gen_pool_first_fit_order_align, NULL); + + pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n", + atomic_pool_size / 1024); + return 0; + +remove_mapping: + dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP); +destroy_genpool: + gen_pool_destroy(atomic_pool); + atomic_pool = NULL; +free_page: + if (!dma_release_from_contiguous(NULL, page, nr_pages)) + __free_pages(page, pool_size_order); +out: + pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n", + atomic_pool_size / 1024); + return -ENOMEM; +} + +bool dma_in_atomic_pool(void *start, size_t size) +{ + return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); +} + +void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) +{ + unsigned long val; + void *ptr = NULL; + + if (!atomic_pool) { + WARN(1, "coherent pool not initialised!\n"); + return NULL; + } + + val = gen_pool_alloc(atomic_pool, size); + if (val) { + phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val); + + *ret_page = pfn_to_page(__phys_to_pfn(phys)); + ptr = (void *)val; + memset(ptr, 0, size); + } + + return ptr; +} + +bool dma_free_from_pool(void *start, size_t size) +{ + if (!dma_in_atomic_pool(start, size)) + return false; + gen_pool_free(atomic_pool, (unsigned long)start, size); + return true; +} + +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t flags, unsigned long attrs) +{ + struct page *page = NULL; + void *ret, *kaddr; + + size = PAGE_ALIGN(size); + + if (!gfpflags_allow_blocking(flags)) { + ret = dma_alloc_from_pool(size, &page, flags); + if (!ret) + return NULL; + *dma_handle = phys_to_dma(dev, page_to_phys(page)); + return ret; + } + + kaddr = dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); + if (!kaddr) + return NULL; + page = virt_to_page(kaddr); + + /* remove any dirty cache lines on the kernel alias */ + arch_dma_prep_coherent(page, size); + + /* create a coherent mapping */ + ret = dma_common_contiguous_remap(page, size, VM_USERMAP, + arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs), + __builtin_return_address(0)); + if (!ret) + dma_direct_free_pages(dev, size, kaddr, *dma_handle, attrs); + return ret; +} + +void arch_dma_free(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle, unsigned long attrs) +{ + if (!dma_free_from_pool(vaddr, PAGE_ALIGN(size))) { + void *kaddr = phys_to_virt(dma_to_phys(dev, dma_handle)); + + vunmap(vaddr); + dma_direct_free_pages(dev, size, kaddr, dma_handle, attrs); + } +} + +long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, + dma_addr_t dma_addr) +{ + return __phys_to_pfn(dma_to_phys(dev, dma_addr)); +} +#endif /* CONFIG_DMA_DIRECT_REMAP */ -- cgit v1.2.3-70-g09d2 From 52f0b3ee0b2caab04e7a1db1cb4009a277a802af Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Nov 2018 19:04:31 +0100 Subject: arm64: remove the dummy_dma_ops mapping_error method Just return DMA_MAPPING_ERROR from __dummy_map_page and let the core dma-mapping code handle the rest. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- arch/arm64/mm/dma-mapping.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index e2e7e5d0f94e..3c2c088a3562 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -119,7 +119,7 @@ static dma_addr_t __dummy_map_page(struct device *dev, struct page *page, enum dma_data_direction dir, unsigned long attrs) { - return 0; + return DMA_MAPPING_ERROR; } static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr, @@ -154,11 +154,6 @@ static void __dummy_sync_sg(struct device *dev, { } -static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr) -{ - return 1; -} - static int __dummy_dma_supported(struct device *hwdev, u64 mask) { return 0; @@ -176,7 +171,6 @@ const struct dma_map_ops dummy_dma_ops = { .sync_single_for_device = __dummy_sync_single, .sync_sg_for_cpu = __dummy_sync_sg, .sync_sg_for_device = __dummy_sync_sg, - .mapping_error = __dummy_mapping_error, .dma_supported = __dummy_dma_supported, }; EXPORT_SYMBOL(dummy_dma_ops); -- cgit v1.2.3-70-g09d2 From cad34be747b8a92146e71c8267f2c1d6794e34c0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Nov 2018 19:35:19 +0100 Subject: iommu/dma-iommu: remove the mapping_error dma_map_ops method Return DMA_MAPPING_ERROR instead of 0 on a dma mapping failure and let the core dma-mapping code handle the rest. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- arch/arm64/mm/dma-mapping.c | 7 +++---- drivers/iommu/dma-iommu.c | 23 ++++++++--------------- include/linux/dma-iommu.h | 1 - 3 files changed, 11 insertions(+), 20 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 3c2c088a3562..4c0f498069e8 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -233,7 +233,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, return NULL; *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); - if (iommu_dma_mapping_error(dev, *handle)) { + if (*handle == DMA_MAPPING_ERROR) { if (coherent) __free_pages(page, get_order(size)); else @@ -250,7 +250,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, return NULL; *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); - if (iommu_dma_mapping_error(dev, *handle)) { + if (*handle == DMA_MAPPING_ERROR) { dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); return NULL; @@ -410,7 +410,7 @@ static dma_addr_t __iommu_map_page(struct device *dev, struct page *page, dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot); if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - !iommu_dma_mapping_error(dev, dev_addr)) + dev_addr != DMA_MAPPING_ERROR) __dma_map_area(page_address(page) + offset, size, dir); return dev_addr; @@ -493,7 +493,6 @@ static const struct dma_map_ops iommu_dma_ops = { .sync_sg_for_device = __iommu_sync_sg_for_device, .map_resource = iommu_dma_map_resource, .unmap_resource = iommu_dma_unmap_resource, - .mapping_error = iommu_dma_mapping_error, }; static int __init __iommu_dma_init(void) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index d1b04753b204..60c7e9e9901e 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -32,8 +32,6 @@ #include #include -#define IOMMU_MAPPING_ERROR 0 - struct iommu_dma_msi_page { struct list_head list; dma_addr_t iova; @@ -523,7 +521,7 @@ void iommu_dma_free(struct device *dev, struct page **pages, size_t size, { __iommu_dma_unmap(iommu_get_dma_domain(dev), *handle, size); __iommu_dma_free_pages(pages, PAGE_ALIGN(size) >> PAGE_SHIFT); - *handle = IOMMU_MAPPING_ERROR; + *handle = DMA_MAPPING_ERROR; } /** @@ -556,7 +554,7 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp, dma_addr_t iova; unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap; - *handle = IOMMU_MAPPING_ERROR; + *handle = DMA_MAPPING_ERROR; min_size = alloc_sizes & -alloc_sizes; if (min_size < PAGE_SIZE) { @@ -649,11 +647,11 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev); if (!iova) - return IOMMU_MAPPING_ERROR; + return DMA_MAPPING_ERROR; if (iommu_map(domain, iova, phys - iova_off, size, prot)) { iommu_dma_free_iova(cookie, iova, size); - return IOMMU_MAPPING_ERROR; + return DMA_MAPPING_ERROR; } return iova + iova_off; } @@ -694,7 +692,7 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents, s->offset += s_iova_off; s->length = s_length; - sg_dma_address(s) = IOMMU_MAPPING_ERROR; + sg_dma_address(s) = DMA_MAPPING_ERROR; sg_dma_len(s) = 0; /* @@ -737,11 +735,11 @@ static void __invalidate_sg(struct scatterlist *sg, int nents) int i; for_each_sg(sg, s, nents, i) { - if (sg_dma_address(s) != IOMMU_MAPPING_ERROR) + if (sg_dma_address(s) != DMA_MAPPING_ERROR) s->offset += sg_dma_address(s); if (sg_dma_len(s)) s->length = sg_dma_len(s); - sg_dma_address(s) = IOMMU_MAPPING_ERROR; + sg_dma_address(s) = DMA_MAPPING_ERROR; sg_dma_len(s) = 0; } } @@ -858,11 +856,6 @@ void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, __iommu_dma_unmap(iommu_get_dma_domain(dev), handle, size); } -int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return dma_addr == IOMMU_MAPPING_ERROR; -} - static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, phys_addr_t msi_addr, struct iommu_domain *domain) { @@ -882,7 +875,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, return NULL; iova = __iommu_dma_map(dev, msi_addr, size, prot, domain); - if (iommu_dma_mapping_error(dev, iova)) + if (iova == DMA_MAPPING_ERROR) goto out_free_page; INIT_LIST_HEAD(&msi_page->list); diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h index e8ca5e654277..e760dc5d1fa8 100644 --- a/include/linux/dma-iommu.h +++ b/include/linux/dma-iommu.h @@ -69,7 +69,6 @@ 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); void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, unsigned long attrs); -int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); /* The DMA API isn't _quite_ the whole story, though... */ void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg); -- cgit v1.2.3-70-g09d2 From 7c703e54cc71df5baa962e24a5663d88173bba5c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Nov 2018 09:51:00 +0100 Subject: arch: switch the default on ARCH_HAS_SG_CHAIN These days architectures are mostly out of the business of dealing with struct scatterlist at all, unless they have architecture specific iommu drivers. Replace the ARCH_HAS_SG_CHAIN symbol with a ARCH_NO_SG_CHAIN one only enabled for architectures with horrible legacy iommu drivers like alpha and parisc, and conditionally for arm which wants to keep it disable for legacy platforms. Signed-off-by: Christoph Hellwig Reviewed-by: Palmer Dabbelt --- .../features/io/sg-chain/arch-support.txt | 33 ---------------------- arch/alpha/Kconfig | 1 + arch/arc/Kconfig | 1 - arch/arm/Kconfig | 2 +- arch/arm64/Kconfig | 1 - arch/ia64/Kconfig | 1 - arch/parisc/Kconfig | 1 + arch/powerpc/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/sparc/Kconfig | 1 - arch/x86/Kconfig | 1 - arch/xtensa/Kconfig | 1 - include/linux/scatterlist.h | 6 ++-- lib/Kconfig | 2 +- lib/scatterlist.c | 2 +- 15 files changed, 8 insertions(+), 47 deletions(-) delete mode 100644 Documentation/features/io/sg-chain/arch-support.txt (limited to 'arch/arm64') diff --git a/Documentation/features/io/sg-chain/arch-support.txt b/Documentation/features/io/sg-chain/arch-support.txt deleted file mode 100644 index 6554f0372c3f..000000000000 --- a/Documentation/features/io/sg-chain/arch-support.txt +++ /dev/null @@ -1,33 +0,0 @@ -# -# Feature name: sg-chain -# Kconfig: ARCH_HAS_SG_CHAIN -# description: arch supports chained scatter-gather lists -# - ----------------------- - | arch |status| - ----------------------- - | alpha: | TODO | - | arc: | ok | - | arm: | ok | - | arm64: | ok | - | c6x: | TODO | - | h8300: | TODO | - | hexagon: | TODO | - | ia64: | ok | - | m68k: | TODO | - | microblaze: | TODO | - | mips: | TODO | - | nds32: | TODO | - | nios2: | TODO | - | openrisc: | TODO | - | parisc: | TODO | - | powerpc: | ok | - | riscv: | TODO | - | s390: | ok | - | sh: | TODO | - | sparc: | ok | - | um: | TODO | - | unicore32: | TODO | - | x86: | ok | - | xtensa: | TODO | - ----------------------- diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 5b4f88363453..a7e748a46c18 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -5,6 +5,7 @@ config ALPHA select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select ARCH_NO_PREEMPT + select ARCH_NO_SG_CHAIN select ARCH_USE_CMPXCHG_LOCKREF select HAVE_AOUT select HAVE_IDE diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index c9e2a1323536..fd48d698da29 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -13,7 +13,6 @@ config ARC select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE - select ARCH_HAS_SG_CHAIN select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3b2852df6eb3..a858ee791ef0 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -19,6 +19,7 @@ config ARM select ARCH_HAVE_CUSTOM_GPIO_H select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_NO_SG_CHAIN if !ARM_HAS_SG_CHAIN select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7 select ARCH_SUPPORTS_ATOMIC_RMW @@ -119,7 +120,6 @@ config ARM . config ARM_HAS_SG_CHAIN - select ARCH_HAS_SG_CHAIN bool config ARM_DMA_USE_IOMMU diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 2e645ea693ea..06cf0ef24367 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -23,7 +23,6 @@ config ARM64 select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SET_MEMORY - select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_SYNC_DMA_FOR_DEVICE diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 36773def6920..d6f203658994 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -29,7 +29,6 @@ config IA64 select HAVE_MEMBLOCK_NODE_MAP select HAVE_VIRT_CPU_ACCOUNTING select ARCH_HAS_DMA_MARK_CLEAN - select ARCH_HAS_SG_CHAIN select VIRT_TO_BUS select ARCH_DISCARD_MEMBLOCK select GENERIC_IRQ_PROBE diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 92a339ee28b3..428ee50fc3db 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -11,6 +11,7 @@ config PARISC select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_NO_SG_CHAIN select ARCH_SUPPORTS_MEMORY_FAILURE select RTC_CLASS select RTC_DRV_GENERIC diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 8be31261aec8..4bc8edd83cee 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -138,7 +138,6 @@ config PPC select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC64 - select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION) select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE if PPC64 diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 5173366af8f3..5624e8607054 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -73,7 +73,6 @@ config S390 select ARCH_HAS_KCOV select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SET_MEMORY - select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_UBSAN_SANITIZE_ALL diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 490b2c95c212..8853b6ceae17 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -40,7 +40,6 @@ config SPARC select MODULES_USE_ELF_RELA select ODD_RT_SIGACTION select OLD_SIGSUSPEND - select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS select LOCKDEP_SMALL if LOCKDEP select NEED_DMA_MAP_STATE diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9d734f3c8234..adc845b66f01 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -66,7 +66,6 @@ config X86 select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_UACCESS_MCSAFE if X86_64 && X86_MCE select ARCH_HAS_SET_MEMORY - select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 239bfb16c58b..75488b606edc 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 config XTENSA def_bool y - select ARCH_HAS_SG_CHAIN select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_NO_COHERENT_DMA_MMAP if !MMU diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 093aa57120b0..b96f0d0b5b8f 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -324,10 +324,10 @@ size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents, * Like SG_CHUNK_SIZE, but for archs that have sg chaining. This limit * is totally arbitrary, a setting of 2048 will get you at least 8mb ios. */ -#ifdef CONFIG_ARCH_HAS_SG_CHAIN -#define SG_MAX_SEGMENTS 2048 -#else +#ifdef CONFIG_ARCH_NO_SG_CHAIN #define SG_MAX_SEGMENTS SG_CHUNK_SIZE +#else +#define SG_MAX_SEGMENTS 2048 #endif #ifdef CONFIG_SG_POOL diff --git a/lib/Kconfig b/lib/Kconfig index a9965f4af4dd..d5a5e2ebf286 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -577,7 +577,7 @@ config SG_POOL # sg chaining option # -config ARCH_HAS_SG_CHAIN +config ARCH_NO_SG_CHAIN def_bool n config ARCH_HAS_PMEM_API diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 7c6096a71704..9ba349e775ef 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -271,7 +271,7 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents, if (nents == 0) return -EINVAL; -#ifndef CONFIG_ARCH_HAS_SG_CHAIN +#ifdef CONFIG_ARCH_NO_SG_CHAIN if (WARN_ON_ONCE(nents > max_ents)) return -EINVAL; #endif -- cgit v1.2.3-70-g09d2 From 3731c3d4774e38b9d91c01943e1e6a243c1776be Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Dec 2018 12:50:26 -0800 Subject: dma-mapping: always build the direct mapping code All architectures except for sparc64 use the dma-direct code in some form, and even for sparc64 we had the discussion of a direct mapping mode a while ago. In preparation for directly calling the direct mapping code don't bother having it optionally but always build the code in. This is a minor hardship for some powerpc and arm configs that don't pull it in yet (although they should in a relase ot two), and sparc64 which currently doesn't need it at all, but it will reduce the ifdef mess we'd otherwise need significantly. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- arch/alpha/Kconfig | 1 - arch/arc/Kconfig | 1 - arch/arm/Kconfig | 1 - arch/arm64/Kconfig | 1 - arch/c6x/Kconfig | 1 - arch/csky/Kconfig | 1 - arch/h8300/Kconfig | 1 - arch/hexagon/Kconfig | 1 - arch/m68k/Kconfig | 1 - arch/microblaze/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/nds32/Kconfig | 1 - arch/nios2/Kconfig | 1 - arch/openrisc/Kconfig | 1 - arch/parisc/Kconfig | 1 - arch/riscv/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/sh/Kconfig | 1 - arch/sparc/Kconfig | 1 - arch/unicore32/Kconfig | 1 - arch/x86/Kconfig | 1 - arch/xtensa/Kconfig | 1 - kernel/dma/Kconfig | 7 ------- kernel/dma/Makefile | 3 +-- 24 files changed, 1 insertion(+), 31 deletions(-) (limited to 'arch/arm64') diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index a7e748a46c18..5da6ff54b3e7 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -203,7 +203,6 @@ config ALPHA_EIGER config ALPHA_JENSEN bool "Jensen" depends on BROKEN - select DMA_DIRECT_OPS help DEC PC 150 AXP (aka Jensen): This is a very old Digital system - one of the first-generation Alpha systems. A number of these systems diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index fd48d698da29..7deaabeb531a 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -17,7 +17,6 @@ config ARC select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select COMMON_CLK - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC) select GENERIC_CLOCKEVENTS select GENERIC_FIND_FIRST_BIT diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index a858ee791ef0..586fc30b23bd 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -30,7 +30,6 @@ config ARM select CLONE_BACKWARDS select CPU_PM if (SUSPEND || CPU_IDLE) select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS - select DMA_DIRECT_OPS if !MMU select DMA_REMAP if MMU select EDAC_SUPPORT select EDAC_ATOMIC_SCRUB diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 06cf0ef24367..2092080240b0 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -80,7 +80,6 @@ config ARM64 select CPU_PM if (SUSPEND || CPU_IDLE) select CRC32 select DCACHE_WORD_ACCESS - select DMA_DIRECT_OPS select DMA_DIRECT_REMAP select EDAC_SUPPORT select FRAME_POINTER diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig index 84420109113d..456e154674d1 100644 --- a/arch/c6x/Kconfig +++ b/arch/c6x/Kconfig @@ -9,7 +9,6 @@ config C6X select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select CLKDEV_LOOKUP - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 select GENERIC_IRQ_SHOW select HAVE_ARCH_TRACEHOOK diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index ea74f3a9eeaf..37bed8aadf95 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -7,7 +7,6 @@ config CSKY select COMMON_CLK select CLKSRC_MMIO select CLKSRC_OF - select DMA_DIRECT_OPS select DMA_DIRECT_REMAP select IRQ_DOMAIN select HANDLE_DOMAIN_IRQ diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index d19c6b16cd5d..6472a0685470 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -22,7 +22,6 @@ config H8300 select HAVE_ARCH_KGDB select HAVE_ARCH_HASH select CPU_NO_EFFICIENT_FFS - select DMA_DIRECT_OPS config CPU_BIG_ENDIAN def_bool y diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 2b688af379e6..d71036c598de 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -31,7 +31,6 @@ config HEXAGON select GENERIC_CLOCKEVENTS_BROADCAST select MODULES_USE_ELF_RELA select GENERIC_CPU_DEVICES - select DMA_DIRECT_OPS ---help--- Qualcomm Hexagon is a processor architecture designed for high performance and low power across a wide variety of applications. diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 1bc9f1ba759a..8a5868e9a3a0 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -26,7 +26,6 @@ config M68K select MODULES_USE_ELF_RELA select OLD_SIGSUSPEND3 select OLD_SIGACTION - select DMA_DIRECT_OPS if HAS_DMA select ARCH_DISCARD_MEMBLOCK config CPU_BIG_ENDIAN diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index effed2efd306..eda9e2315ef5 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -12,7 +12,6 @@ config MICROBLAZE select TIMER_OF select CLONE_BACKWARDS3 select COMMON_CLK - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS select GENERIC_CPU_DEVICES diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 8272ea4c7264..2993aa9842c0 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -16,7 +16,6 @@ config MIPS select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select CPU_PM if CPU_IDLE - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS select GENERIC_CMOS_UPDATE diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 7a04adacb2f0..1af6bbae7220 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -11,7 +11,6 @@ config NDS32 select CLKSRC_MMIO select CLONE_BACKWARDS select COMMON_CLK - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index 7e95506e957a..f6c4b0f49997 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -4,7 +4,6 @@ config NIOS2 select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_NO_SWAP - select DMA_DIRECT_OPS select TIMER_OF select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index 285f7d05c8ed..d0feebad5a8f 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -7,7 +7,6 @@ config OPENRISC def_bool y select ARCH_HAS_SYNC_DMA_FOR_DEVICE - select DMA_DIRECT_OPS select OF select OF_EARLY_FLATTREE select IRQ_DOMAIN diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 428ee50fc3db..6e1b71da0e71 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -185,7 +185,6 @@ config PA11 depends on PA7000 || PA7100LC || PA7200 || PA7300LC select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE - select DMA_DIRECT_OPS select DMA_NONCOHERENT_CACHE_SYNC config PREFETCH diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 55da93f4e818..51d89c4b1dca 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -19,7 +19,6 @@ config RISCV select ARCH_WANT_FRAME_POINTERS select CLONE_BACKWARDS select COMMON_CLK - select DMA_DIRECT_OPS select GENERIC_CLOCKEVENTS select GENERIC_CPU_DEVICES select GENERIC_IRQ_SHOW diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 5624e8607054..21d271d04ca6 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -139,7 +139,6 @@ config S390 select HAVE_COPY_THREAD_TLS select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS - select DMA_DIRECT_OPS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EFFICIENT_UNALIGNED_ACCESS diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index f82a4da7adf3..10fd4e9c454b 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -7,7 +7,6 @@ config SUPERH select ARCH_NO_COHERENT_DMA_MMAP if !MMU select HAVE_PATA_PLATFORM select CLKDEV_LOOKUP - select DMA_DIRECT_OPS select HAVE_IDE if HAS_IOPORT_MAP select HAVE_MEMBLOCK_NODE_MAP select ARCH_DISCARD_MEMBLOCK diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 8853b6ceae17..f5bb9ded1d18 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -48,7 +48,6 @@ config SPARC config SPARC32 def_bool !64BIT select ARCH_HAS_SYNC_DMA_FOR_CPU - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 select CLZ_TAB select HAVE_UID16 diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index a4c05159dca5..2681027d7bff 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -4,7 +4,6 @@ config UNICORE32 select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO - select DMA_DIRECT_OPS select HAVE_GENERIC_DMA_COHERENT select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index adc845b66f01..c14d4a35be13 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -89,7 +89,6 @@ config X86 select CLOCKSOURCE_VALIDATE_LAST_CYCLE select CLOCKSOURCE_WATCHDOG select DCACHE_WORD_ACCESS - select DMA_DIRECT_OPS select EDAC_ATOMIC_SCRUB select EDAC_SUPPORT select GENERIC_CLOCKEVENTS diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 75488b606edc..36338e7564a3 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -9,7 +9,6 @@ config XTENSA select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select COMMON_CLK - select DMA_DIRECT_OPS select DMA_REMAP if MMU select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 41c3b1df70eb..ca88b867e7fe 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -35,13 +35,8 @@ config ARCH_HAS_DMA_COHERENT_TO_PFN config ARCH_HAS_DMA_MMAP_PGPROT bool -config DMA_DIRECT_OPS - bool - depends on HAS_DMA - config DMA_NONCOHERENT_CACHE_SYNC bool - depends on DMA_DIRECT_OPS config DMA_VIRT_OPS bool @@ -49,7 +44,6 @@ config DMA_VIRT_OPS config SWIOTLB bool - select DMA_DIRECT_OPS select NEED_DMA_MAP_STATE config DMA_REMAP @@ -58,5 +52,4 @@ config DMA_REMAP config DMA_DIRECT_REMAP bool - depends on DMA_DIRECT_OPS select DMA_REMAP diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile index f4feeceb8020..a626f643cd63 100644 --- a/kernel/dma/Makefile +++ b/kernel/dma/Makefile @@ -1,9 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_HAS_DMA) += mapping.o +obj-$(CONFIG_HAS_DMA) += mapping.o direct.o obj-$(CONFIG_DMA_CMA) += contiguous.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o -obj-$(CONFIG_DMA_DIRECT_OPS) += direct.o obj-$(CONFIG_DMA_VIRT_OPS) += virt.o obj-$(CONFIG_DMA_API_DEBUG) += debug.o obj-$(CONFIG_SWIOTLB) += swiotlb.o -- cgit v1.2.3-70-g09d2 From 90ac706e98fcb24fb0b0a259558987f33cc2f0f6 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 6 Dec 2018 13:14:44 -0800 Subject: dma-mapping: factor out dummy DMA ops The dummy DMA ops are currently used by arm64 for any device which has an invalid ACPI description and is thus barred from using DMA due to not knowing whether is is cache-coherent or not. Factor these out into general dma-mapping code so that they can be referenced from other common code paths. In the process, we can prune all the optional callbacks which just do the same thing as the default behaviour, and fill in .map_resource for completeness. Signed-off-by: Robin Murphy [hch: moved to a separate source file] Reviewed-by: Rafael J. Wysocki Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck Signed-off-by: Christoph Hellwig --- arch/arm64/include/asm/dma-mapping.h | 4 +- arch/arm64/mm/dma-mapping.c | 86 ------------------------------------ include/linux/dma-mapping.h | 1 + kernel/dma/Makefile | 2 +- kernel/dma/dummy.c | 39 ++++++++++++++++ 5 files changed, 42 insertions(+), 90 deletions(-) create mode 100644 kernel/dma/dummy.c (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index c41f3fb1446c..273e778f7de2 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -24,15 +24,13 @@ #include #include -extern const struct dma_map_ops dummy_dma_ops; - static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { /* * We expect no ISA devices, and all other DMA masters are expected to * have someone call arch_setup_dma_ops at device creation time. */ - return &dummy_dma_ops; + return &dma_dummy_ops; } void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 4c0f498069e8..6ff6ec8806c1 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -89,92 +89,6 @@ static int __swiotlb_mmap_pfn(struct vm_area_struct *vma, } #endif /* CONFIG_IOMMU_DMA */ -/******************************************** - * The following APIs are for dummy DMA ops * - ********************************************/ - -static void *__dummy_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, - unsigned long attrs) -{ - return NULL; -} - -static void __dummy_free(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs) -{ -} - -static int __dummy_mmap(struct device *dev, - struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - return -ENXIO; -} - -static dma_addr_t __dummy_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - return DMA_MAPPING_ERROR; -} - -static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ -} - -static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - unsigned long attrs) -{ - return 0; -} - -static void __dummy_unmap_sg(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, - unsigned long attrs) -{ -} - -static void __dummy_sync_single(struct device *dev, - dma_addr_t dev_addr, size_t size, - enum dma_data_direction dir) -{ -} - -static void __dummy_sync_sg(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) -{ -} - -static int __dummy_dma_supported(struct device *hwdev, u64 mask) -{ - return 0; -} - -const struct dma_map_ops dummy_dma_ops = { - .alloc = __dummy_alloc, - .free = __dummy_free, - .mmap = __dummy_mmap, - .map_page = __dummy_map_page, - .unmap_page = __dummy_unmap_page, - .map_sg = __dummy_map_sg, - .unmap_sg = __dummy_unmap_sg, - .sync_single_for_cpu = __dummy_sync_single, - .sync_single_for_device = __dummy_sync_single, - .sync_sg_for_cpu = __dummy_sync_sg, - .sync_sg_for_device = __dummy_sync_sg, - .dma_supported = __dummy_dma_supported, -}; -EXPORT_SYMBOL(dummy_dma_ops); - static int __init arm64_dma_init(void) { WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(), diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 0f0078490df4..269ee27fc3d9 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -136,6 +136,7 @@ struct dma_map_ops { extern const struct dma_map_ops dma_direct_ops; extern const struct dma_map_ops dma_virt_ops; +extern const struct dma_map_ops dma_dummy_ops; #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile index a626f643cd63..72ff6e46aa86 100644 --- a/kernel/dma/Makefile +++ b/kernel/dma/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_HAS_DMA) += mapping.o direct.o +obj-$(CONFIG_HAS_DMA) += mapping.o direct.o dummy.o obj-$(CONFIG_DMA_CMA) += contiguous.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o obj-$(CONFIG_DMA_VIRT_OPS) += virt.o diff --git a/kernel/dma/dummy.c b/kernel/dma/dummy.c new file mode 100644 index 000000000000..05607642c888 --- /dev/null +++ b/kernel/dma/dummy.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Dummy DMA ops that always fail. + */ +#include + +static int dma_dummy_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + return -ENXIO; +} + +static dma_addr_t dma_dummy_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + return DMA_MAPPING_ERROR; +} + +static int dma_dummy_map_sg(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir, + unsigned long attrs) +{ + return 0; +} + +static int dma_dummy_supported(struct device *hwdev, u64 mask) +{ + return 0; +} + +const struct dma_map_ops dma_dummy_ops = { + .mmap = dma_dummy_mmap, + .map_page = dma_dummy_map_page, + .map_sg = dma_dummy_map_sg, + .dma_supported = dma_dummy_supported, +}; +EXPORT_SYMBOL(dma_dummy_ops); -- cgit v1.2.3-70-g09d2 From 55897af63091ebc2c3f239c6a6666f748113ac50 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 3 Dec 2018 11:43:54 +0100 Subject: dma-direct: merge swiotlb_dma_ops into the dma_direct code While the dma-direct code is (relatively) clean and simple we actually have to use the swiotlb ops for the mapping on many architectures due to devices with addressing limits. Instead of keeping two implementations around this commit allows the dma-direct implementation to call the swiotlb bounce buffering functions and thus share the guts of the mapping implementation. This also simplified the dma-mapping setup on a few architectures where we don't have to differenciate which implementation to use. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- arch/arm64/mm/dma-mapping.c | 2 +- arch/ia64/hp/common/hwsw_iommu.c | 2 +- arch/ia64/hp/common/sba_iommu.c | 6 +- arch/ia64/kernel/dma-mapping.c | 2 +- arch/mips/include/asm/dma-mapping.h | 2 - arch/powerpc/kernel/dma-swiotlb.c | 16 +-- arch/riscv/include/asm/dma-mapping.h | 15 --- arch/x86/kernel/pci-swiotlb.c | 4 +- arch/x86/mm/mem_encrypt.c | 7 -- arch/x86/pci/sta2x11-fixup.c | 1 - include/linux/dma-direct.h | 12 ++ include/linux/swiotlb.h | 74 +++++------ kernel/dma/direct.c | 113 ++++++++++++----- kernel/dma/swiotlb.c | 232 ++--------------------------------- 14 files changed, 150 insertions(+), 338 deletions(-) delete mode 100644 arch/riscv/include/asm/dma-mapping.h (limited to 'arch/arm64') diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 6ff6ec8806c1..ab1e417204d0 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -463,7 +463,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent) { if (!dev->dma_ops) - dev->dma_ops = &swiotlb_dma_ops; + dev->dma_ops = &dma_direct_ops; dev->dma_coherent = coherent; __iommu_setup_dma_ops(dev, dma_base, size, iommu); diff --git a/arch/ia64/hp/common/hwsw_iommu.c b/arch/ia64/hp/common/hwsw_iommu.c index 58969039bed2..f40ca499b246 100644 --- a/arch/ia64/hp/common/hwsw_iommu.c +++ b/arch/ia64/hp/common/hwsw_iommu.c @@ -38,7 +38,7 @@ static inline int use_swiotlb(struct device *dev) const struct dma_map_ops *hwsw_dma_get_ops(struct device *dev) { if (use_swiotlb(dev)) - return &swiotlb_dma_ops; + return &dma_direct_ops; return &sba_dma_ops; } EXPORT_SYMBOL(hwsw_dma_get_ops); diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index 0d21c0b5b23d..5ee74820a0f6 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -2065,8 +2065,6 @@ static int __init acpi_sba_ioc_init_acpi(void) /* This has to run before acpi_scan_init(). */ arch_initcall(acpi_sba_ioc_init_acpi); -extern const struct dma_map_ops swiotlb_dma_ops; - static int __init sba_init(void) { @@ -2080,7 +2078,7 @@ sba_init(void) * a successful kdump kernel boot is to use the swiotlb. */ if (is_kdump_kernel()) { - dma_ops = &swiotlb_dma_ops; + dma_ops = &dma_direct_ops; if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0) panic("Unable to initialize software I/O TLB:" " Try machvec=dig boot option"); @@ -2102,7 +2100,7 @@ sba_init(void) * If we didn't find something sba_iommu can claim, we * need to setup the swiotlb and switch to the dig machvec. */ - dma_ops = &swiotlb_dma_ops; + dma_ops = &dma_direct_ops; if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0) panic("Unable to find SBA IOMMU or initialize " "software I/O TLB: Try machvec=dig boot option"); diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c index 36dd6aa6d759..80cd3e1ea95a 100644 --- a/arch/ia64/kernel/dma-mapping.c +++ b/arch/ia64/kernel/dma-mapping.c @@ -36,7 +36,7 @@ long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, void __init swiotlb_dma_init(void) { - dma_ops = &swiotlb_dma_ops; + dma_ops = &dma_direct_ops; swiotlb_init(1); } #endif diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h index b4c477eb46ce..69f914667f3e 100644 --- a/arch/mips/include/asm/dma-mapping.h +++ b/arch/mips/include/asm/dma-mapping.h @@ -10,8 +10,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { #if defined(CONFIG_MACH_JAZZ) return &jazz_dma_ops; -#elif defined(CONFIG_SWIOTLB) - return &swiotlb_dma_ops; #else return &dma_direct_ops; #endif diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 3d8df2cf8be9..430a7d0aa2cb 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -50,15 +50,15 @@ const struct dma_map_ops powerpc_swiotlb_dma_ops = { .alloc = __dma_nommu_alloc_coherent, .free = __dma_nommu_free_coherent, .mmap = dma_nommu_mmap_coherent, - .map_sg = swiotlb_map_sg_attrs, - .unmap_sg = swiotlb_unmap_sg_attrs, + .map_sg = dma_direct_map_sg, + .unmap_sg = dma_direct_unmap_sg, .dma_supported = swiotlb_dma_supported, - .map_page = swiotlb_map_page, - .unmap_page = swiotlb_unmap_page, - .sync_single_for_cpu = swiotlb_sync_single_for_cpu, - .sync_single_for_device = swiotlb_sync_single_for_device, - .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, - .sync_sg_for_device = swiotlb_sync_sg_for_device, + .map_page = dma_direct_map_page, + .unmap_page = dma_direct_unmap_page, + .sync_single_for_cpu = dma_direct_sync_single_for_cpu, + .sync_single_for_device = dma_direct_sync_single_for_device, + .sync_sg_for_cpu = dma_direct_sync_sg_for_cpu, + .sync_sg_for_device = dma_direct_sync_sg_for_device, .get_required_mask = swiotlb_powerpc_get_required, }; diff --git a/arch/riscv/include/asm/dma-mapping.h b/arch/riscv/include/asm/dma-mapping.h deleted file mode 100644 index 8facc1c8fa05..000000000000 --- a/arch/riscv/include/asm/dma-mapping.h +++ /dev/null @@ -1,15 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#ifndef _RISCV_ASM_DMA_MAPPING_H -#define _RISCV_ASM_DMA_MAPPING_H 1 - -#ifdef CONFIG_SWIOTLB -#include -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) -{ - return &swiotlb_dma_ops; -} -#else -#include -#endif /* CONFIG_SWIOTLB */ - -#endif /* _RISCV_ASM_DMA_MAPPING_H */ diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index bd08b9e1c9e2..5f5302028a9a 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -62,10 +62,8 @@ IOMMU_INIT(pci_swiotlb_detect_4gb, void __init pci_swiotlb_init(void) { - if (swiotlb) { + if (swiotlb) swiotlb_init(0); - dma_ops = &swiotlb_dma_ops; - } } void __init pci_swiotlb_late_init(void) diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 006f373f54ab..385afa2b9e17 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -380,13 +380,6 @@ void __init mem_encrypt_init(void) /* Call into SWIOTLB to update the SWIOTLB DMA buffers */ swiotlb_update_mem_attributes(); - /* - * With SEV, DMA operations cannot use encryption, we need to use - * SWIOTLB to bounce buffer DMA operation. - */ - if (sev_active()) - dma_ops = &swiotlb_dma_ops; - /* * With SEV, we need to unroll the rep string I/O instructions. */ diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 7a5bafb76d77..3cdafea55ab6 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -168,7 +168,6 @@ static void sta2x11_setup_pdev(struct pci_dev *pdev) return; pci_set_consistent_dma_mask(pdev, STA2X11_AMBA_SIZE - 1); pci_set_dma_mask(pdev, STA2X11_AMBA_SIZE - 1); - pdev->dev.dma_ops = &swiotlb_dma_ops; pdev->dev.archdata.is_sta2x11 = true; /* We must enable all devices as master, for audio DMA to work */ diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 1aa73f4907ae..3b0a3ea3876d 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -63,7 +63,19 @@ void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page) dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs); int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir); +void dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); +void dma_direct_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir); +void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); int dma_direct_supported(struct device *dev, u64 mask); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 14aec0b70dd9..7c007ed7505f 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -16,8 +16,6 @@ enum swiotlb_force { SWIOTLB_NO_FORCE, /* swiotlb=noforce */ }; -extern enum swiotlb_force swiotlb_force; - /* * Maximum allowable number of contiguous slabs to map, * must be a power of 2. What is the appropriate value ? @@ -62,56 +60,44 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev, size_t size, enum dma_data_direction dir, enum dma_sync_target target); -/* Accessory functions. */ - -extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs); -extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs); - -extern int -swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, - unsigned long attrs); - -extern void -swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - unsigned long attrs); - -extern void -swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir); - -extern void -swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); - -extern void -swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir); - -extern void -swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); - extern int swiotlb_dma_supported(struct device *hwdev, u64 mask); #ifdef CONFIG_SWIOTLB -extern void __init swiotlb_exit(void); +extern enum swiotlb_force swiotlb_force; +extern phys_addr_t io_tlb_start, io_tlb_end; + +static inline bool is_swiotlb_buffer(phys_addr_t paddr) +{ + return paddr >= io_tlb_start && paddr < io_tlb_end; +} + +bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, + size_t size, enum dma_data_direction dir, unsigned long attrs); +void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); #else -static inline void swiotlb_exit(void) { } -static inline unsigned int swiotlb_max_segment(void) { return 0; } -#endif +#define swiotlb_force SWIOTLB_NO_FORCE +static inline bool is_swiotlb_buffer(phys_addr_t paddr) +{ + return false; +} +static inline bool swiotlb_map(struct device *dev, phys_addr_t *phys, + dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + return false; +} +static inline void swiotlb_exit(void) +{ +} +static inline unsigned int swiotlb_max_segment(void) +{ + return 0; +} +#endif /* CONFIG_SWIOTLB */ extern void swiotlb_print_info(void); extern void swiotlb_set_max_segment(unsigned int); -extern const struct dma_map_ops swiotlb_dma_ops; - #endif /* __LINUX_SWIOTLB_H */ diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index d45306473c90..85d8286a0ba2 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -13,6 +13,7 @@ #include #include #include +#include /* * Most architectures use ZONE_DMA for the first 16 Megabytes, but @@ -209,69 +210,110 @@ void dma_direct_free(struct device *dev, size_t size, dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs); } -static void dma_direct_sync_single_for_device(struct device *dev, +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { - if (dev_is_dma_coherent(dev)) - return; - arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir); + phys_addr_t paddr = dma_to_phys(dev, addr); + + if (unlikely(is_swiotlb_buffer(paddr))) + swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); + + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_device(dev, paddr, size, dir); } -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) -static void dma_direct_sync_sg_for_device(struct device *dev, +void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { struct scatterlist *sg; int i; - if (dev_is_dma_coherent(dev)) - return; + for_each_sg(sgl, sg, nents, i) { + if (unlikely(is_swiotlb_buffer(sg_phys(sg)))) + swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, + dir, SYNC_FOR_DEVICE); - for_each_sg(sgl, sg, nents, i) - arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, + dir); + } } #endif #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) -static void dma_direct_sync_single_for_cpu(struct device *dev, + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { - if (dev_is_dma_coherent(dev)) - return; - arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir); - arch_sync_dma_for_cpu_all(dev); + phys_addr_t paddr = dma_to_phys(dev, addr); + + if (!dev_is_dma_coherent(dev)) { + arch_sync_dma_for_cpu(dev, paddr, size, dir); + arch_sync_dma_for_cpu_all(dev); + } + + if (unlikely(is_swiotlb_buffer(paddr))) + swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); } -static void dma_direct_sync_sg_for_cpu(struct device *dev, +void dma_direct_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { struct scatterlist *sg; int i; - if (dev_is_dma_coherent(dev)) - return; + for_each_sg(sgl, sg, nents, i) { + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); + + if (unlikely(is_swiotlb_buffer(sg_phys(sg)))) + swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, dir, + SYNC_FOR_CPU); + } - for_each_sg(sgl, sg, nents, i) - arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); - arch_sync_dma_for_cpu_all(dev); + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_cpu_all(dev); } -static void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, +void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { + phys_addr_t phys = dma_to_phys(dev, addr); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) dma_direct_sync_single_for_cpu(dev, addr, size, dir); + + if (unlikely(is_swiotlb_buffer(phys))) + swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } -static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir, + attrs); +} +#else +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs) { - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir); } #endif +static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr, + size_t size) +{ + return swiotlb_force != SWIOTLB_FORCE && + (!dev || dma_capable(dev, dma_addr, size)); +} + dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) @@ -279,13 +321,14 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dma_addr = phys_to_dma(dev, phys); - if (unlikely(dev && !dma_capable(dev, dma_addr, size))) { + if (unlikely(!dma_direct_possible(dev, dma_addr, size)) && + !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) { report_addr(dev, dma_addr, size); return DMA_MAPPING_ERROR; } - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_direct_sync_single_for_device(dev, dma_addr, size, dir); + if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(dev, phys, size, dir); return dma_addr; } @@ -299,11 +342,15 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, sg->dma_address = dma_direct_map_page(dev, sg_page(sg), sg->offset, sg->length, dir, attrs); if (sg->dma_address == DMA_MAPPING_ERROR) - return 0; + goto out_unmap; sg_dma_len(sg) = sg->length; } return nents; + +out_unmap: + dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); + return 0; } /* @@ -331,12 +378,14 @@ const struct dma_map_ops dma_direct_ops = { .free = dma_direct_free, .map_page = dma_direct_map_page, .map_sg = dma_direct_map_sg, -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_SWIOTLB) .sync_single_for_device = dma_direct_sync_single_for_device, .sync_sg_for_device = dma_direct_sync_sg_for_device, #endif #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ + defined(CONFIG_SWIOTLB) .sync_single_for_cpu = dma_direct_sync_single_for_cpu, .sync_sg_for_cpu = dma_direct_sync_sg_for_cpu, .unmap_page = dma_direct_unmap_page, diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 2e126bac5d7d..d6361776dc5c 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -21,7 +21,6 @@ #include #include -#include #include #include #include @@ -65,7 +64,7 @@ enum swiotlb_force swiotlb_force; * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this * API. */ -static phys_addr_t io_tlb_start, io_tlb_end; +phys_addr_t io_tlb_start, io_tlb_end; /* * The number of IO TLB blocks (in groups of 64) between io_tlb_start and @@ -383,11 +382,6 @@ void __init swiotlb_exit(void) max_segment = 0; } -static int is_swiotlb_buffer(phys_addr_t paddr) -{ - return paddr >= io_tlb_start && paddr < io_tlb_end; -} - /* * Bounce: copy the swiotlb buffer back to the original dma location */ @@ -623,221 +617,36 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, } } -static dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys, +/* + * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing + * to the device copy the data into it as well. + */ +bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - dma_addr_t dma_addr; + trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force); if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) { dev_warn_ratelimited(dev, "Cannot do DMA to address %pa\n", phys); - return DMA_MAPPING_ERROR; + return false; } /* Oh well, have to allocate and map a bounce buffer. */ *phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start), *phys, size, dir, attrs); if (*phys == DMA_MAPPING_ERROR) - return DMA_MAPPING_ERROR; + return false; /* Ensure that the address returned is DMA'ble */ - dma_addr = __phys_to_dma(dev, *phys); - if (unlikely(!dma_capable(dev, dma_addr, size))) { + *dma_addr = __phys_to_dma(dev, *phys); + if (unlikely(!dma_capable(dev, *dma_addr, size))) { swiotlb_tbl_unmap_single(dev, *phys, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); - return DMA_MAPPING_ERROR; - } - - return dma_addr; -} - -/* - * Map a single buffer of the indicated size for DMA in streaming mode. The - * physical address to use is returned. - * - * Once the device is given the dma address, the device owns this memory until - * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed. - */ -dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - phys_addr_t phys = page_to_phys(page) + offset; - dma_addr_t dev_addr = phys_to_dma(dev, phys); - - BUG_ON(dir == DMA_NONE); - /* - * If the address happens to be in the device's DMA window, - * we can safely return the device addr and not worry about bounce - * buffering it. - */ - if (!dma_capable(dev, dev_addr, size) || - swiotlb_force == SWIOTLB_FORCE) { - trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); - dev_addr = swiotlb_bounce_page(dev, &phys, size, dir, attrs); + return false; } - if (!dev_is_dma_coherent(dev) && - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0 && - dev_addr != DMA_MAPPING_ERROR) - arch_sync_dma_for_device(dev, phys, size, dir); - - return dev_addr; -} - -/* - * Unmap a single streaming mode DMA translation. The dma_addr and size must - * match what was provided for in a previous swiotlb_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. - */ -void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); - - BUG_ON(dir == DMA_NONE); - - if (!dev_is_dma_coherent(hwdev) && - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - arch_sync_dma_for_cpu(hwdev, paddr, size, dir); - - if (is_swiotlb_buffer(paddr)) - swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs); -} - -/* - * Make physical memory consistent for a single streaming mode DMA translation - * after a transfer. - * - * If you perform a swiotlb_map_page() but wish to interrogate the buffer - * using the cpu, yet do not wish to teardown the dma mapping, you must - * call this function before doing so. At the next point you give the dma - * address back to the card, you must first perform a - * swiotlb_dma_sync_for_device, and then the device again owns the buffer - */ -static void -swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - enum dma_sync_target target) -{ - phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); - - BUG_ON(dir == DMA_NONE); - - if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_CPU) - arch_sync_dma_for_cpu(hwdev, paddr, size, dir); - - if (is_swiotlb_buffer(paddr)) - swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target); - - if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_DEVICE) - arch_sync_dma_for_device(hwdev, paddr, size, dir); -} - -void -swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir) -{ - swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU); -} - -void -swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir) -{ - swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE); -} - -/* - * Map a set of buffers described by scatterlist in streaming mode for DMA. - * This is the scatter-gather version of the above swiotlb_map_page - * 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}(SG). - * - * Device ownership issues as mentioned above for swiotlb_map_page are the - * same here. - */ -int -swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, unsigned long attrs) -{ - struct scatterlist *sg; - int i; - - for_each_sg(sgl, sg, nelems, i) { - sg->dma_address = swiotlb_map_page(dev, sg_page(sg), sg->offset, - sg->length, dir, attrs); - if (sg->dma_address == DMA_MAPPING_ERROR) - goto out_error; - sg_dma_len(sg) = sg->length; - } - - return nelems; - -out_error: - swiotlb_unmap_sg_attrs(dev, sgl, i, dir, - attrs | DMA_ATTR_SKIP_CPU_SYNC); - sg_dma_len(sgl) = 0; - return 0; -} - -/* - * Unmap a set of streaming mode DMA translations. Again, cpu read rules - * concerning calls here are the same as for swiotlb_unmap_page() above. - */ -void -swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - unsigned long attrs) -{ - struct scatterlist *sg; - int i; - - BUG_ON(dir == DMA_NONE); - - for_each_sg(sgl, sg, nelems, i) - swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg), dir, - attrs); -} - -/* - * Make physical memory consistent for a set of streaming mode DMA translations - * after a transfer. - * - * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules - * and usage. - */ -static void -swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - enum dma_sync_target target) -{ - struct scatterlist *sg; - int i; - - for_each_sg(sgl, sg, nelems, i) - swiotlb_sync_single(hwdev, sg->dma_address, - sg_dma_len(sg), dir, target); -} - -void -swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir) -{ - swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU); -} - -void -swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir) -{ - swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE); + return true; } /* @@ -851,18 +660,3 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask) { return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask; } - -const struct dma_map_ops swiotlb_dma_ops = { - .alloc = dma_direct_alloc, - .free = dma_direct_free, - .sync_single_for_cpu = swiotlb_sync_single_for_cpu, - .sync_single_for_device = swiotlb_sync_single_for_device, - .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, - .sync_sg_for_device = swiotlb_sync_sg_for_device, - .map_sg = swiotlb_map_sg_attrs, - .unmap_sg = swiotlb_unmap_sg_attrs, - .map_page = swiotlb_map_page, - .unmap_page = swiotlb_unmap_page, - .dma_supported = dma_direct_supported, -}; -EXPORT_SYMBOL(swiotlb_dma_ops); -- cgit v1.2.3-70-g09d2 From 356da6d0cde3323236977fce54c1f9612a742036 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Dec 2018 13:39:32 -0800 Subject: dma-mapping: bypass indirect calls for dma-direct Avoid expensive indirect calls in the fast path DMA mapping operations by directly calling the dma_direct_* ops if we are using the directly mapped DMA operations. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- arch/alpha/include/asm/dma-mapping.h | 2 +- arch/arc/mm/cache.c | 2 +- arch/arm/include/asm/dma-mapping.h | 2 +- arch/arm/mm/dma-mapping-nommu.c | 14 +---- arch/arm64/mm/dma-mapping.c | 3 - arch/ia64/hp/common/hwsw_iommu.c | 2 +- arch/ia64/hp/common/sba_iommu.c | 4 +- arch/ia64/kernel/dma-mapping.c | 1 - arch/mips/include/asm/dma-mapping.h | 2 +- arch/parisc/kernel/setup.c | 4 -- arch/sparc/include/asm/dma-mapping.h | 4 +- arch/x86/kernel/pci-dma.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 2 +- drivers/iommu/amd_iommu.c | 13 +--- include/asm-generic/dma-mapping.h | 2 +- include/linux/dma-direct.h | 17 ------ include/linux/dma-mapping.h | 111 ++++++++++++++++++++++++++++++----- include/linux/dma-noncoherent.h | 5 +- kernel/dma/direct.c | 37 +++--------- kernel/dma/mapping.c | 40 ++++++++----- 20 files changed, 150 insertions(+), 119 deletions(-) (limited to 'arch/arm64') diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h index 8beeafd4f68e..0ee6a5c99b16 100644 --- a/arch/alpha/include/asm/dma-mapping.h +++ b/arch/alpha/include/asm/dma-mapping.h @@ -7,7 +7,7 @@ extern const struct dma_map_ops alpha_pci_ops; static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { #ifdef CONFIG_ALPHA_JENSEN - return &dma_direct_ops; + return NULL; #else return &alpha_pci_ops; #endif diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index f2701c13a66b..e188bb3ede53 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -1280,7 +1280,7 @@ void __init arc_cache_init_master(void) /* * In case of IOC (say IOC+SLC case), pointers above could still be set * but end up not being relevant as the first function in chain is not - * called at all for @dma_direct_ops + * called at all for devices using coherent DMA. * arch_sync_dma_for_cpu() -> dma_cache_*() -> __dma_cache_*() */ } diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 965b7c846ecb..31d3b96f0f4b 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -18,7 +18,7 @@ extern const struct dma_map_ops arm_coherent_dma_ops; static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { - return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_direct_ops; + return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : NULL; } #ifdef __arch_page_to_dma diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c index 712416ecd8e6..f304b10e23a4 100644 --- a/arch/arm/mm/dma-mapping-nommu.c +++ b/arch/arm/mm/dma-mapping-nommu.c @@ -22,7 +22,7 @@ #include "dma.h" /* - * dma_direct_ops is used if + * The generic direct mapping code is used if * - MMU/MPU is off * - cpu is v7m w/o cache support * - device is coherent @@ -209,16 +209,9 @@ const struct dma_map_ops arm_nommu_dma_ops = { }; EXPORT_SYMBOL(arm_nommu_dma_ops); -static const struct dma_map_ops *arm_nommu_get_dma_map_ops(bool coherent) -{ - return coherent ? &dma_direct_ops : &arm_nommu_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; - if (IS_ENABLED(CONFIG_CPU_V7M)) { /* * Cache support for v7m is optional, so can be treated as @@ -234,7 +227,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, dev->archdata.dma_coherent = (get_cr() & CR_M) ? coherent : true; } - dma_ops = arm_nommu_get_dma_map_ops(dev->archdata.dma_coherent); - - set_dma_ops(dev, dma_ops); + if (!dev->archdata.dma_coherent) + set_dma_ops(dev, &arm_nommu_dma_ops); } diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index ab1e417204d0..95eda81e3f2d 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -462,9 +462,6 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent) { - if (!dev->dma_ops) - dev->dma_ops = &dma_direct_ops; - dev->dma_coherent = coherent; __iommu_setup_dma_ops(dev, dma_base, size, iommu); diff --git a/arch/ia64/hp/common/hwsw_iommu.c b/arch/ia64/hp/common/hwsw_iommu.c index f40ca499b246..8840ed97712f 100644 --- a/arch/ia64/hp/common/hwsw_iommu.c +++ b/arch/ia64/hp/common/hwsw_iommu.c @@ -38,7 +38,7 @@ static inline int use_swiotlb(struct device *dev) const struct dma_map_ops *hwsw_dma_get_ops(struct device *dev) { if (use_swiotlb(dev)) - return &dma_direct_ops; + return NULL; return &sba_dma_ops; } EXPORT_SYMBOL(hwsw_dma_get_ops); diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index 5ee74820a0f6..5a361e51cb1e 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -2078,7 +2078,7 @@ sba_init(void) * a successful kdump kernel boot is to use the swiotlb. */ if (is_kdump_kernel()) { - dma_ops = &dma_direct_ops; + dma_ops = NULL; if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0) panic("Unable to initialize software I/O TLB:" " Try machvec=dig boot option"); @@ -2100,7 +2100,7 @@ sba_init(void) * If we didn't find something sba_iommu can claim, we * need to setup the swiotlb and switch to the dig machvec. */ - dma_ops = &dma_direct_ops; + dma_ops = NULL; if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0) panic("Unable to find SBA IOMMU or initialize " "software I/O TLB: Try machvec=dig boot option"); diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c index 80cd3e1ea95a..ad7d9963de34 100644 --- a/arch/ia64/kernel/dma-mapping.c +++ b/arch/ia64/kernel/dma-mapping.c @@ -36,7 +36,6 @@ long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, void __init swiotlb_dma_init(void) { - dma_ops = &dma_direct_ops; swiotlb_init(1); } #endif diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h index 69f914667f3e..20dfaad3a55d 100644 --- a/arch/mips/include/asm/dma-mapping.h +++ b/arch/mips/include/asm/dma-mapping.h @@ -11,7 +11,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) #if defined(CONFIG_MACH_JAZZ) return &jazz_dma_ops; #else - return &dma_direct_ops; + return NULL; #endif } diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index cd227f1cf629..54818cd78bd0 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -99,10 +99,6 @@ void __init dma_ops_init(void) case pcxl2: pa7300lc_init(); - case pcxl: /* falls through */ - case pcxs: - case pcxt: - hppa_dma_ops = &dma_direct_ops; break; default: break; diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h index 55a44f08a9a4..ed32845bd2d2 100644 --- a/arch/sparc/include/asm/dma-mapping.h +++ b/arch/sparc/include/asm/dma-mapping.h @@ -12,11 +12,11 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { #ifdef CONFIG_SPARC_LEON if (sparc_cpu_model == sparc_leon) - return &dma_direct_ops; + return NULL; #endif #if defined(CONFIG_SPARC32) && defined(CONFIG_PCI) if (bus == &pci_bus_type) - return &dma_direct_ops; + return NULL; #endif return dma_ops; } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index f4562fcec681..d460998ae828 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -17,7 +17,7 @@ static bool disable_dac_quirk __read_mostly; -const struct dma_map_ops *dma_ops = &dma_direct_ops; +const struct dma_map_ops *dma_ops; EXPORT_SYMBOL(dma_ops); #ifdef CONFIG_IOMMU_DEBUG diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 61a84b958d67..50637f372e9f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -581,7 +581,7 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) dev_priv->map_mode = vmw_dma_map_populate; - if (dma_ops->sync_single_for_cpu) + if (dma_ops && dma_ops->sync_single_for_cpu) dev_priv->map_mode = vmw_dma_alloc_coherent; #ifdef CONFIG_SWIOTLB if (swiotlb_nr_tbl() == 0) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index c5d6c7c42b0a..567221cca13c 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2184,7 +2184,7 @@ static int amd_iommu_add_device(struct device *dev) dev_name(dev)); iommu_ignore_device(dev); - dev->dma_ops = &dma_direct_ops; + dev->dma_ops = NULL; goto out; } init_iommu_group(dev); @@ -2770,17 +2770,6 @@ int __init amd_iommu_init_dma_ops(void) swiotlb = (iommu_pass_through || sme_me_mask) ? 1 : 0; iommu_detected = 1; - /* - * In case we don't initialize SWIOTLB (actually the common case - * when AMD IOMMU is enabled and SME is not active), make sure there - * are global dma_ops set as a fall-back for devices not handled by - * this driver (for example non-PCI devices). When SME is active, - * make sure that swiotlb variable remains set so the global dma_ops - * continue to be SWIOTLB. - */ - if (!swiotlb) - dma_ops = &dma_direct_ops; - if (amd_iommu_unmap_flush) pr_info("AMD-Vi: IO/TLB flush on unmap enabled\n"); else diff --git a/include/asm-generic/dma-mapping.h b/include/asm-generic/dma-mapping.h index 880a292d792f..c13f46109e88 100644 --- a/include/asm-generic/dma-mapping.h +++ b/include/asm-generic/dma-mapping.h @@ -4,7 +4,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { - return &dma_direct_ops; + return NULL; } #endif /* _ASM_GENERIC_DMA_MAPPING_H */ diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 3b0a3ea3876d..b7338702592a 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -60,22 +60,5 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page); -dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs); -void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, unsigned long attrs); -int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, - enum dma_data_direction dir, unsigned long attrs); -void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, - int nents, enum dma_data_direction dir, unsigned long attrs); -void dma_direct_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir); -void dma_direct_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir); -void dma_direct_sync_single_for_cpu(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir); -void dma_direct_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir); int dma_direct_supported(struct device *dev, u64 mask); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 269ee27fc3d9..f422aec0f53c 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -134,7 +134,6 @@ struct dma_map_ops { #define DMA_MAPPING_ERROR (~(dma_addr_t)0) -extern const struct dma_map_ops dma_direct_ops; extern const struct dma_map_ops dma_virt_ops; extern const struct dma_map_ops dma_dummy_ops; @@ -222,6 +221,69 @@ static inline const struct dma_map_ops *get_dma_ops(struct device *dev) } #endif +static inline bool dma_is_direct(const struct dma_map_ops *ops) +{ + return likely(!ops); +} + +/* + * All the dma_direct_* declarations are here just for the indirect call bypass, + * and must not be used directly drivers! + */ +dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs); +int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, + enum dma_data_direction dir, unsigned long attrs); + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir); +void dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); +#else +static inline void dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ +} +#endif + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir); +void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); +#else +static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ +} +static inline void dma_direct_unmap_sg(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir, + unsigned long attrs) +{ +} +static inline void dma_direct_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ +} +#endif + static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, @@ -232,9 +294,12 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, BUG_ON(!valid_dma_direction(dir)); debug_dma_map_single(dev, ptr, size); - addr = ops->map_page(dev, virt_to_page(ptr), - offset_in_page(ptr), size, - dir, attrs); + if (dma_is_direct(ops)) + addr = dma_direct_map_page(dev, virt_to_page(ptr), + offset_in_page(ptr), size, dir, attrs); + else + addr = ops->map_page(dev, virt_to_page(ptr), + offset_in_page(ptr), size, dir, attrs); debug_dma_map_page(dev, virt_to_page(ptr), offset_in_page(ptr), size, dir, addr, true); @@ -249,7 +314,9 @@ static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->unmap_page) + if (dma_is_direct(ops)) + dma_direct_unmap_page(dev, addr, size, dir, attrs); + else if (ops->unmap_page) ops->unmap_page(dev, addr, size, dir, attrs); debug_dma_unmap_page(dev, addr, size, dir, true); } @@ -272,7 +339,10 @@ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int ents; BUG_ON(!valid_dma_direction(dir)); - ents = ops->map_sg(dev, sg, nents, dir, attrs); + if (dma_is_direct(ops)) + ents = dma_direct_map_sg(dev, sg, nents, dir, attrs); + else + ents = ops->map_sg(dev, sg, nents, dir, attrs); BUG_ON(ents < 0); debug_dma_map_sg(dev, sg, nents, ents, dir); @@ -287,7 +357,9 @@ static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg BUG_ON(!valid_dma_direction(dir)); debug_dma_unmap_sg(dev, sg, nents, dir); - if (ops->unmap_sg) + if (dma_is_direct(ops)) + dma_direct_unmap_sg(dev, sg, nents, dir, attrs); + else if (ops->unmap_sg) ops->unmap_sg(dev, sg, nents, dir, attrs); } @@ -301,7 +373,10 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev, dma_addr_t addr; BUG_ON(!valid_dma_direction(dir)); - addr = ops->map_page(dev, page, offset, size, dir, attrs); + if (dma_is_direct(ops)) + addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); + else + addr = ops->map_page(dev, page, offset, size, dir, attrs); debug_dma_map_page(dev, page, offset, size, dir, addr, false); return addr; @@ -322,7 +397,7 @@ static inline dma_addr_t dma_map_resource(struct device *dev, BUG_ON(pfn_valid(PHYS_PFN(phys_addr))); addr = phys_addr; - if (ops->map_resource) + if (ops && ops->map_resource) addr = ops->map_resource(dev, phys_addr, size, dir, attrs); debug_dma_map_resource(dev, phys_addr, size, dir, addr); @@ -337,7 +412,7 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->unmap_resource) + if (ops && ops->unmap_resource) ops->unmap_resource(dev, addr, size, dir, attrs); debug_dma_unmap_resource(dev, addr, size, dir); } @@ -349,7 +424,9 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->sync_single_for_cpu) + if (dma_is_direct(ops)) + dma_direct_sync_single_for_cpu(dev, addr, size, dir); + else if (ops->sync_single_for_cpu) ops->sync_single_for_cpu(dev, addr, size, dir); debug_dma_sync_single_for_cpu(dev, addr, size, dir); } @@ -368,7 +445,9 @@ static inline void dma_sync_single_for_device(struct device *dev, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->sync_single_for_device) + if (dma_is_direct(ops)) + dma_direct_sync_single_for_device(dev, addr, size, dir); + else if (ops->sync_single_for_device) ops->sync_single_for_device(dev, addr, size, dir); debug_dma_sync_single_for_device(dev, addr, size, dir); } @@ -387,7 +466,9 @@ dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->sync_sg_for_cpu) + if (dma_is_direct(ops)) + dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir); + else if (ops->sync_sg_for_cpu) ops->sync_sg_for_cpu(dev, sg, nelems, dir); debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir); } @@ -399,7 +480,9 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->sync_sg_for_device) + if (dma_is_direct(ops)) + dma_direct_sync_sg_for_device(dev, sg, nelems, dir); + else if (ops->sync_sg_for_device) ops->sync_sg_for_device(dev, sg, nelems, dir); debug_dma_sync_sg_for_device(dev, sg, nelems, dir); diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 306557331d7d..69b36ed31a99 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -38,7 +38,10 @@ pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction); #else -#define arch_dma_cache_sync NULL +static inline void arch_dma_cache_sync(struct device *dev, void *vaddr, + size_t size, enum dma_data_direction direction) +{ +} #endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */ #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 85d8286a0ba2..79da61b49fa4 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -223,6 +223,7 @@ void dma_direct_sync_single_for_device(struct device *dev, if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_device(dev, paddr, size, dir); } +EXPORT_SYMBOL(dma_direct_sync_single_for_device); void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) @@ -240,6 +241,7 @@ void dma_direct_sync_sg_for_device(struct device *dev, dir); } } +EXPORT_SYMBOL(dma_direct_sync_sg_for_device); #endif #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ @@ -258,6 +260,7 @@ void dma_direct_sync_single_for_cpu(struct device *dev, if (unlikely(is_swiotlb_buffer(paddr))) swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); } +EXPORT_SYMBOL(dma_direct_sync_single_for_cpu); void dma_direct_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) @@ -277,6 +280,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev, if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_cpu_all(dev); } +EXPORT_SYMBOL(dma_direct_sync_sg_for_cpu); void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) @@ -289,6 +293,7 @@ void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, if (unlikely(is_swiotlb_buffer(phys))) swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } +EXPORT_SYMBOL(dma_direct_unmap_page); void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs) @@ -300,11 +305,7 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir, attrs); } -#else -void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ -} +EXPORT_SYMBOL(dma_direct_unmap_sg); #endif static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr, @@ -331,6 +332,7 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, arch_sync_dma_for_device(dev, phys, size, dir); return dma_addr; } +EXPORT_SYMBOL(dma_direct_map_page); int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs) @@ -352,6 +354,7 @@ out_unmap: dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); return 0; } +EXPORT_SYMBOL(dma_direct_map_sg); /* * Because 32-bit DMA masks are so common we expect every architecture to be @@ -372,27 +375,3 @@ int dma_direct_supported(struct device *dev, u64 mask) return mask >= phys_to_dma(dev, min_mask); } - -const struct dma_map_ops dma_direct_ops = { - .alloc = dma_direct_alloc, - .free = dma_direct_free, - .map_page = dma_direct_map_page, - .map_sg = dma_direct_map_sg, -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ - defined(CONFIG_SWIOTLB) - .sync_single_for_device = dma_direct_sync_single_for_device, - .sync_sg_for_device = dma_direct_sync_sg_for_device, -#endif -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ - defined(CONFIG_SWIOTLB) - .sync_single_for_cpu = dma_direct_sync_single_for_cpu, - .sync_sg_for_cpu = dma_direct_sync_sg_for_cpu, - .unmap_page = dma_direct_unmap_page, - .unmap_sg = dma_direct_unmap_sg, -#endif - .get_required_mask = dma_direct_get_required_mask, - .dma_supported = dma_direct_supported, - .cache_sync = arch_dma_cache_sync, -}; -EXPORT_SYMBOL(dma_direct_ops); diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 0b18cfbdde95..fc84c81029d9 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -7,6 +7,7 @@ */ #include /* for max_pfn */ #include +#include #include #include #include @@ -229,8 +230,8 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); - BUG_ON(!ops); - if (ops->get_sgtable) + + if (!dma_is_direct(ops) && ops->get_sgtable) return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs); return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size, @@ -293,8 +294,8 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); - BUG_ON(!ops); - if (ops->mmap) + + if (!dma_is_direct(ops) && ops->mmap) return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs); return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); } @@ -324,6 +325,8 @@ u64 dma_get_required_mask(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); + if (dma_is_direct(ops)) + return dma_direct_get_required_mask(dev); if (ops->get_required_mask) return ops->get_required_mask(dev); return dma_default_get_required_mask(dev); @@ -341,7 +344,6 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, const struct dma_map_ops *ops = get_dma_ops(dev); void *cpu_addr; - BUG_ON(!ops); WARN_ON_ONCE(dev && !dev->coherent_dma_mask); if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr)) @@ -352,10 +354,14 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, if (!arch_dma_alloc_attrs(&dev)) return NULL; - if (!ops->alloc) + + if (dma_is_direct(ops)) + cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs); + else if (ops->alloc) + cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs); + else return NULL; - cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs); debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr); return cpu_addr; } @@ -366,8 +372,6 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, { const struct dma_map_ops *ops = get_dma_ops(dev); - BUG_ON(!ops); - if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr)) return; /* @@ -379,11 +383,14 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, */ WARN_ON(irqs_disabled()); - if (!ops->free || !cpu_addr) + if (!cpu_addr) return; debug_dma_free_coherent(dev, size, cpu_addr, dma_handle); - ops->free(dev, size, cpu_addr, dma_handle, attrs); + if (dma_is_direct(ops)) + dma_direct_free(dev, size, cpu_addr, dma_handle, attrs); + else if (ops->free) + ops->free(dev, size, cpu_addr, dma_handle, attrs); } EXPORT_SYMBOL(dma_free_attrs); @@ -397,9 +404,9 @@ int dma_supported(struct device *dev, u64 mask) { const struct dma_map_ops *ops = get_dma_ops(dev); - if (!ops) - return 0; - if (!ops->dma_supported) + if (dma_is_direct(ops)) + return dma_direct_supported(dev, mask); + if (ops->dma_supported) return 1; return ops->dma_supported(dev, mask); } @@ -437,7 +444,10 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->cache_sync) + + if (dma_is_direct(ops)) + arch_dma_cache_sync(dev, vaddr, size, dir); + else if (ops->cache_sync) ops->cache_sync(dev, vaddr, size, dir); } EXPORT_SYMBOL(dma_cache_sync); -- cgit v1.2.3-70-g09d2 From 9ab91e7c5c514b675470d9b57393cbe455722060 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 14 Dec 2018 15:18:08 +0100 Subject: arm64: default to the direct mapping in get_arch_dma_ops Otherwise the direct mapping won't work at all given that a NULL dev->dma_ops causes a fallback. Note that we already explicitly set dev->dma_ops to dma_dummy_ops for dma-incapable devices, so this fallback should not be needed anyway. Fixes: 356da6d0cd ("dma-mapping: bypass indirect calls for dma-direct") Signed-off-by: Christoph Hellwig Reported-by: Marek Szyprowski Tested-by: Marek Szyprowski Reviewed-by: Robin Murphy --- arch/arm64/include/asm/dma-mapping.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index 273e778f7de2..95dbf3ef735a 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -26,11 +26,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { - /* - * We expect no ISA devices, and all other DMA masters are expected to - * have someone call arch_setup_dma_ops at device creation time. - */ - return &dma_dummy_ops; + return NULL; } void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, -- cgit v1.2.3-70-g09d2