From b18814e767a445534ab9ccba02e82a31208f85d6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 4 Nov 2018 17:27:56 +0100 Subject: dma-direct: provide page based alloc/free helpers Some architectures support remapping highmem into DMA coherent allocations. To use the common code for them we need variants of dma_direct_{alloc,free}_pages that do not use kernel virtual addresses. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- kernel/dma/direct.c | 32 ++++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 22a12ab5a5e9..680287779b0a 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -103,14 +103,13 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) min_not_zero(dev->coherent_dma_mask, dev->bus_dma_mask); } -void *dma_direct_alloc_pages(struct device *dev, size_t size, +struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; int page_order = get_order(size); struct page *page = NULL; u64 phys_mask; - void *ret; if (attrs & DMA_ATTR_NO_WARN) gfp |= __GFP_NOWARN; @@ -150,11 +149,22 @@ again: } } + return page; +} + +void *dma_direct_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +{ + struct page *page; + void *ret; + + page = __dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs); if (!page) return NULL; + ret = page_address(page); if (force_dma_unencrypted()) { - set_memory_decrypted((unsigned long)ret, 1 << page_order); + set_memory_decrypted((unsigned long)ret, 1 << get_order(size)); *dma_handle = __phys_to_dma(dev, page_to_phys(page)); } else { *dma_handle = phys_to_dma(dev, page_to_phys(page)); @@ -163,20 +173,22 @@ again: return ret; } -/* - * NOTE: this function must never look at the dma_addr argument, because we want - * to be able to use it as a helper for iommu implementations as well. - */ +void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + if (!dma_release_from_contiguous(dev, page, count)) + __free_pages(page, get_order(size)); +} + void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) { - unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned int page_order = get_order(size); if (force_dma_unencrypted()) set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order); - if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count)) - free_pages((unsigned long)cpu_addr, page_order); + __dma_direct_free_pages(dev, size, virt_to_page(cpu_addr)); } void *dma_direct_alloc(struct device *dev, size_t size, -- cgit v1.2.1 From 704f2c20eaa566f6906e8812b6e2115889bd753d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 22 Sep 2018 20:47:26 +0200 Subject: dma-direct: reject highmem pages from dma_alloc_from_contiguous dma_alloc_from_contiguous can return highmem pages depending on the setup, which a plain non-remapping DMA allocator can't handle. Detect this case and fail the allocation. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- kernel/dma/direct.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'kernel/dma') diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 680287779b0a..c49849bcced6 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -162,6 +162,18 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, if (!page) return NULL; + if (PageHighMem(page)) { + /* + * Depending on the cma= arguments and per-arch setup + * dma_alloc_from_contiguous could return highmem pages. + * Without remapping there is no way to return them here, + * so log an error and fail. + */ + dev_info(dev, "Rejecting highmem page from CMA.\n"); + __dma_direct_free_pages(dev, size, page); + return NULL; + } + ret = page_address(page); if (force_dma_unencrypted()) { set_memory_decrypted((unsigned long)ret, 1 << get_order(size)); -- cgit v1.2.1 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 --- kernel/dma/Kconfig | 4 +++ kernel/dma/Makefile | 2 +- kernel/dma/mapping.c | 84 ------------------------------------------------- kernel/dma/remap.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 93 insertions(+), 85 deletions(-) create mode 100644 kernel/dma/remap.c (limited to 'kernel/dma') diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 645c7a2ecde8..c92e08173ed8 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -51,3 +51,7 @@ config SWIOTLB bool select DMA_DIRECT_OPS select NEED_DMA_MAP_STATE + +config DMA_REMAP + depends on MMU + bool diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile index 7d581e4eea4a..f4feeceb8020 100644 --- a/kernel/dma/Makefile +++ b/kernel/dma/Makefile @@ -7,4 +7,4 @@ 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 - +obj-$(CONFIG_DMA_REMAP) += remap.o diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 58dec7a92b7b..dfbc3deb95cd 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -262,87 +262,3 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, #endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */ } EXPORT_SYMBOL(dma_common_mmap); - -#ifdef CONFIG_MMU -static struct vm_struct *__dma_common_pages_remap(struct page **pages, - size_t size, unsigned long vm_flags, pgprot_t prot, - const void *caller) -{ - struct vm_struct *area; - - area = get_vm_area_caller(size, vm_flags, caller); - if (!area) - return NULL; - - if (map_vm_area(area, prot, pages)) { - vunmap(area->addr); - return NULL; - } - - return area; -} - -/* - * remaps an array of PAGE_SIZE pages into another vm_area - * Cannot be used in non-sleeping contexts - */ -void *dma_common_pages_remap(struct page **pages, size_t size, - unsigned long vm_flags, pgprot_t prot, - const void *caller) -{ - struct vm_struct *area; - - area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller); - if (!area) - return NULL; - - area->pages = pages; - - return area->addr; -} - -/* - * remaps an allocated contiguous region into another vm_area. - * Cannot be used in non-sleeping contexts - */ - -void *dma_common_contiguous_remap(struct page *page, size_t size, - unsigned long vm_flags, - pgprot_t prot, const void *caller) -{ - int i; - struct page **pages; - struct vm_struct *area; - - pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL); - if (!pages) - return NULL; - - for (i = 0; i < (size >> PAGE_SHIFT); i++) - pages[i] = nth_page(page, i); - - area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller); - - kfree(pages); - - if (!area) - return NULL; - return area->addr; -} - -/* - * unmaps a range previously mapped by dma_common_*_remap - */ -void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags) -{ - struct vm_struct *area = find_vm_area(cpu_addr); - - if (!area || (area->flags & vm_flags) != vm_flags) { - WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); - return; - } - - unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size)); - vunmap(cpu_addr); -} -#endif diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c new file mode 100644 index 000000000000..a15c393ea4e5 --- /dev/null +++ b/kernel/dma/remap.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2014 The Linux Foundation + */ +#include +#include +#include + +static struct vm_struct *__dma_common_pages_remap(struct page **pages, + size_t size, unsigned long vm_flags, pgprot_t prot, + const void *caller) +{ + struct vm_struct *area; + + area = get_vm_area_caller(size, vm_flags, caller); + if (!area) + return NULL; + + if (map_vm_area(area, prot, pages)) { + vunmap(area->addr); + return NULL; + } + + return area; +} + +/* + * Remaps an array of PAGE_SIZE pages into another vm_area. + * Cannot be used in non-sleeping contexts + */ +void *dma_common_pages_remap(struct page **pages, size_t size, + unsigned long vm_flags, pgprot_t prot, + const void *caller) +{ + struct vm_struct *area; + + area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller); + if (!area) + return NULL; + + area->pages = pages; + + return area->addr; +} + +/* + * Remaps an allocated contiguous region into another vm_area. + * Cannot be used in non-sleeping contexts + */ +void *dma_common_contiguous_remap(struct page *page, size_t size, + unsigned long vm_flags, + pgprot_t prot, const void *caller) +{ + int i; + struct page **pages; + struct vm_struct *area; + + pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL); + if (!pages) + return NULL; + + for (i = 0; i < (size >> PAGE_SHIFT); i++) + pages[i] = nth_page(page, i); + + area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller); + + kfree(pages); + + if (!area) + return NULL; + return area->addr; +} + +/* + * Unmaps a range previously mapped by dma_common_*_remap + */ +void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags) +{ + struct vm_struct *area = find_vm_area(cpu_addr); + + if (!area || (area->flags & vm_flags) != vm_flags) { + WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); + return; + } + + unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size)); + vunmap(cpu_addr); +} -- cgit v1.2.1 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 --- kernel/dma/Kconfig | 5 ++ kernel/dma/remap.c | 158 ++++++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 162 insertions(+), 1 deletion(-) (limited to 'kernel/dma') 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 v1.2.1 From bfd56cd605219d90b210a5377fca31a644efe95c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 4 Nov 2018 17:38:39 +0100 Subject: dma-mapping: support highmem in the generic remap allocator By using __dma_direct_alloc_pages we can deal entirely with struct page instead of having to derive a kernel virtual address. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- kernel/dma/remap.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index b32bb08f96ae..dcc82dd668f8 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -196,7 +196,7 @@ 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; + void *ret; size = PAGE_ALIGN(size); @@ -208,10 +208,9 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, return ret; } - kaddr = dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); - if (!kaddr) + page = __dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); + if (!page) return NULL; - page = virt_to_page(kaddr); /* remove any dirty cache lines on the kernel alias */ arch_dma_prep_coherent(page, size); @@ -221,7 +220,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs), __builtin_return_address(0)); if (!ret) - dma_direct_free_pages(dev, size, kaddr, *dma_handle, attrs); + __dma_direct_free_pages(dev, size, page); return ret; } @@ -229,10 +228,11 @@ 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)); + phys_addr_t phys = dma_to_phys(dev, dma_handle); + struct page *page = pfn_to_page(__phys_to_pfn(phys)); vunmap(vaddr); - dma_direct_free_pages(dev, size, kaddr, dma_handle, attrs); + __dma_direct_free_pages(dev, size, page); } } -- cgit v1.2.1 From e440e26a0251b054243b3db6356f3869a9f9c2d1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 4 Nov 2018 17:51:50 +0100 Subject: dma-remap: support DMA_ATTR_NO_KERNEL_MAPPING Do not waste vmalloc space on allocations that do not require a mapping into the kernel address space. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- kernel/dma/remap.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index dcc82dd668f8..68a64e3ff6a1 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -200,7 +200,8 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, size = PAGE_ALIGN(size); - if (!gfpflags_allow_blocking(flags)) { + if (!gfpflags_allow_blocking(flags) && + !(attrs & DMA_ATTR_NO_KERNEL_MAPPING)) { ret = dma_alloc_from_pool(size, &page, flags); if (!ret) return NULL; @@ -215,6 +216,9 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, /* remove any dirty cache lines on the kernel alias */ arch_dma_prep_coherent(page, size); + if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) + return page; /* opaque cookie */ + /* create a coherent mapping */ ret = dma_common_contiguous_remap(page, size, VM_USERMAP, arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs), @@ -227,7 +231,10 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, 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))) { + if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) { + /* vaddr is a struct page cookie, not a kernel address */ + __dma_direct_free_pages(dev, size, vaddr); + } else if (!dma_free_from_pool(vaddr, PAGE_ALIGN(size))) { phys_addr_t phys = dma_to_phys(dev, dma_handle); struct page *page = pfn_to_page(__phys_to_pfn(phys)); -- cgit v1.2.1 From a1da439cc0d929891f0f7372c9e03530c809068c Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 5 Dec 2018 11:14:01 +0100 Subject: dma-mapping: fix lack of DMA address assignment in generic remap allocator Commit bfd56cd60521 ("dma-mapping: support highmem in the generic remap allocator") replaced dma_direct_alloc_pages() with __dma_direct_alloc_pages(), which doesn't set dma_handle and zero allocated memory. Fix it by doing this directly in the caller function. Fixes: bfd56cd60521 ("dma-mapping: support highmem in the generic remap allocator") Signed-off-by: Marek Szyprowski Tested-by: Thierry Reding Signed-off-by: Christoph Hellwig --- kernel/dma/remap.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/dma') diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index 68a64e3ff6a1..8a44317cfc1a 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -223,8 +223,14 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, ret = dma_common_contiguous_remap(page, size, VM_USERMAP, arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs), __builtin_return_address(0)); - if (!ret) + if (!ret) { __dma_direct_free_pages(dev, size, page); + return ret; + } + + *dma_handle = phys_to_dma(dev, page_to_phys(page)); + memset(ret, 0, size); + return ret; } -- cgit v1.2.1 From b0cbeae4944924640bf550b75487729a20204c14 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Nov 2018 18:52:35 +0100 Subject: dma-direct: remove the mapping_error dma_map_ops method The dma-direct code already returns (~(dma_addr_t)0x0) on mapping failures, so we can switch over to returning DMA_MAPPING_ERROR and let the core dma-mapping code handle the rest. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- kernel/dma/direct.c | 8 +------- kernel/dma/swiotlb.c | 11 +++++------ 2 files changed, 6 insertions(+), 13 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index c49849bcced6..308f88a750c8 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -289,7 +289,7 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, dma_addr_t dma_addr = phys_to_dma(dev, phys); if (!check_addr(dev, dma_addr, size, __func__)) - return DIRECT_MAPPING_ERROR; + return DMA_MAPPING_ERROR; if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) dma_direct_sync_single_for_device(dev, dma_addr, size, dir); @@ -336,11 +336,6 @@ int dma_direct_supported(struct device *dev, u64 mask) return mask >= phys_to_dma(dev, min_mask); } -int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return dma_addr == DIRECT_MAPPING_ERROR; -} - const struct dma_map_ops dma_direct_ops = { .alloc = dma_direct_alloc, .free = dma_direct_free, @@ -359,7 +354,6 @@ const struct dma_map_ops dma_direct_ops = { #endif .get_required_mask = dma_direct_get_required_mask, .dma_supported = dma_direct_supported, - .mapping_error = dma_direct_mapping_error, .cache_sync = arch_dma_cache_sync, }; EXPORT_SYMBOL(dma_direct_ops); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 045930e32c0e..ff1ce81bb623 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -631,21 +631,21 @@ static dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys, if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) { dev_warn_ratelimited(dev, "Cannot do DMA to address %pa\n", phys); - return DIRECT_MAPPING_ERROR; + return DMA_MAPPING_ERROR; } /* 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 == SWIOTLB_MAP_ERROR) - return DIRECT_MAPPING_ERROR; + return DMA_MAPPING_ERROR; /* Ensure that the address returned is DMA'ble */ 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 DIRECT_MAPPING_ERROR; + return DMA_MAPPING_ERROR; } return dma_addr; @@ -680,7 +680,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, if (!dev_is_dma_coherent(dev) && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0 && - dev_addr != DIRECT_MAPPING_ERROR) + dev_addr != DMA_MAPPING_ERROR) arch_sync_dma_for_device(dev, phys, size, dir); return dev_addr; @@ -789,7 +789,7 @@ swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems, 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 == DIRECT_MAPPING_ERROR) + if (sg->dma_address == DMA_MAPPING_ERROR) goto out_error; sg_dma_len(sg) = sg->length; } @@ -869,7 +869,6 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask) } const struct dma_map_ops swiotlb_dma_ops = { - .mapping_error = dma_direct_mapping_error, .alloc = dma_direct_alloc, .free = dma_direct_free, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, -- cgit v1.2.1 From 9f191555ba4ba8fc82e589670e46a7f79b72a157 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 10 Dec 2018 14:00:28 +0000 Subject: dma-debug: Expose nr_total_entries in debugfs Expose nr_total_entries in debugfs, so that {num,min}_free_entries become even more meaningful to users interested in current/maximum utilisation. This becomes even more relevant once nr_total_entries may change at runtime beyond just the existing AMD GART debug code. Suggested-by: John Garry Signed-off-by: Robin Murphy Tested-by: Qian Cai Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel/dma') diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 231ca4628062..f6a141eb9438 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -142,6 +142,7 @@ static struct dentry *show_all_errors_dent __read_mostly; static struct dentry *show_num_errors_dent __read_mostly; static struct dentry *num_free_entries_dent __read_mostly; static struct dentry *min_free_entries_dent __read_mostly; +static struct dentry *nr_total_entries_dent __read_mostly; static struct dentry *filter_dent __read_mostly; /* per-driver filter related state */ @@ -926,6 +927,12 @@ static int dma_debug_fs_init(void) if (!min_free_entries_dent) goto out_err; + nr_total_entries_dent = debugfs_create_u32("nr_total_entries", 0444, + dma_debug_dent, + &nr_total_entries); + if (!nr_total_entries_dent) + goto out_err; + filter_dent = debugfs_create_file("driver_filter", 0644, dma_debug_dent, NULL, &filter_fops); if (!filter_dent) -- cgit v1.2.1 From f737b095c60c635db260e02fdb9f0efb9f3360c4 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 10 Dec 2018 14:00:27 +0000 Subject: dma-debug: Use pr_fmt() Use pr_fmt() to generate the "DMA-API: " prefix consistently. This results in it being added to a couple of pr_*() messages which were missing it before, and for the err_printk() calls moves it to the actual start of the message instead of somewhere in the middle. Signed-off-by: Robin Murphy Tested-by: Qian Cai Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 74 ++++++++++++++++++++++++++++-------------------------- 1 file changed, 38 insertions(+), 36 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index f6a141eb9438..29486eb9d1dc 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -17,6 +17,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#define pr_fmt(fmt) "DMA-API: " fmt + #include #include #include @@ -235,7 +237,7 @@ static bool driver_filter(struct device *dev) error_count += 1; \ if (driver_filter(dev) && \ (show_all_errors || show_num_errors > 0)) { \ - WARN(1, "%s %s: " format, \ + WARN(1, pr_fmt("%s %s: ") format, \ dev ? dev_driver_string(dev) : "NULL", \ dev ? dev_name(dev) : "NULL", ## arg); \ dump_entry_trace(entry); \ @@ -520,7 +522,7 @@ static void active_cacheline_inc_overlap(phys_addr_t cln) * prematurely. */ WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP, - "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n", + pr_fmt("exceeded %d overlapping mappings of cacheline %pa\n"), ACTIVE_CACHELINE_MAX_OVERLAP, &cln); } @@ -615,7 +617,7 @@ void debug_dma_assert_idle(struct page *page) cln = to_cacheline_number(entry); err_printk(entry->dev, entry, - "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n", + "cpu touching an active dma mapped cacheline [cln=%pa]\n", &cln); } @@ -635,7 +637,7 @@ static void add_dma_entry(struct dma_debug_entry *entry) rc = active_cacheline_insert(entry); if (rc == -ENOMEM) { - pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n"); + pr_err("cacheline tracking ENOMEM, dma-debug disabled\n"); global_disable = true; } @@ -674,7 +676,7 @@ static struct dma_debug_entry *dma_entry_alloc(void) if (list_empty(&free_entries)) { global_disable = true; spin_unlock_irqrestore(&free_entries_lock, flags); - pr_err("DMA-API: debugging out of memory - disabling\n"); + pr_err("debugging out of memory - disabling\n"); return NULL; } @@ -778,7 +780,7 @@ static int prealloc_memory(u32 num_entries) num_free_entries = num_entries; min_free_entries = num_entries; - pr_info("DMA-API: preallocated %d debug entries\n", num_entries); + pr_info("preallocated %d debug entries\n", num_entries); return 0; @@ -851,7 +853,7 @@ static ssize_t filter_write(struct file *file, const char __user *userbuf, * switched off. */ if (current_driver_name[0]) - pr_info("DMA-API: switching off dma-debug driver filter\n"); + pr_info("switching off dma-debug driver filter\n"); current_driver_name[0] = 0; current_driver = NULL; goto out_unlock; @@ -869,7 +871,7 @@ static ssize_t filter_write(struct file *file, const char __user *userbuf, current_driver_name[i] = 0; current_driver = NULL; - pr_info("DMA-API: enable driver filter for driver [%s]\n", + pr_info("enable driver filter for driver [%s]\n", current_driver_name); out_unlock: @@ -888,7 +890,7 @@ static int dma_debug_fs_init(void) { dma_debug_dent = debugfs_create_dir("dma-api", NULL); if (!dma_debug_dent) { - pr_err("DMA-API: can not create debugfs directory\n"); + pr_err("can not create debugfs directory\n"); return -ENOMEM; } @@ -980,7 +982,7 @@ static int dma_debug_device_change(struct notifier_block *nb, unsigned long acti count = device_dma_allocations(dev, &entry); if (count == 0) break; - err_printk(dev, entry, "DMA-API: device driver has pending " + err_printk(dev, entry, "device driver has pending " "DMA allocations while released from device " "[count=%d]\n" "One of leaked entries details: " @@ -1030,14 +1032,14 @@ static int dma_debug_init(void) } if (dma_debug_fs_init() != 0) { - pr_err("DMA-API: error creating debugfs entries - disabling\n"); + pr_err("error creating debugfs entries - disabling\n"); global_disable = true; return 0; } if (prealloc_memory(nr_prealloc_entries) != 0) { - pr_err("DMA-API: debugging out of memory error - disabled\n"); + pr_err("debugging out of memory error - disabled\n"); global_disable = true; return 0; @@ -1047,7 +1049,7 @@ static int dma_debug_init(void) dma_debug_initialized = true; - pr_info("DMA-API: debugging enabled by kernel config\n"); + pr_info("debugging enabled by kernel config\n"); return 0; } core_initcall(dma_debug_init); @@ -1058,7 +1060,7 @@ static __init int dma_debug_cmdline(char *str) return -EINVAL; if (strncmp(str, "off", 3) == 0) { - pr_info("DMA-API: debugging disabled on kernel command line\n"); + pr_info("debugging disabled on kernel command line\n"); global_disable = true; } @@ -1092,11 +1094,11 @@ static void check_unmap(struct dma_debug_entry *ref) if (dma_mapping_error(ref->dev, ref->dev_addr)) { err_printk(ref->dev, NULL, - "DMA-API: device driver tries to free an " + "device driver tries to free an " "invalid DMA memory address\n"); } else { err_printk(ref->dev, NULL, - "DMA-API: device driver tries to free DMA " + "device driver tries to free DMA " "memory it has not allocated [device " "address=0x%016llx] [size=%llu bytes]\n", ref->dev_addr, ref->size); @@ -1105,7 +1107,7 @@ static void check_unmap(struct dma_debug_entry *ref) } if (ref->size != entry->size) { - err_printk(ref->dev, entry, "DMA-API: device driver frees " + err_printk(ref->dev, entry, "device driver frees " "DMA memory with different size " "[device address=0x%016llx] [map size=%llu bytes] " "[unmap size=%llu bytes]\n", @@ -1113,7 +1115,7 @@ static void check_unmap(struct dma_debug_entry *ref) } if (ref->type != entry->type) { - err_printk(ref->dev, entry, "DMA-API: device driver frees " + err_printk(ref->dev, entry, "device driver frees " "DMA memory with wrong function " "[device address=0x%016llx] [size=%llu bytes] " "[mapped as %s] [unmapped as %s]\n", @@ -1121,7 +1123,7 @@ static void check_unmap(struct dma_debug_entry *ref) type2name[entry->type], type2name[ref->type]); } else if ((entry->type == dma_debug_coherent) && (phys_addr(ref) != phys_addr(entry))) { - err_printk(ref->dev, entry, "DMA-API: device driver frees " + err_printk(ref->dev, entry, "device driver frees " "DMA memory with different CPU address " "[device address=0x%016llx] [size=%llu bytes] " "[cpu alloc address=0x%016llx] " @@ -1133,7 +1135,7 @@ static void check_unmap(struct dma_debug_entry *ref) if (ref->sg_call_ents && ref->type == dma_debug_sg && ref->sg_call_ents != entry->sg_call_ents) { - err_printk(ref->dev, entry, "DMA-API: device driver frees " + err_printk(ref->dev, entry, "device driver frees " "DMA sg list with different entry count " "[map count=%d] [unmap count=%d]\n", entry->sg_call_ents, ref->sg_call_ents); @@ -1144,7 +1146,7 @@ static void check_unmap(struct dma_debug_entry *ref) * DMA API don't handle this properly, so check for it here */ if (ref->direction != entry->direction) { - err_printk(ref->dev, entry, "DMA-API: device driver frees " + err_printk(ref->dev, entry, "device driver frees " "DMA memory with different direction " "[device address=0x%016llx] [size=%llu bytes] " "[mapped with %s] [unmapped with %s]\n", @@ -1160,7 +1162,7 @@ static void check_unmap(struct dma_debug_entry *ref) */ if (entry->map_err_type == MAP_ERR_NOT_CHECKED) { err_printk(ref->dev, entry, - "DMA-API: device driver failed to check map error" + "device driver failed to check map error" "[device address=0x%016llx] [size=%llu bytes] " "[mapped as %s]", ref->dev_addr, ref->size, @@ -1185,7 +1187,7 @@ static void check_for_stack(struct device *dev, return; addr = page_address(page) + offset; if (object_is_on_stack(addr)) - err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [addr=%p]\n", addr); + err_printk(dev, NULL, "device driver maps memory from stack [addr=%p]\n", addr); } else { /* Stack is vmalloced. */ int i; @@ -1195,7 +1197,7 @@ static void check_for_stack(struct device *dev, continue; addr = (u8 *)current->stack + i * PAGE_SIZE + offset; - err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [probable addr=%p]\n", addr); + err_printk(dev, NULL, "device driver maps memory from stack [probable addr=%p]\n", addr); break; } } @@ -1215,7 +1217,7 @@ static void check_for_illegal_area(struct device *dev, void *addr, unsigned long { if (overlap(addr, len, _stext, _etext) || overlap(addr, len, __start_rodata, __end_rodata)) - err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len); + err_printk(dev, NULL, "device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len); } static void check_sync(struct device *dev, @@ -1231,7 +1233,7 @@ static void check_sync(struct device *dev, entry = bucket_find_contain(&bucket, ref, &flags); if (!entry) { - err_printk(dev, NULL, "DMA-API: device driver tries " + err_printk(dev, NULL, "device driver tries " "to sync DMA memory it has not allocated " "[device address=0x%016llx] [size=%llu bytes]\n", (unsigned long long)ref->dev_addr, ref->size); @@ -1239,7 +1241,7 @@ static void check_sync(struct device *dev, } if (ref->size > entry->size) { - err_printk(dev, entry, "DMA-API: device driver syncs" + err_printk(dev, entry, "device driver syncs" " DMA memory outside allocated range " "[device address=0x%016llx] " "[allocation size=%llu bytes] " @@ -1252,7 +1254,7 @@ static void check_sync(struct device *dev, goto out; if (ref->direction != entry->direction) { - err_printk(dev, entry, "DMA-API: device driver syncs " + err_printk(dev, entry, "device driver syncs " "DMA memory with different direction " "[device address=0x%016llx] [size=%llu bytes] " "[mapped with %s] [synced with %s]\n", @@ -1263,7 +1265,7 @@ static void check_sync(struct device *dev, if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) && !(ref->direction == DMA_TO_DEVICE)) - err_printk(dev, entry, "DMA-API: device driver syncs " + err_printk(dev, entry, "device driver syncs " "device read-only DMA memory for cpu " "[device address=0x%016llx] [size=%llu bytes] " "[mapped with %s] [synced with %s]\n", @@ -1273,7 +1275,7 @@ static void check_sync(struct device *dev, if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) && !(ref->direction == DMA_FROM_DEVICE)) - err_printk(dev, entry, "DMA-API: device driver syncs " + err_printk(dev, entry, "device driver syncs " "device write-only DMA memory to device " "[device address=0x%016llx] [size=%llu bytes] " "[mapped with %s] [synced with %s]\n", @@ -1283,7 +1285,7 @@ static void check_sync(struct device *dev, if (ref->sg_call_ents && ref->type == dma_debug_sg && ref->sg_call_ents != entry->sg_call_ents) { - err_printk(ref->dev, entry, "DMA-API: device driver syncs " + err_printk(ref->dev, entry, "device driver syncs " "DMA sg list with different entry count " "[map count=%d] [sync count=%d]\n", entry->sg_call_ents, ref->sg_call_ents); @@ -1304,7 +1306,7 @@ static void check_sg_segment(struct device *dev, struct scatterlist *sg) * whoever generated the list forgot to check them. */ if (sg->length > max_seg) - err_printk(dev, NULL, "DMA-API: mapping sg segment longer than device claims to support [len=%u] [max=%u]\n", + err_printk(dev, NULL, "mapping sg segment longer than device claims to support [len=%u] [max=%u]\n", sg->length, max_seg); /* * In some cases this could potentially be the DMA API @@ -1314,7 +1316,7 @@ static void check_sg_segment(struct device *dev, struct scatterlist *sg) start = sg_dma_address(sg); end = start + sg_dma_len(sg) - 1; if ((start ^ end) & ~boundary) - err_printk(dev, NULL, "DMA-API: mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n", + err_printk(dev, NULL, "mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n", start, end, boundary); #endif } @@ -1326,11 +1328,11 @@ void debug_dma_map_single(struct device *dev, const void *addr, return; if (!virt_addr_valid(addr)) - err_printk(dev, NULL, "DMA-API: device driver maps memory from invalid area [addr=%p] [len=%lu]\n", + err_printk(dev, NULL, "device driver maps memory from invalid area [addr=%p] [len=%lu]\n", addr, len); if (is_vmalloc_addr(addr)) - err_printk(dev, NULL, "DMA-API: device driver maps memory from vmalloc area [addr=%p] [len=%lu]\n", + err_printk(dev, NULL, "device driver maps memory from vmalloc area [addr=%p] [len=%lu]\n", addr, len); } EXPORT_SYMBOL(debug_dma_map_single); @@ -1787,7 +1789,7 @@ static int __init dma_debug_driver_setup(char *str) } if (current_driver_name[0]) - pr_info("DMA-API: enable driver filter for driver [%s]\n", + pr_info("enable driver filter for driver [%s]\n", current_driver_name); -- cgit v1.2.1 From 2b9d9ac02b9d8d32c515c82bb17401c429f160ab Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 10 Dec 2018 14:00:29 +0000 Subject: dma-debug: Dynamically expand the dma_debug_entry pool Certain drivers such as large multi-queue network adapters can use pools of mapped DMA buffers larger than the default dma_debug_entry pool of 65536 entries, with the result that merely probing such a device can cause DMA debug to disable itself during boot unless explicitly given an appropriate "dma_debug_entries=..." option. Developers trying to debug some other driver on such a system may not be immediately aware of this, and at worst it can hide bugs if they fail to realise that dma-debug has already disabled itself unexpectedly by the time their code of interest gets to run. Even once they do realise, it can be a bit of a pain to emprirically determine a suitable number of preallocated entries to configure, short of massively over-allocating. There's really no need for such a static limit, though, since we can quite easily expand the pool at runtime in those rare cases that the preallocated entries are insufficient, which is arguably the least surprising and most useful behaviour. To that end, refactor the prealloc_memory() logic a little bit to generalise it for runtime reallocations as well. Signed-off-by: Robin Murphy Tested-by: Qian Cai Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 79 ++++++++++++++++++++++++++++-------------------------- 1 file changed, 41 insertions(+), 38 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 29486eb9d1dc..ef7c90b7a346 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -47,6 +47,8 @@ #ifndef PREALLOC_DMA_DEBUG_ENTRIES #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) #endif +/* If the pool runs out, add this many new entries at once */ +#define DMA_DEBUG_DYNAMIC_ENTRIES 256 enum { dma_debug_single, @@ -646,6 +648,34 @@ static void add_dma_entry(struct dma_debug_entry *entry) */ } +static int dma_debug_create_entries(u32 num_entries, gfp_t gfp) +{ + struct dma_debug_entry *entry, *next_entry; + int i; + + for (i = 0; i < num_entries; ++i) { + entry = kzalloc(sizeof(*entry), gfp); + if (!entry) + goto out_err; + + list_add_tail(&entry->list, &free_entries); + } + + num_free_entries += num_entries; + nr_total_entries += num_entries; + + return 0; + +out_err: + + list_for_each_entry_safe(entry, next_entry, &free_entries, list) { + list_del(&entry->list); + kfree(entry); + } + + return -ENOMEM; +} + static struct dma_debug_entry *__dma_entry_alloc(void) { struct dma_debug_entry *entry; @@ -672,12 +702,14 @@ static struct dma_debug_entry *dma_entry_alloc(void) unsigned long flags; spin_lock_irqsave(&free_entries_lock, flags); - - if (list_empty(&free_entries)) { - global_disable = true; - spin_unlock_irqrestore(&free_entries_lock, flags); - pr_err("debugging out of memory - disabling\n"); - return NULL; + if (num_free_entries == 0) { + if (dma_debug_create_entries(DMA_DEBUG_DYNAMIC_ENTRIES, + GFP_ATOMIC)) { + global_disable = true; + spin_unlock_irqrestore(&free_entries_lock, flags); + pr_err("debugging out of memory - disabling\n"); + return NULL; + } } entry = __dma_entry_alloc(); @@ -764,36 +796,6 @@ int dma_debug_resize_entries(u32 num_entries) * 2. Preallocate a given number of dma_debug_entry structs */ -static int prealloc_memory(u32 num_entries) -{ - struct dma_debug_entry *entry, *next_entry; - int i; - - for (i = 0; i < num_entries; ++i) { - entry = kzalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - goto out_err; - - list_add_tail(&entry->list, &free_entries); - } - - num_free_entries = num_entries; - min_free_entries = num_entries; - - pr_info("preallocated %d debug entries\n", num_entries); - - return 0; - -out_err: - - list_for_each_entry_safe(entry, next_entry, &free_entries, list) { - list_del(&entry->list); - kfree(entry); - } - - return -ENOMEM; -} - static ssize_t filter_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -1038,14 +1040,15 @@ static int dma_debug_init(void) return 0; } - if (prealloc_memory(nr_prealloc_entries) != 0) { + if (dma_debug_create_entries(nr_prealloc_entries, GFP_KERNEL) != 0) { pr_err("debugging out of memory error - disabled\n"); global_disable = true; return 0; } - nr_total_entries = num_free_entries; + min_free_entries = num_free_entries; + pr_info("preallocated %d debug entries\n", nr_total_entries); dma_debug_initialized = true; -- cgit v1.2.1 From ceb51173b2b5bd7af0d99079f6bbacdcfc58fe08 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 10 Dec 2018 14:00:30 +0000 Subject: dma-debug: Make leak-like behaviour apparent Now that we can dynamically allocate DMA debug entries to cope with drivers maintaining excessively large numbers of live mappings, a driver which *does* actually have a bug leaking mappings (and is not unloaded) will no longer trigger the "DMA-API: debugging out of memory - disabling" message until it gets to actual kernel OOM conditions, which means it could go unnoticed for a while. To that end, let's inform the user each time the pool has grown to a multiple of its initial size, which should make it apparent that they either have a leak or might want to increase the preallocation size. Signed-off-by: Robin Murphy Tested-by: Qian Cai Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'kernel/dma') diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index ef7c90b7a346..912c23f4c177 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -691,6 +691,18 @@ static struct dma_debug_entry *__dma_entry_alloc(void) return entry; } +void __dma_entry_alloc_check_leak(void) +{ + u32 tmp = nr_total_entries % nr_prealloc_entries; + + /* Shout each time we tick over some multiple of the initial pool */ + if (tmp < DMA_DEBUG_DYNAMIC_ENTRIES) { + pr_info("dma_debug_entry pool grown to %u (%u00%%)\n", + nr_total_entries, + (nr_total_entries / nr_prealloc_entries)); + } +} + /* struct dma_entry allocator * * The next two functions implement the allocator for @@ -710,6 +722,7 @@ static struct dma_debug_entry *dma_entry_alloc(void) pr_err("debugging out of memory - disabling\n"); return NULL; } + __dma_entry_alloc_check_leak(); } entry = __dma_entry_alloc(); -- cgit v1.2.1 From 0cb0e25e421436a83ee39857923e4213b983e463 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 10 Dec 2018 14:00:32 +0000 Subject: dma/debug: Remove dma_debug_resize_entries() With the only caller now gone, we can clean up this part of dma-debug's exposed internals and make way to tweak the allocation behaviour. Signed-off-by: Robin Murphy Tested-by: Qian Cai Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 46 ---------------------------------------------- 1 file changed, 46 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 912c23f4c177..36a42874b05f 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -755,52 +755,6 @@ static void dma_entry_free(struct dma_debug_entry *entry) spin_unlock_irqrestore(&free_entries_lock, flags); } -int dma_debug_resize_entries(u32 num_entries) -{ - int i, delta, ret = 0; - unsigned long flags; - struct dma_debug_entry *entry; - LIST_HEAD(tmp); - - spin_lock_irqsave(&free_entries_lock, flags); - - if (nr_total_entries < num_entries) { - delta = num_entries - nr_total_entries; - - spin_unlock_irqrestore(&free_entries_lock, flags); - - for (i = 0; i < delta; i++) { - entry = kzalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - break; - - list_add_tail(&entry->list, &tmp); - } - - spin_lock_irqsave(&free_entries_lock, flags); - - list_splice(&tmp, &free_entries); - nr_total_entries += i; - num_free_entries += i; - } else { - delta = nr_total_entries - num_entries; - - for (i = 0; i < delta && !list_empty(&free_entries); i++) { - entry = __dma_entry_alloc(); - kfree(entry); - } - - nr_total_entries -= i; - } - - if (nr_total_entries != num_entries) - ret = 1; - - spin_unlock_irqrestore(&free_entries_lock, flags); - - return ret; -} - /* * DMA-API debugging init code * -- cgit v1.2.1 From ad78dee0b630527bdfed809d1f5ed95c601886ae Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 10 Dec 2018 14:00:33 +0000 Subject: dma-debug: Batch dma_debug_entry allocation DMA debug entries are one of those things which aren't that useful individually - we will always want some larger quantity of them - and which we don't really need to manage the exact number of - we only care about having 'enough'. In that regard, the current behaviour of creating them one-by-one leads to a lot of unwarranted function call overhead and memory wasted on alignment padding. Now that we don't have to worry about freeing anything via dma_debug_resize_entries(), we can optimise the allocation behaviour by grabbing whole pages at once, which will save considerably on the aforementioned overheads, and probably offer a little more cache/TLB locality benefit for traversing the lists under normal operation. This should also give even less reason for an architecture-level override of the preallocation size, so make the definition unconditional - if there is still any desire to change the compile-time value for some platforms it would be better off as a Kconfig option anyway. Since freeing a whole page of entries at once becomes enough of a challenge that it's not really worth complicating dma_debug_init(), we may as well tweak the preallocation behaviour such that as long as we manage to allocate *some* pages, we can leave debugging enabled on a best-effort basis rather than otherwise wasting them. Signed-off-by: Robin Murphy Tested-by: Qian Cai Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 50 +++++++++++++++++++++----------------------------- 1 file changed, 21 insertions(+), 29 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 36a42874b05f..20ab0f6c1b70 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -43,12 +43,9 @@ #define HASH_FN_SHIFT 13 #define HASH_FN_MASK (HASH_SIZE - 1) -/* allow architectures to override this if absolutely required */ -#ifndef PREALLOC_DMA_DEBUG_ENTRIES #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) -#endif /* If the pool runs out, add this many new entries at once */ -#define DMA_DEBUG_DYNAMIC_ENTRIES 256 +#define DMA_DEBUG_DYNAMIC_ENTRIES (PAGE_SIZE / sizeof(struct dma_debug_entry)) enum { dma_debug_single, @@ -648,32 +645,22 @@ static void add_dma_entry(struct dma_debug_entry *entry) */ } -static int dma_debug_create_entries(u32 num_entries, gfp_t gfp) +static int dma_debug_create_entries(gfp_t gfp) { - struct dma_debug_entry *entry, *next_entry; + struct dma_debug_entry *entry; int i; - for (i = 0; i < num_entries; ++i) { - entry = kzalloc(sizeof(*entry), gfp); - if (!entry) - goto out_err; + entry = (void *)get_zeroed_page(gfp); + if (!entry) + return -ENOMEM; - list_add_tail(&entry->list, &free_entries); - } + for (i = 0; i < DMA_DEBUG_DYNAMIC_ENTRIES; i++) + list_add_tail(&entry[i].list, &free_entries); - num_free_entries += num_entries; - nr_total_entries += num_entries; + num_free_entries += DMA_DEBUG_DYNAMIC_ENTRIES; + nr_total_entries += DMA_DEBUG_DYNAMIC_ENTRIES; return 0; - -out_err: - - list_for_each_entry_safe(entry, next_entry, &free_entries, list) { - list_del(&entry->list); - kfree(entry); - } - - return -ENOMEM; } static struct dma_debug_entry *__dma_entry_alloc(void) @@ -715,8 +702,7 @@ static struct dma_debug_entry *dma_entry_alloc(void) spin_lock_irqsave(&free_entries_lock, flags); if (num_free_entries == 0) { - if (dma_debug_create_entries(DMA_DEBUG_DYNAMIC_ENTRIES, - GFP_ATOMIC)) { + if (dma_debug_create_entries(GFP_ATOMIC)) { global_disable = true; spin_unlock_irqrestore(&free_entries_lock, flags); pr_err("debugging out of memory - disabling\n"); @@ -987,7 +973,7 @@ void dma_debug_add_bus(struct bus_type *bus) static int dma_debug_init(void) { - int i; + int i, nr_pages; /* Do not use dma_debug_initialized here, since we really want to be * called to set dma_debug_initialized @@ -1007,15 +993,21 @@ static int dma_debug_init(void) return 0; } - if (dma_debug_create_entries(nr_prealloc_entries, GFP_KERNEL) != 0) { + nr_pages = DIV_ROUND_UP(nr_prealloc_entries, DMA_DEBUG_DYNAMIC_ENTRIES); + for (i = 0; i < nr_pages; ++i) + dma_debug_create_entries(GFP_KERNEL); + if (num_free_entries >= nr_prealloc_entries) { + pr_info("preallocated %d debug entries\n", nr_total_entries); + } else if (num_free_entries > 0) { + pr_warn("%d debug entries requested but only %d allocated\n", + nr_prealloc_entries, nr_total_entries); + } else { pr_err("debugging out of memory error - disabled\n"); global_disable = true; return 0; } - min_free_entries = num_free_entries; - pr_info("preallocated %d debug entries\n", nr_total_entries); dma_debug_initialized = true; -- cgit v1.2.1 From 20b105feda8d42360bd690b8fdf6b2f00ba4a993 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 4 Dec 2018 08:04:31 -0800 Subject: dma-mapping: remove a pointless memset in dma_atomic_pool_init We already zero the memory after allocating it from the pool that this function fills, and having the memset here in this form means we can't support CMA highmem allocations. Signed-off-by: Christoph Hellwig Reported-by: Russell King - ARM Linux --- kernel/dma/remap.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/dma') diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index 8a44317cfc1a..18cc09fc27b9 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -121,7 +121,6 @@ int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot) 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); -- cgit v1.2.1 From 8d59b5f2a44611d7327a2a14b36090d692186f60 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 3 Dec 2018 14:58:59 +0100 Subject: dma-mapping: simplify the dma_sync_single_range_for_{cpu,device} implementation We can just call the regular calls after adding offset the the address instead of reimplementing them. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- kernel/dma/debug.c | 42 ------------------------------------------ 1 file changed, 42 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 20ab0f6c1b70..164706da2a73 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -1633,48 +1633,6 @@ void debug_dma_sync_single_for_device(struct device *dev, } EXPORT_SYMBOL(debug_dma_sync_single_for_device); -void debug_dma_sync_single_range_for_cpu(struct device *dev, - dma_addr_t dma_handle, - unsigned long offset, size_t size, - int direction) -{ - struct dma_debug_entry ref; - - if (unlikely(dma_debug_disabled())) - return; - - ref.type = dma_debug_single; - ref.dev = dev; - ref.dev_addr = dma_handle; - ref.size = offset + size; - ref.direction = direction; - ref.sg_call_ents = 0; - - check_sync(dev, &ref, true); -} -EXPORT_SYMBOL(debug_dma_sync_single_range_for_cpu); - -void debug_dma_sync_single_range_for_device(struct device *dev, - dma_addr_t dma_handle, - unsigned long offset, - size_t size, int direction) -{ - struct dma_debug_entry ref; - - if (unlikely(dma_debug_disabled())) - return; - - ref.type = dma_debug_single; - ref.dev = dev; - ref.dev_addr = dma_handle; - ref.size = offset + size; - ref.direction = direction; - ref.sg_call_ents = 0; - - check_sync(dev, &ref, false); -} -EXPORT_SYMBOL(debug_dma_sync_single_range_for_device); - void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, int direction) { -- cgit v1.2.1 From 05887cb610a54bf568de7f0bc07c4a64e45ac6f9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Dec 2018 12:25:54 -0800 Subject: dma-mapping: move dma_get_required_mask to kernel/dma dma_get_required_mask should really be with the rest of the DMA mapping implementation instead of in drivers/base as a lone outlier. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- kernel/dma/mapping.c | 34 +++++++++++++++++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-) (limited to 'kernel/dma') diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index dfbc3deb95cd..dfe29d18dba1 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -5,7 +5,7 @@ * Copyright (c) 2006 SUSE Linux Products GmbH * Copyright (c) 2006 Tejun Heo */ - +#include /* for max_pfn */ #include #include #include @@ -262,3 +262,35 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, #endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */ } EXPORT_SYMBOL(dma_common_mmap); + +#ifndef ARCH_HAS_DMA_GET_REQUIRED_MASK +static u64 dma_default_get_required_mask(struct device *dev) +{ + u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT); + u32 high_totalram = ((max_pfn - 1) >> (32 - PAGE_SHIFT)); + u64 mask; + + if (!high_totalram) { + /* convert to mask just covering totalram */ + low_totalram = (1 << (fls(low_totalram) - 1)); + low_totalram += low_totalram - 1; + mask = low_totalram; + } else { + high_totalram = (1 << (fls(high_totalram) - 1)); + high_totalram += high_totalram - 1; + mask = (((u64)high_totalram) << 32) + 0xffffffff; + } + return mask; +} + +u64 dma_get_required_mask(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (ops->get_required_mask) + return ops->get_required_mask(dev); + return dma_default_get_required_mask(dev); +} +EXPORT_SYMBOL_GPL(dma_get_required_mask); +#endif + -- cgit v1.2.1 From 7249c1a52df9967cd23550f3dc24fb6ca43cdc6a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Dec 2018 12:43:30 -0800 Subject: dma-mapping: move various slow path functions out of line There is no need to have all setup and coherent allocation / freeing routines inline. Move them out of line to keep the implemeation nicely encapsulated and save some kernel text size. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- kernel/dma/mapping.c | 140 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 138 insertions(+), 2 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index dfe29d18dba1..176ae3e08916 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -223,7 +223,20 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); return ret; } -EXPORT_SYMBOL(dma_common_get_sgtable); + +int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + BUG_ON(!ops); + if (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, + attrs); +} +EXPORT_SYMBOL(dma_get_sgtable_attrs); /* * Create userspace mapping for the DMA-coherent memory. @@ -261,7 +274,31 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, return -ENXIO; #endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */ } -EXPORT_SYMBOL(dma_common_mmap); + +/** + * dma_mmap_attrs - map a coherent DMA allocation into user space + * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices + * @vma: vm_area_struct describing requested user mapping + * @cpu_addr: kernel CPU-view address returned from dma_alloc_attrs + * @dma_addr: device-view address returned from dma_alloc_attrs + * @size: size of memory originally requested in dma_alloc_attrs + * @attrs: attributes of mapping properties requested in dma_alloc_attrs + * + * Map a coherent DMA buffer previously allocated by dma_alloc_attrs into user + * space. The coherent DMA buffer must not be freed by the driver until the + * user space mapping has been released. + */ +int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + BUG_ON(!ops); + if (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); +} +EXPORT_SYMBOL(dma_mmap_attrs); #ifndef ARCH_HAS_DMA_GET_REQUIRED_MASK static u64 dma_default_get_required_mask(struct device *dev) @@ -294,3 +331,102 @@ u64 dma_get_required_mask(struct device *dev) EXPORT_SYMBOL_GPL(dma_get_required_mask); #endif +#ifndef arch_dma_alloc_attrs +#define arch_dma_alloc_attrs(dev) (true) +#endif + +void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t flag, unsigned long attrs) +{ + 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)) + return cpu_addr; + + /* let the implementation decide on the zone to allocate from: */ + flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM); + + if (!arch_dma_alloc_attrs(&dev)) + return NULL; + if (!ops->alloc) + 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; +} +EXPORT_SYMBOL(dma_alloc_attrs); + +void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle, unsigned long attrs) +{ + 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; + /* + * On non-coherent platforms which implement DMA-coherent buffers via + * non-cacheable remaps, ops->free() may call vunmap(). Thus getting + * this far in IRQ context is a) at risk of a BUG_ON() or trying to + * sleep on some machines, and b) an indication that the driver is + * probably misusing the coherent API anyway. + */ + WARN_ON(irqs_disabled()); + + if (!ops->free || !cpu_addr) + return; + + debug_dma_free_coherent(dev, size, cpu_addr, dma_handle); + ops->free(dev, size, cpu_addr, dma_handle, attrs); +} +EXPORT_SYMBOL(dma_free_attrs); + +static inline void dma_check_mask(struct device *dev, u64 mask) +{ + if (sme_active() && (mask < (((u64)sme_get_me_mask() << 1) - 1))) + dev_warn(dev, "SME is active, device will require DMA bounce buffers\n"); +} + +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) + return 1; + return ops->dma_supported(dev, mask); +} +EXPORT_SYMBOL(dma_supported); + +#ifndef HAVE_ARCH_DMA_SET_MASK +int dma_set_mask(struct device *dev, u64 mask) +{ + if (!dev->dma_mask || !dma_supported(dev, mask)) + return -EIO; + + dma_check_mask(dev, mask); + *dev->dma_mask = mask; + return 0; +} +EXPORT_SYMBOL(dma_set_mask); +#endif + +#ifndef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK +int dma_set_coherent_mask(struct device *dev, u64 mask) +{ + if (!dma_supported(dev, mask)) + return -EIO; + + dma_check_mask(dev, mask); + dev->coherent_dma_mask = mask; + return 0; +} +EXPORT_SYMBOL(dma_set_coherent_mask); +#endif -- cgit v1.2.1 From 8ddbe5943c0b1259b5ddb6dc1729863433fc256c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Dec 2018 12:47:50 -0800 Subject: dma-mapping: move dma_cache_sync out of line This isn't exactly a slow path routine, but it is not super critical either, and moving it out of line will help to keep the include chain clean for the following DMA indirection bypass work. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- kernel/dma/mapping.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'kernel/dma') diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 176ae3e08916..0b18cfbdde95 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -430,3 +430,14 @@ int dma_set_coherent_mask(struct device *dev, u64 mask) } EXPORT_SYMBOL(dma_set_coherent_mask); #endif + +void dma_cache_sync(struct device *dev, void *vaddr, size_t size, + enum dma_data_direction dir) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (ops->cache_sync) + ops->cache_sync(dev, vaddr, size, dir); +} +EXPORT_SYMBOL(dma_cache_sync); -- cgit v1.2.1 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 --- kernel/dma/Kconfig | 7 ------- kernel/dma/Makefile | 3 +-- 2 files changed, 1 insertion(+), 9 deletions(-) (limited to 'kernel/dma') 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-$(CONFIG_SWIOTLB) += swiotlb.o -- cgit v1.2.1 From 90ac706e98fcb24fb0b0a259558987f33cc2f0f6 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 6 Dec 2018 13:14:44 -0800 Subject: dma-mapping: factor out dummy DMA ops The dummy DMA ops are currently used by arm64 for any device which has an invalid ACPI description and is thus barred from using DMA due to not knowing whether is is cache-coherent or not. Factor these out into general dma-mapping code so that they can be referenced from other common code paths. In the process, we can prune all the optional callbacks which just do the same thing as the default behaviour, and fill in .map_resource for completeness. Signed-off-by: Robin Murphy [hch: moved to a separate source file] Reviewed-by: Rafael J. Wysocki Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck Signed-off-by: Christoph Hellwig --- kernel/dma/Makefile | 2 +- kernel/dma/dummy.c | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 1 deletion(-) create mode 100644 kernel/dma/dummy.c (limited to 'kernel/dma') diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile index a626f643cd63..72ff6e46aa86 100644 --- a/kernel/dma/Makefile +++ b/kernel/dma/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(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 v1.2.1 From b907e20508d02462a50c2841da0a5e3883fdab39 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 3 Dec 2018 11:42:52 +0100 Subject: swiotlb: remove SWIOTLB_MAP_ERROR We can use DMA_MAPPING_ERROR instead, which already maps to the same value. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- kernel/dma/swiotlb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index ff1ce81bb623..19ba8e473d71 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -526,7 +526,7 @@ not_found: spin_unlock_irqrestore(&io_tlb_lock, flags); if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes)\n", size); - return SWIOTLB_MAP_ERROR; + return DMA_MAPPING_ERROR; found: spin_unlock_irqrestore(&io_tlb_lock, flags); @@ -637,7 +637,7 @@ static dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys, /* 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 == SWIOTLB_MAP_ERROR) + if (*phys == DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; /* Ensure that the address returned is DMA'ble */ -- cgit v1.2.1 From 68c608345cc569bcfa1c1b2add4c00c343ecf933 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Dec 2018 07:06:04 -0800 Subject: swiotlb: remove dma_mark_clean Instead of providing a special dma_mark_clean hook just for ia64, switch ia64 to use the normal arch_sync_dma_for_cpu hooks instead. This means that we now also set the PG_arch_1 bit for pages in the swiotlb buffer, which isn't stricly needed as we will never execute code out of the swiotlb buffer, but otherwise harmless. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- kernel/dma/swiotlb.c | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 19ba8e473d71..2e126bac5d7d 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -706,21 +706,8 @@ void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) arch_sync_dma_for_cpu(hwdev, paddr, size, dir); - if (is_swiotlb_buffer(paddr)) { + if (is_swiotlb_buffer(paddr)) swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs); - return; - } - - if (dir != DMA_FROM_DEVICE) - return; - - /* - * phys_to_virt doesn't work with hihgmem page but we could - * call dma_mark_clean() with hihgmem page here. However, we - * are fine since dma_mark_clean() is null on POWERPC. We can - * make dma_mark_clean() take a physical address if necessary. - */ - dma_mark_clean(phys_to_virt(paddr), size); } /* @@ -750,9 +737,6 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_DEVICE) arch_sync_dma_for_device(hwdev, paddr, size, dir); - - if (!is_swiotlb_buffer(paddr) && dir == DMA_FROM_DEVICE) - dma_mark_clean(phys_to_virt(paddr), size); } void -- cgit v1.2.1 From 58dfd4ac022037c6a562e92fc6d2a778819b2162 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 3 Dec 2018 07:43:05 +0100 Subject: dma-direct: improve addressability error reporting Only report report a DMA addressability report once to avoid spewing the kernel log with repeated message. Also provide a stack trace to make it easy to find the actual caller that caused the problem. Last but not least move the actual check into the fast path and only leave the error reporting in a helper. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- kernel/dma/direct.c | 36 +++++++++++++++--------------------- 1 file changed, 15 insertions(+), 21 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 308f88a750c8..edb24f94ea1e 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -30,27 +30,16 @@ static inline bool force_dma_unencrypted(void) return sev_active(); } -static bool -check_addr(struct device *dev, dma_addr_t dma_addr, size_t size, - const char *caller) +static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size) { - if (unlikely(dev && !dma_capable(dev, dma_addr, size))) { - if (!dev->dma_mask) { - dev_err(dev, - "%s: call on device without dma_mask\n", - caller); - return false; - } - - if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) { - dev_err(dev, - "%s: overflow %pad+%zu of device mask %llx bus mask %llx\n", - caller, &dma_addr, size, - *dev->dma_mask, dev->bus_dma_mask); - } - return false; + if (!dev->dma_mask) { + dev_err_once(dev, "DMA map on device without dma_mask\n"); + } else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) { + dev_err_once(dev, + "overflow %pad+%zu of DMA mask %llx bus mask %llx\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_mask); } - return true; + WARN_ON_ONCE(1); } static inline dma_addr_t phys_to_dma_direct(struct device *dev, @@ -288,8 +277,10 @@ 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 (!check_addr(dev, dma_addr, size, __func__)) + if (unlikely(dev && !dma_capable(dev, dma_addr, size))) { + 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); @@ -306,8 +297,11 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, BUG_ON(!sg_page(sg)); sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg)); - if (!check_addr(dev, sg_dma_address(sg), sg->length, __func__)) + if (unlikely(dev && !dma_capable(dev, sg_dma_address(sg), + sg->length))) { + report_addr(dev, sg_dma_address(sg), sg->length); return 0; + } sg_dma_len(sg) = sg->length; } -- cgit v1.2.1 From 17ac524719f3fc88c1a90528f4789e4b4f618512 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 3 Dec 2018 11:14:09 +0100 Subject: dma-direct: use dma_direct_map_page to implement dma_direct_map_sg No need to duplicate the mapping logic. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- kernel/dma/direct.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'kernel/dma') diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index edb24f94ea1e..d45306473c90 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -217,6 +217,7 @@ static void dma_direct_sync_single_for_device(struct device *dev, arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir); } +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) static void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { @@ -229,6 +230,7 @@ static void dma_direct_sync_sg_for_device(struct device *dev, for_each_sg(sgl, sg, nents, i) 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) @@ -294,19 +296,13 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, struct scatterlist *sg; for_each_sg(sgl, sg, nents, i) { - BUG_ON(!sg_page(sg)); - - sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg)); - if (unlikely(dev && !dma_capable(dev, sg_dma_address(sg), - sg->length))) { - report_addr(dev, sg_dma_address(sg), sg->length); + 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; - } sg_dma_len(sg) = sg->length; } - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_direct_sync_sg_for_device(dev, sgl, nents, dir); return nents; } -- cgit v1.2.1 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 --- kernel/dma/direct.c | 113 ++++++++++++++++++------- kernel/dma/swiotlb.c | 232 +++------------------------------------------------ 2 files changed, 94 insertions(+), 251 deletions(-) (limited to 'kernel/dma') 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 v1.2.1 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 --- kernel/dma/direct.c | 37 ++++++++----------------------------- kernel/dma/mapping.c | 40 +++++++++++++++++++++++++--------------- 2 files changed, 33 insertions(+), 44 deletions(-) (limited to 'kernel/dma') 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 v1.2.1 From 518a2f1925c3165befbf06b75e07636549d92c1c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 14 Dec 2018 09:00:40 +0100 Subject: dma-mapping: zero memory returned from dma_alloc_* If we want to map memory from the DMA allocator to userspace it must be zeroed at allocation time to prevent stale data leaks. We already do this on most common architectures, but some architectures don't do this yet, fix them up, either by passing GFP_ZERO when we use the normal page allocator or doing a manual memset otherwise. Signed-off-by: Christoph Hellwig Acked-by: Geert Uytterhoeven [m68k] Acked-by: Sam Ravnborg [sparc] --- kernel/dma/virt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/dma') diff --git a/kernel/dma/virt.c b/kernel/dma/virt.c index 631ddec4b60a..ebe128833af7 100644 --- a/kernel/dma/virt.c +++ b/kernel/dma/virt.c @@ -13,7 +13,7 @@ static void *dma_virt_alloc(struct device *dev, size_t size, { void *ret; - ret = (void *)__get_free_pages(gfp, get_order(size)); + ret = (void *)__get_free_pages(gfp | __GFP_ZERO, get_order(size)); if (ret) *dma_handle = (uintptr_t)ret; return ret; -- cgit v1.2.1 From 8b1cce9f5832a8eda17d37a3c49fb7dd2d650f46 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 20 Dec 2018 17:35:47 +0100 Subject: dma-mapping: fix inverted logic in dma_supported The cleanup in commit 356da6d0cde3 ("dma-mapping: bypass indirect calls for dma-direct") accidentally inverted the logic in the check for the presence of a ->dma_supported() callback. Switch this back to the way it was to prevent a crash on boot. Fixes: 356da6d0cde3 ("dma-mapping: bypass indirect calls for dma-direct") Signed-off-by: Thierry Reding Signed-off-by: Christoph Hellwig --- kernel/dma/mapping.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/dma') diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index fc84c81029d9..d7c34d2d1ba5 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -406,7 +406,7 @@ int dma_supported(struct device *dev, u64 mask) if (dma_is_direct(ops)) return dma_direct_supported(dev, mask); - if (ops->dma_supported) + if (!ops->dma_supported) return 1; return ops->dma_supported(dev, mask); } -- cgit v1.2.1