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') 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 v1.2.3-59-g8ed1b 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') 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 v1.2.3-59-g8ed1b From f0edfea8ef93ed6cc5f747c46c85c8e53e0798a0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Aug 2018 10:31:08 +0200 Subject: dma-mapping: move the remap helpers to a separate file The dma remap code only makes sense for not cache coherent architectures (or possibly the corner case of highmem CMA allocations) and currently is only used by arm, arm64, csky and xtensa. Split it out into a separate file with a separate Kconfig symbol, which gets the right copyright notice given that this code was written by Laura Abbott working for Code Aurora at that point. Signed-off-by: Christoph Hellwig Acked-by: Laura Abbott Reviewed-by: Robin Murphy --- arch/arm/Kconfig | 1 + arch/arm64/Kconfig | 1 + arch/csky/Kconfig | 1 + arch/xtensa/Kconfig | 1 + kernel/dma/Kconfig | 4 +++ kernel/dma/Makefile | 2 +- kernel/dma/mapping.c | 84 ------------------------------------------------- kernel/dma/remap.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 8 files changed, 97 insertions(+), 85 deletions(-) create mode 100644 kernel/dma/remap.c (limited to 'kernel') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 91be74d8df65..3b2852df6eb3 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -30,6 +30,7 @@ config ARM select CPU_PM if (SUSPEND || CPU_IDLE) select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS select DMA_DIRECT_OPS if !MMU + select DMA_REMAP if MMU select EDAC_SUPPORT select EDAC_ATOMIC_SCRUB select GENERIC_ALLOCATOR diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 787d7850e064..5d065acb6d10 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -82,6 +82,7 @@ config ARM64 select CRC32 select DCACHE_WORD_ACCESS select DMA_DIRECT_OPS + select DMA_REMAP select EDAC_SUPPORT select FRAME_POINTER select GENERIC_ALLOCATOR diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index cb64f8dacd08..8a30e006a845 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -9,6 +9,7 @@ config CSKY select CLKSRC_OF select DMA_DIRECT_OPS select DMA_NONCOHERENT_OPS + select DMA_REMAP select IRQ_DOMAIN select HANDLE_DOMAIN_IRQ select DW_APB_TIMER_OF diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index d29b7365da8d..239bfb16c58b 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -11,6 +11,7 @@ config XTENSA select CLONE_BACKWARDS select COMMON_CLK select DMA_DIRECT_OPS + select DMA_REMAP if MMU select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS select GENERIC_IRQ_SHOW 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 v1.2.3-59-g8ed1b From 0c3b3171ceccb8830c2bb5adff1b4e9b204c1450 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 4 Nov 2018 20:29:28 +0100 Subject: dma-mapping: move the arm64 noncoherent alloc/free support to common code The arm64 codebase to implement coherent dma allocation for architectures with non-coherent DMA is a good start for a generic implementation, given that is uses the generic remap helpers, provides the atomic pool for allocations that can't sleep and still is realtively simple and well tested. Move it to kernel/dma and allow architectures to opt into it using a config symbol. Architectures just need to provide a new arch_dma_prep_coherent helper to writeback an invalidate the caches for any memory that gets remapped for uncached access. Signed-off-by: Christoph Hellwig Reviewed-by: Will Deacon Reviewed-by: Robin Murphy --- arch/arm64/Kconfig | 2 +- arch/arm64/mm/dma-mapping.c | 184 +++------------------------------------- include/linux/dma-mapping.h | 5 ++ include/linux/dma-noncoherent.h | 2 + kernel/dma/Kconfig | 5 ++ kernel/dma/remap.c | 158 +++++++++++++++++++++++++++++++++- 6 files changed, 180 insertions(+), 176 deletions(-) (limited to 'kernel') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 5d065acb6d10..2e645ea693ea 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -82,7 +82,7 @@ config ARM64 select CRC32 select DCACHE_WORD_ACCESS select DMA_DIRECT_OPS - select DMA_REMAP + select DMA_DIRECT_REMAP select EDAC_SUPPORT select FRAME_POINTER select GENERIC_ALLOCATOR diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index a3ac26284845..e2e7e5d0f94e 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -33,113 +33,6 @@ #include -static struct gen_pool *atomic_pool __ro_after_init; - -#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K -static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE; - -static int __init early_coherent_pool(char *p) -{ - atomic_pool_size = memparse(p, &p); - return 0; -} -early_param("coherent_pool", early_coherent_pool); - -static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) -{ - unsigned long val; - void *ptr = NULL; - - if (!atomic_pool) { - WARN(1, "coherent pool not initialised!\n"); - return NULL; - } - - val = gen_pool_alloc(atomic_pool, size); - if (val) { - phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val); - - *ret_page = phys_to_page(phys); - ptr = (void *)val; - memset(ptr, 0, size); - } - - return ptr; -} - -static bool __in_atomic_pool(void *start, size_t size) -{ - return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); -} - -static int __free_from_pool(void *start, size_t size) -{ - if (!__in_atomic_pool(start, size)) - return 0; - - gen_pool_free(atomic_pool, (unsigned long)start, size); - - return 1; -} - -void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t flags, unsigned long attrs) -{ - struct page *page; - void *ptr, *coherent_ptr; - pgprot_t prot = pgprot_writecombine(PAGE_KERNEL); - - size = PAGE_ALIGN(size); - - if (!gfpflags_allow_blocking(flags)) { - struct page *page = NULL; - void *addr = __alloc_from_pool(size, &page, flags); - - if (addr) - *dma_handle = phys_to_dma(dev, page_to_phys(page)); - - return addr; - } - - ptr = dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); - if (!ptr) - goto no_mem; - - /* remove any dirty cache lines on the kernel alias */ - __dma_flush_area(ptr, size); - - /* create a coherent mapping */ - page = virt_to_page(ptr); - coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP, - prot, __builtin_return_address(0)); - if (!coherent_ptr) - goto no_map; - - return coherent_ptr; - -no_map: - dma_direct_free_pages(dev, size, ptr, *dma_handle, attrs); -no_mem: - return NULL; -} - -void arch_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) -{ - if (!__free_from_pool(vaddr, PAGE_ALIGN(size))) { - void *kaddr = phys_to_virt(dma_to_phys(dev, dma_handle)); - - vunmap(vaddr); - dma_direct_free_pages(dev, size, kaddr, dma_handle, attrs); - } -} - -long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, - dma_addr_t dma_addr) -{ - return __phys_to_pfn(dma_to_phys(dev, dma_addr)); -} - pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) { @@ -160,6 +53,11 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, __dma_unmap_area(phys_to_virt(paddr), size, dir); } +void arch_dma_prep_coherent(struct page *page, size_t size) +{ + __dma_flush_area(page_address(page), size); +} + #ifdef CONFIG_IOMMU_DMA static int __swiotlb_get_sgtable_page(struct sg_table *sgt, struct page *page, size_t size) @@ -191,67 +89,6 @@ static int __swiotlb_mmap_pfn(struct vm_area_struct *vma, } #endif /* CONFIG_IOMMU_DMA */ -static int __init atomic_pool_init(void) -{ - pgprot_t prot = __pgprot(PROT_NORMAL_NC); - unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT; - struct page *page; - void *addr; - unsigned int pool_size_order = get_order(atomic_pool_size); - - if (dev_get_cma_area(NULL)) - page = dma_alloc_from_contiguous(NULL, nr_pages, - pool_size_order, false); - else - page = alloc_pages(GFP_DMA32, pool_size_order); - - if (page) { - int ret; - void *page_addr = page_address(page); - - memset(page_addr, 0, atomic_pool_size); - __dma_flush_area(page_addr, atomic_pool_size); - - atomic_pool = gen_pool_create(PAGE_SHIFT, -1); - if (!atomic_pool) - goto free_page; - - addr = dma_common_contiguous_remap(page, atomic_pool_size, - VM_USERMAP, prot, atomic_pool_init); - - if (!addr) - goto destroy_genpool; - - ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr, - page_to_phys(page), - atomic_pool_size, -1); - if (ret) - goto remove_mapping; - - gen_pool_set_algo(atomic_pool, - gen_pool_first_fit_order_align, - NULL); - - pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n", - atomic_pool_size / 1024); - return 0; - } - goto out; - -remove_mapping: - dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP); -destroy_genpool: - gen_pool_destroy(atomic_pool); - atomic_pool = NULL; -free_page: - if (!dma_release_from_contiguous(NULL, page, nr_pages)) - __free_pages(page, pool_size_order); -out: - pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n", - atomic_pool_size / 1024); - return -ENOMEM; -} - /******************************************** * The following APIs are for dummy DMA ops * ********************************************/ @@ -350,8 +187,7 @@ static int __init arm64_dma_init(void) TAINT_CPU_OUT_OF_SPEC, "ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)", ARCH_DMA_MINALIGN, cache_line_size()); - - return atomic_pool_init(); + return dma_atomic_pool_init(GFP_DMA32, __pgprot(PROT_NORMAL_NC)); } arch_initcall(arm64_dma_init); @@ -397,7 +233,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, page = alloc_pages(gfp, get_order(size)); addr = page ? page_address(page) : NULL; } else { - addr = __alloc_from_pool(size, &page, gfp); + addr = dma_alloc_from_pool(size, &page, gfp); } if (!addr) return NULL; @@ -407,7 +243,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, if (coherent) __free_pages(page, get_order(size)); else - __free_from_pool(addr, size); + dma_free_from_pool(addr, size); addr = NULL; } } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { @@ -471,9 +307,9 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, * coherent devices. * Hence how dodgy the below logic looks... */ - if (__in_atomic_pool(cpu_addr, size)) { + if (dma_in_atomic_pool(cpu_addr, size)) { iommu_dma_unmap_page(dev, handle, iosize, 0, 0); - __free_from_pool(cpu_addr, size); + dma_free_from_pool(cpu_addr, size); } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { struct page *page = vmalloc_to_page(cpu_addr); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 0f81c713f6e9..1a0edcde7d14 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -455,6 +455,11 @@ void *dma_common_pages_remap(struct page **pages, size_t size, const void *caller); void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags); +int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot); +bool dma_in_atomic_pool(void *start, size_t size); +void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags); +bool dma_free_from_pool(void *start, size_t size); + /** * dma_mmap_attrs - map a coherent DMA allocation into user space * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 9051b055beec..306557331d7d 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -69,4 +69,6 @@ static inline void arch_sync_dma_for_cpu_all(struct device *dev) } #endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */ +void arch_dma_prep_coherent(struct page *page, size_t size); + #endif /* _LINUX_DMA_NONCOHERENT_H */ diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index c92e08173ed8..41c3b1df70eb 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -55,3 +55,8 @@ config SWIOTLB config DMA_REMAP depends on MMU bool + +config DMA_DIRECT_REMAP + bool + depends on DMA_DIRECT_OPS + select DMA_REMAP diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index a15c393ea4e5..b32bb08f96ae 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -1,8 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (C) 2012 ARM Ltd. * Copyright (c) 2014 The Linux Foundation */ -#include +#include +#include +#include +#include +#include #include #include @@ -86,3 +91,154 @@ void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags) unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size)); vunmap(cpu_addr); } + +#ifdef CONFIG_DMA_DIRECT_REMAP +static struct gen_pool *atomic_pool __ro_after_init; + +#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K +static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE; + +static int __init early_coherent_pool(char *p) +{ + atomic_pool_size = memparse(p, &p); + return 0; +} +early_param("coherent_pool", early_coherent_pool); + +int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot) +{ + unsigned int pool_size_order = get_order(atomic_pool_size); + unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT; + struct page *page; + void *addr; + int ret; + + if (dev_get_cma_area(NULL)) + page = dma_alloc_from_contiguous(NULL, nr_pages, + pool_size_order, false); + else + page = alloc_pages(gfp, pool_size_order); + if (!page) + goto out; + + memset(page_address(page), 0, atomic_pool_size); + arch_dma_prep_coherent(page, atomic_pool_size); + + atomic_pool = gen_pool_create(PAGE_SHIFT, -1); + if (!atomic_pool) + goto free_page; + + addr = dma_common_contiguous_remap(page, atomic_pool_size, VM_USERMAP, + prot, __builtin_return_address(0)); + if (!addr) + goto destroy_genpool; + + ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr, + page_to_phys(page), atomic_pool_size, -1); + if (ret) + goto remove_mapping; + gen_pool_set_algo(atomic_pool, gen_pool_first_fit_order_align, NULL); + + pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n", + atomic_pool_size / 1024); + return 0; + +remove_mapping: + dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP); +destroy_genpool: + gen_pool_destroy(atomic_pool); + atomic_pool = NULL; +free_page: + if (!dma_release_from_contiguous(NULL, page, nr_pages)) + __free_pages(page, pool_size_order); +out: + pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n", + atomic_pool_size / 1024); + return -ENOMEM; +} + +bool dma_in_atomic_pool(void *start, size_t size) +{ + return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); +} + +void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) +{ + unsigned long val; + void *ptr = NULL; + + if (!atomic_pool) { + WARN(1, "coherent pool not initialised!\n"); + return NULL; + } + + val = gen_pool_alloc(atomic_pool, size); + if (val) { + phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val); + + *ret_page = pfn_to_page(__phys_to_pfn(phys)); + ptr = (void *)val; + memset(ptr, 0, size); + } + + return ptr; +} + +bool dma_free_from_pool(void *start, size_t size) +{ + if (!dma_in_atomic_pool(start, size)) + return false; + gen_pool_free(atomic_pool, (unsigned long)start, size); + return true; +} + +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t flags, unsigned long attrs) +{ + struct page *page = NULL; + void *ret, *kaddr; + + size = PAGE_ALIGN(size); + + if (!gfpflags_allow_blocking(flags)) { + ret = dma_alloc_from_pool(size, &page, flags); + if (!ret) + return NULL; + *dma_handle = phys_to_dma(dev, page_to_phys(page)); + return ret; + } + + kaddr = dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); + if (!kaddr) + return NULL; + page = virt_to_page(kaddr); + + /* remove any dirty cache lines on the kernel alias */ + arch_dma_prep_coherent(page, size); + + /* create a coherent mapping */ + ret = dma_common_contiguous_remap(page, size, VM_USERMAP, + arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs), + __builtin_return_address(0)); + if (!ret) + dma_direct_free_pages(dev, size, kaddr, *dma_handle, attrs); + return ret; +} + +void arch_dma_free(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle, unsigned long attrs) +{ + if (!dma_free_from_pool(vaddr, PAGE_ALIGN(size))) { + void *kaddr = phys_to_virt(dma_to_phys(dev, dma_handle)); + + vunmap(vaddr); + dma_direct_free_pages(dev, size, kaddr, dma_handle, attrs); + } +} + +long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, + dma_addr_t dma_addr) +{ + return __phys_to_pfn(dma_to_phys(dev, dma_addr)); +} +#endif /* CONFIG_DMA_DIRECT_REMAP */ -- cgit v1.2.3-59-g8ed1b 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') 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 v1.2.3-59-g8ed1b 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') 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 v1.2.3-59-g8ed1b 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') 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 v1.2.3-59-g8ed1b 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 --- arch/powerpc/kernel/dma-swiotlb.c | 1 - include/linux/dma-direct.h | 3 --- kernel/dma/direct.c | 8 +------- kernel/dma/swiotlb.c | 11 +++++------ 4 files changed, 6 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 5fc335f4d9cd..3d8df2cf8be9 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -59,7 +59,6 @@ const struct dma_map_ops powerpc_swiotlb_dma_ops = { .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, - .mapping_error = dma_direct_mapping_error, .get_required_mask = swiotlb_powerpc_get_required, }; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 61b78f934f64..6e5a47ae7d64 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,8 +5,6 @@ #include #include -#define DIRECT_MAPPING_ERROR (~(dma_addr_t)0) - #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #else @@ -76,5 +74,4 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); -int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr); #endif /* _LINUX_DMA_DIRECT_H */ 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 v1.2.3-59-g8ed1b 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 --- Documentation/DMA-API.txt | 3 +++ kernel/dma/debug.c | 7 +++++++ 2 files changed, 10 insertions(+) (limited to 'kernel') diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index ac66ae2509a9..6bdb095393b0 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -723,6 +723,9 @@ dma-api/min_free_entries This read-only file can be read to get the dma-api/num_free_entries The current number of free dma_debug_entries in the allocator. +dma-api/nr_total_entries The total number of dma_debug_entries in the + allocator, both free and used. + dma-api/driver-filter You can write a name of a driver into this file to limit the debug output to requests from that particular driver. Write an empty string to 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 v1.2.3-59-g8ed1b 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') 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 v1.2.3-59-g8ed1b 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 --- Documentation/DMA-API.txt | 11 +++---- kernel/dma/debug.c | 79 ++++++++++++++++++++++++----------------------- 2 files changed, 46 insertions(+), 44 deletions(-) (limited to 'kernel') diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 6bdb095393b0..0fcb7561af1e 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -717,8 +717,8 @@ dma-api/num_errors The number in this file shows how many dma-api/min_free_entries This read-only file can be read to get the minimum number of free dma_debug_entries the allocator has ever seen. If this value goes - down to zero the code will disable itself - because it is not longer reliable. + down to zero the code will attempt to increase + nr_total_entries to compensate. dma-api/num_free_entries The current number of free dma_debug_entries in the allocator. @@ -745,10 +745,9 @@ driver filter at boot time. The debug code will only print errors for that driver afterwards. This filter can be disabled or changed later using debugfs. When the code disables itself at runtime this is most likely because it ran -out of dma_debug_entries. These entries are preallocated at boot. The number -of preallocated entries is defined per architecture. If it is too low for you -boot with 'dma_debug_entries=' to overwrite the -architectural default. +out of dma_debug_entries and was unable to allocate more on-demand. 65536 +entries are preallocated at boot - if this is too low for you boot with +'dma_debug_entries=' to overwrite the default. :: 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 v1.2.3-59-g8ed1b 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 --- Documentation/DMA-API.txt | 6 +++++- kernel/dma/debug.c | 13 +++++++++++++ 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 0fcb7561af1e..7a7d8a415ce8 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -747,7 +747,11 @@ driver afterwards. This filter can be disabled or changed later using debugfs. When the code disables itself at runtime this is most likely because it ran out of dma_debug_entries and was unable to allocate more on-demand. 65536 entries are preallocated at boot - if this is too low for you boot with -'dma_debug_entries=' to overwrite the default. +'dma_debug_entries=' to overwrite the default. The +code will print to the kernel log each time it has dynamically allocated +as many entries as were initially preallocated. This is to indicate that a +larger preallocation size may be appropriate, or if it happens continually +that a driver may be leaking mappings. :: 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 v1.2.3-59-g8ed1b 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 --- include/linux/dma-debug.h | 7 ------- kernel/dma/debug.c | 46 ---------------------------------------------- 2 files changed, 53 deletions(-) (limited to 'kernel') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index 30213adbb6b9..46e6131a72b6 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -30,8 +30,6 @@ struct bus_type; extern void dma_debug_add_bus(struct bus_type *bus); -extern int dma_debug_resize_entries(u32 num_entries); - extern void debug_dma_map_single(struct device *dev, const void *addr, unsigned long len); @@ -101,11 +99,6 @@ static inline void dma_debug_add_bus(struct bus_type *bus) { } -static inline int dma_debug_resize_entries(u32 num_entries) -{ - return 0; -} - static inline void debug_dma_map_single(struct device *dev, const void *addr, unsigned long len) { 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 v1.2.3-59-g8ed1b 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 --- Documentation/DMA-API.txt | 4 +++- kernel/dma/debug.c | 50 ++++++++++++++++++++--------------------------- 2 files changed, 24 insertions(+), 30 deletions(-) (limited to 'kernel') diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 7a7d8a415ce8..016eb6909b8a 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -747,7 +747,9 @@ driver afterwards. This filter can be disabled or changed later using debugfs. When the code disables itself at runtime this is most likely because it ran out of dma_debug_entries and was unable to allocate more on-demand. 65536 entries are preallocated at boot - if this is too low for you boot with -'dma_debug_entries=' to overwrite the default. The +'dma_debug_entries=' to overwrite the default. Note +that the code allocates entries in batches, so the exact number of +preallocated entries may be greater than the actual number requested. The code will print to the kernel log each time it has dynamically allocated as many entries as were initially preallocated. This is to indicate that a larger preallocation size may be appropriate, or if it happens continually 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 v1.2.3-59-g8ed1b 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') 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 v1.2.3-59-g8ed1b 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 --- include/linux/dma-debug.h | 27 --------------------------- include/linux/dma-mapping.h | 34 ++++++++++------------------------ kernel/dma/debug.c | 42 ------------------------------------------ 3 files changed, 10 insertions(+), 93 deletions(-) (limited to 'kernel') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index 46e6131a72b6..2ad5c363d7d5 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -70,17 +70,6 @@ extern void debug_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size, int direction); -extern void debug_dma_sync_single_range_for_cpu(struct device *dev, - dma_addr_t dma_handle, - unsigned long offset, - size_t size, - int direction); - -extern void debug_dma_sync_single_range_for_device(struct device *dev, - dma_addr_t dma_handle, - unsigned long offset, - size_t size, int direction); - extern void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, int direction); @@ -167,22 +156,6 @@ static inline void debug_dma_sync_single_for_device(struct device *dev, { } -static inline void debug_dma_sync_single_range_for_cpu(struct device *dev, - dma_addr_t dma_handle, - unsigned long offset, - size_t size, - int direction) -{ -} - -static inline void debug_dma_sync_single_range_for_device(struct device *dev, - dma_addr_t dma_handle, - unsigned long offset, - size_t size, - int direction) -{ -} - static inline void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, int direction) diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 7799c2b27849..8916499d2805 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -360,6 +360,13 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, debug_dma_sync_single_for_cpu(dev, addr, size, dir); } +static inline void dma_sync_single_range_for_cpu(struct device *dev, + dma_addr_t addr, unsigned long offset, size_t size, + enum dma_data_direction dir) +{ + return dma_sync_single_for_cpu(dev, addr + offset, size, dir); +} + static inline void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) @@ -372,32 +379,11 @@ static inline void dma_sync_single_for_device(struct device *dev, debug_dma_sync_single_for_device(dev, addr, size, dir); } -static inline void dma_sync_single_range_for_cpu(struct device *dev, - dma_addr_t addr, - unsigned long offset, - 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->sync_single_for_cpu) - ops->sync_single_for_cpu(dev, addr + offset, size, dir); - debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir); -} - static inline void dma_sync_single_range_for_device(struct device *dev, - dma_addr_t addr, - unsigned long offset, - size_t size, - enum dma_data_direction dir) + dma_addr_t addr, unsigned long offset, 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->sync_single_for_device) - ops->sync_single_for_device(dev, addr + offset, size, dir); - debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir); + return dma_sync_single_for_device(dev, addr + offset, size, dir); } static inline void 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 v1.2.3-59-g8ed1b 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 --- drivers/base/platform.c | 31 ------------------------------- kernel/dma/mapping.c | 34 +++++++++++++++++++++++++++++++++- 2 files changed, 33 insertions(+), 32 deletions(-) (limited to 'kernel') diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 41b91af95afb..eae841935a45 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1179,37 +1179,6 @@ int __init platform_bus_init(void) return error; } -#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 - static __initdata LIST_HEAD(early_platform_driver_list); static __initdata LIST_HEAD(early_platform_device_list); 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 v1.2.3-59-g8ed1b 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 --- arch/powerpc/include/asm/dma-mapping.h | 1 - include/linux/dma-mapping.h | 150 +++------------------------------ kernel/dma/mapping.c | 140 +++++++++++++++++++++++++++++- 3 files changed, 151 insertions(+), 140 deletions(-) (limited to 'kernel') diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 8fa394520af6..5201f2b7838c 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -108,7 +108,6 @@ static inline void set_dma_offset(struct device *dev, dma_addr_t off) } #define HAVE_ARCH_DMA_SET_MASK 1 -extern int dma_set_mask(struct device *dev, u64 dma_mask); extern u64 __dma_get_required_mask(struct device *dev); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 3b431cc58794..0bbce52606c2 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -440,107 +440,24 @@ bool dma_in_atomic_pool(void *start, size_t size); void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags); bool dma_free_from_pool(void *start, size_t size); -/** - * dma_mmap_attrs - map a coherent DMA allocation into user space - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @vma: vm_area_struct describing requested user mapping - * @cpu_addr: kernel CPU-view address returned from dma_alloc_attrs - * @handle: 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. - */ -static inline 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); -} - +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); #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0) int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); -static inline 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); -} - +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); #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0) -#ifndef arch_dma_alloc_attrs -#define arch_dma_alloc_attrs(dev) (true) -#endif - -static inline 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; -} - -static inline 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); -} +void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t flag, unsigned long attrs); +void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle, unsigned long attrs); static inline void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) @@ -565,35 +482,9 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) return 0; } -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"); -} - -static inline 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); -} - -#ifndef HAVE_ARCH_DMA_SET_MASK -static inline 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; -} -#endif +int dma_supported(struct device *dev, u64 mask); +int dma_set_mask(struct device *dev, u64 mask); +int dma_set_coherent_mask(struct device *dev, u64 mask); static inline u64 dma_get_mask(struct device *dev) { @@ -602,21 +493,6 @@ static inline u64 dma_get_mask(struct device *dev) return DMA_BIT_MASK(32); } -#ifdef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK -int dma_set_coherent_mask(struct device *dev, u64 mask); -#else -static inline 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; -} -#endif - /* * Set both the DMA mask and the coherent DMA mask to the same thing. * Note that we don't check the return value from dma_set_coherent_mask() 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 v1.2.3-59-g8ed1b 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 --- include/linux/dma-mapping.h | 12 ++---------- kernel/dma/mapping.c | 11 +++++++++++ 2 files changed, 13 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 0bbce52606c2..0f0078490df4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -411,16 +411,8 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, #define dma_map_page(d, p, o, s, r) dma_map_page_attrs(d, p, o, s, r, 0) #define dma_unmap_page(d, a, s, r) dma_unmap_page_attrs(d, a, s, r, 0) -static inline 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); -} +void dma_cache_sync(struct device *dev, void *vaddr, size_t size, + enum dma_data_direction dir); extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, 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 v1.2.3-59-g8ed1b From 3731c3d4774e38b9d91c01943e1e6a243c1776be Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Dec 2018 12:50:26 -0800 Subject: dma-mapping: always build the direct mapping code All architectures except for sparc64 use the dma-direct code in some form, and even for sparc64 we had the discussion of a direct mapping mode a while ago. In preparation for directly calling the direct mapping code don't bother having it optionally but always build the code in. This is a minor hardship for some powerpc and arm configs that don't pull it in yet (although they should in a relase ot two), and sparc64 which currently doesn't need it at all, but it will reduce the ifdef mess we'd otherwise need significantly. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- arch/alpha/Kconfig | 1 - arch/arc/Kconfig | 1 - arch/arm/Kconfig | 1 - arch/arm64/Kconfig | 1 - arch/c6x/Kconfig | 1 - arch/csky/Kconfig | 1 - arch/h8300/Kconfig | 1 - arch/hexagon/Kconfig | 1 - arch/m68k/Kconfig | 1 - arch/microblaze/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/nds32/Kconfig | 1 - arch/nios2/Kconfig | 1 - arch/openrisc/Kconfig | 1 - arch/parisc/Kconfig | 1 - arch/riscv/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/sh/Kconfig | 1 - arch/sparc/Kconfig | 1 - arch/unicore32/Kconfig | 1 - arch/x86/Kconfig | 1 - arch/xtensa/Kconfig | 1 - kernel/dma/Kconfig | 7 ------- kernel/dma/Makefile | 3 +-- 24 files changed, 1 insertion(+), 31 deletions(-) (limited to 'kernel') diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index a7e748a46c18..5da6ff54b3e7 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -203,7 +203,6 @@ config ALPHA_EIGER config ALPHA_JENSEN bool "Jensen" depends on BROKEN - select DMA_DIRECT_OPS help DEC PC 150 AXP (aka Jensen): This is a very old Digital system - one of the first-generation Alpha systems. A number of these systems diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index fd48d698da29..7deaabeb531a 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -17,7 +17,6 @@ config ARC select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select COMMON_CLK - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC) select GENERIC_CLOCKEVENTS select GENERIC_FIND_FIRST_BIT diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index a858ee791ef0..586fc30b23bd 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -30,7 +30,6 @@ config ARM select CLONE_BACKWARDS select CPU_PM if (SUSPEND || CPU_IDLE) select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS - select DMA_DIRECT_OPS if !MMU select DMA_REMAP if MMU select EDAC_SUPPORT select EDAC_ATOMIC_SCRUB diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 06cf0ef24367..2092080240b0 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -80,7 +80,6 @@ config ARM64 select CPU_PM if (SUSPEND || CPU_IDLE) select CRC32 select DCACHE_WORD_ACCESS - select DMA_DIRECT_OPS select DMA_DIRECT_REMAP select EDAC_SUPPORT select FRAME_POINTER diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig index 84420109113d..456e154674d1 100644 --- a/arch/c6x/Kconfig +++ b/arch/c6x/Kconfig @@ -9,7 +9,6 @@ config C6X select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select CLKDEV_LOOKUP - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 select GENERIC_IRQ_SHOW select HAVE_ARCH_TRACEHOOK diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index ea74f3a9eeaf..37bed8aadf95 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -7,7 +7,6 @@ config CSKY select COMMON_CLK select CLKSRC_MMIO select CLKSRC_OF - select DMA_DIRECT_OPS select DMA_DIRECT_REMAP select IRQ_DOMAIN select HANDLE_DOMAIN_IRQ diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index d19c6b16cd5d..6472a0685470 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -22,7 +22,6 @@ config H8300 select HAVE_ARCH_KGDB select HAVE_ARCH_HASH select CPU_NO_EFFICIENT_FFS - select DMA_DIRECT_OPS config CPU_BIG_ENDIAN def_bool y diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 2b688af379e6..d71036c598de 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -31,7 +31,6 @@ config HEXAGON select GENERIC_CLOCKEVENTS_BROADCAST select MODULES_USE_ELF_RELA select GENERIC_CPU_DEVICES - select DMA_DIRECT_OPS ---help--- Qualcomm Hexagon is a processor architecture designed for high performance and low power across a wide variety of applications. diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 1bc9f1ba759a..8a5868e9a3a0 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -26,7 +26,6 @@ config M68K select MODULES_USE_ELF_RELA select OLD_SIGSUSPEND3 select OLD_SIGACTION - select DMA_DIRECT_OPS if HAS_DMA select ARCH_DISCARD_MEMBLOCK config CPU_BIG_ENDIAN diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index effed2efd306..eda9e2315ef5 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -12,7 +12,6 @@ config MICROBLAZE select TIMER_OF select CLONE_BACKWARDS3 select COMMON_CLK - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS select GENERIC_CPU_DEVICES diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 8272ea4c7264..2993aa9842c0 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -16,7 +16,6 @@ config MIPS select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select CPU_PM if CPU_IDLE - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS select GENERIC_CMOS_UPDATE diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 7a04adacb2f0..1af6bbae7220 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -11,7 +11,6 @@ config NDS32 select CLKSRC_MMIO select CLONE_BACKWARDS select COMMON_CLK - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index 7e95506e957a..f6c4b0f49997 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -4,7 +4,6 @@ config NIOS2 select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_NO_SWAP - select DMA_DIRECT_OPS select TIMER_OF select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index 285f7d05c8ed..d0feebad5a8f 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -7,7 +7,6 @@ config OPENRISC def_bool y select ARCH_HAS_SYNC_DMA_FOR_DEVICE - select DMA_DIRECT_OPS select OF select OF_EARLY_FLATTREE select IRQ_DOMAIN diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 428ee50fc3db..6e1b71da0e71 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -185,7 +185,6 @@ config PA11 depends on PA7000 || PA7100LC || PA7200 || PA7300LC select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE - select DMA_DIRECT_OPS select DMA_NONCOHERENT_CACHE_SYNC config PREFETCH diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 55da93f4e818..51d89c4b1dca 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -19,7 +19,6 @@ config RISCV select ARCH_WANT_FRAME_POINTERS select CLONE_BACKWARDS select COMMON_CLK - select DMA_DIRECT_OPS select GENERIC_CLOCKEVENTS select GENERIC_CPU_DEVICES select GENERIC_IRQ_SHOW diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 5624e8607054..21d271d04ca6 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -139,7 +139,6 @@ config S390 select HAVE_COPY_THREAD_TLS select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS - select DMA_DIRECT_OPS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EFFICIENT_UNALIGNED_ACCESS diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index f82a4da7adf3..10fd4e9c454b 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -7,7 +7,6 @@ config SUPERH select ARCH_NO_COHERENT_DMA_MMAP if !MMU select HAVE_PATA_PLATFORM select CLKDEV_LOOKUP - select DMA_DIRECT_OPS select HAVE_IDE if HAS_IOPORT_MAP select HAVE_MEMBLOCK_NODE_MAP select ARCH_DISCARD_MEMBLOCK diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 8853b6ceae17..f5bb9ded1d18 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -48,7 +48,6 @@ config SPARC config SPARC32 def_bool !64BIT select ARCH_HAS_SYNC_DMA_FOR_CPU - select DMA_DIRECT_OPS select GENERIC_ATOMIC64 select CLZ_TAB select HAVE_UID16 diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index a4c05159dca5..2681027d7bff 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -4,7 +4,6 @@ config UNICORE32 select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO - select DMA_DIRECT_OPS select HAVE_GENERIC_DMA_COHERENT select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index adc845b66f01..c14d4a35be13 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -89,7 +89,6 @@ config X86 select CLOCKSOURCE_VALIDATE_LAST_CYCLE select CLOCKSOURCE_WATCHDOG select DCACHE_WORD_ACCESS - select DMA_DIRECT_OPS select EDAC_ATOMIC_SCRUB select EDAC_SUPPORT select GENERIC_CLOCKEVENTS diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 75488b606edc..36338e7564a3 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -9,7 +9,6 @@ config XTENSA select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select COMMON_CLK - select DMA_DIRECT_OPS select DMA_REMAP if MMU select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 41c3b1df70eb..ca88b867e7fe 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -35,13 +35,8 @@ config ARCH_HAS_DMA_COHERENT_TO_PFN config ARCH_HAS_DMA_MMAP_PGPROT bool -config DMA_DIRECT_OPS - bool - depends on HAS_DMA - config DMA_NONCOHERENT_CACHE_SYNC bool - depends on DMA_DIRECT_OPS config DMA_VIRT_OPS bool @@ -49,7 +44,6 @@ config DMA_VIRT_OPS config SWIOTLB bool - select DMA_DIRECT_OPS select NEED_DMA_MAP_STATE config DMA_REMAP @@ -58,5 +52,4 @@ config DMA_REMAP config DMA_DIRECT_REMAP bool - depends on DMA_DIRECT_OPS select DMA_REMAP diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile index f4feeceb8020..a626f643cd63 100644 --- a/kernel/dma/Makefile +++ b/kernel/dma/Makefile @@ -1,9 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_HAS_DMA) += mapping.o +obj-$(CONFIG_HAS_DMA) += mapping.o direct.o obj-$(CONFIG_DMA_CMA) += contiguous.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o -obj-$(CONFIG_DMA_DIRECT_OPS) += direct.o obj-$(CONFIG_DMA_VIRT_OPS) += virt.o obj-$(CONFIG_DMA_API_DEBUG) += debug.o obj-$(CONFIG_SWIOTLB) += swiotlb.o -- cgit v1.2.3-59-g8ed1b From 90ac706e98fcb24fb0b0a259558987f33cc2f0f6 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 6 Dec 2018 13:14:44 -0800 Subject: dma-mapping: factor out dummy DMA ops The dummy DMA ops are currently used by arm64 for any device which has an invalid ACPI description and is thus barred from using DMA due to not knowing whether is is cache-coherent or not. Factor these out into general dma-mapping code so that they can be referenced from other common code paths. In the process, we can prune all the optional callbacks which just do the same thing as the default behaviour, and fill in .map_resource for completeness. Signed-off-by: Robin Murphy [hch: moved to a separate source file] Reviewed-by: Rafael J. Wysocki Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck Signed-off-by: Christoph Hellwig --- arch/arm64/include/asm/dma-mapping.h | 4 +- arch/arm64/mm/dma-mapping.c | 86 ------------------------------------ include/linux/dma-mapping.h | 1 + kernel/dma/Makefile | 2 +- kernel/dma/dummy.c | 39 ++++++++++++++++ 5 files changed, 42 insertions(+), 90 deletions(-) create mode 100644 kernel/dma/dummy.c (limited to 'kernel') diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index c41f3fb1446c..273e778f7de2 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -24,15 +24,13 @@ #include #include -extern const struct dma_map_ops dummy_dma_ops; - static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { /* * We expect no ISA devices, and all other DMA masters are expected to * have someone call arch_setup_dma_ops at device creation time. */ - return &dummy_dma_ops; + return &dma_dummy_ops; } void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 4c0f498069e8..6ff6ec8806c1 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -89,92 +89,6 @@ static int __swiotlb_mmap_pfn(struct vm_area_struct *vma, } #endif /* CONFIG_IOMMU_DMA */ -/******************************************** - * The following APIs are for dummy DMA ops * - ********************************************/ - -static void *__dummy_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, - unsigned long attrs) -{ - return NULL; -} - -static void __dummy_free(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs) -{ -} - -static int __dummy_mmap(struct device *dev, - struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - return -ENXIO; -} - -static dma_addr_t __dummy_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - return DMA_MAPPING_ERROR; -} - -static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ -} - -static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - unsigned long attrs) -{ - return 0; -} - -static void __dummy_unmap_sg(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, - unsigned long attrs) -{ -} - -static void __dummy_sync_single(struct device *dev, - dma_addr_t dev_addr, size_t size, - enum dma_data_direction dir) -{ -} - -static void __dummy_sync_sg(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) -{ -} - -static int __dummy_dma_supported(struct device *hwdev, u64 mask) -{ - return 0; -} - -const struct dma_map_ops dummy_dma_ops = { - .alloc = __dummy_alloc, - .free = __dummy_free, - .mmap = __dummy_mmap, - .map_page = __dummy_map_page, - .unmap_page = __dummy_unmap_page, - .map_sg = __dummy_map_sg, - .unmap_sg = __dummy_unmap_sg, - .sync_single_for_cpu = __dummy_sync_single, - .sync_single_for_device = __dummy_sync_single, - .sync_sg_for_cpu = __dummy_sync_sg, - .sync_sg_for_device = __dummy_sync_sg, - .dma_supported = __dummy_dma_supported, -}; -EXPORT_SYMBOL(dummy_dma_ops); - static int __init arm64_dma_init(void) { WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(), diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 0f0078490df4..269ee27fc3d9 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -136,6 +136,7 @@ struct dma_map_ops { extern const struct dma_map_ops dma_direct_ops; extern const struct dma_map_ops dma_virt_ops; +extern const struct dma_map_ops dma_dummy_ops; #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile index a626f643cd63..72ff6e46aa86 100644 --- a/kernel/dma/Makefile +++ b/kernel/dma/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_HAS_DMA) += mapping.o direct.o +obj-$(CONFIG_HAS_DMA) += mapping.o direct.o dummy.o obj-$(CONFIG_DMA_CMA) += contiguous.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o obj-$(CONFIG_DMA_VIRT_OPS) += virt.o diff --git a/kernel/dma/dummy.c b/kernel/dma/dummy.c new file mode 100644 index 000000000000..05607642c888 --- /dev/null +++ b/kernel/dma/dummy.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Dummy DMA ops that always fail. + */ +#include + +static int dma_dummy_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + return -ENXIO; +} + +static dma_addr_t dma_dummy_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + return DMA_MAPPING_ERROR; +} + +static int dma_dummy_map_sg(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir, + unsigned long attrs) +{ + return 0; +} + +static int dma_dummy_supported(struct device *hwdev, u64 mask) +{ + return 0; +} + +const struct dma_map_ops dma_dummy_ops = { + .mmap = dma_dummy_mmap, + .map_page = dma_dummy_map_page, + .map_sg = dma_dummy_map_sg, + .dma_supported = dma_dummy_supported, +}; +EXPORT_SYMBOL(dma_dummy_ops); -- cgit v1.2.3-59-g8ed1b 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 --- drivers/xen/swiotlb-xen.c | 4 ++-- include/linux/swiotlb.h | 3 --- kernel/dma/swiotlb.c | 4 ++-- 3 files changed, 4 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 6dc969d5ea2f..833e80b46eb2 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -403,7 +403,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir, attrs); - if (map == SWIOTLB_MAP_ERROR) + if (map == DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; dev_addr = xen_phys_to_bus(map); @@ -572,7 +572,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, sg_phys(sg), sg->length, dir, attrs); - if (map == SWIOTLB_MAP_ERROR) { + if (map == DMA_MAPPING_ERROR) { dev_warn(hwdev, "swiotlb buffer is full\n"); /* Don't panic here, we expect map_sg users to do proper error handling. */ diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index a387b59640a4..14aec0b70dd9 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -46,9 +46,6 @@ enum dma_sync_target { SYNC_FOR_DEVICE = 1, }; -/* define the last possible byte of physical address space as a mapping error */ -#define SWIOTLB_MAP_ERROR (~(phys_addr_t)0x0) - extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, phys_addr_t phys, size_t size, 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 v1.2.3-59-g8ed1b 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 --- arch/ia64/Kconfig | 3 ++- arch/ia64/kernel/dma-mapping.c | 20 +++++++++++++++++++- arch/ia64/mm/init.c | 19 ++++++++----------- drivers/xen/swiotlb-xen.c | 20 +------------------- include/linux/dma-direct.h | 8 -------- kernel/dma/swiotlb.c | 18 +----------------- 6 files changed, 31 insertions(+), 57 deletions(-) (limited to 'kernel') diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index d6f203658994..c587e3316c38 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -28,7 +28,8 @@ config IA64 select HAVE_ARCH_TRACEHOOK select HAVE_MEMBLOCK_NODE_MAP select HAVE_VIRT_CPU_ACCOUNTING - select ARCH_HAS_DMA_MARK_CLEAN + select ARCH_HAS_DMA_COHERENT_TO_PFN + select ARCH_HAS_SYNC_DMA_FOR_CPU select VIRT_TO_BUS select ARCH_DISCARD_MEMBLOCK select GENERIC_IRQ_PROBE diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c index 7a471d8d67d4..36dd6aa6d759 100644 --- a/arch/ia64/kernel/dma-mapping.c +++ b/arch/ia64/kernel/dma-mapping.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include +#include #include #include @@ -16,6 +16,24 @@ const struct dma_map_ops *dma_get_ops(struct device *dev) EXPORT_SYMBOL(dma_get_ops); #ifdef CONFIG_SWIOTLB +void *arch_dma_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +{ + return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs); +} + +void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_addr, unsigned long attrs) +{ + dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs); +} + +long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, + dma_addr_t dma_addr) +{ + return page_to_pfn(virt_to_page(cpu_addr)); +} + void __init swiotlb_dma_init(void) { dma_ops = &swiotlb_dma_ops; diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index d5e12ff1d73c..0cf43bb13d6e 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -71,18 +72,14 @@ __ia64_sync_icache_dcache (pte_t pte) * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to * flush them when they get mapped into an executable vm-area. */ -void -dma_mark_clean(void *addr, size_t size) +void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) { - unsigned long pg_addr, end; - - pg_addr = PAGE_ALIGN((unsigned long) addr); - end = (unsigned long) addr + size; - while (pg_addr + PAGE_SIZE <= end) { - struct page *page = virt_to_page(pg_addr); - set_bit(PG_arch_1, &page->flags); - pg_addr += PAGE_SIZE; - } + unsigned long pfn = PHYS_PFN(paddr); + + do { + set_bit(PG_arch_1, &pfn_to_page(pfn)->flags); + } while (++pfn <= PHYS_PFN(paddr + size - 1)); } inline void diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 833e80b46eb2..989cf872b98c 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -441,21 +441,8 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr, xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs); /* NOTE: We use dev_addr here, not paddr! */ - if (is_xen_swiotlb_buffer(dev_addr)) { + if (is_xen_swiotlb_buffer(dev_addr)) 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); } static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, @@ -493,11 +480,6 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, if (target == SYNC_FOR_DEVICE) xen_dma_sync_single_for_device(hwdev, dev_addr, size, dir); - - if (dir != DMA_FROM_DEVICE) - return; - - dma_mark_clean(phys_to_virt(paddr), size); } void diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 6e5a47ae7d64..1aa73f4907ae 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -48,14 +48,6 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) return __sme_clr(__dma_to_phys(dev, daddr)); } -#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN -void dma_mark_clean(void *addr, size_t size); -#else -static inline void dma_mark_clean(void *addr, size_t size) -{ -} -#endif /* CONFIG_ARCH_HAS_DMA_MARK_CLEAN */ - u64 dma_direct_get_required_mask(struct device *dev); void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); 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 v1.2.3-59-g8ed1b 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') 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 v1.2.3-59-g8ed1b 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') 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 v1.2.3-59-g8ed1b From 55897af63091ebc2c3f239c6a6666f748113ac50 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 3 Dec 2018 11:43:54 +0100 Subject: dma-direct: merge swiotlb_dma_ops into the dma_direct code While the dma-direct code is (relatively) clean and simple we actually have to use the swiotlb ops for the mapping on many architectures due to devices with addressing limits. Instead of keeping two implementations around this commit allows the dma-direct implementation to call the swiotlb bounce buffering functions and thus share the guts of the mapping implementation. This also simplified the dma-mapping setup on a few architectures where we don't have to differenciate which implementation to use. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- arch/arm64/mm/dma-mapping.c | 2 +- arch/ia64/hp/common/hwsw_iommu.c | 2 +- arch/ia64/hp/common/sba_iommu.c | 6 +- arch/ia64/kernel/dma-mapping.c | 2 +- arch/mips/include/asm/dma-mapping.h | 2 - arch/powerpc/kernel/dma-swiotlb.c | 16 +-- arch/riscv/include/asm/dma-mapping.h | 15 --- arch/x86/kernel/pci-swiotlb.c | 4 +- arch/x86/mm/mem_encrypt.c | 7 -- arch/x86/pci/sta2x11-fixup.c | 1 - include/linux/dma-direct.h | 12 ++ include/linux/swiotlb.h | 74 +++++------ kernel/dma/direct.c | 113 ++++++++++++----- kernel/dma/swiotlb.c | 232 ++--------------------------------- 14 files changed, 150 insertions(+), 338 deletions(-) delete mode 100644 arch/riscv/include/asm/dma-mapping.h (limited to 'kernel') diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 6ff6ec8806c1..ab1e417204d0 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -463,7 +463,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent) { if (!dev->dma_ops) - dev->dma_ops = &swiotlb_dma_ops; + dev->dma_ops = &dma_direct_ops; dev->dma_coherent = coherent; __iommu_setup_dma_ops(dev, dma_base, size, iommu); diff --git a/arch/ia64/hp/common/hwsw_iommu.c b/arch/ia64/hp/common/hwsw_iommu.c index 58969039bed2..f40ca499b246 100644 --- a/arch/ia64/hp/common/hwsw_iommu.c +++ b/arch/ia64/hp/common/hwsw_iommu.c @@ -38,7 +38,7 @@ static inline int use_swiotlb(struct device *dev) const struct dma_map_ops *hwsw_dma_get_ops(struct device *dev) { if (use_swiotlb(dev)) - return &swiotlb_dma_ops; + return &dma_direct_ops; return &sba_dma_ops; } EXPORT_SYMBOL(hwsw_dma_get_ops); diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index 0d21c0b5b23d..5ee74820a0f6 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -2065,8 +2065,6 @@ static int __init acpi_sba_ioc_init_acpi(void) /* This has to run before acpi_scan_init(). */ arch_initcall(acpi_sba_ioc_init_acpi); -extern const struct dma_map_ops swiotlb_dma_ops; - static int __init sba_init(void) { @@ -2080,7 +2078,7 @@ sba_init(void) * a successful kdump kernel boot is to use the swiotlb. */ if (is_kdump_kernel()) { - dma_ops = &swiotlb_dma_ops; + dma_ops = &dma_direct_ops; if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0) panic("Unable to initialize software I/O TLB:" " Try machvec=dig boot option"); @@ -2102,7 +2100,7 @@ sba_init(void) * If we didn't find something sba_iommu can claim, we * need to setup the swiotlb and switch to the dig machvec. */ - dma_ops = &swiotlb_dma_ops; + dma_ops = &dma_direct_ops; if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0) panic("Unable to find SBA IOMMU or initialize " "software I/O TLB: Try machvec=dig boot option"); diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c index 36dd6aa6d759..80cd3e1ea95a 100644 --- a/arch/ia64/kernel/dma-mapping.c +++ b/arch/ia64/kernel/dma-mapping.c @@ -36,7 +36,7 @@ long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, void __init swiotlb_dma_init(void) { - dma_ops = &swiotlb_dma_ops; + dma_ops = &dma_direct_ops; swiotlb_init(1); } #endif diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h index b4c477eb46ce..69f914667f3e 100644 --- a/arch/mips/include/asm/dma-mapping.h +++ b/arch/mips/include/asm/dma-mapping.h @@ -10,8 +10,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { #if defined(CONFIG_MACH_JAZZ) return &jazz_dma_ops; -#elif defined(CONFIG_SWIOTLB) - return &swiotlb_dma_ops; #else return &dma_direct_ops; #endif diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 3d8df2cf8be9..430a7d0aa2cb 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -50,15 +50,15 @@ const struct dma_map_ops powerpc_swiotlb_dma_ops = { .alloc = __dma_nommu_alloc_coherent, .free = __dma_nommu_free_coherent, .mmap = dma_nommu_mmap_coherent, - .map_sg = swiotlb_map_sg_attrs, - .unmap_sg = swiotlb_unmap_sg_attrs, + .map_sg = dma_direct_map_sg, + .unmap_sg = dma_direct_unmap_sg, .dma_supported = swiotlb_dma_supported, - .map_page = swiotlb_map_page, - .unmap_page = swiotlb_unmap_page, - .sync_single_for_cpu = swiotlb_sync_single_for_cpu, - .sync_single_for_device = swiotlb_sync_single_for_device, - .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, - .sync_sg_for_device = swiotlb_sync_sg_for_device, + .map_page = dma_direct_map_page, + .unmap_page = dma_direct_unmap_page, + .sync_single_for_cpu = dma_direct_sync_single_for_cpu, + .sync_single_for_device = dma_direct_sync_single_for_device, + .sync_sg_for_cpu = dma_direct_sync_sg_for_cpu, + .sync_sg_for_device = dma_direct_sync_sg_for_device, .get_required_mask = swiotlb_powerpc_get_required, }; diff --git a/arch/riscv/include/asm/dma-mapping.h b/arch/riscv/include/asm/dma-mapping.h deleted file mode 100644 index 8facc1c8fa05..000000000000 --- a/arch/riscv/include/asm/dma-mapping.h +++ /dev/null @@ -1,15 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#ifndef _RISCV_ASM_DMA_MAPPING_H -#define _RISCV_ASM_DMA_MAPPING_H 1 - -#ifdef CONFIG_SWIOTLB -#include -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) -{ - return &swiotlb_dma_ops; -} -#else -#include -#endif /* CONFIG_SWIOTLB */ - -#endif /* _RISCV_ASM_DMA_MAPPING_H */ diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index bd08b9e1c9e2..5f5302028a9a 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -62,10 +62,8 @@ IOMMU_INIT(pci_swiotlb_detect_4gb, void __init pci_swiotlb_init(void) { - if (swiotlb) { + if (swiotlb) swiotlb_init(0); - dma_ops = &swiotlb_dma_ops; - } } void __init pci_swiotlb_late_init(void) diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 006f373f54ab..385afa2b9e17 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -380,13 +380,6 @@ void __init mem_encrypt_init(void) /* Call into SWIOTLB to update the SWIOTLB DMA buffers */ swiotlb_update_mem_attributes(); - /* - * With SEV, DMA operations cannot use encryption, we need to use - * SWIOTLB to bounce buffer DMA operation. - */ - if (sev_active()) - dma_ops = &swiotlb_dma_ops; - /* * With SEV, we need to unroll the rep string I/O instructions. */ diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 7a5bafb76d77..3cdafea55ab6 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -168,7 +168,6 @@ static void sta2x11_setup_pdev(struct pci_dev *pdev) return; pci_set_consistent_dma_mask(pdev, STA2X11_AMBA_SIZE - 1); pci_set_dma_mask(pdev, STA2X11_AMBA_SIZE - 1); - pdev->dev.dma_ops = &swiotlb_dma_ops; pdev->dev.archdata.is_sta2x11 = true; /* We must enable all devices as master, for audio DMA to work */ diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 1aa73f4907ae..3b0a3ea3876d 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -63,7 +63,19 @@ void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page) dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs); int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir); +void dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); +void dma_direct_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir); +void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); int dma_direct_supported(struct device *dev, u64 mask); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 14aec0b70dd9..7c007ed7505f 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -16,8 +16,6 @@ enum swiotlb_force { SWIOTLB_NO_FORCE, /* swiotlb=noforce */ }; -extern enum swiotlb_force swiotlb_force; - /* * Maximum allowable number of contiguous slabs to map, * must be a power of 2. What is the appropriate value ? @@ -62,56 +60,44 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev, size_t size, enum dma_data_direction dir, enum dma_sync_target target); -/* Accessory functions. */ - -extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs); -extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs); - -extern int -swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, - unsigned long attrs); - -extern void -swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - unsigned long attrs); - -extern void -swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir); - -extern void -swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); - -extern void -swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir); - -extern void -swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); - extern int swiotlb_dma_supported(struct device *hwdev, u64 mask); #ifdef CONFIG_SWIOTLB -extern void __init swiotlb_exit(void); +extern enum swiotlb_force swiotlb_force; +extern phys_addr_t io_tlb_start, io_tlb_end; + +static inline bool is_swiotlb_buffer(phys_addr_t paddr) +{ + return paddr >= io_tlb_start && paddr < io_tlb_end; +} + +bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, + size_t size, enum dma_data_direction dir, unsigned long attrs); +void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); #else -static inline void swiotlb_exit(void) { } -static inline unsigned int swiotlb_max_segment(void) { return 0; } -#endif +#define swiotlb_force SWIOTLB_NO_FORCE +static inline bool is_swiotlb_buffer(phys_addr_t paddr) +{ + return false; +} +static inline bool swiotlb_map(struct device *dev, phys_addr_t *phys, + dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + return false; +} +static inline void swiotlb_exit(void) +{ +} +static inline unsigned int swiotlb_max_segment(void) +{ + return 0; +} +#endif /* CONFIG_SWIOTLB */ extern void swiotlb_print_info(void); extern void swiotlb_set_max_segment(unsigned int); -extern const struct dma_map_ops swiotlb_dma_ops; - #endif /* __LINUX_SWIOTLB_H */ diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index d45306473c90..85d8286a0ba2 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -13,6 +13,7 @@ #include #include #include +#include /* * Most architectures use ZONE_DMA for the first 16 Megabytes, but @@ -209,69 +210,110 @@ void dma_direct_free(struct device *dev, size_t size, dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs); } -static void dma_direct_sync_single_for_device(struct device *dev, +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { - if (dev_is_dma_coherent(dev)) - return; - arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir); + phys_addr_t paddr = dma_to_phys(dev, addr); + + if (unlikely(is_swiotlb_buffer(paddr))) + swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); + + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_device(dev, paddr, size, dir); } -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) -static void dma_direct_sync_sg_for_device(struct device *dev, +void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { struct scatterlist *sg; int i; - if (dev_is_dma_coherent(dev)) - return; + for_each_sg(sgl, sg, nents, i) { + if (unlikely(is_swiotlb_buffer(sg_phys(sg)))) + swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, + dir, SYNC_FOR_DEVICE); - for_each_sg(sgl, sg, nents, i) - arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, + dir); + } } #endif #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) -static void dma_direct_sync_single_for_cpu(struct device *dev, + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { - if (dev_is_dma_coherent(dev)) - return; - arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir); - arch_sync_dma_for_cpu_all(dev); + phys_addr_t paddr = dma_to_phys(dev, addr); + + if (!dev_is_dma_coherent(dev)) { + arch_sync_dma_for_cpu(dev, paddr, size, dir); + arch_sync_dma_for_cpu_all(dev); + } + + if (unlikely(is_swiotlb_buffer(paddr))) + swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); } -static void dma_direct_sync_sg_for_cpu(struct device *dev, +void dma_direct_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { struct scatterlist *sg; int i; - if (dev_is_dma_coherent(dev)) - return; + for_each_sg(sgl, sg, nents, i) { + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); + + if (unlikely(is_swiotlb_buffer(sg_phys(sg)))) + swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, dir, + SYNC_FOR_CPU); + } - for_each_sg(sgl, sg, nents, i) - arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); - arch_sync_dma_for_cpu_all(dev); + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_cpu_all(dev); } -static void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, +void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { + phys_addr_t phys = dma_to_phys(dev, addr); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) dma_direct_sync_single_for_cpu(dev, addr, size, dir); + + if (unlikely(is_swiotlb_buffer(phys))) + swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } -static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir, + attrs); +} +#else +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs) { - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir); } #endif +static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr, + size_t size) +{ + return swiotlb_force != SWIOTLB_FORCE && + (!dev || dma_capable(dev, dma_addr, size)); +} + dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) @@ -279,13 +321,14 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dma_addr = phys_to_dma(dev, phys); - if (unlikely(dev && !dma_capable(dev, dma_addr, size))) { + if (unlikely(!dma_direct_possible(dev, dma_addr, size)) && + !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) { report_addr(dev, dma_addr, size); return DMA_MAPPING_ERROR; } - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_direct_sync_single_for_device(dev, dma_addr, size, dir); + if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(dev, phys, size, dir); return dma_addr; } @@ -299,11 +342,15 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, sg->dma_address = dma_direct_map_page(dev, sg_page(sg), sg->offset, sg->length, dir, attrs); if (sg->dma_address == DMA_MAPPING_ERROR) - return 0; + goto out_unmap; sg_dma_len(sg) = sg->length; } return nents; + +out_unmap: + dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); + return 0; } /* @@ -331,12 +378,14 @@ const struct dma_map_ops dma_direct_ops = { .free = dma_direct_free, .map_page = dma_direct_map_page, .map_sg = dma_direct_map_sg, -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_SWIOTLB) .sync_single_for_device = dma_direct_sync_single_for_device, .sync_sg_for_device = dma_direct_sync_sg_for_device, #endif #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ + defined(CONFIG_SWIOTLB) .sync_single_for_cpu = dma_direct_sync_single_for_cpu, .sync_sg_for_cpu = dma_direct_sync_sg_for_cpu, .unmap_page = dma_direct_unmap_page, diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 2e126bac5d7d..d6361776dc5c 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -21,7 +21,6 @@ #include #include -#include #include #include #include @@ -65,7 +64,7 @@ enum swiotlb_force swiotlb_force; * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this * API. */ -static phys_addr_t io_tlb_start, io_tlb_end; +phys_addr_t io_tlb_start, io_tlb_end; /* * The number of IO TLB blocks (in groups of 64) between io_tlb_start and @@ -383,11 +382,6 @@ void __init swiotlb_exit(void) max_segment = 0; } -static int is_swiotlb_buffer(phys_addr_t paddr) -{ - return paddr >= io_tlb_start && paddr < io_tlb_end; -} - /* * Bounce: copy the swiotlb buffer back to the original dma location */ @@ -623,221 +617,36 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, } } -static dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys, +/* + * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing + * to the device copy the data into it as well. + */ +bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - dma_addr_t dma_addr; + trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force); if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) { dev_warn_ratelimited(dev, "Cannot do DMA to address %pa\n", phys); - return DMA_MAPPING_ERROR; + return false; } /* Oh well, have to allocate and map a bounce buffer. */ *phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start), *phys, size, dir, attrs); if (*phys == DMA_MAPPING_ERROR) - return DMA_MAPPING_ERROR; + return false; /* Ensure that the address returned is DMA'ble */ - dma_addr = __phys_to_dma(dev, *phys); - if (unlikely(!dma_capable(dev, dma_addr, size))) { + *dma_addr = __phys_to_dma(dev, *phys); + if (unlikely(!dma_capable(dev, *dma_addr, size))) { swiotlb_tbl_unmap_single(dev, *phys, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); - return DMA_MAPPING_ERROR; - } - - return dma_addr; -} - -/* - * Map a single buffer of the indicated size for DMA in streaming mode. The - * physical address to use is returned. - * - * Once the device is given the dma address, the device owns this memory until - * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed. - */ -dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - phys_addr_t phys = page_to_phys(page) + offset; - dma_addr_t dev_addr = phys_to_dma(dev, phys); - - BUG_ON(dir == DMA_NONE); - /* - * If the address happens to be in the device's DMA window, - * we can safely return the device addr and not worry about bounce - * buffering it. - */ - if (!dma_capable(dev, dev_addr, size) || - swiotlb_force == SWIOTLB_FORCE) { - trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); - dev_addr = swiotlb_bounce_page(dev, &phys, size, dir, attrs); + return false; } - if (!dev_is_dma_coherent(dev) && - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0 && - dev_addr != DMA_MAPPING_ERROR) - arch_sync_dma_for_device(dev, phys, size, dir); - - return dev_addr; -} - -/* - * Unmap a single streaming mode DMA translation. The dma_addr and size must - * match what was provided for in a previous swiotlb_map_page call. All - * other usages are undefined. - * - * After this call, reads by the cpu to the buffer are guaranteed to see - * whatever the device wrote there. - */ -void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); - - BUG_ON(dir == DMA_NONE); - - if (!dev_is_dma_coherent(hwdev) && - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - arch_sync_dma_for_cpu(hwdev, paddr, size, dir); - - if (is_swiotlb_buffer(paddr)) - swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs); -} - -/* - * Make physical memory consistent for a single streaming mode DMA translation - * after a transfer. - * - * If you perform a swiotlb_map_page() but wish to interrogate the buffer - * using the cpu, yet do not wish to teardown the dma mapping, you must - * call this function before doing so. At the next point you give the dma - * address back to the card, you must first perform a - * swiotlb_dma_sync_for_device, and then the device again owns the buffer - */ -static void -swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - enum dma_sync_target target) -{ - phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); - - BUG_ON(dir == DMA_NONE); - - if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_CPU) - arch_sync_dma_for_cpu(hwdev, paddr, size, dir); - - if (is_swiotlb_buffer(paddr)) - swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target); - - if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_DEVICE) - arch_sync_dma_for_device(hwdev, paddr, size, dir); -} - -void -swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir) -{ - swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU); -} - -void -swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir) -{ - swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE); -} - -/* - * Map a set of buffers described by scatterlist in streaming mode for DMA. - * This is the scatter-gather version of the above swiotlb_map_page - * interface. Here the scatter gather list elements are each tagged with the - * appropriate dma address and length. They are obtained via - * sg_dma_{address,length}(SG). - * - * Device ownership issues as mentioned above for swiotlb_map_page are the - * same here. - */ -int -swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, unsigned long attrs) -{ - struct scatterlist *sg; - int i; - - for_each_sg(sgl, sg, nelems, i) { - sg->dma_address = swiotlb_map_page(dev, sg_page(sg), sg->offset, - sg->length, dir, attrs); - if (sg->dma_address == DMA_MAPPING_ERROR) - goto out_error; - sg_dma_len(sg) = sg->length; - } - - return nelems; - -out_error: - swiotlb_unmap_sg_attrs(dev, sgl, i, dir, - attrs | DMA_ATTR_SKIP_CPU_SYNC); - sg_dma_len(sgl) = 0; - return 0; -} - -/* - * Unmap a set of streaming mode DMA translations. Again, cpu read rules - * concerning calls here are the same as for swiotlb_unmap_page() above. - */ -void -swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - unsigned long attrs) -{ - struct scatterlist *sg; - int i; - - BUG_ON(dir == DMA_NONE); - - for_each_sg(sgl, sg, nelems, i) - swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg), dir, - attrs); -} - -/* - * Make physical memory consistent for a set of streaming mode DMA translations - * after a transfer. - * - * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules - * and usage. - */ -static void -swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - enum dma_sync_target target) -{ - struct scatterlist *sg; - int i; - - for_each_sg(sgl, sg, nelems, i) - swiotlb_sync_single(hwdev, sg->dma_address, - sg_dma_len(sg), dir, target); -} - -void -swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir) -{ - swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU); -} - -void -swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir) -{ - swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE); + return true; } /* @@ -851,18 +660,3 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask) { return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask; } - -const struct dma_map_ops swiotlb_dma_ops = { - .alloc = dma_direct_alloc, - .free = dma_direct_free, - .sync_single_for_cpu = swiotlb_sync_single_for_cpu, - .sync_single_for_device = swiotlb_sync_single_for_device, - .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, - .sync_sg_for_device = swiotlb_sync_sg_for_device, - .map_sg = swiotlb_map_sg_attrs, - .unmap_sg = swiotlb_unmap_sg_attrs, - .map_page = swiotlb_map_page, - .unmap_page = swiotlb_unmap_page, - .dma_supported = dma_direct_supported, -}; -EXPORT_SYMBOL(swiotlb_dma_ops); -- cgit v1.2.3-59-g8ed1b From 356da6d0cde3323236977fce54c1f9612a742036 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Dec 2018 13:39:32 -0800 Subject: dma-mapping: bypass indirect calls for dma-direct Avoid expensive indirect calls in the fast path DMA mapping operations by directly calling the dma_direct_* ops if we are using the directly mapped DMA operations. Signed-off-by: Christoph Hellwig Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Tony Luck --- arch/alpha/include/asm/dma-mapping.h | 2 +- arch/arc/mm/cache.c | 2 +- arch/arm/include/asm/dma-mapping.h | 2 +- arch/arm/mm/dma-mapping-nommu.c | 14 +---- arch/arm64/mm/dma-mapping.c | 3 - arch/ia64/hp/common/hwsw_iommu.c | 2 +- arch/ia64/hp/common/sba_iommu.c | 4 +- arch/ia64/kernel/dma-mapping.c | 1 - arch/mips/include/asm/dma-mapping.h | 2 +- arch/parisc/kernel/setup.c | 4 -- arch/sparc/include/asm/dma-mapping.h | 4 +- arch/x86/kernel/pci-dma.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 2 +- drivers/iommu/amd_iommu.c | 13 +--- include/asm-generic/dma-mapping.h | 2 +- include/linux/dma-direct.h | 17 ------ include/linux/dma-mapping.h | 111 ++++++++++++++++++++++++++++++----- include/linux/dma-noncoherent.h | 5 +- kernel/dma/direct.c | 37 +++--------- kernel/dma/mapping.c | 40 ++++++++----- 20 files changed, 150 insertions(+), 119 deletions(-) (limited to 'kernel') diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h index 8beeafd4f68e..0ee6a5c99b16 100644 --- a/arch/alpha/include/asm/dma-mapping.h +++ b/arch/alpha/include/asm/dma-mapping.h @@ -7,7 +7,7 @@ extern const struct dma_map_ops alpha_pci_ops; static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { #ifdef CONFIG_ALPHA_JENSEN - return &dma_direct_ops; + return NULL; #else return &alpha_pci_ops; #endif diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index f2701c13a66b..e188bb3ede53 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -1280,7 +1280,7 @@ void __init arc_cache_init_master(void) /* * In case of IOC (say IOC+SLC case), pointers above could still be set * but end up not being relevant as the first function in chain is not - * called at all for @dma_direct_ops + * called at all for devices using coherent DMA. * arch_sync_dma_for_cpu() -> dma_cache_*() -> __dma_cache_*() */ } diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 965b7c846ecb..31d3b96f0f4b 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -18,7 +18,7 @@ extern const struct dma_map_ops arm_coherent_dma_ops; static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { - return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_direct_ops; + return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : NULL; } #ifdef __arch_page_to_dma diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c index 712416ecd8e6..f304b10e23a4 100644 --- a/arch/arm/mm/dma-mapping-nommu.c +++ b/arch/arm/mm/dma-mapping-nommu.c @@ -22,7 +22,7 @@ #include "dma.h" /* - * dma_direct_ops is used if + * The generic direct mapping code is used if * - MMU/MPU is off * - cpu is v7m w/o cache support * - device is coherent @@ -209,16 +209,9 @@ const struct dma_map_ops arm_nommu_dma_ops = { }; EXPORT_SYMBOL(arm_nommu_dma_ops); -static const struct dma_map_ops *arm_nommu_get_dma_map_ops(bool coherent) -{ - return coherent ? &dma_direct_ops : &arm_nommu_dma_ops; -} - void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent) { - const struct dma_map_ops *dma_ops; - if (IS_ENABLED(CONFIG_CPU_V7M)) { /* * Cache support for v7m is optional, so can be treated as @@ -234,7 +227,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, dev->archdata.dma_coherent = (get_cr() & CR_M) ? coherent : true; } - dma_ops = arm_nommu_get_dma_map_ops(dev->archdata.dma_coherent); - - set_dma_ops(dev, dma_ops); + if (!dev->archdata.dma_coherent) + set_dma_ops(dev, &arm_nommu_dma_ops); } diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index ab1e417204d0..95eda81e3f2d 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -462,9 +462,6 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent) { - if (!dev->dma_ops) - dev->dma_ops = &dma_direct_ops; - dev->dma_coherent = coherent; __iommu_setup_dma_ops(dev, dma_base, size, iommu); diff --git a/arch/ia64/hp/common/hwsw_iommu.c b/arch/ia64/hp/common/hwsw_iommu.c index f40ca499b246..8840ed97712f 100644 --- a/arch/ia64/hp/common/hwsw_iommu.c +++ b/arch/ia64/hp/common/hwsw_iommu.c @@ -38,7 +38,7 @@ static inline int use_swiotlb(struct device *dev) const struct dma_map_ops *hwsw_dma_get_ops(struct device *dev) { if (use_swiotlb(dev)) - return &dma_direct_ops; + return NULL; return &sba_dma_ops; } EXPORT_SYMBOL(hwsw_dma_get_ops); diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index 5ee74820a0f6..5a361e51cb1e 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -2078,7 +2078,7 @@ sba_init(void) * a successful kdump kernel boot is to use the swiotlb. */ if (is_kdump_kernel()) { - dma_ops = &dma_direct_ops; + dma_ops = NULL; if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0) panic("Unable to initialize software I/O TLB:" " Try machvec=dig boot option"); @@ -2100,7 +2100,7 @@ sba_init(void) * If we didn't find something sba_iommu can claim, we * need to setup the swiotlb and switch to the dig machvec. */ - dma_ops = &dma_direct_ops; + dma_ops = NULL; if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0) panic("Unable to find SBA IOMMU or initialize " "software I/O TLB: Try machvec=dig boot option"); diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c index 80cd3e1ea95a..ad7d9963de34 100644 --- a/arch/ia64/kernel/dma-mapping.c +++ b/arch/ia64/kernel/dma-mapping.c @@ -36,7 +36,6 @@ long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, void __init swiotlb_dma_init(void) { - dma_ops = &dma_direct_ops; swiotlb_init(1); } #endif diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h index 69f914667f3e..20dfaad3a55d 100644 --- a/arch/mips/include/asm/dma-mapping.h +++ b/arch/mips/include/asm/dma-mapping.h @@ -11,7 +11,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) #if defined(CONFIG_MACH_JAZZ) return &jazz_dma_ops; #else - return &dma_direct_ops; + return NULL; #endif } diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index cd227f1cf629..54818cd78bd0 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -99,10 +99,6 @@ void __init dma_ops_init(void) case pcxl2: pa7300lc_init(); - case pcxl: /* falls through */ - case pcxs: - case pcxt: - hppa_dma_ops = &dma_direct_ops; break; default: break; diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h index 55a44f08a9a4..ed32845bd2d2 100644 --- a/arch/sparc/include/asm/dma-mapping.h +++ b/arch/sparc/include/asm/dma-mapping.h @@ -12,11 +12,11 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { #ifdef CONFIG_SPARC_LEON if (sparc_cpu_model == sparc_leon) - return &dma_direct_ops; + return NULL; #endif #if defined(CONFIG_SPARC32) && defined(CONFIG_PCI) if (bus == &pci_bus_type) - return &dma_direct_ops; + return NULL; #endif return dma_ops; } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index f4562fcec681..d460998ae828 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -17,7 +17,7 @@ static bool disable_dac_quirk __read_mostly; -const struct dma_map_ops *dma_ops = &dma_direct_ops; +const struct dma_map_ops *dma_ops; EXPORT_SYMBOL(dma_ops); #ifdef CONFIG_IOMMU_DEBUG diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 61a84b958d67..50637f372e9f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -581,7 +581,7 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) dev_priv->map_mode = vmw_dma_map_populate; - if (dma_ops->sync_single_for_cpu) + if (dma_ops && dma_ops->sync_single_for_cpu) dev_priv->map_mode = vmw_dma_alloc_coherent; #ifdef CONFIG_SWIOTLB if (swiotlb_nr_tbl() == 0) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index c5d6c7c42b0a..567221cca13c 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2184,7 +2184,7 @@ static int amd_iommu_add_device(struct device *dev) dev_name(dev)); iommu_ignore_device(dev); - dev->dma_ops = &dma_direct_ops; + dev->dma_ops = NULL; goto out; } init_iommu_group(dev); @@ -2770,17 +2770,6 @@ int __init amd_iommu_init_dma_ops(void) swiotlb = (iommu_pass_through || sme_me_mask) ? 1 : 0; iommu_detected = 1; - /* - * In case we don't initialize SWIOTLB (actually the common case - * when AMD IOMMU is enabled and SME is not active), make sure there - * are global dma_ops set as a fall-back for devices not handled by - * this driver (for example non-PCI devices). When SME is active, - * make sure that swiotlb variable remains set so the global dma_ops - * continue to be SWIOTLB. - */ - if (!swiotlb) - dma_ops = &dma_direct_ops; - if (amd_iommu_unmap_flush) pr_info("AMD-Vi: IO/TLB flush on unmap enabled\n"); else diff --git a/include/asm-generic/dma-mapping.h b/include/asm-generic/dma-mapping.h index 880a292d792f..c13f46109e88 100644 --- a/include/asm-generic/dma-mapping.h +++ b/include/asm-generic/dma-mapping.h @@ -4,7 +4,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { - return &dma_direct_ops; + return NULL; } #endif /* _ASM_GENERIC_DMA_MAPPING_H */ diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 3b0a3ea3876d..b7338702592a 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -60,22 +60,5 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page); -dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs); -void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, unsigned long attrs); -int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, - enum dma_data_direction dir, unsigned long attrs); -void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, - int nents, enum dma_data_direction dir, unsigned long attrs); -void dma_direct_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir); -void dma_direct_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir); -void dma_direct_sync_single_for_cpu(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir); -void dma_direct_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir); int dma_direct_supported(struct device *dev, u64 mask); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 269ee27fc3d9..f422aec0f53c 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -134,7 +134,6 @@ struct dma_map_ops { #define DMA_MAPPING_ERROR (~(dma_addr_t)0) -extern const struct dma_map_ops dma_direct_ops; extern const struct dma_map_ops dma_virt_ops; extern const struct dma_map_ops dma_dummy_ops; @@ -222,6 +221,69 @@ static inline const struct dma_map_ops *get_dma_ops(struct device *dev) } #endif +static inline bool dma_is_direct(const struct dma_map_ops *ops) +{ + return likely(!ops); +} + +/* + * All the dma_direct_* declarations are here just for the indirect call bypass, + * and must not be used directly drivers! + */ +dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs); +int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, + enum dma_data_direction dir, unsigned long attrs); + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir); +void dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); +#else +static inline void dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ +} +#endif + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir); +void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); +#else +static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ +} +static inline void dma_direct_unmap_sg(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir, + unsigned long attrs) +{ +} +static inline void dma_direct_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ +} +#endif + static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, @@ -232,9 +294,12 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, BUG_ON(!valid_dma_direction(dir)); debug_dma_map_single(dev, ptr, size); - addr = ops->map_page(dev, virt_to_page(ptr), - offset_in_page(ptr), size, - dir, attrs); + if (dma_is_direct(ops)) + addr = dma_direct_map_page(dev, virt_to_page(ptr), + offset_in_page(ptr), size, dir, attrs); + else + addr = ops->map_page(dev, virt_to_page(ptr), + offset_in_page(ptr), size, dir, attrs); debug_dma_map_page(dev, virt_to_page(ptr), offset_in_page(ptr), size, dir, addr, true); @@ -249,7 +314,9 @@ static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->unmap_page) + if (dma_is_direct(ops)) + dma_direct_unmap_page(dev, addr, size, dir, attrs); + else if (ops->unmap_page) ops->unmap_page(dev, addr, size, dir, attrs); debug_dma_unmap_page(dev, addr, size, dir, true); } @@ -272,7 +339,10 @@ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int ents; BUG_ON(!valid_dma_direction(dir)); - ents = ops->map_sg(dev, sg, nents, dir, attrs); + if (dma_is_direct(ops)) + ents = dma_direct_map_sg(dev, sg, nents, dir, attrs); + else + ents = ops->map_sg(dev, sg, nents, dir, attrs); BUG_ON(ents < 0); debug_dma_map_sg(dev, sg, nents, ents, dir); @@ -287,7 +357,9 @@ static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg BUG_ON(!valid_dma_direction(dir)); debug_dma_unmap_sg(dev, sg, nents, dir); - if (ops->unmap_sg) + if (dma_is_direct(ops)) + dma_direct_unmap_sg(dev, sg, nents, dir, attrs); + else if (ops->unmap_sg) ops->unmap_sg(dev, sg, nents, dir, attrs); } @@ -301,7 +373,10 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev, dma_addr_t addr; BUG_ON(!valid_dma_direction(dir)); - addr = ops->map_page(dev, page, offset, size, dir, attrs); + if (dma_is_direct(ops)) + addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); + else + addr = ops->map_page(dev, page, offset, size, dir, attrs); debug_dma_map_page(dev, page, offset, size, dir, addr, false); return addr; @@ -322,7 +397,7 @@ static inline dma_addr_t dma_map_resource(struct device *dev, BUG_ON(pfn_valid(PHYS_PFN(phys_addr))); addr = phys_addr; - if (ops->map_resource) + if (ops && ops->map_resource) addr = ops->map_resource(dev, phys_addr, size, dir, attrs); debug_dma_map_resource(dev, phys_addr, size, dir, addr); @@ -337,7 +412,7 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->unmap_resource) + if (ops && ops->unmap_resource) ops->unmap_resource(dev, addr, size, dir, attrs); debug_dma_unmap_resource(dev, addr, size, dir); } @@ -349,7 +424,9 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->sync_single_for_cpu) + if (dma_is_direct(ops)) + dma_direct_sync_single_for_cpu(dev, addr, size, dir); + else if (ops->sync_single_for_cpu) ops->sync_single_for_cpu(dev, addr, size, dir); debug_dma_sync_single_for_cpu(dev, addr, size, dir); } @@ -368,7 +445,9 @@ static inline void dma_sync_single_for_device(struct device *dev, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->sync_single_for_device) + if (dma_is_direct(ops)) + dma_direct_sync_single_for_device(dev, addr, size, dir); + else if (ops->sync_single_for_device) ops->sync_single_for_device(dev, addr, size, dir); debug_dma_sync_single_for_device(dev, addr, size, dir); } @@ -387,7 +466,9 @@ dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->sync_sg_for_cpu) + if (dma_is_direct(ops)) + dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir); + else if (ops->sync_sg_for_cpu) ops->sync_sg_for_cpu(dev, sg, nelems, dir); debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir); } @@ -399,7 +480,9 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->sync_sg_for_device) + if (dma_is_direct(ops)) + dma_direct_sync_sg_for_device(dev, sg, nelems, dir); + else if (ops->sync_sg_for_device) ops->sync_sg_for_device(dev, sg, nelems, dir); debug_dma_sync_sg_for_device(dev, sg, nelems, dir); diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 306557331d7d..69b36ed31a99 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -38,7 +38,10 @@ pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction); #else -#define arch_dma_cache_sync NULL +static inline void arch_dma_cache_sync(struct device *dev, void *vaddr, + size_t size, enum dma_data_direction direction) +{ +} #endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */ #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 85d8286a0ba2..79da61b49fa4 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -223,6 +223,7 @@ void dma_direct_sync_single_for_device(struct device *dev, if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_device(dev, paddr, size, dir); } +EXPORT_SYMBOL(dma_direct_sync_single_for_device); void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) @@ -240,6 +241,7 @@ void dma_direct_sync_sg_for_device(struct device *dev, dir); } } +EXPORT_SYMBOL(dma_direct_sync_sg_for_device); #endif #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ @@ -258,6 +260,7 @@ void dma_direct_sync_single_for_cpu(struct device *dev, if (unlikely(is_swiotlb_buffer(paddr))) swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); } +EXPORT_SYMBOL(dma_direct_sync_single_for_cpu); void dma_direct_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) @@ -277,6 +280,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev, if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_cpu_all(dev); } +EXPORT_SYMBOL(dma_direct_sync_sg_for_cpu); void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) @@ -289,6 +293,7 @@ void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, if (unlikely(is_swiotlb_buffer(phys))) swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } +EXPORT_SYMBOL(dma_direct_unmap_page); void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs) @@ -300,11 +305,7 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir, attrs); } -#else -void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ -} +EXPORT_SYMBOL(dma_direct_unmap_sg); #endif static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr, @@ -331,6 +332,7 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, arch_sync_dma_for_device(dev, phys, size, dir); return dma_addr; } +EXPORT_SYMBOL(dma_direct_map_page); int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs) @@ -352,6 +354,7 @@ out_unmap: dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); return 0; } +EXPORT_SYMBOL(dma_direct_map_sg); /* * Because 32-bit DMA masks are so common we expect every architecture to be @@ -372,27 +375,3 @@ int dma_direct_supported(struct device *dev, u64 mask) return mask >= phys_to_dma(dev, min_mask); } - -const struct dma_map_ops dma_direct_ops = { - .alloc = dma_direct_alloc, - .free = dma_direct_free, - .map_page = dma_direct_map_page, - .map_sg = dma_direct_map_sg, -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ - defined(CONFIG_SWIOTLB) - .sync_single_for_device = dma_direct_sync_single_for_device, - .sync_sg_for_device = dma_direct_sync_sg_for_device, -#endif -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ - defined(CONFIG_SWIOTLB) - .sync_single_for_cpu = dma_direct_sync_single_for_cpu, - .sync_sg_for_cpu = dma_direct_sync_sg_for_cpu, - .unmap_page = dma_direct_unmap_page, - .unmap_sg = dma_direct_unmap_sg, -#endif - .get_required_mask = dma_direct_get_required_mask, - .dma_supported = dma_direct_supported, - .cache_sync = arch_dma_cache_sync, -}; -EXPORT_SYMBOL(dma_direct_ops); diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 0b18cfbdde95..fc84c81029d9 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -7,6 +7,7 @@ */ #include /* for max_pfn */ #include +#include #include #include #include @@ -229,8 +230,8 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); - BUG_ON(!ops); - if (ops->get_sgtable) + + if (!dma_is_direct(ops) && ops->get_sgtable) return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs); return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size, @@ -293,8 +294,8 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); - BUG_ON(!ops); - if (ops->mmap) + + if (!dma_is_direct(ops) && ops->mmap) return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs); return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); } @@ -324,6 +325,8 @@ u64 dma_get_required_mask(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); + if (dma_is_direct(ops)) + return dma_direct_get_required_mask(dev); if (ops->get_required_mask) return ops->get_required_mask(dev); return dma_default_get_required_mask(dev); @@ -341,7 +344,6 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, const struct dma_map_ops *ops = get_dma_ops(dev); void *cpu_addr; - BUG_ON(!ops); WARN_ON_ONCE(dev && !dev->coherent_dma_mask); if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr)) @@ -352,10 +354,14 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, if (!arch_dma_alloc_attrs(&dev)) return NULL; - if (!ops->alloc) + + if (dma_is_direct(ops)) + cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs); + else if (ops->alloc) + cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs); + else return NULL; - cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs); debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr); return cpu_addr; } @@ -366,8 +372,6 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, { const struct dma_map_ops *ops = get_dma_ops(dev); - BUG_ON(!ops); - if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr)) return; /* @@ -379,11 +383,14 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, */ WARN_ON(irqs_disabled()); - if (!ops->free || !cpu_addr) + if (!cpu_addr) return; debug_dma_free_coherent(dev, size, cpu_addr, dma_handle); - ops->free(dev, size, cpu_addr, dma_handle, attrs); + if (dma_is_direct(ops)) + dma_direct_free(dev, size, cpu_addr, dma_handle, attrs); + else if (ops->free) + ops->free(dev, size, cpu_addr, dma_handle, attrs); } EXPORT_SYMBOL(dma_free_attrs); @@ -397,9 +404,9 @@ int dma_supported(struct device *dev, u64 mask) { const struct dma_map_ops *ops = get_dma_ops(dev); - if (!ops) - return 0; - if (!ops->dma_supported) + if (dma_is_direct(ops)) + return dma_direct_supported(dev, mask); + if (ops->dma_supported) return 1; return ops->dma_supported(dev, mask); } @@ -437,7 +444,10 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops->cache_sync) + + if (dma_is_direct(ops)) + arch_dma_cache_sync(dev, vaddr, size, dir); + else if (ops->cache_sync) ops->cache_sync(dev, vaddr, size, dir); } EXPORT_SYMBOL(dma_cache_sync); -- cgit v1.2.3-59-g8ed1b 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] --- arch/alpha/kernel/pci_iommu.c | 2 +- arch/arc/mm/dma.c | 2 +- arch/c6x/mm/dma-coherent.c | 5 ++++- arch/m68k/kernel/dma.c | 2 +- arch/microblaze/mm/consistent.c | 2 +- arch/openrisc/kernel/dma.c | 2 +- arch/parisc/kernel/pci-dma.c | 4 ++-- arch/s390/pci/pci_dma.c | 2 +- arch/sparc/kernel/ioport.c | 2 +- arch/sparc/mm/io-unit.c | 2 +- arch/sparc/mm/iommu.c | 2 +- arch/xtensa/kernel/pci-dma.c | 2 +- drivers/misc/mic/host/mic_boot.c | 2 +- kernel/dma/virt.c | 2 +- 14 files changed, 18 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index e1716e0d92fd..aa0f50d0f823 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -443,7 +443,7 @@ static void *alpha_pci_alloc_coherent(struct device *dev, size_t size, gfp &= ~GFP_DMA; try_again: - cpu_addr = (void *)__get_free_pages(gfp, order); + cpu_addr = (void *)__get_free_pages(gfp | __GFP_ZERO, order); if (! cpu_addr) { printk(KERN_INFO "pci_alloc_consistent: " "get_free_pages failed from %pf\n", diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index db203ff69ccf..1525ac00fd02 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -33,7 +33,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, */ BUG_ON(gfp & __GFP_HIGHMEM); - page = alloc_pages(gfp, order); + page = alloc_pages(gfp | __GFP_ZERO, order); if (!page) return NULL; diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c index 01305c787201..75b79571732c 100644 --- a/arch/c6x/mm/dma-coherent.c +++ b/arch/c6x/mm/dma-coherent.c @@ -78,6 +78,7 @@ static void __free_dma_pages(u32 addr, int order) void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, unsigned long attrs) { + void *ret; u32 paddr; int order; @@ -94,7 +95,9 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, if (!paddr) return NULL; - return phys_to_virt(paddr); + ret = phys_to_virt(paddr); + memset(ret, 0, 1 << order); + return ret; } /* diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c index e99993c57d6b..b4aa853051bd 100644 --- a/arch/m68k/kernel/dma.c +++ b/arch/m68k/kernel/dma.c @@ -32,7 +32,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, size = PAGE_ALIGN(size); order = get_order(size); - page = alloc_pages(flag, order); + page = alloc_pages(flag | __GFP_ZERO, order); if (!page) return NULL; diff --git a/arch/microblaze/mm/consistent.c b/arch/microblaze/mm/consistent.c index 45e0a1aa9357..3002cbca3059 100644 --- a/arch/microblaze/mm/consistent.c +++ b/arch/microblaze/mm/consistent.c @@ -81,7 +81,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, size = PAGE_ALIGN(size); order = get_order(size); - vaddr = __get_free_pages(gfp, order); + vaddr = __get_free_pages(gfp | __GFP_ZERO, order); if (!vaddr) return NULL; diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index 159336adfa2f..f79457cb3741 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -89,7 +89,7 @@ arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, .mm = &init_mm }; - page = alloc_pages_exact(size, gfp); + page = alloc_pages_exact(size, gfp | __GFP_ZERO); if (!page) return NULL; diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index 04c48f1ef3fb..239162355b58 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -404,7 +404,7 @@ static void *pcxl_dma_alloc(struct device *dev, size_t size, order = get_order(size); size = 1 << (order + PAGE_SHIFT); vaddr = pcxl_alloc_range(size); - paddr = __get_free_pages(flag, order); + paddr = __get_free_pages(flag | __GFP_ZERO, order); flush_kernel_dcache_range(paddr, size); paddr = __pa(paddr); map_uncached_pages(vaddr, size, paddr); @@ -429,7 +429,7 @@ static void *pcx_dma_alloc(struct device *dev, size_t size, if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) return NULL; - addr = (void *)__get_free_pages(flag, get_order(size)); + addr = (void *)__get_free_pages(flag | __GFP_ZERO, get_order(size)); if (addr) *dma_handle = (dma_addr_t)virt_to_phys(addr); diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 346ba382193a..9e52d1527f71 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -404,7 +404,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size, dma_addr_t map; size = PAGE_ALIGN(size); - page = alloc_pages(flag, get_order(size)); + page = alloc_pages(flag | __GFP_ZERO, get_order(size)); if (!page) return NULL; diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index baa235652c27..f89603855f1e 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -325,7 +325,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, return NULL; size = PAGE_ALIGN(size); - va = (void *) __get_free_pages(gfp, get_order(size)); + va = (void *) __get_free_pages(gfp | __GFP_ZERO, get_order(size)); if (!va) { printk("%s: no %zd pages\n", __func__, size >> PAGE_SHIFT); return NULL; diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c index 91be13935d40..f770ee7229d8 100644 --- a/arch/sparc/mm/io-unit.c +++ b/arch/sparc/mm/io-unit.c @@ -224,7 +224,7 @@ static void *iounit_alloc(struct device *dev, size_t len, return NULL; len = PAGE_ALIGN(len); - va = __get_free_pages(gfp, get_order(len)); + va = __get_free_pages(gfp | __GFP_ZERO, get_order(len)); if (!va) return NULL; diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c index fb771a634452..e8d5d73ca40d 100644 --- a/arch/sparc/mm/iommu.c +++ b/arch/sparc/mm/iommu.c @@ -344,7 +344,7 @@ static void *sbus_iommu_alloc(struct device *dev, size_t len, return NULL; len = PAGE_ALIGN(len); - va = __get_free_pages(gfp, get_order(len)); + va = __get_free_pages(gfp | __GFP_ZERO, get_order(len)); if (va == 0) return NULL; diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c index 1fc138b6bc0a..9171bff76fc4 100644 --- a/arch/xtensa/kernel/pci-dma.c +++ b/arch/xtensa/kernel/pci-dma.c @@ -160,7 +160,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, flag & __GFP_NOWARN); if (!page) - page = alloc_pages(flag, get_order(size)); + page = alloc_pages(flag | __GFP_ZERO, get_order(size)); if (!page) return NULL; diff --git a/drivers/misc/mic/host/mic_boot.c b/drivers/misc/mic/host/mic_boot.c index c327985c9523..6479435ac96b 100644 --- a/drivers/misc/mic/host/mic_boot.c +++ b/drivers/misc/mic/host/mic_boot.c @@ -149,7 +149,7 @@ static void *__mic_dma_alloc(struct device *dev, size_t size, struct scif_hw_dev *scdev = dev_get_drvdata(dev); struct mic_device *mdev = scdev_to_mdev(scdev); dma_addr_t tmp; - void *va = kmalloc(size, gfp); + void *va = kmalloc(size, gfp | __GFP_ZERO); if (va) { tmp = mic_map_single(mdev, va, size); 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 v1.2.3-59-g8ed1b 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') 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 v1.2.3-59-g8ed1b