diff options
Diffstat (limited to 'kernel/dma')
| -rw-r--r-- | kernel/dma/Kconfig | 16 | ||||
| -rw-r--r-- | kernel/dma/Makefile | 1 | ||||
| -rw-r--r-- | kernel/dma/contiguous.c | 6 | ||||
| -rw-r--r-- | kernel/dma/debug.c | 16 | ||||
| -rw-r--r-- | kernel/dma/direct.c | 224 | ||||
| -rw-r--r-- | kernel/dma/mapping.c | 71 | ||||
| -rw-r--r-- | kernel/dma/noncoherent.c | 106 | ||||
| -rw-r--r-- | kernel/dma/swiotlb.c | 334 |
8 files changed, 312 insertions, 462 deletions
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 1b1d63b3634b..645c7a2ecde8 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -13,6 +13,9 @@ config NEED_DMA_MAP_STATE config ARCH_DMA_ADDR_T_64BIT def_bool 64BIT || PHYS_ADDR_T_64BIT +config ARCH_HAS_DMA_COHERENCE_H + bool + config HAVE_GENERIC_DMA_COHERENT bool @@ -26,22 +29,19 @@ config ARCH_HAS_SYNC_DMA_FOR_CPU config ARCH_HAS_SYNC_DMA_FOR_CPU_ALL bool -config DMA_DIRECT_OPS +config ARCH_HAS_DMA_COHERENT_TO_PFN bool - depends on HAS_DMA -config DMA_NONCOHERENT_OPS +config ARCH_HAS_DMA_MMAP_PGPROT bool - depends on HAS_DMA - select DMA_DIRECT_OPS -config DMA_NONCOHERENT_MMAP +config DMA_DIRECT_OPS bool - depends on DMA_NONCOHERENT_OPS + depends on HAS_DMA config DMA_NONCOHERENT_CACHE_SYNC bool - depends on DMA_NONCOHERENT_OPS + depends on DMA_DIRECT_OPS config DMA_VIRT_OPS bool diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile index 6de44e4eb454..7d581e4eea4a 100644 --- a/kernel/dma/Makefile +++ b/kernel/dma/Makefile @@ -4,7 +4,6 @@ obj-$(CONFIG_HAS_DMA) += mapping.o obj-$(CONFIG_DMA_CMA) += contiguous.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o obj-$(CONFIG_DMA_DIRECT_OPS) += direct.o -obj-$(CONFIG_DMA_NONCOHERENT_OPS) += noncoherent.o obj-$(CONFIG_DMA_VIRT_OPS) += virt.o obj-$(CONFIG_DMA_API_DEBUG) += debug.o obj-$(CONFIG_SWIOTLB) += swiotlb.o diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index 286d82329eb0..b2a87905846d 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -49,7 +49,11 @@ static phys_addr_t limit_cmdline; static int __init early_cma(char *p) { - pr_debug("%s(%s)\n", __func__, p); + if (!p) { + pr_err("Config string not provided\n"); + return -EINVAL; + } + size_cmdline = memparse(p, &p); if (*p != '@') return 0; diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index c007d25bee09..231ca4628062 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -1312,6 +1312,22 @@ static void check_sg_segment(struct device *dev, struct scatterlist *sg) #endif } +void debug_dma_map_single(struct device *dev, const void *addr, + unsigned long len) +{ + if (unlikely(dma_debug_disabled())) + return; + + if (!virt_addr_valid(addr)) + err_printk(dev, NULL, "DMA-API: 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", + addr, len); +} +EXPORT_SYMBOL(debug_dma_map_single); + void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, int direction, dma_addr_t dma_addr, bool map_single) diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index de87b0282e74..22a12ab5a5e9 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -1,18 +1,19 @@ // SPDX-License-Identifier: GPL-2.0 /* - * DMA operations that map physical memory directly without using an IOMMU or - * flushing caches. + * Copyright (C) 2018 Christoph Hellwig. + * + * DMA operations that map physical memory directly without using an IOMMU. */ +#include <linux/memblock.h> /* for max_pfn */ #include <linux/export.h> #include <linux/mm.h> #include <linux/dma-direct.h> #include <linux/scatterlist.h> #include <linux/dma-contiguous.h> +#include <linux/dma-noncoherent.h> #include <linux/pfn.h> #include <linux/set_memory.h> -#define DIRECT_MAPPING_ERROR 0 - /* * Most architectures use ZONE_DMA for the first 16 Megabytes, but * some use it for entirely different regions: @@ -41,40 +42,83 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size, return false; } - if (*dev->dma_mask >= DMA_BIT_MASK(32)) { + if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) { dev_err(dev, - "%s: overflow %pad+%zu of device mask %llx\n", - caller, &dma_addr, size, *dev->dma_mask); + "%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; } return true; } +static inline dma_addr_t phys_to_dma_direct(struct device *dev, + phys_addr_t phys) +{ + if (force_dma_unencrypted()) + return __phys_to_dma(dev, phys); + return phys_to_dma(dev, phys); +} + +u64 dma_direct_get_required_mask(struct device *dev) +{ + u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT); + + if (dev->bus_dma_mask && dev->bus_dma_mask < max_dma) + max_dma = dev->bus_dma_mask; + + return (1ULL << (fls64(max_dma) - 1)) * 2 - 1; +} + +static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, + u64 *phys_mask) +{ + if (dev->bus_dma_mask && dev->bus_dma_mask < dma_mask) + dma_mask = dev->bus_dma_mask; + + if (force_dma_unencrypted()) + *phys_mask = __dma_to_phys(dev, dma_mask); + else + *phys_mask = dma_to_phys(dev, dma_mask); + + /* + * Optimistically try the zone that the physical address mask falls + * into first. If that returns memory that isn't actually addressable + * we will fallback to the next lower zone and try again. + * + * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding + * zones. + */ + if (*phys_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) + return GFP_DMA; + if (*phys_mask <= DMA_BIT_MASK(32)) + return GFP_DMA32; + return 0; +} + static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) { - dma_addr_t addr = force_dma_unencrypted() ? - __phys_to_dma(dev, phys) : phys_to_dma(dev, phys); - return addr + size - 1 <= dev->coherent_dma_mask; + return phys_to_dma_direct(dev, phys) + size - 1 <= + min_not_zero(dev->coherent_dma_mask, dev->bus_dma_mask); } -void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs) +void *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; + /* we always manually zero the memory once we are done: */ gfp &= ~__GFP_ZERO; - - /* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */ - if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) - gfp |= GFP_DMA; - if (dev->coherent_dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) - gfp |= GFP_DMA32; - + gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, + &phys_mask); again: /* CMA can be used only in the context which permits sleeping */ if (gfpflags_allow_blocking(gfp)) { @@ -93,15 +137,14 @@ again: page = NULL; if (IS_ENABLED(CONFIG_ZONE_DMA32) && - dev->coherent_dma_mask < DMA_BIT_MASK(64) && + phys_mask < DMA_BIT_MASK(64) && !(gfp & (GFP_DMA32 | GFP_DMA))) { gfp |= GFP_DMA32; goto again; } if (IS_ENABLED(CONFIG_ZONE_DMA) && - dev->coherent_dma_mask < DMA_BIT_MASK(32) && - !(gfp & GFP_DMA)) { + phys_mask < DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) { gfp = (gfp & ~GFP_DMA32) | GFP_DMA; goto again; } @@ -124,7 +167,7 @@ again: * 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(struct device *dev, size_t size, void *cpu_addr, +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; @@ -136,14 +179,96 @@ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, free_pages((unsigned long)cpu_addr, page_order); } +void *dma_direct_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +{ + if (!dev_is_dma_coherent(dev)) + return arch_dma_alloc(dev, size, dma_handle, gfp, attrs); + return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs); +} + +void dma_direct_free(struct device *dev, size_t size, + void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) +{ + if (!dev_is_dma_coherent(dev)) + arch_dma_free(dev, size, cpu_addr, dma_addr, attrs); + else + dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs); +} + +static 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); +} + +static 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) + arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); +} + +#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, + 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); +} + +static 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) + arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); + arch_sync_dma_for_cpu_all(dev); +} + +static void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_direct_sync_single_for_cpu(dev, addr, size, dir); +} + +static 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 + 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) { - dma_addr_t dma_addr = phys_to_dma(dev, page_to_phys(page)) + offset; + 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__)) return DIRECT_MAPPING_ERROR; + + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_direct_sync_single_for_device(dev, dma_addr, size, dir); return dma_addr; } @@ -162,31 +287,29 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, 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; } +/* + * Because 32-bit DMA masks are so common we expect every architecture to be + * able to satisfy them - either by not supporting more physical memory, or by + * providing a ZONE_DMA32. If neither is the case, the architecture needs to + * use an IOMMU instead of the direct mapping. + */ int dma_direct_supported(struct device *dev, u64 mask) { -#ifdef CONFIG_ZONE_DMA - if (mask < phys_to_dma(dev, DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))) - return 0; -#else - /* - * Because 32-bit DMA masks are so common we expect every architecture - * to be able to satisfy them - either by not supporting more physical - * memory, or by providing a ZONE_DMA32. If neither is the case, the - * architecture needs to use an IOMMU instead of the direct mapping. - */ - if (mask < phys_to_dma(dev, DMA_BIT_MASK(32))) - return 0; -#endif - /* - * Upstream PCI/PCIe bridges or SoC interconnects may not carry - * as many DMA address bits as the device itself supports. - */ - if (dev->bus_dma_mask && mask > dev->bus_dma_mask) - return 0; - return 1; + u64 min_mask; + + if (IS_ENABLED(CONFIG_ZONE_DMA)) + min_mask = DMA_BIT_MASK(ARCH_ZONE_DMA_BITS); + else + min_mask = DMA_BIT_MASK(32); + + min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT); + + return mask >= phys_to_dma(dev, min_mask); } int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr) @@ -199,7 +322,20 @@ 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) + .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) + .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, .mapping_error = dma_direct_mapping_error, + .cache_sync = arch_dma_cache_sync, }; EXPORT_SYMBOL(dma_direct_ops); diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index d2a92ddaac4d..58dec7a92b7b 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -7,7 +7,7 @@ */ #include <linux/acpi.h> -#include <linux/dma-mapping.h> +#include <linux/dma-noncoherent.h> #include <linux/export.h> #include <linux/gfp.h> #include <linux/of_device.h> @@ -202,17 +202,26 @@ EXPORT_SYMBOL(dmam_release_declared_memory); * Create scatter-list for the already allocated DMA buffer. */ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t handle, size_t size) + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) { - struct page *page = virt_to_page(cpu_addr); + struct page *page; int ret; - ret = sg_alloc_table(sgt, 1, GFP_KERNEL); - if (unlikely(ret)) - return ret; + if (!dev_is_dma_coherent(dev)) { + if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)) + return -ENXIO; - sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); - return 0; + page = pfn_to_page(arch_dma_coherent_to_pfn(dev, cpu_addr, + dma_addr)); + } else { + page = virt_to_page(cpu_addr); + } + + ret = sg_alloc_table(sgt, 1, GFP_KERNEL); + if (!ret) + sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); + return ret; } EXPORT_SYMBOL(dma_common_get_sgtable); @@ -220,27 +229,37 @@ EXPORT_SYMBOL(dma_common_get_sgtable); * Create userspace mapping for the DMA-coherent memory. */ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size) + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) { - int ret = -ENXIO; #ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP unsigned long user_count = vma_pages(vma); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; + unsigned long pfn; + int ret = -ENXIO; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs); if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) return ret; - if (off < count && user_count <= (count - off)) - ret = remap_pfn_range(vma, vma->vm_start, - page_to_pfn(virt_to_page(cpu_addr)) + off, - user_count << PAGE_SHIFT, - vma->vm_page_prot); -#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */ + if (off >= count || user_count > count - off) + return -ENXIO; - return ret; + if (!dev_is_dma_coherent(dev)) { + if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)) + return -ENXIO; + pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr); + } else { + pfn = page_to_pfn(virt_to_page(cpu_addr)); + } + + return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff, + user_count << PAGE_SHIFT, vma->vm_page_prot); +#else + return -ENXIO; +#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */ } EXPORT_SYMBOL(dma_common_mmap); @@ -327,19 +346,3 @@ void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags) vunmap(cpu_addr); } #endif - -/* - * enables DMA API use for a device - */ -int dma_configure(struct device *dev) -{ - if (dev->bus->dma_configure) - return dev->bus->dma_configure(dev); - return 0; -} - -void dma_deconfigure(struct device *dev) -{ - of_dma_deconfigure(dev); - acpi_dma_deconfigure(dev); -} diff --git a/kernel/dma/noncoherent.c b/kernel/dma/noncoherent.c deleted file mode 100644 index 031fe235d958..000000000000 --- a/kernel/dma/noncoherent.c +++ /dev/null @@ -1,106 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2018 Christoph Hellwig. - * - * DMA operations that map physical memory directly without providing cache - * coherence. - */ -#include <linux/export.h> -#include <linux/mm.h> -#include <linux/dma-direct.h> -#include <linux/dma-noncoherent.h> -#include <linux/scatterlist.h> - -static void dma_noncoherent_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ - arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir); -} - -static void dma_noncoherent_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir) -{ - struct scatterlist *sg; - int i; - - for_each_sg(sgl, sg, nents, i) - arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); -} - -static dma_addr_t dma_noncoherent_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t addr; - - addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); - if (!dma_mapping_error(dev, addr) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - arch_sync_dma_for_device(dev, page_to_phys(page) + offset, - size, dir); - return addr; -} - -static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ - nents = dma_direct_map_sg(dev, sgl, nents, dir, attrs); - if (nents > 0 && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_noncoherent_sync_sg_for_device(dev, sgl, nents, dir); - return nents; -} - -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) -static void dma_noncoherent_sync_single_for_cpu(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ - arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir); - arch_sync_dma_for_cpu_all(dev); -} - -static void dma_noncoherent_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir) -{ - struct scatterlist *sg; - int i; - - 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); -} - -static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_noncoherent_sync_single_for_cpu(dev, addr, size, dir); -} - -static void dma_noncoherent_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_noncoherent_sync_sg_for_cpu(dev, sgl, nents, dir); -} -#endif - -const struct dma_map_ops dma_noncoherent_ops = { - .alloc = arch_dma_alloc, - .free = arch_dma_free, - .mmap = arch_dma_mmap, - .sync_single_for_device = dma_noncoherent_sync_single_for_device, - .sync_sg_for_device = dma_noncoherent_sync_sg_for_device, - .map_page = dma_noncoherent_map_page, - .map_sg = dma_noncoherent_map_sg, -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) - .sync_single_for_cpu = dma_noncoherent_sync_single_for_cpu, - .sync_sg_for_cpu = dma_noncoherent_sync_sg_for_cpu, - .unmap_page = dma_noncoherent_unmap_page, - .unmap_sg = dma_noncoherent_unmap_sg, -#endif - .dma_supported = dma_direct_supported, - .mapping_error = dma_direct_mapping_error, - .cache_sync = arch_dma_cache_sync, -}; -EXPORT_SYMBOL(dma_noncoherent_ops); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 4f8a6dbf0b60..5731daa09a32 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -21,6 +21,7 @@ #include <linux/cache.h> #include <linux/dma-direct.h> +#include <linux/dma-noncoherent.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/spinlock.h> @@ -39,7 +40,7 @@ #include <asm/dma.h> #include <linux/init.h> -#include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/iommu-helper.h> #define CREATE_TRACE_POINTS @@ -73,13 +74,6 @@ static phys_addr_t io_tlb_start, io_tlb_end; static unsigned long io_tlb_nslabs; /* - * When the IOMMU overflows we return a fallback buffer. This sets the size. - */ -static unsigned long io_tlb_overflow = 32*1024; - -static phys_addr_t io_tlb_overflow_buffer; - -/* * This is a free list describing the number of free entries available from * each index */ @@ -126,7 +120,6 @@ setup_io_tlb_npages(char *str) return 0; } early_param("swiotlb", setup_io_tlb_npages); -/* make io_tlb_overflow tunable too? */ unsigned long swiotlb_nr_tbl(void) { @@ -194,16 +187,10 @@ void __init swiotlb_update_mem_attributes(void) bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT); set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); memset(vaddr, 0, bytes); - - vaddr = phys_to_virt(io_tlb_overflow_buffer); - bytes = PAGE_ALIGN(io_tlb_overflow); - set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); - memset(vaddr, 0, bytes); } int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) { - void *v_overflow_buffer; unsigned long i, bytes; bytes = nslabs << IO_TLB_SHIFT; @@ -213,25 +200,14 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) io_tlb_end = io_tlb_start + bytes; /* - * Get the overflow emergency buffer - */ - v_overflow_buffer = memblock_virt_alloc_low_nopanic( - PAGE_ALIGN(io_tlb_overflow), - PAGE_SIZE); - if (!v_overflow_buffer) - return -ENOMEM; - - io_tlb_overflow_buffer = __pa(v_overflow_buffer); - - /* * Allocate and initialize the free list array. This array is used * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE * between io_tlb_start and io_tlb_end. */ - io_tlb_list = memblock_virt_alloc( + io_tlb_list = memblock_alloc( PAGE_ALIGN(io_tlb_nslabs * sizeof(int)), PAGE_SIZE); - io_tlb_orig_addr = memblock_virt_alloc( + io_tlb_orig_addr = memblock_alloc( PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)), PAGE_SIZE); for (i = 0; i < io_tlb_nslabs; i++) { @@ -266,7 +242,7 @@ swiotlb_init(int verbose) bytes = io_tlb_nslabs << IO_TLB_SHIFT; /* Get IO TLB memory from the low pages */ - vstart = memblock_virt_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE); + vstart = memblock_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE); if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) return; @@ -330,7 +306,6 @@ int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) { unsigned long i, bytes; - unsigned char *v_overflow_buffer; bytes = nslabs << IO_TLB_SHIFT; @@ -342,19 +317,6 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) memset(tlb, 0, bytes); /* - * Get the overflow emergency buffer - */ - v_overflow_buffer = (void *)__get_free_pages(GFP_DMA, - get_order(io_tlb_overflow)); - if (!v_overflow_buffer) - goto cleanup2; - - set_memory_decrypted((unsigned long)v_overflow_buffer, - io_tlb_overflow >> PAGE_SHIFT); - memset(v_overflow_buffer, 0, io_tlb_overflow); - io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer); - - /* * Allocate and initialize the free list array. This array is used * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE * between io_tlb_start and io_tlb_end. @@ -390,10 +352,6 @@ cleanup4: sizeof(int))); io_tlb_list = NULL; cleanup3: - free_pages((unsigned long)v_overflow_buffer, - get_order(io_tlb_overflow)); - io_tlb_overflow_buffer = 0; -cleanup2: io_tlb_end = 0; io_tlb_start = 0; io_tlb_nslabs = 0; @@ -407,8 +365,6 @@ void __init swiotlb_exit(void) return; if (late_alloc) { - free_pages((unsigned long)phys_to_virt(io_tlb_overflow_buffer), - get_order(io_tlb_overflow)); free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs * sizeof(phys_addr_t))); free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs * @@ -416,8 +372,6 @@ void __init swiotlb_exit(void) free_pages((unsigned long)phys_to_virt(io_tlb_start), get_order(io_tlb_nslabs << IO_TLB_SHIFT)); } else { - memblock_free_late(io_tlb_overflow_buffer, - PAGE_ALIGN(io_tlb_overflow)); memblock_free_late(__pa(io_tlb_orig_addr), PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); memblock_free_late(__pa(io_tlb_list), @@ -429,7 +383,7 @@ void __init swiotlb_exit(void) max_segment = 0; } -int is_swiotlb_buffer(phys_addr_t paddr) +static int is_swiotlb_buffer(phys_addr_t paddr) { return paddr >= io_tlb_start && paddr < io_tlb_end; } @@ -591,26 +545,6 @@ found: } /* - * Allocates bounce buffer and returns its physical address. - */ -static phys_addr_t -map_single(struct device *hwdev, phys_addr_t phys, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - dma_addr_t start_dma_addr; - - if (swiotlb_force == SWIOTLB_NO_FORCE) { - dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n", - &phys); - return SWIOTLB_MAP_ERROR; - } - - start_dma_addr = __phys_to_dma(hwdev, io_tlb_start); - return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size, - dir, attrs); -} - -/* * tlb_addr is the physical address of the bounce buffer to unmap. */ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, @@ -689,104 +623,32 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, } } -static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr, - size_t size) -{ - u64 mask = DMA_BIT_MASK(32); - - if (dev && dev->coherent_dma_mask) - mask = dev->coherent_dma_mask; - return addr + size - 1 <= mask; -} - -static void * -swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle, - unsigned long attrs) +static dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys, + size_t size, enum dma_data_direction dir, unsigned long attrs) { - phys_addr_t phys_addr; - - if (swiotlb_force == SWIOTLB_NO_FORCE) - goto out_warn; - - phys_addr = swiotlb_tbl_map_single(dev, - __phys_to_dma(dev, io_tlb_start), - 0, size, DMA_FROM_DEVICE, attrs); - if (phys_addr == SWIOTLB_MAP_ERROR) - goto out_warn; - - *dma_handle = __phys_to_dma(dev, phys_addr); - if (!dma_coherent_ok(dev, *dma_handle, size)) - goto out_unmap; - - memset(phys_to_virt(phys_addr), 0, size); - return phys_to_virt(phys_addr); + dma_addr_t dma_addr; -out_unmap: - dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n", - (unsigned long long)dev->coherent_dma_mask, - (unsigned long long)*dma_handle); - - /* - * DMA_TO_DEVICE to avoid memcpy in unmap_single. - * DMA_ATTR_SKIP_CPU_SYNC is optional. - */ - swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); -out_warn: - if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) { - dev_warn(dev, - "swiotlb: coherent allocation failed, size=%zu\n", - size); - dump_stack(); + if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) { + dev_warn_ratelimited(dev, + "Cannot do DMA to address %pa\n", phys); + return DIRECT_MAPPING_ERROR; } - return NULL; -} - -static bool swiotlb_free_buffer(struct device *dev, size_t size, - dma_addr_t dma_addr) -{ - phys_addr_t phys_addr = dma_to_phys(dev, dma_addr); - WARN_ON_ONCE(irqs_disabled()); - - if (!is_swiotlb_buffer(phys_addr)) - return false; - - /* - * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single. - * DMA_ATTR_SKIP_CPU_SYNC is optional. - */ - swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - return true; -} - -static void -swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir, - int do_panic) -{ - if (swiotlb_force == SWIOTLB_NO_FORCE) - return; - - /* - * Ran out of IOMMU space for this operation. This is very bad. - * Unfortunately the drivers cannot handle this operation properly. - * unless they check for dma_mapping_error (most don't) - * When the mapping is small enough return a static buffer to limit - * the damage, or panic when the transfer is too big. - */ - dev_err_ratelimited(dev, "DMA: Out of SW-IOMMU space for %zu bytes\n", - size); + /* 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; - if (size <= io_tlb_overflow || !do_panic) - return; + /* 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; + } - if (dir == DMA_BIDIRECTIONAL) - panic("DMA: Random memory could be DMA accessed\n"); - if (dir == DMA_FROM_DEVICE) - panic("DMA: Random memory could be DMA written\n"); - if (dir == DMA_TO_DEVICE) - panic("DMA: Random memory could be DMA read\n"); + return dma_addr; } /* @@ -801,7 +663,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, enum dma_data_direction dir, unsigned long attrs) { - phys_addr_t map, phys = page_to_phys(page) + offset; + phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dev_addr = phys_to_dma(dev, phys); BUG_ON(dir == DMA_NONE); @@ -810,28 +672,17 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, * 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) - return dev_addr; - - trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); - - /* Oh well, have to allocate and map a bounce buffer. */ - map = map_single(dev, phys, size, dir, attrs); - if (map == SWIOTLB_MAP_ERROR) { - swiotlb_full(dev, size, dir, 1); - return __phys_to_dma(dev, io_tlb_overflow_buffer); + 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); } - dev_addr = __phys_to_dma(dev, map); + if (!dev_is_dma_coherent(dev) && + (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) + arch_sync_dma_for_device(dev, phys, size, dir); - /* Ensure that the address returned is DMA'ble */ - if (dma_capable(dev, dev_addr, size)) - return dev_addr; - - attrs |= DMA_ATTR_SKIP_CPU_SYNC; - swiotlb_tbl_unmap_single(dev, map, size, dir, attrs); - - return __phys_to_dma(dev, io_tlb_overflow_buffer); + return dev_addr; } /* @@ -842,14 +693,18 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, * After this call, reads by the cpu to the buffer are guaranteed to see * whatever the device wrote there. */ -static void unmap_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) +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); return; @@ -867,13 +722,6 @@ static void unmap_single(struct device *hwdev, dma_addr_t dev_addr, dma_mark_clean(phys_to_virt(paddr), size); } -void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - unmap_single(hwdev, dev_addr, size, dir, attrs); -} - /* * Make physical memory consistent for a single streaming mode DMA translation * after a transfer. @@ -893,15 +741,17 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, BUG_ON(dir == DMA_NONE); - if (is_swiotlb_buffer(paddr)) { + 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); - return; - } - if (dir != DMA_FROM_DEVICE) - return; + if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_DEVICE) + arch_sync_dma_for_device(hwdev, paddr, size, dir); - dma_mark_clean(phys_to_virt(paddr), size); + if (!is_swiotlb_buffer(paddr) && dir == DMA_FROM_DEVICE) + dma_mark_clean(phys_to_virt(paddr), size); } void @@ -925,48 +775,31 @@ swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, * appropriate dma address and length. They are obtained via * sg_dma_{address,length}(SG). * - * NOTE: An implementation may be able to use a smaller number of - * DMA address/length pairs than there are SG table elements. - * (for example via virtual mapping capabilities) - * The routine returns the number of addr/length pairs actually - * used, at most nents. - * * Device ownership issues as mentioned above for swiotlb_map_page are the * same here. */ int -swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, +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; - BUG_ON(dir == DMA_NONE); - for_each_sg(sgl, sg, nelems, i) { - phys_addr_t paddr = sg_phys(sg); - dma_addr_t dev_addr = phys_to_dma(hwdev, paddr); - - if (swiotlb_force == SWIOTLB_FORCE || - !dma_capable(hwdev, dev_addr, sg->length)) { - phys_addr_t map = map_single(hwdev, sg_phys(sg), - sg->length, dir, attrs); - if (map == SWIOTLB_MAP_ERROR) { - /* Don't panic here, we expect map_sg users - to do proper error handling. */ - swiotlb_full(hwdev, sg->length, dir, 0); - attrs |= DMA_ATTR_SKIP_CPU_SYNC; - swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir, - attrs); - sg_dma_len(sgl) = 0; - return 0; - } - sg->dma_address = __phys_to_dma(hwdev, map); - } else - sg->dma_address = dev_addr; + sg->dma_address = swiotlb_map_page(dev, sg_page(sg), sg->offset, + sg->length, dir, attrs); + if (sg->dma_address == DIRECT_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; } /* @@ -984,7 +817,7 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) - unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, + swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs); } @@ -1022,12 +855,6 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE); } -int -swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) -{ - return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer)); -} - /* * Return whether the given device DMA address mask can be supported * properly. For example, if your device can only drive the low 24-bits @@ -1040,39 +867,10 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask) return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask; } -void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs) -{ - void *vaddr; - - /* temporary workaround: */ - if (gfp & __GFP_NOWARN) - attrs |= DMA_ATTR_NO_WARN; - - /* - * Don't print a warning when the first allocation attempt fails. - * swiotlb_alloc_coherent() will print a warning when the DMA memory - * allocation ultimately failed. - */ - gfp |= __GFP_NOWARN; - - vaddr = dma_direct_alloc(dev, size, dma_handle, gfp, attrs); - if (!vaddr) - vaddr = swiotlb_alloc_buffer(dev, size, dma_handle, attrs); - return vaddr; -} - -void swiotlb_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, unsigned long attrs) -{ - if (!swiotlb_free_buffer(dev, size, dma_addr)) - dma_direct_free(dev, size, vaddr, dma_addr, attrs); -} - const struct dma_map_ops swiotlb_dma_ops = { - .mapping_error = swiotlb_dma_mapping_error, - .alloc = swiotlb_alloc, - .free = swiotlb_free, + .mapping_error = dma_direct_mapping_error, + .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, |