From b65125c6acf38388d3342b37c18c3b6cc97eeb75 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 12 Apr 2018 14:49:23 +0200 Subject: swiotlb: mark is_swiotlb_buffer static Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy Reviewed-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 965be92c33b5..7ef541ce8f34 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -121,7 +121,6 @@ static inline unsigned int swiotlb_max_segment(void) { return 0; } #endif extern void swiotlb_print_info(void); -extern int is_swiotlb_buffer(phys_addr_t paddr); extern void swiotlb_set_max_segment(unsigned int); extern const struct dma_map_ops swiotlb_dma_ops; -- cgit v1.2.3 From dff8d6c1ed584de65aac40494d3e7468c50980c3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Aug 2018 15:30:39 +0300 Subject: swiotlb: remove the overflow buffer Like all other dma mapping drivers just return an error code instead of an actual memory buffer. The reason for the overflow buffer was that at the time swiotlb was invented there was no way to check for dma mapping errors, but this has long been fixed. Signed-off-by: Christoph Hellwig Acked-by: Catalin Marinas Reviewed-by: Robin Murphy Reviewed-by: Konrad Rzeszutek Wilk --- arch/arm64/mm/dma-mapping.c | 2 +- arch/powerpc/kernel/dma-swiotlb.c | 4 +-- include/linux/dma-direct.h | 2 ++ include/linux/swiotlb.h | 3 -- kernel/dma/direct.c | 2 -- kernel/dma/swiotlb.c | 59 ++------------------------------------- 6 files changed, 8 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 072c51fb07d7..8d91b927e09e 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -324,7 +324,7 @@ static int __swiotlb_dma_supported(struct device *hwdev, u64 mask) static int __swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t addr) { if (swiotlb) - return swiotlb_dma_mapping_error(hwdev, addr); + return dma_direct_mapping_error(hwdev, addr); return 0; } diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 88f3963ca30f..5fc335f4d9cd 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -11,7 +11,7 @@ * */ -#include +#include #include #include #include @@ -59,7 +59,7 @@ 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 = swiotlb_dma_mapping_error, + .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 fbca184ff5a0..bd73e7a91410 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,6 +5,8 @@ #include #include +#define DIRECT_MAPPING_ERROR 0 + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #else diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 7ef541ce8f34..f847c1b265c4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -106,9 +106,6 @@ extern void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, int nelems, enum dma_data_direction dir); -extern int -swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr); - extern int swiotlb_dma_supported(struct device *hwdev, u64 mask); diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 87a6bc2a96c0..f14c376937e5 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -14,8 +14,6 @@ #include #include -#define DIRECT_MAPPING_ERROR 0 - /* * Most architectures use ZONE_DMA for the first 16 Megabytes, but * some use it for entirely different regions: diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 69bf305ee5f8..11dbcd80b4a6 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -72,13 +72,6 @@ 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 +119,6 @@ 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 +186,10 @@ 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; @@ -212,17 +198,6 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) io_tlb_start = __pa(tlb); 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 @@ -330,7 +305,6 @@ 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; @@ -341,19 +315,6 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT); 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 @@ -390,10 +351,6 @@ 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 +364,6 @@ 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 +371,6 @@ 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), @@ -790,7 +743,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, /* Oh well, have to allocate and map a bounce buffer. */ map = map_single(dev, phys, size, dir, attrs); if (map == SWIOTLB_MAP_ERROR) - return __phys_to_dma(dev, io_tlb_overflow_buffer); + return DIRECT_MAPPING_ERROR; dev_addr = __phys_to_dma(dev, map); @@ -801,7 +754,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, 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 DIRECT_MAPPING_ERROR; } /* @@ -985,12 +938,6 @@ 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 @@ -1033,7 +980,7 @@ void swiotlb_free(struct device *dev, size_t size, void *vaddr, } const struct dma_map_ops swiotlb_dma_ops = { - .mapping_error = swiotlb_dma_mapping_error, + .mapping_error = dma_direct_mapping_error, .alloc = swiotlb_alloc, .free = swiotlb_free, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, -- cgit v1.2.3 From fafadcd16595c1df82df399f62421718ec9bf70a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 30 Sep 2018 16:13:33 -0700 Subject: swiotlb: don't dip into swiotlb pool for coherent allocations All architectures that support swiotlb also have a zone that backs up these less than full addressing allocations (usually ZONE_DMA32). Because of that it is rather pointless to fall back to the global swiotlb buffer if the normal dma direct allocation failed - the only thing this will do is to eat up bounce buffers that would be more useful to serve streaming mappings. Signed-off-by: Christoph Hellwig Acked-by: Catalin Marinas Acked-by: Konrad Rzeszutek Wilk --- arch/arm64/mm/dma-mapping.c | 6 +-- include/linux/swiotlb.h | 5 --- kernel/dma/swiotlb.c | 105 +------------------------------------------- 3 files changed, 5 insertions(+), 111 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 8d91b927e09e..eee6cfcfde9e 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -112,7 +112,7 @@ static void *__dma_alloc(struct device *dev, size_t size, return addr; } - ptr = swiotlb_alloc(dev, size, dma_handle, flags, attrs); + ptr = dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); if (!ptr) goto no_mem; @@ -133,7 +133,7 @@ static void *__dma_alloc(struct device *dev, size_t size, return coherent_ptr; no_map: - swiotlb_free(dev, size, ptr, *dma_handle, attrs); + dma_direct_free_pages(dev, size, ptr, *dma_handle, attrs); no_mem: return NULL; } @@ -151,7 +151,7 @@ static void __dma_free(struct device *dev, size_t size, return; vunmap(vaddr); } - swiotlb_free(dev, size, swiotlb_addr, dma_handle, attrs); + dma_direct_free_pages(dev, size, swiotlb_addr, dma_handle, attrs); } static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page, diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index f847c1b265c4..a387b59640a4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -67,11 +67,6 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev, /* Accessory functions. */ -void *swiotlb_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_handle, - gfp_t flags, unsigned long attrs); -void swiotlb_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, unsigned long attrs); - extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 57507b18caa4..1a01b0ac0a5e 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -622,78 +622,6 @@ 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) -{ - 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); - -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(); - } - 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 dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys, size_t size, enum dma_data_direction dir, unsigned long attrs) { @@ -926,39 +854,10 @@ 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 = dma_direct_mapping_error, - .alloc = swiotlb_alloc, - .free = swiotlb_free, + .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, -- cgit v1.2.3