From 327e2c97c46a4d971c5450a9d05b4a673f46c4da Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 7 Apr 2024 21:11:41 -0700 Subject: swiotlb: remove alloc_size argument to swiotlb_tbl_map_single() Currently swiotlb_tbl_map_single() takes alloc_align_mask and alloc_size arguments to specify an swiotlb allocation that is larger than mapping_size. This larger allocation is used solely by iommu_dma_map_single() to handle untrusted devices that should not have DMA visibility to memory pages that are partially used for unrelated kernel data. Having two arguments to specify the allocation is redundant. While alloc_align_mask naturally specifies the alignment of the starting address of the allocation, it can also implicitly specify the size by rounding up the mapping_size to that alignment. Additionally, the current approach has an edge case bug. iommu_dma_map_page() already does the rounding up to compute the alloc_size argument. But swiotlb_tbl_map_single() then calculates the alignment offset based on the DMA min_align_mask, and adds that offset to alloc_size. If the offset is non-zero, the addition may result in a value that is larger than the max the swiotlb can allocate. If the rounding up is done _after_ the alignment offset is added to the mapping_size (and the original mapping_size conforms to the value returned by swiotlb_max_mapping_size), then the max that the swiotlb can allocate will not be exceeded. In view of these issues, simplify the swiotlb_tbl_map_single() interface by removing the alloc_size argument. Most call sites pass the same value for mapping_size and alloc_size, and they pass alloc_align_mask as zero. Just remove the redundant argument from these callers, as they will see no functional change. For iommu_dma_map_page() also remove the alloc_size argument, and have swiotlb_tbl_map_single() compute the alloc_size by rounding up mapping_size after adding the offset based on min_align_mask. This has the side effect of fixing the edge case bug but with no other functional change. Also add a sanity test on the alloc_align_mask. While IOMMU code currently ensures the granule is not larger than PAGE_SIZE, if that guarantee were to be removed in the future, the downstream effect on the swiotlb might go unnoticed until strange allocation failures occurred. Tested on an ARM64 system with 16K page size and some kernel test-only hackery to allow modifying the DMA min_align_mask and the granule size that becomes the alloc_align_mask. Tested these combinations with a variety of original memory addresses and sizes, including those that reproduce the edge case bug: * 4K granule and 0 min_align_mask * 4K granule and 0xFFF min_align_mask (4K - 1) * 16K granule and 0xFFF min_align_mask * 64K granule and 0xFFF min_align_mask * 64K granule and 0x3FFF min_align_mask (16K - 1) With the changes, all combinations pass. Signed-off-by: Michael Kelley Reviewed-by: Petr Tesarik Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 56 +++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 42 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index a5e0dfc44d24..046da973a7e2 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1340,15 +1340,40 @@ static unsigned long mem_used(struct io_tlb_mem *mem) #endif /* CONFIG_DEBUG_FS */ +/** + * swiotlb_tbl_map_single() - bounce buffer map a single contiguous physical area + * @dev: Device which maps the buffer. + * @orig_addr: Original (non-bounced) physical IO buffer address + * @mapping_size: Requested size of the actual bounce buffer, excluding + * any pre- or post-padding for alignment + * @alloc_align_mask: Required start and end alignment of the allocated buffer + * @dir: DMA direction + * @attrs: Optional DMA attributes for the map operation + * + * Find and allocate a suitable sequence of IO TLB slots for the request. + * The allocated space starts at an alignment specified by alloc_align_mask, + * and the size of the allocated space is rounded up so that the total amount + * of allocated space is a multiple of (alloc_align_mask + 1). If + * alloc_align_mask is zero, the allocated space may be at any alignment and + * the size is not rounded up. + * + * The returned address is within the allocated space and matches the bits + * of orig_addr that are specified in the DMA min_align_mask for the device. As + * such, this returned address may be offset from the beginning of the allocated + * space. The bounce buffer space starting at the returned address for + * mapping_size bytes is initialized to the contents of the original IO buffer + * area. Any pre-padding (due to an offset) and any post-padding (due to + * rounding-up the size) is not initialized. + */ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, - size_t mapping_size, size_t alloc_size, - unsigned int alloc_align_mask, enum dma_data_direction dir, - unsigned long attrs) + size_t mapping_size, unsigned int alloc_align_mask, + enum dma_data_direction dir, unsigned long attrs) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned int offset; struct io_tlb_pool *pool; unsigned int i; + size_t size; int index; phys_addr_t tlb_addr; unsigned short pad_slots; @@ -1362,20 +1387,24 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n"); - if (mapping_size > alloc_size) { - dev_warn_once(dev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)", - mapping_size, alloc_size); - return (phys_addr_t)DMA_MAPPING_ERROR; - } + /* + * The default swiotlb memory pool is allocated with PAGE_SIZE + * alignment. If a mapping is requested with larger alignment, + * the mapping may be unable to use the initial slot(s) in all + * sets of IO_TLB_SEGSIZE slots. In such case, a mapping request + * of or near the maximum mapping size would always fail. + */ + dev_WARN_ONCE(dev, alloc_align_mask > ~PAGE_MASK, + "Alloc alignment may prevent fulfilling requests with max mapping_size\n"); offset = swiotlb_align_offset(dev, alloc_align_mask, orig_addr); - index = swiotlb_find_slots(dev, orig_addr, - alloc_size + offset, alloc_align_mask, &pool); + size = ALIGN(mapping_size + offset, alloc_align_mask + 1); + index = swiotlb_find_slots(dev, orig_addr, size, alloc_align_mask, &pool); if (index == -1) { if (!(attrs & DMA_ATTR_NO_WARN)) dev_warn_ratelimited(dev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n", - alloc_size, mem->nslabs, mem_used(mem)); + size, mem->nslabs, mem_used(mem)); return (phys_addr_t)DMA_MAPPING_ERROR; } @@ -1388,7 +1417,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, offset &= (IO_TLB_SIZE - 1); index += pad_slots; pool->slots[index].pad_slots = pad_slots; - for (i = 0; i < nr_slots(alloc_size + offset); i++) + for (i = 0; i < (nr_slots(size) - pad_slots); i++) pool->slots[index + i].orig_addr = slot_addr(orig_addr, i); tlb_addr = slot_addr(pool->start, index) + offset; /* @@ -1543,8 +1572,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size); - swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir, - attrs); + swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, 0, dir, attrs); if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; -- cgit v1.2.3 From fe7514b149e0a8a6f3031d286e52d40163b0b11a Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 7 May 2024 13:20:20 +0200 Subject: dma: compile-out DMA sync op calls when not used Some platforms do have DMA, but DMA there is always direct and coherent. Currently, even on such platforms DMA sync operations are compiled and called. Add a new hidden Kconfig symbol, DMA_NEED_SYNC, and set it only when either sync operations are needed or there is DMA ops or swiotlb or DMA debug is enabled. Compile global dma_sync_*() and dma_need_sync() only when it's set, otherwise provide empty inline stubs. The change allows for future optimizations of DMA sync calls depending on runtime conditions. Signed-off-by: Alexander Lobakin Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 62 ++++++++++++++++++++++++--------------------- kernel/dma/Kconfig | 5 ++++ kernel/dma/mapping.c | 22 ++++++++-------- 3 files changed, 50 insertions(+), 39 deletions(-) (limited to 'kernel') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 4a658de44ee9..a569b56b25e2 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -117,14 +117,6 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, unsigned long attrs); void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs); -void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, - enum dma_data_direction dir); -void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir); -void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); -void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); 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, @@ -147,7 +139,6 @@ u64 dma_get_required_mask(struct device *dev); bool dma_addressing_limited(struct device *dev); size_t dma_max_mapping_size(struct device *dev); size_t dma_opt_mapping_size(struct device *dev); -bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, enum dma_data_direction dir, gfp_t gfp, unsigned long attrs); @@ -195,22 +186,6 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { } -static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir) -{ -} -static inline void dma_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ -} -static inline void dma_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sg, int nelems, enum dma_data_direction dir) -{ -} -static inline void dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sg, int nelems, enum dma_data_direction dir) -{ -} static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return -ENOMEM; @@ -277,10 +252,6 @@ static inline size_t dma_opt_mapping_size(struct device *dev) { return 0; } -static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) -{ - return false; -} static inline unsigned long dma_get_merge_boundary(struct device *dev) { return 0; @@ -310,6 +281,39 @@ static inline int dma_mmap_noncontiguous(struct device *dev, } #endif /* CONFIG_HAS_DMA */ +#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC) +void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir); +void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir); +void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir); +void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir); +bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); +#else /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */ +static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ +} +static inline void dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ +} +static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return false; +} +#endif /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */ + struct page *dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void dma_free_pages(struct device *dev, size_t size, struct page *page, diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index d62f5957f36b..c06e56be0ca1 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -107,6 +107,11 @@ config DMA_BOUNCE_UNALIGNED_KMALLOC bool depends on SWIOTLB +config DMA_NEED_SYNC + def_bool ARCH_HAS_SYNC_DMA_FOR_DEVICE || ARCH_HAS_SYNC_DMA_FOR_CPU || \ + ARCH_HAS_SYNC_DMA_FOR_CPU_ALL || DMA_API_DEBUG || DMA_OPS || \ + SWIOTLB + config DMA_RESTRICTED_POOL bool "DMA Restricted Pool" depends on OF && OF_RESERVED_MEM && SWIOTLB diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 58db8fd70471..c78b78e95a26 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -329,6 +329,7 @@ void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, } EXPORT_SYMBOL(dma_unmap_resource); +#ifdef CONFIG_DMA_NEED_SYNC void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { @@ -385,6 +386,17 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, } EXPORT_SYMBOL(dma_sync_sg_for_device); +bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_map_direct(dev, ops)) + return dma_direct_need_sync(dev, dma_addr); + return ops->sync_single_for_cpu || ops->sync_single_for_device; +} +EXPORT_SYMBOL_GPL(dma_need_sync); +#endif /* CONFIG_DMA_NEED_SYNC */ + /* * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems * that the intention is to allow exporting memory allocated via the @@ -841,16 +853,6 @@ size_t dma_opt_mapping_size(struct device *dev) } EXPORT_SYMBOL_GPL(dma_opt_mapping_size); -bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - - if (dma_map_direct(dev, ops)) - return dma_direct_need_sync(dev, dma_addr); - return ops->sync_single_for_cpu || ops->sync_single_for_device; -} -EXPORT_SYMBOL_GPL(dma_need_sync); - unsigned long dma_get_merge_boundary(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); -- cgit v1.2.3 From f406c8e4b770ca3b0df84a17349e13f2b6b07d10 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 7 May 2024 13:20:21 +0200 Subject: dma: avoid redundant calls for sync operations Quite often, devices do not need dma_sync operations on x86_64 at least. Indeed, when dev_is_dma_coherent(dev) is true and dev_use_swiotlb(dev) is false, iommu_dma_sync_single_for_cpu() and friends do nothing. However, indirectly calling them when CONFIG_RETPOLINE=y consumes about 10% of cycles on a cpu receiving packets from softirq at ~100Gbit rate. Even if/when CONFIG_RETPOLINE is not set, there is a cost of about 3%. Add dev->need_dma_sync boolean and turn it off during the device initialization (dma_set_mask()) depending on the setup: dev_is_dma_coherent() for the direct DMA, !(sync_single_for_device || sync_single_for_cpu) or the new dma_map_ops flag, %DMA_F_CAN_SKIP_SYNC, advertised for non-NULL DMA ops. Then later, if/when swiotlb is used for the first time, the flag is reset back to on, from swiotlb_tbl_map_single(). On iavf, the UDP trafficgen with XDP_DROP in skb mode test shows +3-5% increase for direct DMA. Suggested-by: Christoph Hellwig # direct DMA shortcut Co-developed-by: Eric Dumazet Signed-off-by: Eric Dumazet Signed-off-by: Alexander Lobakin Signed-off-by: Christoph Hellwig --- include/linux/device.h | 4 ++++ include/linux/dma-map-ops.h | 12 ++++++++++ include/linux/dma-mapping.h | 53 ++++++++++++++++++++++++++++++++++++++----- kernel/dma/mapping.c | 55 +++++++++++++++++++++++++++++++++++---------- kernel/dma/swiotlb.c | 6 +++++ 5 files changed, 113 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/include/linux/device.h b/include/linux/device.h index b9f5464f44ed..ed95b829f05b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -691,6 +691,7 @@ struct device_physical_location { * and optionall (if the coherent mask is large enough) also * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. + * @dma_need_sync: The device needs performing DMA sync operations. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -803,6 +804,9 @@ struct device { #ifdef CONFIG_DMA_OPS_BYPASS bool dma_ops_bypass : 1; #endif +#ifdef CONFIG_DMA_NEED_SYNC + bool dma_need_sync:1; +#endif }; /** diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 4abc60f04209..4893cb89cb52 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -18,8 +18,11 @@ struct iommu_ops; * * DMA_F_PCI_P2PDMA_SUPPORTED: Indicates the dma_map_ops implementation can * handle PCI P2PDMA pages in the map_sg/unmap_sg operation. + * DMA_F_CAN_SKIP_SYNC: DMA sync operations can be skipped if the device is + * coherent and it's not an SWIOTLB buffer. */ #define DMA_F_PCI_P2PDMA_SUPPORTED (1 << 0) +#define DMA_F_CAN_SKIP_SYNC (1 << 1) struct dma_map_ops { unsigned int flags; @@ -273,6 +276,15 @@ static inline bool dev_is_dma_coherent(struct device *dev) } #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */ +static inline void dma_reset_need_sync(struct device *dev) +{ +#ifdef CONFIG_DMA_NEED_SYNC + /* Reset it only once so that the function can be called on hotpath */ + if (unlikely(!dev->dma_need_sync)) + dev->dma_need_sync = true; +#endif +} + /* * Check whether potential kmalloc() buffers are safe for non-coherent DMA. */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index a569b56b25e2..eb4e15893b6c 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -282,16 +282,59 @@ static inline int dma_mmap_noncontiguous(struct device *dev, #endif /* CONFIG_HAS_DMA */ #if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC) -void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, +void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir); -void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, +void __dma_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir); -void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, +void __dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir); -void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, +void __dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir); -bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); +bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr); + +static inline bool dma_dev_need_sync(const struct device *dev) +{ + /* Always call DMA sync operations when debugging is enabled */ + return dev->dma_need_sync || IS_ENABLED(CONFIG_DMA_API_DEBUG); +} + +static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_single_for_cpu(dev, addr, 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) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_single_for_device(dev, addr, size, dir); +} + +static inline void dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_sg_for_cpu(dev, sg, nelems, dir); +} + +static inline void dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_sg_for_device(dev, sg, nelems, dir); +} + +static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return dma_dev_need_sync(dev) ? __dma_need_sync(dev, dma_addr) : false; +} #else /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */ +static inline bool dma_dev_need_sync(const struct device *dev) +{ + return false; +} static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index c78b78e95a26..3524bc92c37f 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -330,7 +330,7 @@ void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, EXPORT_SYMBOL(dma_unmap_resource); #ifdef CONFIG_DMA_NEED_SYNC -void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, +void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -342,9 +342,9 @@ void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, ops->sync_single_for_cpu(dev, addr, size, dir); debug_dma_sync_single_for_cpu(dev, addr, size, dir); } -EXPORT_SYMBOL(dma_sync_single_for_cpu); +EXPORT_SYMBOL(__dma_sync_single_for_cpu); -void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, +void __dma_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -356,9 +356,9 @@ void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, ops->sync_single_for_device(dev, addr, size, dir); debug_dma_sync_single_for_device(dev, addr, size, dir); } -EXPORT_SYMBOL(dma_sync_single_for_device); +EXPORT_SYMBOL(__dma_sync_single_for_device); -void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, +void __dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -370,9 +370,9 @@ void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, ops->sync_sg_for_cpu(dev, sg, nelems, dir); debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir); } -EXPORT_SYMBOL(dma_sync_sg_for_cpu); +EXPORT_SYMBOL(__dma_sync_sg_for_cpu); -void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, +void __dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -384,18 +384,47 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, ops->sync_sg_for_device(dev, sg, nelems, dir); debug_dma_sync_sg_for_device(dev, sg, nelems, dir); } -EXPORT_SYMBOL(dma_sync_sg_for_device); +EXPORT_SYMBOL(__dma_sync_sg_for_device); -bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr) { const struct dma_map_ops *ops = get_dma_ops(dev); if (dma_map_direct(dev, ops)) + /* + * dma_need_sync could've been reset on first SWIOTLB buffer + * mapping, but @dma_addr is not necessary an SWIOTLB buffer. + * In this case, fall back to more granular check. + */ return dma_direct_need_sync(dev, dma_addr); - return ops->sync_single_for_cpu || ops->sync_single_for_device; + return true; } -EXPORT_SYMBOL_GPL(dma_need_sync); -#endif /* CONFIG_DMA_NEED_SYNC */ +EXPORT_SYMBOL_GPL(__dma_need_sync); + +static void dma_setup_need_sync(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_map_direct(dev, ops) || (ops->flags & DMA_F_CAN_SKIP_SYNC)) + /* + * dma_need_sync will be reset to %true on first SWIOTLB buffer + * mapping, if any. During the device initialization, it's + * enough to check only for the DMA coherence. + */ + dev->dma_need_sync = !dev_is_dma_coherent(dev); + else if (!ops->sync_single_for_device && !ops->sync_single_for_cpu && + !ops->sync_sg_for_device && !ops->sync_sg_for_cpu) + /* + * Synchronization is not possible when none of DMA sync ops + * is set. + */ + dev->dma_need_sync = false; + else + dev->dma_need_sync = true; +} +#else /* !CONFIG_DMA_NEED_SYNC */ +static inline void dma_setup_need_sync(struct device *dev) { } +#endif /* !CONFIG_DMA_NEED_SYNC */ /* * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems @@ -785,6 +814,8 @@ int dma_set_mask(struct device *dev, u64 mask) arch_dma_set_mask(dev, mask); *dev->dma_mask = mask; + dma_setup_need_sync(dev); + return 0; } EXPORT_SYMBOL(dma_set_mask); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 046da973a7e2..ae3e593eaadb 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1408,6 +1408,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, return (phys_addr_t)DMA_MAPPING_ERROR; } + /* + * If dma_need_sync wasn't set, reset it on first SWIOTLB buffer + * mapping to always sync SWIOTLB buffers. + */ + dma_reset_need_sync(dev); + /* * Save away the mapping from the original address to the DMA address. * This is needed when we sync the memory. Then we sync the buffer if -- cgit v1.2.3 From a6016aac5252da9d22a4dc0b98121b0acdf6d2f5 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 9 May 2024 16:46:16 +0200 Subject: dma: fix DMA sync for drivers not calling dma_set_mask*() There are several reports that the DMA sync shortcut broke non-coherent devices. dev->dma_need_sync is false after the &device allocation and if a driver didn't call dma_set_mask*(), it will still be false even if the device is not DMA-coherent and thus needs synchronizing. Due to historical reasons, there's still a lot of drivers not calling it. Invert the boolean, so that the sync will be performed by default and the shortcut will be enabled only when calling dma_set_mask*(). Reported-by: Steven Price Closes: https://lore.kernel.org/lkml/010686f5-3049-46a1-8230-7752a1b433ff@arm.com Reported-by: Marek Szyprowski Closes: https://lore.kernel.org/lkml/46160534-5003-4809-a408-6b3a3f4921e9@samsung.com Fixes: f406c8e4b770. ("dma: avoid redundant calls for sync operations") Signed-off-by: Alexander Lobakin Signed-off-by: Christoph Hellwig Tested-by: Steven Price Tested-by: Marek Szyprowski --- include/linux/device.h | 4 ++-- include/linux/dma-map-ops.h | 4 ++-- include/linux/dma-mapping.h | 2 +- kernel/dma/mapping.c | 10 +++++----- kernel/dma/swiotlb.c | 2 +- 5 files changed, 11 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/include/linux/device.h b/include/linux/device.h index ed95b829f05b..d4b50accff26 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -691,7 +691,7 @@ struct device_physical_location { * and optionall (if the coherent mask is large enough) also * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. - * @dma_need_sync: The device needs performing DMA sync operations. + * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -805,7 +805,7 @@ struct device { bool dma_ops_bypass : 1; #endif #ifdef CONFIG_DMA_NEED_SYNC - bool dma_need_sync:1; + bool dma_skip_sync:1; #endif }; diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 4893cb89cb52..5217b922d29f 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -280,8 +280,8 @@ static inline void dma_reset_need_sync(struct device *dev) { #ifdef CONFIG_DMA_NEED_SYNC /* Reset it only once so that the function can be called on hotpath */ - if (unlikely(!dev->dma_need_sync)) - dev->dma_need_sync = true; + if (unlikely(dev->dma_skip_sync)) + dev->dma_skip_sync = false; #endif } diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index eb4e15893b6c..f693aafe221f 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -295,7 +295,7 @@ bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr); static inline bool dma_dev_need_sync(const struct device *dev) { /* Always call DMA sync operations when debugging is enabled */ - return dev->dma_need_sync || IS_ENABLED(CONFIG_DMA_API_DEBUG); + return !dev->dma_skip_sync || IS_ENABLED(CONFIG_DMA_API_DEBUG); } static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 3524bc92c37f..3f77c3f8d16d 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -392,7 +392,7 @@ bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr) if (dma_map_direct(dev, ops)) /* - * dma_need_sync could've been reset on first SWIOTLB buffer + * dma_skip_sync could've been reset on first SWIOTLB buffer * mapping, but @dma_addr is not necessary an SWIOTLB buffer. * In this case, fall back to more granular check. */ @@ -407,20 +407,20 @@ static void dma_setup_need_sync(struct device *dev) if (dma_map_direct(dev, ops) || (ops->flags & DMA_F_CAN_SKIP_SYNC)) /* - * dma_need_sync will be reset to %true on first SWIOTLB buffer + * dma_skip_sync will be reset to %false on first SWIOTLB buffer * mapping, if any. During the device initialization, it's * enough to check only for the DMA coherence. */ - dev->dma_need_sync = !dev_is_dma_coherent(dev); + dev->dma_skip_sync = dev_is_dma_coherent(dev); else if (!ops->sync_single_for_device && !ops->sync_single_for_cpu && !ops->sync_sg_for_device && !ops->sync_sg_for_cpu) /* * Synchronization is not possible when none of DMA sync ops * is set. */ - dev->dma_need_sync = false; + dev->dma_skip_sync = true; else - dev->dma_need_sync = true; + dev->dma_skip_sync = false; } #else /* !CONFIG_DMA_NEED_SYNC */ static inline void dma_setup_need_sync(struct device *dev) { } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index ae3e593eaadb..068134697cf1 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1409,7 +1409,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, } /* - * If dma_need_sync wasn't set, reset it on first SWIOTLB buffer + * If dma_skip_sync was set, reset it on first SWIOTLB buffer * mapping to always sync SWIOTLB buffers. */ dma_reset_need_sync(dev); -- cgit v1.2.3