diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-20 20:23:39 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-20 20:23:39 +0300 |
commit | daa121128a2d2ac6006159e2c47676e4fcd21eab (patch) | |
tree | 92f5ebb4ebc9be3535c5c3905ba40ab68cbdf964 /kernel/dma | |
parent | 6e51b4b5bbc07e52b226017936874715629932d1 (diff) | |
parent | a6016aac5252da9d22a4dc0b98121b0acdf6d2f5 (diff) | |
download | linux-daa121128a2d2ac6006159e2c47676e4fcd21eab.tar.xz |
Merge tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma-mapping
Pull dma-mapping updates from Christoph Hellwig:
- optimize DMA sync calls when they are no-ops (Alexander Lobakin)
- fix swiotlb padding for untrusted devices (Michael Kelley)
- add documentation for swiotb (Michael Kelley)
* tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma-mapping:
dma: fix DMA sync for drivers not calling dma_set_mask*()
xsk: use generic DMA sync shortcut instead of a custom one
page_pool: check for DMA sync shortcut earlier
page_pool: don't use driver-set flags field directly
page_pool: make sure frag API fields don't span between cachelines
iommu/dma: avoid expensive indirect calls for sync operations
dma: avoid redundant calls for sync operations
dma: compile-out DMA sync op calls when not used
iommu/dma: fix zeroing of bounce buffer padding used by untrusted devices
swiotlb: remove alloc_size argument to swiotlb_tbl_map_single()
Documentation/core-api: add swiotlb documentation
Diffstat (limited to 'kernel/dma')
-rw-r--r-- | kernel/dma/Kconfig | 5 | ||||
-rw-r--r-- | kernel/dma/mapping.c | 69 | ||||
-rw-r--r-- | kernel/dma/swiotlb.c | 62 |
3 files changed, 104 insertions, 32 deletions
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 5e2d51e1cdf6..81de84318ccc 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -329,7 +329,8 @@ void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, } EXPORT_SYMBOL(dma_unmap_resource); -void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, +#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) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -341,9 +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); @@ -355,9 +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); @@ -369,9 +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); @@ -383,7 +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) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_map_direct(dev, ops)) + /* + * 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. + */ + return dma_direct_need_sync(dev, dma_addr); + return true; +} +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_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_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_skip_sync = true; + else + dev->dma_skip_sync = false; +} +#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 @@ -773,6 +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); @@ -841,16 +884,6 @@ 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); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 0de66f0ff43a..fe1ccb53596f 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; @@ -1362,24 +1387,34 @@ 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; } /* + * If dma_skip_sync was 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 * needed. @@ -1388,7 +1423,7 @@ 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 +1578,7 @@ 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; |