/* * Dynamic DMA mapping support. * * This implementation is a fallback for platforms that do not support * I/O TLBs (aka DMA address translation hardware). * Copyright (C) 2000 Asit Mallick * Copyright (C) 2000 Goutham Rao * Copyright (C) 2000, 2003 Hewlett-Packard Co * David Mosberger-Tang * * 03/05/07 davidm Switch from PCI-DMA to generic device DMA API. * 00/12/13 davidm Rename to swiotlb.c and add mark_clean() to avoid * unnecessary i-cache flushing. * 04/07/.. ak Better overflow handling. Assorted fixes. * 05/09/10 linville Add support for syncing ranges, support syncing for * DMA_BIDIRECTIONAL mappings, miscellaneous cleanup. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #define OFFSET(val,align) ((unsigned long) \ ( (val) & ( (align) - 1))) #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT)) /* * Minimum IO TLB size to bother booting with. Systems with mainly * 64bit capable cards will only lightly use the swiotlb. If we can't * allocate a contiguous 1MB, we're probably in trouble anyway. */ #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT) /* * Enumeration for sync targets */ enum dma_sync_target { SYNC_FOR_CPU = 0, SYNC_FOR_DEVICE = 1, }; int swiotlb_force; /* * Used to do a quick range check in swiotlb_unmap_single and * swiotlb_sync_single_*, to see if the memory was in fact allocated by this * API. */ static char *io_tlb_start, *io_tlb_end; /* * The number of IO TLB blocks (in groups of 64) betweeen io_tlb_start and * io_tlb_end. This is command line adjustable via setup_io_tlb_npages. */ 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; void *io_tlb_overflow_buffer; /* * This is a free list describing the number of free entries available from * each index */ static unsigned int *io_tlb_list; static unsigned int io_tlb_index; /* * We need to save away the original address corresponding to a mapped entry * for the sync operations. */ static struct swiotlb_phys_addr { struct page *page; unsigned int offset; } *io_tlb_orig_addr; /* * Protect the above data structures in the map and unmap calls */ static DEFINE_SPINLOCK(io_tlb_lock); static int __init setup_io_tlb_npages(char *str) { if (isdigit(*str)) { io_tlb_nslabs = simple_strtoul(str, &str, 0); /* avoid tail segment of size < IO_TLB_SEGSIZE */ io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); } if (*str == ',') ++str; if (!strcmp(str, "force")) swiotlb_force = 1; return 1; } __setup("swiotlb=", setup_io_tlb_npages); /* make io_tlb_overflow tunable too? */ void * __weak __init swiotlb_alloc_boot(size_t size, unsigned long nslabs) { return alloc_bootmem_low_pages(size); } void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs) { return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order); } dma_addr_t __weak swiotlb_phys_to_bus(phys_addr_t paddr) { return paddr; } phys_addr_t __weak swiotlb_bus_to_phys(dma_addr_t baddr) { return baddr; } static dma_addr_t swiotlb_virt_to_bus(volatile void *address) { return swiotlb_phys_to_bus(virt_to_phys(address)); } static void *swiotlb_bus_to_virt(dma_addr_t address) { return phys_to_virt(swiotlb_bus_to_phys(address)); } int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size) { return 0; } static dma_addr_t swiotlb_sg_to_bus(struct scatterlist *sg) { return swiotlb_phys_to_bus(page_to_phys(sg_page(sg)) + sg->offset); } static void swiotlb_print_info(unsigned long bytes) { phys_addr_t pstart, pend; dma_addr_t bstart, bend; pstart = virt_to_phys(io_tlb_start); pend = virt_to_phys(io_tlb_end); bstart = swiotlb_phys_to_bus(pstart); bend = swiotlb_phys_to_bus(pend); printk(KERN_INFO "Placing %luMB software IO TLB between %p - %p\n", bytes >> 20, io_tlb_start, io_tlb_end); if (pstart != bstart || pend != bend) printk(KERN_INFO "software IO TLB at phys %#llx - %#llx" " bus %#llx - %#llx\n", (unsigned long long)pstart, (unsigned long long)pend, (unsigned long long)bstart, (unsigned long long)bend); else printk(KERN_INFO "software IO TLB at phys %#llx - %#llx\n", (unsigned long long)pstart, (unsigned long long)pend); } /* * Statically reserve bounce buffer space and initialize bounce buffer data * structures for the software IO TLB used to implement the DMA API. */ void __init swiotlb_init_with_default_size(size_t default_size) { unsigned long i, bytes; if (!io_tlb_nslabs) { io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); } bytes = io_tlb_nslabs << IO_TLB_SHIFT; /* * Get IO TLB memory from the low pages */ io_tlb_start = swiotlb_alloc_boot(bytes, io_tlb_nslabs); if (!io_tlb_start) panic("Cannot allocate SWIOTLB buffer"); io_tlb_end = io_tlb_start + bytes; /* * 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 = alloc_bootmem(io_tlb_nslabs * sizeof(int)); for (i = 0; i < io_tlb_nslabs; i++) io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); io_tlb_index = 0; io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(struct swiotlb_phys_addr)); /* * Get the overflow emergency buffer */ io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow); if (!io_tlb_overflow_buffer) panic("Cannot allocate SWIOTLB overflow buffer!\n"); swiotlb_print_info(bytes); } void __init swiotlb_init(void) { swiotlb_init_with_default_size(64 * (1<<20)); /* default to 64MB */ } /* * Systems with larger DMA zones (those that don't support ISA) can * initialize the swiotlb later using the slab allocator if needed. * This should be just like above, but with some error catching. */ int swiotlb_late_init_with_default_size(size_t default_size) { unsigned long i, bytes, req_nslabs = io_tlb_nslabs; unsigned int order; if (!io_tlb_nslabs) { io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); } /* * Get IO TLB memory from the low pages */ order = get_order(io_tlb_nslabs << IO_TLB_SHIFT); io_tlb_nslabs = SLABS_PER_PAGE << order; bytes = io_tlb_nslabs << IO_TLB_SHIFT; while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) { io_tlb_start = swiotlb_alloc(order, io_tlb_nslabs); if (io_tlb_start) break; order--; } if (!io_tlb_start) goto cleanup1; if (order != get_order(bytes)) { printk(KERN_WARNING "Warning: only able to allocate %ld MB " "for software IO TLB\n", (PAGE_SIZE << order) >> 20); io_tlb_nslabs = SLABS_PER_PAGE << order; bytes = io_tlb_nslabs << IO_TLB_SHIFT; } io_tlb_end = io_tlb_start + bytes; memset(io_tlb_start, 0, bytes); /* * 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 = (unsigned int *)__get_free_pages(GFP_KERNEL, get_order(io_tlb_nslabs * sizeof(int))); if (!io_tlb_list) goto cleanup2; for (i = 0; i < io_tlb_nslabs; i++) io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); io_tlb_index = 0; io_tlb_orig_addr = (struct swiotlb_phys_addr *)__get_free_pages(GFP_KERNEL, get_order(io_tlb_nslabs * sizeof(struct swiotlb_phys_addr))); if (!io_tlb_orig_addr) goto cleanup3; memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(struct swiotlb_phys_addr)); /* * Get the overflow emergency buffer */ io_tlb_overflow_buffer = (void *)__get_free_pages(GFP_DMA, get_order(io_tlb_overflow)); if (!io_tlb_overflow_buffer) goto cleanup4; swiotlb_print_info(bytes); return 0; cleanup4: free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs * sizeof(char *))); io_tlb_orig_addr = NULL; cleanup3: free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs * sizeof(int))); io_tlb_list = NULL; cleanup2: io_tlb_end = NULL; free_pages((unsigned long)io_tlb_start, order); io_tlb_start = NULL; cleanup1: io_tlb_nslabs = req_nslabs; return -ENOMEM; } static int address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size) { return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size); } static inline int range_needs_mapping(void *ptr, size_t size) { return swiotlb_force || swiotlb_arch_range_needs_mapping(ptr, size); } static int is_swiotlb_buffer(char *addr) { return addr >= io_tlb_start && addr < io_tlb_end; } static struct swiotlb_phys_addr swiotlb_bus_to_phys_addr(char *dma_addr) { int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; struct swiotlb_phys_addr buffer = io_tlb_orig_addr[index]; buffer.offset += (long)dma_addr & ((1 << IO_TLB_SHIFT) - 1); buffer.page += buffer.offset >> PAGE_SHIFT; buffer.offset &= PAGE_SIZE - 1; return buffer; } static void __sync_single(struct swiotlb_phys_addr buffer, char *dma_addr, size_t size, int dir) { if (PageHighMem(buffer.page)) { size_t len, bytes; char *dev, *host, *kmp; len = size; while (len != 0) { unsigned long flags; bytes = len; if ((bytes + buffer.offset) > PAGE_SIZE) bytes = PAGE_SIZE - buffer.offset; local_irq_save(flags); /* protects KM_BOUNCE_READ */ kmp = kmap_atomic(buffer.page, KM_BOUNCE_READ); dev = dma_addr + size - len; host = kmp + buffer.offset; if (dir == DMA_FROM_DEVICE) memcpy(host, dev, bytes); else memcpy(dev, host, bytes); kunmap_atomic(kmp, KM_BOUNCE_READ); local_irq_restore(flags); len -= bytes; buffer.page++; buffer.offset = 0; } } else { void *v = page_address(buffer.page) + buffer.offset; if (dir == DMA_TO_DEVICE) memcpy(dma_addr, v, size); else memcpy(v, dma_addr, size); } } /* * Allocates bounce buffer and returns its kernel virtual address. */ static void * map_single(struct device *hwdev, struct swiotlb_phys_addr buffer, size_t size, int dir) { unsigned long flags; char *dma_addr; unsigned int nslots, stride, index, wrap; int i; unsigned long start_dma_addr; unsigned long mask; unsigned long offset_slots; unsigned long max_slots; struct swiotlb_phys_addr slot_buf; mask = dma_get_seg_boundary(hwdev); start_dma_addr = swiotlb_virt_to_bus(io_tlb_start) & mask; offset_slots = ALIGN(start_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; /* * Carefully handle integer overflow which can occur when mask == ~0UL. */ max_slots = mask + 1 ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); /* * For mappings greater than a page, we limit the stride (and * hence alignment) to a page size. */ nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; if (size > PAGE_SIZE) stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT)); else stride = 1; BUG_ON(!nslots); /* * Find suitable number of IO TLB entries size that will fit this * request and allocate a buffer from that IO TLB pool. */ spin_lock_irqsave(&io_tlb_lock, flags); index = ALIGN(io_tlb_index, stride); if (index >= io_tlb_nslabs) index = 0; wrap = index; do { while (iommu_is_span_boundary(index, nslots, offset_slots, max_slots)) { index += stride; if (index >= io_tlb_nslabs) index = 0; if (index == wrap) goto not_found; } /* * If we find a slot that indicates we have 'nslots' number of * contiguous buffers, we allocate the buffers from that slot * and mark the entries as '0' indicating unavailable. */ if (io_tlb_list[index] >= nslots) { int count = 0; for (i = index; i < (int) (index + nslots); i++) io_tlb_list[i] = 0; for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--) io_tlb_list[i] = ++count; dma_addr = io_tlb_start + (index << IO_TLB_SHIFT); /* * Update the indices to avoid searching in the next * round. */ io_tlb_index = ((index + nslots) < io_tlb_nslabs ? (index + nslots) : 0); goto found; } index += stride; if (index >= io_tlb_nslabs) index = 0; } while (index != wrap); not_found: spin_unlock_irqrestore(&io_tlb_lock, flags); return NULL; found: spin_unlock_irqrestore(&io_tlb_lock, flags); /* * 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. */ slot_buf = buffer; for (i = 0; i < nslots; i++) { slot_buf.page += slot_buf.offset >> PAGE_SHIFT; slot_buf.offset &= PAGE_SIZE - 1; io_tlb_orig_addr[index+i] = slot_buf; slot_buf.offset += 1 << IO_TLB_SHIFT; } if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) __sync_single(buffer, dma_addr, size, DMA_TO_DEVICE); return dma_addr; } /* * dma_addr is the kernel virtual address of the bounce buffer to unmap. */ static void unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) { unsigned long flags; int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; struct swiotlb_phys_addr buffer = swiotlb_bus_to_phys_addr(dma_addr); /* * First, sync the memory before unmapping the entry */ if ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)) /* * bounce... copy the data back into the original buffer * and * delete the bounce buffer. */ __sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE); /* * Return the buffer to the free list by setting the corresponding * entries to indicate the number of contigous entries available. * While returning the entries to the free list, we merge the entries * with slots below and above the pool being returned. */ spin_lock_irqsave(&io_tlb_lock, flags); { count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ? io_tlb_list[index + nslots] : 0); /* * Step 1: return the slots to the free list, merging the * slots with superceeding slots */ for (i = index + nslots - 1; i >= index; i--) io_tlb_list[i] = ++count; /* * Step 2: merge the returned slots with the preceding slots, * if available (non zero) */ for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--) io_tlb_list[i] = ++count; } spin_unlock_irqrestore(&io_tlb_lock, flags); } static void sync_single(struct device *hwdev, char *dma_addr, size_t size, int dir, int target) { struct swiotlb_phys_addr buffer = swiotlb_bus_to_phys_addr(dma_addr); switch (target) { case SYNC_FOR_CPU: if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) __sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE); else BUG_ON(dir != DMA_TO_DEVICE); break; case SYNC_FOR_DEVICE: if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) __sync_single(buffer, dma_addr, size, DMA_TO_DEVICE); else BUG_ON(dir != DMA_FROM_DEVICE); break; default: BUG(); } } void * swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags) { dma_addr_t dev_addr; void *ret; int order = get_order(size); u64 dma_mask = DMA_32BIT_MASK; if (hwdev && hwdev->coherent_dma_mask) dma_mask = hwdev->coherent_dma_mask; ret = (void *)__get_free_pages(flags, order); if (ret && !is_buffer_dma_capable(dma_mask, swiotlb_virt_to_bus(ret), size)) { /* * The allocated memory isn't reachable by the device. * Fall back on swiotlb_map_single(). */ free_pages((unsigned long) ret, order); ret = NULL; } if (!ret) { /* * We are either out of memory or the device can't DMA * to GFP_DMA memory; fall back on * swiotlb_map_single(), which will grab memory from * the lowest available address range. */ struct swiotlb_phys_addr buffer; buffer.page = virt_to_page(NULL); buffer.offset = 0; ret = map_single(hwdev, buffer, size, DMA_FROM_DEVICE); if (!ret) return NULL; } memset(ret, 0, size); dev_addr = swiotlb_virt_to_bus(ret); /* Confirm address can be DMA'd by device */ if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) { printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n", (unsigned long long)dma_mask, (unsigned long long)dev_addr); /* DMA_TO_DEVICE to avoid memcpy in unmap_single */ unmap_single(hwdev, ret, size, DMA_TO_DEVICE); return NULL; } *dma_handle = dev_addr; return ret; } void swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle) { WARN_ON(irqs_disabled()); if (!is_swiotlb_buffer(vaddr)) free_pages((unsigned long) vaddr, get_order(size)); else /* DMA_TO_DEVICE to avoid memcpy in unmap_single */ unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE); } static void swiotlb_full(struct device *dev, size_t size, int dir, int do_panic) { /* * 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. */ printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at " "device %s\n", size, dev ? dev->bus_id : "?"); if (size > io_tlb_overflow && do_panic) { if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) panic("DMA: Memory would be corrupted\n"); if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) panic("DMA: Random memory would be DMAed\n"); } } /* * Map a single buffer of the indicated size for DMA in streaming mode. The * physical address to use is returned. * * Once the device is given the dma address, the device owns this memory until * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed. */ dma_addr_t swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size, int dir, struct dma_attrs *attrs) { dma_addr_t dev_addr = swiotlb_virt_to_bus(ptr); void *map; struct swiotlb_phys_addr buffer; BUG_ON(dir == DMA_NONE); /* * If the pointer passed in happens to be in the device's DMA window, * we can safely return the device addr and not worry about bounce * buffering it. */ if (!address_needs_mapping(hwdev, dev_addr, size) && !range_needs_mapping(ptr, size)) return dev_addr; /* * Oh well, have to allocate and map a bounce buffer. */ buffer.page = virt_to_page(ptr); buffer.offset = (unsigned long)ptr & ~PAGE_MASK; map = map_single(hwdev, buffer, size, dir); if (!map) { swiotlb_full(hwdev, size, dir, 1); map = io_tlb_overflow_buffer; } dev_addr = swiotlb_virt_to_bus(map); /* * Ensure that the address returned is DMA'ble */ if (address_needs_mapping(hwdev, dev_addr, size)) panic("map_single: bounce buffer is not DMA'ble"); return dev_addr; } EXPORT_SYMBOL(swiotlb_map_single_attrs); dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir) { return swiotlb_map_single_attrs(hwdev, ptr, size, dir, NULL); } /* * Unmap a single streaming mode DMA translation. The dma_addr and size must * match what was provided for in a previous swiotlb_map_single call. All * other usages are undefined. * * After this call, reads by the cpu to the buffer are guaranteed to see * whatever the device wrote there. */ void swiotlb_unmap_single_attrs(struct device *hwdev, dma_addr_t dev_addr, size_t size, int dir, struct dma_attrs *attrs) { char *dma_addr = swiotlb_bus_to_virt(dev_addr); BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(dma_addr)) unmap_single(hwdev, dma_addr, size, dir); else if (dir == DMA_FROM_DEVICE) dma_mark_clean(dma_addr, size); } EXPORT_SYMBOL(swiotlb_unmap_single_attrs); void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size, int dir) { return swiotlb_unmap_single_attrs(hwdev, dev_addr, size, dir, NULL); } /* * Make physical memory consistent for a single streaming mode DMA translation * after a transfer. * * If you perform a swiotlb_map_single() but wish to interrogate the buffer * using the cpu, yet do not wish to teardown the dma mapping, you must * call this function before doing so. At the next point you give the dma * address back to the card, you must first perform a * swiotlb_dma_sync_for_device, and then the device again owns the buffer */ static void swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, size_t size, int dir, int target) { char *dma_addr = swiotlb_bus_to_virt(dev_addr); BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(dma_addr)) sync_single(hwdev, dma_addr, size, dir, target); else if (dir == DMA_FROM_DEVICE) dma_mark_clean(dma_addr, size); } void swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, size_t size, int dir) { swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU); } void swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, size_t size, int dir) { swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE); } /* * Same as above, but for a sub-range of the mapping. */ static void swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr, unsigned long offset, size_t size, int dir, int target) { char *dma_addr = swiotlb_bus_to_virt(dev_addr) + offset; BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(dma_addr)) sync_single(hwdev, dma_addr, size, dir, target); else if (dir == DMA_FROM_DEVICE) dma_mark_clean(dma_addr, size); } void swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr, unsigned long offset, size_t size, int dir) { swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir, SYNC_FOR_CPU); } void swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr, unsigned long offset, size_t size, int dir) { swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir, SYNC_FOR_DEVICE); } void swiotlb_unmap_sg_attrs(struct device *, struct scatterlist *, int, int, struct dma_attrs *); /* * Map a set of buffers described by scatterlist in streaming mode for DMA. * This is the scatter-gather version of the above swiotlb_map_single * interface. Here the scatter gather list elements are each tagged with the * appropriate dma address and length. They are obtained via * sg_dma_{address,length}(SG). * * 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_single are the * same here. */ int swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, int dir, struct dma_attrs *attrs) { struct scatterlist *sg; struct swiotlb_phys_addr buffer; dma_addr_t dev_addr; int i; BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) { dev_addr = swiotlb_sg_to_bus(sg); if (range_needs_mapping(sg_virt(sg), sg->length) || address_needs_mapping(hwdev, dev_addr, sg->length)) { void *map; buffer.page = sg_page(sg); buffer.offset = sg->offset; map = map_single(hwdev, buffer, sg->length, dir); if (!map) { /* Don't panic here, we expect map_sg users to do proper error handling. */ swiotlb_full(hwdev, sg->length, dir, 0); swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir, attrs); sgl[0].dma_length = 0; return 0; } sg->dma_address = swiotlb_virt_to_bus(map); } else sg->dma_address = dev_addr; sg->dma_length = sg->length; } return nelems; } EXPORT_SYMBOL(swiotlb_map_sg_attrs); int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, int dir) { return swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL); } /* * Unmap a set of streaming mode DMA translations. Again, cpu read rules * concerning calls here are the same as for swiotlb_unmap_single() above. */ void swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, int dir, struct dma_attrs *attrs) { struct scatterlist *sg; int i; BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) { if (sg->dma_address != swiotlb_sg_to_bus(sg)) unmap_single(hwdev, swiotlb_bus_to_virt(sg->dma_address), sg->dma_length, dir); else if (dir == DMA_FROM_DEVICE) dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length); } } EXPORT_SYMBOL(swiotlb_unmap_sg_attrs); void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, int dir) { return swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL); } /* * Make physical memory consistent for a set of streaming mode DMA translations * after a transfer. * * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules * and usage. */ static void swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, int dir, int target) { struct scatterlist *sg; int i; BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) { if (sg->dma_address != swiotlb_sg_to_bus(sg)) sync_single(hwdev, swiotlb_bus_to_virt(sg->dma_address), sg->dma_length, dir, target); else if (dir == DMA_FROM_DEVICE) dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length); } } void swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, int nelems, int dir) { swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU); } void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, int nelems, int dir) { 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 == swiotlb_virt_to_bus(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 * during bus mastering, then you would pass 0x00ffffff as the mask to * this function. */ int swiotlb_dma_supported(struct device *hwdev, u64 mask) { return swiotlb_virt_to_bus(io_tlb_end - 1) <= mask; } EXPORT_SYMBOL(swiotlb_map_single); EXPORT_SYMBOL(swiotlb_unmap_single); EXPORT_SYMBOL(swiotlb_map_sg); EXPORT_SYMBOL(swiotlb_unmap_sg); EXPORT_SYMBOL(swiotlb_sync_single_for_cpu); EXPORT_SYMBOL(swiotlb_sync_single_for_device); EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_cpu); EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device); EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu); EXPORT_SYMBOL(swiotlb_sync_sg_for_device); EXPORT_SYMBOL(swiotlb_dma_mapping_error); EXPORT_SYMBOL(swiotlb_alloc_coherent); EXPORT_SYMBOL(swiotlb_free_coherent); EXPORT_SYMBOL(swiotlb_dma_supported);