X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=lib%2Fswiotlb.c;h=5fddf720da73e42b6568b80f64234e47033bc142;hb=4de85cd6d6018825e19f76f1208775f23ecc393f;hp=170cf56af6a99b00fd1f6808d807a59a7fd24a58;hpb=ceb5ac3264686e75e6951de6a18d4baa9bdecb92;p=safe%2Fjmp%2Flinux-2.6 diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 170cf56..5fddf72 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -97,6 +98,8 @@ static phys_addr_t *io_tlb_orig_addr; */ static DEFINE_SPINLOCK(io_tlb_lock); +static int late_alloc; + static int __init setup_io_tlb_npages(char *str) { @@ -109,49 +112,22 @@ setup_io_tlb_npages(char *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(struct device *hwdev, phys_addr_t paddr) -{ - return paddr; -} - -phys_addr_t __weak swiotlb_bus_to_phys(dma_addr_t baddr) -{ - return baddr; -} - +/* Note that this doesn't work with highmem page */ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev, volatile void *address) { - return swiotlb_phys_to_bus(hwdev, virt_to_phys(address)); + return phys_to_dma(hwdev, 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(phys_addr_t paddr, size_t size) -{ - return 0; -} - -static void swiotlb_print_info(unsigned long bytes) +void swiotlb_print_info(void) { + unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; phys_addr_t pstart, pend; pstart = virt_to_phys(io_tlb_start); @@ -169,7 +145,7 @@ static void swiotlb_print_info(unsigned long bytes) * structures for the software IO TLB used to implement the DMA API. */ void __init -swiotlb_init_with_default_size(size_t default_size) +swiotlb_init_with_default_size(size_t default_size, int verbose) { unsigned long i, bytes; @@ -183,7 +159,7 @@ swiotlb_init_with_default_size(size_t default_size) /* * Get IO TLB memory from the low pages */ - io_tlb_start = swiotlb_alloc_boot(bytes, io_tlb_nslabs); + io_tlb_start = alloc_bootmem_low_pages(bytes); if (!io_tlb_start) panic("Cannot allocate SWIOTLB buffer"); io_tlb_end = io_tlb_start + bytes; @@ -205,14 +181,14 @@ swiotlb_init_with_default_size(size_t default_size) 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); + if (verbose) + swiotlb_print_info(); } void __init -swiotlb_init(void) +swiotlb_init(int verbose) { - swiotlb_init_with_default_size(64 * (1<<20)); /* default to 64MB */ + swiotlb_init_with_default_size(64 * (1<<20), verbose); /* default to 64MB */ } /* @@ -239,7 +215,8 @@ swiotlb_late_init_with_default_size(size_t default_size) 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); + io_tlb_start = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, + order); if (io_tlb_start) break; order--; @@ -288,7 +265,9 @@ swiotlb_late_init_with_default_size(size_t default_size) if (!io_tlb_overflow_buffer) goto cleanup4; - swiotlb_print_info(bytes); + swiotlb_print_info(); + + late_alloc = 1; return 0; @@ -309,20 +288,36 @@ cleanup1: 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(phys_addr_t paddr, size_t size) +void __init swiotlb_free(void) { - return swiotlb_force || swiotlb_arch_range_needs_mapping(paddr, size); + if (!io_tlb_overflow_buffer) + return; + + if (late_alloc) { + free_pages((unsigned long)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 * + sizeof(int))); + free_pages((unsigned long)io_tlb_start, + get_order(io_tlb_nslabs << IO_TLB_SHIFT)); + } else { + free_bootmem_late(__pa(io_tlb_overflow_buffer), + io_tlb_overflow); + free_bootmem_late(__pa(io_tlb_orig_addr), + io_tlb_nslabs * sizeof(phys_addr_t)); + free_bootmem_late(__pa(io_tlb_list), + io_tlb_nslabs * sizeof(int)); + free_bootmem_late(__pa(io_tlb_start), + io_tlb_nslabs << IO_TLB_SHIFT); + } } -static int is_swiotlb_buffer(char *addr) +static int is_swiotlb_buffer(phys_addr_t paddr) { - return addr >= io_tlb_start && addr < io_tlb_end; + return paddr >= virt_to_phys(io_tlb_start) && + paddr < virt_to_phys(io_tlb_end); } /* @@ -341,7 +336,7 @@ static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size, unsigned long flags; while (size) { - sz = min(PAGE_SIZE - offset, size); + sz = min_t(size_t, PAGE_SIZE - offset, size); local_irq_save(flags); buffer = kmap_atomic(pfn_to_page(pfn), @@ -476,7 +471,7 @@ found: * 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) +do_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; @@ -491,7 +486,7 @@ unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) /* * Return the buffer to the free list by setting the corresponding - * entries to indicate the number of contigous entries available. + * entries to indicate the number of contiguous entries available. * While returning the entries to the free list, we merge the entries * with slots below and above the pool being returned. */ @@ -555,9 +550,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, 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(hwdev, ret), - size)) { + if (ret && swiotlb_virt_to_bus(hwdev, ret) + size - 1 > dma_mask) { /* * The allocated memory isn't reachable by the device. */ @@ -579,13 +572,13 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, dev_addr = swiotlb_virt_to_bus(hwdev, ret); /* Confirm address can be DMA'd by device */ - if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) { + if (dev_addr + size - 1 > dma_mask) { 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); + do_unmap_single(hwdev, ret, size, DMA_TO_DEVICE); return NULL; } *dma_handle = dev_addr; @@ -595,14 +588,16 @@ EXPORT_SYMBOL(swiotlb_alloc_coherent); void swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, - dma_addr_t dma_handle) + dma_addr_t dev_addr) { + phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); + WARN_ON(irqs_disabled()); - if (!is_swiotlb_buffer(vaddr)) - free_pages((unsigned long) vaddr, get_order(size)); + if (!is_swiotlb_buffer(paddr)) + 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); + do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE); } EXPORT_SYMBOL(swiotlb_free_coherent); @@ -619,12 +614,15 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic) printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at " "device %s\n", size, dev ? dev_name(dev) : "?"); - 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"); - } + if (size <= io_tlb_overflow || !do_panic) + return; + + 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"); } /* @@ -640,8 +638,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, struct dma_attrs *attrs) { phys_addr_t phys = page_to_phys(page) + offset; - void *ptr = page_address(page) + offset; - dma_addr_t dev_addr = swiotlb_phys_to_bus(dev, phys); + dma_addr_t dev_addr = phys_to_dma(dev, phys); void *map; BUG_ON(dir == DMA_NONE); @@ -650,8 +647,7 @@ 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 (!address_needs_mapping(dev, dev_addr, size) && - !range_needs_mapping(virt_to_phys(ptr), size)) + if (dma_capable(dev, dev_addr, size) && !swiotlb_force) return dev_addr; /* @@ -668,7 +664,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, /* * Ensure that the address returned is DMA'ble */ - if (address_needs_mapping(dev, dev_addr, size)) + if (!dma_capable(dev, dev_addr, size)) panic("map_single: bounce buffer is not DMA'ble"); return dev_addr; @@ -683,17 +679,35 @@ EXPORT_SYMBOL_GPL(swiotlb_map_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, int dir) +{ + phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); + + BUG_ON(dir == DMA_NONE); + + if (is_swiotlb_buffer(paddr)) { + do_unmap_single(hwdev, phys_to_virt(paddr), size, dir); + return; + } + + if (dir != DMA_FROM_DEVICE) + return; + + /* + * phys_to_virt doesn't work with hihgmem page but we could + * call dma_mark_clean() with hihgmem page here. However, we + * are fine since dma_mark_clean() is null on POWERPC. We can + * make dma_mark_clean() take a physical address if necessary. + */ + 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, 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); + unmap_single(hwdev, dev_addr, size, dir); } EXPORT_SYMBOL_GPL(swiotlb_unmap_page); @@ -711,13 +725,19 @@ 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); + phys_addr_t paddr = dma_to_phys(hwdev, 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); + + if (is_swiotlb_buffer(paddr)) { + sync_single(hwdev, phys_to_virt(paddr), size, dir, target); + return; + } + + if (dir != DMA_FROM_DEVICE) + return; + + dma_mark_clean(phys_to_virt(paddr), size); } void @@ -744,13 +764,7 @@ 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); + swiotlb_sync_single(hwdev, dev_addr + offset, size, dir, target); } void @@ -800,10 +814,10 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, for_each_sg(sgl, sg, nelems, i) { phys_addr_t paddr = sg_phys(sg); - dma_addr_t dev_addr = swiotlb_phys_to_bus(hwdev, paddr); + dma_addr_t dev_addr = phys_to_dma(hwdev, paddr); - if (range_needs_mapping(paddr, sg->length) || - address_needs_mapping(hwdev, dev_addr, sg->length)) { + if (swiotlb_force || + !dma_capable(hwdev, dev_addr, sg->length)) { void *map = map_single(hwdev, sg_phys(sg), sg->length, dir); if (!map) { @@ -845,13 +859,9 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, BUG_ON(dir == DMA_NONE); - for_each_sg(sgl, sg, nelems, i) { - if (sg->dma_address != swiotlb_phys_to_bus(hwdev, sg_phys(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); - } + for_each_sg(sgl, sg, nelems, i) + unmap_single(hwdev, sg->dma_address, sg->dma_length, dir); + } EXPORT_SYMBOL(swiotlb_unmap_sg_attrs); @@ -877,15 +887,9 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl, struct scatterlist *sg; int i; - BUG_ON(dir == DMA_NONE); - - for_each_sg(sgl, sg, nelems, i) { - if (sg->dma_address != swiotlb_phys_to_bus(hwdev, sg_phys(sg))) - sync_single(hwdev, swiotlb_bus_to_virt(sg->dma_address), + for_each_sg(sgl, sg, nelems, i) + swiotlb_sync_single(hwdev, 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