diff options
Diffstat (limited to 'lib/swiotlb.c')
| -rw-r--r-- | lib/swiotlb.c | 217 |
1 files changed, 122 insertions, 95 deletions
diff --git a/lib/swiotlb.c b/lib/swiotlb.c index ac25cd28e80..34e3082632d 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -28,6 +28,7 @@ #include <linux/types.h> #include <linux/ctype.h> #include <linux/highmem.h> +#include <linux/gfp.h> #include <asm/io.h> #include <asm/dma.h> @@ -49,19 +50,11 @@ */ #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 unmap_single and - * sync_single_*, to see if the memory was in fact allocated by this + * Used to do a quick range check in swiotlb_tbl_unmap_single and + * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this * API. */ static char *io_tlb_start, *io_tlb_end; @@ -97,6 +90,8 @@ 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) { @@ -109,6 +104,7 @@ setup_io_tlb_npages(char *str) ++str; if (!strcmp(str, "force")) swiotlb_force = 1; + return 1; } __setup("swiotlb=", setup_io_tlb_npages); @@ -121,8 +117,9 @@ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev, return phys_to_dma(hwdev, virt_to_phys(address)); } -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); @@ -135,28 +132,14 @@ static void swiotlb_print_info(unsigned long bytes) (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) +void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) { 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; + bytes = nslabs << IO_TLB_SHIFT; - /* - * Get IO TLB memory from the low pages - */ - io_tlb_start = alloc_bootmem_low_pages(bytes); - if (!io_tlb_start) - panic("Cannot allocate SWIOTLB buffer"); + io_tlb_nslabs = nslabs; + io_tlb_start = tlb; io_tlb_end = io_tlb_start + bytes; /* @@ -176,14 +159,40 @@ 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"); + if (verbose) + swiotlb_print_info(); +} + +/* + * 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, int verbose) +{ + unsigned long 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 = alloc_bootmem_low_pages(bytes); + if (!io_tlb_start) + panic("Cannot allocate SWIOTLB buffer"); - swiotlb_print_info(bytes); + swiotlb_init_with_tbl(io_tlb_start, io_tlb_nslabs, verbose); } 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 */ } /* @@ -260,7 +269,9 @@ 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; @@ -281,6 +292,32 @@ cleanup1: return -ENOMEM; } +void __init swiotlb_free(void) +{ + 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(phys_addr_t paddr) { return paddr >= virt_to_phys(io_tlb_start) && @@ -290,8 +327,8 @@ static int is_swiotlb_buffer(phys_addr_t paddr) /* * Bounce: copy the swiotlb buffer back to the original dma location */ -static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size, - enum dma_data_direction dir) +void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size, + enum dma_data_direction dir) { unsigned long pfn = PFN_DOWN(phys); @@ -327,26 +364,25 @@ static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size, memcpy(phys_to_virt(phys), dma_addr, size); } } +EXPORT_SYMBOL_GPL(swiotlb_bounce); -/* - * Allocates bounce buffer and returns its kernel virtual address. - */ -static void * -map_single(struct device *hwdev, phys_addr_t phys, size_t size, int dir) +void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, + phys_addr_t phys, size_t size, + enum dma_data_direction 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; mask = dma_get_seg_boundary(hwdev); - start_dma_addr = swiotlb_virt_to_bus(hwdev, io_tlb_start) & mask; - offset_slots = ALIGN(start_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + tbl_dma_addr &= mask; + + offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; /* * Carefully handle integer overflow which can occur when mask == ~0UL. @@ -433,12 +469,27 @@ found: return dma_addr; } +EXPORT_SYMBOL_GPL(swiotlb_tbl_map_single); + +/* + * Allocates bounce buffer and returns its kernel virtual address. + */ + +static void * +map_single(struct device *hwdev, phys_addr_t phys, size_t size, + enum dma_data_direction dir) +{ + dma_addr_t start_dma_addr = swiotlb_virt_to_bus(hwdev, io_tlb_start); + + return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size, dir); +} /* * dma_addr is the kernel virtual address of the bounce buffer to unmap. */ -static void -do_unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) +void +swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr, size_t size, + enum dma_data_direction dir) { unsigned long flags; int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; @@ -453,7 +504,7 @@ do_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. */ @@ -476,10 +527,12 @@ do_unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) } spin_unlock_irqrestore(&io_tlb_lock, flags); } +EXPORT_SYMBOL_GPL(swiotlb_tbl_unmap_single); -static void -sync_single(struct device *hwdev, char *dma_addr, size_t size, - int dir, int target) +void +swiotlb_tbl_sync_single(struct device *hwdev, char *dma_addr, size_t size, + enum dma_data_direction dir, + enum dma_sync_target target) { int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; phys_addr_t phys = io_tlb_orig_addr[index]; @@ -503,6 +556,7 @@ sync_single(struct device *hwdev, char *dma_addr, size_t size, BUG(); } } +EXPORT_SYMBOL_GPL(swiotlb_tbl_sync_single); void * swiotlb_alloc_coherent(struct device *hwdev, size_t size, @@ -517,7 +571,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_mask = hwdev->coherent_dma_mask; ret = (void *)__get_free_pages(flags, order); - if (ret && swiotlb_virt_to_bus(hwdev, ret) + size > dma_mask) { + if (ret && swiotlb_virt_to_bus(hwdev, ret) + size - 1 > dma_mask) { /* * The allocated memory isn't reachable by the device. */ @@ -526,8 +580,8 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, } if (!ret) { /* - * We are either out of memory or the device can't DMA - * to GFP_DMA memory; fall back on map_single(), which + * We are either out of memory or the device can't DMA to + * GFP_DMA memory; fall back on map_single(), which * will grab memory from the lowest available address range. */ ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE); @@ -539,13 +593,13 @@ 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 (dev_addr + size > dma_mask) { + 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 */ - do_unmap_single(hwdev, ret, size, DMA_TO_DEVICE); + swiotlb_tbl_unmap_single(hwdev, ret, size, DMA_TO_DEVICE); return NULL; } *dma_handle = dev_addr; @@ -563,13 +617,14 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, if (!is_swiotlb_buffer(paddr)) free_pages((unsigned long)vaddr, get_order(size)); else - /* DMA_TO_DEVICE to avoid memcpy in unmap_single */ - do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE); + /* DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single */ + swiotlb_tbl_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE); } EXPORT_SYMBOL(swiotlb_free_coherent); static void -swiotlb_full(struct device *dev, size_t size, int dir, int do_panic) +swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir, + int do_panic) { /* * Ran out of IOMMU space for this operation. This is very bad. @@ -647,14 +702,14 @@ EXPORT_SYMBOL_GPL(swiotlb_map_page); * whatever the device wrote there. */ static void unmap_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir) + size_t size, enum dma_data_direction 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); + swiotlb_tbl_unmap_single(hwdev, phys_to_virt(paddr), size, dir); return; } @@ -690,14 +745,16 @@ EXPORT_SYMBOL_GPL(swiotlb_unmap_page); */ static void swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir, int target) + size_t size, enum dma_data_direction dir, + enum dma_sync_target target) { phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(paddr)) { - sync_single(hwdev, phys_to_virt(paddr), size, dir, target); + swiotlb_tbl_sync_single(hwdev, phys_to_virt(paddr), size, dir, + target); return; } @@ -724,37 +781,6 @@ swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, EXPORT_SYMBOL(swiotlb_sync_single_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) -{ - swiotlb_sync_single(hwdev, dev_addr + offset, size, dir, target); -} - -void -swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - unsigned long offset, size_t size, - enum dma_data_direction dir) -{ - swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir, - SYNC_FOR_CPU); -} -EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_cpu); - -void -swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr, - unsigned long offset, size_t size, - enum dma_data_direction dir) -{ - swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir, - SYNC_FOR_DEVICE); -} -EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device); - -/* * Map a set of buffers described by scatterlist in streaming mode for DMA. * This is the scatter-gather version of the above swiotlb_map_page * interface. Here the scatter gather list elements are each tagged with the @@ -807,7 +833,7 @@ EXPORT_SYMBOL(swiotlb_map_sg_attrs); int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, - int dir) + enum dma_data_direction dir) { return swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL); } @@ -834,7 +860,7 @@ EXPORT_SYMBOL(swiotlb_unmap_sg_attrs); void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, - int dir) + enum dma_data_direction dir) { return swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL); } @@ -849,7 +875,8 @@ EXPORT_SYMBOL(swiotlb_unmap_sg); */ static void swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl, - int nelems, int dir, int target) + int nelems, enum dma_data_direction dir, + enum dma_sync_target target) { struct scatterlist *sg; int i; |