diff options
Diffstat (limited to 'lib/swiotlb.c')
| -rw-r--r-- | lib/swiotlb.c | 882 |
1 files changed, 521 insertions, 361 deletions
diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 025922807e6..4abda074ea4 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -14,16 +14,21 @@ * 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. + * 08/12/11 beckyb Add highmem support */ #include <linux/cache.h> #include <linux/dma-mapping.h> #include <linux/mm.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/spinlock.h> #include <linux/string.h> +#include <linux/swiotlb.h> +#include <linux/pfn.h> #include <linux/types.h> #include <linux/ctype.h> +#include <linux/highmem.h> +#include <linux/gfp.h> #include <asm/io.h> #include <asm/dma.h> @@ -31,26 +36,14 @@ #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/iommu-helper.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/swiotlb.h> #define OFFSET(val,align) ((unsigned long) \ ( (val) & ( (align) - 1))) -#define SG_ENT_VIRT_ADDRESS(sg) (sg_virt((sg))) -#define SG_ENT_PHYS_ADDRESS(sg) virt_to_bus(SG_ENT_VIRT_ADDRESS(sg)) - -/* - * Maximum allowable number of contiguous slabs to map, - * must be a power of 2. What is the appropriate value ? - * The complexity of {map,unmap}_single is linearly dependent on this value. - */ -#define IO_TLB_SEGSIZE 128 - -/* - * log of the size of each IO TLB slab. The number of slabs is command line - * controllable. - */ -#define IO_TLB_SHIFT 11 - #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT)) /* @@ -60,25 +53,17 @@ */ #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 + * 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; +static phys_addr_t io_tlb_start, io_tlb_end; /* - * The number of IO TLB blocks (in groups of 64) betweeen io_tlb_start and + * The number of IO TLB blocks (in groups of 64) between io_tlb_start and * io_tlb_end. This is command line adjustable via setup_io_tlb_npages. */ static unsigned long io_tlb_nslabs; @@ -88,7 +73,7 @@ static unsigned long io_tlb_nslabs; */ static unsigned long io_tlb_overflow = 32*1024; -void *io_tlb_overflow_buffer; +static phys_addr_t io_tlb_overflow_buffer; /* * This is a free list describing the number of free entries available from @@ -101,13 +86,16 @@ static unsigned int io_tlb_index; * We need to save away the original address corresponding to a mapped entry * for the sync operations. */ -static unsigned char **io_tlb_orig_addr; +#define INVALID_PHYS_ADDR (~(phys_addr_t)0) +static phys_addr_t *io_tlb_orig_addr; /* * Protect the above data structures in the map and unmap calls */ static DEFINE_SPINLOCK(io_tlb_lock); +static int late_alloc; + static int __init setup_io_tlb_npages(char *str) { @@ -120,61 +108,130 @@ setup_io_tlb_npages(char *str) ++str; if (!strcmp(str, "force")) swiotlb_force = 1; - return 1; + + return 0; } -__setup("swiotlb=", setup_io_tlb_npages); +early_param("swiotlb", setup_io_tlb_npages); /* make io_tlb_overflow tunable too? */ -/* - * 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 swiotlb_nr_tbl(void) { - unsigned long i, bytes; + return io_tlb_nslabs; +} +EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); - if (!io_tlb_nslabs) { - io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); +/* default to 64MB */ +#define IO_TLB_DEFAULT_SIZE (64UL<<20) +unsigned long swiotlb_size_or_default(void) +{ + unsigned long size; + + size = io_tlb_nslabs << IO_TLB_SHIFT; + + return size ? size : (IO_TLB_DEFAULT_SIZE); +} + +/* Note that this doesn't work with highmem page */ +static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev, + volatile void *address) +{ + return phys_to_dma(hwdev, virt_to_phys(address)); +} + +static bool no_iotlb_memory; + +void swiotlb_print_info(void) +{ + unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; + unsigned char *vstart, *vend; + + if (no_iotlb_memory) { + pr_warn("software IO TLB: No low mem\n"); + return; } - bytes = io_tlb_nslabs << IO_TLB_SHIFT; + vstart = phys_to_virt(io_tlb_start); + vend = phys_to_virt(io_tlb_end); + + printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n", + (unsigned long long)io_tlb_start, + (unsigned long long)io_tlb_end, + bytes >> 20, vstart, vend - 1); +} + +int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) +{ + void *v_overflow_buffer; + unsigned long i, bytes; + + bytes = nslabs << IO_TLB_SHIFT; + + io_tlb_nslabs = nslabs; + io_tlb_start = __pa(tlb); + io_tlb_end = io_tlb_start + bytes; /* - * Get IO TLB memory from the low pages + * Get the overflow emergency buffer */ - io_tlb_start = alloc_bootmem_low_pages(bytes); - if (!io_tlb_start) - panic("Cannot allocate SWIOTLB buffer"); - io_tlb_end = io_tlb_start + bytes; + v_overflow_buffer = memblock_virt_alloc_low_nopanic( + PAGE_ALIGN(io_tlb_overflow), + PAGE_SIZE); + if (!v_overflow_buffer) + return -ENOMEM; + + io_tlb_overflow_buffer = __pa(v_overflow_buffer); /* * 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_list = memblock_virt_alloc( + PAGE_ALIGN(io_tlb_nslabs * sizeof(int)), + PAGE_SIZE); + io_tlb_orig_addr = memblock_virt_alloc( + PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)), + PAGE_SIZE); + for (i = 0; i < io_tlb_nslabs; i++) { + io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); + io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; + } io_tlb_index = 0; - io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(char *)); - /* - * 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"); + if (verbose) + swiotlb_print_info(); - printk(KERN_INFO "Placing software IO TLB between 0x%lx - 0x%lx\n", - virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end)); + return 0; } -void __init -swiotlb_init(void) +/* + * 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(int verbose) { - swiotlb_init_with_default_size(64 * (1<<20)); /* default to 64MB */ + size_t default_size = IO_TLB_DEFAULT_SIZE; + unsigned char *vstart; + 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 */ + vstart = memblock_virt_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE); + if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) + return; + + if (io_tlb_start) + memblock_free_early(io_tlb_start, + PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + pr_warn("Cannot allocate SWIOTLB buffer"); + no_iotlb_memory = true; } /* @@ -185,8 +242,10 @@ swiotlb_init(void) int swiotlb_late_init_with_default_size(size_t default_size) { - unsigned long i, bytes, req_nslabs = io_tlb_nslabs; + unsigned long bytes, req_nslabs = io_tlb_nslabs; + unsigned char *vstart = NULL; unsigned int order; + int rc = 0; if (!io_tlb_nslabs) { io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); @@ -201,24 +260,51 @@ 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 = (char *)__get_free_pages(GFP_DMA | __GFP_NOWARN, - order); - if (io_tlb_start) + vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, + order); + if (vstart) break; order--; } - if (!io_tlb_start) - goto cleanup1; - + if (!vstart) { + io_tlb_nslabs = req_nslabs; + return -ENOMEM; + } 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; } + rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs); + if (rc) + free_pages((unsigned long)vstart, order); + return rc; +} + +int +swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) +{ + unsigned long i, bytes; + unsigned char *v_overflow_buffer; + + bytes = nslabs << IO_TLB_SHIFT; + + io_tlb_nslabs = nslabs; + io_tlb_start = virt_to_phys(tlb); io_tlb_end = io_tlb_start + bytes; - memset(io_tlb_start, 0, bytes); + + memset(tlb, 0, bytes); + + /* + * Get the overflow emergency buffer + */ + v_overflow_buffer = (void *)__get_free_pages(GFP_DMA, + get_order(io_tlb_overflow)); + if (!v_overflow_buffer) + goto cleanup2; + + io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer); /* * Allocate and initialize the free list array. This array is used @@ -228,88 +314,139 @@ swiotlb_late_init_with_default_size(size_t default_size) 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; + goto cleanup3; - io_tlb_orig_addr = (unsigned char **)__get_free_pages(GFP_KERNEL, - get_order(io_tlb_nslabs * sizeof(char *))); + io_tlb_orig_addr = (phys_addr_t *) + __get_free_pages(GFP_KERNEL, + get_order(io_tlb_nslabs * + sizeof(phys_addr_t))); if (!io_tlb_orig_addr) - goto cleanup3; + goto cleanup4; - memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(char *)); + for (i = 0; i < io_tlb_nslabs; i++) { + io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); + io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; + } + io_tlb_index = 0; - /* - * 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(); - printk(KERN_INFO "Placing %luMB software IO TLB between 0x%lx - " - "0x%lx\n", bytes >> 20, - virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end)); + late_alloc = 1; 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; +cleanup3: + free_pages((unsigned long)v_overflow_buffer, + get_order(io_tlb_overflow)); + io_tlb_overflow_buffer = 0; cleanup2: - io_tlb_end = NULL; - free_pages((unsigned long)io_tlb_start, order); - io_tlb_start = NULL; -cleanup1: - io_tlb_nslabs = req_nslabs; + io_tlb_end = 0; + io_tlb_start = 0; + io_tlb_nslabs = 0; return -ENOMEM; } -static int -address_needs_mapping(struct device *hwdev, dma_addr_t addr) +void __init swiotlb_free(void) { - dma_addr_t mask = 0xffffffff; - /* If the device has a mask, use it, otherwise default to 32 bits */ - if (hwdev && hwdev->dma_mask) - mask = *hwdev->dma_mask; - return (addr & ~mask) != 0; + if (!io_tlb_orig_addr) + return; + + if (late_alloc) { + free_pages((unsigned long)phys_to_virt(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)phys_to_virt(io_tlb_start), + get_order(io_tlb_nslabs << IO_TLB_SHIFT)); + } else { + memblock_free_late(io_tlb_overflow_buffer, + PAGE_ALIGN(io_tlb_overflow)); + memblock_free_late(__pa(io_tlb_orig_addr), + PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); + memblock_free_late(__pa(io_tlb_list), + PAGE_ALIGN(io_tlb_nslabs * sizeof(int))); + memblock_free_late(io_tlb_start, + PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + } + io_tlb_nslabs = 0; } -static inline unsigned int is_span_boundary(unsigned int index, - unsigned int nslots, - unsigned long offset_slots, - unsigned long max_slots) +int is_swiotlb_buffer(phys_addr_t paddr) { - unsigned long offset = (offset_slots + index) & (max_slots - 1); - return offset + nslots > max_slots; + return paddr >= io_tlb_start && paddr < io_tlb_end; } /* - * Allocates bounce buffer and returns its kernel virtual address. + * Bounce: copy the swiotlb buffer back to the original dma location */ -static void * -map_single(struct device *hwdev, char *buffer, size_t size, int dir) +static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir) +{ + unsigned long pfn = PFN_DOWN(orig_addr); + unsigned char *vaddr = phys_to_virt(tlb_addr); + + if (PageHighMem(pfn_to_page(pfn))) { + /* The buffer does not have a mapping. Map it in and copy */ + unsigned int offset = orig_addr & ~PAGE_MASK; + char *buffer; + unsigned int sz = 0; + unsigned long flags; + + while (size) { + sz = min_t(size_t, PAGE_SIZE - offset, size); + + local_irq_save(flags); + buffer = kmap_atomic(pfn_to_page(pfn)); + if (dir == DMA_TO_DEVICE) + memcpy(vaddr, buffer + offset, sz); + else + memcpy(buffer + offset, vaddr, sz); + kunmap_atomic(buffer); + local_irq_restore(flags); + + size -= sz; + pfn++; + vaddr += sz; + offset = 0; + } + } else if (dir == DMA_TO_DEVICE) { + memcpy(vaddr, phys_to_virt(orig_addr), size); + } else { + memcpy(phys_to_virt(orig_addr), vaddr, size); + } +} + +phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, + dma_addr_t tbl_dma_addr, + phys_addr_t orig_addr, size_t size, + enum dma_data_direction dir) { unsigned long flags; - char *dma_addr; + phys_addr_t tlb_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; + if (no_iotlb_memory) + panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer"); + mask = dma_get_seg_boundary(hwdev); - start_dma_addr = virt_to_bus(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. + */ max_slots = mask + 1 ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); @@ -331,56 +468,55 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir) * 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 (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 = 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; - } while (index != wrap); + if (index == wrap) + goto not_found; + } - not_found: - spin_unlock_irqrestore(&io_tlb_lock, flags); - return NULL; - } - 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; + tlb_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); + if (printk_ratelimit()) + dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes)\n", size); + return SWIOTLB_MAP_ERROR; +found: spin_unlock_irqrestore(&io_tlb_lock, flags); /* @@ -389,37 +525,47 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir) * needed. */ for (i = 0; i < nslots; i++) - io_tlb_orig_addr[index+i] = buffer + (i << IO_TLB_SHIFT); + io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) - memcpy(dma_addr, buffer, size); + swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE); - return dma_addr; + return tlb_addr; +} +EXPORT_SYMBOL_GPL(swiotlb_tbl_map_single); + +/* + * Allocates bounce buffer and returns its kernel virtual address. + */ + +phys_addr_t map_single(struct device *hwdev, phys_addr_t phys, size_t size, + enum dma_data_direction dir) +{ + dma_addr_t start_dma_addr = phys_to_dma(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 -unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) +void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_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; - int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; - char *buffer = io_tlb_orig_addr[index]; + int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; + phys_addr_t orig_addr = io_tlb_orig_addr[index]; /* * First, sync the memory before unmapping the entry */ - if (buffer && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) - /* - * bounce... copy the data back into the original buffer * and - * delete the bounce buffer. - */ - memcpy(buffer, dma_addr, size); + if (orig_addr != INVALID_PHYS_ADDR && + ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) + swiotlb_bounce(orig_addr, tlb_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. + * 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. */ @@ -431,8 +577,10 @@ unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) * Step 1: return the slots to the free list, merging the * slots with superceeding slots */ - for (i = index + nslots - 1; i >= index; i--) + for (i = index + nslots - 1; i >= index; i--) { io_tlb_list[i] = ++count; + io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; + } /* * Step 2: merge the returned slots with the preceding slots, * if available (non zero) @@ -442,26 +590,31 @@ 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, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir, + enum dma_sync_target target) { - int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; - char *buffer = io_tlb_orig_addr[index]; + int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; + phys_addr_t orig_addr = io_tlb_orig_addr[index]; - buffer += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1)); + if (orig_addr == INVALID_PHYS_ADDR) + return; + orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1); switch (target) { case SYNC_FOR_CPU: if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) - memcpy(buffer, dma_addr, size); + swiotlb_bounce(orig_addr, tlb_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)) - memcpy(dma_addr, buffer, size); + swiotlb_bounce(orig_addr, tlb_addr, + size, DMA_TO_DEVICE); else BUG_ON(dir != DMA_FROM_DEVICE); break; @@ -469,6 +622,7 @@ 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, @@ -477,68 +631,73 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t dev_addr; void *ret; int order = get_order(size); + u64 dma_mask = DMA_BIT_MASK(32); - /* - * XXX fix me: the DMA API should pass us an explicit DMA mask - * instead, or use ZONE_DMA32 (ia64 overloads ZONE_DMA to be a ~32 - * bit range instead of a 16MB one). - */ - flags |= GFP_DMA; + if (hwdev && hwdev->coherent_dma_mask) + dma_mask = hwdev->coherent_dma_mask; ret = (void *)__get_free_pages(flags, order); - if (ret && address_needs_mapping(hwdev, virt_to_bus(ret))) { - /* - * 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) { + dev_addr = swiotlb_virt_to_bus(hwdev, ret); + if (dev_addr + size - 1 > dma_mask) { + /* + * The allocated memory isn't reachable by the device. + */ + 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. + * 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. */ - dma_addr_t handle; - handle = swiotlb_map_single(NULL, NULL, size, DMA_FROM_DEVICE); - if (swiotlb_dma_mapping_error(handle)) + phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE); + if (paddr == SWIOTLB_MAP_ERROR) return NULL; - ret = bus_to_virt(handle); - } + ret = phys_to_virt(paddr); + dev_addr = phys_to_dma(hwdev, paddr); - memset(ret, 0, size); - dev_addr = virt_to_bus(ret); - - /* Confirm address can be DMA'd by device */ - if (address_needs_mapping(hwdev, dev_addr)) { - printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n", - (unsigned long long)*hwdev->dma_mask, - (unsigned long long)dev_addr); - panic("swiotlb_alloc_coherent: allocated memory is out of " - "range for device"); + /* Confirm address can be DMA'd by device */ + 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 */ + swiotlb_tbl_unmap_single(hwdev, paddr, + size, DMA_TO_DEVICE); + return NULL; + } } + *dma_handle = dev_addr; + memset(ret, 0, size); + return ret; } +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 (!(vaddr >= (void *)io_tlb_start - && vaddr < (void *)io_tlb_end)) - 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 */ - swiotlb_unmap_single (hwdev, dma_handle, size, DMA_TO_DEVICE); + /* DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single */ + swiotlb_tbl_unmap_single(hwdev, paddr, 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. @@ -548,14 +707,17 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic) * 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 : "?"); + "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"); } /* @@ -563,69 +725,91 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic) * 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. + * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed. */ -dma_addr_t -swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir) +dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { - dma_addr_t dev_addr = virt_to_bus(ptr); - void *map; + phys_addr_t map, phys = page_to_phys(page) + offset; + dma_addr_t dev_addr = phys_to_dma(dev, phys); BUG_ON(dir == DMA_NONE); /* - * If the pointer passed in happens to be in the device's DMA window, + * If the address 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) && !swiotlb_force) + if (dma_capable(dev, dev_addr, size) && !swiotlb_force) return dev_addr; - /* - * Oh well, have to allocate and map a bounce buffer. - */ - map = map_single(hwdev, ptr, size, dir); - if (!map) { - swiotlb_full(hwdev, size, dir, 1); - map = io_tlb_overflow_buffer; + trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); + + /* Oh well, have to allocate and map a bounce buffer. */ + map = map_single(dev, phys, size, dir); + if (map == SWIOTLB_MAP_ERROR) { + swiotlb_full(dev, size, dir, 1); + return phys_to_dma(dev, io_tlb_overflow_buffer); } - dev_addr = virt_to_bus(map); + dev_addr = phys_to_dma(dev, map); - /* - * Ensure that the address returned is DMA'ble - */ - if (address_needs_mapping(hwdev, dev_addr)) - panic("map_single: bounce buffer is not DMA'ble"); + /* Ensure that the address returned is DMA'ble */ + if (!dma_capable(dev, dev_addr, size)) { + swiotlb_tbl_unmap_single(dev, map, size, dir); + return phys_to_dma(dev, io_tlb_overflow_buffer); + } return dev_addr; } +EXPORT_SYMBOL_GPL(swiotlb_map_page); /* * 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 + * match what was provided for in a previous swiotlb_map_page 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(struct device *hwdev, dma_addr_t dev_addr, size_t size, - int dir) +static void unmap_single(struct device *hwdev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir) { - char *dma_addr = bus_to_virt(dev_addr); + phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); BUG_ON(dir == DMA_NONE); - if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end) - unmap_single(hwdev, dma_addr, size, dir); - else if (dir == DMA_FROM_DEVICE) - dma_mark_clean(dma_addr, size); + + if (is_swiotlb_buffer(paddr)) { + swiotlb_tbl_unmap_single(hwdev, 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) +{ + unmap_single(hwdev, dev_addr, size, dir); } +EXPORT_SYMBOL_GPL(swiotlb_unmap_page); /* * 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 + * If you perform a swiotlb_map_page() 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 @@ -633,67 +817,43 @@ swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size, */ 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) { - char *dma_addr = bus_to_virt(dev_addr); + phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); BUG_ON(dir == DMA_NONE); - if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end) - 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)) { + swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target); + return; + } + + if (dir != DMA_FROM_DEVICE) + return; + + dma_mark_clean(phys_to_virt(paddr), size); } void swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir) + size_t size, enum dma_data_direction dir) { swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU); } +EXPORT_SYMBOL(swiotlb_sync_single_for_cpu); void swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir) + size_t size, enum dma_data_direction 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 = bus_to_virt(dev_addr) + offset; - - BUG_ON(dir == DMA_NONE); - if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end) - 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); -} +EXPORT_SYMBOL(swiotlb_sync_single_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_single + * This is the scatter-gather version of the above swiotlb_map_page * 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). @@ -704,62 +864,78 @@ swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr, * 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 + * Device ownership issues as mentioned above for swiotlb_map_page are the * same here. */ int -swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, - int dir) +swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, + enum dma_data_direction dir, struct dma_attrs *attrs) { struct scatterlist *sg; - void *addr; - dma_addr_t dev_addr; int i; BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) { - addr = SG_ENT_VIRT_ADDRESS(sg); - dev_addr = virt_to_bus(addr); - if (swiotlb_force || address_needs_mapping(hwdev, dev_addr)) { - void *map = map_single(hwdev, addr, sg->length, dir); - if (!map) { + phys_addr_t paddr = sg_phys(sg); + dma_addr_t dev_addr = phys_to_dma(hwdev, paddr); + + if (swiotlb_force || + !dma_capable(hwdev, dev_addr, sg->length)) { + phys_addr_t map = map_single(hwdev, sg_phys(sg), + sg->length, dir); + if (map == SWIOTLB_MAP_ERROR) { /* Don't panic here, we expect map_sg users to do proper error handling. */ swiotlb_full(hwdev, sg->length, dir, 0); - swiotlb_unmap_sg(hwdev, sgl, i, dir); - sgl[0].dma_length = 0; + swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir, + attrs); + sg_dma_len(sgl) = 0; return 0; } - sg->dma_address = virt_to_bus(map); + sg->dma_address = phys_to_dma(hwdev, map); } else sg->dma_address = dev_addr; - sg->dma_length = sg->length; + sg_dma_len(sg) = sg->length; } return nelems; } +EXPORT_SYMBOL(swiotlb_map_sg_attrs); + +int +swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ + return swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL); +} +EXPORT_SYMBOL(swiotlb_map_sg); /* * Unmap a set of streaming mode DMA translations. Again, cpu read rules - * concerning calls here are the same as for swiotlb_unmap_single() above. + * concerning calls here are the same as for swiotlb_unmap_page() above. */ void -swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, - int dir) +swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, + int nelems, enum dma_data_direction 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 != SG_ENT_PHYS_ADDRESS(sg)) - unmap_single(hwdev, bus_to_virt(sg->dma_address), - sg->dma_length, dir); - else if (dir == DMA_FROM_DEVICE) - dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length); - } + for_each_sg(sgl, sg, nelems, i) + unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir); + +} +EXPORT_SYMBOL(swiotlb_unmap_sg_attrs); + +void +swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ + return swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL); } +EXPORT_SYMBOL(swiotlb_unmap_sg); /* * Make physical memory consistent for a set of streaming mode DMA translations @@ -770,41 +946,39 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, */ 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; - BUG_ON(dir == DMA_NONE); - - for_each_sg(sgl, sg, nelems, i) { - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - sync_single(hwdev, bus_to_virt(sg->dma_address), - sg->dma_length, dir, target); - else if (dir == DMA_FROM_DEVICE) - dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length); - } + for_each_sg(sgl, sg, nelems, i) + swiotlb_sync_single(hwdev, sg->dma_address, + sg_dma_len(sg), dir, target); } void swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir) + int nelems, enum dma_data_direction dir) { swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU); } +EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu); void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir) + int nelems, enum dma_data_direction dir) { swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE); } +EXPORT_SYMBOL(swiotlb_sync_sg_for_device); int -swiotlb_dma_mapping_error(dma_addr_t dma_addr) +swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) { - return (dma_addr == virt_to_bus(io_tlb_overflow_buffer)); + return (dma_addr == phys_to_dma(hwdev, io_tlb_overflow_buffer)); } +EXPORT_SYMBOL(swiotlb_dma_mapping_error); /* * Return whether the given device DMA address mask can be supported @@ -815,20 +989,6 @@ swiotlb_dma_mapping_error(dma_addr_t dma_addr) int swiotlb_dma_supported(struct device *hwdev, u64 mask) { - return virt_to_bus(io_tlb_end - 1) <= mask; + return phys_to_dma(hwdev, 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); |