From c40dba06e9a27d673197a2083828f13eff16b2ab Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 15 Oct 2012 10:19:22 -0700 Subject: swiotlb: Make io_tlb_end a physical address instead of a virtual one This change replaces all references to the virtual address for io_tlb_end with references to the physical address io_tlb_end. The main advantage of replacing the virtual address with a physical address is that we can avoid having to do multiple translations from the virtual address to the physical one needed for testing an existing DMA address. Signed-off-by: Alexander Duyck Signed-off-by: Konrad Rzeszutek Wilk --- lib/swiotlb.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index f114bf6a8e1..c0cbfa1116c 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -57,7 +57,8 @@ int swiotlb_force; * 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 char *io_tlb_start; +static phys_addr_t io_tlb_end; /* * The number of IO TLB blocks (in groups of 64) between io_tlb_start and @@ -125,14 +126,16 @@ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev, void swiotlb_print_info(void) { unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; - phys_addr_t pstart, pend; + phys_addr_t pstart; + unsigned char *vend; pstart = virt_to_phys(io_tlb_start); - pend = virt_to_phys(io_tlb_end); + 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)pstart, (unsigned long long)pend - 1, - bytes >> 20, io_tlb_start, io_tlb_end - 1); + (unsigned long long)pstart, + (unsigned long long)io_tlb_end, + bytes >> 20, io_tlb_start, vend - 1); } void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) @@ -143,7 +146,7 @@ void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) io_tlb_nslabs = nslabs; io_tlb_start = tlb; - io_tlb_end = io_tlb_start + bytes; + io_tlb_end = __pa(io_tlb_start) + bytes; /* * Allocate and initialize the free list array. This array is used @@ -254,7 +257,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) io_tlb_nslabs = nslabs; io_tlb_start = tlb; - io_tlb_end = io_tlb_start + bytes; + io_tlb_end = virt_to_phys(io_tlb_start) + bytes; memset(io_tlb_start, 0, bytes); @@ -304,7 +307,7 @@ cleanup3: sizeof(int))); io_tlb_list = NULL; cleanup2: - io_tlb_end = NULL; + io_tlb_end = 0; io_tlb_start = NULL; io_tlb_nslabs = 0; return -ENOMEM; @@ -339,8 +342,7 @@ void __init swiotlb_free(void) static int is_swiotlb_buffer(phys_addr_t paddr) { - return paddr >= virt_to_phys(io_tlb_start) && - paddr < virt_to_phys(io_tlb_end); + return paddr >= virt_to_phys(io_tlb_start) && paddr < io_tlb_end; } /* @@ -938,6 +940,6 @@ EXPORT_SYMBOL(swiotlb_dma_mapping_error); int swiotlb_dma_supported(struct device *hwdev, u64 mask) { - return swiotlb_virt_to_bus(hwdev, io_tlb_end - 1) <= mask; + return phys_to_dma(hwdev, io_tlb_end - 1) <= mask; } EXPORT_SYMBOL(swiotlb_dma_supported); -- cgit v1.2.3 From ff7204a74931fc67ed13d8febbc322a46833c1fa Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 15 Oct 2012 10:19:28 -0700 Subject: swiotlb: Make io_tlb_start a physical address instead of a virtual one This change replaces all references to the virtual address for io_tlb_start with references to the physical address io_tlb_end. The main advantage of replacing the virtual address with a physical address is that we can avoid having to do multiple translations from the virtual address to the physical one needed for testing an existing DMA address. Signed-off-by: Alexander Duyck Signed-off-by: Konrad Rzeszutek Wilk --- lib/swiotlb.c | 58 +++++++++++++++++++++++++++++----------------------------- 1 file changed, 29 insertions(+), 29 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index c0cbfa1116c..8c4791f17ec 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -57,8 +57,7 @@ int swiotlb_force; * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this * API. */ -static char *io_tlb_start; -static phys_addr_t io_tlb_end; +static phys_addr_t io_tlb_start, io_tlb_end; /* * The number of IO TLB blocks (in groups of 64) between io_tlb_start and @@ -126,16 +125,15 @@ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev, void swiotlb_print_info(void) { unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; - phys_addr_t pstart; - unsigned char *vend; + unsigned char *vstart, *vend; - pstart = virt_to_phys(io_tlb_start); + 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)pstart, + (unsigned long long)io_tlb_start, (unsigned long long)io_tlb_end, - bytes >> 20, io_tlb_start, vend - 1); + bytes >> 20, vstart, vend - 1); } void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) @@ -145,8 +143,8 @@ void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) bytes = nslabs << IO_TLB_SHIFT; io_tlb_nslabs = nslabs; - io_tlb_start = tlb; - io_tlb_end = __pa(io_tlb_start) + bytes; + io_tlb_start = __pa(tlb); + io_tlb_end = io_tlb_start + bytes; /* * Allocate and initialize the free list array. This array is used @@ -176,6 +174,7 @@ void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) static void __init swiotlb_init_with_default_size(size_t default_size, int verbose) { + unsigned char *vstart; unsigned long bytes; if (!io_tlb_nslabs) { @@ -188,11 +187,11 @@ swiotlb_init_with_default_size(size_t default_size, int verbose) /* * Get IO TLB memory from the low pages */ - io_tlb_start = alloc_bootmem_low_pages(PAGE_ALIGN(bytes)); - if (!io_tlb_start) + vstart = alloc_bootmem_low_pages(PAGE_ALIGN(bytes)); + if (!vstart) panic("Cannot allocate SWIOTLB buffer"); - swiotlb_init_with_tbl(io_tlb_start, io_tlb_nslabs, verbose); + swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose); } void __init @@ -210,6 +209,7 @@ int swiotlb_late_init_with_default_size(size_t default_size) { unsigned long bytes, req_nslabs = io_tlb_nslabs; + unsigned char *vstart = NULL; unsigned int order; int rc = 0; @@ -226,14 +226,14 @@ 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 = (void *)__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) { + if (!vstart) { io_tlb_nslabs = req_nslabs; return -ENOMEM; } @@ -242,9 +242,9 @@ swiotlb_late_init_with_default_size(size_t default_size) "for software IO TLB\n", (PAGE_SIZE << order) >> 20); io_tlb_nslabs = SLABS_PER_PAGE << order; } - rc = swiotlb_late_init_with_tbl(io_tlb_start, io_tlb_nslabs); + rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs); if (rc) - free_pages((unsigned long)io_tlb_start, order); + free_pages((unsigned long)vstart, order); return rc; } @@ -256,10 +256,10 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) bytes = nslabs << IO_TLB_SHIFT; io_tlb_nslabs = nslabs; - io_tlb_start = tlb; - io_tlb_end = virt_to_phys(io_tlb_start) + bytes; + io_tlb_start = virt_to_phys(tlb); + io_tlb_end = io_tlb_start + bytes; - memset(io_tlb_start, 0, bytes); + memset(tlb, 0, bytes); /* * Allocate and initialize the free list array. This array is used @@ -308,7 +308,7 @@ cleanup3: io_tlb_list = NULL; cleanup2: io_tlb_end = 0; - io_tlb_start = NULL; + io_tlb_start = 0; io_tlb_nslabs = 0; return -ENOMEM; } @@ -325,7 +325,7 @@ void __init swiotlb_free(void) 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, + free_pages((unsigned long)phys_to_virt(io_tlb_start), get_order(io_tlb_nslabs << IO_TLB_SHIFT)); } else { free_bootmem_late(__pa(io_tlb_overflow_buffer), @@ -334,7 +334,7 @@ void __init swiotlb_free(void) PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); free_bootmem_late(__pa(io_tlb_list), PAGE_ALIGN(io_tlb_nslabs * sizeof(int))); - free_bootmem_late(__pa(io_tlb_start), + free_bootmem_late(io_tlb_start, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); } io_tlb_nslabs = 0; @@ -342,7 +342,7 @@ void __init swiotlb_free(void) static int is_swiotlb_buffer(phys_addr_t paddr) { - return paddr >= virt_to_phys(io_tlb_start) && paddr < io_tlb_end; + return paddr >= io_tlb_start && paddr < io_tlb_end; } /* @@ -455,7 +455,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, 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); + dma_addr = (char *)phys_to_virt(io_tlb_start) + (index << IO_TLB_SHIFT); /* * Update the indices to avoid searching in the next @@ -499,7 +499,7 @@ 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); + 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); } @@ -513,7 +513,7 @@ swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr, size_t size, { 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; + int index = (dma_addr - (char *)phys_to_virt(io_tlb_start)) >> IO_TLB_SHIFT; phys_addr_t phys = io_tlb_orig_addr[index]; /* @@ -554,7 +554,7 @@ 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; + int index = (dma_addr - (char *)phys_to_virt(io_tlb_start)) >> IO_TLB_SHIFT; phys_addr_t phys = io_tlb_orig_addr[index]; phys += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1)); -- cgit v1.2.3 From ee3f6ba896c7e62004b677b0018a0b29b9b26472 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 15 Oct 2012 10:19:34 -0700 Subject: swiotlb: Make io_tlb_overflow_buffer a physical address This change makes it so that we can avoid virt_to_phys overhead when using the io_tlb_overflow_buffer. My original plan was to completely remove the value and replace it with a constant but I had seen that there were recent patches that stated this couldn't be done until all device drivers that depended on that functionality be updated. Signed-off-by: Alexander Duyck Signed-off-by: Konrad Rzeszutek Wilk --- lib/swiotlb.c | 61 +++++++++++++++++++++++++++++++++-------------------------- 1 file changed, 34 insertions(+), 27 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 8c4791f17ec..f8c0d4e1d1d 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -70,7 +70,7 @@ static unsigned long io_tlb_nslabs; */ static unsigned long io_tlb_overflow = 32*1024; -static 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 @@ -138,6 +138,7 @@ void swiotlb_print_info(void) void __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; @@ -146,6 +147,15 @@ void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) io_tlb_start = __pa(tlb); io_tlb_end = io_tlb_start + bytes; + /* + * Get the overflow emergency buffer + */ + v_overflow_buffer = alloc_bootmem_low_pages(PAGE_ALIGN(io_tlb_overflow)); + if (!v_overflow_buffer) + panic("Cannot allocate SWIOTLB overflow buffer!\n"); + + 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 @@ -157,12 +167,6 @@ void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) io_tlb_index = 0; io_tlb_orig_addr = alloc_bootmem_pages(PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); - /* - * Get the overflow emergency buffer - */ - io_tlb_overflow_buffer = alloc_bootmem_low_pages(PAGE_ALIGN(io_tlb_overflow)); - if (!io_tlb_overflow_buffer) - panic("Cannot allocate SWIOTLB overflow buffer!\n"); if (verbose) swiotlb_print_info(); } @@ -252,6 +256,7 @@ 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; @@ -261,6 +266,16 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) 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 * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE @@ -269,7 +284,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL, get_order(io_tlb_nslabs * sizeof(int))); if (!io_tlb_list) - goto cleanup2; + goto cleanup3; for (i = 0; i < io_tlb_nslabs; i++) io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); @@ -280,18 +295,10 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) 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(phys_addr_t)); - /* - * 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(); late_alloc = 1; @@ -299,13 +306,13 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) return 0; cleanup4: - free_pages((unsigned long)io_tlb_orig_addr, - get_order(io_tlb_nslabs * sizeof(phys_addr_t))); - 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 = 0; io_tlb_start = 0; @@ -315,11 +322,11 @@ cleanup2: void __init swiotlb_free(void) { - if (!io_tlb_overflow_buffer) + if (!io_tlb_orig_addr) return; if (late_alloc) { - free_pages((unsigned long)io_tlb_overflow_buffer, + 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))); @@ -328,7 +335,7 @@ void __init swiotlb_free(void) free_pages((unsigned long)phys_to_virt(io_tlb_start), get_order(io_tlb_nslabs << IO_TLB_SHIFT)); } else { - free_bootmem_late(__pa(io_tlb_overflow_buffer), + free_bootmem_late(io_tlb_overflow_buffer, PAGE_ALIGN(io_tlb_overflow)); free_bootmem_late(__pa(io_tlb_orig_addr), PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); @@ -698,7 +705,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, map = map_single(dev, phys, size, dir); if (!map) { swiotlb_full(dev, size, dir, 1); - map = io_tlb_overflow_buffer; + return phys_to_dma(dev, io_tlb_overflow_buffer); } dev_addr = swiotlb_virt_to_bus(dev, map); @@ -708,7 +715,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, */ if (!dma_capable(dev, dev_addr, size)) { swiotlb_tbl_unmap_single(dev, map, size, dir); - dev_addr = swiotlb_virt_to_bus(dev, io_tlb_overflow_buffer); + return phys_to_dma(dev, io_tlb_overflow_buffer); } return dev_addr; @@ -927,7 +934,7 @@ EXPORT_SYMBOL(swiotlb_sync_sg_for_device); int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) { - return (dma_addr == swiotlb_virt_to_bus(hwdev, io_tlb_overflow_buffer)); + return (dma_addr == phys_to_dma(hwdev, io_tlb_overflow_buffer)); } EXPORT_SYMBOL(swiotlb_dma_mapping_error); -- cgit v1.2.3 From e05ed4d1fad9e730995abb08cb9bc3bffac5018b Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 15 Oct 2012 10:19:39 -0700 Subject: swiotlb: Return physical addresses when calling swiotlb_tbl_map_single This change makes it so that swiotlb_tbl_map_single will return a physical address instead of a virtual address when called. The advantage to this once again is that we are avoiding a number of virt_to_phys and phys_to_virt translations by working with everything as a physical address. One change I had to make in order to support using physical addresses is that I could no longer trust 0 to be a invalid physical address on all platforms. So instead I made it so that ~0 is returned on error. This should never be a valid return value as it implies that only one byte would be available for use. In order to clarify things since we now have 2 physical addresses in use inside of swiotlb_tbl_map_single I am renaming phys to orig_addr, and dma_addr to tlb_addr. This way is should be clear that orig_addr is contained within io_orig_addr and tlb_addr is an address within the io_tlb_addr buffer. Signed-off-by: Alexander Duyck Signed-off-by: Konrad Rzeszutek Wilk --- lib/swiotlb.c | 78 ++++++++++++++++++++++++++++++----------------------------- 1 file changed, 40 insertions(+), 38 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index f8c0d4e1d1d..3adc148bb8d 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -393,12 +393,13 @@ void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size, } EXPORT_SYMBOL_GPL(swiotlb_bounce); -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) +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 mask; @@ -462,7 +463,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, 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 = (char *)phys_to_virt(io_tlb_start) + (index << IO_TLB_SHIFT); + tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT); /* * Update the indices to avoid searching in the next @@ -480,7 +481,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, not_found: spin_unlock_irqrestore(&io_tlb_lock, flags); - return NULL; + return SWIOTLB_MAP_ERROR; found: spin_unlock_irqrestore(&io_tlb_lock, flags); @@ -490,11 +491,12 @@ found: * needed. */ for (i = 0; i < nslots; i++) - io_tlb_orig_addr[index+i] = phys + (i << IO_TLB_SHIFT); + io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) - swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE); + swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr), size, + DMA_TO_DEVICE); - return dma_addr; + return tlb_addr; } EXPORT_SYMBOL_GPL(swiotlb_tbl_map_single); @@ -502,9 +504,8 @@ 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) +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); @@ -598,12 +599,15 @@ 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 - 1 > dma_mask) { - /* - * The allocated memory isn't reachable by the device. - */ - 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) { /* @@ -611,13 +615,13 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, * 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); - if (!ret) + phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE); + if (paddr == SWIOTLB_MAP_ERROR) return NULL; - } - memset(ret, 0, size); - dev_addr = swiotlb_virt_to_bus(hwdev, ret); + ret = phys_to_virt(paddr); + dev_addr = phys_to_dma(hwdev, paddr); + } /* Confirm address can be DMA'd by device */ if (dev_addr + size - 1 > dma_mask) { @@ -629,7 +633,10 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, swiotlb_tbl_unmap_single(hwdev, ret, size, DMA_TO_DEVICE); return NULL; } + *dma_handle = dev_addr; + memset(ret, 0, size); + return ret; } EXPORT_SYMBOL(swiotlb_alloc_coherent); @@ -686,9 +693,8 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, enum dma_data_direction dir, struct dma_attrs *attrs) { - phys_addr_t phys = page_to_phys(page) + offset; + phys_addr_t map, phys = page_to_phys(page) + offset; dma_addr_t dev_addr = phys_to_dma(dev, phys); - void *map; BUG_ON(dir == DMA_NONE); /* @@ -699,22 +705,18 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, if (dma_capable(dev, dev_addr, size) && !swiotlb_force) return dev_addr; - /* - * Oh well, have to allocate and map a bounce buffer. - */ + /* Oh well, have to allocate and map a bounce buffer. */ map = map_single(dev, phys, size, dir); - if (!map) { + if (map == SWIOTLB_MAP_ERROR) { swiotlb_full(dev, size, dir, 1); return phys_to_dma(dev, io_tlb_overflow_buffer); } - dev_addr = swiotlb_virt_to_bus(dev, map); + dev_addr = phys_to_dma(dev, map); - /* - * Ensure that the address returned is 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); + swiotlb_tbl_unmap_single(dev, phys_to_virt(map), size, dir); return phys_to_dma(dev, io_tlb_overflow_buffer); } @@ -840,9 +842,9 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, if (swiotlb_force || !dma_capable(hwdev, dev_addr, sg->length)) { - void *map = map_single(hwdev, sg_phys(sg), - sg->length, dir); - if (!map) { + 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); @@ -851,7 +853,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, sgl[0].dma_length = 0; return 0; } - sg->dma_address = swiotlb_virt_to_bus(hwdev, map); + sg->dma_address = phys_to_dma(hwdev, map); } else sg->dma_address = dev_addr; sg->dma_length = sg->length; -- cgit v1.2.3 From 61ca08c3220032dd88815b3465d56cb779258168 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 15 Oct 2012 10:19:44 -0700 Subject: swiotlb: Use physical addresses for swiotlb_tbl_unmap_single This change makes it so that the unmap functionality also uses physical addresses. This helps to further reduce the use of virt_to_phys and phys_to_virt functions. In order to clarify things since we now have 2 physical addresses in use inside of swiotlb_tbl_unmap_single I am renaming phys to orig_addr, and dma_addr to tlb_addr. This way is should be clear that orig_addr is contained within io_orig_addr and tlb_addr is an address within the io_tlb_addr buffer. Signed-off-by: Alexander Duyck Signed-off-by: Konrad Rzeszutek Wilk --- lib/swiotlb.c | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 3adc148bb8d..d7701dcf407 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -515,20 +515,20 @@ phys_addr_t map_single(struct device *hwdev, phys_addr_t phys, size_t size, /* * dma_addr is the kernel virtual address of the bounce buffer to unmap. */ -void -swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr, size_t size, - enum dma_data_direction 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 - (char *)phys_to_virt(io_tlb_start)) >> IO_TLB_SHIFT; - phys_addr_t phys = 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 (phys && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) - swiotlb_bounce(phys, dma_addr, size, DMA_FROM_DEVICE); + swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr), + size, DMA_FROM_DEVICE); /* * Return the buffer to the free list by setting the corresponding @@ -621,17 +621,18 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, ret = phys_to_virt(paddr); dev_addr = phys_to_dma(hwdev, paddr); - } - /* 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); + /* 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, ret, size, DMA_TO_DEVICE); - return NULL; + /* 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; @@ -652,7 +653,7 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, free_pages((unsigned long)vaddr, get_order(size)); else /* DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single */ - swiotlb_tbl_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE); + swiotlb_tbl_unmap_single(hwdev, paddr, size, DMA_TO_DEVICE); } EXPORT_SYMBOL(swiotlb_free_coherent); @@ -716,7 +717,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, /* Ensure that the address returned is DMA'ble */ if (!dma_capable(dev, dev_addr, size)) { - swiotlb_tbl_unmap_single(dev, phys_to_virt(map), size, dir); + swiotlb_tbl_unmap_single(dev, map, size, dir); return phys_to_dma(dev, io_tlb_overflow_buffer); } @@ -740,7 +741,7 @@ static void unmap_single(struct device *hwdev, dma_addr_t dev_addr, BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(paddr)) { - swiotlb_tbl_unmap_single(hwdev, phys_to_virt(paddr), size, dir); + swiotlb_tbl_unmap_single(hwdev, paddr, size, dir); return; } -- cgit v1.2.3 From fbfda893eb570bbe9e9ad9128b6e9cf2a1e48c87 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 15 Oct 2012 10:19:49 -0700 Subject: swiotlb: Use physical addresses instead of virtual in swiotlb_tbl_sync_single This change makes it so that the sync functionality also uses physical addresses. This helps to further reduce the use of virt_to_phys and phys_to_virt functions. In order to clarify things since we now have 2 physical addresses in use inside of swiotlb_tbl_sync_single I am renaming phys to orig_addr, and dma_addr to tlb_addr. This way is should be clear that orig_addr is contained within io_orig_addr and tlb_addr is an address within the io_tlb_addr buffer. Signed-off-by: Alexander Duyck Signed-off-by: Konrad Rzeszutek Wilk --- lib/swiotlb.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index d7701dcf407..16a548dc91a 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -557,26 +557,27 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, } EXPORT_SYMBOL_GPL(swiotlb_tbl_unmap_single); -void -swiotlb_tbl_sync_single(struct device *hwdev, char *dma_addr, size_t size, - enum dma_data_direction dir, - enum dma_sync_target 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 - (char *)phys_to_virt(io_tlb_start)) >> IO_TLB_SHIFT; - phys_addr_t phys = 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]; - phys += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1)); + 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)) - swiotlb_bounce(phys, dma_addr, size, DMA_FROM_DEVICE); + swiotlb_bounce(orig_addr, phys_to_virt(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)) - swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE); + swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr), + size, DMA_TO_DEVICE); else BUG_ON(dir != DMA_FROM_DEVICE); break; @@ -785,8 +786,7 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(paddr)) { - swiotlb_tbl_sync_single(hwdev, phys_to_virt(paddr), size, dir, - target); + swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target); return; } -- cgit v1.2.3 From af51a9f1848ff50079a10def56a2c064f326af22 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 15 Oct 2012 10:19:55 -0700 Subject: swiotlb: Do not export swiotlb_bounce since there are no external consumers Currently swiotlb is the only consumer for swiotlb_bounce. Since that is the case it doesn't make much sense to be exporting it so make it a static function only. In addition we can save a few more lines of code by making it so that it accepts the DMA address as a physical address instead of a virtual one. This is the last piece in essentially pushing all of the DMA address values to use physical addresses in swiotlb. In order to clarify things since we now have 2 physical addresses in use inside of swiotlb_bounce I am renaming phys to orig_addr, and dma_addr to tlb_addr. This way is should be clear that orig_addr is contained within io_orig_addr and tlb_addr is an address within the io_tlb_addr buffer. Signed-off-by: Alexander Duyck Signed-off-by: Konrad Rzeszutek Wilk --- lib/swiotlb.c | 35 ++++++++++++++++------------------- 1 file changed, 16 insertions(+), 19 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 16a548dc91a..196b06984de 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -355,14 +355,15 @@ static int is_swiotlb_buffer(phys_addr_t paddr) /* * Bounce: copy the swiotlb buffer back to the original dma location */ -void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size, - enum dma_data_direction 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(phys); + 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 = phys & ~PAGE_MASK; + unsigned int offset = orig_addr & ~PAGE_MASK; char *buffer; unsigned int sz = 0; unsigned long flags; @@ -373,25 +374,23 @@ void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size, local_irq_save(flags); buffer = kmap_atomic(pfn_to_page(pfn)); if (dir == DMA_TO_DEVICE) - memcpy(dma_addr, buffer + offset, sz); + memcpy(vaddr, buffer + offset, sz); else - memcpy(buffer + offset, dma_addr, sz); + memcpy(buffer + offset, vaddr, sz); kunmap_atomic(buffer); local_irq_restore(flags); size -= sz; pfn++; - dma_addr += sz; + vaddr += sz; offset = 0; } + } else if (dir == DMA_TO_DEVICE) { + memcpy(vaddr, phys_to_virt(orig_addr), size); } else { - if (dir == DMA_TO_DEVICE) - memcpy(dma_addr, phys_to_virt(phys), size); - else - memcpy(phys_to_virt(phys), dma_addr, size); + memcpy(phys_to_virt(orig_addr), vaddr, size); } } -EXPORT_SYMBOL_GPL(swiotlb_bounce); phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, @@ -493,8 +492,7 @@ found: for (i = 0; i < nslots; i++) io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) - swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr), size, - DMA_TO_DEVICE); + swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE); return tlb_addr; } @@ -526,9 +524,8 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, /* * First, sync the memory before unmapping the entry */ - if (phys && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) - swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr), - size, DMA_FROM_DEVICE); + if (orig_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 @@ -569,14 +566,14 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, switch (target) { case SYNC_FOR_CPU: if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr), + 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)) - swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr), + swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE); else BUG_ON(dir != DMA_FROM_DEVICE); -- cgit v1.2.3