From eb605a5754d050a25a9f00d718fb173f24c486ef Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 10 May 2010 15:14:54 -0400 Subject: swiotlb: add swiotlb_tbl_map_single library function swiotlb_tbl_map_single() takes the dma address of iotlb instead of using swiotlb_virt_to_bus(). [v2: changed swiotlb_tlb to swiotlb_tbl] [v3: changed u64 to dma_addr_t] This patch: This is a set of patches that separate the address translation (virt_to_phys, virt_to_bus, etc) and allocation of the SWIOTLB buffer from the SWIOTLB library. The idea behind this set of patches is to make it possible to have separate mechanisms for translating virtual to physical or virtual to DMA addresses on platforms which need an SWIOTLB, and where physical != PCI bus address and also to allocate the core IOTLB memory outside SWIOTLB. One customers of this is the pv-ops project, which can switch between different modes of operation depending on the environment it is running in: bare-metal or virtualized (Xen for now). Another is the Wii DMA - used to implement the MEM2 DMA facility needed by its EHCI controller (for details: http://lkml.org/lkml/2010/5/18/303) On bare-metal SWIOTLB is used when there are no hardware IOMMU. In virtualized environment it used when PCI pass-through is enabled for the guest. The problems with PCI pass-through is that the guest's idea of PFN's is not the real thing. To fix that, there is translation layer for PFN->machine frame number and vice-versa. To bubble that up to the SWIOTLB layer there are two possible solutions. One solution has been to wholesale copy the SWIOTLB, stick it in arch/x86/xen/swiotlb.c and modify the virt_to_phys, phys_to_virt and others to use the Xen address translation functions. Unfortunately, since the kernel can run on bare-metal, there would be big code overlap with the real SWIOTLB. (git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen.git xen/dom0/swiotlb-new) Another approach, which this set of patches explores, is to abstract the address translation and address determination functions away from the SWIOTLB book-keeping functions. This way the core SWIOTLB library functions are present in one place, while the address related functions are in a separate library that can be loaded when running under non-bare-metal platform. Changelog: Since the last posting [v8.2] Konrad has done: - Added this changelog in the patch and referenced in the other patches this description. - 'enum dma_data_direction direction' to 'enum dma.. dir' so to be unified. [v8-v8.2 changes:] - Rolled-up the last two patches in one. - Rebased against linus latest. That meant dealing with swiotlb_sync_single_range_* changes. - added Acked-by: Fujita Tomonori and Tested-by: Albert Herranz [v7-v8 changes:] - Minimized the list of exported functions. - Integrated Fujita's patches and changed "swiotlb_tlb" to "swiotlb_tbl" in them. [v6-v7 changes:] - Minimized the amount of exported functions/variable with a prefix of: "swiotbl_tbl". - Made the usage of 'int dir' to be 'enum dma_data_direction'. [v5-v6 changes:] - Made the exported functions/variables have the 'swiotlb_bk' prefix. - dropped the checkpatches/other reworks Signed-off-by: FUJITA Tomonori Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Albert Herranz --- lib/swiotlb.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/lib/swiotlb.c b/lib/swiotlb.c index a009055140ec..783aff00024c 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -361,25 +361,22 @@ static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size, } } -/* - * 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, int dir) { unsigned long flags; char *dma_addr; unsigned int nslots, stride, index, wrap; int i; - unsigned long start_dma_addr; unsigned long mask; unsigned long offset_slots; unsigned long max_slots; 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. @@ -467,6 +464,18 @@ found: return dma_addr; } +/* + * 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) +{ + 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. */ -- cgit v1.2.3 From abbceff7d7a884968e876e52578da1db4a4f6b54 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 10 May 2010 15:15:12 -0400 Subject: swiotlb: add the swiotlb initialization function with iotlb memory This enables the caller to initialize swiotlb with its own iotlb memory. See "swiotlb: swiotlb: add swiotlb_tbl_map_single library function" for full description of patchset. [v2: changed ..with_tlb to ..with_tbl] Signed-off-by: FUJITA Tomonori Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Albert Herranz --- include/linux/swiotlb.h | 1 + lib/swiotlb.c | 48 ++++++++++++++++++++++++++++++------------------ 2 files changed, 31 insertions(+), 18 deletions(-) diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 81a4e213c6cf..b406261d8887 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -23,6 +23,7 @@ extern int swiotlb_force; #define IO_TLB_SHIFT 11 extern void swiotlb_init(int verbose); +extern void swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size, diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 783aff00024c..ec61e1507d0a 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -140,28 +140,14 @@ void swiotlb_print_info(void) (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, int verbose) +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 = nslabs << IO_TLB_SHIFT; - 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"); + io_tlb_nslabs = nslabs; + io_tlb_start = tlb; io_tlb_end = io_tlb_start + bytes; /* @@ -185,6 +171,32 @@ swiotlb_init_with_default_size(size_t default_size, int 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_init_with_tbl(io_tlb_start, io_tlb_nslabs, verbose); +} + void __init swiotlb_init(int verbose) { -- cgit v1.2.3 From bfc5501f6d816082274e10cd45a2d5f32603b328 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Mon, 10 May 2010 15:54:20 -0400 Subject: swiotlb: Make internal bookkeeping functions have 'swiotlb_tbl' prefix. The functions that operate on io_tlb_list/io_tlb_start/io_tlb_orig_addr have the prefix 'swiotlb_tbl' now. See "swiotlb: swiotlb: add swiotlb_tbl_map_single library function" for full description of patchset. Signed-off-by: Konrad Rzeszutek Wilk Acked-by: FUJITA Tomonori Tested-by: Albert Herranz --- lib/swiotlb.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/lib/swiotlb.c b/lib/swiotlb.c index ec61e1507d0a..1fc15bf63945 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -61,8 +61,8 @@ enum dma_sync_target { 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; @@ -492,7 +492,8 @@ map_single(struct device *hwdev, phys_addr_t phys, size_t size, int 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) +swiotlb_tbl_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; @@ -532,7 +533,7 @@ do_unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) } static void -sync_single(struct device *hwdev, char *dma_addr, size_t size, +swiotlb_tbl_sync_single(struct device *hwdev, char *dma_addr, size_t size, int dir, int target) { int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; @@ -580,8 +581,8 @@ 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); @@ -599,7 +600,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, (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; @@ -617,8 +618,8 @@ 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); @@ -708,7 +709,7 @@ static void unmap_single(struct device *hwdev, dma_addr_t 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; } @@ -751,7 +752,8 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t 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; } -- cgit v1.2.3 From 22d48269984fc93a71f65a54aa422aacf5fdb926 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Mon, 10 May 2010 15:01:15 -0500 Subject: swiotlb: search and replace "int dir" with "enum dma_data_direction dir" .. to catch anybody doing something funky. See "swiotlb: swiotlb: add swiotlb_tbl_map_single library function" for full description of patchset. [v2: swiotlb_sync_single_range_* no more - removed usage] [v3: enum dma_data_direction direction -> enum dma_data_direction dir] Signed-off-by: Konrad Rzeszutek Wilk Acked-by: FUJITA Tomonori Tested-by: Albert Herranz --- include/linux/swiotlb.h | 4 ++-- lib/swiotlb.c | 23 +++++++++++++---------- 2 files changed, 15 insertions(+), 12 deletions(-) diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index b406261d8887..250d766f17f7 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -43,11 +43,11 @@ extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, - int direction); + enum dma_data_direction dir); extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, - int direction); + enum dma_data_direction dir); extern int swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 1fc15bf63945..5f60157f31d8 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -374,7 +374,8 @@ static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size, } void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, - phys_addr_t phys, size_t size, int dir) + phys_addr_t phys, size_t size, + enum dma_data_direction dir) { unsigned long flags; char *dma_addr; @@ -481,7 +482,8 @@ found: */ static void * -map_single(struct device *hwdev, phys_addr_t phys, size_t size, int dir) +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); @@ -493,7 +495,7 @@ map_single(struct device *hwdev, phys_addr_t phys, size_t size, int dir) */ static void swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr, size_t size, - int dir) + enum dma_data_direction dir) { unsigned long flags; int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; @@ -534,7 +536,7 @@ swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr, size_t size, static void swiotlb_tbl_sync_single(struct device *hwdev, char *dma_addr, size_t size, - int dir, int target) + enum dma_data_direction dir, int target) { int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; phys_addr_t phys = io_tlb_orig_addr[index]; @@ -624,7 +626,8 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, 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. @@ -702,7 +705,7 @@ 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); @@ -745,7 +748,7 @@ 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, int target) { phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); @@ -832,7 +835,7 @@ 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); } @@ -859,7 +862,7 @@ 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); } @@ -874,7 +877,7 @@ 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, int target) { struct scatterlist *sg; int i; -- cgit v1.2.3 From d7ef1533a90f432615d25729c2477bac9e72051d Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 28 May 2010 11:37:10 -0400 Subject: swiotlb: Make swiotlb bookkeeping functions visible in the header file. We put the functions dealing with the operations on the SWIOTLB buffer in the header and make those functions non-static. And also make the functions exported via EXPORT_SYMBOL_GPL. See "swiotlb: swiotlb: add swiotlb_tbl_map_single library function" for full description of patchset. [v2: swiotlb_sync_single_range_for_* no more. Remove usage.] Signed-off-by: Konrad Rzeszutek Wilk Acked-by: FUJITA Tomonori Tested-by: Albert Herranz --- include/linux/swiotlb.h | 22 ++++++++++++++++++++++ lib/swiotlb.c | 29 ++++++++++++++--------------- 2 files changed, 36 insertions(+), 15 deletions(-) diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 250d766f17f7..8c0e349f4a6c 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -25,6 +25,28 @@ extern int swiotlb_force; extern void swiotlb_init(int verbose); extern void swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); +/* + * Enumeration for sync targets + */ +enum dma_sync_target { + SYNC_FOR_CPU = 0, + SYNC_FOR_DEVICE = 1, +}; +extern 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); + +extern void swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr, + size_t size, enum dma_data_direction dir); + +extern void swiotlb_tbl_sync_single(struct device *hwdev, char *dma_addr, + size_t size, enum dma_data_direction dir, + enum dma_sync_target target); + +/* Accessory functions. */ +extern void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size, + enum dma_data_direction dir); + extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags); diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 5f60157f31d8..34e3082632d8 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -50,14 +50,6 @@ */ #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; /* @@ -335,8 +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); @@ -372,6 +364,7 @@ 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); void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, phys_addr_t phys, size_t size, @@ -476,6 +469,7 @@ found: return dma_addr; } +EXPORT_SYMBOL_GPL(swiotlb_tbl_map_single); /* * Allocates bounce buffer and returns its kernel virtual address. @@ -493,7 +487,7 @@ 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. */ -static void +void swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr, size_t size, enum dma_data_direction dir) { @@ -533,10 +527,12 @@ swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr, size_t size, } spin_unlock_irqrestore(&io_tlb_lock, flags); } +EXPORT_SYMBOL_GPL(swiotlb_tbl_unmap_single); -static void +void swiotlb_tbl_sync_single(struct device *hwdev, char *dma_addr, size_t size, - enum dma_data_direction dir, int target) + 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]; @@ -560,6 +556,7 @@ swiotlb_tbl_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, @@ -748,7 +745,8 @@ EXPORT_SYMBOL_GPL(swiotlb_unmap_page); */ static void swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction 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); @@ -877,7 +875,8 @@ EXPORT_SYMBOL(swiotlb_unmap_sg); */ static void swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, int target) + int nelems, enum dma_data_direction dir, + enum dma_sync_target target) { struct scatterlist *sg; int i; -- cgit v1.2.3