Add a common helper for dma-mapping core for mapping a coherent buffer to userspace.

Reported-by: Subash Patel subashrp@gmail.com Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Acked-by: Kyungmin Park kyungmin.park@samsung.com Tested-By: Subash Patel subash.ramaswamy@linaro.org --- drivers/base/dma-coherent.c | 42 ++++++++++++++++++++++++++++++++++++ include/asm-generic/dma-coherent.h | 4 +++- 2 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c index bb0025c..1b85949 100644 --- a/drivers/base/dma-coherent.c +++ b/drivers/base/dma-coherent.c @@ -10,6 +10,7 @@ struct dma_coherent_mem { void *virt_base; dma_addr_t device_base; + phys_addr_t pfn_base; int size; int flags; unsigned long *bitmap; @@ -44,6 +45,7 @@ int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,

dev->dma_mem->virt_base = mem_base; dev->dma_mem->device_base = device_addr; + dev->dma_mem->pfn_base = PFN_DOWN(bus_addr); dev->dma_mem->size = pages; dev->dma_mem->flags = flags;

@@ -176,3 +178,43 @@ int dma_release_from_coherent(struct device *dev, int order, void *vaddr) return 0; } EXPORT_SYMBOL(dma_release_from_coherent); + +/** + * dma_mmap_from_coherent() - try to mmap the memory allocated from + * per-device coherent memory pool to userspace + * @dev: device from which the memory was allocated + * @vma: vm_area for the userspace memory + * @vaddr: cpu address returned by dma_alloc_from_coherent + * @size: size of the memory buffer allocated by dma_alloc_from_coherent + * + * This checks whether the memory was allocated from the per-device + * coherent memory pool and if so, maps that memory to the provided vma. + * + * Returns 1 if we correctly mapped the memory, or 0 if + * dma_release_coherent() should proceed with mapping memory from + * generic pools. + */ +int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma, + void *vaddr, size_t size, int *ret) +{ + struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; + + if (mem && vaddr >= mem->virt_base && vaddr + size <= + (mem->virt_base + (mem->size << PAGE_SHIFT))) { + unsigned long off = vma->vm_pgoff; + int start = (vaddr - mem->virt_base) >> PAGE_SHIFT; + int user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + int count = size >> PAGE_SHIFT; + + *ret = -ENXIO; + if (off < count && user_count <= count - off) { + unsigned pfn = mem->pfn_base + start + off; + *ret = remap_pfn_range(vma, vma->vm_start, pfn, + user_count << PAGE_SHIFT, + vma->vm_page_prot); + } + return 1; + } + return 0; +} +EXPORT_SYMBOL(dma_mmap_from_coherent); diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h index 85a3ffa..abfb268 100644 --- a/include/asm-generic/dma-coherent.h +++ b/include/asm-generic/dma-coherent.h @@ -3,13 +3,15 @@

#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT /* - * These two functions are only for dma allocator. + * These three functions are only for dma allocator. * Don't use them in device drivers. */ int dma_alloc_from_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle, void **ret); int dma_release_from_coherent(struct device *dev, int order, void *vaddr);

+int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, size_t size, int *ret); /* * Standard interface */

Replace all calls to printk with pr_* functions family.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Tested-By: Subash Patel subash.ramaswamy@linaro.org --- arch/arm/mm/dma-mapping.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 7ec0863..322c70a 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -184,14 +184,14 @@ static int __init consistent_init(void)

pud = pud_alloc(&init_mm, pgd, base); if (!pud) { - printk(KERN_ERR "%s: no pud tables\n", __func__); + pr_err("%s: no pud tables\n", __func__); ret = -ENOMEM; break; }

pmd = pmd_alloc(&init_mm, pud, base); if (!pmd) { - printk(KERN_ERR "%s: no pmd tables\n", __func__); + pr_err("%s: no pmd tables\n", __func__); ret = -ENOMEM; break; } @@ -199,7 +199,7 @@ static int __init consistent_init(void)

pte = pte_alloc_kernel(pmd, base); if (!pte) { - printk(KERN_ERR "%s: no pte tables\n", __func__); + pr_err("%s: no pte tables\n", __func__); ret = -ENOMEM; break; } @@ -222,7 +222,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot, int bit;

if (!consistent_pte) { - printk(KERN_ERR "%s: not initialised\n", __func__); + pr_err("%s: not initialised\n", __func__); dump_stack(); return NULL; } @@ -281,14 +281,14 @@ static void __dma_free_remap(void *cpu_addr, size_t size)

c = arm_vmregion_find_remove(&consistent_head, (unsigned long)cpu_addr); if (!c) { - printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n", + pr_err("%s: trying to free invalid coherent area: %p\n", __func__, cpu_addr); dump_stack(); return; }

if ((c->vm_end - c->vm_start) != size) { - printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n", + pr_err("%s: freeing wrong coherent size (%ld != %d)\n", __func__, c->vm_end - c->vm_start, size); dump_stack(); size = c->vm_end - c->vm_start; @@ -310,8 +310,8 @@ static void __dma_free_remap(void *cpu_addr, size_t size) }

if (pte_none(pte) || !pte_present(pte)) - printk(KERN_CRIT "%s: bad page in kernel page table\n", - __func__); + pr_crit("%s: bad page in kernel page table\n", + __func__); } while (size -= PAGE_SIZE);

flush_tlb_kernel_range(c->vm_start, c->vm_end);

This patch removes the need for the offset parameter in dma bounce functions. This is required to let dma-mapping framework on ARM architecture to use common, generic dma_map_ops based dma-mapping helpers.

Background and more detailed explaination:

dma_*_range_* functions are available from the early days of the dma mapping api. They are the correct way of doing a partial syncs on the buffer (usually used by the network device drivers). This patch changes only the internal implementation of the dma bounce functions to let them tunnel through dma_map_ops structure. The driver api stays unchanged, so driver are obliged to call dma_*_range_* functions to keep code clean and easy to understand.

The only drawback from this patch is reduced detection of the dma api abuse. Let us consider the following code:

dma_addr = dma_map_single(dev, ptr, 64, DMA_TO_DEVICE); dma_sync_single_range_for_cpu(dev, dma_addr+16, 0, 32, DMA_TO_DEVICE);

Without the patch such code fails, because dma bounce code is unable to find the bounce buffer for the given dma_address. After the patch the above sync call will be equivalent to:

dma_sync_single_range_for_cpu(dev, dma_addr, 16, 32, DMA_TO_DEVICE);

which succeeds.

I don't consider this as a real problem, because DMA API abuse should be caught by debug_dma_* function family. This patch lets us to simplify the internal low-level implementation without chaning the driver visible API.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Acked-by: Kyungmin Park kyungmin.park@samsung.com Tested-By: Subash Patel subash.ramaswamy@linaro.org --- arch/arm/common/dmabounce.c | 13 +++++-- arch/arm/include/asm/dma-mapping.h | 67 ++++++++++++++++++------------------ arch/arm/mm/dma-mapping.c | 4 +-- 3 files changed, 45 insertions(+), 39 deletions(-)

diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index 210ad1b..32e9cc6 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -173,7 +173,8 @@ find_safe_buffer(struct dmabounce_device_info *device_info, dma_addr_t safe_dma_ read_lock_irqsave(&device_info->lock, flags);

list_for_each_entry(b, &device_info->safe_buffers, node) - if (b->safe_dma_addr == safe_dma_addr) { + if (b->safe_dma_addr <= safe_dma_addr && + b->safe_dma_addr + b->size > safe_dma_addr) { rb = b; break; } @@ -362,9 +363,10 @@ void __dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, EXPORT_SYMBOL(__dma_unmap_page);

int dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr, - unsigned long off, size_t sz, enum dma_data_direction dir) + size_t sz, enum dma_data_direction dir) { struct safe_buffer *buf; + unsigned long off;

dev_dbg(dev, "%s(dma=%#x,off=%#lx,sz=%zx,dir=%x)\n", __func__, addr, off, sz, dir); @@ -373,6 +375,8 @@ int dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr, if (!buf) return 1;

+ off = addr - buf->safe_dma_addr; + BUG_ON(buf->direction != dir);

dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n", @@ -391,9 +395,10 @@ int dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr, EXPORT_SYMBOL(dmabounce_sync_for_cpu);

int dmabounce_sync_for_device(struct device *dev, dma_addr_t addr, - unsigned long off, size_t sz, enum dma_data_direction dir) + size_t sz, enum dma_data_direction dir) { struct safe_buffer *buf; + unsigned long off;

dev_dbg(dev, "%s(dma=%#x,off=%#lx,sz=%zx,dir=%x)\n", __func__, addr, off, sz, dir); @@ -402,6 +407,8 @@ int dmabounce_sync_for_device(struct device *dev, dma_addr_t addr, if (!buf) return 1;

+ off = addr - buf->safe_dma_addr; + BUG_ON(buf->direction != dir);

dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n", diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 6a838da..eeddbe2 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -266,19 +266,17 @@ extern void __dma_unmap_page(struct device *, dma_addr_t, size_t, /* * Private functions */ -int dmabounce_sync_for_cpu(struct device *, dma_addr_t, unsigned long, - size_t, enum dma_data_direction); -int dmabounce_sync_for_device(struct device *, dma_addr_t, unsigned long, - size_t, enum dma_data_direction); +int dmabounce_sync_for_cpu(struct device *, dma_addr_t, size_t, enum dma_data_direction); +int dmabounce_sync_for_device(struct device *, dma_addr_t, size_t, enum dma_data_direction); #else static inline int dmabounce_sync_for_cpu(struct device *d, dma_addr_t addr, - unsigned long offset, size_t size, enum dma_data_direction dir) + size_t size, enum dma_data_direction dir) { return 1; }

static inline int dmabounce_sync_for_device(struct device *d, dma_addr_t addr, - unsigned long offset, size_t size, enum dma_data_direction dir) + size_t size, enum dma_data_direction dir) { return 1; } @@ -401,6 +399,33 @@ static inline void dma_unmap_page(struct device *dev, dma_addr_t handle, __dma_unmap_page(dev, handle, size, dir); }

+ +static inline void dma_sync_single_for_cpu(struct device *dev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + BUG_ON(!valid_dma_direction(dir)); + + debug_dma_sync_single_for_cpu(dev, handle, size, dir); + + if (!dmabounce_sync_for_cpu(dev, handle, size, dir)) + return; + + __dma_single_dev_to_cpu(dma_to_virt(dev, handle), size, dir); +} + +static inline void dma_sync_single_for_device(struct device *dev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + BUG_ON(!valid_dma_direction(dir)); + + debug_dma_sync_single_for_device(dev, handle, size, dir); + + if (!dmabounce_sync_for_device(dev, handle, size, dir)) + return; + + __dma_single_cpu_to_dev(dma_to_virt(dev, handle), size, dir); +} + /** * dma_sync_single_range_for_cpu * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices @@ -423,40 +448,14 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t handle, unsigned long offset, size_t size, enum dma_data_direction dir) { - BUG_ON(!valid_dma_direction(dir)); - - debug_dma_sync_single_for_cpu(dev, handle + offset, size, dir); - - if (!dmabounce_sync_for_cpu(dev, handle, offset, size, dir)) - return; - - __dma_single_dev_to_cpu(dma_to_virt(dev, handle) + offset, size, dir); + dma_sync_single_for_cpu(dev, handle + offset, size, dir); }

static inline void dma_sync_single_range_for_device(struct device *dev, dma_addr_t handle, unsigned long offset, size_t size, enum dma_data_direction dir) { - BUG_ON(!valid_dma_direction(dir)); - - debug_dma_sync_single_for_device(dev, handle + offset, size, dir); - - if (!dmabounce_sync_for_device(dev, handle, offset, size, dir)) - return; - - __dma_single_cpu_to_dev(dma_to_virt(dev, handle) + offset, size, dir); -} - -static inline void dma_sync_single_for_cpu(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - dma_sync_single_range_for_cpu(dev, handle, 0, size, dir); -} - -static inline void dma_sync_single_for_device(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - dma_sync_single_range_for_device(dev, handle, 0, size, dir); + dma_sync_single_for_device(dev, handle + offset, size, dir); }

/* diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index e4ac5fc..a16993a 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -660,7 +660,7 @@ void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int i;

for_each_sg(sg, s, nents, i) { - if (!dmabounce_sync_for_cpu(dev, sg_dma_address(s), 0, + if (!dmabounce_sync_for_cpu(dev, sg_dma_address(s), sg_dma_len(s), dir)) continue;

@@ -686,7 +686,7 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int i;

for_each_sg(sg, s, nents, i) { - if (!dmabounce_sync_for_device(dev, sg_dma_address(s), 0, + if (!dmabounce_sync_for_device(dev, sg_dma_address(s), sg_dma_len(s), dir)) continue;

This patch converts all dma_sg methods to be generic (independent of the current DMA mapping implementation for ARM architecture). All dma sg operations are now implemented on top of respective dma_map_page/dma_sync_single_for* operations from dma_map_ops structure.

Before this patch there were custom methods for all scatter/gather related operations. They iterated over the whole scatter list and called cache related operations directly (which in turn checked if we use dma bounce code or not and called respective version). This patch changes them not to use such shortcut. Instead it provides similar loop over scatter list and calls methods from the device's dma_map_ops structure. This enables us to use device dependent implementations of cache related operations (direct linear or dma bounce) depending on the provided dma_map_ops structure.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Acked-by: Kyungmin Park kyungmin.park@samsung.com Tested-By: Subash Patel subash.ramaswamy@linaro.org --- arch/arm/mm/dma-mapping.c | 43 +++++++++++++++++++------------------------ 1 file changed, 19 insertions(+), 24 deletions(-)

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 70be6e1..b50fa57 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -622,7 +622,7 @@ void ___dma_page_dev_to_cpu(struct page *page, unsigned long off, EXPORT_SYMBOL(___dma_page_dev_to_cpu);

/** - * dma_map_sg - map a set of SG buffers for streaming mode DMA + * arm_dma_map_sg - map a set of SG buffers for streaming mode DMA * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices * @sg: list of buffers * @nents: number of buffers to map @@ -640,12 +640,13 @@ EXPORT_SYMBOL(___dma_page_dev_to_cpu); int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, struct dma_attrs *attrs) { + struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; int i, j;

for_each_sg(sg, s, nents, i) { - s->dma_address = __dma_map_page(dev, sg_page(s), s->offset, - s->length, dir); + s->dma_address = ops->map_page(dev, sg_page(s), s->offset, + s->length, dir, attrs); if (dma_mapping_error(dev, s->dma_address)) goto bad_mapping; } @@ -653,12 +654,12 @@ int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,

bad_mapping: for_each_sg(sg, s, i, j) - __dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir); + ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs); return 0; }

/** - * dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg + * arm_dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices * @sg: list of buffers * @nents: number of buffers to unmap (same as was passed to dma_map_sg) @@ -670,15 +671,17 @@ int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, struct dma_attrs *attrs) { + struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; + int i;

for_each_sg(sg, s, nents, i) - __dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir); + ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs); }

/** - * dma_sync_sg_for_cpu + * arm_dma_sync_sg_for_cpu * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices * @sg: list of buffers * @nents: number of buffers to map (returned from dma_map_sg) @@ -687,21 +690,17 @@ void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir) { + struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; int i;

- for_each_sg(sg, s, nents, i) { - if (!dmabounce_sync_for_cpu(dev, sg_dma_address(s), - sg_dma_len(s), dir)) - continue; - - __dma_page_dev_to_cpu(sg_page(s), s->offset, - s->length, dir); - } + for_each_sg(sg, s, nents, i) + ops->sync_single_for_cpu(dev, sg_dma_address(s), s->length, + dir); }

/** - * dma_sync_sg_for_device + * arm_dma_sync_sg_for_device * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices * @sg: list of buffers * @nents: number of buffers to map (returned from dma_map_sg) @@ -710,17 +709,13 @@ void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir) { + struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; int i;

- for_each_sg(sg, s, nents, i) { - if (!dmabounce_sync_for_device(dev, sg_dma_address(s), - sg_dma_len(s), dir)) - continue; - - __dma_page_cpu_to_dev(sg_page(s), s->offset, - s->length, dir); - } + for_each_sg(sg, s, nents, i) + ops->sync_single_for_device(dev, sg_dma_address(s), s->length, + dir); }

/*

This patch just performs a global cleanup in DMA mapping implementation for ARM architecture. Some of the tiny helper functions have been moved to the caller code, some have been merged together.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Acked-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de Tested-By: Subash Patel subash.ramaswamy@linaro.org --- arch/arm/mm/dma-mapping.c | 88 +++++++++++++-------------------------------- 1 file changed, 24 insertions(+), 64 deletions(-)

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index c949668..dddb406 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -40,64 +40,12 @@ * the CPU does do speculative prefetches, which means we clean caches * before transfers and delay cache invalidation until transfer completion. * - * Private support functions: these are not part of the API and are - * liable to change. Drivers must not use these. */ -static inline void __dma_single_cpu_to_dev(const void *kaddr, size_t size, - enum dma_data_direction dir) -{ - extern void ___dma_single_cpu_to_dev(const void *, size_t, - enum dma_data_direction); - - if (!arch_is_coherent()) - ___dma_single_cpu_to_dev(kaddr, size, dir); -} - -static inline void __dma_single_dev_to_cpu(const void *kaddr, size_t size, - enum dma_data_direction dir) -{ - extern void ___dma_single_dev_to_cpu(const void *, size_t, - enum dma_data_direction); - - if (!arch_is_coherent()) - ___dma_single_dev_to_cpu(kaddr, size, dir); -} - -static inline void __dma_page_cpu_to_dev(struct page *page, unsigned long off, - size_t size, enum dma_data_direction dir) -{ - extern void ___dma_page_cpu_to_dev(struct page *, unsigned long, +static void __dma_page_cpu_to_dev(struct page *, unsigned long, size_t, enum dma_data_direction); - - if (!arch_is_coherent()) - ___dma_page_cpu_to_dev(page, off, size, dir); -} - -static inline void __dma_page_dev_to_cpu(struct page *page, unsigned long off, - size_t size, enum dma_data_direction dir) -{ - extern void ___dma_page_dev_to_cpu(struct page *, unsigned long, +static void __dma_page_dev_to_cpu(struct page *, unsigned long, size_t, enum dma_data_direction);

- if (!arch_is_coherent()) - ___dma_page_dev_to_cpu(page, off, size, dir); -} - - -static inline dma_addr_t __dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir) -{ - __dma_page_cpu_to_dev(page, offset, size, dir); - return pfn_to_dma(dev, page_to_pfn(page)) + offset; -} - -static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle, - size_t size, enum dma_data_direction dir) -{ - __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)), - handle & ~PAGE_MASK, size, dir); -} - /** * arm_dma_map_page - map a portion of a page for streaming DMA * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices @@ -112,11 +60,13 @@ static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle, * The device owns this memory once this call has completed. The CPU * can regain ownership by calling dma_unmap_page(). */ -static inline dma_addr_t arm_dma_map_page(struct device *dev, struct page *page, +static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - return __dma_map_page(dev, page, offset, size, dir); + if (!arch_is_coherent()) + __dma_page_cpu_to_dev(page, offset, size, dir); + return pfn_to_dma(dev, page_to_pfn(page)) + offset; }

/** @@ -133,27 +83,31 @@ static inline dma_addr_t arm_dma_map_page(struct device *dev, struct page *page, * After this call, reads by the CPU to the buffer are guaranteed to see * whatever the device wrote there. */ -static inline void arm_dma_unmap_page(struct device *dev, dma_addr_t handle, +static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - __dma_unmap_page(dev, handle, size, dir); + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)), + handle & ~PAGE_MASK, size, dir); }

-static inline void arm_dma_sync_single_for_cpu(struct device *dev, +static void arm_dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { unsigned int offset = handle & (PAGE_SIZE - 1); struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); - __dma_page_dev_to_cpu(page, offset, size, dir); + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(page, offset, size, dir); }

-static inline void arm_dma_sync_single_for_device(struct device *dev, +static void arm_dma_sync_single_for_device(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { unsigned int offset = handle & (PAGE_SIZE - 1); struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); - __dma_page_cpu_to_dev(page, offset, size, dir); + if (!arch_is_coherent()) + __dma_page_cpu_to_dev(page, offset, size, dir); }

static int arm_dma_set_mask(struct device *dev, u64 dma_mask); @@ -647,7 +601,13 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, } while (left); }

-void ___dma_page_cpu_to_dev(struct page *page, unsigned long off, +/* + * Make an area consistent for devices. + * Note: Drivers should NOT use this function directly, as it will break + * platforms with CONFIG_DMABOUNCE. + * Use the driver DMA support - see dma-mapping.h (dma_sync_*) + */ +static void __dma_page_cpu_to_dev(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { unsigned long paddr; @@ -663,7 +623,7 @@ void ___dma_page_cpu_to_dev(struct page *page, unsigned long off, /* FIXME: non-speculating: flush on bidirectional mappings? */ }

-void ___dma_page_dev_to_cpu(struct page *page, unsigned long off, +static void __dma_page_dev_to_cpu(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { unsigned long paddr = page_to_phys(page) + off;

This patch add a complete implementation of DMA-mapping API for devices which have IOMMU support.

This implementation tries to optimize dma address space usage by remapping all possible physical memory chunks into a single dma address space chunk.

DMA address space is managed on top of the bitmap stored in the dma_iommu_mapping structure stored in device->archdata. Platform setup code has to initialize parameters of the dma address space (base address, size, allocation precision order) with arm_iommu_create_mapping() function. To reduce the size of the bitmap, all allocations are aligned to the specified order of base 4 KiB pages.

dma_alloc_* functions allocate physical memory in chunks, each with alloc_pages() function to avoid failing if the physical memory gets fragmented. In worst case the allocated buffer is composed of 4 KiB page chunks.

dma_map_sg() function minimizes the total number of dma address space chunks by merging of physical memory chunks into one larger dma address space chunk. If requested chunk (scatter list entry) boundaries match physical page boundaries, most calls to dma_map_sg() requests will result in creating only one chunk in dma address space.

dma_map_page() simply creates a mapping for the given page(s) in the dma address space.

All dma functions also perform required cache operation like their counterparts from the arm linear physical memory mapping version.

This patch contains code and fixes kindly provided by: - Krishna Reddy vdumpa@nvidia.com, - Andrzej Pietrasiewicz andrzej.p@samsung.com, - Hiroshi DOYU hdoyu@nvidia.com

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Acked-by: Kyungmin Park kyungmin.park@samsung.com Reviewed-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Tested-By: Subash Patel subash.ramaswamy@linaro.org --- arch/arm/Kconfig | 8 + arch/arm/include/asm/device.h | 3 + arch/arm/include/asm/dma-iommu.h | 34 ++ arch/arm/mm/dma-mapping.c | 712 +++++++++++++++++++++++++++++++++++++- arch/arm/mm/vmregion.h | 2 +- 5 files changed, 747 insertions(+), 12 deletions(-) create mode 100644 arch/arm/include/asm/dma-iommu.h

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index c8111c5..97478a5 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -46,6 +46,14 @@ config ARM config ARM_HAS_SG_CHAIN bool

+config NEED_SG_DMA_LENGTH + bool + +config ARM_DMA_USE_IOMMU + select NEED_SG_DMA_LENGTH + select ARM_HAS_SG_CHAIN + bool + config HAVE_PWM bool

diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h index 6e2cb0e..b69c0d3 100644 --- a/arch/arm/include/asm/device.h +++ b/arch/arm/include/asm/device.h @@ -14,6 +14,9 @@ struct dev_archdata { #ifdef CONFIG_IOMMU_API void *iommu; /* private IOMMU data */ #endif +#ifdef CONFIG_ARM_DMA_USE_IOMMU + struct dma_iommu_mapping *mapping; +#endif };

struct omap_device; diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h new file mode 100644 index 0000000..799b094 --- /dev/null +++ b/arch/arm/include/asm/dma-iommu.h @@ -0,0 +1,34 @@ +#ifndef ASMARM_DMA_IOMMU_H +#define ASMARM_DMA_IOMMU_H + +#ifdef __KERNEL__ + +#include <linux/mm_types.h> +#include <linux/scatterlist.h> +#include <linux/dma-debug.h> +#include <linux/kmemcheck.h> + +struct dma_iommu_mapping { + /* iommu specific data */ + struct iommu_domain *domain; + + void *bitmap; + size_t bits; + unsigned int order; + dma_addr_t base; + + spinlock_t lock; + struct kref kref; +}; + +struct dma_iommu_mapping * +arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size, + int order); + +void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping); + +int arm_iommu_attach_device(struct device *dev, + struct dma_iommu_mapping *mapping); + +#endif /* __KERNEL__ */ +#endif diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 2501866..3ac4760 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -19,6 +19,8 @@ #include <linux/dma-mapping.h> #include <linux/highmem.h> #include <linux/slab.h> +#include <linux/iommu.h> +#include <linux/vmalloc.h>

#include <asm/memory.h> #include <asm/highmem.h> @@ -26,6 +28,7 @@ #include <asm/tlbflush.h> #include <asm/sizes.h> #include <asm/mach/arch.h> +#include <asm/dma-iommu.h>

#include "mm.h"

@@ -155,6 +158,21 @@ static u64 get_coherent_dma_mask(struct device *dev) return mask; }

+static void __dma_clear_buffer(struct page *page, size_t size) +{ + void *ptr; + /* + * Ensure that the allocated pages are zeroed, and that any data + * lurking in the kernel direct-mapped region is invalidated. + */ + ptr = page_address(page); + if (ptr) { + memset(ptr, 0, size); + dmac_flush_range(ptr, ptr + size); + outer_flush_range(__pa(ptr), __pa(ptr) + size); + } +} + /* * Allocate a DMA buffer for 'dev' of size 'size' using the * specified gfp mask. Note that 'size' must be page aligned. @@ -163,7 +181,6 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf { unsigned long order = get_order(size); struct page *page, *p, *e; - void *ptr; u64 mask = get_coherent_dma_mask(dev);

#ifdef CONFIG_DMA_API_DEBUG @@ -192,14 +209,7 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++) __free_page(p);

- /* - * Ensure that the allocated pages are zeroed, and that any data - * lurking in the kernel direct-mapped region is invalidated. - */ - ptr = page_address(page); - memset(ptr, 0, size); - dmac_flush_range(ptr, ptr + size); - outer_flush_range(__pa(ptr), __pa(ptr) + size); + __dma_clear_buffer(page, size);

return page; } @@ -348,7 +358,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot, u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);

pte = consistent_pte[idx] + off; - c->vm_pages = page; + c->priv = page;

do { BUG_ON(!pte_none(*pte)); @@ -509,13 +519,14 @@ int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr); if (c) { unsigned long off = vma->vm_pgoff; + struct page *pages = c->priv;

kern_size = (c->vm_end - c->vm_start) >> PAGE_SHIFT;

if (off < kern_size && user_size <= (kern_size - off)) { ret = remap_pfn_range(vma, vma->vm_start, - page_to_pfn(c->vm_pages) + off, + page_to_pfn(pages) + off, user_size << PAGE_SHIFT, vma->vm_page_prot); } @@ -654,6 +665,9 @@ int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, int i, j;

for_each_sg(sg, s, nents, i) { +#ifdef CONFIG_NEED_SG_DMA_LENGTH + s->dma_length = s->length; +#endif s->dma_address = ops->map_page(dev, sg_page(s), s->offset, s->length, dir, attrs); if (dma_mapping_error(dev, s->dma_address)) @@ -762,3 +776,679 @@ static int __init dma_debug_do_init(void) return 0; } fs_initcall(dma_debug_do_init); + +#ifdef CONFIG_ARM_DMA_USE_IOMMU + +/* IOMMU */ + +static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping, + size_t size) +{ + unsigned int order = get_order(size); + unsigned int align = 0; + unsigned int count, start; + unsigned long flags; + + count = ((PAGE_ALIGN(size) >> PAGE_SHIFT) + + (1 << mapping->order) - 1) >> mapping->order; + + if (order > mapping->order) + align = (1 << (order - mapping->order)) - 1; + + spin_lock_irqsave(&mapping->lock, flags); + start = bitmap_find_next_zero_area(mapping->bitmap, mapping->bits, 0, + count, align); + if (start > mapping->bits) { + spin_unlock_irqrestore(&mapping->lock, flags); + return DMA_ERROR_CODE; + } + + bitmap_set(mapping->bitmap, start, count); + spin_unlock_irqrestore(&mapping->lock, flags); + + return mapping->base + (start << (mapping->order + PAGE_SHIFT)); +} + +static inline void __free_iova(struct dma_iommu_mapping *mapping, + dma_addr_t addr, size_t size) +{ + unsigned int start = (addr - mapping->base) >> + (mapping->order + PAGE_SHIFT); + unsigned int count = ((size >> PAGE_SHIFT) + + (1 << mapping->order) - 1) >> mapping->order; + unsigned long flags; + + spin_lock_irqsave(&mapping->lock, flags); + bitmap_clear(mapping->bitmap, start, count); + spin_unlock_irqrestore(&mapping->lock, flags); +} + +static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, gfp_t gfp) +{ + struct page **pages; + int count = size >> PAGE_SHIFT; + int array_size = count * sizeof(struct page *); + int i = 0; + + if (array_size <= PAGE_SIZE) + pages = kzalloc(array_size, gfp); + else + pages = vzalloc(array_size); + if (!pages) + return NULL; + + while (count) { + int j, order = __ffs(count); + + pages[i] = alloc_pages(gfp | __GFP_NOWARN, order); + while (!pages[i] && order) + pages[i] = alloc_pages(gfp | __GFP_NOWARN, --order); + if (!pages[i]) + goto error; + + if (order) + split_page(pages[i], order); + j = 1 << order; + while (--j) + pages[i + j] = pages[i] + j; + + __dma_clear_buffer(pages[i], PAGE_SIZE << order); + i += 1 << order; + count -= 1 << order; + } + + return pages; +error: + while (--i) + if (pages[i]) + __free_pages(pages[i], 0); + if (array_size < PAGE_SIZE) + kfree(pages); + else + vfree(pages); + return NULL; +} + +static int __iommu_free_buffer(struct device *dev, struct page **pages, size_t size) +{ + int count = size >> PAGE_SHIFT; + int array_size = count * sizeof(struct page *); + int i; + for (i = 0; i < count; i++) + if (pages[i]) + __free_pages(pages[i], 0); + if (array_size < PAGE_SIZE) + kfree(pages); + else + vfree(pages); + return 0; +} + +/* + * Create a CPU mapping for a specified pages + */ +static void * +__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot) +{ + struct arm_vmregion *c; + size_t align; + size_t count = size >> PAGE_SHIFT; + int bit; + + if (!consistent_pte[0]) { + pr_err("%s: not initialised\n", __func__); + dump_stack(); + return NULL; + } + + /* + * Align the virtual region allocation - maximum alignment is + * a section size, minimum is a page size. This helps reduce + * fragmentation of the DMA space, and also prevents allocations + * smaller than a section from crossing a section boundary. + */ + bit = fls(size - 1); + if (bit > SECTION_SHIFT) + bit = SECTION_SHIFT; + align = 1 << bit; + + /* + * Allocate a virtual address in the consistent mapping region. + */ + c = arm_vmregion_alloc(&consistent_head, align, size, + gfp & ~(__GFP_DMA | __GFP_HIGHMEM), NULL); + if (c) { + pte_t *pte; + int idx = CONSISTENT_PTE_INDEX(c->vm_start); + int i = 0; + u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1); + + pte = consistent_pte[idx] + off; + c->priv = pages; + + do { + BUG_ON(!pte_none(*pte)); + + set_pte_ext(pte, mk_pte(pages[i], prot), 0); + pte++; + off++; + i++; + if (off >= PTRS_PER_PTE) { + off = 0; + pte = consistent_pte[++idx]; + } + } while (i < count); + + dsb(); + + return (void *)c->vm_start; + } + return NULL; +} + +/* + * Create a mapping in device IO address space for specified pages + */ +static dma_addr_t +__iommu_create_mapping(struct device *dev, struct page **pages, size_t size) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + dma_addr_t dma_addr, iova; + int i, ret = DMA_ERROR_CODE; + + dma_addr = __alloc_iova(mapping, size); + if (dma_addr == DMA_ERROR_CODE) + return dma_addr; + + iova = dma_addr; + for (i = 0; i < count; ) { + unsigned int next_pfn = page_to_pfn(pages[i]) + 1; + phys_addr_t phys = page_to_phys(pages[i]); + unsigned int len, j; + + for (j = i + 1; j < count; j++, next_pfn++) + if (page_to_pfn(pages[j]) != next_pfn) + break; + + len = (j - i) << PAGE_SHIFT; + ret = iommu_map(mapping->domain, iova, phys, len, 0); + if (ret < 0) + goto fail; + iova += len; + i = j; + } + return dma_addr; +fail: + iommu_unmap(mapping->domain, dma_addr, iova-dma_addr); + __free_iova(mapping, dma_addr, size); + return DMA_ERROR_CODE; +} + +static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t size) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + + /* + * add optional in-page offset from iova to size and align + * result to page size + */ + size = PAGE_ALIGN((iova & ~PAGE_MASK) + size); + iova &= PAGE_MASK; + + iommu_unmap(mapping->domain, iova, size); + __free_iova(mapping, iova, size); + return 0; +} + +static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) +{ + pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); + struct page **pages; + void *addr = NULL; + + *handle = DMA_ERROR_CODE; + size = PAGE_ALIGN(size); + + pages = __iommu_alloc_buffer(dev, size, gfp); + if (!pages) + return NULL; + + *handle = __iommu_create_mapping(dev, pages, size); + if (*handle == DMA_ERROR_CODE) + goto err_buffer; + + addr = __iommu_alloc_remap(pages, size, gfp, prot); + if (!addr) + goto err_mapping; + + return addr; + +err_mapping: + __iommu_remove_mapping(dev, *handle, size); +err_buffer: + __iommu_free_buffer(dev, pages, size); + return NULL; +} + +static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + struct dma_attrs *attrs) +{ + struct arm_vmregion *c; + + vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); + c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr); + + if (c) { + struct page **pages = c->priv; + + unsigned long uaddr = vma->vm_start; + unsigned long usize = vma->vm_end - vma->vm_start; + int i = 0; + + do { + int ret; + + ret = vm_insert_page(vma, uaddr, pages[i++]); + if (ret) { + pr_err("Remapping memory, error: %d\n", ret); + return ret; + } + + uaddr += PAGE_SIZE; + usize -= PAGE_SIZE; + } while (usize > 0); + } + return 0; +} + +/* + * free a page as defined by the above mapping. + * Must not be called with IRQs disabled. + */ +void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, struct dma_attrs *attrs) +{ + struct arm_vmregion *c; + size = PAGE_ALIGN(size); + + c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr); + if (c) { + struct page **pages = c->priv; + __dma_free_remap(cpu_addr, size); + __iommu_remove_mapping(dev, handle, size); + __iommu_free_buffer(dev, pages, size); + } +} + +/* + * Map a part of the scatter-gather list into contiguous io address space + */ +static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, + size_t size, dma_addr_t *handle, + enum dma_data_direction dir) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + dma_addr_t iova, iova_base; + int ret = 0; + unsigned int count; + struct scatterlist *s; + + size = PAGE_ALIGN(size); + *handle = DMA_ERROR_CODE; + + iova_base = iova = __alloc_iova(mapping, size); + if (iova == DMA_ERROR_CODE) + return -ENOMEM; + + for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) { + phys_addr_t phys = page_to_phys(sg_page(s)); + unsigned int len = PAGE_ALIGN(s->offset + s->length); + + if (!arch_is_coherent()) + __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); + + ret = iommu_map(mapping->domain, iova, phys, len, 0); + if (ret < 0) + goto fail; + count += len >> PAGE_SHIFT; + iova += len; + } + *handle = iova_base; + + return 0; +fail: + iommu_unmap(mapping->domain, iova_base, count * PAGE_SIZE); + __free_iova(mapping, iova_base, size); + return ret; +} + +/** + * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to map + * @dir: DMA transfer direction + * + * Map a set of buffers described by scatterlist in streaming mode for DMA. + * The scatter gather list elements are merged together (if possible) and + * tagged with the appropriate dma address and length. They are obtained via + * sg_dma_{address,length}. + */ +int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + struct scatterlist *s = sg, *dma = sg, *start = sg; + int i, count = 0; + unsigned int offset = s->offset; + unsigned int size = s->offset + s->length; + unsigned int max = dma_get_max_seg_size(dev); + + for (i = 1; i < nents; i++) { + s = sg_next(s); + + s->dma_address = DMA_ERROR_CODE; + s->dma_length = 0; + + if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) { + if (__map_sg_chunk(dev, start, size, &dma->dma_address, + dir) < 0) + goto bad_mapping; + + dma->dma_address += offset; + dma->dma_length = size - offset; + + size = offset = s->offset; + start = s; + dma = sg_next(dma); + count += 1; + } + size += s->length; + } + if (__map_sg_chunk(dev, start, size, &dma->dma_address, dir) < 0) + goto bad_mapping; + + dma->dma_address += offset; + dma->dma_length = size - offset; + + return count+1; + +bad_mapping: + for_each_sg(sg, s, count, i) + __iommu_remove_mapping(dev, sg_dma_address(s), sg_dma_len(s)); + return 0; +} + +/** + * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to unmap (same as was passed to dma_map_sg) + * @dir: DMA transfer direction (same as was passed to dma_map_sg) + * + * Unmap a set of streaming mode DMA translations. Again, CPU access + * rules concerning calls here are the same as for dma_unmap_single(). + */ +void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + struct scatterlist *s; + int i; + + for_each_sg(sg, s, nents, i) { + if (sg_dma_len(s)) + __iommu_remove_mapping(dev, sg_dma_address(s), + sg_dma_len(s)); + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(sg_page(s), s->offset, + s->length, dir); + } +} + +/** + * arm_iommu_sync_sg_for_cpu + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to map (returned from dma_map_sg) + * @dir: DMA transfer direction (same as was passed to dma_map_sg) + */ +void arm_iommu_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + struct scatterlist *s; + int i; + + for_each_sg(sg, s, nents, i) + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir); + +} + +/** + * arm_iommu_sync_sg_for_device + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to map (returned from dma_map_sg) + * @dir: DMA transfer direction (same as was passed to dma_map_sg) + */ +void arm_iommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + struct scatterlist *s; + int i; + + for_each_sg(sg, s, nents, i) + if (!arch_is_coherent()) + __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); +} + + +/** + * arm_iommu_map_page + * @dev: valid struct device pointer + * @page: page that buffer resides in + * @offset: offset into page for start of buffer + * @size: size of buffer to map + * @dir: DMA transfer direction + * + * IOMMU aware version of arm_dma_map_page() + */ +static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + dma_addr_t dma_addr; + int ret, len = PAGE_ALIGN(size + offset); + + if (!arch_is_coherent()) + __dma_page_cpu_to_dev(page, offset, size, dir); + + dma_addr = __alloc_iova(mapping, len); + if (dma_addr == DMA_ERROR_CODE) + return dma_addr; + + ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, 0); + if (ret < 0) + goto fail; + + return dma_addr + offset; +fail: + __free_iova(mapping, dma_addr, len); + return DMA_ERROR_CODE; +} + +/** + * arm_iommu_unmap_page + * @dev: valid struct device pointer + * @handle: DMA address of buffer + * @size: size of buffer (same as passed to dma_map_page) + * @dir: DMA transfer direction (same as passed to dma_map_page) + * + * IOMMU aware version of arm_dma_unmap_page() + */ +static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + dma_addr_t iova = handle & PAGE_MASK; + struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + int offset = handle & ~PAGE_MASK; + int len = PAGE_ALIGN(size + offset); + + if (!iova) + return; + + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(page, offset, size, dir); + + iommu_unmap(mapping->domain, iova, len); + __free_iova(mapping, iova, len); +} + +static void arm_iommu_sync_single_for_cpu(struct device *dev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + dma_addr_t iova = handle & PAGE_MASK; + struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + unsigned int offset = handle & ~PAGE_MASK; + + if (!iova) + return; + + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(page, offset, size, dir); +} + +static void arm_iommu_sync_single_for_device(struct device *dev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + dma_addr_t iova = handle & PAGE_MASK; + struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + unsigned int offset = handle & ~PAGE_MASK; + + if (!iova) + return; + + __dma_page_cpu_to_dev(page, offset, size, dir); +} + +struct dma_map_ops iommu_ops = { + .alloc = arm_iommu_alloc_attrs, + .free = arm_iommu_free_attrs, + .mmap = arm_iommu_mmap_attrs, + + .map_page = arm_iommu_map_page, + .unmap_page = arm_iommu_unmap_page, + .sync_single_for_cpu = arm_iommu_sync_single_for_cpu, + .sync_single_for_device = arm_iommu_sync_single_for_device, + + .map_sg = arm_iommu_map_sg, + .unmap_sg = arm_iommu_unmap_sg, + .sync_sg_for_cpu = arm_iommu_sync_sg_for_cpu, + .sync_sg_for_device = arm_iommu_sync_sg_for_device, +}; + +/** + * arm_iommu_create_mapping + * @bus: pointer to the bus holding the client device (for IOMMU calls) + * @base: start address of the valid IO address space + * @size: size of the valid IO address space + * @order: accuracy of the IO addresses allocations + * + * Creates a mapping structure which holds information about used/unused + * IO address ranges, which is required to perform memory allocation and + * mapping with IOMMU aware functions. + * + * The client device need to be attached to the mapping with + * arm_iommu_attach_device function. + */ +struct dma_iommu_mapping * +arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size, + int order) +{ + unsigned int count = size >> (PAGE_SHIFT + order); + unsigned int bitmap_size = BITS_TO_LONGS(count) * sizeof(long); + struct dma_iommu_mapping *mapping; + int err = -ENOMEM; + + if (!count) + return ERR_PTR(-EINVAL); + + mapping = kzalloc(sizeof(struct dma_iommu_mapping), GFP_KERNEL); + if (!mapping) + goto err; + + mapping->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + if (!mapping->bitmap) + goto err2; + + mapping->base = base; + mapping->bits = BITS_PER_BYTE * bitmap_size; + mapping->order = order; + spin_lock_init(&mapping->lock); + + mapping->domain = iommu_domain_alloc(bus); + if (!mapping->domain) + goto err3; + + kref_init(&mapping->kref); + return mapping; +err3: + kfree(mapping->bitmap); +err2: + kfree(mapping); +err: + return ERR_PTR(err); +} + +static void release_iommu_mapping(struct kref *kref) +{ + struct dma_iommu_mapping *mapping = + container_of(kref, struct dma_iommu_mapping, kref); + + iommu_domain_free(mapping->domain); + kfree(mapping->bitmap); + kfree(mapping); +} + +void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping) +{ + if (mapping) + kref_put(&mapping->kref, release_iommu_mapping); +} + +/** + * arm_iommu_attach_device + * @dev: valid struct device pointer + * @mapping: io address space mapping structure (returned from + * arm_iommu_create_mapping) + * + * Attaches specified io address space mapping to the provided device, + * this replaces the dma operations (dma_map_ops pointer) with the + * IOMMU aware version. More than one client might be attached to + * the same io address space mapping. + */ +int arm_iommu_attach_device(struct device *dev, + struct dma_iommu_mapping *mapping) +{ + int err; + + err = iommu_attach_device(mapping->domain, dev); + if (err) + return err; + + kref_get(&mapping->kref); + dev->archdata.mapping = mapping; + set_dma_ops(dev, &iommu_ops); + + pr_info("Attached IOMMU controller to %s device.\n", dev_name(dev)); + return 0; +} + +#endif diff --git a/arch/arm/mm/vmregion.h b/arch/arm/mm/vmregion.h index 162be66..bf312c3 100644 --- a/arch/arm/mm/vmregion.h +++ b/arch/arm/mm/vmregion.h @@ -17,7 +17,7 @@ struct arm_vmregion { struct list_head vm_list; unsigned long vm_start; unsigned long vm_end; - struct page *vm_pages; + void *priv; int vm_active; const void *caller; };