From b4382e715d6240e460c29a730c5fe9740aea68e5 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Thu, 9 Oct 2014 15:26:35 -0700 Subject: [PATCH 1/4] lib/genalloc.c: add power aligned algorithm One of the more common algorithms used for allocation is to align the start address of the allocation to the order of size requested. Add this as an algorithm option for genalloc. Signed-off-by: Laura Abbott Acked-by: Will Deacon Acked-by: Olof Johansson Reviewed-by: Catalin Marinas Cc: Arnd Bergmann Cc: David Riley Cc: Ritesh Harjain Cc: Russell King Cc: Thierry Reding Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 505e3be6c082489a32a88e042f930d047b6415bc) Signed-off-by: Mark Brown --- include/linux/genalloc.h | 4 ++++ lib/genalloc.c | 20 ++++++++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 661d374aeb2d..d278793da6e7 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -106,6 +106,10 @@ extern void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo, extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, void *data); +extern unsigned long gen_pool_first_fit_order_align(unsigned long *map, + unsigned long size, unsigned long start, unsigned int nr, + void *data); + extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, void *data); diff --git a/lib/genalloc.c b/lib/genalloc.c index b35cfa9bc3d4..095b8f9b1a50 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -446,6 +446,26 @@ unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size, } EXPORT_SYMBOL(gen_pool_first_fit); +/** + * gen_pool_first_fit_order_align - find the first available region + * of memory matching the size requirement. The region will be aligned + * to the order of the size specified. + * @map: The address to base the search on + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + * @nr: The number of zeroed bits we're looking for + * @data: additional data - unused + */ +unsigned long gen_pool_first_fit_order_align(unsigned long *map, + unsigned long size, unsigned long start, + unsigned int nr, void *data) +{ + unsigned long align_mask = roundup_pow_of_two(nr) - 1; + + return bitmap_find_next_zero_area(map, size, start, nr, align_mask); +} +EXPORT_SYMBOL(gen_pool_first_fit_order_align); + /** * gen_pool_best_fit - find the best fitting region of memory * macthing the size requirement (no alignment constraint) From e4d45c70b7bad66ada07b19edcc1ffa692c1845b Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Thu, 9 Oct 2014 15:26:38 -0700 Subject: [PATCH 2/4] lib/genalloc.c: add genpool range check function After allocating an address from a particular genpool, there is no good way to verify if that address actually belongs to a genpool. Introduce addr_in_gen_pool which will return if an address plus size falls completely within the genpool range. Signed-off-by: Laura Abbott Acked-by: Will Deacon Reviewed-by: Olof Johansson Reviewed-by: Catalin Marinas Cc: Arnd Bergmann Cc: David Riley Cc: Ritesh Harjain Cc: Russell King Cc: Thierry Reding Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 9efb3a421d55d30b65fb0dbee05108d15c6c55f7) Signed-off-by: Mark Brown --- include/linux/genalloc.h | 3 +++ lib/genalloc.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+) diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index d278793da6e7..bc24f34c6ecb 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -117,6 +117,9 @@ extern struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order, int nid); extern struct gen_pool *dev_get_gen_pool(struct device *dev); +bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, + size_t size); + #ifdef CONFIG_OF extern struct gen_pool *of_get_named_gen_pool(struct device_node *np, const char *propname, int index); diff --git a/lib/genalloc.c b/lib/genalloc.c index 095b8f9b1a50..f8b131bd920e 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -368,6 +368,35 @@ void gen_pool_for_each_chunk(struct gen_pool *pool, } EXPORT_SYMBOL(gen_pool_for_each_chunk); +/** + * addr_in_gen_pool - checks if an address falls within the range of a pool + * @pool: the generic memory pool + * @start: start address + * @size: size of the region + * + * Check if the range of addresses falls within the specified pool. Returns + * true if the entire range is contained in the pool and false otherwise. + */ +bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, + size_t size) +{ + bool found = false; + unsigned long end = start + size; + struct gen_pool_chunk *chunk; + + rcu_read_lock(); + list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk) { + if (start >= chunk->start_addr && start <= chunk->end_addr) { + if (end <= chunk->end_addr) { + found = true; + break; + } + } + } + rcu_read_unlock(); + return found; +} + /** * gen_pool_avail - get available free space of the pool * @pool: pool to get available free space From dd403c2d2cf5c25eb82310bfe70704c0ea8452b7 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Thu, 9 Oct 2014 15:26:40 -0700 Subject: [PATCH 3/4] common: dma-mapping: introduce common remapping functions For architectures without coherent DMA, memory for DMA may need to be remapped with coherent attributes. Factor out the the remapping code from arm and put it in a common location to reduce code duplication. As part of this, the arm APIs are now migrated away from ioremap_page_range to the common APIs which use map_vm_area for remapping. This should be an equivalent change and using map_vm_area is more correct as ioremap_page_range is intended to bring in io addresses into the cpu space and not regular kernel managed memory. Signed-off-by: Laura Abbott Reviewed-by: Catalin Marinas Cc: Arnd Bergmann Cc: David Riley Cc: Olof Johansson Cc: Ritesh Harjain Cc: Russell King Cc: Thierry Reding Cc: Will Deacon Cc: James Hogan Cc: Laura Abbott Cc: Mitchel Humpherys Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 513510ddba9650fc7da456eefeb0ead7632324f6) Signed-off-by: Mark Brown --- arch/arm/mm/dma-mapping.c | 57 +++---------------- drivers/base/dma-mapping.c | 72 ++++++++++++++++++++++++ include/asm-generic/dma-mapping-common.h | 9 +++ 3 files changed, 90 insertions(+), 48 deletions(-) diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index ef3e0f3aac96..b2aa3e4f0e67 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -265,37 +265,19 @@ static void * __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot, const void *caller) { - struct vm_struct *area; - unsigned long addr; - /* * DMA allocation can be mapped to user space, so lets * set VM_USERMAP flags too. */ - area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP, - caller); - if (!area) - return NULL; - addr = (unsigned long)area->addr; - area->phys_addr = __pfn_to_phys(page_to_pfn(page)); - - if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) { - vunmap((void *)addr); - return NULL; - } - return (void *)addr; + return dma_common_contiguous_remap(page, size, + VM_ARM_DMA_CONSISTENT | VM_USERMAP, + prot, caller); } static void __dma_free_remap(void *cpu_addr, size_t size) { - unsigned int flags = VM_ARM_DMA_CONSISTENT | VM_USERMAP; - struct vm_struct *area = find_vm_area(cpu_addr); - if (!area || (area->flags & flags) != flags) { - WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); - return; - } - unmap_kernel_range((unsigned long)cpu_addr, size); - vunmap(cpu_addr); + dma_common_free_remap(cpu_addr, size, + VM_ARM_DMA_CONSISTENT | VM_USERMAP); } #define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K @@ -1167,29 +1149,8 @@ static void * __iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot, const void *caller) { - unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; - struct vm_struct *area; - unsigned long p; - - area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP, - caller); - if (!area) - return NULL; - - area->pages = pages; - area->nr_pages = nr_pages; - p = (unsigned long)area->addr; - - for (i = 0; i < nr_pages; i++) { - phys_addr_t phys = __pfn_to_phys(page_to_pfn(pages[i])); - if (ioremap_page_range(p, p + PAGE_SIZE, phys, prot)) - goto err; - p += PAGE_SIZE; - } - return area->addr; -err: - unmap_kernel_range((unsigned long)area->addr, size); - vunmap(area->addr); + return dma_common_pages_remap(pages, size, + VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller); return NULL; } @@ -1386,8 +1347,8 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, } if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) { - unmap_kernel_range((unsigned long)cpu_addr, size); - vunmap(cpu_addr); + dma_common_free_remap(cpu_addr, size, + VM_ARM_DMA_CONSISTENT | VM_USERMAP); } __iommu_remove_mapping(dev, handle, size); diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c index 0ce39a33b3c2..9c36ca9ed1dd 100644 --- a/drivers/base/dma-mapping.c +++ b/drivers/base/dma-mapping.c @@ -10,6 +10,8 @@ #include #include #include +#include +#include #include /* @@ -267,3 +269,73 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, return ret; } EXPORT_SYMBOL(dma_common_mmap); + +#ifdef CONFIG_MMU +/* + * remaps an array of PAGE_SIZE pages into another vm_area + * Cannot be used in non-sleeping contexts + */ +void *dma_common_pages_remap(struct page **pages, size_t size, + unsigned long vm_flags, pgprot_t prot, + const void *caller) +{ + struct vm_struct *area; + + area = get_vm_area_caller(size, vm_flags, caller); + if (!area) + return NULL; + + area->pages = pages; + + if (map_vm_area(area, prot, pages)) { + vunmap(area->addr); + return NULL; + } + + return area->addr; +} + +/* + * remaps an allocated contiguous region into another vm_area. + * Cannot be used in non-sleeping contexts + */ + +void *dma_common_contiguous_remap(struct page *page, size_t size, + unsigned long vm_flags, + pgprot_t prot, const void *caller) +{ + int i; + struct page **pages; + void *ptr; + unsigned long pfn; + + pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL); + if (!pages) + return NULL; + + for (i = 0, pfn = page_to_pfn(page); i < (size >> PAGE_SHIFT); i++) + pages[i] = pfn_to_page(pfn + i); + + ptr = dma_common_pages_remap(pages, size, vm_flags, prot, caller); + + kfree(pages); + + return ptr; +} + +/* + * unmaps a range previously mapped by dma_common_*_remap + */ +void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags) +{ + struct vm_struct *area = find_vm_area(cpu_addr); + + if (!area || (area->flags & vm_flags) != vm_flags) { + WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); + return; + } + + unmap_kernel_range((unsigned long)cpu_addr, size); + vunmap(cpu_addr); +} +#endif diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h index de8bf89940f8..a9fd248f5d48 100644 --- a/include/asm-generic/dma-mapping-common.h +++ b/include/asm-generic/dma-mapping-common.h @@ -179,6 +179,15 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size); +void *dma_common_contiguous_remap(struct page *page, size_t size, + unsigned long vm_flags, + pgprot_t prot, const void *caller); + +void *dma_common_pages_remap(struct page **pages, size_t size, + unsigned long vm_flags, pgprot_t prot, + const void *caller); +void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags); + /** * dma_mmap_attrs - map a coherent DMA allocation into user space * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices From 598e8b9c75705238d4e0c7ff8532ca4acfefdcde Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Fri, 29 Aug 2014 16:08:02 +0100 Subject: [PATCH 4/4] arm64: Add brackets around user_stack_pointer() Commit 5f888a1d33 (ARM64: perf: support dwarf unwinding in compat mode) changes user_stack_pointer() to return the compat SP for 32-bit tasks but without brackets around the whole definition, with possible issues on the call sites (noticed with a subsequent fix for KSTK_ESP). Fixes: 5f888a1d33c4 (ARM64: perf: support dwarf unwinding in compat mode) Reported-by: Sudeep Holla Cc: Signed-off-by: Catalin Marinas Signed-off-by: Will Deacon (cherry picked from commit 2520d039728b2a3c5ae7f79fe2a0e9d182855b12) Signed-off-by: Mark Brown --- arch/arm64/include/asm/ptrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index b8e7cf199ce6..47d0ab177f7e 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -132,7 +132,7 @@ struct pt_regs { (!((regs)->pstate & PSR_F_BIT)) #define user_stack_pointer(regs) \ - (!compat_user_mode(regs)) ? ((regs)->sp) : ((regs)->compat_sp) + (!compat_user_mode(regs) ? (regs)->sp : (regs)->compat_sp) /* * Are the current registers suitable for user mode? (used to maintain