diff options
Diffstat (limited to 'arch/arm/mm')
-rw-r--r-- | arch/arm/mm/alignment.c | 6 | ||||
-rw-r--r-- | arch/arm/mm/cache-l2x0.c | 8 | ||||
-rw-r--r-- | arch/arm/mm/cache-v7.S | 3 | ||||
-rw-r--r-- | arch/arm/mm/context.c | 7 | ||||
-rw-r--r-- | arch/arm/mm/dma-mapping.c | 128 | ||||
-rw-r--r-- | arch/arm/mm/flush.c | 2 | ||||
-rw-r--r-- | arch/arm/mm/init.c | 2 | ||||
-rw-r--r-- | arch/arm/mm/ioremap.c | 1 | ||||
-rw-r--r-- | arch/arm/mm/mm.h | 3 | ||||
-rw-r--r-- | arch/arm/mm/mmu.c | 8 | ||||
-rw-r--r-- | arch/arm/mm/tlb-v7.S | 6 |
11 files changed, 140 insertions, 34 deletions
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 9107231aacc5..b9f60ebe3bc4 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -699,7 +699,6 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs, unsigned long instr = *pinstr; u16 tinst1 = (instr >> 16) & 0xffff; u16 tinst2 = instr & 0xffff; - poffset->un = 0; switch (tinst1 & 0xffe0) { /* A6.3.5 Load/Store multiple */ @@ -854,9 +853,10 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) break; case 0x08000000: /* ldm or stm, or thumb-2 32bit instruction */ - if (thumb2_32b) + if (thumb2_32b) { + offset.un = 0; handler = do_alignment_t32_to_handler(&instr, regs, &offset); - else + } else handler = do_alignment_ldmstm; break; diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 2a8e380501e8..97ec2565805a 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -368,14 +368,18 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) /* l2x0 controller is disabled */ writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL); - l2x0_saved_regs.aux_ctrl = aux; - l2x0_inv_all(); /* enable L2X0 */ writel_relaxed(1, l2x0_base + L2X0_CTRL); } + /* Re-read it in case some bits are reserved. */ + aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); + + /* Save the value for resuming. */ + l2x0_saved_regs.aux_ctrl = aux; + outer_cache.inv_range = l2x0_inv_range; outer_cache.clean_range = l2x0_clean_range; outer_cache.flush_range = l2x0_flush_range; diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 39e3fb3db801..3b172275262e 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -211,6 +211,9 @@ ENTRY(v7_coherent_user_range) * isn't mapped, fail with -EFAULT. */ 9001: +#ifdef CONFIG_ARM_ERRATA_775420 + dsb +#endif mov r0, #-EFAULT mov pc, lr UNWIND(.fnend ) diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 119bc52ab93e..4e07eec1270d 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -63,10 +63,11 @@ static int contextidr_notifier(struct notifier_block *unused, unsigned long cmd, pid = task_pid_nr(thread->task) << ASID_BITS; asm volatile( " mrc p15, 0, %0, c13, c0, 1\n" - " bfi %1, %0, #0, %2\n" - " mcr p15, 0, %1, c13, c0, 1\n" + " and %0, %0, %2\n" + " orr %0, %0, %1\n" + " mcr p15, 0, %0, c13, c0, 1\n" : "=r" (contextidr), "+r" (pid) - : "I" (ASID_BITS)); + : "I" (~ASID_MASK)); isb(); return NOTIFY_OK; diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index c2cdf6500f75..13f555d62491 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -267,17 +267,19 @@ static void __dma_free_remap(void *cpu_addr, size_t size) vunmap(cpu_addr); } +#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K + struct dma_pool { size_t size; spinlock_t lock; unsigned long *bitmap; unsigned long nr_pages; void *vaddr; - struct page *page; + struct page **pages; }; static struct dma_pool atomic_pool = { - .size = SZ_256K, + .size = DEFAULT_DMA_COHERENT_POOL_SIZE, }; static int __init early_coherent_pool(char *p) @@ -287,6 +289,21 @@ static int __init early_coherent_pool(char *p) } early_param("coherent_pool", early_coherent_pool); +void __init init_dma_coherent_pool_size(unsigned long size) +{ + /* + * Catch any attempt to set the pool size too late. + */ + BUG_ON(atomic_pool.vaddr); + + /* + * Set architecture specific coherent pool size only if + * it has not been changed by kernel command line parameter. + */ + if (atomic_pool.size == DEFAULT_DMA_COHERENT_POOL_SIZE) + atomic_pool.size = size; +} + /* * Initialise the coherent pool for atomic allocations. */ @@ -297,6 +314,7 @@ static int __init atomic_pool_init(void) unsigned long nr_pages = pool->size >> PAGE_SHIFT; unsigned long *bitmap; struct page *page; + struct page **pages; void *ptr; int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long); @@ -304,21 +322,33 @@ static int __init atomic_pool_init(void) if (!bitmap) goto no_bitmap; + pages = kzalloc(nr_pages * sizeof(struct page *), GFP_KERNEL); + if (!pages) + goto no_pages; + if (IS_ENABLED(CONFIG_CMA)) ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page); else ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot, &page, NULL); if (ptr) { + int i; + + for (i = 0; i < nr_pages; i++) + pages[i] = page + i; + spin_lock_init(&pool->lock); pool->vaddr = ptr; - pool->page = page; + pool->pages = pages; pool->bitmap = bitmap; pool->nr_pages = nr_pages; pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n", (unsigned)pool->size / 1024); return 0; } + + kfree(pages); +no_pages: kfree(bitmap); no_bitmap: pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n", @@ -358,7 +388,7 @@ void __init dma_contiguous_remap(void) if (end > arm_lowmem_limit) end = arm_lowmem_limit; if (start >= end) - return; + continue; map.pfn = __phys_to_pfn(start); map.virtual = __phys_to_virt(start); @@ -423,7 +453,7 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page) unsigned int pageno; unsigned long flags; void *ptr = NULL; - size_t align; + unsigned long align_mask; if (!pool->vaddr) { WARN(1, "coherent pool not initialised!\n"); @@ -435,35 +465,53 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page) * small, so align them to their order in pages, minimum is a page * size. This helps reduce fragmentation of the DMA space. */ - align = PAGE_SIZE << get_order(size); + align_mask = (1 << get_order(size)) - 1; spin_lock_irqsave(&pool->lock, flags); pageno = bitmap_find_next_zero_area(pool->bitmap, pool->nr_pages, - 0, count, (1 << align) - 1); + 0, count, align_mask); if (pageno < pool->nr_pages) { bitmap_set(pool->bitmap, pageno, count); ptr = pool->vaddr + PAGE_SIZE * pageno; - *ret_page = pool->page + pageno; + *ret_page = pool->pages[pageno]; + } else { + pr_err_once("ERROR: %u KiB atomic DMA coherent pool is too small!\n" + "Please increase it with coherent_pool= kernel parameter!\n", + (unsigned)pool->size / 1024); } spin_unlock_irqrestore(&pool->lock, flags); return ptr; } +static bool __in_atomic_pool(void *start, size_t size) +{ + struct dma_pool *pool = &atomic_pool; + void *end = start + size; + void *pool_start = pool->vaddr; + void *pool_end = pool->vaddr + pool->size; + + if (start < pool_start || start >= pool_end) + return false; + + if (end <= pool_end) + return true; + + WARN(1, "Wrong coherent size(%p-%p) from atomic pool(%p-%p)\n", + start, end - 1, pool_start, pool_end - 1); + + return false; +} + static int __free_from_pool(void *start, size_t size) { struct dma_pool *pool = &atomic_pool; unsigned long pageno, count; unsigned long flags; - if (start < pool->vaddr || start > pool->vaddr + pool->size) + if (!__in_atomic_pool(start, size)) return 0; - if (start + size > pool->vaddr + pool->size) { - WARN(1, "freeing wrong coherent size from pool\n"); - return 0; - } - pageno = (start - pool->vaddr) >> PAGE_SHIFT; count = size >> PAGE_SHIFT; @@ -648,12 +696,12 @@ void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, if (arch_is_coherent() || nommu()) { __dma_free_buffer(page, size); + } else if (__free_from_pool(cpu_addr, size)) { + return; } else if (!IS_ENABLED(CONFIG_CMA)) { __dma_free_remap(cpu_addr, size); __dma_free_buffer(page, size); } else { - if (__free_from_pool(cpu_addr, size)) - return; /* * Non-atomic allocations cannot be freed with IRQs disabled */ @@ -1090,10 +1138,22 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t si return 0; } +static struct page **__atomic_get_pages(void *addr) +{ + struct dma_pool *pool = &atomic_pool; + struct page **pages = pool->pages; + int offs = (addr - pool->vaddr) >> PAGE_SHIFT; + + return pages + offs; +} + static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs) { struct vm_struct *area; + if (__in_atomic_pool(cpu_addr, PAGE_SIZE)) + return __atomic_get_pages(cpu_addr); + if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) return cpu_addr; @@ -1103,6 +1163,34 @@ static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs) return NULL; } +static void *__iommu_alloc_atomic(struct device *dev, size_t size, + dma_addr_t *handle) +{ + struct page *page; + void *addr; + + addr = __alloc_from_pool(size, &page); + if (!addr) + return NULL; + + *handle = __iommu_create_mapping(dev, &page, size); + if (*handle == DMA_ERROR_CODE) + goto err_mapping; + + return addr; + +err_mapping: + __free_from_pool(addr, size); + return NULL; +} + +static void __iommu_free_atomic(struct device *dev, struct page **pages, + dma_addr_t handle, size_t size) +{ + __iommu_remove_mapping(dev, handle, size); + __free_from_pool(page_address(pages[0]), size); +} + static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) { @@ -1113,6 +1201,9 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); + if (gfp & GFP_ATOMIC) + return __iommu_alloc_atomic(dev, size, handle); + pages = __iommu_alloc_buffer(dev, size, gfp); if (!pages) return NULL; @@ -1179,6 +1270,11 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, return; } + if (__in_atomic_pool(cpu_addr, size)) { + __iommu_free_atomic(dev, pages, handle, size); + return; + } + if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) { unmap_kernel_range((unsigned long)cpu_addr, size); vunmap(cpu_addr); diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 77458548e031..40ca11ed6e5f 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -231,8 +231,6 @@ void __sync_icache_dcache(pte_t pteval) struct page *page; struct address_space *mapping; - if (!pte_present_user(pteval)) - return; if (cache_is_vipt_nonaliasing() && !pte_exec(pteval)) /* only flush non-aliasing VIPT caches for exec mappings */ return; diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 9aec41fa80ae..ad722f1208a5 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -324,7 +324,7 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align) BUG_ON(!arm_memblock_steal_permitted); - phys = memblock_alloc(size, align); + phys = memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE); memblock_free(phys, size); memblock_remove(phys, size); diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 566750fa57d4..491f6b3336f5 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -247,6 +247,7 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, if (!area) return NULL; addr = (unsigned long)area->addr; + area->phys_addr = __pfn_to_phys(pfn); #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE) if (DOMAIN_IO == 0 && diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 6776160618ef..a8ee92da3544 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -55,6 +55,9 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page /* permanent static mappings from iotable_init() */ #define VM_ARM_STATIC_MAPPING 0x40000000 +/* empty mapping */ +#define VM_ARM_EMPTY_MAPPING 0x20000000 + /* mapping type (attributes) for permanent static mappings */ #define VM_ARM_MTYPE(mt) ((mt) << 20) #define VM_ARM_MTYPE_MASK (0x1f << 20) diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 4c2d0451e84a..c2fa21d0103e 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -807,7 +807,7 @@ static void __init pmd_empty_section_gap(unsigned long addr) vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm)); vm->addr = (void *)addr; vm->size = SECTION_SIZE; - vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING; + vm->flags = VM_IOREMAP | VM_ARM_EMPTY_MAPPING; vm->caller = pmd_empty_section_gap; vm_area_add_early(vm); } @@ -820,7 +820,7 @@ static void __init fill_pmd_gaps(void) /* we're still single threaded hence no lock needed here */ for (vm = vmlist; vm; vm = vm->next) { - if (!(vm->flags & VM_ARM_STATIC_MAPPING)) + if (!(vm->flags & (VM_ARM_STATIC_MAPPING | VM_ARM_EMPTY_MAPPING))) continue; addr = (unsigned long)vm->addr; if (addr < next) @@ -961,8 +961,8 @@ void __init sanity_check_meminfo(void) * Check whether this memory bank would partially overlap * the vmalloc area. */ - if (__va(bank->start + bank->size) > vmalloc_min || - __va(bank->start + bank->size) < __va(bank->start)) { + if (__va(bank->start + bank->size - 1) >= vmalloc_min || + __va(bank->start + bank->size - 1) <= __va(bank->start)) { unsigned long newsize = vmalloc_min - __va(bank->start); printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx " "to -%.8llx (vmalloc region overlap).\n", diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S index c2021139cb56..ea94765acf9a 100644 --- a/arch/arm/mm/tlb-v7.S +++ b/arch/arm/mm/tlb-v7.S @@ -38,10 +38,10 @@ ENTRY(v7wbi_flush_user_tlb_range) dsb mov r0, r0, lsr #PAGE_SHIFT @ align address mov r1, r1, lsr #PAGE_SHIFT -#ifdef CONFIG_ARM_ERRATA_720789 - mov r3, #0 -#else asid r3, r3 @ mask ASID +#ifdef CONFIG_ARM_ERRATA_720789 + ALT_SMP(W(mov) r3, #0 ) + ALT_UP(W(nop) ) #endif orr r0, r3, r0, lsl #PAGE_SHIFT @ Create initial MVA mov r1, r1, lsl #PAGE_SHIFT |