diff options
34 files changed, 1770 insertions, 319 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index c1601e5a8b7..41996c68a5c 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -508,6 +508,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Also note the kernel might malfunction if you disable some critical bits. + cma=nn[MG] [ARM,KNL] + Sets the size of kernel global memory area for contiguous + memory allocations. For more information, see + include/linux/dma-contiguous.h + cmo_free_hint= [PPC] Format: { yes | no } Specify whether pages are marked as being inactive when they are freed. This is used in CMO environments @@ -515,6 +520,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. a hypervisor. Default: yes + coherent_pool=nn[KMG] [ARM,KNL] + Sets the size of memory pool for coherent, atomic dma + allocations if Contiguous Memory Allocator (CMA) is used. + code_bytes [X86] How many bytes of object code to print in an oops report. Range: 0 - 8192 diff --git a/arch/Kconfig b/arch/Kconfig index 684eb5af439..0a3ffe46e56 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -142,6 +142,9 @@ config HAVE_ARCH_TRACEHOOK config HAVE_DMA_ATTRS bool +config HAVE_DMA_CONTIGUOUS + bool + config USE_GENERIC_SMP_HELPERS bool diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 97478a5d316..24d3302a1b8 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -5,6 +5,8 @@ config ARM select HAVE_DMA_API_DEBUG select HAVE_IDE if PCI || ISA || PCMCIA select HAVE_DMA_ATTRS + select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7) + select CMA if (CPU_V6 || CPU_V6K || CPU_V7) select HAVE_MEMBLOCK select RTC_LIB select SYS_SUPPORTS_APM_EMULATION diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h new file mode 100644 index 00000000000..3ed37b4d93d --- /dev/null +++ b/arch/arm/include/asm/dma-contiguous.h @@ -0,0 +1,15 @@ +#ifndef ASMARM_DMA_CONTIGUOUS_H +#define ASMARM_DMA_CONTIGUOUS_H + +#ifdef __KERNEL__ +#ifdef CONFIG_CMA + +#include <linux/types.h> +#include <asm-generic/dma-contiguous.h> + +void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size); + +#endif +#endif + +#endif diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h index b36f3654bf5..a6efcdd6fd2 100644 --- a/arch/arm/include/asm/mach/map.h +++ b/arch/arm/include/asm/mach/map.h @@ -30,6 +30,7 @@ struct map_desc { #define MT_MEMORY_DTCM 12 #define MT_MEMORY_ITCM 13 #define MT_MEMORY_SO 14 +#define MT_MEMORY_DMA_READY 15 #ifdef CONFIG_MMU extern void iotable_init(struct map_desc *, int); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index ebfac782593..1b3096dfb96 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -81,6 +81,7 @@ __setup("fpe=", fpe_setup); extern void paging_init(struct machine_desc *desc); extern void sanity_check_meminfo(void); extern void reboot_setup(char *str); +extern void setup_dma_zone(struct machine_desc *desc); unsigned int processor_id; EXPORT_SYMBOL(processor_id); @@ -939,12 +940,8 @@ void __init setup_arch(char **cmdline_p) machine_desc = mdesc; machine_name = mdesc->name; -#ifdef CONFIG_ZONE_DMA - if (mdesc->dma_zone_size) { - extern unsigned long arm_dma_zone_size; - arm_dma_zone_size = mdesc->dma_zone_size; - } -#endif + setup_dma_zone(mdesc); + if (mdesc->restart_mode) reboot_setup(&mdesc->restart_mode); diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 3ac47604a6c..ea6b4315409 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -17,7 +17,9 @@ #include <linux/init.h> #include <linux/device.h> #include <linux/dma-mapping.h> +#include <linux/dma-contiguous.h> #include <linux/highmem.h> +#include <linux/memblock.h> #include <linux/slab.h> #include <linux/iommu.h> #include <linux/vmalloc.h> @@ -29,6 +31,9 @@ #include <asm/sizes.h> #include <asm/mach/arch.h> #include <asm/dma-iommu.h> +#include <asm/mach/map.h> +#include <asm/system_info.h> +#include <asm/dma-contiguous.h> #include "mm.h" @@ -181,22 +186,6 @@ 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; - u64 mask = get_coherent_dma_mask(dev); - -#ifdef CONFIG_DMA_API_DEBUG - u64 limit = (mask + 1) & ~mask; - if (limit && size >= limit) { - dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n", - size, mask); - return NULL; - } -#endif - - if (!mask) - return NULL; - - if (mask < 0xffffffffULL) - gfp |= GFP_DMA; page = alloc_pages(gfp, order); if (!page) @@ -279,6 +268,11 @@ static int __init consistent_init(void) unsigned long base = consistent_base; unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT; +#ifndef CONFIG_ARM_DMA_USE_IOMMU + if (cpu_architecture() >= CPU_ARCH_ARMv6) + return 0; +#endif + consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL); if (!consistent_pte) { pr_err("%s: no memory\n", __func__); @@ -319,9 +313,101 @@ static int __init consistent_init(void) return ret; } - core_initcall(consistent_init); +static void *__alloc_from_contiguous(struct device *dev, size_t size, + pgprot_t prot, struct page **ret_page); + +static struct arm_vmregion_head coherent_head = { + .vm_lock = __SPIN_LOCK_UNLOCKED(&coherent_head.vm_lock), + .vm_list = LIST_HEAD_INIT(coherent_head.vm_list), +}; + +size_t coherent_pool_size = DEFAULT_CONSISTENT_DMA_SIZE / 8; + +static int __init early_coherent_pool(char *p) +{ + coherent_pool_size = memparse(p, &p); + return 0; +} +early_param("coherent_pool", early_coherent_pool); + +/* + * Initialise the coherent pool for atomic allocations. + */ +static int __init coherent_init(void) +{ + pgprot_t prot = pgprot_dmacoherent(pgprot_kernel); + size_t size = coherent_pool_size; + struct page *page; + void *ptr; + + if (cpu_architecture() < CPU_ARCH_ARMv6) + return 0; + + ptr = __alloc_from_contiguous(NULL, size, prot, &page); + if (ptr) { + coherent_head.vm_start = (unsigned long) ptr; + coherent_head.vm_end = (unsigned long) ptr + size; + printk(KERN_INFO "DMA: preallocated %u KiB pool for atomic coherent allocations\n", + (unsigned)size / 1024); + return 0; + } + printk(KERN_ERR "DMA: failed to allocate %u KiB pool for atomic coherent allocation\n", + (unsigned)size / 1024); + return -ENOMEM; +} +/* + * CMA is activated by core_initcall, so we must be called after it. + */ +postcore_initcall(coherent_init); + +struct dma_contig_early_reserve { + phys_addr_t base; + unsigned long size; +}; + +static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS] __initdata; + +static int dma_mmu_remap_num __initdata; + +void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) +{ + dma_mmu_remap[dma_mmu_remap_num].base = base; + dma_mmu_remap[dma_mmu_remap_num].size = size; + dma_mmu_remap_num++; +} + +void __init dma_contiguous_remap(void) +{ + int i; + for (i = 0; i < dma_mmu_remap_num; i++) { + phys_addr_t start = dma_mmu_remap[i].base; + phys_addr_t end = start + dma_mmu_remap[i].size; + struct map_desc map; + unsigned long addr; + + if (end > arm_lowmem_limit) + end = arm_lowmem_limit; + if (start >= end) + return; + + map.pfn = __phys_to_pfn(start); + map.virtual = __phys_to_virt(start); + map.length = end - start; + map.type = MT_MEMORY_DMA_READY; + + /* + * Clear previous low-memory mapping + */ + for (addr = __phys_to_virt(start); addr < __phys_to_virt(end); + addr += PMD_SIZE) + pmd_clear(pmd_off_k(addr)); + + iotable_init(&map, 1); + } +} + static void * __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot, const void *caller) @@ -428,6 +514,122 @@ static void __dma_free_remap(void *cpu_addr, size_t size) arm_vmregion_free(&consistent_head, c); } +static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr, + void *data) +{ + struct page *page = virt_to_page(addr); + pgprot_t prot = *(pgprot_t *)data; + + set_pte_ext(pte, mk_pte(page, prot), 0); + return 0; +} + +static void __dma_remap(struct page *page, size_t size, pgprot_t prot) +{ + unsigned long start = (unsigned long) page_address(page); + unsigned end = start + size; + + apply_to_page_range(&init_mm, start, size, __dma_update_pte, &prot); + dsb(); + flush_tlb_kernel_range(start, end); +} + +static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp, + pgprot_t prot, struct page **ret_page, + const void *caller) +{ + struct page *page; + void *ptr; + page = __dma_alloc_buffer(dev, size, gfp); + if (!page) + return NULL; + + ptr = __dma_alloc_remap(page, size, gfp, prot, caller); + if (!ptr) { + __dma_free_buffer(page, size); + return NULL; + } + + *ret_page = page; + return ptr; +} + +static void *__alloc_from_pool(struct device *dev, size_t size, + struct page **ret_page, const void *caller) +{ + struct arm_vmregion *c; + size_t align; + + if (!coherent_head.vm_start) { + printk(KERN_ERR "%s: coherent pool not initialised!\n", + __func__); + dump_stack(); + return NULL; + } + + /* + * Align the region allocation - allocations from pool are rather + * 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); + c = arm_vmregion_alloc(&coherent_head, align, size, 0, caller); + if (c) { + void *ptr = (void *)c->vm_start; + struct page *page = virt_to_page(ptr); + *ret_page = page; + return ptr; + } + return NULL; +} + +static int __free_from_pool(void *cpu_addr, size_t size) +{ + unsigned long start = (unsigned long)cpu_addr; + unsigned long end = start + size; + struct arm_vmregion *c; + + if (start < coherent_head.vm_start || end > coherent_head.vm_end) + return 0; + + c = arm_vmregion_find_remove(&coherent_head, (unsigned long)start); + + if ((c->vm_end - c->vm_start) != size) { + printk(KERN_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; + } + + arm_vmregion_free(&coherent_head, c); + return 1; +} + +static void *__alloc_from_contiguous(struct device *dev, size_t size, + pgprot_t prot, struct page **ret_page) +{ + unsigned long order = get_order(size); + size_t count = size >> PAGE_SHIFT; + struct page *page; + + page = dma_alloc_from_contiguous(dev, count, order); + if (!page) + return NULL; + + __dma_clear_buffer(page, size); + __dma_remap(page, size, prot); + + *ret_page = page; + return page_address(page); +} + +static void __free_from_contiguous(struct device *dev, struct page *page, + size_t size) +{ + __dma_remap(page, size, pgprot_kernel); + dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); +} + static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot) { prot = dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs) ? @@ -436,21 +638,58 @@ static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot) return prot; } +#define nommu() 0 + #else /* !CONFIG_MMU */ -#define __dma_alloc_remap(page, size, gfp, prot, c) page_address(page) -#define __dma_free_remap(addr, size) do { } while (0) +#define nommu() 1 + #define __get_dma_pgprot(attrs, prot) __pgprot(0) +#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c) NULL +#define __alloc_from_pool(dev, size, ret_page, c) NULL +#define __alloc_from_contiguous(dev, size, prot, ret) NULL +#define __free_from_pool(cpu_addr, size) 0 +#define __free_from_contiguous(dev, page, size) do { } while (0) +#define __dma_free_remap(cpu_addr, size) do { } while (0) #endif /* CONFIG_MMU */ -static void * -__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, - pgprot_t prot, const void *caller) +static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp, + struct page **ret_page) +{ + struct page *page; + page = __dma_alloc_buffer(dev, size, gfp); + if (!page) + return NULL; + + *ret_page = page; + return page_address(page); +} + + + +static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, + gfp_t gfp, pgprot_t prot, const void *caller) { + u64 mask = get_coherent_dma_mask(dev); struct page *page; void *addr; +#ifdef CONFIG_DMA_API_DEBUG + u64 limit = (mask + 1) & ~mask; + if (limit && size >= limit) { + dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n", + size, mask); + return NULL; + } +#endif + + if (!mask) + return NULL; + + if (mask < 0xffffffffULL) + gfp |= GFP_DMA; + /* * Following is a work-around (a.k.a. hack) to prevent pages * with __GFP_COMP being passed to split_page() which cannot @@ -463,19 +702,17 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); - page = __dma_alloc_buffer(dev, size, gfp); - if (!page) - return NULL; - - if (!arch_is_coherent()) - addr = __dma_alloc_remap(page, size, gfp, prot, caller); + if (arch_is_coherent() || nommu()) + addr = __alloc_simple_buffer(dev, size, gfp, &page); + else if (cpu_architecture() < CPU_ARCH_ARMv6) + addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller); + else if (gfp & GFP_ATOMIC) + addr = __alloc_from_pool(dev, size, &page, caller); else - addr = page_address(page); + addr = __alloc_from_contiguous(dev, size, prot, &page); if (addr) *handle = pfn_to_dma(dev, page_to_pfn(page)); - else - __dma_free_buffer(page, size); return addr; } @@ -506,54 +743,48 @@ int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, { int ret = -ENXIO; #ifdef CONFIG_MMU - unsigned long user_size, kern_size; - struct arm_vmregion *c; - + unsigned long pfn = dma_to_pfn(dev, dma_addr); vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret)) return ret; - user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; - - 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(pages) + off, - user_size << PAGE_SHIFT, - vma->vm_page_prot); - } - } + ret = remap_pfn_range(vma, vma->vm_start, + pfn + vma->vm_pgoff, + vma->vm_end - vma->vm_start, + vma->vm_page_prot); #endif /* CONFIG_MMU */ return ret; } /* - * free a page as defined by the above mapping. - * Must not be called with IRQs disabled. + * Free a buffer as defined by the above mapping. */ void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs) { - WARN_ON(irqs_disabled()); + struct page *page = pfn_to_page(dma_to_pfn(dev, handle)); if (dma_release_from_coherent(dev, get_order(size), cpu_addr)) return; size = PAGE_ALIGN(size); - if (!arch_is_coherent()) + if (arch_is_coherent() || nommu()) { + __dma_free_buffer(page, size); + } else if (cpu_architecture() < CPU_ARCH_ARMv6) { __dma_free_remap(cpu_addr, size); - - __dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size); + __dma_free_buffer(page, size); + } else { + if (__free_from_pool(cpu_addr, size)) + return; + /* + * Non-atomic allocations cannot be freed with IRQs disabled + */ + WARN_ON(irqs_disabled()); + __free_from_contiguous(dev, page, size); + } } static void dma_cache_maint_page(struct page *page, unsigned long offset, diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 8f5813bbffb..c21d06c7dd7 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -20,6 +20,7 @@ #include <linux/highmem.h> #include <linux/gfp.h> #include <linux/memblock.h> +#include <linux/dma-contiguous.h> #include <asm/mach-types.h> #include <asm/memblock.h> @@ -226,6 +227,17 @@ static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole, } #endif +void __init setup_dma_zone(struct machine_desc *mdesc) +{ +#ifdef CONFIG_ZONE_DMA + if (mdesc->dma_zone_size) { + arm_dma_zone_size = mdesc->dma_zone_size; + arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1; + } else + arm_dma_limit = 0xffffffff; +#endif +} + static void __init arm_bootmem_free(unsigned long min, unsigned long max_low, unsigned long max_high) { @@ -273,12 +285,9 @@ static void __init arm_bootmem_free(unsigned long min, unsigned long max_low, * Adjust the sizes according to any special requirements for * this machine type. */ - if (arm_dma_zone_size) { + if (arm_dma_zone_size) arm_adjust_dma_zone(zone_size, zhole_size, arm_dma_zone_size >> PAGE_SHIFT); - arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1; - } else - arm_dma_limit = 0xffffffff; #endif free_area_init_node(0, zone_size, min, zhole_size); @@ -364,6 +373,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) if (mdesc->reserve) mdesc->reserve(); + /* + * reserve memory for DMA contigouos allocations, + * must come from DMA area inside low memory + */ + dma_contiguous_reserve(min(arm_dma_limit, arm_lowmem_limit)); + arm_memblock_steal_permitted = false; memblock_allow_resize(); memblock_dump_all(); diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 27f4a619b35..93dc0c17cdc 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -67,5 +67,8 @@ extern u32 arm_dma_limit; #define arm_dma_limit ((u32)~0) #endif +extern phys_addr_t arm_lowmem_limit; + void __init bootmem_init(void); void arm_mm_memblock_reserve(void); +void dma_contiguous_remap(void); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index aa78de8bfdd..e5dad60b558 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -288,6 +288,11 @@ static struct mem_type mem_types[] = { PMD_SECT_UNCACHED | PMD_SECT_XN, .domain = DOMAIN_KERNEL, }, + [MT_MEMORY_DMA_READY] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY, + .prot_l1 = PMD_TYPE_TABLE, + .domain = DOMAIN_KERNEL, + }, }; const struct mem_type *get_mem_type(unsigned int type) @@ -429,6 +434,7 @@ static void __init build_mem_type_table(void) if (arch_is_coherent() && cpu_is_xsc3()) { mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; } @@ -460,6 +466,7 @@ static void __init build_mem_type_table(void) mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; } @@ -512,6 +519,7 @@ static void __init build_mem_type_table(void) mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd; mem_types[MT_MEMORY].prot_pte |= kern_pgprot; + mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot; mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask; mem_types[MT_ROM].prot_sect |= cp->pmd; @@ -596,7 +604,7 @@ static void __init alloc_init_section(pud_t *pud, unsigned long addr, * L1 entries, whereas PGDs refer to a group of L1 entries making * up one logical pointer to an L2 table. */ - if (((addr | end | phys) & ~SECTION_MASK) == 0) { + if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0) { pmd_t *p = pmd; #ifndef CONFIG_ARM_LPAE @@ -814,7 +822,7 @@ static int __init early_vmalloc(char *arg) } early_param("vmalloc", early_vmalloc); -static phys_addr_t lowmem_limit __initdata = 0; +phys_addr_t arm_lowmem_limit __initdata = 0; void __init sanity_check_meminfo(void) { @@ -897,8 +905,8 @@ void __init sanity_check_meminfo(void) bank->size = newsize; } #endif - if (!bank->highmem && bank->start + bank->size > lowmem_limit) - lowmem_limit = bank->start + bank->size; + if (!bank->highmem && bank->start + bank->size > arm_lowmem_limit) + arm_lowmem_limit = bank->start + bank->size; j++; } @@ -923,8 +931,8 @@ void __init sanity_check_meminfo(void) } #endif meminfo.nr_banks = j; - high_memory = __va(lowmem_limit - 1) + 1; - memblock_set_current_limit(lowmem_limit); + high_memory = __va(arm_lowmem_limit - 1) + 1; + memblock_set_current_limit(arm_lowmem_limit); } static inline void prepare_page_table(void) @@ -949,8 +957,8 @@ static inline void prepare_page_table(void) * Find the end of the first block of lowmem. */ end = memblock.memory.regions[0].base + memblock.memory.regions[0].size; - if (end >= lowmem_limit) - end = lowmem_limit; + if (end >= arm_lowmem_limit) + end = arm_lowmem_limit; /* * Clear out all the kernel space mappings, except for the first @@ -1093,8 +1101,8 @@ static void __init map_lowmem(void) phys_addr_t end = start + reg->size; struct map_desc map; - if (end > lowmem_limit) - end = lowmem_limit; + if (end > arm_lowmem_limit) + end = arm_lowmem_limit; if (start >= end) break; @@ -1115,11 +1123,12 @@ void __init paging_init(struct machine_desc *mdesc) { void *zero_page; - memblock_set_current_limit(lowmem_limit); + memblock_set_current_limit(arm_lowmem_limit); build_mem_type_table(); prepare_page_table(); map_lowmem(); + dma_contiguous_remap(); devicemaps_init(mdesc); kmap_init(); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c9866b0b77d..7cbdfdac3c7 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -31,6 +31,7 @@ config X86 select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS + select HAVE_DMA_CONTIGUOUS if !SWIOTLB select HAVE_KRETPROBES select HAVE_OPTPROBES select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h new file mode 100644 index 00000000000..c0924165997 --- /dev/null +++ b/arch/x86/include/asm/dma-contiguous.h @@ -0,0 +1,13 @@ +#ifndef ASMX86_DMA_CONTIGUOUS_H +#define ASMX86_DMA_CONTIGUOUS_H + +#ifdef __KERNEL__ + +#include <linux/types.h> +#include <asm-generic/dma-contiguous.h> + +static inline void +dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { } + +#endif +#endif diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 4b4331d7193..7b9227b44b9 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -13,6 +13,7 @@ #include <asm/io.h> #include <asm/swiotlb.h> #include <asm-generic/dma-coherent.h> +#include <linux/dma-contiguous.h> #ifdef CONFIG_ISA # define ISA_DMA_BIT_MASK DMA_BIT_MASK(24) @@ -62,6 +63,10 @@ extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, struct dma_attrs *attrs); +extern void dma_generic_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr, + struct dma_attrs *attrs); + static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) { if (!dev->dma_mask) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 3003250ac51..62c9457ccd2 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -100,14 +100,18 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, struct dma_attrs *attrs) { unsigned long dma_mask; - struct page *page; + struct page *page = NULL; + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; dma_addr_t addr; dma_mask = dma_alloc_coherent_mask(dev, flag); flag |= __GFP_ZERO; again: - page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); + if (!(flag & GFP_ATOMIC)) + page = dma_alloc_from_contiguous(dev, count, get_order(size)); + if (!page) + page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); if (!page) return NULL; @@ -127,6 +131,16 @@ again: return page_address(page); } +void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_addr, struct dma_attrs *attrs) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + struct page *page = virt_to_page(vaddr); + + if (!dma_release_from_contiguous(dev, page, count)) + free_pages((unsigned long)vaddr, get_order(size)); +} + /* * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel * parameter documentation. diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index f96050685b4..871be4a84c7 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -74,12 +74,6 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, return nents; } -static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, struct dma_attrs *attrs) -{ - free_pages((unsigned long)vaddr, get_order(size)); -} - static void nommu_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) @@ -97,7 +91,7 @@ static void nommu_sync_sg_for_device(struct device *dev, struct dma_map_ops nommu_dma_ops = { .alloc = dma_generic_alloc_coherent, - .free = nommu_free_coherent, + .free = dma_generic_free_coherent, .map_sg = nommu_map_sg, .map_page = nommu_map_page, .sync_single_for_device = nommu_sync_single_for_device, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 1a290156205..d6c956e674c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -50,6 +50,7 @@ #include <asm/pci-direct.h> #include <linux/init_ohci1394_dma.h> #include <linux/kvm_para.h> +#include <linux/dma-contiguous.h> #include <linux/errno.h> #include <linux/kernel.h> @@ -934,6 +935,7 @@ void __init setup_arch(char **cmdline_p) } #endif memblock.current_limit = get_max_mapped(); + dma_contiguous_reserve(0); /* * NOTE: On x86-32, only from this point on, fixmaps are ready for use. diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 9aa618acfe9..9b21469482a 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -192,4 +192,93 @@ config DMA_SHARED_BUFFER APIs extension; the file's descriptor can then be passed on to other driver. +config CMA + bool "Contiguous Memory Allocator (EXPERIMENTAL)" + depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK && EXPERIMENTAL + select MIGRATION + help + This enables the Contiguous Memory Allocator which allows drivers + to allocate big physically-contiguous blocks of memory for use with + hardware components that do not support I/O map nor scatter-gather. + + For more information see <include/linux/dma-contiguous.h>. + If unsure, say "n". + +if CMA + +config CMA_DEBUG + bool "CMA debug messages (DEVELOPMENT)" + depends on DEBUG_KERNEL + help + Turns on debug messages in CMA. This produces KERN_DEBUG + messages for every CMA call as well as various messages while + processing calls such as dma_alloc_from_contiguous(). + This option does not affect warning and error messages. + +comment "Default contiguous memory area size:" + +config CMA_SIZE_MBYTES + int "Size in Mega Bytes" + depends on !CMA_SIZE_SEL_PERCENTAGE + default 16 + help + Defines the size (in MiB) of the default memory area for Contiguous + Memory Allocator. + +config CMA_SIZE_PERCENTAGE + int "Percentage of total memory" + depends on !CMA_SIZE_SEL_MBYTES + default 10 + help + Defines the size of the default memory area for Contiguous Memory + Allocator as a percentage of the total memory in the system. + +choice + prompt "Selected region size" + default CMA_SIZE_SEL_ABSOLUTE + +config CMA_SIZE_SEL_MBYTES + bool "Use mega bytes value only" + +config CMA_SIZE_SEL_PERCENTAGE + bool "Use percentage value only" + +config CMA_SIZE_SEL_MIN + bool "Use lower value (minimum)" + +config CMA_SIZE_SEL_MAX + bool "Use higher value (maximum)" + +endchoice + +config CMA_ALIGNMENT + int "Maximum PAGE_SIZE order of alignment for contiguous buffers" + range 4 9 + default 8 + help + DMA mapping framework by default aligns all buffers to the smallest + PAGE_SIZE order which is greater than or equal to the requested buffer + size. This works well for buffers up to a few hundreds kilobytes, but + for larger buffers it just a memory waste. With this parameter you can + specify the maximum PAGE_SIZE order for contiguous buffers. Larger + buffers will be aligned only to this specified order. The order is + expressed as a power of two multiplied by the PAGE_SIZE. + + For example, if your system defaults to 4KiB pages, the order value + of 8 means that the buffers will be aligned up to 1MiB only. + + If unsure, leave the default value "8". + +config CMA_AREAS + int "Maximum count of the CMA device-private areas" + default 7 + help + CMA allows to create CMA areas for particular devices. This parameter + sets the maximum number of such device private CMA areas in the + system. + + If unsure, leave the default value "7". + +endif + endmenu diff --git a/drivers/base/Makefile b/drivers/base/Makefile index b6d1b9c4200..5aa2d703d19 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -6,6 +6,7 @@ obj-y := core.o bus.o dd.o syscore.o \ attribute_container.o transport_class.o \ topology.o obj-$(CONFIG_DEVTMPFS) += devtmpfs.o +obj-$(CONFIG_CMA) += dma-contiguous.o obj-y += power/ obj-$(CONFIG_HAS_DMA) += dma-mapping.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c new file mode 100644 index 00000000000..78efb0306a4 --- /dev/null +++ b/drivers/base/dma-contiguous.c @@ -0,0 +1,401 @@ +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski <m.szyprowski@samsung.com> + * Michal Nazarewicz <mina86@mina86.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + */ + +#define pr_fmt(fmt) "cma: " fmt + +#ifdef CONFIG_CMA_DEBUG +#ifndef DEBUG +# define DEBUG +#endif +#endif + +#include <asm/page.h> +#include <asm/dma-contiguous.h> + +#include <linux/memblock.h> +#include <linux/err.h> +#include <linux/mm.h> +#include <linux/mutex.h> +#include <linux/page-isolation.h> +#include <linux/slab.h> +#include <linux/swap.h> +#include <linux/mm_types.h> +#include <linux/dma-contiguous.h> + +#ifndef SZ_1M +#define SZ_1M (1 << 20) +#endif + +struct cma { + unsigned long base_pfn; + unsigned long count; + unsigned long *bitmap; +}; + +struct cma *dma_contiguous_default_area; + +#ifdef CONFIG_CMA_SIZE_MBYTES +#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES +#else +#define CMA_SIZE_MBYTES 0 +#endif + +/* + * Default global CMA area size can be defined in kernel's .config. + * This is usefull mainly for distro maintainers to create a kernel + * that works correctly for most supported systems. + * The size can be set in bytes or as a percentage of the total memory + * in the system. + * + * Users, who want to set the size of global CMA area for their system + * should use cma= kernel parameter. + */ +static const unsigned long size_bytes = CMA_SIZE_MBYTES * SZ_1M; +static long size_cmdline = -1; + +static int __init early_cma(char *p) +{ + pr_debug("%s(%s)\n", __func__, p); + size_cmdline = memparse(p, &p); + return 0; +} +early_param("cma", early_cma); + +#ifdef CONFIG_CMA_SIZE_PERCENTAGE + +static unsigned long __init __maybe_unused cma_early_percent_memory(void) +{ + struct memblock_region *reg; + unsigned long total_pages = 0; + + /* + * We cannot use memblock_phys_mem_size() here, because + * memblock_analyze() has not been called yet. + */ + for_each_memblock(memory, reg) + total_pages += memblock_region_memory_end_pfn(reg) - + memblock_region_memory_base_pfn(reg); + + return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT; +} + +#else + +static inline __maybe_unused unsigned long cma_early_percent_memory(void) +{ + return 0; +} + +#endif + +/** + * dma_contiguous_reserve() - reserve area for contiguous memory handling + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This function reserves memory from early allocator. It should be + * called by arch specific code once the early allocator (memblock or bootmem) + * has been activated and all other subsystems have already allocated/reserved + * memory. + */ +void __init dma_contiguous_reserve(phys_addr_t limit) +{ + unsigned long selected_size = 0; + + pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit); + + if (size_cmdline != -1) { + selected_size = size_cmdline; + } else { +#ifdef CONFIG_CMA_SIZE_SEL_MBYTES + selected_size = size_bytes; +#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE) + selected_size = cma_early_percent_memory(); +#elif defined(CONFIG_CMA_SIZE_SEL_MIN) + selected_size = min(size_bytes, cma_early_percent_memory()); +#elif defined(CONFIG_CMA_SIZE_SEL_MAX) + selected_size = max(size_bytes, cma_early_percent_memory()); +#endif + } + + if (selected_size) { + pr_debug("%s: reserving %ld MiB for global area\n", __func__, + selected_size / SZ_1M); + + dma_declare_contiguous(NULL, selected_size, 0, limit); + } +}; + +static DEFINE_MUTEX(cma_mutex); + +static __init int cma_activate_area(unsigned long base_pfn, unsigned long count) +{ + unsigned long pfn = base_pfn; + unsigned i = count >> pageblock_order; + struct zone *zone; + + WARN_ON_ONCE(!pfn_valid(pfn)); + zone = page_zone(pfn_to_page(pfn)); + + do { + unsigned j; + base_pfn = pfn; + for (j = pageblock_nr_pages; j; --j, pfn++) { + WARN_ON_ONCE(!pfn_valid(pfn)); + if (page_zone(pfn_to_page(pfn)) != zone) + return -EINVAL; + } + init_cma_reserved_pageblock(pfn_to_page(base_pfn)); + } while (--i); + return 0; +} + +static __init struct cma *cma_create_area(unsigned long base_pfn, + unsigned long count) +{ + int bitmap_size = BITS_TO_LONGS(count) * sizeof(long); + struct cma *cma; + int ret = -ENOMEM; + + pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count); + + cma = kmalloc(sizeof *cma, GFP_KERNEL); + if (!cma) + return ERR_PTR(-ENOMEM); + + cma->base_pfn = base_pfn; + cma->count = count; + cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + + if (!cma->bitmap) + goto no_mem; + + ret = cma_activate_area(base_pfn, count); + if (ret) + goto error; + + pr_debug("%s: returned %p\n", __func__, (void *)cma); + return cma; + +error: + kfree(cma->bitmap); +no_mem: + kfree(cma); + return ERR_PTR(ret); +} + +static struct cma_reserved { + phys_addr_t start; + unsigned long size; + struct device *dev; +} cma_reserved[MAX_CMA_AREAS] __initdata; +static unsigned cma_reserved_count __initdata; + +static int __init cma_init_reserved_areas(void) +{ + struct cma_reserved *r = cma_reserved; + unsigned i = cma_reserved_count; + + pr_debug("%s()\n", __func__); + + for (; i; --i, ++r) { + struct cma *cma; + cma = cma_create_area(PFN_DOWN(r->start), + r->size >> PAGE_SHIFT); + if (!IS_ERR(cma)) + dev_set_cma_area(r->dev, cma); + } + return 0; +} +core_initcall(cma_init_reserved_areas); + +/** + * dma_declare_contiguous() - reserve area for contiguous memory handling + * for particular device + * @dev: Pointer to device structure. + * @size: Size of the reserved memory. + * @base: Start address of the reserved memory (optional, 0 for any). + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This function reserves memory for specified device. It should be + * called by board specific code when early allocator (memblock or bootmem) + * is still activate. + */ +int __init dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit) +{ + struct cma_reserved *r = &cma_reserved[cma_reserved_count]; + unsigned long alignment; + + pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__, + (unsigned long)size, (unsigned long)base, + (unsigned long)limit); + + /* Sanity checks */ + if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) { + pr_err("Not enough slots for CMA reserved regions!\n"); + return -ENOSPC; + } + + if (!size) + return -EINVAL; + + /* Sanitise input arguments */ + alignment = PAGE_SIZE << max(MAX_ORDER, pageblock_order); + base = ALIGN(base, alignment); + size = ALIGN(size, alignment); + limit &= ~(alignment - 1); + + /* Reserve memory */ + if (base) { + if (memblock_is_region_reserved(base, size) || + memblock_reserve(base, size) < 0) { + base = -EBUSY; + goto err; + } + } else { + /* + * Use __memblock_alloc_base() since + * memblock_alloc_base() panic()s. + */ + phys_addr_t addr = __memblock_alloc_base(size, alignment, limit); + if (!addr) { + base = -ENOMEM; + goto err; + } else if (addr + size > ~(unsigned long)0) { + memblock_free(addr, size); + base = -EINVAL; + goto err; + } else { + base = addr; + } + } + + /* + * Each reserved area must be initialised later, when more kernel + * subsystems (like slab allocator) are available. + */ + r->start = base; + r->size = size; + r->dev = dev; + cma_reserved_count++; + pr_info("CMA: reserved %ld MiB at %08lx\n", size / SZ_1M, + (unsigned long)base); + + /* Architecture specific contiguous memory fixup. */ + dma_contiguous_early_fixup(base, size); + return 0; +err: + pr_err("CMA: failed to reserve %ld MiB\n", size / SZ_1M); + return base; +} + +/** + * dma_alloc_from_contiguous() - allocate pages from contiguous area + * @dev: Pointer to device for which the allocation is performed. + * @count: Requested number of pages. + * @align: Requested alignment of pages (in PAGE_SIZE order). + * + * This function allocates memory buffer for specified device. It uses + * device specific contiguous memory area if available or the default + * global one. Requires architecture specific get_dev_cma_area() helper + * function. + */ +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int align) +{ + unsigned long mask, pfn, pageno, start = 0; + struct cma *cma = dev_get_cma_area(dev); + int ret; + + if (!cma || !cma->count) + return NULL; + + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma, + count, align); + + if (!count) + return NULL; + + mask = (1 << align) - 1; + + mutex_lock(&cma_mutex); + + for (;;) { + pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count, + start, count, mask); + if (pageno >= cma->count) { + ret = -ENOMEM; + goto error; + } + + pfn = cma->base_pfn + pageno; + ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA); + if (ret == 0) { + bitmap_set(cma->bitmap, pageno, count); + break; + } else if (ret != -EBUSY) { + goto error; + } + pr_debug("%s(): memory range at %p is busy, retrying\n", + __func__, pfn_to_page(pfn)); + /* try again with a bit different memory target */ + start = pageno + mask + 1; + } + + mutex_unlock(&cma_mutex); + + pr_debug("%s(): returned %p\n", __func__, pfn_to_page(pfn)); + return pfn_to_page(pfn); +error: + mutex_unlock(&cma_mutex); + return NULL; +} + +/** + * dma_release_from_contiguous() - release allocated pages + * @dev: Pointer to device for which the pages were allocated. + * @pages: Allocated pages. + * @count: Number of allocated pages. + * + * This function releases memory allocated by dma_alloc_from_contiguous(). + * It returns false when provided pages do not belong to contiguous area and + * true otherwise. + */ +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + struct cma *cma = dev_get_cma_area(dev); + unsigned long pfn; + + if (!cma || !pages) + return false; + + pr_debug("%s(page %p)\n", __func__, (void *)pages); + + pfn = page_to_pfn(pages); + + if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) + return false; + + VM_BUG_ON(pfn + count > cma->base_pfn + cma->count); + + mutex_lock(&cma_mutex); + bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count); + free_contig_range(pfn, count); + mutex_unlock(&cma_mutex); + + return true; +} diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h new file mode 100644 index 00000000000..c544356b374 --- /dev/null +++ b/include/asm-generic/dma-contiguous.h @@ -0,0 +1,28 @@ +#ifndef ASM_DMA_CONTIGUOUS_H +#define ASM_DMA_CONTIGUOUS_H + +#ifdef __KERNEL__ +#ifdef CONFIG_CMA + +#include <linux/device.h> +#include <linux/dma-contiguous.h> + +static inline struct cma *dev_get_cma_area(struct device *dev) +{ + if (dev && dev->cma_area) + return dev->cma_area; + return dma_contiguous_default_area; +} + +static inline void dev_set_cma_area(struct device *dev, struct cma *cma) +{ + if (dev) + dev->cma_area = cma; + if (!dev || !dma_contiguous_default_area) + dma_contiguous_default_area = cma; +} + +#endif +#endif + +#endif diff --git a/include/linux/device.h b/include/linux/device.h index 5ad17cccdd7..e3399290436 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -661,6 +661,10 @@ struct device { struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ +#ifdef CONFIG_CMA + struct cma *cma_area; /* contiguous memory area for dma + allocations */ +#endif /* arch specific additions */ struct dev_archdata archdata; diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h new file mode 100644 index 00000000000..2f303e4b7ed --- /dev/null +++ b/include/linux/dma-contiguous.h @@ -0,0 +1,110 @@ +#ifndef __LINUX_CMA_H +#define __LINUX_CMA_H + +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski <m.szyprowski@samsung.com> + * Michal Nazarewicz <mina86@mina86.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + */ + +/* + * Contiguous Memory Allocator + * + * The Contiguous Memory Allocator (CMA) makes it possible to + * allocate big contiguous chunks of memory after the system has + * booted. + * + * Why is it needed? + * + * Various devices on embedded systems have no scatter-getter and/or + * IO map support and require contiguous blocks of memory to + * operate. They include devices such as cameras, hardware video + * coders, etc. + * + * Such devices often require big memory buffers (a full HD frame + * is, for instance, more then 2 mega pixels large, i.e. more than 6 + * MB of memory), which makes mechanisms such as kmalloc() or + * alloc_page() ineffective. + * + * At the same time, a solution where a big memory region is + * reserved for a device is suboptimal since often more memory is + * reserved then strictly required and, moreover, the memory is + * inaccessible to page system even if device drivers don't use it. + * + * CMA tries to solve this issue by operating on memory regions + * where only movable pages can be allocated from. This way, kernel + * can use the memory for pagecache and when device driver requests + * it, allocated pages can be migrated. + * + * Driver usage + * + * CMA should not be used by the device drivers directly. It is + * only a helper framework for dma-mapping subsystem. + * + * For more information, see kernel-docs in drivers/base/dma-contiguous.c + */ + +#ifdef __KERNEL__ + +struct cma; +struct page; +struct device; + +#ifdef CONFIG_CMA + +/* + * There is always at least global CMA area and a few optional device + * private areas configured in kernel .config. + */ +#define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) + +extern struct cma *dma_contiguous_default_area; + +void dma_contiguous_reserve(phys_addr_t addr_limit); +int dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit); + +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int order); +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count); + +#else + +#define MAX_CMA_AREAS (0) + +static inline void dma_contiguous_reserve(phys_addr_t limit) { } + +static inline +int dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit) +{ + return -ENOSYS; +} + +static inline +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int order) +{ + return NULL; +} + +static inline +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + return false; +} + +#endif + +#endif + +#endif diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 581e74b7df9..1e49be49d32 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -391,4 +391,16 @@ static inline bool pm_suspended_storage(void) } #endif /* CONFIG_PM_SLEEP */ +#ifdef CONFIG_CMA + +/* The below functions must be run on a range from a single zone. */ +extern int alloc_contig_range(unsigned long start, unsigned long end, + unsigned migratetype); +extern void free_contig_range(unsigned long pfn, unsigned nr_pages); + +/* CMA stuff */ +extern void init_cma_reserved_pageblock(struct page *page); + +#endif + #endif /* __LINUX_GFP_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index dff71150966..26f2040b8b0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -35,13 +35,39 @@ */ #define PAGE_ALLOC_COSTLY_ORDER 3 -#define MIGRATE_UNMOVABLE 0 -#define MIGRATE_RECLAIMABLE 1 -#define MIGRATE_MOVABLE 2 -#define MIGRATE_PCPTYPES 3 /* the number of types on the pcp lists */ -#define MIGRATE_RESERVE 3 -#define MIGRATE_ISOLATE 4 /* can't allocate from here */ -#define MIGRATE_TYPES 5 +enum { + MIGRATE_UNMOVABLE, + MIGRATE_RECLAIMABLE, + MIGRATE_MOVABLE, + MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ + MIGRATE_RESERVE = MIGRATE_PCPTYPES, +#ifdef CONFIG_CMA + /* + * MIGRATE_CMA migration type is designed to mimic the way + * ZONE_MOVABLE works. Only movable pages can be allocated + * from MIGRATE_CMA pageblocks and page allocator never + * implicitly change migration type of MIGRATE_CMA pageblock. + * + * The way to use it is to change migratetype of a range of + * pageblocks to MIGRATE_CMA which can be done by + * __free_pageblock_cma() function. What is important though + * is that a range of pageblocks must be aligned to + * MAX_ORDER_NR_PAGES should biggest page be bigger then + * a single pageblock. + */ + MIGRATE_CMA, +#endif + MIGRATE_ISOLATE, /* can't allocate from here */ + MIGRATE_TYPES +}; + +#ifdef CONFIG_CMA +# define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) +# define cma_wmark_pages(zone) zone->min_cma_pages +#else +# define is_migrate_cma(migratetype) false +# define cma_wmark_pages(zone) 0 +#endif #define for_each_migratetype_order(order, type) \ for (order = 0; order < MAX_ORDER; order++) \ @@ -347,6 +373,13 @@ struct zone { /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif +#ifdef CONFIG_CMA + /* + * CMA needs to increase watermark levels during the allocation + * process to make sure that the system is not starved. + */ + unsigned long min_cma_pages; +#endif struct free_area free_area[MAX_ORDER]; #ifndef CONFIG_SPARSEMEM diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 051c1b1ede4..3bdcab30ca4 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -3,7 +3,7 @@ /* * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE. - * If specified range includes migrate types other than MOVABLE, + * If specified range includes migrate types other than MOVABLE or CMA, * this will fail with -EBUSY. * * For isolating all pages in the range finally, the caller have to @@ -11,27 +11,27 @@ * test it. */ extern int -start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn); +start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype); /* * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE. * target range is [start_pfn, end_pfn) */ extern int -undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn); +undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype); /* - * test all pages in [start_pfn, end_pfn)are isolated or not. + * Test all pages in [start_pfn, end_pfn) are isolated or not. */ -extern int -test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn); +int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn); /* - * Internal funcs.Changes pageblock's migrate type. - * Please use make_pagetype_isolated()/make_pagetype_movable(). + * Internal functions. Changes pageblock's migrate type. */ extern int set_migratetype_isolate(struct page *page); -extern void unset_migratetype_isolate(struct page *page); +extern void unset_migratetype_isolate(struct page *page, unsigned migratetype); #endif diff --git a/mm/Kconfig b/mm/Kconfig index e338407f122..39220026c79 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -198,7 +198,7 @@ config COMPACTION config MIGRATION bool "Page migration" def_bool y - depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION + depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA help Allows the migration of the physical location of pages of processes while the virtual addresses are not changed. This is useful in diff --git a/mm/Makefile b/mm/Makefile index 50ec00ef2a0..8aada89efbb 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -13,7 +13,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ page_isolation.o mm_init.o mmu_context.o percpu.o \ - $(mmu-y) + compaction.o $(mmu-y) obj-y += init-mm.o ifdef CONFIG_NO_BOOTMEM @@ -32,7 +32,6 @@ obj-$(CONFIG_NUMA) += mempolicy.o obj-$(CONFIG_SPARSEMEM) += sparse.o obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o obj-$(CONFIG_SLOB) += slob.o -obj-$(CONFIG_COMPACTION) += compaction.o obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o obj-$(CONFIG_KSM) += ksm.o obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o diff --git a/mm/compaction.c b/mm/compaction.c index 74a8c825ff2..da7d35ea510 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -16,30 +16,11 @@ #include <linux/sysfs.h> #include "internal.h" +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + #define CREATE_TRACE_POINTS #include <trace/events/compaction.h> -/* - * compact_control is used to track pages being migrated and the free pages - * they are being migrated to during memory compaction. The free_pfn starts - * at the end of a zone and migrate_pfn begins at the start. Movable pages - * are moved to the end of a zone during a compaction run and the run - * completes when free_pfn <= migrate_pfn - */ -struct compact_control { - struct list_head freepages; /* List of free pages to migrate to */ - struct list_head migratepages; /* List of pages being migrated */ - unsigned long nr_freepages; /* Number of isolated free pages */ - unsigned long nr_migratepages; /* Number of pages to migrate */ - unsigned long free_pfn; /* isolate_freepages search base */ - unsigned long migrate_pfn; /* isolate_migratepages search base */ - bool sync; /* Synchronous migration */ - - int order; /* order a direct compactor needs */ - int migratetype; /* MOVABLE, RECLAIMABLE etc */ - struct zone *zone; -}; - static unsigned long release_freepages(struct list_head *freelist) { struct page *page, *next; @@ -54,24 +35,35 @@ static unsigned long release_freepages(struct list_head *freelist) return count; } -/* Isolate free pages onto a private freelist. Must hold zone->lock */ -static unsigned long isolate_freepages_block(struct zone *zone, - unsigned long blockpfn, - struct list_head *freelist) +static void map_pages(struct list_head *list) +{ + struct page *page; + + list_for_each_entry(page, list, lru) { + arch_alloc_page(page, 0); + kernel_map_pages(page, 1, 1); + } +} + +static inline bool migrate_async_suitable(int migratetype) +{ + return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE; +} + +/* + * Isolate free pages onto a private freelist. Caller must hold zone->lock. + * If @strict is true, will abort returning 0 on any invalid PFNs or non-free + * pages inside of the pageblock (even though it may still end up isolating + * some pages). + */ +static unsigned long isolate_freepages_block(unsigned long blockpfn, + unsigned long end_pfn, + struct list_head *freelist, + bool strict) { - unsigned long zone_end_pfn, end_pfn; int nr_scanned = 0, total_isolated = 0; struct page *cursor; - /* Get the last PFN we should scan for free pages at */ - zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; - end_pfn = min(blockpfn + pageblock_nr_pages, zone_end_pfn); - - /* Find the first usable PFN in the block to initialse page cursor */ - for (; blockpfn < end_pfn; blockpfn++) { - if (pfn_valid_within(blockpfn)) - break; - } cursor = pfn_to_page(blockpfn); /* Isolate free pages. This assumes the block is valid */ @@ -79,15 +71,23 @@ static unsigned long isolate_freepages_block(struct zone *zone, int isolated, i; struct page *page = cursor; - if (!pfn_valid_within(blockpfn)) + if (!pfn_valid_within(blockpfn)) { + if (strict) + return 0; continue; + } nr_scanned++; - if (!PageBuddy(page)) + if (!PageBuddy(page)) { + if (strict) + return 0; continue; + } /* Found a free page, break it into order-0 pages */ isolated = split_free_page(page); + if (!isolated && strict) + return 0; total_isolated += isolated; for (i = 0; i < isolated; i++) { list_add(&page->lru, freelist); @@ -105,114 +105,71 @@ static unsigned long isolate_freepages_block(struct zone *zone, return total_isolated; } -/* Returns true if the page is within a block suitable for migration to */ -static bool suitable_migration_target(struct page *page) -{ - - int migratetype = get_pageblock_migratetype(page); - - /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ - if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE) - return false; - - /* If the page is a large free page, then allow migration */ - if (PageBuddy(page) && page_order(page) >= pageblock_order) - return true; - - /* If the block is MIGRATE_MOVABLE, allow migration */ - if (migratetype == MIGRATE_MOVABLE) - return true; - - /* Otherwise skip the block */ - return false; -} - -/* - * Based on information in the current compact_control, find blocks - * suitable for isolating free pages from and then isolate them. +/** + * isolate_freepages_range() - isolate free pages. + * @start_pfn: The first PFN to start isolating. + * @end_pfn: The one-past-last PFN. + * + * Non-free pages, invalid PFNs, or zone boundaries within the + * [start_pfn, end_pfn) range are considered errors, cause function to + * undo its actions and return zero. + * + * Otherwise, function returns one-past-the-last PFN of isolated page + * (which may be greater then end_pfn if end fell in a middle of + * a free page). */ -static void isolate_freepages(struct zone *zone, - struct compact_control *cc) +unsigned long +isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn) { - struct page *page; - unsigned long high_pfn, low_pfn, pfn; - unsigned long flags; - int nr_freepages = cc->nr_freepages; - struct list_head *freelist = &cc->freepages; - - /* - * Initialise the free scanner. The starting point is where we last - * scanned from (or the end of the zone if starting). The low point - * is the end of the pageblock the migration scanner is using. - */ - pfn = cc->free_pfn; - low_pfn = cc->migrate_pfn + pageblock_nr_pages; + unsigned long isolated, pfn, block_end_pfn, flags; + struct zone *zone = NULL; + LIST_HEAD(freelist); - /* - * Take care that if the migration scanner is at the end of the zone - * that the free scanner does not accidentally move to the next zone - * in the next isolation cycle. - */ - high_pfn = min(low_pfn, pfn); - - /* - * Isolate free pages until enough are available to migrate the - * pages on cc->migratepages. We stop searching if the migrate - * and free page scanners meet or enough free pages are isolated. - */ - for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; - pfn -= pageblock_nr_pages) { - unsigned long isolated; + if (pfn_valid(start_pfn)) + zone = page_zone(pfn_to_page(start_pfn)); - if (!pfn_valid(pfn)) - continue; + for (pfn = start_pfn; pfn < end_pfn; pfn += isolated) { + if (!pfn_valid(pfn) || zone != page_zone(pfn_to_page(pfn))) + break; /* - * Check for overlapping nodes/zones. It's possible on some - * configurations to have a setup like - * node0 node1 node0 - * i.e. it's possible that all pages within a zones range of - * pages do not belong to a single zone. + * On subsequent iterations ALIGN() is actually not needed, + * but we keep it that we not to complicate the code. */ - page = pfn_to_page(pfn); - if (page_zone(page) != zone) - continue; + block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); + block_end_pfn = min(block_end_pfn, end_pfn); - /* Check the block is suitable for migration */ - if (!suitable_migration_target(page)) - continue; + spin_lock_irqsave(&zone->lock, flags); + isolated = isolate_freepages_block(pfn, block_end_pfn, + &freelist, true); + spin_unlock_irqrestore(&zone->lock, flags); /* - * Found a block suitable for isolating free pages from. Now - * we disabled interrupts, double check things are ok and - * isolate the pages. This is to minimise the time IRQs - * are disabled + * In strict mode, isolate_freepages_block() returns 0 if + * there are any holes in the block (ie. invalid PFNs or + * non-free pages). */ - isolated = 0; - spin_lock_irqsave(&zone->lock, flags); - if (suitable_migration_target(page)) { - isolated = isolate_freepages_block(zone, pfn, freelist); - nr_freepages += isolated; - } - spin_unlock_irqrestore(&zone->lock, flags); + if (!isolated) + break; /* - * Record the highest PFN we isolated pages from. When next - * looking for free pages, the search will restart here as - * page migration may have returned some pages to the allocator + * If we managed to isolate pages, it is always (1 << n) * + * pageblock_nr_pages for some non-negative n. (Max order + * page may span two pageblocks). */ - if (isolated) - high_pfn = max(high_pfn, pfn); } /* split_free_page does not map the pages */ - list_for_each_entry(page, freelist, lru) { - arch_alloc_page(page, 0); - kernel_map_pages(page, 1, 1); + map_pages(&freelist); + + if (pfn < end_pfn) { + /* Loop terminated early, cleanup. */ + release_freepages(&freelist); + return 0; } - cc->free_pfn = high_pfn; - cc->nr_freepages = nr_freepages; + /* We don't use freelists for anything. */ + return pfn; } /* Update the number of anon and file isolated pages in the zone */ @@ -243,38 +200,34 @@ static bool too_many_isolated(struct zone *zone) return isolated > (inactive + active) / 2; } -/* possible outcome of isolate_migratepages */ -typedef enum { - ISOLATE_ABORT, /* Abort compaction now */ - ISOLATE_NONE, /* No pages isolated, continue scanning */ - ISOLATE_SUCCESS, /* Pages isolated, migrate */ -} isolate_migrate_t; - -/* - * Isolate all pages that can be migrated from the block pointed to by - * the migrate scanner within compact_control. +/** + * isolate_migratepages_range() - isolate all migrate-able pages in range. + * @zone: Zone pages are in. + * @cc: Compaction control structure. + * @low_pfn: The first PFN of the range. + * @end_pfn: The one-past-the-last PFN of the range. + * + * Isolate all pages that can be migrated from the range specified by + * [low_pfn, end_pfn). Returns zero if there is a fatal signal + * pending), otherwise PFN of the first page that was not scanned + * (which may be both less, equal to or more then end_pfn). + * + * Assumes that cc->migratepages is empty and cc->nr_migratepages is + * zero. + * + * Apart from cc->migratepages and cc->nr_migratetypes this function + * does not modify any cc's fields, in particular it does not modify + * (or read for that matter) cc->migrate_pfn. */ -static isolate_migrate_t isolate_migratepages(struct zone *zone, - struct compact_control *cc) +unsigned long +isolate_migratepages_range(struct zone *zone, struct compact_control *cc, + unsigned long low_pfn, unsigned long end_pfn) { - unsigned long low_pfn, end_pfn; unsigned long last_pageblock_nr = 0, pageblock_nr; unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE; - /* Do not scan outside zone boundaries */ - low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); - - /* Only scan within a pageblock boundary */ - end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages); - - /* Do not cross the free scanner or scan within a memory hole */ - if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) { - cc->migrate_pfn = end_pfn; - return ISOLATE_NONE; - } - /* * Ensure that there are not too many pages isolated from the LRU * list by either parallel reclaimers or compaction. If there are, @@ -283,12 +236,12 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, while (unlikely(too_many_isolated(zone))) { /* async migration should just abort */ if (!cc->sync) - return ISOLATE_ABORT; + return 0; congestion_wait(BLK_RW_ASYNC, HZ/10); if (fatal_signal_pending(current)) - return ISOLATE_ABORT; + return 0; } /* Time to isolate some pages for migration */ @@ -351,7 +304,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, */ pageblock_nr = low_pfn >> pageblock_order; if (!cc->sync && last_pageblock_nr != pageblock_nr && - get_pageblock_migratetype(page) != MIGRATE_MOVABLE) { + !migrate_async_suitable(get_pageblock_migratetype(page))) { low_pfn += pageblock_nr_pages; low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1; last_pageblock_nr = pageblock_nr; @@ -396,11 +349,124 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, acct_isolated(zone, cc); spin_unlock_irq(&zone->lru_lock); - cc->migrate_pfn = low_pfn; trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); - return ISOLATE_SUCCESS; + return low_pfn; +} + +#endif /* CONFIG_COMPACTION || CONFIG_CMA */ +#ifdef CONFIG_COMPACTION + +/* Returns true if the page is within a block suitable for migration to */ +static bool suitable_migration_target(struct page *page) +{ + + int migratetype = get_pageblock_migratetype(page); + + /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ + if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE) + return false; + + /* If the page is a large free page, then allow migration */ + if (PageBuddy(page) && page_order(page) >= pageblock_order) + return true; + + /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ + if (migrate_async_suitable(migratetype)) + return true; + + /* Otherwise skip the block */ + return false; +} + +/* + * Based on information in the current compact_control, find blocks + * suitable for isolating free pages from and then isolate them. + */ +static void isolate_freepages(struct zone *zone, + struct compact_control *cc) +{ + struct page *page; + unsigned long high_pfn, low_pfn, pfn, zone_end_pfn, end_pfn; + unsigned long flags; + int nr_freepages = cc->nr_freepages; + struct list_head *freelist = &cc->freepages; + + /* + * Initialise the free scanner. The starting point is where we last + * scanned from (or the end of the zone if starting). The low point + * is the end of the pageblock the migration scanner is using. + */ + pfn = cc->free_pfn; + low_pfn = cc->migrate_pfn + pageblock_nr_pages; + + /* + * Take care that if the migration scanner is at the end of the zone + * that the free scanner does not accidentally move to the next zone + * in the next isolation cycle. + */ + high_pfn = min(low_pfn, pfn); + + zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; + + /* + * Isolate free pages until enough are available to migrate the + * pages on cc->migratepages. We stop searching if the migrate + * and free page scanners meet or enough free pages are isolated. + */ + for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; + pfn -= pageblock_nr_pages) { + unsigned long isolated; + + if (!pfn_valid(pfn)) + continue; + + /* + * Check for overlapping nodes/zones. It's possible on some + * configurations to have a setup like + * node0 node1 node0 + * i.e. it's possible that all pages within a zones range of + * pages do not belong to a single zone. + */ + page = pfn_to_page(pfn); + if (page_zone(page) != zone) + continue; + + /* Check the block is suitable for migration */ + if (!suitable_migration_target(page)) + continue; + + /* + * Found a block suitable for isolating free pages from. Now + * we disabled interrupts, double check things are ok and + * isolate the pages. This is to minimise the time IRQs + * are disabled + */ + isolated = 0; + spin_lock_irqsave(&zone->lock, flags); + if (suitable_migration_target(page)) { + end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn); + isolated = isolate_freepages_block(pfn, end_pfn, + freelist, false); + nr_freepages += isolated; + } + spin_unlock_irqrestore(&zone->lock, flags); + + /* + * Record the highest PFN we isolated pages from. When next + * looking for free pages, the search will restart here as + * page migration may have returned some pages to the allocator + */ + if (isolated) + high_pfn = max(high_pfn, pfn); + } + + /* split_free_page does not map the pages */ + map_pages(freelist); + + cc->free_pfn = high_pfn; + cc->nr_freepages = nr_freepages; } /* @@ -449,6 +515,44 @@ static void update_nr_listpages(struct compact_control *cc) cc->nr_freepages = nr_freepages; } +/* possible outcome of isolate_migratepages */ +typedef enum { + ISOLATE_ABORT, /* Abort compaction now */ + ISOLATE_NONE, /* No pages isolated, continue scanning */ + ISOLATE_SUCCESS, /* Pages isolated, migrate */ +} isolate_migrate_t; + +/* + * Isolate all pages that can be migrated from the block pointed to by + * the migrate scanner within compact_control. + */ +static isolate_migrate_t isolate_migratepages(struct zone *zone, + struct compact_control *cc) +{ + unsigned long low_pfn, end_pfn; + + /* Do not scan outside zone boundaries */ + low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); + + /* Only scan within a pageblock boundary */ + end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages); + + /* Do not cross the free scanner or scan within a memory hole */ + if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) { + cc->migrate_pfn = end_pfn; + return ISOLATE_NONE; + } + + /* Perform the isolation */ + low_pfn = isolate_migratepages_range(zone, cc, low_pfn, end_pfn); + if (!low_pfn) + return ISOLATE_ABORT; + + cc->migrate_pfn = low_pfn; + + return ISOLATE_SUCCESS; +} + static int compact_finished(struct zone *zone, struct compact_control *cc) { @@ -795,3 +899,5 @@ void compaction_unregister_node(struct node *node) return device_remove_file(&node->dev, &dev_attr_compact); } #endif /* CONFIG_SYSFS && CONFIG_NUMA */ + +#endif /* CONFIG_COMPACTION */ diff --git a/mm/internal.h b/mm/internal.h index 2189af49178..aee4761cf9a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -100,6 +100,39 @@ extern void prep_compound_page(struct page *page, unsigned long order); extern bool is_free_buddy_page(struct page *page); #endif +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + +/* + * in mm/compaction.c + */ +/* + * compact_control is used to track pages being migrated and the free pages + * they are being migrated to during memory compaction. The free_pfn starts + * at the end of a zone and migrate_pfn begins at the start. Movable pages + * are moved to the end of a zone during a compaction run and the run + * completes when free_pfn <= migrate_pfn + */ +struct compact_control { + struct list_head freepages; /* List of free pages to migrate to */ + struct list_head migratepages; /* List of pages being migrated */ + unsigned long nr_freepages; /* Number of isolated free pages */ + unsigned long nr_migratepages; /* Number of pages to migrate */ + unsigned long free_pfn; /* isolate_freepages search base */ + unsigned long migrate_pfn; /* isolate_migratepages search base */ + bool sync; /* Synchronous migration */ + + int order; /* order a direct compactor needs */ + int migratetype; /* MOVABLE, RECLAIMABLE etc */ + struct zone *zone; +}; + +unsigned long +isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn); +unsigned long +isolate_migratepages_range(struct zone *zone, struct compact_control *cc, + unsigned long low_pfn, unsigned long end_pfn); + +#endif /* * function for dealing with page's order in buddy system. diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 97cc2733551..c99ad4e6b88 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1404,7 +1404,7 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags) /* Not a free page */ ret = 1; } - unset_migratetype_isolate(p); + unset_migratetype_isolate(p, MIGRATE_MOVABLE); unlock_memory_hotplug(); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 6629fafd6ce..fc898cb4fe8 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -891,7 +891,7 @@ static int __ref offline_pages(unsigned long start_pfn, nr_pages = end_pfn - start_pfn; /* set above range as isolated */ - ret = start_isolate_page_range(start_pfn, end_pfn); + ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); if (ret) goto out; @@ -956,7 +956,7 @@ repeat: We cannot do rollback at this point. */ offline_isolated_pages(start_pfn, end_pfn); /* reset pagetype flags and makes migrate type to be MOVABLE */ - undo_isolate_page_range(start_pfn, end_pfn); + undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); /* removal success */ zone->present_pages -= offlined_pages; zone->zone_pgdat->node_present_pages -= offlined_pages; @@ -981,7 +981,7 @@ failed_removal: start_pfn, end_pfn); memory_notify(MEM_CANCEL_OFFLINE, &arg); /* pushback to free area */ - undo_isolate_page_range(start_pfn, end_pfn); + undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); out: unlock_memory_hotplug(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 918330f71db..ed85c02c1f6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -57,6 +57,7 @@ #include <linux/ftrace_event.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> +#include <linux/migrate.h> #include <linux/page-debug-flags.h> #include <asm/tlbflush.h> @@ -513,10 +514,10 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, * free pages of length of (1 << order) and marked with _mapcount -2. Page's * order is recorded in page_private(page) field. * So when we are allocating or freeing one, we can derive the state of the - * other. That is, if we allocate a small block, and both were - * free, the remainder of the region must be split into blocks. + * other. That is, if we allocate a small block, and both were + * free, the remainder of the region must be split into blocks. * If a block is freed, and its buddy is also free, then this - * triggers coalescing into a block of larger size. + * triggers coalescing into a block of larger size. * * -- wli */ @@ -749,6 +750,24 @@ void __meminit __free_pages_bootmem(struct page *page, unsigned int order) __free_pages(page, order); } +#ifdef CONFIG_CMA +/* Free whole pageblock and set it's migration type to MIGRATE_CMA. */ +void __init init_cma_reserved_pageblock(struct page *page) +{ + unsigned i = pageblock_nr_pages; + struct page *p = page; + + do { + __ClearPageReserved(p); + set_page_count(p, 0); + } while (++p, --i); + + set_page_refcounted(page); + set_pageblock_migratetype(page, MIGRATE_CMA); + __free_pages(page, pageblock_order); + totalram_pages += pageblock_nr_pages; +} +#endif /* * The order of subdivision here is critical for the IO subsystem. @@ -874,11 +893,17 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, * This array describes the order lists are fallen back to when * the free lists for the desirable migrate type are depleted */ -static int fallbacks[MIGRATE_TYPES][MIGRATE_TYPES-1] = { - [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, - [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, - [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, - [MIGRATE_RESERVE] = { MIGRATE_RESERVE, MIGRATE_RESERVE, MIGRATE_RESERVE }, /* Never used */ +static int fallbacks[MIGRATE_TYPES][4] = { + [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, + [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, +#ifdef CONFIG_CMA + [MIGRATE_MOVABLE] = { MIGRATE_CMA, MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, + [MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */ +#else + [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, +#endif + [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */ + [MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */ }; /* @@ -973,12 +998,12 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) /* Find the largest possible block of pages in the other list */ for (current_order = MAX_ORDER-1; current_order >= order; --current_order) { - for (i = 0; i < MIGRATE_TYPES - 1; i++) { + for (i = 0;; i++) { migratetype = fallbacks[start_migratetype][i]; /* MIGRATE_RESERVE handled later if necessary */ if (migratetype == MIGRATE_RESERVE) - continue; + break; area = &(zone->free_area[current_order]); if (list_empty(&area->free_list[migratetype])) @@ -993,11 +1018,18 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) * pages to the preferred allocation list. If falling * back for a reclaimable kernel allocation, be more * aggressive about taking ownership of free pages + * + * On the other hand, never change migration + * type of MIGRATE_CMA pageblocks nor move CMA + * pages on different free lists. We don't + * want unmovable pages to be allocated from + * MIGRATE_CMA areas. */ - if (unlikely(current_order >= (pageblock_order >> 1)) || - start_migratetype == MIGRATE_RECLAIMABLE || - page_group_by_mobility_disabled) { - unsigned long pages; + if (!is_migrate_cma(migratetype) && + (unlikely(current_order >= pageblock_order / 2) || + start_migratetype == MIGRATE_RECLAIMABLE || + page_group_by_mobility_disabled)) { + int pages; pages = move_freepages_block(zone, page, start_migratetype); @@ -1015,11 +1047,14 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) rmv_page_order(page); /* Take ownership for orders >= pageblock_order */ - if (current_order >= pageblock_order) + if (current_order >= pageblock_order && + !is_migrate_cma(migratetype)) change_pageblock_range(page, current_order, start_migratetype); - expand(zone, page, order, current_order, area, migratetype); + expand(zone, page, order, current_order, area, + is_migrate_cma(migratetype) + ? migratetype : start_migratetype); trace_mm_page_alloc_extfrag(page, order, current_order, start_migratetype, migratetype); @@ -1061,17 +1096,17 @@ retry_reserve: return page; } -/* +/* * Obtain a specified number of elements from the buddy allocator, all under * a single hold of the lock, for efficiency. Add them to the supplied list. * Returns the number of new pages which were placed at *list. */ -static int rmqueue_bulk(struct zone *zone, unsigned int order, +static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, int migratetype, int cold) { - int i; - + int mt = migratetype, i; + spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype); @@ -1091,7 +1126,12 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, list_add(&page->lru, list); else list_add_tail(&page->lru, list); - set_page_private(page, migratetype); + if (IS_ENABLED(CONFIG_CMA)) { + mt = get_pageblock_migratetype(page); + if (!is_migrate_cma(mt) && mt != MIGRATE_ISOLATE) + mt = migratetype; + } + set_page_private(page, mt); list = &page->lru; } __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); @@ -1371,8 +1411,12 @@ int split_free_page(struct page *page) if (order >= pageblock_order - 1) { struct page *endpage = page + (1 << order) - 1; - for (; page < endpage; page += pageblock_nr_pages) - set_pageblock_migratetype(page, MIGRATE_MOVABLE); + for (; page < endpage; page += pageblock_nr_pages) { + int mt = get_pageblock_migratetype(page); + if (mt != MIGRATE_ISOLATE && !is_migrate_cma(mt)) + set_pageblock_migratetype(page, + MIGRATE_MOVABLE); + } } return 1 << order; @@ -2086,16 +2130,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, } #endif /* CONFIG_COMPACTION */ -/* The really slow allocator path where we enter direct reclaim */ -static inline struct page * -__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) +/* Perform direct synchronous page reclaim */ +static int +__perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, + nodemask_t *nodemask) { - struct page *page = NULL; struct reclaim_state reclaim_state; - bool drained = false; + int progress; cond_resched(); @@ -2106,7 +2147,7 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, reclaim_state.reclaimed_slab = 0; current->reclaim_state = &reclaim_state; - *did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); + progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); current->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); @@ -2114,6 +2155,21 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, cond_resched(); + return progress; +} + +/* The really slow allocator path where we enter direct reclaim */ +static inline struct page * +__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, enum zone_type high_zoneidx, + nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, + int migratetype, unsigned long *did_some_progress) +{ + struct page *page = NULL; + bool drained = false; + + *did_some_progress = __perform_reclaim(gfp_mask, order, zonelist, + nodemask); if (unlikely(!(*did_some_progress))) return NULL; @@ -4301,7 +4357,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, init_waitqueue_head(&pgdat->kswapd_wait); pgdat->kswapd_max_order = 0; pgdat_page_cgroup_init(pgdat); - + for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; unsigned long size, realsize, memmap_pages; @@ -4976,14 +5032,7 @@ static void setup_per_zone_lowmem_reserve(void) calculate_totalreserve_pages(); } -/** - * setup_per_zone_wmarks - called when min_free_kbytes changes - * or when memory is hot-{added|removed} - * - * Ensures that the watermark[min,low,high] values for each zone are set - * correctly with respect to min_free_kbytes. - */ -void setup_per_zone_wmarks(void) +static void __setup_per_zone_wmarks(void) { unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10); unsigned long lowmem_pages = 0; @@ -5030,6 +5079,11 @@ void setup_per_zone_wmarks(void) zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2); zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); + + zone->watermark[WMARK_MIN] += cma_wmark_pages(zone); + zone->watermark[WMARK_LOW] += cma_wmark_pages(zone); + zone->watermark[WMARK_HIGH] += cma_wmark_pages(zone); + setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); } @@ -5038,6 +5092,20 @@ void setup_per_zone_wmarks(void) calculate_totalreserve_pages(); } +/** + * setup_per_zone_wmarks - called when min_free_kbytes changes + * or when memory is hot-{added|removed} + * + * Ensures that the watermark[min,low,high] values for each zone are set + * correctly with respect to min_free_kbytes. + */ +void setup_per_zone_wmarks(void) +{ + mutex_lock(&zonelists_mutex); + __setup_per_zone_wmarks(); + mutex_unlock(&zonelists_mutex); +} + /* * The inactive anon list should be small enough that the VM never has to * do too much work, but large enough that each inactive page has a chance @@ -5412,14 +5480,16 @@ static int __count_immobile_pages(struct zone *zone, struct page *page, int count) { unsigned long pfn, iter, found; + int mt; + /* * For avoiding noise data, lru_add_drain_all() should be called * If ZONE_MOVABLE, the zone never contains immobile pages */ if (zone_idx(zone) == ZONE_MOVABLE) return true; - - if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE) + mt = get_pageblock_migratetype(page); + if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt)) return true; pfn = page_to_pfn(page); @@ -5536,7 +5606,7 @@ out: return ret; } -void unset_migratetype_isolate(struct page *page) +void unset_migratetype_isolate(struct page *page, unsigned migratetype) { struct zone *zone; unsigned long flags; @@ -5544,12 +5614,259 @@ void unset_migratetype_isolate(struct page *page) spin_lock_irqsave(&zone->lock, flags); if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) goto out; - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - move_freepages_block(zone, page, MIGRATE_MOVABLE); + set_pageblock_migratetype(page, migratetype); + move_freepages_block(zone, page, migratetype); out: spin_unlock_irqrestore(&zone->lock, flags); } +#ifdef CONFIG_CMA + +static unsigned long pfn_max_align_down(unsigned long pfn) +{ + return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES, + pageblock_nr_pages) - 1); +} + +static unsigned long pfn_max_align_up(unsigned long pfn) +{ + return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES, + pageblock_nr_pages)); +} + +static struct page * +__alloc_contig_migrate_alloc(struct page *page, unsigned long private, + int **resultp) +{ + return alloc_page(GFP_HIGHUSER_MOVABLE); +} + +/* [start, end) must belong to a single zone. */ +static int __alloc_contig_migrate_range(unsigned long start, unsigned long end) +{ + /* This function is based on compact_zone() from compaction.c. */ + + unsigned long pfn = start; + unsigned int tries = 0; + int ret = 0; + + struct compact_control cc = { + .nr_migratepages = 0, + .order = -1, + .zone = page_zone(pfn_to_page(start)), + .sync = true, + }; + INIT_LIST_HEAD(&cc.migratepages); + + migrate_prep_local(); + + while (pfn < end || !list_empty(&cc.migratepages)) { + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + + if (list_empty(&cc.migratepages)) { + cc.nr_migratepages = 0; + pfn = isolate_migratepages_range(cc.zone, &cc, + pfn, end); + if (!pfn) { + ret = -EINTR; + break; + } + tries = 0; + } else if (++tries == 5) { + ret = ret < 0 ? ret : -EBUSY; + break; + } + + ret = migrate_pages(&cc.migratepages, + __alloc_contig_migrate_alloc, + 0, false, MIGRATE_SYNC); + } + + putback_lru_pages(&cc.migratepages); + return ret > 0 ? 0 : ret; +} + +/* + * Update zone's cma pages counter used for watermark level calculation. + */ +static inline void __update_cma_watermarks(struct zone *zone, int count) +{ + unsigned long flags; + spin_lock_irqsave(&zone->lock, flags); + zone->min_cma_pages += count; + spin_unlock_irqrestore(&zone->lock, flags); + setup_per_zone_wmarks(); +} + +/* + * Trigger memory pressure bump to reclaim some pages in order to be able to + * allocate 'count' pages in single page units. Does similar work as + *__alloc_pages_slowpath() function. + */ +static int __reclaim_pages(struct zone *zone, gfp_t gfp_mask, int count) +{ + enum zone_type high_zoneidx = gfp_zone(gfp_mask); + struct zonelist *zonelist = node_zonelist(0, gfp_mask); + int did_some_progress = 0; + int order = 1; + + /* + * Increase level of watermarks to force kswapd do his job + * to stabilise at new watermark level. + */ + __update_cma_watermarks(zone, count); + + /* Obey watermarks as if the page was being allocated */ + while (!zone_watermark_ok(zone, 0, low_wmark_pages(zone), 0, 0)) { + wake_all_kswapd(order, zonelist, high_zoneidx, zone_idx(zone)); + + did_some_progress = __perform_reclaim(gfp_mask, order, zonelist, + NULL); + if (!did_some_progress) { + /* Exhausted what can be done so it's blamo time */ + out_of_memory(zonelist, gfp_mask, order, NULL, false); + } + } + + /* Restore original watermark levels. */ + __update_cma_watermarks(zone, -count); + + return count; +} + +/** + * alloc_contig_range() -- tries to allocate given range of pages + * @start: start PFN to allocate + * @end: one-past-the-last PFN to allocate + * @migratetype: migratetype of the underlaying pageblocks (either + * #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks + * in range must have the same migratetype and it must + * be either of the two. + * + * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES + * aligned, however it's the caller's responsibility to guarantee that + * we are the only thread that changes migrate type of pageblocks the + * pages fall in. + * + * The PFN range must belong to a single zone. + * + * Returns zero on success or negative error code. On success all + * pages which PFN is in [start, end) are allocated for the caller and + * need to be freed with free_contig_range(). + */ +int alloc_contig_range(unsigned long start, unsigned long end, + unsigned migratetype) +{ + struct zone *zone = page_zone(pfn_to_page(start)); + unsigned long outer_start, outer_end; + int ret = 0, order; + + /* + * What we do here is we mark all pageblocks in range as + * MIGRATE_ISOLATE. Because pageblock and max order pages may + * have different sizes, and due to the way page allocator + * work, we align the range to biggest of the two pages so + * that page allocator won't try to merge buddies from + * different pageblocks and change MIGRATE_ISOLATE to some + * other migration type. + * + * Once the pageblocks are marked as MIGRATE_ISOLATE, we + * migrate the pages from an unaligned range (ie. pages that + * we are interested in). This will put all the pages in + * range back to page allocator as MIGRATE_ISOLATE. + * + * When this is done, we take the pages in range from page + * allocator removing them from the buddy system. This way + * page allocator will never consider using them. + * + * This lets us mark the pageblocks back as + * MIGRATE_CMA/MIGRATE_MOVABLE so that free pages in the + * aligned range but not in the unaligned, original range are + * put back to page allocator so that buddy can use them. + */ + + ret = start_isolate_page_range(pfn_max_align_down(start), + pfn_max_align_up(end), migratetype); + if (ret) + goto done; + + ret = __alloc_contig_migrate_range(start, end); + if (ret) + goto done; + + /* + * Pages from [start, end) are within a MAX_ORDER_NR_PAGES + * aligned blocks that are marked as MIGRATE_ISOLATE. What's + * more, all pages in [start, end) are free in page allocator. + * What we are going to do is to allocate all pages from + * [start, end) (that is remove them from page allocator). + * + * The only problem is that pages at the beginning and at the + * end of interesting range may be not aligned with pages that + * page allocator holds, ie. they can be part of higher order + * pages. Because of this, we reserve the bigger range and + * once this is done free the pages we are not interested in. + * + * We don't have to hold zone->lock here because the pages are + * isolated thus they won't get removed from buddy. + */ + + lru_add_drain_all(); + drain_all_pages(); + + order = 0; + outer_start = start; + while (!PageBuddy(pfn_to_page(outer_start))) { + if (++order >= MAX_ORDER) { + ret = -EBUSY; + goto done; + } + outer_start &= ~0UL << order; + } + + /* Make sure the range is really isolated. */ + if (test_pages_isolated(outer_start, end)) { + pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n", + outer_start, end); + ret = -EBUSY; + goto done; + } + + /* + * Reclaim enough pages to make sure that contiguous allocation + * will not starve the system. + */ + __reclaim_pages(zone, GFP_HIGHUSER_MOVABLE, end-start); + + /* Grab isolated pages from freelists. */ + outer_end = isolate_freepages_range(outer_start, end); + if (!outer_end) { + ret = -EBUSY; + goto done; + } + + /* Free head and tail (if any) */ + if (start != outer_start) + free_contig_range(outer_start, start - outer_start); + if (end != outer_end) + free_contig_range(end, outer_end - end); + +done: + undo_isolate_page_range(pfn_max_align_down(start), + pfn_max_align_up(end), migratetype); + return ret; +} + +void free_contig_range(unsigned long pfn, unsigned nr_pages) +{ + for (; nr_pages--; ++pfn) + __free_page(pfn_to_page(pfn)); +} +#endif + #ifdef CONFIG_MEMORY_HOTREMOVE /* * All pages in the range must be isolated before calling this. diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 4ae42bb4089..c9f04774f2b 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -24,6 +24,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * to be MIGRATE_ISOLATE. * @start_pfn: The lower PFN of the range to be isolated. * @end_pfn: The upper PFN of the range to be isolated. + * @migratetype: migrate type to set in error recovery. * * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in * the range will never be allocated. Any free pages and pages freed in the @@ -32,8 +33,8 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * start_pfn/end_pfn must be aligned to pageblock_order. * Returns 0 on success and -EBUSY if any part of range cannot be isolated. */ -int -start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) +int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype) { unsigned long pfn; unsigned long undo_pfn; @@ -56,7 +57,7 @@ undo: for (pfn = start_pfn; pfn < undo_pfn; pfn += pageblock_nr_pages) - unset_migratetype_isolate(pfn_to_page(pfn)); + unset_migratetype_isolate(pfn_to_page(pfn), migratetype); return -EBUSY; } @@ -64,8 +65,8 @@ undo: /* * Make isolated pages available again. */ -int -undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) +int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype) { unsigned long pfn; struct page *page; @@ -77,7 +78,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) page = __first_valid_page(pfn, pageblock_nr_pages); if (!page || get_pageblock_migratetype(page) != MIGRATE_ISOLATE) continue; - unset_migratetype_isolate(page); + unset_migratetype_isolate(page, migratetype); } return 0; } @@ -86,7 +87,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) * all pages in [start_pfn...end_pfn) must be in the same zone. * zone->lock must be held before call this. * - * Returns 1 if all pages in the range is isolated. + * Returns 1 if all pages in the range are isolated. */ static int __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn) diff --git a/mm/vmstat.c b/mm/vmstat.c index 7db1b9bab49..0dad31dc161 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -613,6 +613,9 @@ static char * const migratetype_names[MIGRATE_TYPES] = { "Reclaimable", "Movable", "Reserve", +#ifdef CONFIG_CMA + "CMA", +#endif "Isolate", }; |