diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 19:42:40 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 19:42:40 -0800 |
commit | 7c225c69f86c934e3be9be63ecde754e286838d7 (patch) | |
tree | ff2df419b0c4886b37407235f7d21215e4cf45e4 /arch | |
parent | 6363b3f3ac5be096d08c8c504128befa0c033529 (diff) | |
parent | 1b7176aea0a924ac59c6a283129d3e8eb00aa915 (diff) |
Merge branch 'akpm' (patches from Andrew)
Merge updates from Andrew Morton:
- a few misc bits
- ocfs2 updates
- almost all of MM
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (131 commits)
memory hotplug: fix comments when adding section
mm: make alloc_node_mem_map a void call if we don't have CONFIG_FLAT_NODE_MEM_MAP
mm: simplify nodemask printing
mm,oom_reaper: remove pointless kthread_run() error check
mm/page_ext.c: check if page_ext is not prepared
writeback: remove unused function parameter
mm: do not rely on preempt_count in print_vma_addr
mm, sparse: do not swamp log with huge vmemmap allocation failures
mm/hmm: remove redundant variable align_end
mm/list_lru.c: mark expected switch fall-through
mm/shmem.c: mark expected switch fall-through
mm/page_alloc.c: broken deferred calculation
mm: don't warn about allocations which stall for too long
fs: fuse: account fuse_inode slab memory as reclaimable
mm, page_alloc: fix potential false positive in __zone_watermark_ok
mm: mlock: remove lru_add_drain_all()
mm, sysctl: make NUMA stats configurable
shmem: convert shmem_init_inodecache() to void
Unify migrate_pages and move_pages access checks
mm, pagevec: rename pagevec drained field
...
Diffstat (limited to 'arch')
59 files changed, 308 insertions, 1600 deletions
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h index 0722ec6be692..6821f1249300 100644 --- a/arch/arm/include/asm/dma-iommu.h +++ b/arch/arm/include/asm/dma-iommu.h @@ -7,7 +7,6 @@ #include <linux/mm_types.h> #include <linux/scatterlist.h> #include <linux/dma-debug.h> -#include <linux/kmemcheck.h> #include <linux/kref.h> #define ARM_MAPPING_ERROR (~(dma_addr_t)0x0) diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index b2902a5cd780..2d7344f0e208 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -57,7 +57,7 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) static inline void clean_pte_table(pte_t *pte) { diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index c1c1a5c67da1..61e281cb29fb 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -141,7 +141,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd_base) pte = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free(mm, pte); - atomic_long_dec(&mm->nr_ptes); + mm_dec_nr_ptes(mm); no_pmd: pud_clear(pud); pmd_free(mm, pmd); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index ba6aab55d464..a93339f5178f 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -85,7 +85,7 @@ config ARM64 select HAVE_ARCH_BITREVERSE select HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_JUMP_LABEL - select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48) + select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48) select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index d25f4f137c2a..5ca6a573a701 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -26,7 +26,7 @@ #define check_pgt_cache() do { } while (0) -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #if CONFIG_PGTABLE_LEVELS > 2 diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 81f03959a4ab..acba49fb5aac 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -11,6 +11,7 @@ */ #define pr_fmt(fmt) "kasan: " fmt +#include <linux/bootmem.h> #include <linux/kasan.h> #include <linux/kernel.h> #include <linux/sched/task.h> @@ -35,77 +36,117 @@ static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); * with the physical address from __pa_symbol. */ -static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr, - unsigned long end) +static phys_addr_t __init kasan_alloc_zeroed_page(int node) { - pte_t *pte; - unsigned long next; + void *p = memblock_virt_alloc_try_nid(PAGE_SIZE, PAGE_SIZE, + __pa(MAX_DMA_ADDRESS), + MEMBLOCK_ALLOC_ACCESSIBLE, node); + return __pa(p); +} + +static pte_t *__init kasan_pte_offset(pmd_t *pmd, unsigned long addr, int node, + bool early) +{ + if (pmd_none(*pmd)) { + phys_addr_t pte_phys = early ? __pa_symbol(kasan_zero_pte) + : kasan_alloc_zeroed_page(node); + __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); + } + + return early ? pte_offset_kimg(pmd, addr) + : pte_offset_kernel(pmd, addr); +} - if (pmd_none(*pmd)) - __pmd_populate(pmd, __pa_symbol(kasan_zero_pte), PMD_TYPE_TABLE); +static pmd_t *__init kasan_pmd_offset(pud_t *pud, unsigned long addr, int node, + bool early) +{ + if (pud_none(*pud)) { + phys_addr_t pmd_phys = early ? __pa_symbol(kasan_zero_pmd) + : kasan_alloc_zeroed_page(node); + __pud_populate(pud, pmd_phys, PMD_TYPE_TABLE); + } + + return early ? pmd_offset_kimg(pud, addr) : pmd_offset(pud, addr); +} + +static pud_t *__init kasan_pud_offset(pgd_t *pgd, unsigned long addr, int node, + bool early) +{ + if (pgd_none(*pgd)) { + phys_addr_t pud_phys = early ? __pa_symbol(kasan_zero_pud) + : kasan_alloc_zeroed_page(node); + __pgd_populate(pgd, pud_phys, PMD_TYPE_TABLE); + } + + return early ? pud_offset_kimg(pgd, addr) : pud_offset(pgd, addr); +} + +static void __init kasan_pte_populate(pmd_t *pmd, unsigned long addr, + unsigned long end, int node, bool early) +{ + unsigned long next; + pte_t *pte = kasan_pte_offset(pmd, addr, node, early); - pte = pte_offset_kimg(pmd, addr); do { + phys_addr_t page_phys = early ? __pa_symbol(kasan_zero_page) + : kasan_alloc_zeroed_page(node); next = addr + PAGE_SIZE; - set_pte(pte, pfn_pte(sym_to_pfn(kasan_zero_page), - PAGE_KERNEL)); + set_pte(pte, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); } while (pte++, addr = next, addr != end && pte_none(*pte)); } -static void __init kasan_early_pmd_populate(pud_t *pud, - unsigned long addr, - unsigned long end) +static void __init kasan_pmd_populate(pud_t *pud, unsigned long addr, + unsigned long end, int node, bool early) { - pmd_t *pmd; unsigned long next; + pmd_t *pmd = kasan_pmd_offset(pud, addr, node, early); - if (pud_none(*pud)) - __pud_populate(pud, __pa_symbol(kasan_zero_pmd), PMD_TYPE_TABLE); - - pmd = pmd_offset_kimg(pud, addr); do { next = pmd_addr_end(addr, end); - kasan_early_pte_populate(pmd, addr, next); + kasan_pte_populate(pmd, addr, next, node, early); } while (pmd++, addr = next, addr != end && pmd_none(*pmd)); } -static void __init kasan_early_pud_populate(pgd_t *pgd, - unsigned long addr, - unsigned long end) +static void __init kasan_pud_populate(pgd_t *pgd, unsigned long addr, + unsigned long end, int node, bool early) { - pud_t *pud; unsigned long next; + pud_t *pud = kasan_pud_offset(pgd, addr, node, early); - if (pgd_none(*pgd)) - __pgd_populate(pgd, __pa_symbol(kasan_zero_pud), PUD_TYPE_TABLE); - - pud = pud_offset_kimg(pgd, addr); do { next = pud_addr_end(addr, end); - kasan_early_pmd_populate(pud, addr, next); + kasan_pmd_populate(pud, addr, next, node, early); } while (pud++, addr = next, addr != end && pud_none(*pud)); } -static void __init kasan_map_early_shadow(void) +static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, + int node, bool early) { - unsigned long addr = KASAN_SHADOW_START; - unsigned long end = KASAN_SHADOW_END; unsigned long next; pgd_t *pgd; pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - kasan_early_pud_populate(pgd, addr, next); + kasan_pud_populate(pgd, addr, next, node, early); } while (pgd++, addr = next, addr != end); } +/* The early shadow maps everything to a single page of zeroes */ asmlinkage void __init kasan_early_init(void) { BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_END - (1UL << 61)); BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE)); BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE)); - kasan_map_early_shadow(); + kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE, + true); +} + +/* Set up full kasan mappings, ensuring that the mapped pages are zeroed */ +static void __init kasan_map_populate(unsigned long start, unsigned long end, + int node) +{ + kasan_pgd_populate(start & PAGE_MASK, PAGE_ALIGN(end), node, false); } /* @@ -142,8 +183,8 @@ void __init kasan_init(void) struct memblock_region *reg; int i; - kimg_shadow_start = (u64)kasan_mem_to_shadow(_text); - kimg_shadow_end = (u64)kasan_mem_to_shadow(_end); + kimg_shadow_start = (u64)kasan_mem_to_shadow(_text) & PAGE_MASK; + kimg_shadow_end = PAGE_ALIGN((u64)kasan_mem_to_shadow(_end)); mod_shadow_start = (u64)kasan_mem_to_shadow((void *)MODULES_VADDR); mod_shadow_end = (u64)kasan_mem_to_shadow((void *)MODULES_END); @@ -161,19 +202,8 @@ void __init kasan_init(void) clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); - vmemmap_populate(kimg_shadow_start, kimg_shadow_end, - pfn_to_nid(virt_to_pfn(lm_alias(_text)))); - - /* - * vmemmap_populate() has populated the shadow region that covers the - * kernel image with SWAPPER_BLOCK_SIZE mappings, so we have to round - * the start and end addresses to SWAPPER_BLOCK_SIZE as well, to prevent - * kasan_populate_zero_shadow() from replacing the page table entries - * (PMD or PTE) at the edges of the shadow region for the kernel - * image. - */ - kimg_shadow_start = round_down(kimg_shadow_start, SWAPPER_BLOCK_SIZE); - kimg_shadow_end = round_up(kimg_shadow_end, SWAPPER_BLOCK_SIZE); + kasan_map_populate(kimg_shadow_start, kimg_shadow_end, + pfn_to_nid(virt_to_pfn(lm_alias(_text)))); kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, (void *)mod_shadow_start); @@ -191,9 +221,9 @@ void __init kasan_init(void) if (start >= end) break; - vmemmap_populate((unsigned long)kasan_mem_to_shadow(start), - (unsigned long)kasan_mem_to_shadow(end), - pfn_to_nid(virt_to_pfn(start))); + kasan_map_populate((unsigned long)kasan_mem_to_shadow(start), + (unsigned long)kasan_mem_to_shadow(end), + pfn_to_nid(virt_to_pfn(start))); } /* diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c index 328f0a292316..cf464100e838 100644 --- a/arch/frv/mm/init.c +++ b/arch/frv/mm/init.c @@ -42,21 +42,9 @@ #undef DEBUG /* - * BAD_PAGE is the page that is used for page faults when linux - * is out-of-memory. Older versions of linux just did a - * do_exit(), but using this instead means there is less risk - * for a process dying in kernel mode, possibly leaving a inode - * unused etc.. - * - * BAD_PAGETABLE is the accompanying page-table: it is initialized - * to point to BAD_PAGE entries. - * * ZERO_PAGE is a special page that is used for zero-initialized * data and COW. */ -static unsigned long empty_bad_page_table; -static unsigned long empty_bad_page; - unsigned long empty_zero_page; EXPORT_SYMBOL(empty_zero_page); @@ -72,8 +60,6 @@ void __init paging_init(void) unsigned long zones_size[MAX_NR_ZONES] = {0, }; /* allocate some pages for kernel housekeeping tasks */ - empty_bad_page_table = (unsigned long) alloc_bootmem_pages(PAGE_SIZE); - empty_bad_page = (unsigned long) alloc_bootmem_pages(PAGE_SIZE); empty_zero_page = (unsigned long) alloc_bootmem_pages(PAGE_SIZE); memset((void *) empty_zero_page, 0, PAGE_SIZE); diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c index eeead51bed2d..015287ac8ce8 100644 --- a/arch/h8300/mm/init.c +++ b/arch/h8300/mm/init.c @@ -40,20 +40,9 @@ #include <asm/sections.h> /* - * BAD_PAGE is the page that is used for page faults when linux - * is out-of-memory. Older versions of linux just did a - * do_exit(), but using this instead means there is less risk - * for a process dying in kernel mode, possibly leaving a inode - * unused etc.. - * - * BAD_PAGETABLE is the accompanying page-table: it is initialized - * to point to BAD_PAGE entries. - * * ZERO_PAGE is a special page that is used for zero-initialized * data and COW. */ -static unsigned long empty_bad_page_table; -static unsigned long empty_bad_page; unsigned long empty_zero_page; /* @@ -78,8 +67,6 @@ void __init paging_init(void) * Initialize the bad page table and bad page to point * to a couple of allocated pages. */ - empty_bad_page_table = (unsigned long)alloc_bootmem_pages(PAGE_SIZE); - empty_bad_page = (unsigned long)alloc_bootmem_pages(PAGE_SIZE); empty_zero_page = (unsigned long)alloc_bootmem_pages(PAGE_SIZE); memset((void *)empty_zero_page, 0, PAGE_SIZE); diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig index 0d9446c37ae8..498398d915c1 100644 --- a/arch/m32r/Kconfig +++ b/arch/m32r/Kconfig @@ -196,8 +196,8 @@ config TIMER_DIVIDE default "128" config CPU_BIG_ENDIAN - bool "Generate big endian code" - default n + bool + default !CPU_LITTLE_ENDIAN config CPU_LITTLE_ENDIAN bool "Generate little endian code" diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 67fe6dc5211c..0036ea0c7173 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -31,12 +31,7 @@ * tables. Each page table is also a single 4K page, giving 512 (== * PTRS_PER_PTE) 8 byte ptes. Each pud entry is initialized to point to * invalid_pmd_table, each pmd entry is initialized to point to - * invalid_pte_table, each pte is initialized to 0. When memory is low, - * and a pmd table or a page table allocation fails, empty_bad_pmd_table - * and empty_bad_page_table is returned back to higher layer code, so - * that the failure is recognized later on. Linux does not seem to - * handle these failures very well though. The empty_bad_page_table has - * invalid pte entries in it, to force page faults. + * invalid_pte_table, each pte is initialized to 0. * * Kernel mappings: kernel mappings are held in the swapper_pg_table. * The layout is identical to userspace except it's indexed with the @@ -175,7 +170,6 @@ printk("%s:%d: bad pgd %016lx.\n", __FILE__, __LINE__, pgd_val(e)) extern pte_t invalid_pte_table[PTRS_PER_PTE]; -extern pte_t empty_bad_page_table[PTRS_PER_PTE]; #ifndef __PAGETABLE_PUD_FOLDED /* diff --git a/arch/mn10300/kernel/head.S b/arch/mn10300/kernel/head.S index 73e00fc78072..0b15f759e0d2 100644 --- a/arch/mn10300/kernel/head.S +++ b/arch/mn10300/kernel/head.S @@ -434,14 +434,6 @@ ENTRY(empty_zero_page) .space PAGE_SIZE .balign PAGE_SIZE -ENTRY(empty_bad_page) - .space PAGE_SIZE - - .balign PAGE_SIZE -ENTRY(empty_bad_pte_table) - .space PAGE_SIZE - - .balign PAGE_SIZE ENTRY(large_page_table) .space PAGE_SIZE diff --git a/arch/openrisc/include/asm/dma-mapping.h b/arch/openrisc/include/asm/dma-mapping.h index f41bd3cb76d9..e212a1f0b6d2 100644 --- a/arch/openrisc/include/asm/dma-mapping.h +++ b/arch/openrisc/include/asm/dma-mapping.h @@ -23,7 +23,6 @@ */ #include <linux/dma-debug.h> -#include <linux/kmemcheck.h> #include <linux/dma-mapping.h> extern const struct dma_map_ops or1k_dma_map_ops; diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h index a14203c005f1..e11f03007b57 100644 --- a/arch/powerpc/include/asm/pgalloc.h +++ b/arch/powerpc/include/asm/pgalloc.h @@ -18,7 +18,7 @@ static inline gfp_t pgtable_gfp_flags(struct mm_struct *mm, gfp_t gfp) } #endif /* MODULE */ -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) #ifdef CONFIG_PPC_BOOK3S #include <asm/book3s/pgalloc.h> diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 1571a498a33f..a9b9083c5e49 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -433,6 +433,7 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, pud = pud_offset(pgd, start); pgd_clear(pgd); pud_free_tlb(tlb, pud, start); + mm_dec_nr_puds(tlb->mm); } /* diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 05e15386d4cb..a7e998158f37 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -200,7 +200,7 @@ static void destroy_pagetable_page(struct mm_struct *mm) /* We allow PTE_FRAG_NR fragments from a PTE page */ if (page_ref_sub_and_test(page, PTE_FRAG_NR - count)) { pgtable_page_dtor(page); - free_hot_cold_page(page, 0); + free_unref_page(page); } } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index ac0717a90ca6..1ec3aee43624 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -404,7 +404,7 @@ void pte_fragment_free(unsigned long *table, int kernel) if (put_page_testzero(page)) { if (!kernel) pgtable_page_dtor(page); - free_hot_cold_page(page, 0); + free_unref_page(page); } } diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 43607bb12cc2..cf4c1cb17dcd 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -44,6 +44,8 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.asce_limit = STACK_TOP_MAX; mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_REGION3; + /* pgd_alloc() did not account this pud */ + mm_inc_nr_puds(mm); break; case -PAGE_SIZE: /* forked 5-level task, set new asce with new_mm->pgd */ @@ -59,7 +61,7 @@ static inline int init_new_context(struct task_struct *tsk, /* forked 2-level compat task, set new asce with new mm->pgd */ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; - /* pgd_alloc() did not increase mm->nr_pmds */ + /* pgd_alloc() did not account this pmd */ mm_inc_nr_pmds(mm); } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); diff --git a/arch/sh/kernel/dwarf.c b/arch/sh/kernel/dwarf.c index e1d751ae2498..1a2526676a87 100644 --- a/arch/sh/kernel/dwarf.c +++ b/arch/sh/kernel/dwarf.c @@ -1172,11 +1172,11 @@ static int __init dwarf_unwinder_init(void) dwarf_frame_cachep = kmem_cache_create("dwarf_frames", sizeof(struct dwarf_frame), 0, - SLAB_PANIC | SLAB_HWCACHE_ALIGN | SLAB_NOTRACK, NULL); + SLAB_PANIC | SLAB_HWCACHE_ALIGN, NULL); dwarf_reg_cachep = kmem_cache_create("dwarf_regs", sizeof(struct dwarf_reg), 0, - SLAB_PANIC | SLAB_HWCACHE_ALIGN | SLAB_NOTRACK, NULL); + SLAB_PANIC | SLAB_HWCACHE |